A data modeling method and system for reliability analysis of mine power supply equipment

Abstract

The present invention provides a data modeling method and system for reliability analysis of mine power supply equipment, including: respectively collecting equipment operation data corresponding to each power supply equipment, obtaining effective equipment data corresponding to each mining area through preprocessing and performing neural network training and decision training, constructing a reliability model corresponding to each power supply equipment, operating the reliability model to obtain several equipment evaluation values ​​of the corresponding power supply equipment to derive the operation reliability parameters of the power supply equipment, determining the fault operation trend of the corresponding power supply equipment based on the operation reliability parameters, generating and displaying fault maintenance suggestions in combination with the equipment functions of the corresponding power supply equipment, simulating the corresponding fault maintenance suggestions using the reliability model, transmitting the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display, and improving the fault prediction and management capabilities of the power supply equipment through data collection, modeling analysis and reliability evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of reliability modeling and analysis, and in particular to a data modeling method and system for reliability analysis of mining power supply equipment. Background Art

[0002] Mine power supply equipment is designed and manufactured specifically for power supply in specialized environments such as mines and mining areas. This equipment typically requires high levels of safety, reliability, durability, and protection against explosions, moisture, and dust to withstand the harsh conditions found in mining environments. Its primary function is to provide stable and safe power to various equipment used in mining operations. Mine power supply equipment is essential infrastructure for safe and efficient mine operations, encompassing everything from power transformation, transmission, and distribution to various electrical equipment and control systems. Due to the unique nature of mining environments, mine power supply equipment must demonstrate a high degree of safety, stability, reliability, and robust protection.

[0003] With the development of automated and intelligent mining, intelligent monitoring and remote control of mine power supply equipment are becoming a trend, improving the efficiency and safety of mine power management. However, current monitoring and control systems rely on manual analysis of equipment data to achieve monitoring and control. While these systems can achieve the desired monitoring and control goals, they can suffer from significant errors, often resulting in inferences only minutes before a mine accident occurs.

[0004] Therefore, the present invention provides a data modeling method and system for reliability analysis of mining power supply equipment. Summary of the Invention

[0005] The present invention provides a data modeling method and system for reliability analysis of mining power supply equipment, which improves the fault prediction and management capabilities of power supply equipment through data collection, modeling analysis and reliability evaluation.

[0006] The present invention provides a data modeling method for reliability analysis of mine power supply equipment, comprising:

[0007] Step 1: respectively collecting the equipment operation data corresponding to each power supply equipment, and pre-processing each of the equipment operation data to obtain the valid equipment data corresponding to each mining area;

[0008] Step 2: Performing neural network training and decision training on each valid device data respectively, obtaining a number of device modeling conditions corresponding to each power supply device, and constructing a reliability model corresponding to each power supply device;

[0009] Step 3: Run the reliability model to obtain several equipment evaluation values ​​corresponding to the power supply equipment, and derive the operation reliability parameters of the power supply equipment based on the equipment evaluation values;

[0010] Step 4: determining a fault operation trend of the power supply device based on the operational reliability parameter, generating and displaying a fault maintenance suggestion in combination with the device function of the power supply device;

[0011] Step 5: Utilize the reliability model to simulate the corresponding fault maintenance suggestion, and transmit the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display.

[0012] In one practicable manner,

[0013] Also includes:

[0014] A three-dimensional visual dynamic diagram of the corresponding power supply equipment is created based on the fault maintenance information and transmitted to the power supply monitoring platform for display.

[0015] In one practicable manner,

[0016] The step 1 comprises:

[0017] Step 11: Count the power supply equipment list corresponding to each mining area and generate equipment verification conditions for each mining area;

[0018] Step 12: using the equipment verification conditions to identify and verify the equipment attributes corresponding to each of the power supply equipment, and determining the mining area to which each of the power supply equipment belongs;

[0019] Step 13: Synchronously clean and normalize the equipment operation data corresponding to the same power supply equipment in the mining area to obtain and store the valid equipment data corresponding to each mining area.

[0020] In one practicable manner,

[0021] The step 12 comprises:

[0022] Step 121: using the equipment verification conditions, classify the equipment attributes corresponding to each power supply equipment into a plurality of equipment categories, and determine the mining area to which each power supply equipment belongs;

[0023] Step 122: Screening the overlapping power supply equipment and corresponding overlapping equipment attributes between different mining areas, determining the established power supply equipment corresponding to each mining area, and determining the unmatched conditions corresponding to each mining area based on the matching information between the established equipment attributes corresponding to each established power supply equipment and the corresponding equipment verification conditions;

[0024] Step 123: Identify the condition value corresponding to each of the unmatched conditions respectively, match the attribute value corresponding to each of the overlapping equipment attributes with the condition value respectively, and match the corresponding mining area for each of the overlapping power supply equipment based on the matching results.

