A method and system for operation and maintenance management of the status of 5G communication base station equipment

Abstract

The present invention discloses a method and system for operation and maintenance management of the status of 5G communication base station equipment, which relates to the technical field of data processing. The method includes: preprocessing real-time operation status data; constructing an equipment degradation model based on historical maintenance data to determine the real-time degradation status of each unit in the 5G communication base station equipment; identifying prone-to-failure points based on the historical maintenance data combined with the real-time operation status data, and identifying potential failure points based on their real-time degradation status using an abductive reasoning network; monitoring the status of the prone-to-failure points and target potential failure points; judging whether equipment maintenance is required based on the status monitoring results. If so, a target maintenance plan is formulated based on the operation and maintenance model combined with equipment load analysis; equipment maintenance is carried out on the 5G communication base station equipment based on the target maintenance plan, and the equipment maintenance information is encrypted and uploaded to the cloud platform. The present invention enables the operation and maintenance management of 5G communication base station equipment to achieve a more ideal effect.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of data processing, and particularly relates to a method and system for operation and maintenance management of the status of 5G communication base station equipment. Background Art

[0002] As a key facility for users to obtain communication services, the security and reliability of the operation of 5G communication base stations are crucial for the operation stability of the entire communication network. And with the rapid development of 5G technology, the number of 5G communication base stations has further increased, which also makes the operation and maintenance management of the status of base station equipment an urgent technical problem to be solved. Currently, in the operation and maintenance management of the status of 5G communication base station equipment, it is usually through relevant operation and maintenance personnel to check the degradation status of each unit in the 5G communication base station equipment. However, this method is too dependent on the professional qualities of the operation and maintenance personnel, and cannot guarantee the accuracy of checking the degradation status of each unit in the communication base station equipment, which may lead to an unclear and specific understanding of the status of the communication base station equipment. At the same time, in the current operation and maintenance management of base station equipment status, the identification of potential fault points is lacking, resulting in the inability to timely detect the anomalies occurring at the potential fault points, affecting the timeliness of emergency repair of the target unit in the communication base station equipment, and having a great impact on the operation and maintenance management of 5G communication base stations. When there are relevant equipment units in the communication base station that need to be repaired, currently, the maintenance plan is usually determined through comparative analysis of the operating equipment parameters. However, the reliability of the maintenance plan determined by this method is not high, and at the same time, resource allocation is not taken into account, which may lead to low equipment repair quality, making the operation and maintenance management of 5G communication base station equipment fail to achieve the expected effect and affecting the reliability of the operation of the communication base station. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and system for operation and maintenance management of the status of 5G communication base station equipment, improving the reliability of the operation of the communication base station and enabling the operation and maintenance management of 5G communication base station equipment to achieve a more ideal effect.

[0004] To solve the above technical problems, the present invention provides a method for operation and maintenance management of the status of 5G communication base station equipment, and the method includes:

[0005] Obtain the real-time operation status data of each unit in the 5G communication base station equipment, and preprocess the real-time operation status data to obtain the preprocessed real-time operation status data;

[0006] Obtain the historical maintenance data of each unit, construct an equipment degradation model based on the historical maintenance data, and determine the real-time degradation status of each unit in the 5G communication base station equipment by using the preprocessed real-time operation status data based on the equipment degradation model;

[0007] Identify the failure-prone points based on the historical maintenance data combined with the preprocessed real-time operation status data, and identify the target potential failure points based on the real-time degradation status of each unit using the abductive reasoning network;

[0008] Monitor the status of the failure-prone points and target potential failure points to obtain the status monitoring results;

[0009] Based on the status monitoring results, determine whether equipment maintenance is required. If it is determined that equipment maintenance is required, formulate a target maintenance plan based on the operation and maintenance model using the status monitoring results combined with equipment load analysis;

[0010] Perform equipment maintenance on the 5G communication base station equipment based on the target maintenance plan, encrypt the equipment maintenance information, and upload the encrypted equipment maintenance information to the cloud platform.

[0011] Optionally, the preprocessing of the real-time operation status data to obtain the preprocessed real-time operation status data includes:

[0012] Perform noise reduction processing on the real-time operation status data to obtain the real-time operation status data after noise reduction processing;

[0013] Perform data transformation processing on the real-time operation status data after noise reduction processing to obtain the preprocessed real-time operation status data.

[0014] Optionally, the construction of the equipment degradation model based on the historical maintenance data includes:

[0015] Construct an equipment operation status parameter sequence and an equipment health status parameter sequence based on the historical maintenance data, and perform sensitive parameter screening based on the equipment operation status parameter sequence and the equipment health status parameter sequence to obtain the target sensitive parameters;

[0016] Obtain the influence parameters of the equipment degradation process based on the target sensitive parameters;

[0017] Obtain a number of preset degradation indicators, and establish an edge degradation model of the Wiener process based on the number of preset degradation indicators;

[0018] Construct an equipment degradation model based on the influence parameters and the edge degradation model.

[0019] Optionally, the determination of the real-time degradation status of each unit in the 5G communication base station equipment based on the equipment degradation model using the preprocessed real-time operation status data includes:

[0020] Determine the equipment decline amount based on the equipment degradation model using the preprocessed real-time operation status data;

[0021] Predict the service life of the target unit in the 5G communication base station equipment by using the preprocessed real-time operation status data based on the equipment degradation model, and determine the real-time degradation status of each unit in the 5G communication base station equipment based on the equipment degradation amount and service life.

[0022] Optionally, the identifying of the prone-to-failure points based on the historical maintenance data combined with the preprocessed real-time operation status data includes:

[0023] Calculate the failure parameters of each unit in the 5G communication base station equipment within a preset time period based on the historical maintenance data, and obtain the failure occurrence pattern based on the failure parameters within the preset time period;

[0024] Identify the prone-to-failure points based on the failure occurrence pattern by using the preset failure classification criteria combined with the preprocessed real-time operation status data.

