Stacker equipment state monitoring and fault prediction method and system, medium and terminal

Abstract

The invention provides a stacker equipment state monitoring and fault prediction method and system, a medium and a terminal, and the method comprises the steps: installing a vibration sensor at each key part of a stacker, and collecting and storing vibration data; data preprocessing and feature engineering are carried out on the vibration data in combination with data in a stacker PLC; establishing a model for evaluating the state of each vulnerable part of the stacker according to the processed data by using a machine learning method; in the operation process of the stacking machine, the trained model is used for evaluating the state of the stacking machine, the damage time of each part is predicted, and a reasonable maintenance plan is suggested. The equipment state of the stacking machine can be accurately mastered in real time, maintenance personnel are helped to find faults of the stacking machine in time, a maintenance plan is reasonably arranged, the operation stability of the stacking machine is improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of mechanical engineering technology, and relates to a control method and system, and in particular to a method, system, medium and terminal for monitoring the state and predicting faults of stacker equipment. Background Art

[0002] With the widespread use of logistics equipment in factories, its stable operation ability has become increasingly important for ensuring the overall stability of production. Equipment at key nodes, such as stackers, will cause huge losses if they stop unexpectedly. The traditional approach is to avoid equipment abnormalities by regularly shutting down for inspection and maintenance, replacing equipment parts in advance, etc., but this approach often results in excessive maintenance, which will increase the company's production and operation costs. Moreover, there is a certain degree of randomness in the time of damage to parts, and even frequent maintenance cannot absolutely guarantee the normal operation of the stacker. Therefore, companies are in urgent need of a method and system that can monitor the current status of stacker equipment in real time and predict the time and type of failure.

[0003] The research on fault prediction based on equipment operating status has become a discipline since the 1960s. However, the dominant idea at that time was to use logical reasoning to analyze faults, which required mathematical modeling and analysis of application targets based on professional knowledge. Therefore, fault prediction applications were difficult to develop, expensive, and difficult to migrate. However, the rapid development of smart sensors and machine learning related technologies in recent years has provided a technical foundation for realizing low-cost fault prediction applications.

[0004] Since most stackers do not provide data that can reflect their own status, additional sensors need to be installed on the stacker. Compared with other types of sensors, external vibration sensors have the advantages of low cost, easy installation, and no interference with the operation of the stacker. In addition, the collected vibration data can reflect the status of each part of the stacker. However, vibration data is not intuitive, and only people with professional knowledge and experience can analyze vibration data. Therefore, a system is needed to automatically judge the current status of the stacker based on the vibration data, predict the failure of the stacker, and present the results in an intuitive way. Machine learning technology is the best choice to realize this system. Summary of the invention

[0005] The purpose of the present invention is to provide a method, system, medium and terminal for monitoring the equipment status and predicting faults of a stacker, which are used to accurately grasp the equipment status of the stacker in real time, help maintenance personnel to promptly discover stacker faults, reasonably arrange maintenance plans, improve the operating stability of the stacker and reduce maintenance costs.

[0006] To achieve the above-mentioned purpose and other related purposes, the present invention provides, on the one hand, a method for monitoring the equipment status and predicting faults of a stacker, comprising: installing vibration sensors on key parts of the stacker to collect and save vibration data; performing data preprocessing and feature engineering on the vibration data in combination with the data in the stacker PLC; using a machine learning method to establish a model for evaluating the status of each vulnerable part of the stacker based on the processed data; using the trained model to evaluate the status of the stacker during operation, predict the damage time of each part, and recommend a reasonable maintenance plan.

[0007] In one embodiment of the present invention, the step of installing vibration sensors on key parts of the stacker to collect and save vibration data includes: the vibration sensors are installed as much as possible at positions where the vibration changes significantly when the vulnerable parts are damaged. If the appropriate installation position cannot be determined, vibration sensors are installed at possible positions, and appropriate sensors are retained based on the modeling effect of subsequent machine learning; for each part whose status needs to be evaluated, data on its complete process from completely normal to damaged needs to be collected. If a part lacks damage data, data can be collected by simulating failures.