[0025] In one practicable manner,

[0026] The step 13 includes:

[0027] Step 131: Time-check and sort the equipment operation data corresponding to the same power supply equipment in the mining area to obtain a plurality of synchronous operation data corresponding to each mining area, and clean each synchronous operation data using a preset cleaning rule to obtain a plurality of data defects corresponding to each synchronous operation data;

[0028] Step 132: Identify the defect location and defect attribute of each data defect in the corresponding synchronous operation data, determine a number of defect items corresponding to each synchronous operation data, perform corresponding defect processing on each defect item, normalize the processed synchronous operation data, and construct valid equipment data corresponding to each mining area;

[0029] Step 133: Counting a number of valid equipment data corresponding to each of the mining areas, constructing the equipment synchronization status corresponding to the mining area, and synchronously storing the valid equipment data and equipment synchronization status corresponding to each of the mining areas.

[0030] In one practicable manner,

[0031] The step 2 comprises:

[0032] Step 21: Using a BP neural network to train each valid device data, obtain the output features corresponding to each valid device data at each network layer of the BP neural network, and establish the operation prediction information and operation error information corresponding to each power supply device in combination with the network function corresponding to each network layer;

[0033] Step 22: constructing a prediction decision tree based on the operation prediction information and the operation error information corresponding to each power supply device, and performing ensemble training on each tree node in the prediction decision tree using random forest to obtain a plurality of device structure information corresponding to each power supply device;

[0034] Step 23: Based on the operation prediction information and the operation error information, several fault standard features corresponding to the power supply equipment are established, each of the equipment structure information is converted into equipment modeling conditions, and the equipment model corresponding to the power supply equipment is constructed using the equipment modeling conditions. The function of the equipment model is corrected using the corresponding fault standard features to obtain the reliability model corresponding to each of the power supply equipment.

[0035] In one practicable manner,

[0036] The step 3 comprises:

[0037] Step 31: Run the reliability model to obtain a number of predicted operating data of the power supply device, construct the predicted operating states of the power supply device at different prediction times based on the predicted operating data, and evaluate the failure rate corresponding to each predicted operating state;

[0038] Step 32: Constructing device performance conversion characteristics corresponding to the power supply device at different prediction times based on the predicted operation data, and performing fault identification on the predicted operation data using the fault information set corresponding to each power supply device to obtain potential fault attributes corresponding to the power supply device at different prediction times;

[0039] Step 33: Comprehensively evaluate the failure rate, device performance conversion characteristics, and potential failure attributes of the power supply device at different prediction times using preset evaluation criteria to obtain several device evaluation values ​​corresponding to the power supply device at different prediction times;

[0040] Step 34: Construct the change trend corresponding to each equipment evaluation value, deduce the device operation law corresponding to each equipment component in the power supply equipment, use the predicted operating status to construct the overall operation law of the power supply equipment, use the overall operation law to proportionally calculate the device operation law, and obtain the operation reliability parameters corresponding to the equipment component.

[0041] In one practicable manner,

[0042] The step 4 comprises:

[0043] Step 41: constructing an operation stability feature corresponding to the power supply device based on the operation reliability parameter; when the operation stability feature is abnormal, inputting each of the operation reliability parameters into the reliability model for reliability analysis to obtain information on the impact of each of the operation reliability parameters on the power supply device;

[0044] Step 42: training the impact performance information to generate a fault operation trend of the power supply device, using the fault operation trend to identify the corresponding device function, and determining several functional abnormality characteristics of the power supply device;

[0045] Step 43: Searching for the abnormal maintenance method corresponding to each of the functional abnormality characteristics, generating and displaying a fault maintenance suggestion for the power supply equipment.

[0046] In one practicable manner,

[0047] The step 5 comprises:

[0048] Step 51: converting the fault maintenance suggestion into a plurality of maintenance operation conditions, simulating the maintenance operation conditions using the corresponding reliability model, adjusting the operation sequence corresponding to each maintenance operation condition, and obtaining a plurality of simulation maintenance results;

[0049] Step 52: Evaluate the efficiency and quality of each of the simulated maintenance results, select the maintenance results with the highest efficiency and the highest quality, and establish an effective maintenance plan for the corresponding power supply equipment using the corresponding target operation sequence;

[0050] Step 53: Based on the fault maintenance suggestion, several faults to be maintained of the power supply equipment are determined, and fault maintenance information of the power supply equipment is generated in combination with the corresponding effective maintenance plan. Each piece of fault maintenance information is transmitted to the power supply system monitoring platform of the corresponding mining area for display.

[0051] This embodiment provides a data modeling system for reliability analysis of mining power supply equipment, including:

[0052] A data acquisition module is used to respectively collect the equipment operation data corresponding to each power supply device, and pre-process each of the equipment operation data to obtain the valid equipment data corresponding to each mining area;

[0053] A modeling execution module is used to perform neural network training and decision training on each of the valid device data, obtain a plurality of device modeling conditions corresponding to each of the power supply devices, and construct a reliability model corresponding to each of the power supply devices;

[0054] a reliability evaluation module, configured to execute the reliability model to obtain a plurality of equipment evaluation values ​​corresponding to the power supply equipment, and derive operational reliability parameters of the power supply equipment based on the equipment evaluation values;

[0055] a fault identification module, configured to determine a fault operation trend corresponding to the power supply device based on the operation reliability parameter, and generate and display a fault maintenance suggestion in combination with the device function of the power supply device;

[0056] The maintenance execution module is used to use the reliability model to simulate the corresponding fault maintenance suggestion and transmit the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display.

