CN109213034B - Equipment health degree monitoring method and device, computer equipment and readable storage medium - Google Patents
Equipment health degree monitoring method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN109213034B CN109213034B CN201810978149.5A CN201810978149A CN109213034B CN 109213034 B CN109213034 B CN 109213034B CN 201810978149 A CN201810978149 A CN 201810978149A CN 109213034 B CN109213034 B CN 109213034B
- Authority
- CN
- China
- Prior art keywords
- equipment
- monitored
- monitoring
- training
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 136
- 230000036541 health Effects 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000004519 manufacturing process Methods 0.000 claims abstract description 94
- 230000009471 action Effects 0.000 claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 85
- 238000012795 verification Methods 0.000 claims description 36
- 238000013527 convolutional neural network Methods 0.000 claims description 20
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 16
- 238000001514 detection method Methods 0.000 abstract description 10
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a method and a device for monitoring equipment health degree, computer equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring production action information and yield monitoring data of equipment to be monitored within a preset time length; and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length. The invention does not need excessive parameter adjustment, can quickly train a health monitoring model as long as enough data are accumulated, has high automation degree of the detection process, saves a large amount of time and labor cost, and can accurately quantify the health degree, thereby selecting the most appropriate maintenance time.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for monitoring equipment health degree, computer equipment and a computer readable storage medium.
Background
In the field of industrial production, there is a need to monitor the health of industrial equipment. Health monitoring of industrial equipment is a technology urgently needed by the industry at present, and is a prerequisite for realizing predictive maintenance.
The maintenance of electromechanical devices by the industry community typically employs both periodic maintenance and post-failure maintenance. The former has high cost and poor flexibility, and is difficult to find out the equipment problem in the latent stage. The latter is liable to cause serious damage to the equipment and the consequences of the failure of large batches of products, with huge losses to the plant.
Therefore, there is a need for an economical and reliable equipment maintenance scheme that neither costs the test when there is no problem, nor handles the problem in time to cause serious consequences.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a method and an apparatus for monitoring a health degree of a device, a computer device, and a computer readable storage medium, so as to avoid the problem that a cost is not spent for detection when there is no problem, and the problem can be timely handled when the problem occurs, thereby avoiding causing serious consequences.
In a first aspect, an embodiment of the present invention provides an apparatus health monitoring method, where the method includes:
acquiring production action information and yield monitoring data of equipment to be monitored within a preset time length;
and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the obtaining of yield monitoring data of a device to be monitored within a preset time duration includes:
acquiring production audio data of equipment to be monitored within a preset time;
and identifying the production audio data through a pre-established production monitoring system to obtain the production monitoring data of the equipment to be monitored within the preset time length.
With reference to the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where before processing the production action information and the production monitoring data through a pre-trained health monitoring model, the method further includes:
acquiring a training data set corresponding to the equipment to be monitored;
and training a health monitoring model according to the training data set.
With reference to the second possible implementation manner of the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the obtaining a training data set corresponding to the device to be monitored includes:
the method comprises the steps of obtaining production action information of the equipment to be monitored in a period of time, and recording production audio data of the equipment to be monitored in the period of time through recording equipment;
identifying and processing the production audio data in the period of time through a pre-established yield monitoring model to obtain yield monitoring data corresponding to the production action information;
and determining the production action information and the yield monitoring data corresponding to the production action information as a training data set corresponding to the equipment to be monitored.
With reference to the second possible implementation manner of the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the training of the health monitoring model according to the training data set includes:
dividing the training data set into a training set and a verification set;
training an OneClassSVM model through the training set;
analyzing the verification set through the OneClassSVM model to obtain a health degree curve corresponding to the verification set;
adjusting a negative sample proportion parameter in the OneClassSVM model according to the verification set and a health degree curve corresponding to the verification set;
and determining the adjusted OneClassSVM model as a health monitoring model corresponding to the equipment to be monitored.
In a second aspect, an embodiment of the present invention provides an apparatus for monitoring health of a device, where the apparatus includes:
the system comprises an acquisition module, a monitoring module and a monitoring module, wherein the acquisition module is used for acquiring production action information and yield monitoring data of equipment to be monitored within preset time;
and the monitoring processing module is used for processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length.