[0025] Optionally, the identifying of the target potential failure points based on the abductive reasoning network by using the real-time degradation status of each unit includes:

[0026] Construct a three-dimensional digital model of each unit, and establish the functional association rules between each unit;

[0027] Perform limit working simulation on each unit based on the three-dimensional digital model and the functional association rules, obtain the corresponding limit working parameters, and obtain the abductive reasoning rule set by using the abductive reasoning network based on the corresponding limit working parameters and normal working parameters;

[0028] Determine the first potential failure point based on the abductive reasoning rule set;

[0029] Construct an equipment failure knowledge ontology, perform knowledge extraction by using machine learning based on the historical maintenance data to obtain the target knowledge, and construct a potential failure knowledge base based on the equipment failure knowledge ontology and the target knowledge;

[0030] Determine the second potential failure point based on the potential failure knowledge base combined with the real-time degradation status of each unit;

[0031] Determine the target potential failure point based on the first potential failure point and the second potential failure point.

[0032] Optionally, the performing of status monitoring on the prone-to-failure points and the target potential failure points to obtain the status monitoring result includes:

[0033] Adjust the monitoring parameters, and perform status monitoring on the prone-to-failure points and the target potential failure points based on the adjusted monitoring parameters to obtain the status monitoring result.

[0034] Optionally, the formulating of the target maintenance plan based on the operation and maintenance model by using the status monitoring result combined with the equipment load analysis includes:

[0035] Obtain operation and maintenance content information, and extract semantic keywords in the operation and maintenance semantic content corresponding to the operation and maintenance content information;

[0036] Perform content-level classification processing on the semantic keywords based on the operation and maintenance semantic content to obtain the content-level classification result of the semantic keywords;

[0037] Perform tree relationship construction processing on the semantic keywords corresponding to the content-level classification result to obtain a semantic keyword tree structure diagram;

[0038] Establish an index between the semantic keywords of each node in the semantic keyword tree structure diagram and their corresponding operation and maintenance semantic content to form an operation and maintenance policy knowledge graph, and construct an operation and maintenance model based on the operation and maintenance policy knowledge graph. Determine the initial maintenance plan based on the operation and maintenance model using the status monitoring results;

[0039] Obtain the running load condition of the operation and maintenance equipment during operation, and adjust the resource allocation and task scheduling of the operation and maintenance equipment based on the running load condition using the status monitoring results in combination with the resource scheduling dimension;

[0040] Improve the initial maintenance plan based on the adjusted resource allocation and task scheduling of the operation and maintenance equipment to obtain a target maintenance plan.

[0041] Optionally, performing equipment maintenance on the 5G communication base station equipment based on the target maintenance plan and encrypting the equipment maintenance information includes:

[0042] Schedule the corresponding operation and maintenance equipment to perform equipment maintenance on the 5G communication base station equipment based on the target maintenance plan, and perform asymmetric encryption on the equipment maintenance information to obtain the encrypted equipment maintenance information.

[0043] In addition, the present invention also provides a system for operation and maintenance management of the status of 5G communication base station equipment, and the system includes:

[0044] Data preprocessing module: used to obtain the real-time operation status data of each unit in the 5G communication base station equipment, and preprocess the real-time operation status data to obtain the preprocessed real-time operation status data;

[0045] Real-time degradation status determination module: used to obtain the historical maintenance data of each unit, construct an equipment degradation model based on the historical maintenance data, and determine the real-time degradation status of each unit in the 5G communication base station equipment based on the equipment degradation model using the preprocessed real-time operation status data;

[0046] Fault point identification module: used to identify prone fault points based on the historical maintenance data combined with the preprocessed real-time operation status data, and identify target potential fault points based on the abductive reasoning network using the real-time degradation status of each unit;

[0047] Fault point status monitoring module: used to monitor the status of the prone fault points and target potential fault points to obtain status monitoring results;

[0048] Maintenance plan formulation module: used to determine whether equipment maintenance is required based on the status monitoring results. If it is determined that equipment maintenance is required, a target maintenance plan is formulated based on the operation and maintenance model using the status monitoring results combined with equipment load analysis;

[0049] Equipment maintenance and maintenance information processing module: used to perform equipment maintenance on 5G communication base station equipment based on the target maintenance plan, encrypt the equipment maintenance information, and upload the encrypted equipment maintenance information to the cloud platform.

[0050] In the embodiment of the present invention, an equipment degradation model is constructed based on the equipment degradation impact parameters generated from historical maintenance data and the edge degradation model. According to the equipment degradation model, the real-time degradation status of each unit in the 5G communication base station equipment is determined, which can improve the accuracy of identifying the degradation status of each unit in the 5G communication base station equipment and more clearly understand the specific situation of the communication base station equipment. By determining the first potential fault points through the abductive reasoning rule set and the second potential fault points through the potential fault knowledge base to determine the target potential fault points, the accuracy of identifying potential fault points can be improved. Monitoring the status of potential fault points can timely detect abnormalities occurring in potential fault points and avoid affecting the emergency repair timeliness of the target unit in the communication base station equipment. When it is determined that there are relevant equipment units in the communication base station that need to be repaired, a target maintenance plan is formulated based on the operation and maintenance model using the status monitoring results combined with equipment load analysis, improving the reliability of the formulated maintenance plan, improving the equipment maintenance quality, and at the same time realizing the improvement of operation and maintenance management efficiency, effectively solving the problem of low operation and maintenance management efficiency in the prior art, and enabling the operation and maintenance management of 5G communication base station equipment to achieve a more ideal effect. Brief Description of the Drawings

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0052] Figure 1It is a schematic flowchart of a method for operation and maintenance management of the 5G communication base station equipment status in the first embodiment of the present invention;

[0053] Figure 2 It is a schematic flowchart of a method for operation and maintenance management of the 5G communication base station equipment status in the second embodiment of the present invention

[0054] Figure 3 It is a schematic diagram of the structural composition of a system for operation and maintenance management of the 5G communication base station equipment status in the embodiment of the present invention;

[0055] Figure 4 It is a schematic diagram of the structure of the abductive reasoning network in the embodiment of the present invention;

[0056] Figure 5 It is a schematic diagram of the 5G communication base station network topology in the embodiment of the present invention. Detailed implementation manners

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Embodiment 1

[0059] Please refer to Figure 1 , Figure 1 It is a schematic flowchart of a method for operation and maintenance management of the 5G communication base station equipment status in the first embodiment of the present invention, and the method includes:

[0060] S11: Obtain the real-time operation status data of each unit in the 5G communication base station equipment, and preprocess the real-time operation status data to obtain the preprocessed real-time operation status data;

[0061] In the specific implementation process of the present invention, the preprocessing of the real-time operation status data to obtain the preprocessed real-time operation status data includes: performing noise reduction processing on the real-time operation status data to obtain the real-time operation status data after noise reduction processing; performing data transformation processing on the real-time operation status data after noise reduction processing to obtain the preprocessed real-time operation status data.

