Mining circuit fault self-diagnosis method and system

Through machine learning models, predict the circuit data of mining equipment, build circuit waveform diagrams, determine the start time period and cause of the fault, solve the problem that existing systems cannot predict circuit failures, realize accurate early warning of circuit failures of mining equipment, and ensure the guarantee of Production safety.

CN118937970AInactive Publication Date: 2024-11-12JINING MINING GRP HAINA TECH ELECTROMECHANICAL CO

Patent Information

Application Number
CN202411397929.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-09
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing mining equipment circuit fault diagnosis system cannot predict future changes in circuit data, and cannot accurately determine the fault period and cause of the fault, making it difficult to make advance warnings, affecting production stability and safety.

Method used

The machine learning model is used to predict circuit data, and by obtaining the type and circuit sensing data of mining equipment, building a circuit waveform diagram, determining the start time period and cause of the fault, and providing a fault warning.

Benefits of technology

It realizes prediction of future changes in mining equipment circuit data, accurately determines the fault period and cause, provides pre-warning, and ensures the stability and safety of mining production.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118937970A_ABST
    Figure CN118937970A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of fault diagnosis, and discloses a mining circuit fault self-diagnosis method and system, and the method comprises the steps: obtaining the type of mining equipment, and obtaining the circuit sensing data and circuit influence data of the mining equipment in a time period from T-M to T; matching a preset first machine learning model and a preset second machine learning model, and inputting the circuit sensing data and the circuit influence data into the corresponding preset first machine learning model to predict predicted circuit data in a future time period from T to T + M; constructing a circuit actual oscillogram according to the predicted circuit data, and obtaining a circuit fault result of the mining equipment according to the circuit actual oscillogram; inputting the circuit abnormal wave band graph into a preset second machine learning model, and determining a fault reason; fault early warning is carried out according to the circuit fault starting time period and the fault reason; according to the invention, the stability of mining production and the safety of mining production workers can be ensured through fault early warning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and more specifically, to a method and system for self-diagnosis of mine circuit faults. Background Art

[0002] With the development and modernization of the mining industry, mining equipment plays a vital role in the mining process; however, mining equipment may face various circuit failures during long-term use, which will not only cause equipment downtime, but also have a serious impact on production and even endanger production safety; therefore, it is particularly important to diagnose circuit failures in mining equipment in a timely and accurate manner.

[0003] Traditional circuit fault diagnosis methods mainly rely on manual detection and experience-based judgment, and have the disadvantages of slow diagnosis speed and low accuracy. With the continuous development and application of artificial intelligence technology, it has become possible to automatically diagnose circuit faults in mining equipment with the help of intelligent methods. However, the existing automated diagnosis system still has certain limitations in adapting to the mining environment and improving diagnostic accuracy and speed.

[0004] At present, although there are some intelligent mining equipment circuit fault diagnosis methods, for example, the Chinese patent with the authorization publication number CN113658414B discloses a mining equipment fault early warning method, device, terminal device and storage medium. Although the above method and the prior art can provide early warning of mining equipment faults, research and practical application of the above method and the prior art have found that the above method and the prior art have at least the following defects: (1) It is impossible to predict the future changes of mining equipment circuit data (such as current value). Furthermore, it is impossible to accurately determine the future fault period and future fault performance (i.e., circuit abnormality band diagram) of mining equipment circuits based on the future changes of circuit data. (2) It is impossible to determine the cause of the fault based on the fault symptoms, making it difficult to provide advance warning. Furthermore, it is difficult to ensure the stability of mining production and the safety of mining workers. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for self-diagnosis of mining circuit faults.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for self-diagnosis of mining circuit faults, the method comprising: Obtain the type of mining equipment, and obtain the circuit sensing data and circuit impact data of the mining equipment in the period from TM to T, where T and M are both integers greater than zero; Matching the corresponding preset first machine learning model and the preset second machine learning model according to the type of mining equipment, inputting the circuit sensing data and the circuit impact data in the time period from TM to T into the corresponding preset first machine learning model to predict the predicted circuit data in the future time period from T to T+M; Constructing a circuit actual waveform diagram of the corresponding mining equipment according to the predicted circuit data in the future period from T to T+M, and obtaining a circuit fault result of the mining equipment according to the circuit actual waveform diagram, wherein the circuit fault result includes a circuit abnormal band diagram and a circuit fault starting period; Inputting the circuit abnormal band diagram into the corresponding preset second machine learning model to determine the cause of the failure of the corresponding mining equipment; Fault warning is carried out according to the starting period and cause of circuit fault of mining equipment.

