JP4736613B2 - Process management device, process management program, recording medium recording process management program, and process management method - Google Patents

Description

  The present invention relates to a process management apparatus, a process management method, a process management program, and a recording medium that records the program.

  In a factory production line, process improvement processing is required to improve the yield. As the process improvement process, first, a process that causes a defect of a manufactured product is specified, and adjustment or cleaning of the device is performed so as to remove the cause.

  However, in a manufacturing process composed of a plurality of processes, various factors such as a defect in a part of the manufacturing apparatus, a problem in setting the manufacturing apparatus, and a problem in the conveyance path can be considered as candidates for the cause of failure. For example, a circuit board surface mounting system process is divided into a printing process, a mounting process, and a reflow process. In the printing process, solder paste is applied on the substrate, and in the mounting process, components are installed on the substrate. In the final reflow process, the solder is melted by applying heat to bond the components. In such a surface mounting system, when a bridging failure occurs, there are many possible causes of bridging failure such as mask misalignment and lower mold contamination, but one or more of these are fundamental factors.

  When a phenomenon that causes a defect appears, not only does a symptom of a defect appear in a manufactured product, but it also has some influence on the operation history of the manufacturing apparatus and the inspection history of the inspection apparatus. The data regarding the symptoms of these defective products, and the data regarding the operation history of the manufacturing apparatus and the inspection history of the inspection apparatus become enormous, and it is difficult to analyze the occurrence of defects.

  Here, production managers with abundant experience in production management know empirically the relationship between the effects of defective factors on defective products, manufacturing equipment, and inspection equipment, and how to interpret the effects. It is possible to improve the process. However, inexperienced production managers must examine the factors one by one to identify the factors, and spend a lot of time improving the process.

  Therefore, there is a demand for a technique capable of realizing the estimation of the cause of abnormality with high accuracy and high efficiency, regardless of the skill level of the production manager in the production site. As such a technique, Patent Document 1 shown below proposes a method for obtaining information from an inspection machine provided in each process (printing process-mounting process-reflow process) and performing inference by that. .

  However, in the surface mounting system, not all information necessary for factor estimation can be acquired from the inspection machine. For example, the solder area taken from the front of the substrate can be collected by using image processing technology, but information such as the warpage of the substrate needs to be confirmed by a human from the side of the substrate. Here, it is conceivable to provide a configuration for detecting the warpage of the substrate, but it is not preferable to increase the cost of the inspection machine more than necessary. Therefore, it is preferable to input information from a human in addition to inspection result data from the inspection machine. That is, in order to perform factor estimation, it is necessary to perform cooperative inference between machines and people.

When factor estimation is performed by inputting information from a human, how to reduce the number of questions and perform reasoning accurately becomes a problem. For example, Patent Document 2 shown below proposes a method of giving an evaluation value based on the occurrence frequency in advance as a method of determining the question order.
JP-A-6-196900 (published July 15, 1994 (July 15, 1994)) Japanese Laid-Open Patent Publication No. Hei 6-0103073 (published on April 15, 1994 (1994.4.15)) Japanese Unexamined Patent Publication No. 2004-126641 (Published April 22, 2004 (2004.4.22)) JP 2002-297387 A (published on October 11, 2002 (2002.10.11)) JP 2004-117229 A (published on April 15, 2004 (2004.4.15)) JP 2004-198436 A (released July 15, 2004 (2004.7.15))

  In the method disclosed in the above-mentioned Patent Document 2, a question is generated from a frequently occurring question. In this case, a question with a low occurrence frequency is asked later, but in reality, a question with a low occurrence frequency may be important. That is, depending on the situation, there is a problem that it may take a lot of time to estimate the failure factor.

  The present invention has been made in view of the above problems, and its purpose is to identify a failure factor in any situation when a failure factor is estimated using an answer from a user. Another object of the present invention is to provide a process management apparatus, a process management program, a recording medium on which a process management program is recorded, and a process management method that can keep the number of questions required for the process low.

In order to solve the above-described problem, the process management apparatus according to the present invention provides one or more defect factor candidates for each of a plurality of defect results that may occur in a processing system that processes an object. An estimated knowledge recording unit that records factor estimated knowledge information indicating the diagnosis path of factor estimation from each defect result to each defect factor corresponding to the defect result as knowledge of the tree structure by conditional branching; and the estimated knowledge Inference processing means for performing factor estimation processing based on the factor estimation knowledge information recorded in the recording unit, and corresponding to the conditions included in the factor estimation knowledge information in the process of performing the factor estimation processing by the inference processing means Input control means for obtaining an answer from the user to the question to be asked, and a degree satisfying the condition based on the answer obtained by the input control means A degree-of-fit calculation means for calculating the degree of goodness to be shown, and a diagnosis path narrowing means for setting a specific diagnostic path and a failure factor out of the factor estimation target. The diagnostic path and the failure factor including the condition when the diagnostic path and the failure factor are less than or equal to a predetermined threshold when the fitness calculated by the fitness level calculating unit or the fitness calculated by the fitness level calculating unit among degrees, Ri the diagnostic path and good factors der when values representing the set of fitness in a particular diagnostic paths is equal to or less than a predetermined threshold value, the goodness of fit, 0 or 1 following numbers in conjunction represented, is characterized that you have become the answer is acceptable for the condition such as the goodness of fit is larger than 0 and smaller than 1.

In addition, the process management method according to the present invention associates one or more defect factor candidates with each of a plurality of defect results that may occur in a processing system that processes an object, and each defect result. Recorded in the estimated knowledge recording step for recording factor estimated knowledge information indicating the diagnosis path of the factor estimation leading to each failure factor corresponding to the failure result as knowledge of the tree structure by conditional branching, and the estimated knowledge recording step An inference processing step for performing factor estimation processing based on the factor estimation knowledge information, and a response from a user to a question corresponding to a condition included in the factor estimation knowledge information in the process of performing the factor estimation processing in the inference processing step Based on the input control step for acquiring and the answer acquired in the input control step. A fitness calculation step for calculating a fitness indicating the degree of error, and a diagnostic path narrowing step for setting a specific diagnostic path and a failure factor as excluded from the factor estimation target. The diagnostic path and the failure factor including the condition when the specific diagnostic path and the failure factor to be set are less than or equal to a predetermined threshold when the fitness calculated in the fitness calculation step or the fitness calculation step of relevance calculated in, Ri the diagnostic path and good factors der when values representing the set of fitness in a particular diagnostic paths is equal to or less than a predetermined threshold value, the goodness of fit, 0 The above answer to the condition that the degree of conformity is a value greater than 0 and less than 1 is allowed, as expressed by a number of 1 or less. Now it is characterized by a Rukoto.

  In the above configuration or method, the factor estimation process is performed based on the factor estimation knowledge information indicating the diagnosis path of factor estimation from each failure result to each failure factor corresponding to the failure result as knowledge of the tree structure by conditional branching. Is called. This factor estimation process proceeds when a question corresponding to the condition included in the factor estimation knowledge information is presented to the user and the user answers it. In this process, the condition is satisfied. A goodness of fit indicating the degree is calculated. Then, the diagnostic path and the failure factor including the condition where the fitness is less than or equal to a predetermined threshold, or the value representative of the set of fitness included in the specific diagnostic path is less than or equal to the predetermined threshold. The diagnosis pass and the failure factor are set as factors not to be estimated.

  Therefore, since the number of questions presented to the user can be reduced, the time and labor required for the factor estimation process can be reduced. In addition, when the degree of conformity is less than or equal to a threshold value, or when a value representing a set of conformity levels is less than or equal to a predetermined threshold value, it is unlikely that the failure factor is a true failure factor of the corresponding failure result. By using the goodness of fit as a criterion for narrowing down the diagnostic path, it is possible to accurately reduce the diagnostic path and reduce the number of questions regardless of the occurrence of defects. It becomes. That is, according to the above configuration or method, it is possible to reach a true defect factor in a shorter time under any circumstances.

  In the process management apparatus according to the present invention, in the above configuration, the display control means for displaying factor estimation knowledge information including the diagnosis path and the failure factor set as the factor estimation target by the diagnosis path narrowing means on the display unit It is good also as a structure further equipped with.

  According to said structure, the factor estimation knowledge information which consists of the diagnostic path narrowed down by the diagnostic path narrowing means and a defect factor will be displayed on a display part. Therefore, by presenting factor estimation knowledge information that is narrowed down in the process of factor estimation processing to the user, the user is made aware of the process of factor estimation processing and future prospects, and the validity of factor estimation results. Is possible.