[0062] Specifically, real-time operation status data of each unit in the 5G communication base station device is obtained through a data acquisition device. The data acquisition device may include an image acquisition device, a pressure sensor, a temperature sensor, etc. Each unit in the 5G communication base station device may include a baseband processing unit, an active antenna unit, a transmission unit, a power supply and a cooling unit, etc. The real-time operation status data may include the temperature, pressure and load conditions of each unit, etc. As Figure 5 shown, the real-time operation status data of each unit in the 5G communication base station device is obtained through the perception layer, and the real-time operation status data is input into the platform layer for processing through the relevant data transmission protocol of the access layer. The real-time operation status data is subjected to noise reduction processing, and the real-time operation status data is input into a denoising autoencoder for noise reduction processing to obtain the real-time operation status data after noise reduction processing. The real-time operation status data after noise reduction processing is subjected to data transformation processing, the data format of the real-time operation status data after noise reduction processing is converted, and the real-time operation status data after data format conversion is subjected to data transformation and dimensionality reduction. Data transformation and dimensionality reduction is to extract relevant features from the initial data features through clustering analysis and reduce the data dimensionality, so as to complete the data conversion processing and obtain the preprocessed real-time operation status data.

[0063] S12: Obtain the historical maintenance data of each unit, construct a device degradation model based on the historical maintenance data, and determine the real-time degradation status of each unit in the 5G communication base station device by using the preprocessed real-time operation status data based on the device degradation model;

[0064] In the specific implementation process of the present invention, the constructing a device degradation model based on the historical maintenance data includes: constructing a device operation status parameter sequence and a device health status parameter sequence based on the historical maintenance data, and performing sensitive parameter screening based on the device operation status parameter sequence and the device health status parameter sequence to obtain target sensitive parameters; obtaining influence parameters of the device degradation process based on the target sensitive parameters; obtaining a plurality of preset degradation indicators, and establishing a marginal degradation model of the Wiener process based on the plurality of preset degradation indicators; constructing a device degradation model based on the influence parameters and the marginal degradation model.

[0065] Further, the determining the real-time degradation status of each unit in the 5G communication base station device by using the preprocessed real-time operation status data based on the device degradation model includes: determining the device degradation amount by using the preprocessed real-time operation status data based on the device degradation model; predicting the service life of the target unit in the 5G communication base station device by using the preprocessed real-time operation status data based on the device degradation model, and determining the real-time degradation status of each unit in the 5G communication base station device based on the device degradation amount and the service life.

[0066] Specifically, obtain the historical maintenance data of each unit from the database. The historical maintenance data includes the failure conditions, failure times, usage durations, failure occurrence times, and failure repair information of each unit in the 5G communication base station equipment, etc. Construct an equipment operation status parameter sequence and an equipment health status parameter sequence based on the historical maintenance data. Set a unit time interval, and construct the equipment operation status parameter sequence and the equipment health status parameter sequence according to the set unit time interval in combination with the historical normal operation data of each unit. The equipment operation status parameter sequence includes an equipment operation abnormal status parameter sequence. Conduct sensitive parameter screening based on the equipment operation status parameter sequence and the equipment health status parameter sequence. Use the equipment operation status parameter sequence as the comparison sequence and the equipment health status parameter sequence as the reference sequence. Calculate the grey correlation degree value between the two according to the comparison sequence and the reference sequence. Use the correlation analysis method to calculate the Pearson correlation coefficient of the comparison sequence and the reference sequence. Calculate the target coefficient according to the grey correlation degree value, the Pearson correlation coefficient, and their preset weights. Select several target sensitive parameters from the equipment operation status parameters according to the target coefficient. The sensitive parameters are used to characterize the equipment degradation data in the equipment operation status monitoring data. Obtain the influence parameters of the equipment degradation process based on the target sensitive parameters, and obtain the external environment influence parameters. The external environment influence parameters include the environmental temperature, humidity, and pressure at each time point, etc. Generate an external factor cumulative parameter set for a preset time period according to the external environment influence parameters. Calculate the Pearson correlation coefficient between the external factor cumulative parameter set and the sensitive parameter set composed of several target sensitive parameters. Select the influence parameters of the equipment degradation process from the external environment influence parameters and several sensitive parameters according to the Pearson correlation coefficient. Obtain several preset degradation indicators. The preset degradation indicators may include the expiration value of the usage duration of each unit in the communication base station, the number of times of reaching the limit load, the coverage interference index, and the number of repairs, etc. The preset degradation indicators are shown in the following table:

[0067] Preset Degradation Index Classification Index Name Control Plane Index Number of Times of Reaching the Limit Load Usage Duration of Each Unit Service Plane Index Number of Repairs Service Plane Delay Average Throughput Rate Coverage Interference Index Average Bit Error Rate Channel Utilization Rate

[0068] An edge degradation model of the Wiener process is established based on a number of preset degradation indicators. A stochastic process model is established for the preset degradation indicators. A state transition equation and a measurement equation are established according to the stochastic process model. A dependence relationship between a number of degradation indicators is established according to the state transition equation and the measurement equation. An edge degradation model of the Wiener process is constructed according to the dependence relationship. The edge degradation model of the Wiener process is used to characterize the degradation situation in a continuous-time stochastic process. An equipment degradation model is constructed based on the influence parameters and the edge degradation model. A degradation model of parameter correlation is constructed based on the influence parameters and the edge degradation model, which is the equipment degradation model. Based on the equipment degradation model, the equipment degradation amount is determined using the preprocessed real-time operating status data. The preprocessed real-time operating status data is input into the equipment degradation model to output the equipment degradation amount. Based on the equipment degradation model, the service life of the target unit in the 5G communication base station equipment is predicted using the preprocessed real-time operating status data. The time probability density function of each stage of each unit in the base station equipment is determined according to the equipment degradation model. The total time probability density function is determined according to the time probability density of each stage. The service life of the target unit in the 5G communication base station equipment is determined according to the total time probability density function combined with the preprocessed real-time operating status data. This service life is the remaining available life of the target unit. The real-time degradation status of each unit in the 5G communication base station equipment is determined based on the equipment degradation amount and the service life. The real-time degradation status of each unit in the 5G communication base station equipment can be quantified according to the equipment degradation amount, the service life, and their corresponding preset ratios. Thus, the accuracy of the description of the degradation process of the base station equipment is improved.

