A remote fault diagnosis method and system for a stacker-reclaimer based on bus communication

Abstract

The application discloses a kind of based on bus communication's stacker-reclaimer remote fault diagnosis method and system, it is related to coal conveying system technical field, including: by installing sensor and data acquisition device on stacker-reclaimer, the operating parameter of equipment is collected in real time;Data is transmitted to auxiliary machine control room using Profibus bus communication mode, builds fault diagnosis platform on auxiliary machine control room server, realizes fault early warning and analysis, provides fault information.The remote fault diagnosis method based on bus communication provided in the application improves the reliability of equipment, reduces the failure rate, and ensures the stable operation of the coal conveying system. Remote monitoring and fault diagnosis are realized, labor cost is effectively reduced, and work efficiency is improved. The fault elimination time is shortened, the impact of equipment downtime on production is minimized to the greatest extent, and the overall operation efficiency of the system is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal conveying system, in particular to a remote fault diagnosis method and system of stacker-reclaimer based on bus communication. BACKGROUND

[0002] The stacker-reclaimer of circular coal yard is a key equipment in the coal conveying system, and undertakes the tasks of unloading coal and loading coal, and its running condition directly affects the stability and reliability of the whole system.

[0003] However, the stacker-reclaimer is controlled by PLC, and other equipment of the coal conveying system is controlled by DCS, and the stacker-reclaimer is isolated from the coal conveying system, forming an information island. The running personnel cannot accurately monitor the running state of the equipment in real time, and it is difficult to discover potential faults in real time, which may cause delay and expansion of faults; when the stacker-reclaimer fails, it is difficult to provide information support for the maintenance personnel, and the fault handling time is prolonged; at the same time, the fault diagnosis is highly dependent on experienced technical personnel, and there is human judgment error, which seriously affects the normal operation of the equipment and reduces the efficiency of the whole system. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] To solve the above technical problems, the present application provides the following technical scheme: a remote fault diagnosis method of stacker-reclaimer based on bus communication, comprising:

[0006] By installing sensors and data acquisition devices on the stacker-reclaimer, the running parameters of the equipment are collected in real time;

[0007] The data is transmitted to the auxiliary machine control room by using Profibus bus communication mode, a fault diagnosis platform is built on the server in the auxiliary machine control room, fault early warning and analysis are realized, and fault information is provided.

[0008] As a preferred scheme of the remote fault diagnosis method of stacker-reclaimer based on bus communication, the sensor comprises a material taking scraper motor current transformer and voltage transformer, a material stacking rotation angle encoder, a material taking rotation angle encoder, and a material taking pitch angle encoder.

[0009] The data acquisition device comprises a material stacking rotary frequency converter, a material taking rotary frequency converter, a material taking pitch frequency converter, and an S7-300.

[0010] As a preferred scheme of the remote fault diagnosis method of the stacker-reclaimer based on bus communication, the operating parameters include stacker rotating motor current, voltage / circuit breaker and contactor state, reclaimer rotating motor current, voltage / circuit breaker and contactor state, reclaimer luffing motor current, voltage / circuit breaker and contactor state, reclaimer flight motor current, voltage / circuit breaker and contactor state, stacker belt motor current, voltage / circuit breaker and contactor state, stacker rotating angle encoder, reclaimer rotating angle encoder, reclaimer luffing angle encoder data, reclaimer flight machine front material position data, reclaimer flight machine middle material position data, reclaimer flight machine rear material position data, pull rope switch state, tearing switch state, deviation switch state, and each action instruction.

[0011] As a preferred scheme of the remote fault diagnosis method of the stacker-reclaimer based on bus communication, the Profibus bus communication mode includes stacker rotating frequency converter, reclaimer rotating frequency converter, reclaimer luffing frequency converter, Siemens S7-300, IM365, CP342-5, DP bus, OLM, optical fiber transceiver, DCS server, DCS engineer station, and DCS operator station.

[0012] The data transmission includes adding a Profibus-DP communication module CP342-5 to the stacker-reclaimer PLC rack, performing I / O virtual address and actual PLC address mapping, and performing communication between the CP342-5 and the DCS after the CP342-5 reads CPU address data, so as to realize data transmission between the DCS and the stacker-reclaimer PLC.

[0013] The master-slave communication interconnection device is configured between the stacker-reclaimer PLC and the DCS, the stacker-reclaimer PLC is used as a slave station, the DCS is used as a master station, and a client / server structure is adopted.