[0008] In one embodiment of the present invention, the step of preprocessing and feature engineering the vibration data in combination with the data in the stacker PLC includes: dividing the data of each stacking process of the stacker from the vibration data according to the time according to the data in the stacker PLC, and further dividing the vibration data of each stacking into stages such as receiving boxes, transportation, storage at station 1, continued transportation, storage at station 2, and return; the length of the vibration data of the same stage of each stacking is made the same by filling zeros at the end of shorter data. Then, the vibration data of each stage is respectively subjected to DFT transformation to obtain its frequency domain data; with the stacking process of the stacker as the granularity, the vibration time domain data and frequency domain data of each stage, as well as the number of stacking stations, the weight of goods on the stations, the transportation direction, and the target position warehouse layer are spliced ​​together to obtain the input data for modeling; for each vulnerable part, the score when it is just replaced is marked as the highest score, the score when it is damaged is marked as the highest score, and the score at other times during the period is marked as the linear interpolation calculated according to the stacker running time, so as to obtain the output data for modeling.

[0009] In one embodiment of the present invention, the step of using a machine learning method to establish a model for evaluating the status of each vulnerable part of the stacker based on processed data includes: for each vulnerable part, by calculating the correlation coefficient between each dimension of the input data and the part score, discarding the dimensions with a smaller correlation coefficient in the input data, thereby reducing the dimension of the input data, and then using the GBDT algorithm to use the reduced-dimensional data as output and the part score data as output to train a model for evaluating the status of this part.

[0010] In one embodiment of the present invention, the steps of using a trained model to evaluate the state of the stacker during operation, predicting the damage time of each part, and suggesting a reasonable maintenance plan include: reading data from the vibration sensor and the stacker PLC in real time, using a stacking process as the granularity, using the trained model to evaluate the current score of each part, and saving the score; for each part, taking its score sequence from the last maintenance to the current one, using linear regression to fit the score sequence, using the fitted linear model to predict the future score of the part, and taking the time when the part score is reduced to a threshold as the estimated time of part damage; if the scores of a part in recent times are all lower than the threshold, or the part is expected to be damaged in the near future, a warning is issued; the expected damage time of the next part is brought forward by a certain time as the recommended maintenance time, and all parts whose expected damage time is within a certain range of the recommended maintenance time are recommended parts for maintenance.

[0011] On the other hand, the present invention provides a stacker equipment status monitoring and fault prediction system, including: a vibration sensor for collecting vibration data on the stacker; a historical data collection module for collecting, saving and providing historical data on the vibration sensor and PLC; a model training module for performing data preprocessing and feature engineering on the vibration data in combination with the data in the stacker PLC, and using a machine learning method to establish a model for evaluating the status of each vulnerable part of the stacker based on the processed data; a real-time analysis module for using the trained model to evaluate the status of the stacker during the operation of the stacker, predict the damage time of each part, and recommend a reasonable maintenance plan; and a result display module for displaying the real-time analysis results to the user.

[0012] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the stacker equipment status monitoring and fault prediction method when executed by a processor.

[0013] The last aspect of the present invention provides a terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the stacker equipment status monitoring and fault prediction method.

[0014] As described above, the stacker equipment status monitoring and fault prediction method, system, medium and terminal described in the present invention have the following beneficial effects: the equipment status of the stacker can be accurately grasped in real time, helping maintenance personnel to promptly discover stacker faults, reasonably arrange maintenance plans, improve the stacker operation stability and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1Shown is a flow chart of a stacker equipment status monitoring and fault prediction method in one embodiment of the present invention.

[0016] Figure 2 Shown is a schematic diagram of the principle structure of a stacker equipment status monitoring and fault prediction system in one embodiment of the present invention.

