KR101840419B1 - System and method for predicting fault of elements in skin pass mill and leveler - Google Patents

Abstract

The system includes a data collecting unit for collecting operating factors of a roughing mill and a shape correcting unit of a rough rolling mill during a cold rolling and plating process, according to an embodiment of the present invention; Based on the fluctuation characteristics of the above factors, a data mining technique based on Big Data is used to derive operating conditions for the occurrence of faults, and the occurrence rate of major defects that can occur in the roughing mill and the shape calibrator An equipment fault diagnosis predicting unit for diagnosing and predicting a facility fault occurrence rate according to the incidence rate of major faults and providing alarms and operation guides to a user; And an evaluation unit for evaluating suitability of the user to the provision of the operation guide and availability of the fault prediction data.

Description

FIELD OF THE INVENTION The present invention relates to a system and method for improving the quality of a rolling mill and a shape correcting apparatus,

The present invention relates to a system and method for maintenance and repair of a roughing mill and a shape correcting apparatus.

In the maintenance of the SKIN PASS MILL and LEVLER equipment of the cold rolling and plating line, performance deterioration due to wear, impact fatigue, contamination and aging occurs over time. In the event of a failure of the equipment, this may cause the product to fail or lead to the interruption of rolling production. The facility maintenance method is divided into preventive maintenance, predictive maintenance, condition based maintenance, breakdown maintenance, and reactive maintenance. Maintenance, etc., but these have had fundamental limitations in predicting and preventing the occurrence of facility failure.

Preventive maintenance, which is a proactive maintenance, is an empirical precautionary maintenance rather than a failure prediction because the components are not damaged at regular intervals. It takes considerable time for the overhaul process when component damage occurs within the maintenance period , Leading to a large production loss. In the case of Predictive Maintenance and Condition Based Maintenance, it is also impossible to avoid component failures caused by unexpected overloads during the operation of the equipment. In case of components with sudden failure modes, It is impossible to provide.

In addition, the breakdown maintenance and the passive maintenance method (Reactive Maintenance), which is a reactive maintenance method, is a type of maintenance that performs repair replacement after a facility has been deteriorated or stopped (broken) Down Time, which causes a loss due to production disruption.

Korean Patent Publication No. 10-2014-0038265 (Apr. 28, 2014)

It is an object of the present invention to classify facility defect factors, which occur frequently during operation, into quality data-based data mining for temper rolling mills and shape correcting machine facilities, which are important facilities directly connected to product quality in cold rolling and plating processes, By monitoring and analyzing in real time using the technique, it is possible to predict the occurrence condition of defects and to recognize the occurrence of facility defects early so that the operator can cope with them early. The present invention provides a system and method for preventing equipment failure of a temper rolling mill and a shape correcting machine.

The rough rolling mill and the shape correcting device failure prevention maintenance system according to an embodiment of the present invention includes a data collecting part for collecting operating factors of a rough rolling mill (skin pass mill) and shape factors of a shape calibrator during a cold rolling and plating process, ; Based on the variation trend of each of the operating factors of the skin pass mill and the variation trend of each of the operating factors of the shape calibrator, a data mining technique based on Big Big Data is utilized The operating conditions for the defect occurrence of each of the skin pass mill and the shape calibrator are derived and the major defect occurrence rates that can be generated in the skin pass mill and the shape calibrator And an equipment failure diagnosis predicting unit for diagnosing and predicting a facility failure rate according to the incidence rate of major faults and providing an alarm and operation guide to the user; And an evaluation unit for evaluating suitability of the user to the operation guide provided by the facility fault diagnosis predicting unit and utilization availability of the fault prediction data in the future, And a variation factor calculator for calculating a variation between operation factors collected in each of the time zones during the N passes of the shape calibrator (Leveler); And predicting major faults to be generated in the skin pass mill and the shape calibrator during the N pass and a facility fault incidence due to the major faults based on the magnitude and the increment of the variation, And a guide providing section for predicting the facility failure rate and providing guidance to the facility, wherein the facility failure rate prediction and guide providing section provides different operation maintenance guides according to the facility failure rate according to the major defect, The providing section predicts a facility failure time point based on a distribution chart of major defect occurrence rates generated in the roughing mill and the shape correcting machine during the N passes calculated based on the increase amount of the variation, And the surface roughness, and the shape correcting device (Level er) are the wave and bend, vibration, and rotation number, and the facility fault diagnosis predicting unit predicts the equipment fault diagnosis unit based on the form data (wave and bending chattering mark, (Daily inspection, fine diagnosis period, and facility replacement history), it is predicted that the major fault occurrence rate and the facility fault due to the major fault occurrence rate are considered.

