Method and system for constructing power equipment operation management knowledge base

Abstract

The invention discloses a construction method and system of a power equipment operation management knowledge base, and relates to the field of power equipment operation management.The construction method comprises the steps that edge nodes are deployed, and operation data of power equipment are collected in real time through a sensor and processed; constructing a local knowledge base of the edge nodes based on the processed operation data, the basic information of the power equipment and the fault information; based on the local knowledge base, generating a virtual simulation model of the power equipment, and obtaining virtual simulation data of the power equipment; carrying out global integration on fault prediction, operation data and virtual simulation data, and optimizing a virtual simulation model and an inference rule; the edge node performs adaptive expansion on a local knowledge base according to the optimized virtual simulation model and the reasoning rule; data are collected and processed in real time through the edge nodes, dependence on the central server is reduced, and the response speed of the system is increased.

Description

Technical Field

[0001] The present invention relates to the field of power equipment operation management, and in particular to a method and system for constructing a power equipment operation management knowledge base. Background Art

[0002] With the continuous expansion of the scale of power systems and the increase in the complexity of power equipment, the operation and management of power equipment has gradually become one of the key links in the safe and stable operation of power systems. The traditional power equipment management method mainly relies on manual inspections and regular maintenance. This method is difficult to timely and effectively discover potential operating failures of equipment when faced with the complex and changeable operating environment of power equipment.

[0003] In recent years, with the rapid development of technologies such as the Internet of Things (IoT), edge computing, and big data, the operation and management of power equipment has gradually shifted towards intelligence and automation. The existing equipment monitoring system usually relies on the centralized processing mode of the central server, and the computing power of the edge nodes is not fully utilized, resulting in low data processing efficiency. Especially when the number of devices is large, the central server can easily become a bottleneck. Summary of the invention

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

[0005] Therefore, the present invention provides a method for constructing a knowledge base for power equipment operation management to solve the problem of untimely response in large-scale power equipment management caused by centralized data processing.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for constructing a knowledge base for power equipment operation management, which comprises:

[0008] Deploy edge nodes to collect and process the operating data of power equipment in real time through sensors;

[0009] Build a local knowledge base of edge nodes based on processed operation data, basic information of power equipment and fault information;

[0010] Based on the local knowledge base, a virtual simulation model of the power equipment is generated to obtain virtual simulation data of the power equipment;

[0011] The virtual simulation data and operation data of power equipment are integrated to obtain fused data, and the fault prediction of power equipment is obtained through reasoning with a distributed reasoning engine;

[0012] Globally integrate fault prediction, operation data and virtual simulation data to optimize virtual simulation models and inference rules;

[0013] The edge nodes adaptively expand the local knowledge base based on the optimized virtual simulation model and inference rules.

[0014] As a preferred solution of the method for constructing the power equipment operation management knowledge base of the present invention, the edge nodes are deployed to collect the operation data of the power equipment in real time through sensors and process the data. The specific steps are as follows:

[0015] Deploy edge nodes on power equipment. Each sensor communicates with the edge computing node through a standardized protocol. At the same time, the edge node establishes communication with the central server.

[0016] Collect operating data of power equipment through sensors;

[0017] The collected operation data is processed at the edge node.

[0018] As a preferred solution of the method for constructing the power equipment operation management knowledge base of the present invention, the local knowledge base of the edge node is constructed based on the processed operation data, basic information of the power equipment and fault information. The specific steps are as follows:

[0019] According to different data types and functional requirements, the local knowledge base is divided into equipment basic information unit, operation status unit and fault information unit;

[0020] Obtain basic information of power equipment, edge nodes and sensors from power equipment manufacturers and installation records, perform standard processing, create a unique identifier for each power equipment, edge node and sensor, associate and store it with the basic information of the power equipment, and obtain a basic information unit of the equipment;

[0021] The operation data of the power equipment is sorted with the timestamp as the primary key and stored in the operation status unit. Every time the sensor collects the operation data of the power equipment, the operation status unit automatically updates the storage;

[0022] Fault information is collected from maintenance records of power equipment, and standardized, and the processed fault information is associated with a device identifier and stored in a fault information unit;

[0023] Create key field indexes for information in the local knowledge base and establish a fast retrieval mechanism.