[0057] The achievable beneficial effects of the above technical solution are: in order to effectively ensure the safe and stable operation of mine power supply equipment, neural network training and decision training are performed on the equipment operation data generated by the power supply equipment in each mine area during operation, and the equipment modeling conditions of each power supply equipment are obtained, thereby constructing a reliability model of the power supply equipment. By running the model, the equipment evaluation value of the power supply equipment is determined, and the operating reliability parameters of the power supply equipment are further derived to determine the fault operation trend of the power supply equipment, and then fault maintenance suggestions are established for different faults. Finally, the fault maintenance information derived according to the reliability model is transmitted to the power supply system monitoring platform of the corresponding mine area for display. In this way, machine learning algorithms can be used to establish a reliability analysis model for power supply equipment, and the operating status and reliability evaluation results of the power supply equipment can be displayed, which can help relevant personnel predict the operation failures of power supply equipment, effectively improve the management efficiency of mine power supply equipment, and reduce equipment failure rates.

[0058] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1 A schematic diagram of the workflow of a data modeling method for reliability analysis of mining power supply equipment according to an embodiment of the present invention;

[0062] Figure 2 Schematic diagram of the composition of a data modeling system for reliability analysis of mining power supply equipment in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0064] Example 1

[0065] This embodiment provides a data modeling method for reliability analysis of mining power supply equipment. Figure 1 Shown, including:

[0066] Step 1: respectively collecting the equipment operation data corresponding to each power supply equipment, and pre-processing each of the equipment operation data to obtain the valid equipment data corresponding to each mining area;

[0067] Step 2: Performing neural network training and decision training on each valid device data respectively, obtaining a number of device modeling conditions corresponding to each power supply device, and constructing a reliability model corresponding to each power supply device;

[0068] Step 3: Run the reliability model to obtain several equipment evaluation values ​​corresponding to the power supply equipment, and derive the operation reliability parameters of the power supply equipment based on the equipment evaluation values;

[0069] Step 4: determining a fault operation trend of the power supply device based on the operational reliability parameter, generating and displaying a fault maintenance suggestion in combination with the device function of the power supply device;

[0070] Step 5: Utilize the reliability model to simulate the corresponding fault maintenance suggestion, and transmit the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display.

[0071] In this example, the device operation data refers to the data generated by the power supply device when it is working, and one power supply device corresponds to one piece of device operation data;

[0072] In this example, preprocessing includes data cleaning and normalization;

[0073] In this example, the equipment modeling conditions represent the conditions required to establish a reliability model;

[0074] In this example, the equipment evaluation value represents the result of a numerical evaluation of the operating status of the power supply equipment. The corresponding operating status includes: voltage, current, power, frequency, stability, load, power, vibration, noise, power quality, and energy efficiency;

[0075] In this example, the operation reliability parameter represents a parameter value corresponding to the reliability of the power supply equipment;

[0076] In this example, a power supply system monitoring platform is set up in each mining area.

[0077] The working principle and beneficial effects of the above technical solution: In order to effectively ensure the safe and stable operation of mine power supply equipment, neural network training and decision training are performed on the equipment operation data generated by the power supply equipment in each mine area during operation to obtain the equipment modeling conditions of each power supply equipment, thereby constructing a reliability model of the power supply equipment. By running the model, the equipment evaluation value of the power supply equipment is determined, and the operating reliability parameters of the power supply equipment are further derived to determine the fault operation trend of the power supply equipment, and then fault maintenance suggestions are established for different faults. Finally, the fault maintenance information derived based on the reliability model is transmitted to the power supply system monitoring platform of the corresponding mine area for display. In this way, machine learning algorithms can be used to establish a reliability analysis model for power supply equipment, and the operating status and reliability evaluation results of the power supply equipment can be displayed, which can help relevant personnel predict the operation failures of power supply equipment, effectively improve the management efficiency of mine power supply equipment, and reduce equipment failure rates.

[0078] Example 2

[0079] Based on Example 1, the data modeling method for reliability analysis of mining power supply equipment further includes:

[0080] A three-dimensional visual dynamic diagram of the corresponding power supply equipment is created based on the fault maintenance information and transmitted to the power supply monitoring platform for display.

[0081] The working principle and beneficial effects of the above technical solution: by displaying the operating status and reliability evaluation results of the equipment through three-dimensional or two-dimensional graphics, relevant personnel can understand the working conditions of the power supply equipment more intuitively.