With reference to the second aspect, an embodiment of the present invention provides a first possible implementation manner of the second aspect, where the apparatus further includes:
the model training module is used for acquiring a training data set corresponding to the equipment to be monitored; and training a health monitoring model according to the training data set.
With reference to the first possible implementation manner of the second aspect, an embodiment of the present invention provides a second possible implementation manner of the second aspect, where the model training module includes:
the dividing unit is used for dividing the training data set into a training set and a verification set;
the training unit is used for training the OneClassSVM model through the training set;
the analysis unit is used for analyzing the verification set through the OneClassSVM model to obtain a health degree curve corresponding to the verification set;
the adjusting unit is used for adjusting the negative sample proportion parameters in the OneClassSVM model according to the verification set and the health degree curve corresponding to the verification set;
and the determining unit is used for determining the adjusted OneClassSVM model as a health monitoring model corresponding to the equipment to be monitored.
In a third aspect, an embodiment of the present invention provides a computer device, where the apparatus includes a processor and a memory;
the memory stores executable instructions, and when the apparatus runs, the processor executes the executable instructions stored in the memory to implement the device health monitoring method according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where executable instructions are stored in the computer-readable storage medium, and the executable instructions are executed by a processor to implement the device health monitoring method according to the first aspect.
In the embodiment of the invention, production action information and yield monitoring data of equipment to be monitored in a preset time length are obtained; and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length. The invention does not need excessive parameter adjustment, can quickly train a health monitoring model as long as enough data are accumulated, has high automation degree of the detection process, saves a large amount of time and labor cost, and can accurately quantify the health degree, thereby selecting the most appropriate maintenance time.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart illustrating a pre-training health monitoring model provided in embodiment 1 of the present invention;
fig. 2 is a flowchart illustrating an apparatus health monitoring method according to embodiment 1 of the present invention;
fig. 3 is a flowchart illustrating another method for monitoring health of a device according to embodiment 1 of the present invention;
fig. 4 is a diagram illustrating the effect of monitoring the health of a device provided in embodiment 1 of the present invention;
FIG. 5 is a waveform diagram illustrating an abnormal health of a device provided in embodiment 1 of the present invention;
fig. 6 is a schematic structural diagram illustrating an apparatus health monitoring device provided in embodiment 2 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It is considered that two types of equipment maintenance modes, namely regular maintenance and post-fault maintenance, are generally adopted in the related art. The periodic maintenance cost is high, the flexibility is poor, and equipment problems in the latent stage are difficult to find. The maintenance after the failure easily causes serious damage to the equipment and unqualified products in large quantities, and brings huge loss to factories. Based on this, embodiments of the present invention provide a method and an apparatus for monitoring equipment health, a computer device, and a computer-readable storage medium, which are described below by way of embodiments.
Example 1
The embodiment of the invention provides a method for monitoring equipment health degree. Before the health degree of the equipment to be monitored is monitored by the method, a yield monitoring system for monitoring the yield of the equipment to be monitored needs to be established. Wherein, output monitoring system includes recording equipment and monitor terminal, and recording equipment can be microphone or recorder etc. and recording equipment sets up near treating monitor device, and recording equipment and monitor terminal communicate through wired or wireless mode.
In the embodiment of the invention, the equipment to be monitored can be one or more production equipment, the equipment to be monitored can make sound in the production process, and the audio data generated in the production process of the equipment to be monitored is collected by the recording equipment arranged near the equipment to be monitored. And the recording equipment sends the recorded audio data to the monitoring terminal. The monitoring terminal converts the audio data into two-dimensional frequency spectrum data of a time-frequency domain through Fourier decomposition, a process starting point and a process ending point of each production are marked in the two-dimensional frequency spectrum data, the marked two-dimensional frequency spectrum data are divided into a plurality of training data according to a preset time interval, and a convolutional neural network is trained according to the plurality of training data. And after the convolutional neural network is trained, a yield monitoring system corresponding to the equipment to be monitored is established. The monitoring terminal can monitor the output of the equipment to be monitored in real time through the trained convolutional neural network.
