Station global equipment information management system

Abstract

The invention discloses a global equipment information management system for a station, belongs to the technical field of information management, and solves the problem that the maintenance time of electrical equipment / system of the electrical station is shortened by managing the electrical process of the electrical station so as to ensure that engineers can be assisted in judging the specific fault type at the first time. The fault module is used for judging a fault problem according to information fed back by the screening module; the screening module is used for pre-judging the fault after extracting the environmental parameters in real time according to the parameter recording template, and feeding back screening information; and the parameter recording module is used for extracting the environmental parameters of the electrical equipment in real time according to the electrical measurement module. Real-time environmental parameters of the electrical equipment are automatically detected through the electrical measurement module and transmitted to the parameter recording module, the positive and negative interference completion modules judge environmental parameter faults in real time, and even under electromagnetic radiation interference, the sensor still provides fault information, assists in maintenance, shortens maintenance time and guarantees personal safety.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to a site global equipment information management system. Background Art

[0002] Electrical stations usually refer to the collection of facilities used for power generation, substations, distribution and power dispatching in the power system. These stations are the core components of the power supply network and are responsible for efficiently and safely transmitting electrical energy from power stations to the user end. At the power generation station, the original energy is converted into electrical energy through various energy conversion technologies, such as thermal power generation, hydropower generation, nuclear power generation or renewable energy generation. The substation is responsible for adjusting the voltage to meet the needs of long-distance transmission or local distribution to ensure the stable supply of electrical energy. The distribution station further converts high-voltage electrical energy into low-voltage electrical energy suitable for household and commercial use and distributes it to various users. The power dispatching center monitors the power grid status in real time through advanced monitoring and control systems, optimizes the allocation of power resources, and ensures the stable operation of the power grid and the reliability of power supply. In addition, with the development of smart grid technology, modern electrical stations are increasingly integrating automation, informationization and intelligent technologies, which improves the efficiency and flexibility of the power system, and also provides solutions to cope with the volatility and uncertainty of renewable energy.

[0003] It is necessary to carry out a certain degree of management for the electrical processes used in electrical stations, especially the operation and maintenance management of these electrical equipment and systems. For electrical stations, the failure of the above-mentioned electrical equipment and systems will have a very significant negative impact.

[0004] First, safety risk is one of the most prominent issues. Once the electrical system fails, key safety equipment such as the control system, cooling system or emergency shutdown system may fail, leading to serious safety hazards.

[0005] Secondly, power outage is one of the common consequences of electrical equipment failure in electrical stations. Once a generator, transformer or transmission line fails, the electrical station may shut down, affecting the stability and reliability of power supply. This will not only bring difficulties to the operation of the electrical station itself, but also affect the power supply in the surrounding areas, which may cause serious social and economic impacts.

[0006] In addition, electrical equipment failures can also lead to production losses and economic losses. The downtime or reduced power generation capacity of electrical stations will lead to reduced power production, which in turn will cause production losses and reduced revenue. At the same time, repairing and replacing faulty equipment also requires a lot of time and resources, further exacerbating the extent of economic losses.

[0007] Electrical equipment failures can also have serious impacts on the environment. For example, cooling system failure or radiation leakage can lead to pollution and damage to the surrounding environment, causing long-term pollution effects on soil, water and air, and posing a serious threat to ecosystems and human health.

[0008] To sum up, it can be understood that electrical sites need to take proper management actions for the electrical equipment and electrical processes therein to avoid the occurrence of negative problems.

[0009] In the prior art, electrical stations often obtain various parameters of various electrical equipment or systems and combine the work experience of engineers to determine whether a fault occurs, and it is necessary to determine the specific fault of each electrical equipment or system during the specific maintenance process. Taking the generator as an example, in the electrical station, due to the high temperature and electromagnetic radiation in its working environment, it is very easy to have problems such as 1. insulation failure; 2. bearing failure; 3. rotor imbalance; 4. excessive rotor vibration; 5. winding failure; 6. excitation system failure during the working process, and the manifestations of these fault problems are basically 1. overheating; 2. noise; 3. abnormal current; 4. abnormal voltage; 5. smoke. In the case of similar manifestations of the fault problems, engineers need to combine their more senior experience and the on-site maintenance situation to determine the specific fault. However, for those in the electrical station, long-term stay for maintenance and judgment will not only cause a clear physical health impact on the engineers responsible for maintenance, but also cause a large amount of excess energy in the electrical station to be wasted and consumed for no reason, and cannot be converted into electricity in time for people to use.