The method for predicting facility failure of a roughing mill and a shape straightener according to an embodiment of the present invention is characterized in that in a data collecting unit, operating factors of a rough rolling mill (skin pass mill) and shape factors of a shape calibrator during a cold rolling and plating process Collecting operational factors; The equipment fault diagnosis predicting unit derives operating conditions for occurrence of defects by utilizing a data mining technique based on Big Data based on the fluctuation property of the operating factors, And a facility fault diagnosis prediction step of diagnosing and predicting a facility fault incidence rate according to the main fault occurrence rate that can be generated in the shape correcting unit and an alarm and operation guide to a user; And an evaluation step of assessing suitability of the user to the operation guide provided in the facility fault diagnosis prediction step and evaluation of utility as future fault prediction data in the evaluation part, Calculating a variation between the operation factors collected in the time zone during the N passes of the skin pass mill and the shape calibrator of the cold rolling and plating process in the variation calculation unit; And the major defect and major defect occurrence rate of the constituent facilities of each of the skin pass mill and the shape calibrator which can be generated according to the magnitude of the variation and the amount of variation in the facility failure prediction and guide providing, Estimating a facility failure rate to be generated in the roughing mill and the shape correcting machine during an N pass based on a defect occurrence rate and providing an optimal operation guide; And estimating an equipment failure time point based on a distribution chart of major defect occurrence rates generated in the roughing mill and the shape correcting machine during N passes calculated on the basis of the operating frequency of the rough rolling mill, And surface roughness, and the operating factors of the shape calibrator are wave and half And the equipment failure diagnosis predicting unit predicts the facility fault diagnosis unit based on the form data (wave and bending chattering mark), irregular data (daily inspection, precision diagnosis time, facility Replacement history) of the main faults and the main faults incidence rate.

The solution of the above-mentioned problems does not list all the features of the present invention. Various means for solving the problems of the present invention can be understood in detail with reference to the specific embodiments of the following detailed description

According to an embodiment of the present invention, the facility failure detection and maintenance system of the skin pass mill and the shape calibrator can continuously monitor the variation of the major operating factors and can perform data mining And it is possible to predict the anomalous signs before the occurrence of equipment failure in the cold rolling and plating process of the skin pass mill and shape calibrator. .

It is possible to suppress the incidence rate of equipment failures of the rough rolling mill (skin pass mill) and the shape calibrator (leveler) of the cold rolling and plating process in advance, and to quickly change the equipment due to the equipment failure, It is possible to reduce the incidence of defects by selecting the upper and lower limit values through analysis of abnormal factors by data. In addition, there is an advantage that it is possible to prevent production rate decrease and large accident in advance due to shutdown due to facility failure.

FIG. 1 is a block diagram showing a system for predicting a facility failure of a roughing mill and a shape correcting apparatus for a cold rolling and plating process according to an embodiment of the present invention. Referring to FIG.
FIG. 2 is a flowchart for explaining a cold rolling and plating process facility failure prevention method according to an embodiment of the present invention. Referring to FIG.
FIG. 3 is an example of deriving operating conditions for occurrence of defective cases by applying a data mining technique using Big Data.
4 is a diagram illustrating an exemplary computing environment in which one or more embodiments disclosed herein may be implemented.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art to which the present invention pertains.