As shown in fig. 1, after the yield monitoring system corresponding to the device to be monitored is established in the above manner, the following steps a1-a2 are first used to train the health monitoring model corresponding to the device to be monitored, which specifically include:
a1: and acquiring a training data set corresponding to the equipment to be monitored.
The method comprises the steps of obtaining production action information of equipment to be monitored in a period of time, and recording production audio data of the equipment to be monitored in the period of time through recording equipment; identifying and processing the production audio data within a period of time through a pre-established yield monitoring model to obtain yield monitoring data corresponding to the production action information; and determining the production action information and the yield monitoring data corresponding to the production action information as a training data set corresponding to the equipment to be monitored.
The production action information comprises information such as time and operating parameters of equipment to be monitored. After the production audio data corresponding to the equipment to be monitored is obtained, the production audio data are identified through a convolutional neural network in a pre-established yield monitoring model, the non-normalized original output of the convolutional neural network is used as the yield monitoring data corresponding to the production action information, and the production action information and the corresponding yield monitoring data are determined as a training data set corresponding to the equipment to be monitored. The training data set does not need to be marked, so that the workload can be saved, and the monitoring efficiency can be improved.
A2: the health monitoring model is trained according to the training data set.
Dividing a training data set into a training set and a verification set; the oneplasssvm model is trained through a training set. Wherein the oneclassvm model can distinguish whether the new input is similar to the samples in the training set. And analyzing the verification set through the OneClassSVM model to obtain a health degree curve corresponding to the verification set. And adjusting the negative sample proportion parameter in the OneClassSVM model according to the verification set and the health degree curve corresponding to the verification set. And determining the adjusted OneClassSVM model as a health monitoring model corresponding to the equipment to be monitored.
In the embodiment of the invention, the larger the scale of the training data set is, the better the training data set is, because the original output of the convolutional neural network in the yield detection system is only a one-dimensional array, the data amount of the convolutional neural network is determined by the duration of single production and the number of different stages, usually tens to hundreds of orders of magnitude, the training complexity of the OneClassSVM model is very low, and signals as many as possible can be selected as the training data set under the allowable condition without distinguishing the signals of normal production and abnormal production.
Training of the OneClassSVM model requires adjustment of the proportion of negative samples, and according to the proportion, most of data distributed most intensively in a training data set are used as positive samples, and the rest outliers are used as negative samples, so that an interface is obtained. Therefore, the proportion of the negative samples should be as close as possible to the proportion occupied by the actual abnormal production action, and the estimation can be carried out according to the failure frequency of the equipment to be monitored in the past. If the frequency of the failure of the equipment to be monitored in the past does not exist, the failure frequency can be determined in the following mode of continuous trial and error:
samples of two periods of time are prepared to be respectively used for a training set and a check set, firstly, a trial negative sample proportion is given, for example, 10%, a OneClassSVM model is trained by the training set, the health degree corresponding to the check set is calculated through the trained OneClassSVM model, the time with lower health degree is analyzed, and whether the problem corresponds to the equipment to be monitored or not is judged. If the device to be monitored has no problem but the health is low in many cases, the negative sample ratio can be reduced. If the health degree is lower every time and corresponds to the problem of the equipment to be monitored, the proportion of the negative samples is tried to be increased, and whether the missing equipment problem is not detected or not is judged. The trial and error are repeated to obtain a proper negative sample ratio.
After the proportion of the negative samples is determined by the method, the proportion parameters of the negative samples in the OneClassSVM model are adjusted. The adjusted OneClassSVM model is the health monitoring model corresponding to the equipment to be monitored.
As shown in fig. 2, after the health monitoring model corresponding to the device to be monitored is trained through the operations of the above steps a1-a2, the health monitoring model is used to monitor the health of the device to be monitored, and the method specifically includes:
step 101: and acquiring production action information and yield monitoring data of the equipment to be monitored within a preset time.
The preset time period may be 1 hour, 12 hours, one day or one week, etc. The method comprises the steps of obtaining production action information of equipment to be monitored within preset time, and obtaining production audio data of the equipment to be monitored within the preset time through a recording device arranged near the equipment to be monitored. And identifying and processing the production audio data through a convolutional neural network in a pre-established yield monitoring system to obtain the yield monitoring data of the equipment to be monitored within a preset time.
Step 102: and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within a preset time length.