[0082] Example 3

[0083] On the basis of Example 1, the data modeling method for reliability analysis of mining power supply equipment, step 1, comprises:

[0084] Step 11: Count the power supply equipment list corresponding to each mining area and generate equipment verification conditions for each mining area;

[0085] Step 12: using the equipment verification conditions to identify and verify the equipment attributes corresponding to each of the power supply equipment, and determining the mining area to which each of the power supply equipment belongs;

[0086] Step 13: Synchronously clean and normalize the equipment operation data corresponding to the same power supply equipment in the mining area to obtain and store the valid equipment data corresponding to each mining area.

[0087] In this example, since the mining areas vary in size, a larger mining area may have multiple power supply devices, so a list of power supply devices corresponding to each mining area is compiled in advance;

[0088] In this example, the device attribute represents the attribute of a power supply device and is used to distinguish different types of devices.

[0089] The working principle and beneficial effects of the above technical solution are as follows: before collecting the equipment operation data of the power supply equipment, the equipment verification conditions of each mining area are first determined according to the power supply equipment list of each mining area, and then the mining area to which each power supply equipment belongs is determined in combination with the attributes of the power supply equipment. Then, the equipment operation data of the same mining area are synchronously cleaned and normalized to obtain the valid equipment data of each mining area. In this way, the collected equipment operation data can be in an orderly transmission state, which can not only supervise each mining area, but also ensure the integrity of the equipment data, and avoid data loss and supervision failure.

[0090] Example 4

[0091] On the basis of Example 3, the data modeling method for reliability analysis of mining power supply equipment, step 12, includes:

[0092] Step 121: using the equipment verification conditions, classify the equipment attributes corresponding to each power supply equipment into a plurality of equipment categories, and determine the mining area to which each power supply equipment belongs;

[0093] Step 122: Screening the overlapping power supply equipment and corresponding overlapping equipment attributes between different mining areas, determining the established power supply equipment corresponding to each mining area, and determining the unmatched conditions corresponding to each mining area based on the matching information between the established equipment attributes corresponding to each established power supply equipment and the corresponding equipment verification conditions;

[0094] Step 123: Identify the condition value corresponding to each of the unmatched conditions respectively, match the attribute value corresponding to each of the overlapping equipment attributes with the condition value respectively, and match the corresponding mining area for each of the overlapping power supply equipment based on the matching results.

[0095] In this example, the equipment type represents the result of classifying the power supply equipment in the same mining area into one category;

[0096] In this example, overlapping power supply equipment means that one power supply equipment matches two or more mining areas;

[0097] In this example, establishing the power supply equipment means the power supply equipment corresponding to only one mining area;

[0098] In this example, the unmatched condition indicates that there is no equipment suitability condition with a matching result;

[0099] In this example, the condition value represents a value that needs to be satisfied when matching an unmatched condition.

[0100] The working principle and beneficial effects of the above technical solution are as follows: by using the equipment verification conditions to verify the properties of the power supply equipment, the power supply equipment is divided into several categories, the mining area to which each power supply equipment belongs is determined, and then the overlapping power supply equipment is secondary classified to determine the mining area to which each power supply equipment belongs. In this way, the location of each power supply equipment can be quickly determined, laying the foundation for subsequent reliability analysis.

[0101] Example 5

[0102] On the basis of Example 3, the data modeling method for reliability analysis of mining power supply equipment, step 13, includes:

[0103] Step 131: Time-check and sort the equipment operation data corresponding to the same power supply equipment in the mining area to obtain a plurality of synchronous operation data corresponding to each mining area, and clean each synchronous operation data using a preset cleaning rule to obtain a plurality of data defects corresponding to each synchronous operation data;

[0104] Step 132: Identify the defect location and defect attribute of each data defect in the corresponding synchronous operation data, determine a number of defect items corresponding to each synchronous operation data, perform corresponding defect processing on each defect item, normalize the processed synchronous operation data, and construct valid equipment data corresponding to each mining area;

[0105] Step 133: Counting a number of valid equipment data corresponding to each of the mining areas, constructing the equipment synchronization status corresponding to the mining area, and synchronously storing the valid equipment data and equipment synchronization status corresponding to each of the mining areas.

[0106] In this example, time verification sorting means first verifying the generation time of each piece of device operation data, and then sorting the operation device data in chronological order;

[0107] In this example, data defects include: outliers, format errors, data duplication, data missing, and data misalignment;

[0108] In this example, the defect item represents a defect in the synchronization operation data that needs to be processed;

[0109] In this example, the device synchronization state indicates the working state of the power supply device.

[0110] The working principle and beneficial effects of the above technical solution are as follows: by sorting the equipment operation data of each mining area by time, the synchronous operation data of each mining area is obtained, and further defects in the synchronous operation data are eliminated through data cleaning and normalization, and the data is adjusted to a unified format to obtain valid equipment data of each mining area. Finally, the equipment synchronization status of the mining area is constructed based on the valid equipment data and stored synchronously. In this way, defects in the data can be eliminated, ensuring that the obtained data can truly reflect the status of the equipment, and improving the accuracy and effectiveness of mining area supervision.