[0010] Therefore, it is necessary to manage the electrical processes of the electrical station to ensure that engineers can get assistance in determining the specific fault at the first time, so as to shorten the maintenance time of the electrical equipment / system of the electrical station.

[0011] Therefore, a station global equipment information management system is proposed to solve or alleviate the above problems. Summary of the invention

[0012] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a site global equipment information management system.

[0013] In order to achieve the above object, the present invention adopts the following technical solutions: A global equipment information management system for a station includes a fault module: used to judge the fault problem according to the information fed back by the identification module; Identification module: used to extract environmental parameters in real time according to the parameter collection template, predict fault judgment, and feedback identification information; Parameter collection module: It is used to extract the environmental parameters of electrical equipment in real time according to the electrical measurement module, match the problem using the prediction model, and feedback the fault judgment; Electrical measurement module: used to extract environmental parameters of electrical equipment in real time based on sensors, and pass them to the parameter collection module for problem matching.

[0014] Preferably, the prediction model includes a positive interference completion module; Positive interference completion module: used to simulate and complete the environmental parameters to the state before electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, match them with the fault parameter library, and reflect the fault judgment; Fault parameter library: used to match corresponding fault judgments based on the environmental parameters recorded by the sensor under various fault conditions of electrical equipment.

[0015] Preferably, the positive interference complement module is used to simulate and complement the environmental parameters to the state before electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, match them with the fault parameter library, and reflect the method of fault judgment, including the following steps: The electrical measurement module extracts several electrical devices when there is no electromagnetic interference, and the electrical measurement module extracts several electrical devices when there is electromagnetic interference to obtain normalized spectrum analysis data 1 and spectrum analysis data 2 respectively; Use spectrum analysis data 1 as a training set to mark spectrum features under normal and fault conditions; Select a random forest regression model and train it using the training set to learn the noise spectrum data patterns under normal and fault conditions; The spectrum analysis data 2 is taken as input, and the trained random forest regression model is used for prediction to obtain the completed spectrum analysis data 2; The completed spectrum analysis data is reversely converted to environmental parameters, and the variance is calculated with the fault parameter library, the closest fault parameters are obtained by comparison, and the fault judgment is output.

[0016] Preferably, the prediction model further includes a negative interference completion module; Negative interference completion module: used to simulate and complete the fault parameter library to the state after electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, so that the two match and reflect the fault judgment.

[0017] Preferably, the negative interference complement module is used to simulate and complement the fault parameter library to the state after electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, so that the two are matched, and the method for reflecting the fault judgment includes the following steps: The fault parameter library and the electrical measurement module extract a number of electrical devices during electromagnetic interference to obtain normalized spectrum analysis data 3 and spectrum analysis data 4 respectively; Extract statistical features from spectrum analysis data, including frequency peak, frequency bandwidth, time domain characteristics, power spectrum density, etc.; Analyze interference characteristics using spectrum analysis data and establish an electromagnetic interference model; Generate simulated interference signals according to electromagnetic interference models; Combining the simulated interference signal with the spectrum analysis data 3, and adjusting the spectrum analysis data 3 to a state after electromagnetic interference; The completed spectrum analysis data is reversely converted to the environmental parameters of the state after electromagnetic interference, and the variance is calculated with the environmental parameters transmitted by the electrical measurement module, and the closest fault parameters are obtained by comparison, and the fault judgment is output.

[0018] Preferably, the identification module further includes a manual collection module; Manual collection module: It is used to sort out and eliminate the fault information based on the manual feedback of the fault parameter library. After the fault core is determined, the fault problem library is formed using the fault core.

[0019] Preferably, the manual collection module is used to sort out and eliminate the fault information fed back by the fault parameter library manually, and after the fault core is obtained, the method of forming a fault problem library using the fault core includes the following steps: Manually divide the fault information fed back by the fault parameter library into long sentences, word segmentation, stop word removal, and part-of-speech tagging; Calculate the frequency of each word in each long sentence; Calculate the inverse document frequency of each word in each long sentence; Multiply the word frequency by the inverse document frequency to get the weight value of each word; Extract the words with the weight values ​​sorted at the end of each long sentence to form the fault core; The fault core is stored to form a fault problem library.