The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification. Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when an element is referred to as " including " an element, it is to be understood that the element may include other elements as well as other elements, And does not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.

Prior to describing the present invention, the characteristics of the temper rolling mill and the shape calibrator used in the cold rolling and plating processes are generally different from those developed for the first time and after a certain period of time after the equipment is started. Abrasion, squeezing, deformation, and fatigue, and the performance of the machine is deteriorated. This causes destabilization of the rolling process and deteriorates the performance and reliability of the product.

Therefore, the reliability of the equipment and the system may be deteriorated due to the degradation of the performance and reliability of the product. However, there is no way to directly and quickly grasp the reliability degradation of such equipment and systems. The engineer who manages and operates the system has only knowledge about the operation of the equipment and the setting of the parameters of the equipment, but it is difficult to know how the reliability of the equipment and the system changes.

In other words, in order to grasp the abnormality of the rough rolling mill and shape calibrator during the cold rolling and plating process and to grasp the reliability, it is necessary to accumulate a large number of process parameters arising from the manufacturing process in a database, and to use the data mining The dynamic operation and construction of the rolling process control which can predict whether or not the rolling process can be predicted.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will now be described in detail with reference to the accompanying drawings, in which: FIG. 1 is a schematic view of a roughing mill according to an embodiment of the present invention;

FIG. 1 is a block diagram illustrating a roughing mill and a shape correcting device failure prevention maintenance system according to an embodiment of the present invention. Referring to FIG.

1, an equipment failure prediction system 100 of a roughing mill and a shape correcting machine according to an embodiment of the present invention includes a data collecting unit 200, an equipment failure diagnosis predicting unit 300, a database 400 , And an evaluation unit 500. [

The data collecting unit 200 collects the operating factors of the roughing mill and the shape correcting unit during the cold rolling and plating processes.

The data collecting unit 200 collects key operating factors according to the operation of each of the facilities from sensors that sense the operation of equipment included in a skin pass mill and a shape calibrator.

More specifically, the data collecting unit 200 may be a storage medium that collects and collects the time-dependent operating factors of the temper rolling mill during the N passes of the cold rolling and plating processes.

Also, the data collecting unit 200 may be a storage medium storing operating factors of the shape calibrator operated during N passes of the cold rolling and plating process.

Also, the data collecting unit 200 may be a storage medium storing normal operating factors of the roughing mill and the shape calibrator operated during N passes of the roughing mill and the shape calibrator.

Major defects and data acquisition plans according to the type of operating factors of the temper rolling mill are as follows.

Major defects of the temper rolling mill according to the vibration of the first operating factor are chattering marks, and the tensile bridle rolls, work rolls and back up rolls of the front and rear stages A vibration sensor is installed at each position of the chock to measure the vibration value.

The main defects according to the second operating factor reduction amount of the temper rolling mill are wave, bending and drawing defects. The rolls are a roll force cylinder, a load cell of a bender cylinder, Install a pressure gauge to measure the force exerted on the strip.

The main defect of the quality rolling mill according to the third operation factor foreign matter contamination is the contamination degree such as the transfer of foreign substance on the surface of the material, and the density / cleanliness value is measured by installing the meter of the wet tank, the thermometer and the density meter.

The fourth failure factor of the temper rolling mill depends on the surface roughness of the strip surface defects and the elapsed time of the roll replacement time, which has a problem in the use of the strip of the subsequent process. Therefore, the on-line illuminometer is installed to measure and monitor the surface roughness of the work roll.

Fifth operation factor of the temper rolling mill The major defect according to the number of revolutions of the work roll is the roll mark and the number of revolutions is measured by installing a pulse generator on the main work roll.

The following are major deficiencies and data acquisition plans according to the types of operational factors of the geometric calibrator.