  In the process management apparatus according to the present invention, in the above configuration, when the display control means has a number of failure factors that are not set to be subject to factor estimation by the diagnostic path narrowing means is equal to or less than a predetermined threshold value. In addition, the factor estimation knowledge information may be displayed on the display unit.

  According to the above configuration, since the factor estimation knowledge information is displayed on the display unit in a state where the number of failure factors remaining as failure factor candidates is equal to or less than a predetermined threshold, It is possible to present factor estimation knowledge information in a state where defect factors are narrowed down. As a result, it is possible to prevent a situation in which the user is confused by presenting more information than necessary.

  Further, in the process management apparatus according to the present invention, in the above configuration, the display control unit has obtained answers to all conditions included in the diagnostic path set as the factor estimation target by the diagnostic path narrowing unit. However, when the number of failure factors that can be narrowed down by the answer does not change, the factor estimation knowledge information may be displayed on the display unit.

  According to the above configuration, since the condition and the failure factor correspond one-to-one, it is possible to present the factor estimation knowledge information in a state where the failure factor is narrowed down to some extent to the user. . As a result, it is possible to prevent a situation in which the user is confused by presenting more information than necessary.

  The process management apparatus according to the present invention, in the above configuration, has an inspection result input means for receiving inspection result data from an inspection apparatus for inspecting a processing process in the processing system, and an inspection result received by the inspection result input means. A test result recording unit for recording data, and the input control unit responds to a question corresponding to a condition included in the factor estimation knowledge information in a process in which the factor estimation processing is performed by the reasoning processing unit. Thus, it may be configured to switch between a case where an answer is acquired from a user and a case where an answer is acquired from the inspection result data.

  According to the above configuration, the inspection result data as a result of the inspection performed by the inspection apparatus is received by the inspection result input unit, and the received inspection result data is recorded in the inspection result recording unit. Further, in the process of performing the factor estimation process, switching between a case where an answer from a user is acquired and a case where an answer is acquired based on test result data is performed according to the contents of the question. Accordingly, conditions that can be determined based on the inspection result data can be determined based on the inspection result data, and conditions that cannot be determined based on the inspection result data can be determined based on the answer from the user. As a result, it is possible to perform efficient and accurate inference by cooperating the judgment by the machine and the judgment by the human to perform the factor estimation.

  Further, in the process management apparatus according to the present invention, in the configuration described above, the display control unit displays information on the fitness calculated by the fitness calculation unit in accordance with a condition corresponding to the fitness. It is good also as a structure displayed on these.

  According to said structure, the information regarding a fitness level is displayed on a display part corresponding to conditions. Therefore, more detailed information regarding the process of the factor estimation process can be presented to the user, and the user can easily determine the factor estimation.

  Further, the process management apparatus according to the present invention, in the above-described configuration, relates to a failure factor set as a factor estimation target by the diagnostic path narrowing means, and a set of suitability levels for the conditions included in the diagnostic path leading to the failure factor It is also possible to further comprise a certainty factor calculating means for calculating a value representing the certainty factor as the certainty factor, and the display control means displays information on the certainty factor on the display unit in association with the defect factor.

  According to said structure, the information regarding a certainty factor is displayed with respect to the defect factor candidate. The certainty factor is a value indicating a high possibility that the failure factor is a failure factor of a failure result as an estimation target, so that each failure factor candidate is a true failure factor for the user. It is possible to present an index for determining whether or not. Note that examples of values representative of the set of fitness levels include a minimum value and an average value.

  Further, in the above configuration, the process management apparatus according to the present invention is effective among the conditions included in the diagnostic path leading to the failure factor with respect to the failure factor set as the factor estimation target by the diagnostic path narrowing means. Further comprising a reliability calculation means for calculating a value indicating a ratio of the answers obtained as reliability, and the display control means displays information on the reliability on the display unit in association with the defect factor. Also good.

According to said structure, the information regarding reliability is displayed with respect to the defect factor candidate. Since the reliability is a value indicating the reliability of the certainty factor calculated with respect to the failure factor, the user can determine whether or not each failure factor candidate is a true failure factor. It is possible to present an index.

  Further, in the process management apparatus according to the present invention, in the configuration described above, the input control unit accepts a selection input of a failure factor set as a factor estimation target, which is displayed on the display unit, and the inference process described above The means may be configured to verify the condition included in the diagnostic path corresponding to the failure factor designated by the selection input.

  According to the above configuration, when a specific failure factor is selected from the failure factors set as the factor estimation target, the factor estimation process related to the failure factor is performed. Therefore, it is possible for the user to first ask a question about a failure factor that is highly likely to be a true failure factor from among the displayed failure factor candidates, thereby efficiently performing the factor estimation process. Can be done.

  Further, in the process management apparatus according to the present invention, in the above configuration, the input control unit receives a deletion instruction input of a failure factor set as a factor estimation target and displayed on the display unit, and the diagnosis The path narrowing means may be configured to set the diagnostic path corresponding to the failure factor designated by the deletion instruction input and the failure factor as outside the factor estimation target.

  According to the above configuration, when a specific failure factor is instructed to be deleted from the failure factors set as the factor estimation target, the diagnostic path corresponding to the failure factor and the failure factor are excluded from the factor estimation target. Will be set as Therefore, it is possible for the user to exclude a failure factor that is unlikely to be a true failure factor from the failure factor candidates, and the factor estimation process can be performed efficiently. It becomes.

  The process management apparatus may be realized by a computer, and in this case, a process management program for causing the process management apparatus to be realized by a computer by operating the computer as each of the means, and recording the program Computer-readable recording media are also within the scope of the present invention.

As described above, the process management apparatus according to the present invention associates one or more defect factor candidates with each of a plurality of defect results that may occur in a processing system that processes an object, An estimated knowledge recording unit for recording factor estimation knowledge information indicating a diagnosis path of factor estimation from each failure result to each failure factor corresponding to the failure result as knowledge of a tree structure by conditional branching, and the estimated knowledge recording unit Inference processing means for performing factor estimation processing based on the recorded factor estimation knowledge information, and in response to a question corresponding to a condition included in the factor estimation knowledge information in the process of performing factor estimation processing by the inference processing means An input control means for obtaining an answer from the user, and a fitness indicating the degree of satisfying the condition based on the answer obtained by the input control means A fitness calculation means for calculating, and a diagnosis path limitation means that sets a specific diagnostic path and failure factor as the factor estimating excluded, specific diagnostic path and failure the diagnostic path limitation means is configured as outside factors estimation target Among the diagnostic path and the failure factor including the condition when the factor calculated by the fitness calculator is less than or equal to a predetermined threshold, or the factor calculated by the fitness calculator, This is a configuration that is a diagnostic path and a failure factor when a value representative of a set of fitness levels included in a specific diagnostic path is equal to or less than a predetermined threshold. As a result, it is possible to reach the true failure factor in a shorter time in any situation.

  An embodiment of the present invention is described below with reference to the drawings. In the present embodiment, a process management system applied to a production system having a printed circuit board production line will be described. However, the present invention is not limited to a printed circuit board production system. It can be applied to general management. In addition, the treatment process of the object is, for example, an industrial product production process, an industrial product, an agricultural product, or a raw material inspection process, a waste object (for example, factory waste, factory wastewater, waste gas, garbage, etc.) It means a processing process, an inspection process for waste objects, an inspection process for equipment, a recycling process, and the like.

(Production system configuration)
First, a printed circuit board production system (processing system) 1 to which a process management system according to this embodiment is applied will be described with reference to FIG. The production line in the production system 1 includes each process (printing process, mounting process, reflow process, etc.) for manufacturing a printed circuit board. In the example shown in the figure, the production system 1 includes a printing device 11 that performs a solder printing process of pasting solder on a substrate, a mounting device 12 that performs a component mounting process of mounting electronic components on the substrate, and an electronic component on the substrate. A soldering device 13 for performing a reflow process for soldering and a process management device 10 for managing the production system 1. The printing device 11, the mounting device 12, and the soldering device 13 are arranged in this order from upstream to downstream in the product flow of the production system 1.