[0007] Furthermore, the circuit sensing data includes the actual measured value of current, voltage and resistance of the built-in circuit of the mining equipment; the circuit influence data includes internal influence data and external influence data; the internal influence data includes the actual measured value of circuit temperature and the actual measured value of circuit vibration of the built-in circuit of the mining equipment; the external influence data includes the actual measured value of ambient temperature and the actual measured value of ambient humidity of the environment in which the mining equipment is located.

[0008] Further, the matching of the corresponding preset first machine learning model and the preset second machine learning model includes: Extracting the mining equipment type corresponding to the mining equipment, and extracting a mapping relationship library between the mining equipment type and the model data; the model data includes a preset first machine learning model and a preset second machine learning model associated with the corresponding mining equipment type; The mining equipment type is input into the mapping relationship library for relationship matching to obtain model data corresponding to the mining equipment type.

[0009] Furthermore, the generation logic of the preset first machine learning model is as follows: Acquire historical circuit training data, and divide the historical circuit training data into a circuit data training set and a circuit data test set; the historical circuit training data includes circuit feature data and its corresponding predicted circuit data; Wherein, the circuit characteristic data includes circuit sensing data and circuit influence data; the predicted circuit data includes one of a current prediction value, a voltage prediction value or a resistance prediction value; Constructing a regression network, taking the circuit feature data in the circuit data training set as the input feature of the regression network, and taking the predicted circuit data in the circuit data training set as the output feature of the regression network, performing model training on the regression network, and obtaining an initial regression network; The initial regression network is model verified using the circuit data test set, and an initial regression network that is less than or equal to a preset test error threshold is output as the preset first machine learning model.

[0010] Furthermore, the actual waveform diagram of the circuit is one of a current waveform diagram, a voltage waveform diagram or a resistance waveform diagram.

[0011] Furthermore, the method of obtaining the circuit fault result of the mining equipment according to the actual circuit waveform diagram includes: The actual circuit waveform diagram of the mining equipment is equally divided to obtain N subdivided bands in the actual circuit waveform diagram, where N is an integer greater than zero; Obtain a pre-stored circuit standard waveform diagram, calculate the difference between the circuit standard waveform diagram and each image form subdivided band, and obtain Q differences, where Q is an integer greater than zero; Sort the Q differences in descending order, and use the subdivided band corresponding to the first difference in the sorting order as the circuit abnormality band diagram; The time interval of the circuit abnormality band diagram is extracted, and the time interval of the circuit abnormality band diagram is used as the starting period of the circuit fault.

[0012] Furthermore, the generation logic of the preset second machine learning model is as follows: Acquire historical fault diagnosis training data, and divide the historical fault diagnosis training data into a fault diagnosis training set and a fault diagnosis test set; the historical fault diagnosis training data includes a circuit abnormality band diagram and an annotated label of the corresponding fault cause; Construct a classifier, use the circuit abnormal band map in the fault diagnosis training set as the input data of the classifier, and use the label of the fault cause in the fault diagnosis training set as the input data of the classifier, train the classifier, and obtain an initial classification network; The initial classification network is model verified using the fault diagnosis test set, and the initial classification network with a test accuracy greater than or equal to a preset threshold is output as the preset second machine learning model.