[0024] As a preferred solution of the method for constructing the power equipment operation management knowledge base of the present invention, wherein: based on the local knowledge base, a virtual simulation model of the power equipment is generated to obtain virtual simulation data of the power equipment, the specific steps are as follows:

[0025] Conduct mathematical modeling based on the physical characteristics, operating characteristics and historical operating data of power equipment;

[0026] Through Ohm's law and power equation, the power output of power equipment under different load conditions is simulated. The specific contents are as follows;

[0027] The temperature rise process of power equipment under different load conditions is simulated through the heating formula of resistance and the heat balance equation;

[0028] Compare the virtual simulation model with the operational data and adjust the impedance, load conditions, heat dissipation coefficient and power loss in the virtual simulation model;

[0029] Based on the fault information in the fault information unit, parameters corresponding to different faults are set in the virtual simulation model to simulate the fault occurrence process, and the virtual simulation model parameters are adjusted by comparing the output results of the virtual simulation model with the fault information;

[0030] Iteratively compare the output results of the virtual simulation model with the operating data and fault information, and adjust the impedance, load conditions, heat dissipation coefficient and power loss coefficient according to the deviation of each comparison;

[0031] The virtual simulation model generates virtual simulation data of power equipment by simulating the operating status of power equipment in different scenarios.

[0032] As a preferred solution of the method for constructing the power equipment operation management knowledge base of the present invention, wherein: the fusion data of the power equipment virtual simulation data and the operation data are integrated to obtain the fusion data, and the fault prediction of the power equipment is obtained by reasoning with the distributed reasoning engine. The specific steps are as follows:

[0033] Processing the virtual simulation data according to the processing flow of the operation data;

[0034] Use interpolation algorithm and dynamic time warping algorithm to time align and synchronize virtual simulation data and operation data;

[0035] Extract key features from the operating data, extract key parameters from the virtual simulation data, and combine them to form a multi-dimensional feature vector containing the operating data and the virtual simulation data;

[0036] Deploy a distributed inference engine on each edge node, and each edge node runs the distributed inference engine independently;

[0037] The distributed reasoning engine extracts the equipment's operating data and fault information from the local knowledge base, builds a rule base, and sets the reasoning threshold based on the fault information;

[0038] The distributed reasoning engine extracts parameters from the multidimensional feature vector and compares them with the operating data and thresholds in the rule base to obtain anomalies and potential faults.

[0039] When the distributed reasoning engine detects an anomaly, it starts the virtual simulation model to generate a hypothetical scenario, simulate the operating status of the power equipment under the detected anomaly, and predict the failure of the power equipment.

[0040] As a preferred solution of the method for constructing the power equipment operation management knowledge base of the present invention, the specific steps of globally integrating fault prediction, operation data and virtual simulation data, optimizing virtual simulation models and inference rules are as follows:

[0041] After completing data processing, reasoning, and analysis locally, the edge node synchronizes data with the central server to aggregate data from different edge nodes.

[0042] The central server performs timestamp alignment and deduplication processing on the aggregated data;

[0043] Extract multi-dimensional features from the aggregated data, and the central server performs time series analysis on the multi-dimensional features to identify the changing trends and periodicity during the operation of the equipment;

[0044] The aggregated data is classified by similarity through a clustering algorithm, and a feature vector is constructed for each device in each time period;

[0045] By calculating the Euclidean distance between feature vectors, the similarity between data of different edge nodes is measured, and the data of similar devices are classified into one category. Based on the clustering results, the common problems of different edge nodes are obtained;

[0046] Based on common problems, the fault tree analysis method is used to analyze the factors that cause the problems, and solutions are given based on the collected fault information;

[0047] The central server integrates the analysis results and solutions and feeds them back to the edge nodes;

[0048] The edge node updates the local knowledge base content based on feedback, and the virtual simulation model and distributed reasoning engine perform simulation and reasoning based on the updated local knowledge base.

[0049] As a preferred solution of the method for constructing the power equipment operation management knowledge base of the present invention, the edge node adaptively expands the local knowledge base according to the optimized virtual simulation model and reasoning rules. The specific steps are as follows:

[0050] Based on the reasoning results of the optimized virtual simulation model and reasoning rules, the local knowledge base automatically expands the corresponding content;

[0051] Each time the local knowledge base is updated, the virtual simulation model and the distributed reasoning engine perform simulation and reasoning of the operation of the power equipment according to the updated local knowledge base;

[0052] After the simulation and reasoning are completed, they will continue to be uploaded to the central server to form a two-way feedback mechanism.