  Further, a printing inspection device 14 a is disposed in the vicinity of the printing device 11, a mounting inspection device 14 b is disposed in the vicinity of the mounting device 12, and a soldering inspection device 14 c is disposed in the vicinity of the soldering device 13. . The print inspection device 14 a is for inspecting the quality of the substrate processed by the printing device 11. The mounting inspection device 14b inspects the substrate processed by the mounting device 12. The soldering inspection device 14 c is for inspecting the substrate processed by the soldering device 13. Hereinafter, when it is not necessary to distinguish the print inspection device 14a, the mounting inspection device 14b, and the soldering inspection device 14c, they are simply referred to as the inspection device 14.

  In addition, the process management apparatus 10 performs overall management of the entire production system 1 and performs factor estimation processing and analysis processing described later. The process management apparatus 10 receives various information inputs and instruction inputs from a user as a production manager and performs various processes.

  The process management device 10, the printing device 11, the mounting device 12, the soldering device 13, the printing inspection device 14a, the mounting inspection device 14b, and the soldering inspection device 14c form a communication network by being connected to each other via a communication line. ing. Note that the communication network may have any form as long as the apparatuses can communicate with each other. For example, a form in which a LAN (Local Area Network) is formed is assumed.

  In addition to the process management device 10, a terminal device on which a user performs operation input is provided separately in a state connected to the communication network, and data input to the process management device 10 and various screen displays are performed by this terminal device. It is good.

  In the above example, the inspection device 14 is provided corresponding to each of the printing device 11, the mounting device 12, and the soldering device 13. However, in the production system 1, at least one inspection device 14 is provided. What is necessary is just to be provided. For example, if at least the soldering inspection device 14c is provided, it is possible to detect defects occurring in the final manufacturing result.

(Configuration of process control device)
Next, the configuration of the process management apparatus 10 will be described below with reference to FIG. As shown in the figure, the process management apparatus 10 includes a control unit 30, an inspection result input unit (inspection result input means) 40, an input unit 21, a display unit 22, an estimated knowledge recording unit 23, a question data recording unit 24, an inference. A process temporary storage unit 25 and a process state database 26 are provided.

  The input unit 21 receives an instruction input from the user, an information input, and the like, and includes, for example, a key input unit such as a keyboard and buttons, a pointing device such as a mouse, and the like. The display unit 22 displays various processing contents in the process management apparatus 10, and is configured by a display device such as a liquid crystal display device or a CRT (Cathode Ray Tube).

  The inspection result input unit 40 receives data related to the inspection result of the manufacturing process in the production system 1. The print result input unit 41, the mounting result input unit 42, the soldering result input unit 43, and the manufacturing apparatus history input unit 44. It has. The print result input unit 41 receives the inspection result from the print inspection apparatus 14a. The mounting result input unit 42 receives the inspection result from the mounting inspection device 14b. The soldering result input unit 43 receives an inspection result from the soldering inspection device 14c. The manufacturing apparatus history input unit 44 receives information regarding the manufacturing history from the printing apparatus 11, the mounting apparatus 12, and the soldering apparatus 13.

  The inspection result input unit 40 receives information on the inspection result from at least one of the printing device 11, the mounting device 12, the soldering device 13, the printing inspection device 14a, the mounting inspection device 14b, and the soldering inspection device 14c. It only has to be like this. For example, if only the inspection result data relating to the soldering result is received from the soldering inspection device 14c, the inspection result data relating to the defect occurring in the final manufacturing result can be acquired.

  The estimated knowledge recording unit 23 records factor estimated knowledge information. The factor estimation knowledge information is information for searching for a factor for each of a plurality of failure results, and is recorded as a causal network. Details of the causal network will be described later.

  The question data recording unit 24 records the question information presented to the user in performing factor estimation as a question database. Each question information included in this question database is linked to factor estimated knowledge information recorded in the estimated knowledge recording unit 23, and corresponds to each node of the causal network.

  The inference process temporary storage unit 25 stores inference process information obtained according to the progress of inference in the inference process performed in the inference unit 32.

  The process state database 26 is a database that records data (inspection result data) related to the inspection result of the manufacturing process in the production system 1 accepted by the inspection result input unit 40. That is, the process state database 26 is manufactured from the inspection result by the printing inspection device 14a, the inspection result by the mounting inspection device 14b, the inspection result by the soldering inspection device 14c, the printing device 11, the mounting device 12, and the soldering device 13. Information about the history is recorded.

  The estimated knowledge recording unit 23, the question data recording unit 24, and the process state database 26 are realized by a non-volatile recording medium such as a hard disk device. The inference process temporary storage unit 25 is realized by a work memory such as a RAM (Random Access Memory).

  The control unit 30 controls processing in the process management apparatus 10, and includes an input display control unit (input control unit / display control unit) 31, an inference unit 32, a knowledge conversion unit 33, a question generation unit 34, and a feature amount. A calculation unit 35 is provided.

  The knowledge conversion unit 33 reads the factor estimation knowledge information recorded in the estimation knowledge recording unit 23 and generates a production rule as inference knowledge. The production rule, which will be described in detail later, is information in a data format suitable for causing a computer to perform inference processing for factor estimation.

  In response to a request from the inference unit 32, the question generation unit 34 reads out question information corresponding to each process of the inference process from the question data recording unit 24, and generates a question. In response to a request from the inference unit 32, the feature amount calculation unit 35 reads the inspection result data recorded in the process state database 26, and calculates a required feature amount by performing statistical calculation or the like.

  The input display control unit 31 receives input information from the input unit 21 and performs display control on the display unit 22, and includes a question input / output control unit 51, a factor input / output control unit 52, and an inference process display. A control unit 53 is provided.

  The question input / output control unit 51 displays a question on the display unit 22 in response to an instruction from the inference unit 32, and performs a process of receiving an answer input to the question and transmitting it to the inference unit 32. The factor input / output control unit 52 displays on the display unit 22 candidate factors estimated in response to an instruction from the inference unit 32 and information on each factor, and accepts an instruction input for the displayed factor to generate an inference unit. The process of transmitting to 32 is performed. The inference process display control unit 53 performs a process of displaying the causal network in the inference process on the display unit 22 in accordance with an instruction from the inference unit 32.

  The inference unit 32 performs an inference process for estimating a factor, and includes an inference processing unit (inference processing unit) 61, a fitness calculation unit (a fitness calculation unit) 62, and a certainty factor calculation unit (a certainty factor calculation unit) 63. , A reliability calculation section (reliability calculation means) 64 and a diagnostic path narrowing section (diagnostic path narrowing means) 65 are provided.

  The inference processing unit 61 performs a process for comprehensively controlling the factor estimation process. When an answer to a question associated with a specific node of the causal network is obtained, the suitability degree calculating unit 62 conforms to the node connected next to the node according to the content of the answer. The process which calculates is performed. The certainty factor calculation unit 63 performs a process of calculating the certainty factor for each estimated factor based on the fitness obtained by the factor estimation process. The reliability calculation unit 64 performs a process of calculating reliability indicating how reliable the certainty factor is for each estimated factor. The diagnostic path narrowing unit 65 performs processing for narrowing down the diagnostic path of the causal network according to a predetermined condition. Details of the inference process, the fitness calculation process, the certainty calculation process, the reliability calculation process, and the diagnosis path narrowing process will be described later.

(Causal network)
Next, a causal network as factor estimation knowledge information recorded in the estimation knowledge recording unit 23 will be described. The causal network is information indicating the inference process from each failure result to the cause of the failure result (hereinafter referred to as failure factor) as knowledge of the tree structure. In the causal network, there are a plurality of nodes in the middle of a diagnostic path from a failure result to a failure factor. When a branch of a diagnostic path occurs at this node, a diagnostic path from a specific failure result to a plurality of failure factors is formed.

  Each node shows a specific phenomenon, and when there is a high possibility that the cause of the phenomenon corresponding to a certain node is a phenomenon corresponding to a downstream node in the diagnostic path of the node, these two nodes The goodness of fit between them will be high.

  FIG. 3 schematically illustrates an example of a causal network. In the drawing, d1 indicates a failure result, c1 to c4 indicate failure factors, and s1 to s5 indicate phenomena corresponding to nodes. In the example shown in the figure, for the d1 failure result, failure factors c1 to c4 are assumed as candidates, and the diagnostic path corresponding to each failure factor is configured by a chain of nodes s1 to s5. . In the case of this causal network, five diagnostic paths are included as shown in FIG.