The health monitoring model OneClassSVM model trained by the method classifies the production action information and the yield monitoring data, determines whether the normal production action or the abnormal production action belongs to, takes the proportion of the normal production action to the total production times in a period of time as an index for measuring the health degree of the equipment, and can draw a health degree curve of the equipment to be monitored in a preset time period.
In order to facilitate understanding of the health monitoring scheme provided by the present invention, a detailed analysis is performed below with reference to the accompanying drawings. As shown in fig. 3, a training set waveform, a verification set waveform and a waveform to be recognized corresponding to a device to be monitored are obtained, and the training set waveform, the verification set waveform and the waveform to be recognized are respectively recognized by a yield monitoring system, so as to obtain a training set CNN (convolutional neural network) original output, a verification set CNN original output and a CNN original output to be recognized. And performing OneClassSVM model training by using the original output of the training set CNN, and performing parameter adjustment on the trained OneClassSVM model according to the original output of the verification set CNN. And after parameter adjustment, in the practical application process of the OneClassSVM model, judging whether the original output of the CNN to be identified is normal or not through the OneClassSVM model to obtain the equipment health degree of the equipment to be monitored.
In the embodiment of the invention, a production detection system is built for a certain device or a plurality of devices by recording audio through microphones arranged beside the device in each application. And then obtaining the production action information of a period of time and the output of the convolutional neural network in the yield detection system corresponding to each production action, dividing the data into two segments according to the time, and respectively using the two segments as a training set and a verification set. And training the OneClassSVM model by using the training set, analyzing the verification set by using the trained model to obtain a health degree curve, and adjusting parameters expressing the proportion of negative samples in the OneClassSVM model according to the reasonability or not of the health degree curve. After the parameter adjustment is finished, the health degree analysis can be carried out on the new data by using the OneClassSVM model.
Fig. 4 shows the result of analyzing the device health of an SMT (surface mount technology) mounter by the device health method provided by the embodiment of the present invention. The curve of fig. 4 shows three points in total, where there is an obvious decrease in health degree, except for the first and third points, which are caused by the factory debugging of the equipment, the decrease in the middle point corresponds to an abnormality of the production action, which is also obvious from the waveform recorded by the microphone, as shown in fig. 5, in the stage of waveform abnormality, the tail of the waveform corresponding to the production action lacks several peaks, which may correspond to the incompleteness of the production action. After the abnormality occurs, the factory can react and correct the result after about 10 hours, and if the health degree monitoring scheme provided by the invention is used, the obvious decrease of the health degree curve can be seen after 1-2 hours of the abnormality. The problem of the equipment to be monitored can be reacted more timely.
In the embodiment of the invention, production action information and yield monitoring data of equipment to be monitored in a preset time length are obtained; and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length. The invention does not need excessive parameter adjustment, can quickly train a health monitoring model as long as enough data are accumulated, has high automation degree of the detection process, saves a large amount of time and labor cost, and can accurately quantify the health degree, thereby selecting the most appropriate maintenance time.
Example 2
As shown in fig. 6, an embodiment of the present invention provides an apparatus health monitoring device, which is configured to perform the method provided in embodiment 1. The device includes:
the acquisition module 20 is configured to acquire production action information and yield monitoring data of the device to be monitored within a preset time duration;
and the monitoring processing module 21 is configured to process the production action information and the yield monitoring data through a pre-trained health monitoring model, and obtain a health degree curve of the device to be monitored within a preset time period.
The acquiring module 20 is configured to acquire the audio data generated by the device to be monitored within a preset time duration; and identifying the production audio data through a pre-established production monitoring system to obtain the production monitoring data of the equipment to be monitored within the preset time length.
The device also includes: the model training module is used for acquiring a training data set corresponding to the equipment to be monitored; the health monitoring model is trained according to the training data set.
The model training module is used for acquiring the production action information of the equipment to be monitored in a period of time and recording the production audio data of the equipment to be monitored in the period of time through the recording equipment; identifying and processing the production audio data in the period of time through a pre-established yield monitoring model to obtain yield monitoring data corresponding to the production action information; and determining the production action information and the yield monitoring data corresponding to the production action information as a training data set corresponding to the equipment to be monitored.