[0053] In a second aspect, the present invention provides a system for constructing a knowledge base for power equipment operation management, including a data acquisition module, a knowledge base construction module, a simulation module, a data fusion module, a global optimization module and an adaptive expansion module;

[0054] The data acquisition module is used to deploy edge nodes, collect the operating data of power equipment in real time through sensors, and process it;

[0055] The processed operation data, basic information of power equipment and fault information are used to build a local knowledge base of the edge node;

[0056] The simulation module is used to generate a virtual simulation model of the power equipment based on the local knowledge base to obtain virtual simulation data of the power equipment;

[0057] The data fusion module is used to fuse the virtual simulation data and the operation data of the power equipment to obtain fused data, and obtain the fault prediction of the power equipment through the distributed reasoning engine;

[0058] The global optimization module is used to globally integrate fault prediction, local knowledge base and virtual simulation data, and optimize virtual simulation models and inference rules;

[0059] The adaptive expansion module is used by the edge node to adaptively expand the local knowledge base according to the optimized virtual simulation model and reasoning rules.

[0060] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for constructing an electric power equipment operation management knowledge base as described in the first aspect of the present invention.

[0061] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for constructing an electric power equipment operation management knowledge base as described in the first aspect of the present invention.

[0062] The beneficial effects of the present invention are as follows: the present invention collects and processes data in real time through edge nodes, reduces dependence on central servers, improves the response speed of the system, builds a local knowledge base based on the processed data, realizes effective management of equipment historical data, and provides a reliable basis for fault prediction. The generation and optimization of virtual simulation models enable the system to simulate the operation of equipment under different conditions in advance, further improving the prediction accuracy. By integrating operation data and simulation data, the distributed reasoning engine infers the health status of the equipment in real time, ensuring the accuracy of fault prediction. The system ensures continuous optimization of equipment management by adaptively expanding the knowledge base and dynamically updating simulation models and reasoning rules, which significantly improves the intelligent level of power equipment operation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0064] Figure 1 This is a flowchart of the method for constructing the power equipment operation management knowledge base in Example 1.

[0065] Figure 2 This is a module diagram of the system for constructing the power equipment operation management knowledge base in Example 1. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0069] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a method for constructing a power equipment operation management knowledge base, comprising the following steps:

[0070] S1. Deploy edge nodes to collect and process the operating data of power equipment in real time through sensors.

[0071] Deploy edge nodes on power equipment (such as power stations, substations, and near key equipment). Each node has storage and computing capabilities. Each sensor communicates with the edge computing node through a standardized protocol. At the same time, the edge node establishes communication with the central server.

[0072] Collect voltage, current, temperature and other operating data of power equipment by installing sensors;

[0073] Process the collected operation data at the edge node;

[0074] Specifically, the Z-score outlier detection algorithm is used to perform preliminary cleaning of the operating data and remove outliers;

[0075] The edge nodes perform unified unit conversion on the cleaned data. The temperature data is uniformly converted to Celsius, the voltage data is uniformly converted to volts, and the current data is uniformly converted to amperes.

[0076] The standardized operation data of the unit is uniformly formatted and stored in JSON (JavaScript Object Notation) format;

[0077] The principal component analysis (PCA) method was used to reduce the dimension of the formatted operating data.

[0078] S2. Build a local knowledge base of the edge node based on the processed operation data, basic information of power equipment and fault information.

[0079] According to different data types and functional requirements, the local knowledge base is divided into equipment basic information unit, operation status unit and fault information unit;

[0080] Obtain basic information of power equipment, edge nodes and sensors from power equipment manufacturers and installation records, such as equipment model, serial number, installation date, rated voltage, power, current, installation location, maintenance records, etc., and perform standard processing to create a unique identifier for each power equipment, edge node and sensor, and store it in association with the basic information of the power equipment to obtain a basic equipment information unit;

[0081] The operation data of the power equipment is sorted with the timestamp as the primary key and stored in the operation status unit. Every time the sensor collects the operation data of the power equipment, the operation status unit automatically updates the storage;

[0082] Collect fault information from the maintenance records of the power equipment, such as the time of occurrence of the fault, the type of fault, the cause of the fault and the fault handling measures, perform standardized processing, associate the processed fault information with the equipment identifier, and store it in the fault information unit;

[0083] For standardization, specifically, it is to make unified standard conversions for the measurement units and formats of the same type of data, for example, the date format is unified as year, month, day, hour, and minute, the voltage unit is volt, the current unit is ampere, etc.;

[0084] Create key field indexes for information in the local knowledge base and establish a fast retrieval mechanism.