  Here, for example, when the knowledge structure is such that the failure factors c1 to c4 are directly connected to the failure result of d1, the conditions for determining the degree of fitness for each failure factor are extremely complicated. On the other hand, in the case of the tree structure knowledge structure as described above, the conditions for determining the conformity of the phenomenon causing the failure result, the phenomenon causing each phenomenon, and the failure factor causing each phenomenon are as follows. If you look at it, it will be relatively simple. Therefore, it is possible to perform reasoning inference processing by verifying relatively simple conditions, and even a user with a low level of skill can appropriately narrow down the factors.

(Generation of production rules)
Next, a process of generating a production rule from the causal network diagnosis path by the knowledge conversion unit 33 will be described. As described above, the production rule is information in a data format suitable for causing a computer to perform inference processing for factor estimation. The knowledge conversion unit 33 reads out information on the target diagnostic path from the causal network information recorded in the estimated knowledge recording unit 23, and generates a production rule corresponding to the diagnostic path.

  A production rule includes information on conditions between nodes during a specific diagnosis path from failure results to failure factors, and failure factor information that is true when all of these conditions are met. is there. Therefore, it is possible to determine whether or not the corresponding failure factor is true by making a simple determination of whether or not all the conditions between the nodes are satisfied, and the information is suitable for computer processing. Yes.

  FIG. 5A shows an example of a diagnostic path. In the example shown in the figure, the diagnosis path is a path from the failure result of d1 to the failure factor of c1 through the nodes as phenomena of s1 to s3 in this order. In addition, information regarding conditions regarding f1 to f4 is set as diagnosis knowledge corresponding to the conditions between the nodes. That is, in order to estimate that the defective result of d1 is derived from the phenomenon of s1, it is necessary to satisfy the condition of f1 = large. Similarly, the condition for estimating from s1 to s2 is f2 = Large, the condition for estimation from s2 to s3 is f3 = large, and the condition for estimation from s3 to c1 is f4 = large.

  Based on the diagnostic path information as described above, the knowledge conversion unit 33 generates a production rule as shown in FIG. The production rule is information that the corresponding failure factor is true when the condition obtained by combining the conditions between all the nodes included in the diagnosis path from the failure result to the failure factor with AND is satisfied. The production rule shown in FIG. 5B shows information that c1 is true when all the conditions of f1 = large, f2 = large, f3 = large, and f4 = large are satisfied. .

  In addition, when multiple conditions combined with "and" are set as conditions between nodes, the production rule includes the multiple conditions combined with "and" and diagnoses from failure results to failure factors. When the condition obtained by combining the conditions between all the nodes included in the path with “and” is satisfied, the information indicates that the corresponding failure factor is true.

  In the example shown in FIG. 6A, the conditions for the estimation from s1 to s2 are f2 = large and f5 = large. As shown in FIG. 6B, the production rule in this case is that c1 is true when all the conditions of f1 = large, f2 = large, f5 = large, f3 = large, and f4 = large are satisfied. It becomes information that it is.

  Further, when a plurality of conditions combined with or are set as conditions between nodes, production rules corresponding to the respective conditions combined with or are generated. In other words, each production rule is included in the diagnosis path from the failure result to the failure cause, and is combined with all the conditions between the nodes other than the nodes set with multiple conditions combined with or. The information is that the corresponding failure factor is true when the condition obtained by combining any one of the conditions with AND is satisfied. In addition, production rules are generated as many as the number of conditions connected by or.

  In the example shown in FIG. 7A, the condition for estimation from s1 to s2 is f2 = large or f5 = large. In this case, as shown in FIG. 7B, a production rule that c1 is true when all the conditions of f1 = large, f2 = large, f3 = large, and f4 = large are satisfied, Two of the production rules that c1 is true when all the conditions of f1 = large, f5 = large, f3 = large, and f4 = large are satisfied are generated.

  If a supplementary path exists, a production rule is generated by combining and combining the conditions included in the supplementary path with the production rule corresponding to the diagnostic path leading to the same failure factor. The node of the diagnostic path defines an intermediate phenomenon for reaching the cause from the defect. However, there is knowledge that describes phenomena directly related to factors such as overall trends, not intermediate phenomena. This is described as a supplementary path.

  In the example shown in FIG. 8A, there is a diagnostic path from the phenomenon of s4 to the failure factor of c1 as a supplementary path, and this condition is f5 = large. In this case, as shown in FIG. 8B, when all the conditions of f1 = large, f2 = large, f3 = large, f4 = large, and f5 = large are satisfied, c1 is true. A rule is generated.

(Fitness calculation process)
Next, the fitness calculation processing by the fitness calculator 62 will be described. The degree of conformity indicates a degree that satisfies the conditions set between the nodes in the production rule. This degree of conformity is represented by a number from 0 to 1, and the higher the number, the higher the condition is satisfied.

  Here, when there are no two choices of whether the condition is completely satisfied or not completely satisfied, the degree of conformity is two, 1 or 0. On the other hand, in the present embodiment, by using fuzzy theory, an answer to a condition where the fitness is a value larger than 0 and smaller than 1 is allowed. Thereby, even when the answer to the condition is ambiguous, an inference result reflecting the ambiguous state can be obtained. Therefore, it is not necessary to force an ambiguous answer to an extreme answer, and it is possible to prevent improper inference. Further, since the numerical value of the fitness level indicates the degree of certainty of inference to the next node, the numerical value of the fitness level can be used as a material for determining the suitability of the inference.

  Specifically, first, a membership function is set for each language value that is a candidate for an answer to the corresponding condition. The fitness for each language value is calculated by referring to the membership function according to the language value input as an answer. More specifically, first, the fitness for the language value input as an answer is 1.0. Then, the fitness for a language value other than the language value input as an answer is determined by taking the min of the membership function corresponding to the language value and the membership function corresponding to the input language value, and calculating the max value thereof. It shall be obtained by calculation. Here, if there is no intersection between the membership function corresponding to the language value input as an answer and the membership function corresponding to the input language value, the fitness is set to 0.0.

  Information about the language value that is a candidate for the answer to each condition and each membership function is recorded in the estimated knowledge recording unit 23. Then, the fitness calculator 62 calculates the fitness by reading out the information recorded in the estimated knowledge recording unit 23. In addition, the fitness level calculation unit 62 records the calculated fitness level information in the inference process temporary storage unit 25 together with information on conditions corresponding to the fitness level.

  Here, as an example, the condition “is is large?” Is set, and three types of responses “large”, “mid”, and “small” are assumed as answers to this. In the following description, the degree of matching calculation process will be described. FIG. 9A and FIG. 9B show an example of a membership function for three types of answers, “large”, “mid”, and “small”. In the example shown in FIG. 9A, if the answer is “large”, the fitness as large is 1.0, the fitness as mid is 0.5, and the fitness as small is 0. .0. In the example shown in FIG. 9B, if the answer is “large”, the fitness as large is 1.0, the fitness as mid is 0.7, and the fitness as small. Becomes 0.3.

(Confidence calculation process)
Next, the calculation process of the certainty factor by the certainty factor calculation part 63 is demonstrated. The certainty factor is a value provided corresponding to each failure factor, and is a value indicating a high possibility that the failure factor is a failure factor of a failure result as an estimation target.

  The certainty factor is obtained as follows. First, a production rule corresponding to a diagnostic path from a failure result as an estimation target to a corresponding failure factor is extracted. Then, among the conditions included in the extracted production rule, the condition for which the fitness is calculated is extracted, and the fitness with the smallest value among these is set as the certainty. When there are multiple production rules corresponding to the diagnostic path from the failure result as the estimation target to the corresponding failure factor, the certainty factor is calculated for each production rule, and among the calculated certainty factors, The largest certainty factor is set as the certainty factor for the corresponding failure factor.

  Note that the certainty factor calculation unit 63 acquires the necessary goodness-of-fit by reading out the goodness-of-fit information recorded in the inference process temporary storage unit 25 and the condition information corresponding to the goodness-of-fit, Calculate the degree. The calculated certainty factor is recorded in the inference process temporary storage unit 25 together with information on the corresponding failure factor.

For example, in the case of the example shown in FIGS. 7A and 7B, the certainty factor for the failure factor of c1 is obtained as follows. First, the fitness for all conditions f1 to f5 is extracted. Here, these fitness levels are defined as g1 to g5. Then, the certainty factor for the failure factor of c1 is
certainty factor (c1) = max (min (g1, g2, g3, g4), min (g1, g3, g4, g5))
Sought by.