The model training module comprises:
the dividing unit is used for dividing the training data set into a training set and a verification set;
the training unit is used for training the OneClassSVM model through a training set;
the analysis unit is used for analyzing the verification set through the OneClassSVM model to obtain a health degree curve corresponding to the verification set;
the adjusting unit is used for adjusting the negative sample proportion parameters in the OneClassSVM model according to the verification set and the health degree curve corresponding to the verification set;
and the determining unit is used for determining the adjusted OneClassSVM model as a health monitoring model corresponding to the equipment to be monitored.
In the embodiment of the invention, production action information and yield monitoring data of equipment to be monitored in a preset time length are obtained; and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length. The invention does not need excessive parameter adjustment, can quickly train a health monitoring model as long as enough data are accumulated, has high automation degree of the detection process, saves a large amount of time and labor cost, and can accurately quantify the health degree, thereby selecting the most appropriate maintenance time.
Example 3
The embodiment of the invention provides computer equipment, which comprises a processor and a memory;
the memory stores executable instructions, and when the device runs, the processor executes the executable instructions stored in the memory to implement the device health monitoring method provided in embodiment 1.
The computer equipment executes the instruction through the processor to obtain the production action information and the yield monitoring data of the equipment to be monitored within a preset time length; and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length. The health monitoring model can be trained quickly as long as enough data are accumulated without excessive parameter adjustment, the automation degree of the detection process is high, a large amount of time and labor cost are saved, the health degree can be accurately quantified, and therefore the most appropriate maintenance time can be selected.
Example 4
The embodiment of the present invention provides a computer-readable storage medium, where executable instructions are stored in the computer-readable storage medium, and the executable instructions are executed by a computer to implement the method for monitoring the health degree of equipment provided in embodiment 1.
After a computer executable instruction stored in the computer storage medium is executed, acquiring production action information and yield monitoring data of equipment to be monitored within a preset time length; and processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length. The health monitoring model can be trained quickly as long as enough data are accumulated without excessive parameter adjustment, the automation degree of the detection process is high, a large amount of time and labor cost are saved, the health degree can be accurately quantified, and therefore the most appropriate maintenance time can be selected.
The device health degree monitoring device provided by the embodiment of the invention can be specific hardware on the device or software or firmware installed on the device. The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments. It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the foregoing systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided by the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the present invention in its spirit and scope. Are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (4)
1. A method for monitoring health of a device, the method comprising:
acquiring production action information and yield monitoring data of equipment to be monitored within a preset time length;
processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length;
the monitoring terminal converts audio data into two-dimensional frequency spectrum data of a time-frequency domain through Fourier decomposition, a process starting point and a process end point of each production are marked in the two-dimensional frequency spectrum data, the marked two-dimensional frequency spectrum data are divided into a plurality of training data according to a preset time interval, a convolutional neural network is trained according to the plurality of training data, and a yield monitoring model corresponding to the equipment to be monitored is established after the convolutional neural network is trained;
before the production action information and the production monitoring data are processed through a pre-trained health monitoring model, the method further comprises the following steps:
acquiring a training data set corresponding to the equipment to be monitored;
training a health monitoring model according to the training data set;
the acquiring of the training data set corresponding to the device to be monitored includes:
the method comprises the steps of obtaining production action information of the equipment to be monitored in a period of time, and recording production audio data of the equipment to be monitored in the period of time through recording equipment;
identifying and processing the production audio data in the period of time through a pre-established yield monitoring model to obtain yield monitoring data corresponding to the production action information;
determining the production action information and the yield monitoring data corresponding to the production action information as a training data set corresponding to the equipment to be monitored;
the training of the health monitoring model according to the training data set comprises:
dividing the training data set into a training set and a verification set;
training an OneClassSVM model through the training set;
analyzing the verification set through the OneClassSVM model to obtain a health degree curve corresponding to the verification set;
adjusting a negative sample proportion parameter in the OneClassSVM model according to the verification set and a health degree curve corresponding to the verification set;
and determining the adjusted OneClassSVM model as a health monitoring model corresponding to the equipment to be monitored.