[0069] S13: Identify the prone-to-failure points based on the historical maintenance data combined with the preprocessed real-time operating status data, and identify the target potential failure points based on the abductive inference network using the real-time degradation status of each unit;

[0070] In the specific implementation process of the present invention, the identification of the prone-to-failure points based on the historical maintenance data combined with the preprocessed real-time operating status data includes: calculating the failure parameters of each unit in the 5G communication base station equipment within a preset time period based on the historical maintenance data, and obtaining the failure occurrence pattern based on the failure parameters within the preset time period; identifying the prone-to-failure points based on the failure occurrence pattern using the preset failure classification criteria combined with the preprocessed real-time operating status data.

[0071] Further, the abductive reasoning network identifies target potential fault points by using the real-time degradation states of each unit, including: constructing three-dimensional digital models of each unit and establishing functional association rules between each unit; performing extreme working simulations on each unit based on the three-dimensional digital models and functional association rules to obtain corresponding extreme working parameters, and obtaining an abductive reasoning rule set by using the abductive reasoning network based on the corresponding extreme working parameters and normal working parameters; determining the first potential fault point based on the abductive reasoning rule set; constructing an equipment fault knowledge ontology, performing knowledge extraction by using machine learning based on the historical maintenance data to obtain target knowledge, and constructing a potential fault knowledge base based on the equipment fault knowledge ontology and the target knowledge; determining the second potential fault point based on the potential fault knowledge base in combination with the real-time degradation states of each unit; and determining the target potential fault point based on the first potential fault point and the second potential fault point.

[0072] Specifically, calculate the fault parameters of each unit in the 5G communication base station equipment within a preset time period based on the historical maintenance data. The fault parameters may include the fault occurrence time, the faulty unit, the fault type, etc. Then, obtain the fault occurrence pattern based on the fault parameters within the preset time period. Count the number of faults and the fault types that occurred in each unit within the preset time period according to the fault parameters within the preset time period. Generate a fault frequency distribution based on the number of faults and the fault types that occurred in each unit within the preset time period, and obtain the fault occurrence pattern according to the fault frequency distribution. Use the preset fault classification criteria combined with the preprocessed real-time operation status data to identify the prone-to-fault points based on the fault occurrence pattern. The preset fault classification criteria can be: level 1 fault, which has little impact on the equipment safety and almost no impact on the operation; level 2 fault, which has a certain impact on the equipment and has a certain impact on the operation but is tolerable; level 3 fault, which has a greater impact on the equipment safety and has a greater impact on the operation but can be carried out through the standby method; level 4 fault, which has a great impact on the equipment safety and has a serious impact on the operation and needs to be eliminated immediately. Classify the fault types in the fault occurrence frequency according to the preset fault classification criteria, and conduct a comparative analysis by combining the fault occurrence frequency after fault type classification with the preprocessed real-time operation status data to obtain the prone-to-fault points, thereby improving the reliability of identifying the prone-to-fault points. Construct a three-dimensional digital model of each unit, define the key features of each unit in the 5G communication base station equipment, and define the corresponding attributes and feature reconstruction methods for each key feature. Determine the geometric layer and data layer of the three-dimensional digital model, import the theoretical working principle model of each unit, construct the corresponding three-dimensional digital model according to the theoretical working principle model of each unit combined with the geometric layer and the data layer, and establish the functional association rules between each unit. Based on the three-dimensional digital model and the functional association rules, conduct a limit working simulation on each unit. In the simulation software, conduct an operation simulation of each unit under the limit state according to the three-dimensional digital model and the functional association rules. The limit state may include high-temperature scenarios, high-load scenarios, high-humidity scenarios, etc., to obtain its operation data under the limit state, that is, obtain the corresponding limit working parameters. Then, based on the corresponding limit working parameters and normal working parameters, use an abductive reasoning network to obtain an abductive reasoning rule set. The normal working parameters can be obtained through the parameter database of each unit. The abductive reasoning network can be used to simulate highly non-linear fault identification problems. This network is a hierarchical network with feed-forward function nodes, and the multi-layer node function is composed of simple low-order polynomials. Its 3- or 4-layer polynomial network usually meets the complex system modeling requirements. Use the difference between the corresponding limit working parameters and normal working parameters as the input variable, input the input variable into the abductive reasoning network, and output the abductive reasoning rule set. Based on the abductive reasoning rule set, determine the first potential fault point. The abductive reasoning rules can search for all fault events that have a causal relationship with the fault type, thereby being able to determine the first potential fault point.Construct an equipment failure knowledge ontology through a preset ontology construction tool, and construct the equipment failure knowledge ontology from four aspects: class, object property, data property, and instance. Use machine learning for knowledge extraction based on the historical maintenance data, use a failure prediction model to predict failure events for the historical maintenance data, obtain the failure event prediction results, extract the failure types in the historical maintenance data, and extract the failure types with a frequency greater than or equal to the preset occurrence frequency as high-frequency events. Combine the high-frequency events, generate association rules using the association rule algorithm, generate target knowledge based on the association rules, high-frequency events, and failure event prediction results, and form a potential failure knowledge base based on the equipment failure knowledge ontology and the target knowledge. The constructed potential failure knowledge base can realize the visualization of failure judgment knowledge. Determine the second potential failure point based on the potential failure knowledge base and the real-time degradation state of each unit. Determine the second potential failure point according to the association rules in the potential failure knowledge base and the real-time degradation state of each unit. Determine the target potential failure point based on the first potential failure point and the second potential failure point, and perform repeated elimination processing on the first potential failure point and the second potential failure point to determine the target potential failure point.

[0073] S14: Monitor the state of the failure-prone points and the target potential failure points to obtain the state monitoring results;

[0074] In the specific implementation process of the present invention, the monitoring the state of the failure-prone points and the target potential failure points to obtain the state monitoring results includes: adjusting the monitoring parameters, and monitoring the state of the failure-prone points and the target potential failure points based on the adjusted monitoring parameters to obtain the state monitoring results.