[0013] A mine circuit fault self-diagnosis system, comprising: The data collection module is used to obtain the type of mining equipment, and to obtain the circuit sensing data and circuit impact data of the mining equipment in the period from TM to T, where T and M are both integers greater than zero; A data prediction module is used to match the corresponding preset first machine learning model and the preset second machine learning model according to the type of mining equipment, and input the circuit sensing data and circuit impact data in the time period from TM to T into the corresponding preset first machine learning model to predict the predicted circuit data in the future time period from T to T+M; The first fault diagnosis module is used to construct a circuit actual waveform diagram of the corresponding mining equipment according to the predicted circuit data in the future period from T to T+M, and obtain the circuit fault result of the mining equipment according to the circuit actual waveform diagram, wherein the circuit fault result includes a circuit abnormal band diagram and a circuit fault starting period; A second fault diagnosis module is used to input the circuit abnormality band diagram into the corresponding preset second machine learning model to determine the fault cause of the corresponding mining equipment; The fault warning module is used to provide fault warning according to the starting period and cause of the circuit fault of the mining equipment.

[0014] An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, any one of the above-mentioned methods for self-diagnosis of mining circuit faults is implemented.

[0015] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, any one of the above-mentioned methods for self-diagnosis of mining circuit faults is implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present application discloses a method and system for self-diagnosis of mining circuit faults, comprising: obtaining the type of mining equipment, and obtaining circuit sensing data and circuit influence data of the mining equipment in a period from TM to T; matching a preset first machine learning model and a preset second machine learning model, inputting the circuit sensing data and the circuit influence data into the corresponding preset first machine learning model to predict the predicted circuit data in a future period from T to T+M; constructing a circuit actual waveform diagram according to the predicted circuit data, and obtaining the circuit fault result of the mining equipment according to the circuit actual waveform diagram; inputting the circuit abnormal band diagram into the preset second machine learning model to determine the cause of the fault; and performing fault warning according to the circuit fault starting period and the fault cause; based on the above process, the present invention can predict the future changes (such as current value) of the circuit data of the mining equipment, and further, it is conducive to accurately determining the future fault period and future fault characterization of the mining equipment circuit based on the future changes of the circuit data; at the same time, by determining the cause of the fault based on the fault characterization, it is conducive to prior warning, and further, it is conducive to ensuring the stability of mining production and the safety of mining production workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a mine circuit fault self-diagnosis method provided by the present invention; Figure 2 A module structure diagram of a mining circuit fault self-diagnosis system provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1 As shown, this embodiment discloses a method for self-diagnosis of mining circuit faults, the method comprising: S101: Acquire the type of mining equipment, and acquire the circuit sensing data and circuit impact data of the mining equipment in the period from TM to T, where T and M are both integers greater than zero; It should be understood that in mining production, various types of mining equipment are needed, such as mining conveyors, crushers, vibrating screens, and gas detectors, etc. The types of mining equipment are pre-stored in the system data. Due to the complexity of mining production scenarios, it is difficult to conduct long-term and stable management and control of the operating status of various types of mining equipment in mining production scenarios. Therefore, it is necessary to monitor the faults of these equipment circuits in real time to ensure the stability of mining production and the safety of mining workers. Specifically, the circuit sensing data includes the current measured value, voltage measured value and resistance measured value of the built-in circuit of the mining equipment; the circuit impact data includes internal impact data and external impact data; the internal impact data includes the circuit temperature measured value and circuit vibration measured value of the built-in circuit of the mining equipment; the external impact data includes the ambient temperature measured value and ambient humidity measured value of the environment in which the mining equipment is located; It should be noted that the circuit sensing data and circuit impact data are collected in real time by various preset sensors; the various sensors include but are not limited to current sensors, voltage sensors, resistance sensors, temperature sensors, vibration sensors and humidity sensors; It can be understood that: the change of the predicted circuit data in the future time period is subject to the circuit sensor data and the circuit influence data, that is, the circuit sensor data and the circuit influence data are important factors that cause changes in the current prediction value, the voltage prediction value or the resistance prediction value; an example is that, for example, as the load of mining equipment (such as load amount and load time, etc.) continues to increase, the built-in circuit of the mining equipment will generate high temperature, and the excessively high circuit temperature will cause the mining equipment to shut down, short circuit or circuit board burnout and other abnormalities, thereby causing the mining equipment to malfunction; similarly, the influencing parameters such as the ambient temperature and ambient humidity of the environment in which the mining equipment is located also have corresponding fault-inducing tendencies.