  In the above example, the degree of conformity that is the smallest value among the degrees of conformance of the conditions included in the extracted production rule is set as the certainty, but the present invention is not limited to this. Instead, it may be a value representative of a set of fitness included in the production rule, for example, an average value.

(Reliability calculation process)
Next, reliability calculation processing by the reliability calculation unit 64 will be described. The reliability is a value provided corresponding to each failure factor, and the reliability indicating the reliability of the certainty factor calculated for the failure factor is obtained by the following equation.
confidence _i = (AnsNum _i -UnknownNum _i ) / (QuestNum _i )
In the above equation, confidence _i indicates the reliability for the failure factor i. QuestNum _i indicates the number of conditions (questions) included in the diagnostic path from the failure result to be estimated to the corresponding failure factor. AnsNum _i indicates the number of answers (answers) among the conditions (questions) included in the diagnostic path. UnknownNum _i indicates the number of conditions (questions) for which an answer is obtained, that are answered as unknown. That is, the reliability is a value indicating the ratio of those for which valid answers are obtained with respect to the conditions (questions) included in the diagnostic path from the failure result to be estimated to the corresponding failure factor. When valid answers are obtained for all the conditions, the reliability has a maximum value of 1.0.

  In addition, the reliability calculation unit 64 obtains the required fitness by reading out the fitness information recorded in the inference process temporary storage unit 25 and information on the conditions corresponding to the fitness, Calculate the degree. Further, the calculated reliability is recorded in the inference process temporary storage unit 25 together with information on the corresponding failure factor.

(Specific examples of causal networks)
Next, a specific example of the causal network will be described with reference to FIG. In the example shown in the figure, a causal network for “bridge failure” as a failure result is shown. In this example, for “Bad defect”, “Mounting position deviation”, “Lead bending”, “Low paste flux activity”, “Part oxidation”, “Part dirt”, “Paste area” Eight defective factors are “large”, “paste misalignment”, and “heater temperature setting is high”. A diagnosis path from a failure result of “bridge failure” to the above eight failure factors is set as knowledge of the tree structure.

In the example shown in FIG. 10, the production rule obtained from the diagnostic path leading to the three failure factors of “mounting position deviation”, “lead bending”, and “paste flux activity is low”
IF ((Contact between lead and land) = Yes & (Part displacement) = (Large)) then (Mounting displacement)
IF ((There is contact between the lead and land) = Yes & (Part displacement) = (Normal)) then (Lead bending)
IF ((There is a land without paste) = Yes & (There is non-wetting in the land) = Yes & (Paste flux activity) = (Low)) then (Paste flux activity is low)
It becomes.

Further, in the example shown in FIG. 10, there are two diagnostic paths that lead to a failure factor of “the area of the paste is large”, so the production rules obtained from these two are as follows:
IF ((The heat dripping property is outside the specified value) = Yes & (Paste amount) = (Many)) then (Paste area is large)
IF ((There is a phenomenon that the paste wets to the shoulder of the lead) = Yes & (Reflow oven temperature) = (Normal)) then (Paste area is large)
It becomes.

In the example shown in FIG. 10, the diagnostic path that leads to the failure factor of “the heater temperature setting is high” includes the supplementary path.
IF ((There is a phenomenon in which the paste wets up to the shoulder of the lead) = Yes & (Reflow furnace temperature) = (High) & (Heater setting) = (High) & (A phenomenon in which the paste wets the entire board) Yes) then (the heater temperature setting is high )
It becomes.

(Narrowing diagnosis path)
Next, diagnostic path narrowing processing by the diagnostic path narrowing unit 65 will be described. In the case of the knowledge structure as shown in FIG. 10, search methods for specifying factors generally include breadth-first search, depth-first search, and the like. The breadth-first search is a method in which when there are a plurality of options at a certain node, all the options are first verified, and then options further extended from each option are verified. In addition, depth-first search is a method in which if there are multiple options at a node, the options behind that one option are verified, and after reaching the conclusion, the next option is verified to the conclusion. is there.

  In the present embodiment, a diagnosis path narrowing process, which will be described later, is performed by employing a breadth-first search. When the breadth-first search is performed in the causal network shown in FIG. 10, the suitability for the conditions between nodes is determined in the order indicated by the numbers in parentheses in FIG.

  When the fitness is calculated by the fitness calculator 62 for the condition between the nodes, the diagnosis path narrowing unit 65 determines whether the calculated fitness is equal to or less than a predetermined threshold. Here, when it is determined that the fitness level is equal to or less than the threshold value, the diagnostic path narrowing unit 65 sets the diagnostic path node including the condition and the failure factor out of the factor estimation target in the diagnostic path. In other words, when the fitness is less than or equal to the threshold value, it can be determined that the failure factor of the diagnostic path including the node estimated by the condition is unlikely to be a true failure factor of the corresponding failure result. By omitting the path factor estimation process, the process efficiency can be improved.

  For example, as shown in FIG. 12, according to the answer to the condition (1), that is, the condition that “the lead and the land are in contact”, the degree of conformity to the condition is calculated to be 0.2, Assume that the threshold is set to 0.3. In this case, the path of the knowledge structure after the node “lead position touches the land” estimated based on the condition (1) is set as a factor estimation target. That is, at this time, the failure factors such as “mounting position deviation” and “lead bending” are excluded from the failure factor candidates.

  In the above example, the diagnostic path and the failure factor set as being not subject to factor estimation are determined based on whether or not the condition that the fitness is equal to or less than the threshold is included. The diagnosis path and the failure factor when the value is less than or equal to the threshold value may be set as being not subject to factor estimation. That is, when the certainty factor is less than or equal to the threshold value, it can be determined that the failure factor of the diagnostic path corresponding to the certainty factor is unlikely to be a true defect factor of the corresponding defect result. By omitting the estimation process, the efficiency of the process can be improved.

(Causal network display control)
When the diagnosis path narrowing process is performed as described above, the inference process display control unit 53 causes the display unit 22 to display when at least one of the following two display conditions is satisfied. The causal network that has been narrowed down is displayed. The first display condition is that the number of defect factors remaining as defect factor candidates is equal to or less than a predetermined threshold, and the second display condition is that even if an answer to the remaining condition is obtained, The number of failure factors that can be narrowed down by answers does not change.

  When the first display condition is satisfied, the number of failure factors remaining as failure factor candidates is equal to or less than a predetermined threshold value. By displaying the causal network on the display unit 22 in this state, It is possible to present a factor estimation causal relationship in a state where defect factors are narrowed down to some extent.

  When the second display condition is satisfied, the condition and the cause of failure correspond to each other on a one-to-one basis. By displaying the causal network on the display unit 22 in this state, the cause of failure to some extent is given to the user. It becomes possible to present the cause of the failure in the state where is narrowed down.

  Here, let us consider a case where the causal network is displayed on the display unit 22 in a state where the diagnosis path narrowing-down process as described above is not performed. In this case, since the amount of knowledge of factor estimation indicated by the causal network is usually enormous, even if such a causal network is displayed on the display unit 22, the user is too confused by the amount of information. Become.

  On the other hand, the causal network is displayed on the display unit 22 only when the display conditions as described above are satisfied, so that the user can perform the entire factor estimation in a state where the conditions are narrowed down to some extent. It becomes possible to grasp the image. As a result, it is possible to specify a failure factor by the user's judgment without verifying all conditions, or to select a condition to be verified by the user.

  For example, the search further proceeds from the state shown in FIG. 12, and the degree of fitness for the condition (2) shown in FIG. 12 is 1.0, the degree of fitness for the condition (3) is 0.0, and the condition for (4) is satisfied. Assume that the fitness is 0.3. In this case, as shown in FIG. 13, the remaining route becomes a branch of the knowledge structure after the node “paste falls from the land” estimated by the condition (2). Here, if the threshold value in the first display condition is set to “3”, since there are three defect factor candidates in the state shown in FIG. 13, the causal network in this state is displayed on the display unit. 22 will be displayed.

  Further, in the state shown in FIG. 11, the fitness for the condition (1) is 0.8, the fitness for the condition (2) is 0.2, the fitness for the condition (3) is 0.9, (4 14), the remaining route is as shown in FIG. 14, assuming that the fitness threshold is set to 0.3. In this case, even if an answer to the remaining condition is obtained, the number of failure factors that can be narrowed down by the answer does not change, so the second display condition is satisfied, and the causal network in this state is It is displayed on the display unit 22.