[0075] Specifically, adjusting the monitoring parameters, that is, adjusting the monitoring frequency and range of the areas where the failure-prone points and the target potential failure points are located. The state detection can be performed through a combination of sensors such as relevant cameras or intelligent boxes. Monitoring the state of the failure-prone points and the target potential failure points based on the adjusted monitoring parameters means monitoring the data of the failure-prone points and the target potential failure points according to the adjusted monitoring parameters to obtain the state monitoring results.

[0076] S15: Judge whether equipment maintenance is required based on the state monitoring results. If it is judged that equipment maintenance is required, formulate a target maintenance plan based on the operation and maintenance model using the state monitoring results in combination with equipment load analysis;

[0077] In the specific implementation process of the present invention, formulating a target maintenance plan by using the state monitoring results in combination with equipment load analysis based on the operation and maintenance model includes: obtaining operation and maintenance content information, and extracting semantic keywords in the operation and maintenance semantic content corresponding to the operation and maintenance content information; performing content-level classification processing on the semantic keywords based on the operation and maintenance semantic content to obtain a content-level classification result of the semantic keywords; performing tree relationship construction processing on the semantic keywords corresponding to the content-level classification result to obtain a semantic keyword tree structure diagram; establishing an index between the semantic keywords of each node in the semantic keyword tree structure diagram and their corresponding operation and maintenance semantic content to form an operation and maintenance strategy knowledge graph, and constructing an operation and maintenance model based on the operation and maintenance strategy knowledge graph. Using the state monitoring results based on the operation and maintenance model to determine an initial maintenance plan; obtaining the running load situation of the operation and maintenance equipment during operation, and adjusting the resource allocation and task scheduling of the operation and maintenance equipment by using the state monitoring results in combination with the resource scheduling dimension based on the running load situation; improving the initial maintenance plan based on the adjusted resource allocation and task scheduling of the operation and maintenance equipment to obtain a target maintenance plan.

[0078] Specifically, the operation data in the monitoring results of each unit is compared with the preset fault warning threshold. If the preset fault warning threshold is reached, it indicates that the unit needs equipment maintenance. Obtain the operation and maintenance content information, which is the text content of the maintenance strategy for each unit, including the types and quantities of the operation and maintenance equipment used, etc. Input the operation and maintenance content information into the semantic recognition model for semantic recognition processing to obtain the operation and maintenance semantic content. The semantic recognition model is a convergent model obtained by inputting the sample data set into the deep neural network. Extract the semantic keywords in the operation and maintenance semantic content corresponding to the operation and maintenance content information. Based on the graph sorting algorithm, perform keyword extraction processing on the operation and maintenance semantic content to obtain the semantic keywords. Perform content level classification processing on the semantic keywords based on the operation and maintenance semantic content, and perform content level classification according to the different operation and maintenance levels of each unit in the communication base station equipment to obtain the content level classification result of the semantic keywords. Based on the semantic keywords corresponding to the content level classification result, perform tree relationship construction processing on the semantic keywords. Determine the node positions of each semantic keyword in the tree structure according to the content level classification result, that is, determine the semantic keywords corresponding to the root node and the other nodes in the tree structure. Fill the semantic keywords corresponding to the content level classification result into the corresponding positions in the root node and each of the other nodes in the tree structure to obtain the semantic keyword tree structure diagram; establish an index between the semantic keyword of each node in the semantic keyword tree structure diagram and its corresponding operation and maintenance semantic content. Assign a corresponding first element to the semantic keyword of each node and a corresponding second element to the operation and maintenance semantic content, and establish an index association according to the first element and the second element to form an operation and maintenance strategy knowledge graph. Based on the operation and maintenance strategy knowledge graph, construct an operation and maintenance model, and use the status monitoring result to determine the initial maintenance plan based on the operation and maintenance model. Obtain the operation load situation of the operation and maintenance equipment during operation. Based on the operation load situation, use the status monitoring result to combine the resource scheduling dimension to adjust the resource allocation and task scheduling of the operation and maintenance equipment, and exclude the operation and maintenance equipment with an overloaded operation load situation. Improve the initial maintenance plan based on the adjusted resource allocation and task scheduling of the operation and maintenance equipment, and adjust the operation and maintenance equipment scheduling in the initial maintenance plan to obtain the target maintenance plan.

[0079] S16: Based on the target maintenance plan, perform equipment maintenance on the 5G communication base station equipment, encrypt the equipment maintenance information, and upload the encrypted equipment maintenance information to the cloud platform.

[0080] In the specific implementation process of the present invention, the performing equipment maintenance on the 5G communication base station equipment based on the target maintenance plan and encrypting the equipment maintenance information includes: scheduling the corresponding operation and maintenance equipment based on the target maintenance plan to perform equipment maintenance on the 5G communication base station equipment, and performing asymmetric encryption on the equipment maintenance information to obtain the encrypted equipment maintenance information.

[0081] Specifically, based on the target maintenance plan, the corresponding operation and maintenance equipment is scheduled to repair the 5G communication base station equipment. The equipment maintenance information is asymmetrically encrypted. The equipment maintenance information is encrypted based on a preset public key to obtain the encrypted equipment maintenance information, and the encrypted equipment maintenance information is uploaded to the cloud platform in the platform layer to prevent the information from being tampered with or maliciously read.

[0082] In the embodiment of the present invention, an equipment degradation model is constructed based on the equipment degradation influence parameters and the edge degradation model generated from historical maintenance data. According to the equipment degradation model, the real-time degradation status of each unit in the 5G communication base station equipment is determined, which can improve the recognition accuracy of the degradation status of each unit in the 5G communication base station equipment and more clearly understand the specific situation of the communication base station equipment. By determining the first potential fault point through the abductive reasoning rule set and the second potential fault point through the potential fault knowledge base, the recognition accuracy of the potential fault point can be improved. By monitoring the status of the potential fault point, the anomalies occurring at the potential fault point can be detected in a timely manner, avoiding affecting the emergency repair timeliness of the target unit in the communication base station equipment. When it is determined that there are relevant equipment units in the communication base station that need to be repaired, based on the operation and maintenance model, a target maintenance plan is formulated by combining the status monitoring results with equipment load analysis, improving the reliability of the formulated maintenance plan, improving the equipment maintenance quality, and at the same time realizing the improvement of operation and maintenance management efficiency, effectively solving the problem of low operation and maintenance management efficiency in the prior art, and enabling the operation and maintenance management of the 5G communication base station equipment to achieve a more ideal effect.