The main defects according to the first operation parameter Wave and bend of the shape calibrator are wave and bending. The position sensor is installed at each position of the roll cassette and the position level is detected. Mesh (Intermesh) amount is received.

The main defect due to vibration of the second working parameter of the shape calibrator is a chattering mark. The vibration value is measured by installing a vibration sensor at each position of a roll cassette, a housing, and a reducer.

The major defect according to the number of revolutions of the third operation of the shape calibrator is a roll mark, and a pulse generator is installed on each main roll to measure the number of revolutions of the roll.

Next, the equipment fault diagnosis predicting unit 300 applies and analyzes a data mining technique to the big data of the database 400 on the basis of the fluctuation property of the operational factors, Chattering Mark, fluctuation of operating factors by defects such as defective drawing of foreign matter), as well as atypical data (daily inspection, precise diagnosis time, facility replacement history) A function of diagnosing and predicting a facility failure according to the incidence rate of major defects that can occur in the rolling mill, the shape correcting device, and the major defect occurrence rate.

More specifically, the facility fault diagnosis predicting unit 300 may include a factor calculation unit 310, an equipment failure prediction unit, and a guide providing unit 320.

The operating factor variation calculator 310 calculates the variation between the operating factors generated in the temper rolling mill and the shape calibrator during the N pass period of the temper rolling process.

The number of rotations of the first work roll WR of the temper rolling mill at time t1 of the N pass process is A1 and the number of revolutions of the first work roll WR of the temper rolling mill at the time t1 of the N pass process of normal operation factor, when the speed is A2, the variation (△ a) of the (rotation of the first work roll) operating parameters of the rolling mill may be a skin-pass A1-A2.

As another example of the calculation of the variation, at the time point t2 of the N pass process, the intermesh amount according to the descending force of the shape correcting device is M1, and at the time point t2 of the N pass process of the normal operation factor, When the intermesh amount is M2, the variation ( DELTA M) of the operating factor (intermeshed amount) of the shape calibrator may be M1-M2.

As another example of the calculation of the variation, when the vibration amount of the roll cassette of the shape calibrator is V1 at the time point t3 of the N pass process and at the time point t3 of the N pass process of the normal operation factor, When the amount of vibration of the cassette is V2, the variation ? V of the operating factor (amount of vibration of the roll cassette) of the shape calibrator may be V1-V.

The facility failure prediction and guide providing unit 320 predicts a major defect occurrence rate of the roughing mill and the shape correcting apparatus that can be generated according to the magnitude of the variation.

The facility failure prediction and guide providing unit 320 predicts a major defect occurrence rate according to the magnitude of the change based on the operation time.

The facility failure prediction and guide providing unit 320 may use multiple linear regression (MLR), partial linear regression (PLS), RIDGE, and LASSO to derive defect occurrence operation conditions using the operation big data of the database 400 Predicts the rate of facility failure using one or more of the Least Absolute Shrinkage and Selection Operator, Smoothly Clipped Absolute Deviation (SCAD), Minimax Concave Penalty (MCP), Support Vector Machine (SVM), Bagging, Boosting and Random Forest algorithms. .

In addition, the facility failure prediction and guide providing unit 320 may calculate a main fault incidence rate to be generated in the skin pass mill and the shape calibrator during an N pass calculated based on the increase amount of the variation, Based on the fault incidence rate, predict the facility failure rate and the facility failure prediction time.

More specifically, the distribution charts of the major defect occurrence rates generated during the N-path predicted by the equipment failure prediction and guide providing unit 320 are analyzed through a data mining algorithm using the big data of the database, Estimate the failure rate of the facilities based on the result of the distribution.

The data mining algorithm applied to the facility failure prediction and guide providing unit 320 may include a classification algorithm for predicting one or more discontinuous variables based on other characteristics of the data set, A regression algorithm that predicts one or more contiguous variables, a segmentation algorithm that divides data into groups or clusters of similar items of property, and a connection algorithm that finds a correlation between various characteristics in the data set.