2. An equipment health monitoring apparatus, the apparatus comprising:
the system comprises an acquisition module, a monitoring module and a monitoring module, wherein the acquisition module is used for acquiring production action information and yield monitoring data of equipment to be monitored within preset time; the monitoring terminal converts the audio data into two-dimensional frequency spectrum data of a time-frequency domain through Fourier decomposition, a process starting point and a process end point of each production are marked in the two-dimensional frequency spectrum data, the marked two-dimensional frequency spectrum data are divided into a plurality of training data according to a preset time interval, and a convolutional neural network is trained according to the plurality of training data; after a convolutional neural network is trained, a yield monitoring model corresponding to equipment to be monitored is established;
the monitoring processing module is used for processing the production action information and the yield monitoring data through a pre-trained health monitoring model to obtain a health degree curve of the equipment to be monitored within the preset time length;
the device further comprises:
the model training module is used for acquiring the production action information of the equipment to be monitored in a period of time and recording the production audio data of the equipment to be monitored in the period of time through the recording equipment; identifying and processing the production audio data in the period of time through a pre-established yield monitoring model to obtain yield monitoring data corresponding to the production action information; determining the production action information and the yield monitoring data corresponding to the production action information as a training data set corresponding to the equipment to be monitored; training a health monitoring model according to the training data set;
the model training module comprises:
the dividing unit is used for dividing the training data set into a training set and a verification set;
the training unit is used for training the OneClassSVM model through the training set;
the analysis unit is used for analyzing the verification set through the OneClassSVM model to obtain a health degree curve corresponding to the verification set;
the adjusting unit is used for adjusting the negative sample proportion parameters in the OneClassSVM model according to the verification set and the health degree curve corresponding to the verification set;
and the determining unit is used for determining the adjusted OneClassSVM model as a health monitoring model corresponding to the equipment to be monitored.
3. A computer device comprising a processor and a memory;
the memory stores executable instructions that, when executed by the computer device, are executed by the processor to implement the device health monitoring method of claim 1.
4. A computer-readable storage medium having stored thereon executable instructions that are executed by a processor to implement the device health monitoring method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810978149.5A CN109213034B (en) | 2018-08-27 | 2018-08-27 | Equipment health degree monitoring method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810978149.5A CN109213034B (en) | 2018-08-27 | 2018-08-27 | Equipment health degree monitoring method and device, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109213034A CN109213034A (en) | 2019-01-15 |
| CN109213034B true CN109213034B (en) | 2020-04-21 |
Family
ID=64989668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810978149.5A Active CN109213034B (en) | 2018-08-27 | 2018-08-27 | Equipment health degree monitoring method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109213034B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262950A (en) * | 2019-05-21 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Abnormal movement detection method and device based on many index |
| CN111310697B (en) * | 2020-02-17 | 2023-03-24 | 硕橙（厦门）科技有限公司 | Equipment operation period detection and health degree analysis method and device and storage medium |
| CN113008494A (en) * | 2021-02-01 | 2021-06-22 | 上海盛磊信息科技有限公司 | Radome structure health degree monitoring equipment and monitoring method based on deep learning |
| CN115295016B (en) * | 2022-07-29 | 2025-05-30 | 硕橙（厦门）科技有限公司 | A method, device, equipment and storage medium for monitoring equipment operation status |
| CN115270993B (en) * | 2022-08-23 | 2023-06-23 | 南通思诺船舶科技有限公司 | Diesel engine set state detection method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002054654A2 (en) * | 2001-01-08 | 2002-07-11 | Vextec Corporation | Method and apparatus for predicting failure in a system |
| US7020593B2 (en) * | 2002-12-04 | 2006-03-28 | International Business Machines Corporation | Method for ensemble predictive modeling by multiplicative adjustment of class probability: APM (adjusted probability model) |
| CN103262069A (en) * | 2010-12-21 | 2013-08-21 | 国际商业机器公司 | Method and system for predictive modeling |