[0017] Figure 3 It is a schematic diagram showing the principle structure of a terminal in one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0020] Embodiment 1

[0021] A method for monitoring the state of a stacker and predicting faults, comprising:

[0022] Install vibration sensors on key parts of the stacker to collect and save vibration data;

[0023] Combine the data in the stacker PLC to perform data preprocessing and feature engineering on the vibration data;

[0024] Use machine learning methods to build a model to evaluate the status of each vulnerable part of the stacker based on the processed data;

[0025] During the operation of the stacker crane, the trained model is used to evaluate the status of the stacker crane, predict the damage time of each part, and recommend a reasonable maintenance plan.

[0026] The following will describe in detail the method for monitoring the state of the stacker equipment and predicting faults provided by this embodiment in conjunction with the diagram. Figure 1 , showing a flow chart of a method for stacker equipment status monitoring and fault prediction in one embodiment.

[0027] like Figure 1 As shown, the method for stacker equipment status monitoring and fault prediction specifically includes the following steps:

[0028] S11, install vibration sensors on key parts of the stacker to collect and save vibration data.

[0029] In this embodiment, the S11 includes:

[0030] Vibration sensors should be installed at locations where vibration changes are obvious when vulnerable parts are damaged. If the appropriate installation location cannot be determined, vibration sensors should be installed at possible locations, and appropriate sensors should be retained based on the modeling results of subsequent machine learning.

[0031] For each part whose status needs to be evaluated, data from its complete process from normal to damaged needs to be collected. If a part lacks damage data, data can be collected by simulating failures.

[0032] S12, performing data preprocessing and feature engineering on the vibration data in combination with the data in the stacker PLC.

[0033] In this embodiment, the S12 includes:

[0034] According to the data in the stacker PLC, the data of each stacking process of the stacker is divided from the vibration data according to time, and the vibration data of each stacking is further divided into stages such as receiving the box, transportation, warehousing at station 1, continued transportation, warehousing at station 2, and return.

[0035] The length of the vibration data of the same stage in each stack is made the same by padding the end of the shorter data with zeros. Then the vibration data of each stage is subjected to DFT transformation to obtain its frequency domain data.

[0036] Taking the stacking process of the stacker as the granularity, the vibration time domain data, frequency domain data of each stage, as well as the mark data of the number of stacking stations, the weight of the goods on the stations, the transportation direction, and the target location warehouse layer are spliced ​​together to obtain the input data for modeling.

[0037] For each vulnerable part, the score when it is just replaced is marked as the highest score, the score when it is damaged is marked as the highest score, and the scores at other times in the meantime are marked as linear interpolations calculated according to the stacker's running time, thereby obtaining the output data of the modeling.

[0038] S13, using machine learning methods to establish a model for evaluating the status of each vulnerable part of the stacker based on the processed data.

[0039] Specifically, for each vulnerable part, the correlation coefficient between each dimension of the input data and the part score is calculated, and the dimensions with smaller correlation coefficients in the input data are discarded, thereby reducing the dimension of the input data. Then, the GBDT algorithm is used to use the reduced-dimensional data as output and the part score data as output to train a model for evaluating the status of this part.

[0040] S14, during the operation of the stacker, the trained model is used to evaluate the status of the stacker, predict the damage time of each part, and recommend a reasonable maintenance plan.

[0041] In this embodiment, the S12 includes:

[0042] Read data from vibration sensors and stacker PLC in real time, use the trained model to evaluate the current score of each part based on the granularity of a stacking process, and save the score.

[0043] For each part, take its score sequence from the last repair to the current one, use linear regression to fit the score sequence, use the fitted linear model to predict the future score of the part, and take the time until the part score drops to the threshold as the expected part damage time.

[0044] If a part's recent scores are below the threshold, or if the part is expected to break in the near future, a warning is issued;

[0045] The estimated damage time of the next part is set in advance by a certain time as the recommended maintenance time, and the parts whose estimated damage time is within a certain range of the recommended maintenance time are all recommended maintenance parts.

[0046] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for monitoring the state of the stacker equipment and predicting faults is implemented.

[0047] At any possible level of technical detail combination, the present application may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present application.