[0111] Example 6

[0112] Based on Example 1, the data modeling method for reliability analysis of mining power supply equipment, step 2, includes:

[0113] Step 21: Using a BP neural network to train each valid device data, obtain the output features corresponding to each valid device data at each network layer of the BP neural network, and establish the operation prediction information and operation error information corresponding to each power supply device in combination with the network function corresponding to each network layer;

[0114] Step 22: constructing a prediction decision tree based on the operation prediction information and the operation error information corresponding to each power supply device, and performing ensemble training on each tree node in the prediction decision tree using random forest to obtain a plurality of device structure information corresponding to each power supply device;

[0115] Step 23: Based on the operation prediction information and the operation error information, several fault standard features corresponding to the power supply equipment are established, each of the equipment structure information is converted into equipment modeling conditions, and the equipment model corresponding to the power supply equipment is constructed using the equipment modeling conditions. The function of the equipment model is corrected using the corresponding fault standard features to obtain the reliability model corresponding to each of the power supply equipment.

[0116] In this example, the network layer includes input layer, hidden layer and output layer;

[0117] In this example, the output characteristics represent the characteristics of the data output after the valid device data passes through each network layer;

[0118] In this example, the operation prediction information represents information that predicts the power supply equipment will present during future operation;

[0119] In this example, the operation error information indicates the error that is predicted to be exhibited by the power supply equipment during future operation;

[0120] In this example, the prediction decision tree represents a tree diagram that constructs a structure about the operating equipment using the operation prediction information and the operation error information;

[0121] In this example, the fault standard feature represents the standard corresponding to when a type of fault occurs in the power supply equipment;

[0122] In this example, the device modeling condition represents the condition for building the device model;

[0123] In this example, function modification refers to the process of adjusting the fault threshold of each function in the device model according to the fault standard characteristics.

[0124] The working principle and beneficial effects of the above technical solution are as follows: the effective equipment data is trained through the BP neural network to determine the operation prediction information and operation error information of each power supply equipment, thereby constructing a prediction decision tree, and the prediction decision tree is integrated and trained using the random forest to obtain the equipment structure information of the power supply equipment, and further construct the fault standard characteristics of the power supply equipment, so that the equipment structure information can be converted into equipment modeling conditions to construct the equipment model of the power supply equipment, and further use the fault standard characteristics to perform functional correction on the equipment model to generate a reliability model of the power supply equipment. In this way, a reliability model can be established for each power supply equipment, and the model is completely consistent with the function of the power supply equipment, so that the model can better identify the reliability of the power supply equipment.

[0125] Example 7

[0126] Based on Example 1, the data modeling method for reliability analysis of mining power supply equipment, step 3, includes:

[0127] Step 31: Run the reliability model to obtain a number of predicted operating data of the power supply device, construct the predicted operating states of the power supply device at different prediction times based on the predicted operating data, and evaluate the failure rate corresponding to each predicted operating state;

[0128] Step 32: Constructing device performance conversion characteristics corresponding to the power supply device at different prediction times based on the predicted operation data, and performing fault identification on the predicted operation data using the fault information set corresponding to each power supply device to obtain potential fault attributes corresponding to the power supply device at different prediction times;

[0129] Step 33: Comprehensively evaluate the failure rate, device performance conversion characteristics, and potential failure attributes of the power supply device at different prediction times using preset evaluation criteria to obtain several device evaluation values ​​corresponding to the power supply device at different prediction times;

[0130] Step 34: Construct the change trend corresponding to each equipment evaluation value, deduce the device operation law corresponding to each equipment component in the power supply equipment, use the predicted operating status to construct the overall operation law of the power supply equipment, use the overall operation law to proportionally calculate the device operation law, and obtain the operation reliability parameters corresponding to the equipment component.

[0131] In this example, the device performance conversion characteristics represent characteristics of changes in the operating functions of the power supply equipment at different times;

[0132] In this example, the potential fault attribute represents the possible faults of the power supply equipment at different prediction moments;

[0133] In this example, comprehensive evaluation refers to the process of comprehensively evaluating the performance of the power supply equipment.

[0134] The working principle and beneficial effects of the above technical solution are as follows: the predicted operation data of the power supply equipment is obtained through the operation reliability model, and then the predicted operation status corresponding to the power supply equipment at different prediction times is constructed to evaluate its failure rate. At the same time, a comprehensive evaluation is performed on the equipment performance conversion characteristics and potential fault attributes at different prediction times, and the evaluation value of the power supply equipment at different prediction times is obtained. By analyzing the device operation rules of each equipment component and the overall operation rules of the power supply equipment, a number of operation reliability parameters of the power supply equipment are generated. In this way, the functions of the power supply equipment can be comprehensively analyzed and effectively and accurately predicted.