(Example of factor estimation display screen)
Next, an example of a display screen displayed on the display unit 22 for the user in the factor estimation process will be described. FIG. 15 shows an example of a question screen that presents a question to the user and receives an answer input in the course of the factor estimation process. As shown in the figure, the question screen includes a question display area, a defect factor candidate display area, and a causal network display area.

  In the question display area, a question presented to the user in the course of the factor estimation process and a history of the user's answer to the question are displayed. The question input / output control unit 51 controls the display of questions and the input of answers from the user in the question display area. The inference processing unit 61 transmits the question data acquired from the question generation unit 34 to the question input / output control unit 51 as the factor estimation progresses, and the question input / output control unit 51 displays the question data in the question display area. . Also, the answer input to the question accepted by the question input / output control unit 51 is transmitted to the inference processing unit 61 and recorded in the inference process temporary storage unit 25. That is, the inference process temporary storage unit 25 records the question presented to the user and the history of answer input to the user, and the question input / output control unit 51 records the history recorded in the inference process temporary storage unit 25. The history is displayed by reading.

  In the defect factor candidate display area, defect factors remaining as defect factor candidates in the process of the factor estimation process are displayed. Although details will be described later, a certainty factor and / or a reliability factor may be displayed for each defect factor candidate. Although details will be described later, an input for selecting a defect factor to be a question from among candidates for a defect factor displayed in the defect factor candidate display area, or an input for selecting a defect factor to be excluded from the defect factor candidates. May be accepted. The factor input / output control unit 52 displays the defect factor candidates in the defect factor candidate display area and receives selection inputs.

  In the causal network display area, the diagnostic path is narrowed down by the diagnostic path narrowing unit 65 in the course of the factor estimation process, and the corresponding causal network is displayed when the above display condition is satisfied. The causal network display in this causal network display area is performed by the inference process display control unit 53. In addition, the display of the defect factor candidate displayed in the defect factor candidate display area is also displayed when the above display condition is satisfied.

  Next, the process of factor estimation shown in FIG. 15 will be described. In the example shown in the figure, “Bad failure” is set as a failure result, and the answer “Yes” is input to the question “Is there a land without paste?”. Further, the degree of conformity with respect to nodes other than the node “paste falls from the land” is smaller than a predetermined threshold based on the failure result “bridge failure”, and the diagnosis path narrowing unit 65 determines the diagnosis paths after these nodes. It has been deleted. In this case, there are three candidate failure factors in the diagnostic path after the node “Paste falls from the land”: “Paste flux activity is low”, “Part oxidation”, and “Part dirt”. Since the condition is satisfied, the causal network is displayed in the causal network display area. These three failure factor candidates are displayed in the failure factor candidate display area.

  In addition, when the answer “Yes” is input to the question “Is there a land without paste?”, The path from the failure result “Bridge failure” to the node “Paste falls from the land” The fitness is 1.0. The numerical value information of the fitness is displayed on the corresponding path in the causal network display area. When the fitness is calculated, numerical information of the fitness is displayed, and the corresponding path is displayed with a line thickness corresponding to the size of the fitness. In addition, the display form of the fitness level is not limited to the above example, and only one of the fitness level information display and the path line thickness display may be displayed. In addition, the fitness level can be recognized by the user. Any display form may be used as long as it is in a form.

In this state, the certainty factor and the reliability with respect to the failure factor “the paste flux activity is low” are calculated as follows. First, the production rule of the diagnostic path corresponding to the failure factor is
IF ((There is a land with no paste) = Yes & (Land is not wet) = No entry & (Paste flux activity) = No entry) then (Paste flux activity is low)
It becomes.

  In this case, the certainty factor is 1.0. Further, since one answer is obtained for three questions, the reliability is 1 / 3≈0.3.

  Next, the process of factor estimation shown in FIG. 16 will be described. In this process, from the state shown in FIG. 15, a question is selected for the failure factor “low flux activity of paste” displayed in the failure factor candidate display area. Then, the question “How active is the paste?” Is asked, and the answer “normal” is entered.

  As shown in the figure, it is possible to designate a failure factor that the user decides to make a question out of the failure factors displayed in the failure factor candidate display area. The inference processing unit 61 extracts the question of the condition corresponding to the path leading to the failure factor selected by the question from the causal network, and the question input / output control unit 51 displays the question extracted by the inference processing unit 61 in the question display area. Control to be displayed. As a result, the user can first ask a question about a failure factor that is likely to be a true failure factor from the displayed failure factor candidates, and the factor estimation process can be performed efficiently. Can be performed.

  In addition, since the answer to the question “How active is the paste?” Is “ordinary”, the fitness calculator 62 considers the membership function corresponding to the corresponding question. A degree of 0.5 is calculated. The fitness information is displayed on the corresponding path in the causal network display area, and the corresponding path is displayed with a line thickness corresponding to the magnitude of the fitness.

In this state, the certainty factor and the reliability with respect to the failure factor “the paste flux activity is low” are calculated as follows. First, the production rule of the diagnostic path corresponding to the failure factor is
IF ((There is a land without paste) = Yes & (Land is not wet) = No input & (Paste flux activity) = (Normal)) then (Paste flux activity is low)
It becomes.

  In this case, the certainty factor is 0.5. In addition, since two answers are obtained for three questions, the reliability is 2 / 3≈0.7.

  Next, the process of factor estimation shown in FIG. 17 will be described. In this process, from the state shown in FIG. 15, a deletion instruction is given for the failure factor “low flux activity of paste” displayed in the failure factor candidate display area. When such a deletion instruction is given, the display is changed as shown in FIG. That is, the defect factor instructed to be deleted from the defect factor candidate display area is deleted, and the causal network in a state where the diagnostic path leading to the defect factor instructed to be deleted is displayed in the causal network display area.

  In this way, the user can remove a failure factor that is unlikely to be a true failure factor from the failure factor candidates displayed in the failure factor candidate display area from the failure factor candidates. It has become. As a result, the factor estimation process can be performed efficiently.

  Next, the process of factor estimation shown in FIG. 19 will be described. In this process, in the state shown in FIG. 16, an answer “low” is input to the question “how active is the paste?” Is displayed in the defect factor candidate display area. Questions are further selected for the failure factor “low flux activity of paste”. And this has led to the question "Is the land wet?"

  As described above, by repeatedly selecting a question for a specific failure factor, the conditions included in the diagnostic path leading to the corresponding failure factor are presented to the user as a question from the downstream side. Thereby, the reliability with respect to the corresponding failure factor can be efficiently improved by preferentially asking the question with respect to the specific failure factor. That is, when there is a candidate for a failure factor that is expected to be a true failure factor, the user preferentially improves the reliability of the failure factor to determine whether the prediction is appropriate. It becomes possible to make a judgment immediately.

  In the example shown in FIG. 19, information on the certainty factor and the reliability factor at that time is displayed for each of the failure factors displayed in the failure factor candidate display area. In the example shown in the figure, display is performed on the right side of each failure factor in the form of “(confidence / reliability)”.

  Next, the process of factor estimation shown in FIG. 20 will be described. In this process, in the state shown in FIG. 16, an answer “low” is input to the question “how active is the paste?” Is displayed in the defect factor candidate display area. Questions are selected for both failure factors such as “part oxidation” and “part contamination”. As a result, the question “Is the part dirty?” Has been asked.

  That is, when a question is selected for a plurality of failure factors, a question with a high possibility of causing a difference in the certainty factor for each of the selected failure factors is performed. In other words, when there are a plurality of failure factor candidates that are expected to be true failure factors, the user is asked which question has a high possibility of causing a difference in certainty, so that which failure factor is true It is possible to quickly confirm whether there is a high possibility of being a failure factor.

  Next, a display example of a diagnosis result will be described with reference to FIGS. In the above question screen, when a specific failure factor is selected and an instruction to display a diagnosis screen is given by the user, a diagnosis screen for displaying a diagnosis result for the corresponding failure factor is displayed. This diagnosis screen is provided with a question display area and a diagnosis result display area.

  In the question display area, a question presented to the user in the course of the factor estimation process and a history of the user's answer to the question are displayed. The question input / output control unit 51 displays the history by reading the history recorded in the inference process temporary storage unit 25.

  In the diagnosis result display area, a diagnosis path leading to the selected failure factor is displayed. The diagnosis path is extracted from the causal network by the inference processing unit 61, and the extracted diagnosis path is displayed in the diagnosis result display area by the inference process display control unit 53.