[0048] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, (but not limited to) an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0049] The computer-readable program described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives a computer-readable program instruction from the network, and forwards the computer-readable program instruction for storage in the computer-readable storage medium in each computing / processing device. The computer program instruction for performing the operation of the present application can be an assembly instruction, an instruction set architecture (ISA) instruction, a machine instruction, a machine-related instruction, a microcode, a firmware instruction, a state setting data, an integrated circuit configuration data, or a source code or object code written in any combination of one or more programming languages, wherein the programming language includes an object-oriented programming language, such as Smalltalk, C++, etc., and a procedural programming language, such as "C" language or similar programming language. Computer readable program instructions can be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In certain embodiments, by using the state information of computer readable program instructions to personalize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs), the electronic circuits can execute computer readable program instructions, thereby realizing various aspects of the present application.

[0050] Embodiment 2

[0051] This embodiment provides a stacker equipment status monitoring and fault prediction system, including:

[0052] Vibration sensors, used to collect vibration data on the stacker;

[0053] Historical data collection module, used to collect, save and provide historical data on vibration sensors and PLC;

[0054] Model training module, which is used to preprocess and feature-engineer the vibration data in combination with the data in the stacker PLC, and use machine learning methods to establish a model for evaluating the status of each vulnerable part of the stacker based on the processed data;

[0055] A real-time analysis module is used to evaluate the status of the stacker using the trained model during its operation, predict the damage time of each part, and recommend a reasonable maintenance plan;

[0056] The result display module is used to display the real-time analysis results to the user.

[0057] The following will describe in detail the stacker equipment status monitoring and fault prediction system provided by this embodiment in conjunction with the diagram. Figure 2 , which is a schematic diagram of the principle structure of a stacker equipment status monitoring and fault prediction system in one embodiment. Figure 2 As shown, the stacker equipment status monitoring and fault prediction system 2 includes: a vibration sensor 21, a historical data collection module 22, a model training module 23, a real-time analysis module 24, and a result display module 25.

[0058] The vibration sensor 21 is used to collect vibration data on the stacker.

[0059] The historical data collection module 22 is used to collect, save and provide historical data on the vibration sensor and PLC.

[0060] The model training module 23 is used to perform data preprocessing and feature engineering on the vibration data in combination with the data in the stacker PLC, and use a machine learning method to establish a model for evaluating the status of each vulnerable part of the stacker based on the processed data.

[0061] Specifically, the data preprocessing and feature engineering for vibration data combined with data in the stacker PLC include:

[0062] According to the data in the stacker PLC, the data of each stacking process of the stacker is divided from the vibration data according to time, and the vibration data of each stacking is further divided into the stages of receiving boxes, transportation, storage at station 1, continued transportation, storage at station 2, and return;

[0063] The length of the vibration data of the same stage of each stack is made the same by padding the end of the shorter data with zeros. Then the vibration data of each stage is transformed by DFT to obtain its frequency domain data;

[0064] Taking the stacking process of the stacker as the granularity, the vibration time domain data and frequency domain data of each stage, as well as the number of stacking stations, the weight of the goods on the stations, the transportation direction, and the mark data of the target location store layer are spliced ​​together to obtain the input data for modeling;

[0065] For each vulnerable part, the score when it is just replaced is marked as the highest score, the score when it is damaged is marked as the highest score, and the scores at other times in the meantime are marked as linear interpolations calculated according to the stacker's running time, thereby obtaining the output data of the modeling.

[0066] Specifically, the model for evaluating the status of each vulnerable part of the stacker crane is established based on the processed data using the machine learning method, including:

[0067] For each vulnerable part, the correlation coefficient between each dimension of the input data and the part score is calculated, and the dimensions with smaller correlation coefficients in the input data are discarded to reduce the dimension of the input data. Then, the GBDT algorithm is used to use the reduced-dimensional data as output and the part score data as output to train a model for evaluating the status of this part.

[0068] The real-time analysis module 24 is used to evaluate the status of the stacker using the trained model during the operation of the stacker, predict the damage time of each component, and recommend a reasonable maintenance plan.