In addition, it may further include a decision tree algorithm, an artificial neural network algorithm, and a cluster analysis algorithm.

For reference, data mining refers to a series of analysis processes that extract useful knowledge by searching, finding and modeling relationships, patterns, rules, etc. existing in these data from a large amount of data.

The functions of data mining include Classification, Estimation, Predecation, Affinity Grouping, Clustering, and Descriotion.

The process of extracting data from data mining can be divided into ① sampling ② exploration ③ modification / modification ④ modeling ⑤ evaluation.

(1) Sampling is the process of extracting an appropriate amount of sample from raw data; (2) Exploring is the search of various data to obtain basic information such as basic statistical data, frequency distribution tables, average, variance, (3) Modification / conversion is a process of transforming data through conversion, quantification, and grouping of variables for efficient use of data. (4) Modeling is the process of using appropriate techniques (5) Assessment is the process of evaluating the reliability and usefulness of the results of modeling.

On the other hand, the neural network is proposed in consideration of a physiological model of a neuron, which is a basic unit of the human cerebrum, and includes a node that receives input from the outside and a node that performs output to the outside, In the presence of a hidden node, weights are given to the connection between the node and the node, so that the value of one node is multiplied with the connection weight and transmitted to the other node.

On the other hand, in the process facility management system, the neural network can be mainly used for forecasting due to abnormal operation of the equipment. It is necessary to derive the important parameters of the plant operation in the process and how these variables affect the final yield And learning about it can help to predict how the final yield will change if it is changed to a new environment or when new variables are added.

A decision tree is used to determine which class a new data belongs to in a predefined class by a rule that classifies the class. In order to create a rule, it is necessary to have the data in which the class is defined, and it is necessary to consider the algorithm for generating the rule and the form in which the derived rule is to be displayed.

Also, pattern analysis using clustering can be utilized. Unlike classification, clustering does not have a predefined class in data, and groups data of similar characteristics according to a predetermined algorithm. It is possible to analyze the characteristics of the process pattern and the operation pattern of the equipment through such clustering and to know statistical characteristics according to the process pattern and the operation pattern of the equipment, Can be identified.

The database 400 is a medium that stores Big Data and is a medium in which fixed data (wave and bump chattering mark, fluctuation of operating factors for defects such as embossed foreign matters) and irregular data , Precise diagnosis timing, and facility replacement history).

Next, the facility failure prediction and guide providing unit 320 provides an optimal operation guide according to the occurrence rate of the facility failure.

The evaluation unit 500 evaluates whether or not the operation guide is proper as data of a future facility fault diagnosis.

FIG. 2 is a flowchart illustrating a method of predicting an equipment failure of a roughing mill and a shape calibrator according to an embodiment of the present invention. Referring to FIG.

Referring to FIG. 2, the method for predicting facility equipment of a roughing mill and a shape calibrating apparatus (S700) according to an embodiment of the present invention includes first sensing the operation of constituent facilities in a roughing mill and a shape calibrator in a data collecting unit 200 (S710) the main operating factors according to the operation of each of the constituent facilities from the sensors.

Thereafter, in the equipment fault diagnosis predicting unit 300, a data mining technique is applied to the big data of the database 400 based on the magnitude of the fluctuation of the operating factors of the constituent facilities and the variation of the variation, (S720), which diagnoses and predicts an equipment failure of the structural equipment according to the incidence rate of major defects that can occur in the roughing mill and the shape correcting machine and the incidence rate of the major defects by deriving the conditions.

More specifically, in operation S720, the operation factor variation calculating unit 310 calculates a variation between the operating factors generated in the roughing mill and the shape correcting apparatus during the N pass period of the rough rolling process (S721).

The number of rotations of the first work roll WR of the temper rolling mill at time t1 of the N pass process is A1 and the number of revolutions of the first work roll WR of the temper rolling mill at the time t1 of the N pass process of normal operation factor, when the speed is A2, the variation (△ a) of the (rotation of the first work roll) operating parameters of the rolling mill may be a skin-pass A1-A2.