  Also, on this diagnostic path, numerical information of the fitness level corresponding to the path between the nodes is displayed, and the corresponding path is displayed with a line thickness corresponding to the size of the fitness level. In addition, the display form of the fitness level is not limited to the above example, and only one of the fitness level information display and the path line thickness display may be displayed. In addition, the fitness level can be recognized by the user. Any display form may be used as long as it is in a form.

  In this way, by displaying the question answer history and diagnosis path information for a specific defect factor, it is possible to present the validity of the factor estimation result to the user.

  FIG. 21 shows an example of a diagnosis result for the failure factor c1 with respect to the failure result d1, and FIG. 22 shows an example of a diagnosis result for the failure factor “component contamination” with respect to the failure result “bridge failure”. ing. As shown in these figures, the diagnosis results may be displayed even if the answers to all the questions included in the diagnostic path are not obtained, and the answers to all the questions included in the diagnostic path The diagnosis result may be displayed in a state where is obtained.

(Factor estimation process flow)
Next, the flow of factor estimation processing will be described with reference to the flowchart shown in FIG. When the factor estimation process is started, first, in step 1 (hereinafter referred to as S1), a question screen is displayed on the display unit 22 by the input display control unit 31. In the question display area on the question screen, an area for inputting a defect result is provided. The failure result is input by the user to the area for inputting the failure result, and this input information is received by the question input / output control unit 51 (S2). Then, the failure result information is stored in the inference process temporary storage unit 25 by the inference processing unit 61.

  When the failure result is input, the inference processing unit 61 extracts the causal network information for the corresponding failure result from the estimated knowledge recording unit 23 (S3). At this time, the inference processing unit 61 acquires the causal network information converted into the production rules by the knowledge conversion unit 33. Then, the inference processing unit 61 performs a breadth-first search on the extracted causal network (S4).

  The inference processing unit 61 sequentially reads out the conditions to be verified by the breadth-first search, and determines whether the conditions determine the fitness based on the input from the user or the fitness based on the inspection result obtained by the inspection device 14 Is determined (S5).

  In S5, when it is determined that the read condition is for determining the degree of fitness based on the inspection result, the feature amount calculation unit 35 reads the inspection result data from the process state database 26 and is necessary for determining the corresponding condition. The feature amount is calculated. On the other hand, if it is determined in S5 that the read condition is to determine the degree of fitness based on an input from the user, the question is displayed in the question display area on the question screen by the question input / output control unit 51, and the user An answer to the question is input (S7).

  Thereafter, the fitness calculator 62 calculates the fitness based on the feature value obtained in S6 or the user input obtained in S7 (S8). When the fitness is calculated, the diagnosis path narrowing unit 65 determines whether or not the fitness is equal to or less than a predetermined threshold value. It is set as not being estimated (S9).

  Next, the inference process display control unit 53 determines whether or not the above display condition is satisfied (S10), and if the display condition is not satisfied, the process returns to the process from S5 and returns to the next condition. Is verified.

  On the other hand, when the display condition is satisfied, the inference process display control unit 53 performs control to display the causal network whose diagnosis path is narrowed down at that time in the causal network display area on the question screen. In addition, the factor input / output control unit 52 performs control to display the defect factor candidates narrowed down at that time in the defect factor candidate display area on the question screen (S11). Further, for each of the defective factor candidates, the certainty factor calculation unit 63 calculates the certainty factor, and the reliability calculation unit 64 calculates the reliability factor (S12).

  When the failure factor candidates and the causal network are displayed, the user instruction input confirmation process in S13, S15, S17, and S19, which will be described later, is performed. In the flowchart, these steps are sequentially performed. However, in actuality, when a user instruction is input, a step corresponding to the instruction input content is performed.

  In S <b> 13, the factor input / output control unit 52 determines whether or not a user instruction input for question selection has been made for a specific defect factor. When there is a user instruction input for selecting a question, the inference processing unit 61 extracts a question for the defect factor selected by the question (S14), returns to the processing from S5, and verifies the extracted question. Is called.

  In S <b> 15, the factor input / output control unit 52 determines whether or not a deletion user instruction is input for a specific defect factor. When there is a deletion user instruction input, the diagnostic path narrowing unit 65 deletes the diagnostic path leading to the defective factor instructed to delete from the causal network at that time (S16). In addition, the failure input instructed to be deleted from the failure factor candidate display area by the factor input / output control unit 52 is deleted, and the diagnostic path leading to the defect factor instructed to be deleted in the causal network display area by the inference process display control unit 53 A causal network with deleted is displayed. Thereafter, returning to the processing from S5, verification for the next condition is performed.

  In S <b> 17, the factor input / output control unit 52 determines whether or not there is a user instruction input for displaying the diagnosis result. When there is a diagnosis result display instruction, a diagnosis screen for displaying a diagnosis result for the corresponding failure factor is displayed.

  In S <b> 19, the input display control unit 31 determines whether or not there has been a user instruction input for instructing the end of the factor estimation process. When the end instruction is not performed, the process returns to the process from S5, the verification for the next condition is performed, and when the end instruction is performed, the factor estimating process is ended.

  In addition, each block with which the control part 30 of the process management apparatus 10 is provided may be comprised by hardware logic, and may be implement | achieved by software using CPU as follows.

  That is, the control unit 30 includes a CPU (central processing unit) that executes instructions of a control program that realizes each function, a ROM (read only memory) that stores the program, a RAM (random access memory) that expands the program, A storage device (recording medium) such as a memory for storing the program and various data is provided. An object of the present invention is to provide a recording medium in which a program code (execution format program, intermediate code program, source program) of a control program of the control unit 30 which is software that realizes the above-described functions is recorded so as to be readable by a computer. This can also be achieved by supplying the control unit 30 and reading and executing the program code recorded on the recording medium by the computer (or CPU or MPU).

  Examples of the recording medium include a tape system such as a magnetic tape and a cassette tape, a magnetic disk such as a floppy (registered trademark) disk / hard disk, and an optical disk such as a CD-ROM / MO / MD / DVD / CD-R. Card system such as IC card, IC card (including memory card) / optical card, or semiconductor memory system such as mask ROM / EPROM / EEPROM / flash ROM.

  The control unit 30 may be configured to be connectable to a communication network, and the program code may be supplied via the communication network. The communication network is not particularly limited. For example, the Internet, intranet, extranet, LAN, ISDN, VAN, CATV communication network, virtual private network, telephone line network, mobile communication network, satellite communication. A net or the like is available. Further, the transmission medium constituting the communication network is not particularly limited. For example, even in the case of wired such as IEEE 1394, USB, power line carrier, cable TV line, telephone line, ADSL line, etc., infrared rays such as IrDA and remote control, Bluetooth ( (Registered trademark), 802.11 wireless, HDR, mobile phone network, satellite line, terrestrial digital network, and the like can also be used. The present invention can also be realized in the form of a computer data signal embedded in a carrier wave in which the program code is embodied by electronic transmission.

  The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope shown in the claims. That is, embodiments obtained by combining technical means appropriately modified within the scope of the claims are also included in the technical scope of the present invention.

  The process management apparatus according to the present invention is suitable for, for example, management of a printed circuit board production process, but is not limited thereto, industrial product production process, industrial product, agricultural product, or raw material inspection process, disposal object The present invention can be widely applied to the entire processing process of the object such as a processing process (for example, factory waste, factory waste water, waste gas, trash, etc.), an inspection process of the disposal object, an inspection process of the facility, a recycling process, and the like.