[0085] S3. Based on the local knowledge base, a virtual simulation model of the power equipment is generated to obtain virtual simulation data of the power equipment.

[0086] Based on the operation data, power equipment information and fault information of the power equipment in the local knowledge base, mathematical modeling is performed to simulate the operation of the power equipment in multiple scenarios;

[0087] Through Ohm's law and power equation, the power output of power equipment under different load conditions is simulated, and the expression is as follows:

[0088] U = I (R + jX);

[0089]

[0090] Among them, U is voltage, I is current, R is the active resistance of the power equipment, j is an imaginary unit, X is the reactive resistance of the power equipment, S is the total power, P1 is the active power, and P2 is the reactive power;

[0091] The temperature rise process of power equipment under different load conditions is simulated by the heating formula of resistance and the heat balance equation. The expression is as follows

[0092] P3=I 2 R;

[0093]

[0094] Among them, P3 is the power loss of the power equipment, ΔT is the temperature change of the power equipment, and K is the heat dissipation coefficient;

[0095] Compare the output results of the virtual simulation model with the operating data, and adjust the impedance, load conditions, heat dissipation coefficient and power loss in the virtual simulation model to make the output results of the virtual simulation model fit the operating data;

[0096] For example, when the voltage of the actual device drops too fast when the load increases, while the voltage drops more slowly in the simulation model, the greater voltage drop is reflected by increasing the active resistance and reactive impedance in the impedance. When the temperature rise rate of the device at high load in actual operation is faster than the prediction of the simulation model, it indicates that the heat dissipation coefficient in the model is set too high. At this time, the heat dissipation coefficient should be reduced to reflect the actual heat dissipation capacity of the device;

[0097] Based on the fault information in the fault information unit, parameters corresponding to different faults are set in the virtual simulation model to simulate the fault occurrence process, and the virtual simulation model parameters are adjusted by comparing the output results of the virtual simulation model with the fault information;

[0098] For example, when the equipment is under high load conditions, the temperature rises rapidly, leading to overheating failures. By analyzing historical data, it is found that when the load of the equipment exceeds 80%, the temperature rise curve shows obvious nonlinear growth. The simulation model adjusts the correction coefficient in the thermal balance equation to make it present a steeper temperature rise curve when the load exceeds 80%.

[0099] Iteratively compare the output results of the virtual simulation model with the operating data and fault information, and adjust the impedance, load conditions, heat dissipation coefficient and power loss coefficient according to the deviation of each comparison to complete the optimization of the virtual simulation model;

[0100] The virtual simulation model generates virtual simulation data of power equipment by simulating the operating status of power equipment in different scenarios;

[0101] Specifically, normal and abnormal load scenarios of power equipment, ambient temperature change scenarios, and equipment aging scenarios are set, and the input conditions of each scenario, including load current, ambient temperature, etc., are input into the virtual simulation model;

[0102] Based on the input conditions, the virtual simulation model calculates the power output and temperature rise process of the power equipment in different model scenarios, reflecting the operation of the power equipment in different scenarios.

[0103] S4. The virtual simulation data and operation data of the power equipment are integrated to obtain fused data, and the fault prediction of the power equipment is obtained through reasoning with a distributed reasoning engine.

[0104] Processing the virtual simulation data according to the processing flow of the operation data;

[0105] Use interpolation algorithm and dynamic time warping algorithm to time align and synchronize virtual simulation data and operation data;

[0106] Specifically, the timestamp of the running data is used as the standard time point to generate a unified time axis, and the data points are filled by interpolation so that the two sets of data have similar timestamps, and preliminary alignment and synchronization are performed;

[0107] For the virtual simulation data, interpolation processing is performed on the virtual simulation data according to the timestamp of the running data to generate virtual simulation data consistent with the timestamp of the running data;

[0108] For running data, when the timestamp intervals are uneven and there are missing points, an interpolation algorithm is used to synchronize the time;

[0109] After interpolation, the dynamic time warping algorithm is used to dynamically stretch and compress the time axis so that the two time series can be optimally matched and the data at different sampling frequencies can be aligned;