| CN103439933A (en) * | 2013-08-13 | 2013-12-11 | 清华大学 | System and method for production process self-adaption monitoring using OCSVM |
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN107797537A (en) * | 2017-11-10 | 2018-03-13 | 上海第二工业大学 | A kind of prognostic and health management method applied to automatic production line |
| CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10610162B2 (en) * | 2016-05-31 | 2020-04-07 | Stmicroelectronics S.R.L. | Method for the detecting electrocardiogram anomalies and corresponding system |
-
2018
- 2018-08-27 CN CN201810978149.5A patent/CN109213034B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002054654A2 (en) * | 2001-01-08 | 2002-07-11 | Vextec Corporation | Method and apparatus for predicting failure in a system |
| US7020593B2 (en) * | 2002-12-04 | 2006-03-28 | International Business Machines Corporation | Method for ensemble predictive modeling by multiplicative adjustment of class probability: APM (adjusted probability model) |
| CN103262069A (en) * | 2010-12-21 | 2013-08-21 | 国际商业机器公司 | Method and system for predictive modeling |
| CN103439933A (en) * | 2013-08-13 | 2013-12-11 | 清华大学 | System and method for production process self-adaption monitoring using OCSVM |
| CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN107797537A (en) * | 2017-11-10 | 2018-03-13 | 上海第二工业大学 | A kind of prognostic and health management method applied to automatic production line |
Non-Patent Citations (1)
| Title |
|---|
| 基于One-Class AVM的机载塔康测距信息异常监测方法研究;李城梁;《现代导航》;20150615;第282-285页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109213034A (en) | 2019-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213034B (en) | Equipment health degree monitoring method and device, computer equipment and readable storage medium | |
| CN108731923B (en) | Fault detection method and device for rotary mechanical equipment | |
| EP2797034B1 (en) | Event analyzer and computer-readable storage medium | |
| JP7664918B2 (en) | Abnormal modulation cause identification device, abnormal modulation cause identification method, and abnormal modulation cause identification program | |
| US11657121B2 (en) | Abnormality detection device, abnormality detection method and computer readable medium | |
| CN113988325A (en) | Power system fault early warning method and device, terminal equipment and storage medium | |
| CN107942956B (en) | Information processing device, information processing method, information processing program, and recording medium | |
| US20160196175A1 (en) | Information processing system, information processing method, and program | |
| CN112329183B (en) | Equipment state data acquisition method and device, electronic equipment and storage medium | |
| CN111954857A (en) | Determination of the cause of the abnormal event | |
| CN116975639B (en) | Abnormality prevention and control system and method for equipment | |
| JP7604486B2 (en) | Abnormal modulation cause identification device, abnormal modulation cause identification method, and abnormal modulation cause identification program | |
| CN111984442A (en) | Method and device for detecting abnormality of computer cluster system, and storage medium | |
| WO2017150286A1 (en) | System analyzing device, system analyzing method, and computer-readable recording medium | |
| JP2009110262A (en) | Filter device, filtering method for filter device and filtering program | |
| CN112398706A (en) | Data evaluation standard determination method, device and storage medium, electronic equipment | |
| CN118914733B (en) | A stability evaluation method for chip varistors based on polarity reversal test | |
| JP7664919B2 (en) | Abnormal modulation cause identification device, abnormal modulation cause identification method, and abnormal modulation cause identification program | |
| EP4160338A1 (en) | Abnormal modulation cause display device, abnormal modulation cause display method, and abnormal modulation cause display program | |
| CN118013443B (en) | Online real-time vacuum dry pump abnormality detection method based on generation model algorithm | |
| CN113052272A (en) | Abnormity detection method and device, electronic equipment and storage medium | |
| CN117204863B (en) | Sleep state staging method and system based on single-channel EEG and acceleration | |
| JP7664920B2 (en) | Abnormal modulation cause identification device, abnormal modulation cause identification method, and abnormal modulation cause identification program | |
| CN115906008A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN115648592A (en) | Method and system for evaluating running state of extruder and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yang Zongtou Inventor after: Tian Wenjing Inventor after: Tan Yi Inventor after: Zhuang Yan Inventor after: Chen Rui Inventor after: Huang Zhaoxian Inventor after: Wang Yougan Inventor after: Li Bohan Inventor before: Yang Zongtou Inventor before: Tian Wenjing Inventor before: Tan Yi Inventor before: Zhuang Yan Inventor before: Chen Rui Inventor before: Huang Zhaoxian Inventor before: Wang Yougan |
|
| CB03 | Change of inventor or designer information |