[0083] Embodiment 2

[0084] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a method for operation and maintenance management of the 5G communication base station equipment status in the second embodiment of the present invention. The method includes:

[0085] S21: Obtain the real-time operation status data of each unit in the 5G communication base station equipment, and preprocess the real-time operation status data to obtain the preprocessed real-time operation status data;

[0086] S22: Obtain the historical maintenance data of each unit, construct an equipment degradation model based on the historical maintenance data, and determine the real-time degradation status of each unit in the 5G communication base station equipment by using the preprocessed real-time operation status data based on the equipment degradation model;

[0087] S23: Identify the prone-to-failure points based on the historical maintenance data combined with the preprocessed real-time operation status data;

[0088] S24: Construct the 3D digital models of each unit and establish the functional association rules between each unit;

[0089] In the specific implementation process of the present invention, the 3D digital models of each unit are constructed, the key features of each unit in the 5G communication base station equipment are defined, corresponding attributes and feature reconstruction methods are defined for each key feature, the geometric layer and data layer of the 3D digital model are determined, the theoretical working principle models of each unit are imported, and the corresponding 3D digital models are constructed according to the theoretical working principle models of each unit in combination with the geometric layer and data layer, and the functional association rules between each unit are established. The functional association rules between each unit are established according to the information and physical transfer rules between each unit.

[0090] S25: Perform limit working simulation on each unit based on the 3D digital model and the functional association rules, obtain the corresponding limit working parameters, and obtain the abductive inference rule set by using the abductive inference network based on the corresponding limit working parameters and normal working parameters;

[0091] In the specific implementation process of the present invention, limit working simulation is performed on each unit based on the 3D digital model and the functional association rules. According to the 3D digital model and the functional association rules, the operation simulation of each unit in the limit state is carried out in the simulation software. The limit state may include high-temperature scenarios, high-load scenarios, high-humidity scenarios, etc., and the operation data in the limit state is obtained, that is, the corresponding limit working parameters are obtained, and the abductive inference rule set is obtained by using the abductive inference network based on the corresponding limit working parameters and normal working parameters. The normal working parameters can be obtained through the parameter database of each unit. The abductive inference network can be used to simulate highly non-linear fault identification problems. As Figure 4 shown, the network is a hierarchical network with feed-forward function nodes, and the multi-layer node functions are composed of simple low-order polynomials. Its 3-polynomial network usually satisfies complex system modeling. The first layer is three types of nodes, namely a one-term polynomial input and two two-term polynomial inputs. The second layer includes one type of node, which is a two-term polynomial input. The third layer is one type of node, which is a three-term polynomial input. Through the processing of multiple types of nodes, the final processing result can be obtained. The difference between the corresponding limit working parameters and normal working parameters is used as the input variable, and the input variable is input into the abductive inference network to output the abductive inference rule set.

[0092] S26: Determine the first potential fault point based on the abductive inference rule set;

[0093] In the specific implementation process of the present invention, the first potential fault point is determined based on the abductive inference rule set. The abductive inference rule can search for all fault events that have a causal relationship with the fault type, so as to be able to determine the first potential fault point.

[0094] S27: Construct an equipment failure knowledge ontology, perform knowledge extraction using machine learning based on the historical maintenance data to obtain target knowledge, and construct a potential failure knowledge base based on the equipment failure knowledge ontology and the target knowledge;

[0095] In the specific implementation process of the present invention, an equipment failure knowledge ontology is constructed through a preset ontology construction tool, and the equipment failure knowledge ontology is constructed from four aspects: class, object property, data property, and instance. Perform knowledge extraction using machine learning based on the historical maintenance data, use a failure prediction model to predict failure events in the historical maintenance data to obtain a failure event prediction result, perform event extraction on the failure types in the historical maintenance data, extract the failure types with a frequency greater than or equal to a preset occurrence frequency as high-frequency events, combine the high-frequency events, generate association rules using the association rule algorithm, generate target knowledge based on the association rules, high-frequency events, and failure event prediction results, and form a potential failure knowledge base based on the equipment failure knowledge ontology and the target knowledge. The constructed potential failure knowledge base can realize the visualization of failure judgment knowledge.

[0096] S28: Determine a second potential failure point based on the potential failure knowledge base in combination with the real-time degradation state of each unit, and determine a target potential failure point based on the first potential failure point and the second potential failure point;

[0097] In the specific implementation process of the present invention, determine a second potential failure point based on the potential failure knowledge base in combination with the real-time degradation state of each unit, and determine a second potential failure point according to the association rules in the potential failure knowledge base in combination with the real-time degradation state of each unit. Determine a target potential failure point based on the first potential failure point and the second potential failure point, and perform repeated elimination processing on the first potential failure point and the second potential failure point to determine the target potential failure point.

[0098] S29: Monitor the states of the failure-prone points and the target potential failure points to obtain a state monitoring result;

[0099] S30: Judge whether equipment maintenance is required based on the state monitoring result;

[0100] In the specific implementation process of the present invention, perform data monitoring on the failure-prone points and the target potential failure points according to the adjusted monitoring parameters, and judge whether equipment maintenance is required based on the obtained monitoring data. If the obtained monitoring data is within the normal range, there is no need for maintenance temporarily, enter step S29, and continue to monitor the failure-prone points and the potential failure points. If the obtained monitoring data is abnormal, enter step S30 to formulate a maintenance plan.

[0101] S31: If it is determined that equipment maintenance is required, a target maintenance plan is formulated based on the operation and maintenance model by combining the status monitoring results with equipment load analysis;

[0102] S32: Based on the target maintenance plan, equipment maintenance is carried out on the 5G communication base station equipment, the equipment maintenance information is encrypted, and the encrypted equipment maintenance information is uploaded to the cloud platform.