[0110] Extract key features from the operating data, such as voltage fluctuation, frequency change, and temperature rise rate, and extract key parameters from the virtual simulation data, such as power output under load and temperature rise curve, and combine them to form a multi-dimensional feature vector containing the operating data and virtual simulation data;

[0111] Deploy a distributed inference engine on each edge node, and each edge node runs the distributed inference engine independently;

[0112] The distributed reasoning engine extracts the equipment's operating data and fault information from the local knowledge base, builds a rule base, and sets the reasoning threshold based on the fault information. The threshold is the voltage, current, and temperature values ​​when the fault occurs. For example, a voltage fluctuation exceeding ±5% is considered an abnormal state, and a temperature rise exceeding 80°C is considered an overheating state.

[0113] The distributed inference engine extracts parameters from the multidimensional feature vector, including voltage, current, vibration frequency, and temperature rise; and compares them with the operating data and thresholds in the rule base to obtain abnormalities and potential faults;

[0114] When the distributed reasoning engine detects an anomaly, it starts the virtual simulation model to generate a hypothetical scenario, simulate the operating state of the power equipment under the detected anomaly, and predict the failure of the power equipment;

[0115] The inference engine outputs a health status diagnosis report of the equipment based on the simulation results. The report includes the current status of the power equipment (such as normal, overloaded, overheated, etc.), possible future faults (such as overheating, abnormal vibration), and the probability of fault occurrence;

[0116] When the inference engine predicts certain fault points and abnormal conditions, the system generates a preventive maintenance plan based on historical fault information and current equipment status;

[0117] The inference engine provides optimization suggestions for equipment maintenance strategies by simulating different operating scenarios (such as load changes, ambient temperature increases, equipment aging, etc.);

[0118] After the maintenance suggestions are formed, the system will provide feedback based on the actual maintenance results. If the recommended preventive measures successfully avoid equipment failure, the system will adjust the rule base in the inference engine and optimize the subsequent reasoning process.

[0119] S5. Globally integrate fault prediction, local knowledge base and virtual simulation data to optimize virtual simulation models and inference rules.

[0120] After completing data processing, reasoning, and analysis locally, the edge node synchronizes data with the central server to aggregate data from different edge nodes.

[0121] Specifically, the edge node packages the fault prediction of power equipment, local knowledge base, and virtual simulation data obtained by the distributed inference engine into a unified format, and uses a differential compression algorithm to upload only the data that has changed since the last synchronization, reducing bandwidth usage;

[0122] Upload the packaged data to the central server via the MQTT protocol;

[0123] The central server performs timestamp alignment and deduplication processing on the aggregated data;

[0124] Extract multi-dimensional features from the aggregated data, and the central server performs time series analysis on the multi-dimensional features to identify the changing trends and periodicity during the operation of the equipment;

[0125] The aggregated data is classified by similarity through a clustering algorithm, and a feature vector is constructed for each device in each time period;

[0126] By calculating the Euclidean distance between feature vectors, the similarity between data of different edge nodes is measured, and the data of similar devices are classified into one category. Based on the clustering results, the common problems of different edge nodes are obtained;

[0127] Based on common problems, the fault tree analysis method is used to analyze the factors that cause the problems, and solutions are given based on the collected fault information;

[0128] Specifically, for example, when the power equipment of multiple edge nodes has the same overheating fault in a high temperature environment (such as an ambient temperature exceeding 40°C), the central server infers that there may be a problem with the heat dissipation design of the equipment, and increases the number of fans inside or outside the equipment or improves the fan power to enhance air circulation to accelerate the discharge of heat. When the equipment is running in a high temperature environment, it is recommended to use a dynamic load adjustment strategy to reduce the load of the equipment to reduce heat generation and avoid long-term high-load operation of the equipment in a high temperature environment;

[0129] When the load of multiple power devices exceeds the rated value, the power output drops significantly, which indicates that the load distribution of the equipment is unreasonable and there is a potential overload risk. It is recommended that when the equipment exceeds the rated load, the overload protection mechanism is automatically turned on to limit the power output of the equipment to prevent the equipment from running for too long in an overloaded state, thereby reducing the risk of equipment damage;

[0130] The central server integrates the analysis results and solutions and feeds them back to the edge nodes;

[0131] The edge node updates the local knowledge base content based on the feedback, and the virtual simulation model and distributed reasoning engine perform simulation and reasoning based on the updated local knowledge base;

[0132] Specifically, the global optimization parameters sent by the central server are updated to the local knowledge base, and the new fault form and its characteristics are added to the fault information unit;

[0133] The distributed reasoning engine combines new fault forms and their characteristics, recalibrates the reasoning threshold, starts the virtual simulation model, and analyzes and reasons about the operation of power equipment.