[0014] As a preferred scheme of the remote fault diagnosis method of the stacker-reclaimer based on bus communication, the remote fault diagnosis platform is established on the DCS server, the platform displays the operating state of the stacker-reclaimer in real time, and has trend analysis and alarm functions.

[0015] The data is divided into different working conditions through a clustering model, then the data is input into a fault diagnosis model of a corresponding working condition, and the equipment operating condition is judged.

[0016] The historical data of the operating parameters are collected, the historical data are divided into 9 categories through a DBSCAN model, and when real-time data transmission is performed, the data is attributed to a certain working condition and then input into a fault diagnosis model of the corresponding working condition.

[0017] As a preferred scheme of the bus communication-based remote fault diagnosis method of the stacker-reclaimer, the fault diagnosis model comprises a machine learning-based diagnosis algorithm, historical data is collected, a support vector machine model is trained, future 1 min data is predicted, the predicted value is compared with the actual value, and if the error is within ±15%, it is determined to be normal.

[0018] The statistical-based diagnosis algorithm finds out abnormal data points by comparing the difference between the current data and the historical data, determines that it is normal if the error is within ±15%, and determines the cause and location of the fault through statistical methods.

[0019] The fault diagnosis model is trained according to different working conditions, and the fault diagnosis model is divided into 9 according to the 9 working conditions classified by the clustering model, and the running data of different working conditions is judged by using different fault diagnosis models.

[0020] If one of the fault diagnosis models issues an abnormal alarm, the fault warning platform displays the alarm, and if both algorithms issue an abnormal alarm, the stacker-reclaimer is directly stopped.

[0021] As a preferred scheme of the bus communication-based remote fault diagnosis method of the stacker-reclaimer, the PLC of the stacker-reclaimer collects 197 data points, removes 5 output points, and retains 192 input data points.

[0022] According to the fault diagnosis preset standard, 157 input data points are screened out, and 35 key input data points are obtained.

[0023] The 35 input data points are screened by using the variance selection method, the variance threshold is set to 0.02, 5 data points with a variance lower than the threshold are removed, and 30 input data points are retained.

[0024] The 30 input data points screened by the variance are screened by using the mutual information method, the mutual information threshold is set to 0.32, 24 data points with a higher mutual information value are selected as the final input features, and the remaining 6 data points are removed.

[0025] The stacker rotation, the material taking rotation, the material taking pitch, the material taking scraper, and the material taking belt current are taken as output values, and the remaining 24 screened data points are taken as input values of the support vector machine model.

[0026] The genetic algorithm is used to optimize the hyperparameter kernel function parameter σ and the regularization parameter C of the support vector machine model, and finally σ is 1.1032 and C is 15.7568.

[0027] The screened input data and the optimized parameters are input into the trained support vector machine model, and the predicted fault diagnosis result is directly output.

[0028] Another object of the present application is to provide a bus communication-based remote fault diagnosis system for a stacker-reclaimer, which can solve the problem of ensuring safety and confidentiality of data transmission in existing network operation by constructing a remote safety communication system for network operation.

[0029] To solve the above technical problems, the present application provides the following technical solutions: a bus communication-based remote fault diagnosis system for a stacker-reclaimer, comprising: a collection unit and a prediction unit; the collection unit is used to collect the running parameters of the equipment in real time by installing sensors and data collection devices on the stacker-reclaimer; and the prediction unit is used to transmit the data to an auxiliary machine control room by using a Profibus bus communication mode, build a fault diagnosis platform on the server in the auxiliary machine control room, realize fault early warning and analysis, and provide fault information.

[0030] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the bus communication-based remote fault diagnosis method for a stacker-reclaimer as described above when executing the computer program.

[0031] A computer readable storage medium stores a computer program, and the computer program implements the steps of the bus communication-based remote fault diagnosis method for a stacker-reclaimer as described above when executed by a processor.

[0032] The bus communication-based remote fault diagnosis method for a stacker-reclaimer provided by the present application improves the reliability of the equipment, reduces the failure rate, and ensures the stable operation of the coal conveying system. Remote monitoring and fault diagnosis are realized, the labor cost is effectively reduced, and the work efficiency is improved. The fault elimination time is shortened, the impact of equipment downtime on production is minimized, and the overall operation efficiency of the system is improved. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0034] Figure 1 A bus communication-based remote fault diagnosis method for a stacker-reclaimer provided by an embodiment of the present application is provided.