[0069] Specifically, it is used to evaluate the status of the stacker crane using the trained model during its operation, predict the damage time of each part, and recommend a reasonable maintenance plan including:

[0070] Read data from vibration sensors and stacker PLC in real time, use the trained model to evaluate the current score of each part based on a stacking process, and save the score;

[0071] For each part, take its score sequence from the last repair to the current one, use linear regression to fit the score sequence, use the fitted linear model to predict the future score of the part, and take the time until the part score drops to the threshold as the estimated part damage time;

[0072] If a part's recent scores are below the threshold, or if the part is expected to break in the near future, a warning is issued;

[0073] The estimated damage time of the next part is set in advance by a certain time as the recommended maintenance time, and the parts whose estimated damage time is within a certain range of the recommended maintenance time are all recommended maintenance parts.

[0074] The result display module 25 is used to display the real-time analysis results to the user.

[0075] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements, or they can all be implemented in the form of hardware, or some modules can be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example: the x module can be a separately established processing element, or it can be integrated in a certain chip of the above system. In addition, the x module can also be stored in the memory of the above system in the form of program code, and called and executed by a certain processing element of the above system. The implementation of other modules is similar. These modules can be integrated together in whole or in part, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software. The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), one or more digital singnal processors (DSP), one or more field programmable gate arrays (FPGA), etc. When a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. These modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0076] Embodiment 3

[0077] This embodiment provides a terminal. Figure 3 , which is a schematic diagram showing the principle structure of a terminal in an embodiment. Figure 3 As shown, the terminal 300 includes: a memory 301, a processor 302, and a communicator 303; the memory 301 is used to store computer instructions; the processor 302 executes the computer instructions to implement the following Figure 1 The method described; the communicator 303 is used to communicate with one or more handles.

[0078] In some embodiments, the number of the memory 301 in the terminal 300 can be one or more, the number of the processor 302 can be one or more, the number of the communicator 303 can be one or more, and Figure 3 Take one as an example.

[0079] In one embodiment of the present application, the processor 302 in the terminal 300 will follow the following steps: Figure 2 In the above steps, one or more instructions corresponding to the process of the application are loaded into the memory 301, and the processor 302 runs the application stored in the memory 301, thereby achieving the following Figure 1 The method for stacker equipment status monitoring and fault prediction.

[0080] The memory 301 may include a random access memory (RAM), or may include a non-volatile memory, such as at least one disk memory. The memory 301 stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic services and processing hardware-based tasks.

[0081] The processor 302 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0082] The communicator 303 is used to realize the communication connection between the database access device and other devices (such as a client, a read-write library, and a read-only library). The communicator 303 may include one or more modules of different communication modes, for example, a CAN communication module connected to a CAN bus communication. The communication connection may be one or more wired / wireless communication modes and combinations thereof. The communication modes include: any one or more of the Internet, CAN, intranet, wide area network (WAN), local area network (LAN), wireless network, digital subscriber line (DSL) network, frame relay network, asynchronous transfer mode (ATM) network, virtual private network (VPN) and / or any other suitable communication network. For example: any one or more of WIFI, Bluetooth, NFC, GPRS, GSM, and Ethernet and a variety of combinations.

[0083] The protection scope of the method for stacker equipment status monitoring and fault prediction described in the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0084] The present invention also provides a stacker equipment status monitoring and fault prediction system, which can implement the stacker equipment status monitoring and fault prediction method described in the present invention. However, the implementation device of the stacker equipment status monitoring and fault prediction method described in the present invention includes but is not limited to the structure of the stacker equipment status monitoring and fault prediction system listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0085] In summary, the stacker equipment status monitoring and fault prediction method, system, medium and terminal of the present invention can accurately grasp the equipment status of the stacker in real time through the machine learning method, help maintenance personnel to find stacker faults in time, arrange maintenance plans reasonably, improve the operation stability of the stacker, and reduce maintenance costs. The present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

[0086] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for monitoring the state of a stacker equipment and predicting faults, characterized in that: include: Install vibration sensors on key parts of the stacker to collect and save vibration data; Combine the data in the stacker PLC to perform data preprocessing and feature engineering on the vibration data; Use machine learning methods to build a model to evaluate the status of each vulnerable part of the stacker based on the processed data; During the operation of the stacker crane, the trained model is used to evaluate the status of the stacker crane, predict the damage time of each part, and recommend a reasonable maintenance plan.