[0134] S6. The edge node adaptively expands the local knowledge base according to the optimized virtual simulation model and reasoning rules.

[0135] Based on the optimized virtual simulation model and the reasoning results of the distributed reasoning engine, the local knowledge base automatically expands the corresponding content;

[0136] Specifically, new device information is added to the device basic information unit, a new operating state is added to the operating state unit, and a new fault type is added to the fault information unit;

[0137] Each time the local knowledge base is updated, the virtual simulation model and the distributed reasoning engine perform simulation and reasoning of the operation of the power equipment according to the updated local knowledge base;

[0138] After the simulation and reasoning are completed, they will continue to be uploaded to the central server to form a two-way feedback mechanism.

[0139] The present embodiment also provides a system for constructing a knowledge base for power equipment operation management, including: a data acquisition module, a knowledge base construction module, a simulation module, a data fusion module, a global optimization module and an adaptive expansion module; the data acquisition module is used to deploy edge nodes, collect the operation data of power equipment in real time through sensors, and process it; the knowledge base construction module is used to construct a local knowledge base of the edge node based on the processed operation data, basic information of the power equipment and fault information; the simulation module is used to generate a virtual simulation model of the power equipment based on the local knowledge base to obtain virtual simulation data of the power equipment; the data fusion module is used to fuse the virtual simulation data of the power equipment and the operation data to obtain fused data, and obtain the fault prediction of the power equipment through the distributed reasoning engine reasoning; the global optimization module is used to globally integrate the fault prediction, local knowledge base and virtual simulation data, and optimize the virtual simulation model and reasoning rules; the adaptive expansion module is used for the edge node to adaptively expand the local knowledge base according to the optimized virtual simulation model and reasoning rules.

[0140] This embodiment also provides a computer device, which is suitable for the method of constructing a knowledge base for power equipment operation management, and includes: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of constructing a knowledge base for power equipment operation management as proposed in the above embodiment.

[0141] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0142] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for constructing a knowledge base for power equipment operation management proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0143] In summary, the present invention reduces dependence on central servers and improves the response speed of the system through: edge nodes collect and process data in real time, builds a local knowledge base based on the processed data, realizes effective management of equipment historical data, and provides a reliable basis for fault prediction; the generation and optimization of virtual simulation models enable the system to simulate the operation of equipment under different conditions in advance, further improving the prediction accuracy; by integrating operation data and simulation data, the distributed reasoning engine infers the health status of the equipment in real time, ensuring the accuracy of fault prediction; the system ensures continuous optimization of equipment management by adaptively expanding the knowledge base and dynamically updating simulation models and reasoning rules, which significantly improves the level of intelligence in the operation and management of power equipment.

[0144] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the file encryption method are provided.

[0145] In order to verify the effectiveness of the proposed method for constructing a knowledge base for power equipment operation management, actual experimental deployment and data recording were carried out.

[0146] The equipment includes a transformer with a rated power of 500kW and a generator with a rated power of 400kW. The edge node collects data such as voltage, current, and equipment temperature in real time through sensors.

[0147] A virtual simulation model of the power equipment was constructed to simulate the power output and temperature rise process of the power equipment under various load conditions, such as setting the power output and temperature rise curve of the equipment when the load increases to 80%.

[0148] Through the virtual simulation model, the operating parameters of the equipment under different loads were calculated and compared with the operating data. The output of the simulation model is very close to the operating status of the actual equipment, with an error within 5%.

[0149] In the subsequent stage of the experiment, the system used a distributed reasoning engine to predict the health status of the equipment by integrating virtual simulation data with operation data. The reasoning engine achieved early warning of equipment overheating, overload and other failures based on the extracted multi-dimensional feature vectors, combined with historical data and fault information. The system generated maintenance suggestions and fed back to the operation and maintenance personnel. During the reasoning process, the system compared the virtual simulation and operation data. When the load reached more than 80%, the system detected that the temperature of the equipment was rising too fast, triggering the early warning mechanism.