[0035] Figure 2 A bus communication-based remote fault diagnosis method for a stacker-reclaimer provided by an embodiment of the present application is provided.

[0036] Figure 3 A bus communication-based stacker-reclaimer remote fault diagnosis system is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application are described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0038] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details that are set forth in the following description, and it is understood that persons having ordinary skill in the art can make and use other embodiments of the present application without departing from the scope of the present application. Accordingly, the present application is not intended to be limited by the embodiments described herein.

[0039] Embodiment 1

[0040] Reference Figures 1-2 For an embodiment of the present application, a bus communication-based stacker-reclaimer remote fault diagnosis method is provided, comprising:

[0041] S1, by installing sensors and data acquisition devices on the stacker-reclaimer, real-time acquisition of the operating parameters of the equipment.

[0042] S2, using Profibus bus communication mode to transmit data to the auxiliary machine control room, building a fault diagnosis platform on the server in the auxiliary machine control room, realizing fault early warning and analysis, and providing fault information.

[0043] The sensors include a current transformer and a voltage transformer of a first take-up scraper motor, a current transformer and a voltage transformer of a second take-up scraper motor, a stack rotation angle encoder, a take-up rotation angle encoder, a take-up pitch angle encoder, a take-up scraper motor front material position sensor, a take-up scraper motor middle material position sensor, and a take-up scraper motor rear material position sensor.

[0044] Among them, the first take-up scraper motor and the second take-up scraper motor are two motors with the same function.

[0045] The data acquisition device includes a stack rotation frequency converter, a take-up rotation frequency converter, a take-up pitch frequency converter, and an S7-300.

[0046] The communication system comprises a stack rotating frequency converter, a material taking rotating frequency converter, a material taking pitch frequency converter, a Siemens S7-300 CPU, an IM368, a CP342-5, a DP bus, an OLM, a fiber transceiver, a DCS server, a DCS engineer station and a DCS operator station.

[0047] A Profibus-DP communication module CP342-5 is added to the stacker-reclaimer PLC rack to perform I / O virtual address and actual PLC address mapping, and the CP342-5 communicates with the DCS after reading the CPU address to realize data transmission between the DCS and the stacker-reclaimer PLC.

[0048] The master-slave communication interconnection device is configured between the stacker-reclaimer PLC and the DCS, the stacker-reclaimer PLC is taken as a slave station, the DCS is taken as a master station, and the client / server structure is adopted.

[0049] The stack rotating frequency converter, the material taking rotating frequency converter and the material taking pitch frequency converter collect the stack rotating motor current, voltage, the material taking rotating motor current, voltage, the material taking pitch motor current and voltage, and the rest of the data is read by the S7-300, the frequency converter communicates with the S7-300 to transmit the data to the S7-300 and the CP342-5, the I / O virtual address and the actual PLC address mapping are performed, the CP342-5 communicates with the DCS after reading the CPU address data, and the stacker-reclaimer S7-300 becomes the next slave station of the DCS.

[0050] The collected equipment operating parameters include the stack rotating motor current, voltage, circuit breaker and contactor state, the material taking rotating motor current, voltage, circuit breaker and contactor state, the material taking pitch motor current, voltage, circuit breaker and contactor state, the material taking scraper motor current, voltage, circuit breaker and contactor state, the stack belt motor current, voltage, circuit breaker and contactor state, the stack rotating angle encoder, the material taking rotating angle encoder, the material taking pitch angle encoder data, the material taking scraper left front material position data, right front material position data, left middle material position data, right middle material position data, left rear material position data and right rear material position data.

[0051] The remote fault diagnosis platform is established on the DCS server, the platform can display the running state of the stacker-reclaimer in real time, has the trend analysis and alarm functions.

[0052] The fault diagnosis is divided into two parts, the data is divided into different working conditions through the clustering model, then the data is input into the fault diagnosis model of the corresponding working condition to judge the equipment running condition.

[0053] Each parameter is input into the model, and the model automatically divides it into 9 categories, which is obtained by the model.

[0054] The historical data is collected, and the historical data is divided into 9 categories, i.e. 9 operation conditions, by using a DBSCAN model. When real-time data is transmitted, the data is attributed to a certain condition, and then input into a fault diagnosis model corresponding to the condition.