[0103] In the embodiment of the present invention, an equipment degradation model is constructed based on the equipment degradation impact parameters generated from historical maintenance data and the edge degradation model. According to the equipment degradation model, the real-time degradation status of each unit in the 5G communication base station equipment is determined, which can improve the recognition accuracy of the degradation status of each unit in the 5G communication base station equipment and more clearly understand the specific situation of the communication base station equipment. By determining the first potential fault point through the abductive reasoning rule set and the second potential fault point through the potential fault knowledge base to determine the target potential fault point, the recognition accuracy of the potential fault point can be improved. By monitoring the status of the potential fault point, the anomalies occurring at the potential fault point can be detected in time, avoiding affecting the emergency repair timeliness of the target unit in the communication base station equipment. When it is determined that there are relevant equipment units in the communication base station that need to be repaired, a target maintenance plan is formulated based on the operation and maintenance model by combining the status monitoring results with equipment load analysis, improving the reliability of the formulated maintenance plan, improving the equipment maintenance quality, and at the same time realizing the improvement of operation and maintenance management efficiency, effectively solving the problem of low operation and maintenance management efficiency in the prior art, and enabling the operation and maintenance management of the 5G communication base station equipment to achieve a more ideal effect.

[0104] Embodiment Three

[0105] Please refer to Figure 3 , Figure 3 which is a schematic structural composition diagram of a system for operation and maintenance management of the 5G communication base station equipment status in the embodiment of the present invention. The system includes:

[0106] Data preprocessing module 31: used to obtain the real-time operation status data of each unit in the 5G communication base station equipment and preprocess the real-time operation status data to obtain the preprocessed real-time operation status data;

[0107] Real-time degradation status determination module 32: used to obtain the historical maintenance data of each unit, construct an equipment degradation model based on the historical maintenance data, and determine the real-time degradation status of each unit in the 5G communication base station equipment by using the preprocessed real-time operation status data based on the equipment degradation model;

[0108] Fault point identification module 33: used to identify the prone-to-fault points based on the historical maintenance data combined with the preprocessed real-time operation status data, and identify the target potential fault points by using the real-time degradation status of each unit based on the abductive reasoning network;

[0109] Fault point status monitoring module 34: used to perform status monitoring on the prone-to-fault points and target potential fault points to obtain status monitoring results;

[0110] Maintenance plan formulation module 35: used to judge whether equipment maintenance is required based on the status monitoring results. If it is judged that equipment maintenance is required, a target maintenance plan is formulated based on the operation and maintenance model by combining the status monitoring results with equipment load analysis;

[0111] Equipment maintenance and maintenance information processing module 36: used to perform equipment maintenance on the 5G communication base station equipment based on the target maintenance plan, encrypt the equipment maintenance information, and upload the encrypted equipment maintenance information to the cloud platform.

[0112] In the specific implementation process of the present invention, the specific implementation manners of the system items can refer to the implementation manners of the above method items, which will not be elaborated here.

[0113] In the embodiments of the present invention, an equipment degradation model is constructed based on the equipment degradation impact parameters and the edge degradation model generated from historical maintenance data, and the real-time degradation status of each unit in the 5G communication base station equipment is determined according to the equipment degradation model, which can improve the recognition accuracy of the degradation status of each unit in the 5G communication base station equipment and more clearly understand the specific situation of the communication base station equipment. By determining the first potential fault point through the abductive reasoning rule set and the second potential fault point determined by the potential fault knowledge base to determine the target potential fault point, the recognition accuracy of the potential fault point can be improved. Performing status monitoring on the potential fault point can timely detect the abnormalities occurring at the potential fault point and avoid affecting the emergency repair timeliness of the target unit in the communication base station equipment. When it is judged that there are relevant equipment units in the communication base station that need to be repaired, a target maintenance plan is formulated based on the operation and maintenance model by combining the status monitoring results with equipment load analysis, which improves the reliability of the formulated maintenance plan, improves the equipment maintenance quality, and at the same time realizes the improvement of the operation and maintenance management efficiency, effectively solving the problem of low operation and maintenance management efficiency in the prior art and enabling the operation and maintenance management of the 5G communication base station equipment to achieve a more ideal effect.

[0114] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium can include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0115] In addition, the above has introduced in detail a method and system for operation and maintenance management of the status of a 5G communication base station device provided by the embodiments of the present invention. Specific examples should have been used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention. At the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for operation and maintenance management of the status of 5G communication base station equipment, characterized in that, The method includes: Obtaining the real-time operation status data of each unit in the 5G communication base station device, and preprocessing the real-time operation status data to obtain the preprocessed real-time operation status data; Obtaining the historical maintenance data of each unit, constructing an equipment degradation model based on the historical maintenance data, and determining the real-time degradation status of each unit in the 5G communication base station device by using the preprocessed real-time operation status data based on the equipment degradation model; Identifying the prone-to-failure points based on the historical maintenance data combined with the preprocessed real-time operation status data, and identifying the target potential failure points by using the real-time degradation status of each unit based on the abductive reasoning network; Performing status monitoring on the prone-to-failure points and the target potential failure points to obtain a status monitoring result; Judging whether equipment maintenance is required based on the status monitoring result. If it is judged that equipment maintenance is required, then formulating a target maintenance plan based on the status monitoring result combined with equipment load analysis by using an operation and maintenance model; Performing equipment maintenance on the 5G communication base station device based on the target maintenance plan, encrypting the equipment maintenance information, and uploading the encrypted equipment maintenance information to the cloud platform; Among them, constructing an equipment degradation model based on the historical maintenance data includes: constructing an equipment operation status parameter sequence and an equipment health status parameter sequence based on the historical maintenance data, and performing sensitive parameter screening based on the equipment operation status parameter sequence and the equipment health status parameter sequence to obtain target sensitive parameters; obtaining the influence parameters of the equipment degradation process based on the target sensitive parameters; obtaining a number of preset degradation indicators, and establishing a marginal degradation model of the Wiener process based on the number of preset degradation indicators; constructing an equipment degradation model based on the influence parameters and the marginal degradation model; Identifying the target potential failure points by using the real-time degradation status of each unit based on the abductive reasoning network includes: constructing a three-dimensional digital model of each unit, and establishing functional association rules between each unit; performing extreme working simulation on each unit based on the three-dimensional digital model and the functional association rules to obtain corresponding extreme working parameters, and obtaining an abductive reasoning rule set by using the abductive reasoning network based on the corresponding extreme working parameters and normal working parameters; determining the first potential failure point based on the abductive reasoning rule set; constructing an equipment failure knowledge ontology, performing knowledge extraction by using machine learning based on the historical maintenance data to obtain target knowledge, and constructing a potential failure knowledge base based on the equipment failure knowledge ontology and the target knowledge; determining the second potential failure point based on the potential failure knowledge base combined with the real-time degradation status of each unit; determining the target potential failure point based on the first potential failure point and the second potential failure point.