[0150] The details are shown in Table 1 below:

[0151] Table 1 Experimental data comparison table

[0152]

[0153]

[0154] Through the comparative analysis of the above experimental data, it can be seen that the method for constructing the power equipment operation management knowledge base proposed in the present invention shows obvious advantages under various loads.

[0155] First, in terms of voltage fluctuation control, the voltage fluctuation under the prior art SCADA system is large, especially when the load reaches 100%, the fluctuation is as high as 12.3%. The edge node in the present invention optimizes the simulation model and inference rules, and the voltage fluctuation is only 8.0%, which is significantly lower than the level of the prior art.

[0156] In terms of equipment temperature rise, the temperature of the prior art SCADA system reaches 45°C when the load reaches 100%. The present invention, through the optimization of the simulation model and the distributed computing of the edge inference engine, can predict the temperature rise trend of the equipment in advance and adjust the operating parameters of the equipment according to the feedback mechanism, so that the temperature rise is only 38°C, reducing the risk of overheating of the equipment.

[0157] Overall, the present invention not only realizes efficient monitoring of the operating status of power equipment through real-time data collection and processing of edge nodes, but also realizes early warning and effective control of equipment failures through the combination of simulation model optimization and reasoning engine.

[0158] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a knowledge base for power equipment operation management, characterized in that: include: Deploy edge nodes to collect and process the operating data of power equipment in real time through sensors; Build a local knowledge base of edge nodes based on processed operation data, basic information of power equipment and fault information; Based on the local knowledge base, a virtual simulation model of the power equipment is generated to obtain virtual simulation data of the power equipment; The virtual simulation data and operation data of power equipment are integrated to obtain fused data, and the fault prediction of power equipment is obtained through reasoning with a distributed reasoning engine; Failure prediction 、 Globally integrate local knowledge base and virtual simulation data to optimize virtual simulation models and reasoning rules; The edge nodes adaptively expand the local knowledge base based on the optimized virtual simulation model and inference rules.

2. The method for constructing a knowledge base for power equipment operation management according to claim 1, characterized in that: The edge nodes are deployed to collect and process the operation data of the power equipment in real time through sensors. The specific steps are as follows: Deploy edge nodes on power equipment. Each sensor communicates with the edge computing node through a standardized protocol. At the same time, the edge node establishes communication with the central server. Collect operating data of power equipment through sensors; The collected operation data is processed at the edge node.

3. The method for constructing a knowledge base for power equipment operation management according to claim 2, characterized in that: The local knowledge base of the edge node is constructed based on the processed operation data, basic information of the power equipment and fault information. The specific steps are as follows: According to different data types and functional requirements, the local knowledge base is divided into equipment basic information unit, operation status unit and fault information unit; Obtain basic information of power equipment, edge nodes and sensors from power equipment manufacturers and installation records, perform standard processing, create a unique identifier for each power equipment, edge node and sensor, associate and store it with the basic information of the power equipment, and obtain a basic information unit of the equipment; The operation data of the power equipment is sorted with the timestamp as the primary key and stored in the operation status unit. Every time the sensor collects the operation data of the power equipment, the operation status unit automatically updates the storage; Fault information is collected from maintenance records of power equipment, and standardized, and the processed fault information is associated with a device identifier and stored in a fault information unit; Create key field indexes for information in the local knowledge base and establish a fast retrieval mechanism.

4. The method for constructing a knowledge base for power equipment operation management according to claim 3, characterized in that: The virtual simulation model of the power equipment is generated based on the local knowledge base to obtain the virtual simulation data of the power equipment. The specific steps are as follows: Conduct mathematical modeling based on the physical characteristics, operating characteristics and historical operating data of power equipment; Through Ohm's law and power equation, the power output of power equipment under different load conditions is simulated. The specific contents are as follows; The temperature rise process of power equipment under different load conditions is simulated through the heating formula of resistance and the heat balance equation; Compare the virtual simulation model with the operational data and adjust the impedance, load conditions, heat dissipation coefficient and power loss in the virtual simulation model; Based on the fault information in the fault information unit, parameters corresponding to different faults are set in the virtual simulation model to simulate the fault occurrence process, and the virtual simulation model parameters are adjusted by comparing the output results of the virtual simulation model with the fault information; Iteratively compare the output results of the virtual simulation model with the operating data and fault information, and adjust the impedance, load conditions, heat dissipation coefficient and power loss coefficient according to the deviation of each comparison; The virtual simulation model generates virtual simulation data of power equipment by simulating the operating status of power equipment in different scenarios.