[0135] Example 8

[0136] On the basis of Example 1, the data modeling method for reliability analysis of mining power supply equipment, step 4, includes:

[0137] Step 41: constructing an operation stability feature corresponding to the power supply device based on the operation reliability parameter; when the operation stability feature is abnormal, inputting each of the operation reliability parameters into the reliability model for reliability analysis to obtain information on the impact of each of the operation reliability parameters on the power supply device;

[0138] Step 42: training the impact performance information to generate a fault operation trend of the power supply device, using the fault operation trend to identify the corresponding device function, and determining several functional abnormality characteristics of the power supply device;

[0139] Step 43: Searching for the abnormal maintenance method corresponding to each of the functional abnormality characteristics, generating and displaying a fault maintenance suggestion for the power supply equipment.

[0140] In this example, the impact performance information indicates the impact of the operation reliability parameter on the power supply equipment.

[0141] The working principle and beneficial effects of the above technical solution are as follows: when the power supply equipment is in an unstable operating state, its operating reliability parameters are input into the corresponding reliability model for analysis, and the influence of each operating reliability parameter on the power supply equipment is trained to determine the fault operation trend of the power supply equipment, thereby determining the functional abnormality characteristics of the power supply equipment. Finally, according to the abnormal maintenance method corresponding to each functional abnormality characteristic, the fault maintenance recommendation of the power supply equipment is constructed to provide complete and accurate fault maintenance recommendations to relevant personnel, helping them make maintenance decisions.

[0142] Example 9

[0143] Based on Example 1, the data modeling method for reliability analysis of mining power supply equipment, step 5, includes:

[0144] Step 51: converting the fault maintenance suggestion into a plurality of maintenance operation conditions, simulating the maintenance operation conditions using the corresponding reliability model, adjusting the operation sequence corresponding to each maintenance operation condition, and obtaining a plurality of simulation maintenance results;

[0145] Step 52: Evaluate the efficiency and quality of each of the simulated maintenance results, select the maintenance results with the highest efficiency and the highest quality, and establish an effective maintenance plan for the corresponding power supply equipment using the corresponding target operation sequence;

[0146] Step 53: Based on the fault maintenance suggestion, several faults to be maintained of the power supply equipment are determined, and fault maintenance information of the power supply equipment is generated in combination with the corresponding effective maintenance plan. Each piece of fault maintenance information is transmitted to the power supply system monitoring platform of the corresponding mining area for display.

[0147] In this example, efficiency evaluation represents the process of analyzing the failure maintenance efficiency of each simulated maintenance result;

[0148] In this example, quality evaluation refers to the process of analyzing the fault maintenance quality of each simulated maintenance result.

[0149] The working principle and beneficial effects of the above technical solution are as follows: the reliability model is used to simulate maintenance fault suggestions, and the execution process of the maintenance fault suggestions is adjusted during the simulation process to generate a high-efficiency, high-quality maintenance plan. Then, the fault maintenance information of the power supply equipment is constructed in combination with the maintenance faults of the power supply equipment and transmitted to the corresponding power supply system monitoring platform for display. In this way, not only fault warning can be achieved, but also an effective fault maintenance visit can be generated, providing technical reference for the emergency work of relevant personnel.

[0150] Example 10

[0151] This embodiment provides a data modeling system for reliability analysis of mining power supply equipment. Figure 2 Shown, including:

[0152] A data acquisition module is used to respectively collect the equipment operation data corresponding to each power supply device, and pre-process each of the equipment operation data to obtain the valid equipment data corresponding to each mining area;

[0153] A modeling execution module is used to perform neural network training and decision training on each of the valid device data, obtain a plurality of device modeling conditions corresponding to each of the power supply devices, and construct a reliability model corresponding to each of the power supply devices;

[0154] a reliability evaluation module, configured to execute the reliability model to obtain a plurality of equipment evaluation values ​​corresponding to the power supply equipment, and derive operational reliability parameters of the power supply equipment based on the equipment evaluation values;

[0155] a fault identification module, configured to determine a fault operation trend corresponding to the power supply device based on the operation reliability parameter, and generate and display a fault maintenance suggestion in combination with the device function of the power supply device;

[0156] The maintenance execution module is used to use the reliability model to simulate the corresponding fault maintenance suggestion and transmit the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display.

[0157] In this example, the device operation data refers to the data generated by the power supply device when it is working, and one power supply device corresponds to one piece of device operation data;

[0158] In this example, preprocessing includes data cleaning and normalization;

[0159] In this example, the equipment modeling conditions represent the conditions required to establish a reliability model;

[0160] In this example, the equipment evaluation value represents the result of a numerical evaluation of the operating status of the power supply equipment. The corresponding operating status includes: voltage, current, power, frequency, stability, load, power, vibration, noise, power quality, and energy efficiency;

[0161] In this example, the operation reliability parameter represents a parameter value corresponding to the reliability of the power supply equipment;

[0162] In this example, a power supply system monitoring platform is set up in each mining area.