[0055] According to the fault diagnosis model, the fault diagnosis model is divided into two parts: a diagnosis algorithm based on machine learning: a large amount of historical data is collected, a support vector machine model is trained, future 1 min data is predicted, and the predicted value is compared with the actual value, and if the error is within ± 15%, it is determined to be normal; a diagnosis algorithm based on statistics: by comparing the difference between the current data and the historical data, the abnormal data points are found, and if the error is within ± 15%, it is determined to be normal, and the cause and position of the fault are determined by a statistical method.

[0056] The fault diagnosis model is trained according to the 9 conditions classified by the clustering model, and the fault diagnosis model is divided into 9, and the operation data of different conditions is judged by using different fault diagnosis models.

[0057] The diagnosis model is divided into two parts, and if one of them issues an abnormal alarm, it is displayed on the fault warning platform, and if both algorithms issue an abnormal alarm, the stacker-reclaimer is directly stopped, and the improved effect is shown in FIG. 2, wherein the X axis is the month, and the Y axis is the downtime caused by the fault.

[0058] The stacker-reclaimer PLC collects 197 data points, removes five output points, and has 192 input points at this time. According to the fault diagnosis preset standard, 157 input points are removed, and at this time, there are 35 input points in total. A variance selection method is used, and since a part of the data points have been excluded, the threshold value is small, and is set to 0.02. Five data points are deleted again, and finally, a mutual information method is used, the threshold value is set to 0.32, six data points are discarded again, and 24 inputs are retained.

[0059] The stacker rotation, the material taking rotation, the material taking pitch, the material taking scraper, and the material taking belt current are used as output values, and the others are used as input values.

[0060] The hyperparameters of the support vector machine model, the kernel function parameter sigma and the regularization parameter C, are optimized by using a genetic algorithm, sigma is 1.1032, and C is 15.7568.

[0061] The values are input into the trained support vector machine model, and the predicted output values are directly output.

[0062] Embodiment 2

[0063] Reference Figure 3 An embodiment of the present application provides a stacker-reclaimer remote fault diagnosis system based on bus communication, which comprises:

[0064] The acquisition unit 100 and the prediction unit 200;

[0065] The acquisition unit 100 is used for acquiring the operation parameters of the equipment in real time by installing sensors and data acquisition devices on the stacker-reclaimer.

[0066] The prediction unit 200 is used for transmitting data to the auxiliary machine control room by using a Profibus bus communication mode, building a fault diagnosis platform on a server in the auxiliary machine control room, realizing fault early warning and analysis, and providing fault information.

[0067] Embodiment 3

[0068] One embodiment of the present application is different from the first two embodiments, and is characterized in that:

[0069] If the functions are realized in the form of software function units and sold or used as independent products, the functions can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium and include a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0070] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute the instructions, or in conjunction with these instruction execution systems, apparatus or devices. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by or in conjunction with an instruction execution system, apparatus or device, or in conjunction with these instruction execution systems, apparatus or devices.

[0071] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer readable medium can be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via an optical scanner, then compiled, interpreted, or otherwise processed, as necessary, and stored in a computer memory.