As another example of the calculation of the variation, at the time point t2 of the N pass process, the intermesh amount according to the descending force of the shape correcting device is M1, and at the time point t2 of the N pass process of the normal operation factor, When the intermesh amount is M2, the variation ( DELTA M) of the operating factor (intermeshed amount) of the shape calibrator may be M1-M2.

As another example of the calculation of the variation, when the vibration amount of the roll cassette of the shape calibrator is V1 at the time point t3 of the N pass process and at the time point t3 of the N pass process of the normal operation factor, When the amount of vibration of the cassette is V2, the variation ? V of the operating factor (amount of oscillation of the roll cassette) of the shape calibrator may be V1-V2.

Major defects and data acquisition plans according to the types of operating factors of the temper rolling mill are as follows.

The major defect due to the vibration of the first rolling mill of the temper rolling mill is the chattering mark. The vibration value is measured by installing a vibration sensor at each position of the tension bridle roll, work roll and back up roll of the front and rear end.

Waves, bends and draw defects are major defects according to the second operating factor reduction of the temper rolling mill. Load cell or pressure gauge of Roll Force Cylinder, Bender 'Cylinder is installed and the force applied to the strip is measured.

The main defect of the quality rolling mill according to the third operation factor foreign matter contamination is the contamination degree such as the transfer of foreign substance on the surface of the material, and the density / cleanliness value is measured by installing the meter of the wet tank, the thermometer and the density meter.

The fourth failure factor of the temper rolling mill depends on the surface roughness of the strip surface defects and the elapsed time of the roll replacement time, which has a problem in the use of the strip of the subsequent process. Therefore, the on-line illuminometer is installed to measure and monitor the surface roughness of the work roll.

The main defect of the temper rolling mill according to the number of revolutions of the fifth working factor roll of the rolling mill is the roll mark, and a pulse generator is installed in the main work roll to measure the number of revolutions.

The following are major defects and data acquisition plans according to the type of operation factor of the geometric calibrator.

The major defects according to the first operation parameter Wave and bend of the shape calibrator are wave and bending. The position sensor is installed at each position of the roll cassette, and the level is sensed and interface with the installed PLC Intermesh amount is received.

The main defect of the second calibration factor vibration of the shape calibrator is chattering mark, and the vibration value is measured by installing a vibrator sensor at each position of Roll Cassette, Housing, and Reducer.

The main defect according to the number of revolutions of the third operation factor of the shape calibrator is a roll mark, and a pulse generator is installed on each main roll to measure the number of revolutions of the roll.

Then, the equipment failure prediction and guide providing unit 320 calculates a major defect occurrence rate of the roughing mill and the shape correcting machine that can be generated according to the magnitude and the increase amount of the variation based on the operation big data of the database 400 (S722) to estimate the incidence of facility failure and to provide a guide for operation.

In this case, the facility failure prediction and guide providing unit 320 may be configured to perform the facility failure prediction and the guide providing unit 320 in the form of multiple linear regression (MLR), partial least squares (PLS), RIDGE, minimum absolute shrinkage and selection operator Minimax Concave Penalty), SVM (Support Vector Machine), Bagging, Boosting, and Random Forest.

Next, the evaluating unit 500 evaluates whether or not it is appropriate after the user's confirmation of the abnormality symptom determination and the guide presentation (S730). It can be used as an indicator of the anomaly indication for the same condition in the future depending on the judgment of the user's suitability.

Therefore, according to one embodiment of the present invention, the roughing mill and the shape correcting device equipment failure prevention maintenance system can continuously monitor the change trend of the major operating factors in real time using the data mining technique using the big data, And an advantage that the abnormality symptom can be predicted before the equipment failure of the shape correcting device.