5. The method for constructing a knowledge base for power equipment operation management according to claim 4, characterized in that: The fusion data is obtained by fusing the virtual simulation data and the operation data of the power equipment, and the fault prediction of the power equipment is obtained by reasoning with the distributed reasoning engine. The specific steps are as follows: Processing the virtual simulation data according to the processing flow of the operation data; Use interpolation algorithm and dynamic time warping algorithm to time align and synchronize virtual simulation data and operation data; Extract key features from the operating data, extract key parameters from the virtual simulation data and combine them to form a multi-dimensional feature vector containing the operating data and the virtual simulation data; Deploy a distributed inference engine on each edge node, and each edge node runs the distributed inference engine independently; The distributed reasoning engine extracts the equipment's operating data and fault information from the local knowledge base, builds a rule base, and sets the reasoning threshold based on the fault information; The distributed reasoning engine extracts parameters from the multidimensional feature vector and compares them with the operating data and thresholds in the rule base to obtain anomalies and potential faults. When the distributed reasoning engine detects an anomaly, it starts the virtual simulation model to generate a hypothetical scenario, simulate the operating status of the power equipment under the detected anomaly, and predict the failure of the power equipment.

6. The method for constructing a knowledge base for power equipment operation management according to claim 5, characterized in that: The specific steps of globally integrating fault prediction, local knowledge base and virtual simulation data and optimizing virtual simulation models and inference rules are as follows: After completing data processing, reasoning, and analysis locally, the edge node synchronizes data with the central server to aggregate data from different edge nodes. The central server performs timestamp alignment and deduplication processing on the aggregated data; Extract multi-dimensional features from the aggregated data, and the central server performs time series analysis on the multi-dimensional features to identify the changing trends and periodicity during the operation of the equipment; The aggregated data is classified by similarity through a clustering algorithm, and a feature vector is constructed for each device in each time period; By calculating the Euclidean distance between feature vectors, the similarity between data of different edge nodes is measured, and the data of similar devices are classified into one category. Based on the clustering results, the common problems of different edge nodes are obtained; Based on common problems, the fault tree analysis method is used to analyze the factors that cause the problems, and solutions are given based on the collected fault information; The central server integrates the analysis results and solutions and feeds them back to the edge nodes; The edge node updates the local knowledge base content based on feedback, and the virtual simulation model and distributed reasoning engine perform simulation and reasoning based on the updated local knowledge base.

7. The method for constructing a knowledge base for power equipment operation management according to claim 6, characterized in that: The edge node adaptively expands the local knowledge base according to the optimized virtual simulation model and inference rules. The specific steps are as follows: Based on the reasoning results of the optimized virtual simulation model and reasoning rules, the local knowledge base automatically expands the corresponding content; Each time the local knowledge base is updated, the virtual simulation model and the distributed reasoning engine perform simulation and reasoning of the operation of the power equipment according to the updated local knowledge base; After the simulation and reasoning are completed, they will continue to be uploaded to the central server to form a two-way feedback mechanism.

8. A system for constructing a knowledge base for electric power equipment operation management, based on the method for constructing a knowledge base for electric power equipment operation management according to any one of claims 1 to 7, characterized in that: Including data acquisition module, knowledge base construction module, simulation module, data fusion module, global optimization module and adaptive expansion module; The data acquisition module is used to deploy edge nodes, collect the operating data of power equipment in real time through sensors, and process it; The knowledge base construction module is used to construct a local knowledge base of the edge node based on the processed operation data, basic information of the power equipment and fault information; The simulation module is used to generate a virtual simulation model of the power equipment based on the local knowledge base to obtain virtual simulation data of the power equipment; The data fusion module is used to fuse the virtual simulation data and the operation data of the power equipment to obtain fused data, and obtain the fault prediction of the power equipment through the distributed reasoning engine; The global optimization module is used to globally integrate fault prediction, local knowledge base and virtual simulation data, and optimize virtual simulation models and inference rules; The adaptive expansion module is used by the edge node to adaptively expand the local knowledge base according to the optimized virtual simulation model and reasoning rules.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for constructing the power equipment operation management knowledge base according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing a power equipment operation management knowledge base as described in any one of claims 1 to 7 are implemented.

Images