[0072] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following techniques, which are well known in the art of hardware implementation, can be used: a combination of logic gates in a logic circuit, a combination of processor(s) and memory(ies) that executes software, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0073] It should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, but not to limit the present application. Even though the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced, without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A remote fault diagnosis method for a stacker-reclaimer based on bus communication, characterized in that, include: By installing sensors and data acquisition devices on the stacker-reclaimer, the operating parameters of the equipment can be collected in real time. Data is transmitted to the auxiliary machine control room using Profibus bus communication. A fault diagnosis platform is built on the server in the auxiliary machine control room to realize fault early warning and analysis and provide fault information. The sensors include a current transformer and a voltage transformer for the scraper motor, a stacking rotation angle encoder, a picking rotation angle encoder, and a picking pitch angle encoder. The data acquisition device includes a stacking rotary frequency converter, a picking rotary frequency converter, a picking pitch frequency converter, and an S7-300. The operating parameters include the current, voltage / circuit breaker and contactor status of the stacking rotary motor, the current, voltage / circuit breaker and contactor status of the picking rotary motor, the current, voltage, circuit breaker and contactor status of the picking pitch motor, the current, voltage / circuit breaker and contactor status of the picking scraper motor, the current, voltage / circuit breaker and contactor status of the stacking belt motor, the data of the stacking rotation angle encoder, the picking rotation angle encoder, and the picking pitch angle encoder, the material level data in front of the picking scraper, the material level data in the middle of the picking scraper, the material level data behind the picking scraper, the status of the pull rope switch, the status of the tear switch, the status of the deviation switch, and various action commands; The fault diagnosis platform is built on the DCS server. The platform displays the operating status of the stacker-reclaimer in real time and has trend analysis and alarm functions. The data is divided into different operating conditions by using a clustering model, and then the data is input into the fault diagnosis model of the corresponding operating condition to determine the equipment operating status. Historical data of the operating parameters are collected, and the historical data is divided into 9 categories using the DBSCAN model. During real-time data transmission, the data is assigned to a certain operating condition and then input into the fault diagnosis model of the corresponding operating condition. The fault diagnosis model includes a machine learning-based diagnostic algorithm, which collects historical data, trains a support vector machine model, predicts data for the next 1 minute, compares the predicted value with the actual value, and determines that the error is within ±15% if the error is normal. The statistical diagnostic algorithm identifies abnormal data points by comparing the differences between current data and historical data. If the error is within ±15%, it is judged as normal. The cause and location of the fault are determined by statistical methods. The fault diagnosis model is trained under different working conditions. Based on the nine working conditions classified by the clustering model, the fault diagnosis model is divided into nine types. Different fault diagnosis models are used to judge the operating data of different working conditions. If one of the fault diagnosis models issues an abnormal alarm, it will be displayed on the fault early warning platform. If both algorithms issue abnormal alarms, the stacker-reclaimer will be stopped directly. The stacker-reclaimer PLC collected a total of 197 data points. After removing 5 output points, 192 input data points were retained. Based on the preset fault diagnosis criteria, 157 input data points were eliminated, resulting in 35 key input data points. The 35 input data points were filtered using the variance selection method. A variance threshold of 0.02 was set, and 5 data points with variances lower than the threshold were removed, leaving 30 input data points. 30 input data points reserved after difference screening are screened by mutual information method, mutual information threshold is set as 0.32, 24 data points with high mutual information value are selected as final input features, and the remaining 6 data points are removed; The stacking rotation, material taking rotation, material taking pitch, material taking scraper and material taking belt currents are used as output values, and the remaining 24 data points after screening are used as input values of the support vector machine model; The genetic algorithm is used to optimize the kernel function parameter σ and the regularization parameter C of the support vector machine model, and finally σ is 1.1032 and C is 15.7568; The screened input data and the optimized parameters are input into the trained support vector machine model, and the predicted fault diagnosis result is directly output.

2. The bus communication-based stacker-reclaimer remote fault diagnosis method according to claim 1, characterized in that: The Profibus bus communication mode comprises a stacking rotation frequency converter, a material taking rotation frequency converter, a material taking pitch frequency converter, a Siemens S7-300, an IM365, a CP342-5, a DP bus, an OLM, a fiber transceiver, a DCS server, a DCS engineer station and a DCS operator station; The data transmission comprises adding a Profibus-DP communication module CP342-5 on the stacking and rehandling machine PLC rack, performing I / O virtual address and actual PLC address mapping, communicating with the DCS after the CP342-5 reads the CPU address data, and realizing the data transmission between the DCS and the stacking and rehandling machine PLC; The master-slave communication interconnection device is configured between the stacking and rehandling machine PLC and the DCS, the stacking and rehandling machine PLC is used as a slave station, the DCS is used as a master station, and a client / server structure is adopted.

3. A system employing a bus communication-based stacker-reclaimer remote fault diagnosis method according to any one of claims 1 to 2, characterized by, It comprises: a collection unit (100) and a prediction unit (200); The collection unit (100) is used for collecting the running parameters of the equipment in real time by installing sensors and data collection devices on the stacking and rehandling machine; The prediction unit (200) is used for transmitting data to the auxiliary machine control room by the Profibus bus communication mode, building a fault diagnosis platform on the server in the auxiliary machine control room, realizing fault early warning and analysis, and providing fault information.

4. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to realize the steps of the bus communication based remote fault diagnosis method of the stacking and rehandling machine in any one of claims 1 to 2.

5. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the bus communication based remote fault diagnosis method of the stacking and rehandling machine in any one of claims 1 to 2.

Images