It is possible to suppress the occurrence rate of the facility failure of the rough rolling mill and the shape correcting machine in advance and to rapidly change the equipment according to the equipment failure and to stop the operation due to the equipment failure and to reduce the production rate, Can be prevented in advance.

FIG. 3 shows an example of a process of analyzing data using CART, which is one of the data mining techniques. More specifically, when an abnormal symptom that is outside normal operating conditions is detected, And then classifies or clusters a number of operating conditions of the occurrence of the abnormality in the order of association analysis, visualization, and summarization, This is an example of predicting a bad operating condition by finding a decision variable that affects a variable.

FIG. 4 is a diagram illustrating an exemplary computing environment in which one or more embodiments disclosed herein may be implemented, and is illustrative of a system 1000 including a computing device 1100 configured to implement one or more of the embodiments described above. / RTI >

For example, the computing device 1100 may be a personal computer, a server computer, a handheld or laptop device, a mobile device (mobile phone, PDA, media player, etc.), a multiprocessor system, a consumer electronics device, A distributed computing environment including any of the above-described systems or devices, and the like. The computing device 1100 may include at least one processing unit 1110 and memory 1120. [ The processing unit 1110 may include, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, an application specific integrated circuit (ASIC), a field programmable gate array And may have a plurality of cores. The memory 1120 can be a volatile memory (e.g., RAM, etc.), a non-volatile memory (e.g., ROM, flash memory, etc.) or a combination thereof.

In addition, the computing device 1100 may include additional storage 1130. Storage 1130 includes, but is not limited to, magnetic storage, optical storage, and the like. The storage 1130 may store computer readable instructions for implementing one or more embodiments as disclosed herein, and other computer readable instructions for implementing an operating system, application programs, and the like. The computer readable instructions stored in storage 1130 may be loaded into memory 1120 for execution by processing unit 1110.

In addition, computing device 1100 may include input device (s) 1140 and output device (s) 1150. Here, input device (s) 1140 may include, for example, a keyboard, a mouse, a pen, a voice input device, a touch input device, an infrared camera, a video input device, or any other input device. Also, output device (s) 1150 can include, for example, one or more displays, speakers, printers, or any other output device. In addition, computing device 1100 may use an input device or output device included in another computing device as input device (s) 1140 or output device (s) 1150. [

The computing device 1100 may also include communication connection (s) 1160 that allow the computing device 1100 to communicate with other devices (e.g., computing device 1300). (S) 1160 may include a modem, a network interface card (NIC), an integrated network interface, a radio frequency transmitter / receiver, an infrared port, a USB connection or other Interface. Also, the communication connection (s) 1160 may include a wired connection or a wireless connection.

Each component of the computing device 1100 described above may be connected by various interconnects (e.g., peripheral component interconnect (PCI), USB, firmware (IEEE 1394), optical bus architecture, etc.) And may be interconnected by the network 1200.

As used herein, the terms "component," "component," and the like generally refer to a computer-related entity, which is hardware, a combination of hardware and software, software, or software in execution.

For example, an element may be, but is not limited to being, a processor, an object, an executable, an executable thread, a program and / or a computer running on a processor. For example, both the application running on the controller and the controller may be components. One or more components may reside within a process and / or thread of execution, and the components may be localized on one computer and distributed among two or more computers.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

100: Equipment failure prevention system of quality rolling mill and shape calibrator
200: Data collecting unit
300: Equipment fault diagnosis prediction unit
310: Operation factor variation calculation unit
320: Equipment Prediction and Guide Offering
400: Database (Data Base)
500: Evaluation unit

Claims (9)