[0020] S102: matching the corresponding preset first machine learning model and the preset second machine learning model according to the type of mining equipment, inputting the circuit sensing data and the circuit impact data in the time period from TM to T into the corresponding preset first machine learning model to predict the predicted circuit data in the future time period from T to T+M; In implementation, the matching of the corresponding preset first machine learning model and the preset second machine learning model includes: Extracting the mining equipment type corresponding to the mining equipment, and extracting a mapping relationship library between the mining equipment type and the model data; the model data includes a preset first machine learning model and a preset second machine learning model associated with the corresponding mining equipment type; It can be understood that: a mapping relationship library is pre-stored in the system database, and the mapping relationship library contains a plurality of mapping relationships between mining equipment types and model data. In each mapping relationship between mining equipment types and model data, there is a mining equipment type and the model data matching it; each mining equipment type and the model data matching it are determined by the technicians in advance by binding relationship; Input the mining equipment type into the mapping relationship library for relationship matching to obtain model data corresponding to the mining equipment type; Exemplarily, it is assumed that the type of mining equipment is a conveyor, and there is a mapping relationship between the type of mining equipment and model data corresponding to the conveyor in the mapping relationship library, and the model data in the mapping relationship includes a preset first machine learning model for obtaining predicted circuit data of the conveyor in a future time period and a preset second machine learning model for obtaining the cause of the failure of the conveyor in the future time period; In implementation, the generation logic of the preset first machine learning model is as follows: Acquire historical circuit training data, and divide the historical circuit training data into a circuit data training set and a circuit data test set; the historical circuit training data includes circuit feature data and its corresponding predicted circuit data; Wherein, the circuit characteristic data includes circuit sensing data and circuit influence data; the predicted circuit data includes one of a current prediction value, a voltage prediction value or a resistance prediction value; It should be noted that: referring to the above overview, the circuit sensor data and circuit influence data in the historical circuit training data are collected and recorded by technicians in advance through various sensors; the predicted circuit data in the historical circuit training data are obtained by technicians by marking according to the corresponding relationship between the circuit characteristic data of the previous period and the circuit sensor data of the next period, that is, the current measured value in the circuit sensor data corresponding to the next period is marked as the current predicted value. Similarly, the logic for obtaining the voltage predicted value or the resistance predicted value is the same, and no further elaboration is made here; Constructing a regression network, taking the circuit feature data in the circuit data training set as the input feature of the regression network, and taking the predicted circuit data in the circuit data training set as the output feature of the regression network, performing model training on the regression network, and obtaining an initial regression network; Using the circuit data test set to perform model verification on the initial regression network, outputting an initial regression network that is less than or equal to a preset test error threshold as a preset first machine learning model; It should be noted that the regression network is a specific one of algorithm models such as random forest regression, decision tree regression, support vector machine regression, polynomial regression or neural network model.