[0163] The working principle and beneficial effects of the above technical solution: In order to effectively ensure the safe and stable operation of mine power supply equipment, neural network training and decision training are performed on the equipment operation data generated by the power supply equipment in each mine area during operation to obtain the equipment modeling conditions of each power supply equipment, thereby constructing a reliability model of the power supply equipment. By running the model, the equipment evaluation value of the power supply equipment is determined, and the operating reliability parameters of the power supply equipment are further derived to determine the fault operation trend of the power supply equipment, and then fault maintenance suggestions are established for different faults. Finally, the fault maintenance information derived based on the reliability model is transmitted to the power supply system monitoring platform of the corresponding mine area for display. In this way, machine learning algorithms can be used to establish a reliability analysis model for power supply equipment, and the operating status and reliability evaluation results of the power supply equipment can be displayed, which can help relevant personnel predict the operation failures of power supply equipment, effectively improve the management efficiency of mine power supply equipment, and reduce equipment failure rates.

[0164] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A data modeling method for reliability analysis of mine power supply equipment, characterized in that: include: Step 1: respectively collecting the equipment operation data corresponding to each power supply equipment, and pre-processing each of the equipment operation data to obtain the valid equipment data corresponding to each mining area; Step 2: Performing neural network training and decision training on each valid device data respectively, obtaining a number of device modeling conditions corresponding to each power supply device, and constructing a reliability model corresponding to each power supply device; Step 3: Run the reliability model to obtain several equipment evaluation values ​​corresponding to the power supply equipment, and derive the operation reliability parameters of the power supply equipment based on the equipment evaluation values; Step 4: determining a fault operation trend of the power supply device based on the operational reliability parameter, generating and displaying a fault maintenance suggestion in combination with the device function of the power supply device; Step 5: Utilize the reliability model to simulate the corresponding fault maintenance suggestion, and transmit the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display; The step 2 comprises: Step 21: Using a BP neural network to train each valid device data, obtain the output features corresponding to each valid device data at each network layer of the BP neural network, and establish the operation prediction information and operation error information corresponding to each power supply device in combination with the network function corresponding to each network layer; Step 22: constructing a prediction decision tree based on the operation prediction information and the operation error information corresponding to each power supply device, and performing ensemble training on each tree node in the prediction decision tree using random forest to obtain a plurality of device structure information corresponding to each power supply device; Step 23: Based on the operation prediction information and the operation error information, several fault standard features corresponding to the power supply equipment are established, each of the equipment structure information is converted into equipment modeling conditions, and the equipment model corresponding to the power supply equipment is constructed using the equipment modeling conditions. The function of the equipment model is corrected using the corresponding fault standard features to obtain the reliability model corresponding to each of the power supply equipment.

2. The data modeling method for reliability analysis of mining power supply equipment according to claim 1, characterized in that: Also includes: A three-dimensional visual dynamic diagram of the corresponding power supply equipment is created based on the fault maintenance information and transmitted to the power supply system monitoring platform for display.

3. The data modeling method for reliability analysis of mining power supply equipment according to claim 1, characterized in that: The step 1 comprises: Step 11: Count the power supply equipment list corresponding to each mining area and generate equipment verification conditions for each mining area; Step 12: using the equipment verification conditions to identify and verify the equipment attributes corresponding to each of the power supply equipment, and determining the mining area to which each of the power supply equipment belongs; Step 13: Synchronously clean and normalize the equipment operation data corresponding to the same power supply equipment in the mining area to obtain and store the valid equipment data corresponding to each mining area.

4. A data modeling method for reliability analysis of mine power supply equipment according to claim 3, characterized in that: The step 12 comprises: Step 121: using the equipment verification conditions, classify the equipment attributes corresponding to each power supply equipment into a plurality of equipment categories, and determine the mining area to which each power supply equipment belongs; Step 122: Screening the overlapping power supply equipment and corresponding overlapping equipment attributes between different mining areas, determining the established power supply equipment corresponding to each mining area, and determining the unmatched conditions corresponding to each mining area based on the matching information between the established equipment attributes corresponding to each established power supply equipment and the corresponding equipment verification conditions; Step 123: Identify the condition value corresponding to each of the unmatched conditions respectively, match the attribute value corresponding to each of the overlapping equipment attributes with the condition value respectively, and match the corresponding mining area for each of the overlapping power supply equipment based on the matching results.

5. The data modeling method for reliability analysis of mining power supply equipment according to claim 3, characterized in that: The step 13 includes: Step 131: Time-check and sort the equipment operation data corresponding to the same power supply equipment in the mining area to obtain a plurality of synchronous operation data corresponding to each mining area, and clean each synchronous operation data using a preset cleaning rule to obtain a plurality of data defects corresponding to each synchronous operation data; Step 132: Identify the defect location and defect attribute of each data defect in the corresponding synchronous operation data, determine a number of defect items corresponding to each synchronous operation data, perform corresponding defect processing on each defect item, normalize the processed synchronous operation data, and construct valid equipment data corresponding to each mining area; Step 133: Counting a number of valid equipment data corresponding to each of the mining areas, constructing the equipment synchronization status corresponding to the mining area, and synchronously storing the valid equipment data and equipment synchronization status corresponding to each of the mining areas.