2. The method for stacker equipment status monitoring and fault prediction according to claim 1, characterized in that: The steps of installing vibration sensors on key parts of the stacker to collect and save vibration data include: Vibration sensors should be installed at locations where vibration changes are obvious when vulnerable parts are damaged. If the appropriate installation location cannot be determined, vibration sensors should be installed at possible locations, and appropriate sensors should be retained based on the modeling results of subsequent machine learning. For each part whose status needs to be evaluated, data from its complete process from normal to damaged needs to be collected. If a part lacks damage data, data can be collected by simulating failures.

3. The method for stacker equipment status monitoring and fault prediction according to claim 1, characterized in that: The steps of data preprocessing and feature engineering for vibration data combined with data from the stacker PLC include: According to the data in the stacker PLC, the data of each stacking process of the stacker is divided from the vibration data according to time, and the vibration data of each stacking is further divided into the stages of receiving boxes, transportation, storage at station 1, continued transportation, storage at station 2, and return; The length of the vibration data of the same stage of each stack is made the same by padding the end of the shorter data with zeros. Then the vibration data of each stage is transformed by DFT to obtain its frequency domain data; Taking the stacking process of the stacker as the granularity, the vibration time domain data and frequency domain data of each stage, as well as the number of stacking stations, the weight of the goods on the stations, the transportation direction, and the mark data of the target location store layer are spliced ​​together to obtain the input data for modeling; For each vulnerable part, the score when it is just replaced is marked as the highest score, the score when it is damaged is marked as the lowest score, and the scores at other times in the meantime are marked as linear interpolations calculated according to the stacker's running time, thereby obtaining the output data of the modeling.

4. The method for stacker equipment status monitoring and fault prediction according to claim 1, characterized in that: The steps of using machine learning methods to establish a model for evaluating the status of each vulnerable part of the stacker crane based on the processed data include: For each vulnerable part, the correlation coefficient between each dimension of the input data and the part score is calculated, and the dimensions with smaller correlation coefficients in the input data are discarded to reduce the dimension of the input data. Then, the GBDT algorithm is used to use the reduced-dimensional data as output and the part score data as output to train a model for evaluating the status of this part.

5. The method for stacker equipment status monitoring and fault prediction according to claim 1, characterized in that: The steps to use the trained model to evaluate the status of the stacker crane during its operation, predict the damage time of each part, and recommend a reasonable maintenance plan include: Read data from vibration sensors and stacker PLC in real time, use the trained model to evaluate the current score of each part based on a stacking process, and save the score; For each part, take its score sequence from the last repair to the current one, use linear regression to fit the score sequence, use the fitted linear model to predict the future score of the part, and take the time until the part score drops to the threshold as the estimated part damage time; If a part's recent scores are below the threshold, or if the part is expected to break in the near future, a warning is issued; The estimated damage time of the next part is set in advance by a certain time as the recommended maintenance time, and the parts whose estimated damage time is within a certain range of the recommended maintenance time are all recommended maintenance parts.

6. A stacker equipment status monitoring and fault prediction system, characterized in that: include: Vibration sensors, used to collect vibration data on the stacker; Historical data collection module, used to collect, save and provide historical data on vibration sensors and PLC; Model training module, which is used to preprocess and feature-engineer the vibration data in combination with the data in the stacker PLC, and use machine learning methods to establish a model for evaluating the status of each vulnerable part of the stacker based on the processed data; A real-time analysis module is used to evaluate the status of the stacker using the trained model during its operation, predict the damage time of each part, and recommend a reasonable maintenance plan; The result display module is used to display the real-time analysis results to the user.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the stacker equipment status monitoring and fault prediction method described in any one of claims 1 to 5 is implemented.

8. A terminal, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the stacker equipment status monitoring and fault prediction method according to any one of claims 1 to 5.

Images