[0021] S103: constructing a circuit actual waveform diagram of the corresponding mining equipment according to the predicted circuit data in the future period from T to T+M, and obtaining a circuit fault result of the mining equipment according to the circuit actual waveform diagram, wherein the circuit fault result includes a circuit abnormal band diagram and a circuit fault starting period; Specifically, the actual waveform diagram of the circuit is one of a current waveform diagram, a voltage waveform diagram or a resistance waveform diagram; It should be understood that: after predicting the predicted circuit data in the future time period from T to T+M, if the predicted circuit data is the current predicted value at each moment in the future time period from T to T+M, then the current predicted value at each moment in the future time period from T to T+M is input into the data analysis software, such as Origin software, with time as the horizontal axis, the current predicted value as the vertical axis, and the current predicted value at each moment as the coordinate point, and the coordinate points are connected by curves to construct the actual circuit waveform diagram of the corresponding mining equipment, that is, the current waveform diagram; similarly, if the predicted circuit data is the voltage predicted value or the resistance predicted value at each moment in the future time period from T to T+M, then the construction process of the voltage waveform diagram or the resistance waveform diagram is the same as the above-mentioned current waveform diagram. For details, refer to the above narrative logic, and no repetition is made here; In implementation, the method of obtaining the circuit fault result of mining equipment according to the actual circuit waveform diagram includes: The actual circuit waveform diagram of the mining equipment is equally divided to obtain N subdivided bands in the actual circuit waveform diagram, where N is an integer greater than zero; Obtain a pre-stored circuit standard waveform diagram, calculate the difference between the circuit standard waveform diagram and each image form subdivided band, and obtain Q differences, where Q is an integer greater than zero; It should be noted that: in the pre-stored system data of the circuit standard waveform diagram, the circuit standard waveform diagram includes a circuit standard waveform diagram composed of current value, a circuit standard waveform diagram composed of voltage value and a circuit standard waveform diagram composed of resistance value, which is determined according to the prior experiments and selection of the technicians, and the circuit standard waveform diagram shows the normal waveform of the corresponding mining equipment circuit and the fluctuation range of the normal waveform; It should also be noted that: the difference between the circuit standard waveform diagram and each image form subdivision band is calculated by the Euclidean distance formula; the Euclidean distance formula is a method for measuring the distance between vectors, which is widely used in image processing and is used to measure the difference between images; that is, by calculating the Euclidean distance between the circuit standard waveform diagram and each image form subdivision band, the Euclidean distance is used as the difference, and Q differences are obtained; Sort the Q differences in descending order, and use the subdivided band corresponding to the first difference in the sorting order as the circuit abnormality band diagram; Extracting the time interval of the circuit abnormal band diagram, and taking the time interval of the circuit abnormal band diagram as the circuit fault starting period; Exemplarily, assuming that there are three subdivided bands in the actual waveform diagram of the circuit, and the time interval of each subdivided band is 9:00 to 9:10, 9:10 to 9:20, and 9:20 to 9:30, and the subdivided band corresponding to 9:10 to 9:20 is the subdivided band corresponding to the first difference in sorting, then the subdivided band corresponding to 9:10 to 9:20 is used as the circuit abnormality band diagram, and the time interval from 9:10 to 9:20 is used as the starting period of the circuit fault.

[0022] S104: inputting the circuit abnormal band diagram into the corresponding preset second machine learning model to determine the cause of the failure of the corresponding mining equipment; In implementation, the generation logic of the preset second machine learning model is as follows: Acquire historical fault diagnosis training data, and divide the historical fault diagnosis training data into a fault diagnosis training set and a fault diagnosis test set; the historical fault diagnosis training data includes a circuit abnormality band diagram and an annotated label of the corresponding fault cause; It should be noted that: the circuit abnormal band diagram in the historical fault diagnosis training data is obtained by pre-collection and processing, and its specific acquisition logic details refer to the above description; the labeling labels of the fault causes in the historical fault diagnosis training data are obtained by the technicians manually labeling each circuit abnormal band diagram in advance; wherein, the fault causes include but are not limited to load overload, equipment aging or excessive external environment temperature, etc.; Construct a classifier, use the circuit abnormal band map in the fault diagnosis training set as the input data of the classifier, and use the label of the fault cause in the fault diagnosis training set as the input data of the classifier, train the classifier, and obtain an initial classification network; Using the fault diagnosis test set to perform model verification on the initial classification network, outputting an initial classification network that is greater than or equal to a preset test accuracy threshold as a preset second machine learning model; It should be noted that the classifier is a specific one of algorithm models such as a convolutional neural network (CNN), a recurrent neural network (RNN) or an integrated learning model.

[0023] S105: Produce a fault warning according to the starting period of the circuit fault of the mining equipment and the fault cause; It can be understood that the starting period of the circuit fault is obtained through the prediction and judgment process and is a future time. Therefore, providing advance warning to relevant maintenance departments based on the starting period of the circuit fault is beneficial to ensuring the safety of mining production workers. At the same time, providing advance feedback on the cause of the fault is beneficial to ensuring the stability of mining production.