6. The data modeling method for reliability analysis of mining power supply equipment according to claim 1, characterized in that: The step 3 comprises: Step 31: Run the reliability model to obtain a number of predicted operating data of the power supply device, construct the predicted operating states of the power supply device at different prediction times based on the predicted operating data, and evaluate the failure rate corresponding to each predicted operating state; Step 32: Constructing device performance conversion characteristics corresponding to the power supply device at different prediction times based on the predicted operation data, and performing fault identification on the predicted operation data using the fault information set corresponding to each power supply device to obtain potential fault attributes corresponding to the power supply device at different prediction times; Step 33: Comprehensively evaluate the failure rate, device performance conversion characteristics, and potential failure attributes of the power supply device at different prediction times using preset evaluation criteria to obtain several device evaluation values ​​corresponding to the power supply device at different prediction times; Step 34: Construct the change trend corresponding to each equipment evaluation value, deduce the device operation law corresponding to each equipment component in the power supply equipment, use the predicted operating status to construct the overall operation law of the power supply equipment, use the overall operation law to proportionally calculate the device operation law, and obtain the operation reliability parameters corresponding to the equipment component.

7. The data modeling method for reliability analysis of mining power supply equipment according to claim 1, characterized in that: The step 4 comprises: Step 41: constructing an operation stability feature corresponding to the power supply device based on the operation reliability parameter; when the operation stability feature is abnormal, inputting each of the operation reliability parameters into the reliability model for reliability analysis to obtain information on the impact of each of the operation reliability parameters on the power supply device; Step 42: training the impact performance information to generate a fault operation trend of the power supply device, using the fault operation trend to identify the corresponding device function, and determining several functional abnormality characteristics of the power supply device; Step 43: Searching for the abnormal maintenance method corresponding to each of the functional abnormality characteristics, generating and displaying a fault maintenance suggestion for the power supply equipment.

8. The data modeling method for reliability analysis of mining power supply equipment according to claim 1, characterized in that: The step 5 comprises: Step 51: converting the fault maintenance suggestion into a plurality of maintenance operation conditions, simulating the maintenance operation conditions using the corresponding reliability model, adjusting the operation sequence corresponding to each maintenance operation condition, and obtaining a plurality of simulation maintenance results; Step 52: Evaluate the efficiency and quality of each of the simulated maintenance results, select the maintenance results with the highest efficiency and the highest quality, and establish an effective maintenance plan for the corresponding power supply equipment using the corresponding target operation sequence; Step 53: Based on the fault maintenance suggestion, several faults to be maintained of the power supply equipment are determined, and fault maintenance information of the power supply equipment is generated in combination with the corresponding effective maintenance plan. Each piece of fault maintenance information is transmitted to the power supply system monitoring platform of the corresponding mining area for display.

9. A data modeling system for reliability analysis of mine power supply equipment, characterized in that: include: A data acquisition module is used to respectively collect the equipment operation data corresponding to each power supply device, and pre-process each of the equipment operation data to obtain the valid equipment data corresponding to each mining area; A modeling execution module is used to perform neural network training and decision training on each of the valid device data, obtain a plurality of device modeling conditions corresponding to each of the power supply devices, and construct a reliability model corresponding to each of the power supply devices; a reliability evaluation module, configured to execute the reliability model to obtain a plurality of equipment evaluation values ​​corresponding to the power supply equipment, and derive operational reliability parameters of the power supply equipment based on the equipment evaluation values; a fault identification module, configured to determine a fault operation trend corresponding to the power supply device based on the operation reliability parameter, and generate and display a fault maintenance suggestion in combination with the device function of the power supply device; a maintenance execution module, configured to simulate the corresponding fault maintenance suggestion using the reliability model, and transmit the generated fault maintenance information to the power supply system monitoring platform of the corresponding mining area for display; The modeling execution module performs neural network training and decision training on each valid device data, obtains a plurality of device modeling conditions corresponding to each power supply device, and constructs a reliability model corresponding to each power supply device, including: Using a BP neural network to train each of the valid device data, respectively, to obtain the output features corresponding to each network layer of the BP neural network for each of the valid device data, and combining the network functions corresponding to each of the network layers to establish the operation prediction information and operation error information corresponding to each of the power supply devices; Constructing a prediction decision tree based on the operation prediction information and the operation error information corresponding to each power supply device, and using random forest to perform ensemble training on each tree node in the prediction decision tree to obtain a plurality of device structure information corresponding to each power supply device; Based on the operation prediction information and the operation error information, several fault standard characteristics of the corresponding power supply equipment are established, and each of the equipment structure information is converted into equipment modeling conditions respectively. The equipment modeling conditions are used to construct the equipment model corresponding to the power supply equipment, and the corresponding fault standard characteristics are used to perform functional corrections on the equipment model to obtain the reliability model corresponding to each of the power supply equipment.

Images