It is a block diagram which shows schematic structure of the process management apparatus which concerns on one Embodiment of this invention. It is a block diagram which shows schematic structure of the production system containing the said process management apparatus. It is a figure which shows an example of a causal network typically. It is a figure which shows the diagnostic path | pass obtained from the causal network shown in FIG. (A) is a figure which shows an example of a diagnostic path | pass, (b) is a figure which shows the production rule produced | generated by the diagnostic path | pass of (a). (A) is a figure which shows the other example of a diagnostic path | pass, (b) is a figure which shows the production rule produced | generated by the diagnostic path | pass of (a). (A) is a figure which shows the further another example of a diagnostic path | pass, (b) is a figure which shows the production rule produced | generated by the diagnostic path | pass of (a). (A) is a figure which shows the further another example of a diagnostic path | pass, (b) is a figure which shows the production rule produced | generated by the diagnostic path | pass of (a). (A) And (b) is a figure which shows an example of the membership function with respect to three types of answers of "large (large)", "normal (mid)", and "small (small)". It is a knowledge structure figure which shows the specific example of a causal network. FIG. 11 is a knowledge structure diagram further illustrating an order in which a breadth-first search is performed in the knowledge structure illustrated in FIG. 10. FIG. 11 is a knowledge structure diagram further showing paths that are deleted by the narrowing-down process in the knowledge structure shown in FIG. 10. FIG. 11 is a knowledge structure diagram illustrating an example of a state in which paths are deleted by a narrowing process in the knowledge structure illustrated in FIG. 10. FIG. 11 is a knowledge structure diagram illustrating another example of a state in which a path is deleted by a narrowing process in the knowledge structure illustrated in FIG. 10. It is a display screen figure which shows the example of a question screen which presents a question to a user and receives an answer input in the course of a factor estimation process. It is a display screen figure which shows the other example of the said question screen. It is a display screen figure which shows the other example of the said question screen. It is a display screen figure which shows the other example of the said question screen. It is a display screen figure which shows the other example of the said question screen. It is a display screen figure which shows the other example of the said question screen. It is a display screen figure which shows the example of the diagnostic screen which displays the diagnostic result with respect to a defect factor. It is a display screen figure which shows the specific example of the said diagnostic screen. It is a flowchart which shows the flow of a factor estimation process.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Process management apparatus 11 Printing apparatus 12 Mounting apparatus 13 Apparatus 14 Inspection apparatus 14a Printing inspection apparatus 14b Mounting inspection apparatus 14c Inspection apparatus 21 Input part 22 Display part 23 Estimation knowledge recording part 24 Question data recording part 25 Inference process temporary storage part 26 Process State database 30 Control unit 31 Input display control unit (input control means / display control means)
32 inference unit 33 knowledge conversion unit 34 question generation unit 35 feature amount calculation unit 40 inspection result input unit (inspection result input means)
41 Print Result Input Unit 42 Mounting Result Input Unit 43 Soldering Result Input Unit 44 Manufacturing Device History Input Unit 51 Question Input / Output Control Unit 52 Factor Input / Output Control Unit 53 Inference Process Display Control Unit 61 Inference Processing Unit (Inference Processing Means)
62 Goodness-of-fit calculation unit
63 certainty factor calculation unit (confidence factor calculation means)
64 reliability calculation unit (reliability calculation means)
65 Diagnosis path narrowing section (diagnostic path narrowing means)

Claims (14)

One or more defect factor candidates are associated with each of a plurality of defect results that may occur in a processing system that performs processing on an object, and each defect result is assigned to each defect factor corresponding to the defect result. An estimated knowledge recording unit for recording factor estimation knowledge information indicating a diagnosis path of the factor estimation leading to the tree structure knowledge by conditional branching;
Inference processing means for performing factor estimation processing based on the factor estimation knowledge information recorded in the estimation knowledge recording unit;
In the process in which factor inference processing is performed by the inference processing means, input control means for obtaining an answer from the user to the question corresponding to the condition included in the factor inference knowledge information;
On the basis of the answer acquired by the input control means, a fitness level calculation means for calculating a fitness level indicating a level satisfying the condition,
A diagnostic path narrowing means for setting a specific diagnostic path and a failure factor as factors not to be estimated, and
A diagnostic path including the condition when a specific diagnostic path and a failure factor set by the diagnostic path narrowing means as being excluded from the factor estimation target and the fitness calculated by the fitness computing means is equal to or less than a predetermined threshold; Defective factor or the diagnostic path and the defective factor when the value representing the set of fitness included in a specific diagnostic path is less than a predetermined threshold among the fitness calculated by the fitness calculator der is,
The goodness of fit, with is represented by 0 or 1 the following numbers, characterized that you have become the answer is acceptable for the condition such as the goodness of fit is larger than 0 and smaller than 1 Process management device.   2. The process management apparatus according to claim 1, further comprising display control means for displaying factor estimation knowledge information consisting of a diagnosis path set as a factor estimation target and a defect factor by the diagnosis path narrowing means on a display unit. .   The display control means displays the factor estimation knowledge information on the display unit when the number of failure factors not set as factor estimation targets by the diagnostic path narrowing means is equal to or less than a predetermined threshold. The process management apparatus according to claim 2.   Even if the display control means obtains answers to all the conditions included in the diagnostic path set as the factor estimation target by the diagnostic path narrowing means, the number of failure factors that can be narrowed down by the answers does not change 3. The process management apparatus according to claim 2, wherein the factor estimation knowledge information is displayed on a display unit. An inspection result input means for receiving inspection result data from an inspection device for inspecting a processing process in the processing system;
An inspection result recording unit for recording the inspection result data received by the inspection result input means;
When the input control means obtains an answer from the user according to the content of the question corresponding to the condition included in the factor estimation knowledge information in the process of performing the factor estimation process by the inference processing means, and the inspection The process management apparatus according to claim 1, wherein the process management apparatus switches between the case of obtaining from result data.   3. The process management apparatus according to claim 2, wherein the display control means displays information on the fitness calculated by the fitness calculation means on the display unit in correspondence with a condition corresponding to the fitness. . A certainty factor calculating means for calculating, as a certainty factor, a value representative of a set of conformances with respect to the conditions included in the diagnostic path leading to the defect factor for the defect factor set as the factor estimation target by the diagnostic path narrowing unit; Prepared,
3. The process management apparatus according to claim 2, wherein the display control means displays information on the certainty factor on the display unit in association with the defect factor. Regarding the failure factor set as the factor estimation target by the diagnostic path narrowing means, a value indicating the proportion of the conditions included in the diagnostic path leading to the failure factor that have a valid answer is calculated as the reliability. Further comprising a reliability calculation means,
The process control apparatus according to claim 2, wherein the display control unit displays information on the reliability on the display unit in association with the failure factor. The input control means accepts a selection input of a failure factor set as a factor estimation target displayed on the display unit,
3. The process management apparatus according to claim 2, wherein the inference processing means performs verification on a condition included in a diagnostic path corresponding to a failure factor designated by the selection input. The input control means accepts a deletion instruction input of a failure factor set as a factor estimation target displayed on the display unit,
3. The process management apparatus according to claim 2, wherein the diagnostic path narrowing means sets the diagnostic path corresponding to the failure factor designated by the deletion instruction input and the failure factor as not being subject to factor estimation.   A question display area in which the display control means displays a question presented to the user in the course of the factor estimation process; a fault factor remaining as a fault factor candidate in the course of the factor estimation process And a factor estimation knowledge information display region for displaying factor estimation knowledge information consisting of a diagnostic path and a failure factor set as a factor estimation target by the diagnostic path narrowing means. The process management apparatus according to claim 2, wherein the process management apparatus is provided above. A process management program for operating the process management apparatus according to any one of claims 1 to 11 , wherein the process management program causes a computer to function as each of the above means. A computer-readable recording medium on which the process management program according to claim 12 is recorded. One or more defect factor candidates are associated with each of a plurality of defect results that may occur in a processing system that performs processing on an object, and each defect result is assigned to each defect factor corresponding to the defect result. An estimated knowledge recording step for recording factor estimated knowledge information indicating a diagnostic path of the leading factor estimation as knowledge of the tree structure by conditional branching;
An inference processing step for performing factor estimation processing based on the factor estimation knowledge information recorded in the estimation knowledge recording step;
In the process of performing the factor estimation process in the inference processing step, an input control step for obtaining an answer from the user to the question corresponding to the condition included in the factor estimation knowledge information;
On the basis of the answer acquired in the input control step, a fitness level calculating step for calculating a fitness level indicating a level satisfying the condition,
A diagnostic path narrowing step for setting a specific diagnostic path and a failure factor as factors not to be estimated, and
The diagnostic path including the condition when the specific diagnostic path and the failure factor set as factors excluded from the factor estimation target in the diagnostic path narrowing step are less than or equal to a predetermined threshold calculated in the fitness calculation step The failure path, or the diagnosis path and the failure when the value representing the set of fitness levels included in the specific diagnostic path is less than or equal to a predetermined threshold among the fitness levels calculated in the fitness level calculation step. Ri factors der,
The goodness of fit, with is represented by 0 or 1 the following numbers, characterized that you have become the answer is acceptable for the condition such as the goodness of fit is larger than 0 and smaller than 1 Process control method.

Images