[0024] Example 2: Please refer to Figure 2 As shown, based on the same inventive concept, referring to the above embodiment 1, this embodiment discloses a mining circuit fault self-diagnosis system. The details of this embodiment are detailed with reference to the contents of the above embodiment 1. The system includes: The data collection module 210 is used to obtain the type of mining equipment, and to obtain the circuit sensing data and circuit impact data of the mining equipment in the period from TM to T, where T and M are both integers greater than zero; The data prediction module 220 is used to match the corresponding preset first machine learning model and the preset second machine learning model according to the type of mining equipment, and input the circuit sensing data and the circuit impact data in the time period from TM to T into the corresponding preset first machine learning model to predict the predicted circuit data in the future time period from T to T+M; The first fault diagnosis module 230 is used to construct a circuit actual waveform diagram of the corresponding mining equipment according to the predicted circuit data in the future period from T to T+M, and obtain the circuit fault result of the mining equipment according to the circuit actual waveform diagram, wherein the circuit fault result includes a circuit abnormal band diagram and a circuit fault starting period; A second fault diagnosis module 240 is used to input the circuit abnormality band diagram into the corresponding preset second machine learning model to determine the fault cause of the corresponding mining equipment; The fault warning module 250 is used to issue a fault warning according to the starting period of the circuit fault of the mining equipment and the fault cause.

[0025] Example 3: Please refer to Figure 3 As shown, this embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the mining circuit fault self-diagnosis method provided by any one of the above methods.

[0026] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for self-diagnosis of a mining circuit fault in the embodiment of the present application, based on the method for self-diagnosis of a mining circuit fault introduced in the embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements the electronic device used in the method for self-diagnosis of a mining circuit fault in the embodiment of the present application, it belongs to the scope of protection of the present application.

[0027] Example 4: Please refer to Figure 4 As shown, this embodiment discloses a computer-readable storage medium, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the mining circuit fault self-diagnosis method provided by any one of the above methods.

[0028] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0029] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0030] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0031] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0032] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0033] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0034] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0035] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for self-diagnosis of mining circuit faults, characterized in that: The method comprises: Obtain the type of mining equipment, and obtain the circuit sensing data and circuit impact data of the mining equipment in the period from TM to T, where T and M are both integers greater than zero; Matching the corresponding preset first machine learning model and the preset second machine learning model according to the type of mining equipment, inputting the circuit sensing data and the circuit impact data in the time period from TM to T into the corresponding preset first machine learning model to predict the predicted circuit data in the future time period from T to T+M; Constructing a circuit actual waveform diagram of the corresponding mining equipment according to the predicted circuit data in the future period from T to T+M, and obtaining a circuit fault result of the mining equipment according to the circuit actual waveform diagram, wherein the circuit fault result includes a circuit abnormal band diagram and a circuit fault starting period; Inputting the circuit abnormal band diagram into the corresponding preset second machine learning model to determine the cause of the failure of the corresponding mining equipment; Fault warning is carried out according to the starting period and cause of circuit fault of mining equipment.

2. The method for self-diagnosis of mining circuit faults according to claim 1, characterized in that: The circuit sensing data includes the actual measured value of current, voltage and resistance of the built-in circuit of the mining equipment; the circuit influence data includes internal influence data and external influence data; the internal influence data includes the actual measured value of circuit temperature and the actual measured value of circuit vibration of the built-in circuit of the mining equipment; the external influence data includes the actual measured value of ambient temperature and the actual measured value of ambient humidity of the environment in which the mining equipment is located.

3. The method for self-diagnosis of mining circuit faults according to claim 2, characterized in that: The matching corresponding preset first machine learning model and preset second machine learning model includes: Extracting the mining equipment type corresponding to the mining equipment, and extracting a mapping relationship library between the mining equipment type and the model data; the model data includes a preset first machine learning model and a preset second machine learning model associated with the corresponding mining equipment type; The mining equipment type is input into the mapping relationship library for relationship matching to obtain model data corresponding to the mining equipment type.