2. The method for operation and maintenance management of the 5G communication base station equipment status according to claim 1, characterized in that, The preprocessing of the real-time operation status data to obtain the preprocessed real-time operation status data includes: Performing noise reduction processing on the real-time operation status data to obtain the real-time operation status data after noise reduction processing; Performing data transformation processing on the real-time operation status data after noise reduction processing to obtain the preprocessed real-time operation status data.

3. The method for operation and maintenance management of the 5G communication base station equipment status according to claim 1, characterized in that, The determining of the real-time degradation status of each unit in the 5G communication base station device by using the preprocessed real-time operation status data based on the equipment degradation model includes: Determine the equipment degradation amount based on the pre - processed real - time operation status data using the equipment degradation model; Predict the service life of the target unit in the 5G communication base station equipment based on the pre - processed real - time operation status data using the equipment degradation model, and determine the real - time degradation status of each unit in the 5G communication base station equipment based on the equipment degradation amount and service life.

4. The method for operation and maintenance management of the 5G communication base station equipment status according to claim 1, characterized in that, Identifying the prone - to - failure points based on the historical maintenance data combined with the pre - processed real - time operation status data includes: Calculate the failure parameters of each unit in the 5G communication base station equipment within a preset time period based on the historical maintenance data, and obtain the failure occurrence pattern based on the failure parameters within the preset time period; Identify the prone - to - failure points based on the failure occurrence pattern using the preset failure classification criteria combined with the pre - processed real - time operation status data.

5. The method for operation and maintenance management of the 5G communication base station equipment status according to claim 1, wherein, The state monitoring of the prone - to - failure points and target potential failure points to obtain the state monitoring results includes: Adjust the monitoring parameters, and perform state monitoring on the prone - to - failure points and target potential failure points based on the adjusted monitoring parameters to obtain the state monitoring results.

6. The method for operation and maintenance management of the 5G communication base station equipment status according to claim 1, characterized in that, Formulating the target maintenance plan based on the operation and maintenance model using the state monitoring results combined with equipment load analysis includes: Obtain the operation and maintenance content information, and extract the semantic keywords in the corresponding operation and maintenance semantic content of the operation and maintenance content information; Perform content - level classification processing on the semantic keywords based on the operation and maintenance semantic content to obtain the content - level classification result of the semantic keywords; Perform tree - shaped relationship construction processing on the semantic keywords corresponding to the content - level classification result to obtain the semantic keyword tree - shaped structure diagram; Establish an index between the semantic keywords of each node in the semantic keyword tree - shaped structure diagram and their corresponding operation and maintenance semantic content to form an operation and maintenance strategy knowledge graph, and construct an operation and maintenance model based on the operation and maintenance strategy knowledge graph. Determine the initial maintenance plan based on the operation and maintenance model using the state monitoring results; Obtain the operation load situation of the operation and maintenance equipment during operation, and adjust the resource allocation and task scheduling of the operation and maintenance equipment based on the operation load situation using the state monitoring results combined with the resource scheduling dimension; Improve the initial maintenance plan based on the adjusted resource allocation and task scheduling of the operation and maintenance equipment to obtain the target maintenance plan.

7. The method for operation and maintenance management of the 5G communication base station equipment status according to claim 1, characterized in that, Perform equipment maintenance on the 5G communication base station equipment based on the target maintenance plan, and encrypt the equipment maintenance information, including: Dispatch the corresponding operation and maintenance equipment to perform equipment maintenance on the 5G communication base station equipment based on the target maintenance plan, and perform asymmetric encryption on the equipment maintenance information to obtain the encrypted equipment maintenance information.

8. A system for operation and maintenance management of the status of 5G communication base station equipment, characterized in that, The system includes: Data pre - processing module: used to obtain the real - time operation status data of each unit in the 5G communication base station equipment, and pre - process the real - time operation status data to obtain the pre - processed real - time operation status data; Real - time degradation status determination module: used to obtain the historical maintenance data of each unit, construct an equipment degradation model based on the historical maintenance data, and determine the real - time degradation status of each unit in the 5G communication base station equipment based on the equipment degradation model using the pre - processed real - time operation status data; Fault point identification module: used to identify prone-to-fault points based on the historical maintenance data combined with the preprocessed real-time operation status data, and identify target potential fault points based on the abductive reasoning network using the real-time degradation status of each unit; Fault point status monitoring module: used to monitor the status of the prone-to-fault points and target potential fault points to obtain status monitoring results; Maintenance plan formulation module: used to judge whether equipment maintenance is required based on the status monitoring results. If it is judged that equipment maintenance is required, a target maintenance plan is formulated based on the operation and maintenance model using the status monitoring results combined with equipment load analysis; Equipment maintenance and maintenance information processing module: used to perform equipment maintenance on the 5G communication base station equipment based on the target maintenance plan, encrypt the equipment maintenance information, and upload the encrypted equipment maintenance information to the cloud platform; Among them, constructing an equipment degradation model based on the historical maintenance data includes: constructing an equipment operation status parameter sequence and an equipment health status parameter sequence based on the historical maintenance data, and performing sensitive parameter screening based on the equipment operation status parameter sequence and the equipment health status parameter sequence to obtain target sensitive parameters; obtaining influence parameters of the equipment degradation process based on the target sensitive parameters; obtaining a number of preset degradation indicators, and establishing an edge degradation model of the Wiener process based on the number of preset degradation indicators; constructing an equipment degradation model based on the influence parameters and the edge degradation model; Identifying target potential fault points based on the abductive reasoning network using the real-time degradation status of each unit includes: constructing a three-dimensional digital model of each unit and establishing functional association rules between each unit; performing limit working simulation on each unit based on the three-dimensional digital model and the functional association rules to obtain corresponding limit working parameters, and obtaining an abductive reasoning rule set using the abductive reasoning network based on the corresponding limit working parameters and normal working parameters; determining the first potential fault point based on the abductive reasoning rule set; constructing an equipment fault knowledge ontology, performing knowledge extraction using machine learning based on the historical maintenance data to obtain target knowledge, and constructing a potential fault knowledge base based on the equipment fault knowledge ontology and the target knowledge; determining the second potential fault point based on the potential fault knowledge base combined with the real-time degradation status of each unit; determining the target potential fault point based on the first potential fault point and the second potential fault point.

Images