A data collecting unit for collecting operating factors of a skin pass mill during a cold rolling and plating process and operation parameters of a shape calibrator;
Based on the variation trend of each of the operating factors of the skin pass mill and the variation trend of each of the operating factors of the shape calibrator, a data mining technique based on Big Big Data is utilized The operating conditions for the defect occurrence of each of the skin pass mill and the shape calibrator are derived and the major defect occurrence rate that can be generated in the skin pass mill and the shape calibrator And an equipment failure diagnosis predicting unit for diagnosing and predicting a facility failure rate according to the incidence rate of major faults and providing an alarm and operation guide to the user; And
And an evaluation unit for evaluating whether the user is suitable for the operation guide provided by the facility fault diagnosis predicting unit,
The facility fault diagnosis predicting unit
A variation factor calculator for calculating a variation between operating factors collected in each of the time zones during the N passes of the skin pass mill and the shape calibrator; And
Predicting the major faults to be generated in the skin pass mill and the shape calibrator during the N pass and the facility failure rate due to the main faults based on the magnitude of the variation and the increase in the variation, And a guidance providing section for predicting the facility occurrence rate,
The facility failure occurrence rate prediction and guide providing unit may provide different operation maintenance guides according to the occurrence rate of the facility failure according to the main flaw,
The facility failure rate estimation and guidance providing unit
Predicting an equipment failure time point based on a distribution chart of major defect occurrence rates generated in the roughing mill and the shape correcting machine during N passes calculated on the basis of the increase amount of the variation,
The operating factors of the skin pass mill are vibration, a reduction amount, a foreign matter deposition, and a surface roughness. The operating factors of the shape calibrator are wave and bending, vibration,
The facility fault diagnosis predicting unit may calculate the facility fault diagnosis predicting result by taking into consideration the regular data (wave and bending chattering mark, fluctuation of the operating factor of each fault of the draw defective foreign matter) and atypical data (daily inspection, A system for predicting facility failure of a roughing mill and a shape correcting machine for predicting equipment failure due to a major defect occurrence rate and an occurrence rate of the major defect.
delete delete delete delete delete delete A method using an equipment failure prediction maintenance system of a roughing mill and a shape correcting machine according to claim 1,
A collecting step of collecting operating factors of a skin pass mill and a condition factor of a shape calibrator during a cold rolling and plating process in a data collecting part;
The equipment fault diagnosis predicting unit derives operating conditions for occurrence of defects by utilizing a data mining technique based on Big Data based on the fluctuation property of the operating factors, And a facility fault diagnosis prediction step of diagnosing and predicting a facility fault incidence rate according to the main fault occurrence rate that can be generated in the shape correcting unit and an alarm and operation guide to a user; And
And an evaluation step of evaluating suitability of the user to the operation guide provided in the facility fault diagnosis prediction step and evaluation of utility as future fault prediction data in the evaluation part,
The facility fault diagnosis prediction step
Calculating a variation between the operation factors collected in each of the time zones during the N passes of the skin pass mill and the shape calibrator of the cold rolling and plating process in the operation factor variation calculating unit; And
The major defect and major defect occurrence rate of the constituent facilities of each of the skin pass mill and the shape calibrator which can be generated according to the magnitude of the variation and the increase amount of the variation in the facility failure prediction and guide providing are calculated, Estimating an incidence rate of facility failures to be generated in the temper rolling mill and the shape calibrator during an N pass based on the incidence rate to provide an optimal operation guide,
The facility failure rate estimation and guidance providing unit
Predicting an equipment failure time point based on a distribution chart of major defect occurrence rates generated in the roughing mill and the shape correcting machine during N passes calculated on the basis of the increase amount of the variation,
The operating factors of the skin pass mill are vibration, a reduction amount, a foreign matter deposition, and a surface roughness. The operating factors of the shape calibrator are wave and bending, vibration,
The facility fault diagnosis predicting unit may calculate the facility fault diagnosis predicting result by taking into consideration the regular data (wave and bending chattering mark, fluctuation of the operating factor of each fault of the draw defective foreign matter) and atypical data (daily inspection, A method for predicting facility failure of a roughing mill and a shape correcting machine for predicting equipment failure due to a major defect occurrence rate and the occurrence rate of the main defect.
delete

Images