4. The method for self-diagnosis of mining circuit faults according to claim 3, characterized in that: The generation logic of the preset first machine learning model is as follows: Acquire historical circuit training data, and divide the historical circuit training data into a circuit data training set and a circuit data test set; the historical circuit training data includes circuit feature data and its corresponding predicted circuit data; Wherein, the circuit characteristic data includes circuit sensing data and circuit influence data; the predicted circuit data includes one of a current prediction value, a voltage prediction value or a resistance prediction value; Construct a regression network, use the circuit feature data in the circuit data training set as the input feature of the regression network, and use the predicted circuit data in the circuit data training set as the output feature of the regression network, perform model training on the regression network, and obtain an initial regression network; The initial regression network is model verified using the circuit data test set, and an initial regression network that is less than or equal to a preset test error threshold is output as the preset first machine learning model.

5. The method for self-diagnosis of mining circuit faults according to claim 4, characterized in that: The actual waveform diagram of the circuit is one of a current waveform diagram, a voltage waveform diagram or a resistance waveform diagram.

6. The method for self-diagnosis of mining circuit faults according to claim 5, characterized in that: The method of obtaining the circuit fault result of the mining equipment according to the actual circuit waveform diagram includes: The actual circuit waveform diagram of the mining equipment is equally divided to obtain N subdivided bands in the actual circuit waveform diagram, where N is an integer greater than zero; Obtain a pre-stored circuit standard waveform diagram, calculate the difference between the circuit standard waveform diagram and each image form subdivided band, and obtain Q differences, where Q is an integer greater than zero; Sort the Q differences in descending order, and use the subdivided band corresponding to the first difference in the sorting order as the circuit abnormality band diagram; The time interval of the circuit abnormality band diagram is extracted, and the time interval of the circuit abnormality band diagram is used as the starting period of the circuit fault.

7. The method for self-diagnosis of mining circuit faults according to claim 6, characterized in that: The generation logic of the preset second machine learning model is as follows: Acquire historical fault diagnosis training data, and divide the historical fault diagnosis training data into a fault diagnosis training set and a fault diagnosis test set; the historical fault diagnosis training data includes a circuit abnormal band diagram and annotated labels of corresponding fault causes; Construct a classifier, use the circuit abnormal band map in the fault diagnosis training set as the input data of the classifier, and use the label of the fault cause in the fault diagnosis training set as the input data of the classifier, train the classifier, and obtain an initial classification network; The initial classification network is model verified using the fault diagnosis test set, and the initial classification network with a test accuracy greater than or equal to a preset threshold is output as the preset second machine learning model.

8. A mine circuit fault self-diagnosis system, characterized in that: include: The data collection module is used to obtain the type of mining equipment, and to obtain the circuit sensing data and circuit impact data of the mining equipment in the period from TM to T, where T and M are both integers greater than zero; A data prediction module is used to match the corresponding preset first machine learning model and the preset second machine learning model according to the type of mining equipment, and input the circuit sensing data and circuit impact data in the time period from TM to T into the corresponding preset first machine learning model to predict the predicted circuit data in the future time period from T to T+M; The first fault diagnosis module is used to construct a circuit actual waveform diagram of the corresponding mining equipment according to the predicted circuit data in the future period from T to T+M, and obtain the circuit fault result of the mining equipment according to the circuit actual waveform diagram, wherein the circuit fault result includes a circuit abnormal band diagram and a circuit fault starting period; A second fault diagnosis module is used to input the circuit abnormality band diagram into the corresponding preset second machine learning model to determine the fault cause of the corresponding mining equipment; The fault warning module is used to provide fault warning according to the starting period and cause of the circuit fault of the mining equipment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the mining circuit fault self-diagnosis method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for self-diagnosis of mining circuit faults according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Fault diagnosis method for mine fan

    CN109826818A

  • Fault recording method and system and terminal equipment

    CN110751045A

  • Power transmission line fault classification method and device

    CN111856209A

  • Cascaded multilevel inverter open-circuit fault identification and positioning method and system

    CN111948573A

  • BiGRU-based intelligent electric meter metering module fault prediction and diagnosis method

    CN112763967A

Cited By

  • Data enhancement type permanent magnet synchronous motor test method and system

    CN119147964A