[0020] Preferably, the screening module further includes a final case collection module; Final case collection module: It is used to sort out and eliminate the correct fault judgment information based on the manual feedback of the fault judgment output by the prediction model, and enter the fault problem library after the fault core is determined.

[0021] Preferably, the final case collection module is used to sort out and eliminate the information based on the correct fault judgment feedback output by the prediction model, and after the fault core is determined, the method of entering the fault problem library includes the following steps: The correct fault judgments of the fault judgment feedback output by the prediction model are manually divided into long sentences, word segmentation, stop words removal, and part-of-speech tagging; Calculate the frequency of each word in each long sentence; Calculate the inverse document frequency of each word in each long sentence; Multiply the word frequency by the inverse document frequency to get the weight value of each word; Extract the words with the weight values ​​sorted at the end of each long sentence to form the fault core; Store the fault core in the fault problem library.

[0022] Preferably, the fault module includes a generator fault module, a steam turbine fault module, a cooling system fault module, and a control system fault module, and the electrical measurement module includes a voltage sensor, a current sensor, a temperature sensor, a sound sensor, and a smoke sensor.

[0023] The present invention has the following beneficial effects: The present invention can detect the real-time environmental parameters of electrical equipment by the electrical measurement module and transmit them to the parameter collection module. The positive interference complement module and the negative interference complement module in the parameter collection module respectively perform fault judgment and prediction of the real-time environmental parameters, thereby achieving that when electromagnetic radiation in the electrical station interferes with electromagnetic signals, the sensors in the electrical measurement module can still provide specific fault information of the electrical equipment for reference, assist maintenance engineers in repairing the electrical equipment, reduce the time that maintenance engineers stay in the electrical station, ensure their personal safety, and also shorten the repair time of the electrical equipment / system in the electrical station. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a structural block diagram of the present invention; Figure 2 It is a structural block diagram of the electrical measurement module in the present invention. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0026] A global equipment information management system for a station, such as Figure 1 and 2 As shown, Including fault module: used to judge the fault problem according to the information fed back by the identification module; Identification module: used to extract environmental parameters in real time according to the parameter collection template, predict fault judgment, and feedback identification information; Parameter collection module: It is used to extract the environmental parameters of electrical equipment in real time according to the electrical measurement module, match the problem using the prediction model, and feedback the fault judgment; Electrical measurement module: used to extract environmental parameters of electrical equipment in real time based on sensors, and pass them to the parameter collection module for problem matching.

[0027] The environmental parameters of electrical equipment are extracted through the sensors in the electrical measurement module. The generator is the main electrical equipment. During the detection, the electrical measurement module includes voltage sensors, current sensors, temperature sensors, sound sensors, and smoke sensors. The problems encountered by the generator in the electrical station are mainly: 1. Insulation failure; 2. Bearing failure; 3. Rotor imbalance; 4. Excessive rotor vibration; 5. Winding failure; 6. Excitation system failure; and the main manifestations of the above six faults also basically include overheating, noise, abnormal voltage, abnormal current, and smoke. Therefore, voltage sensors, current sensors, temperature sensors, sound sensors, and smoke sensors are set. Five sensors are used to extract environmental parameters during the working process of the generator. After the above environmental parameters pass through the prediction model in the parameter collection module, the matching problems can be obtained, and the definite fault judgment can be output to the maintenance engineer who has not yet gone to the faulty generator, so as to prepare and pave the way for the maintenance work of the maintenance engineer in advance. With the high accuracy of this system, it can greatly shorten the time that the maintenance engineer stays in the electrical station, reduce the possible harm of radiation in the electrical station to the human body, ensure their health and safety, and also greatly shorten the downtime of the generator in the electrical station, reducing the energy waste and consumption caused by its shutdown.

[0028] Preferably, the prediction model includes a positive interference completion module; Positive interference completion module: used to simulate and complete the environmental parameters to the state before electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, match them with the fault parameter library, and reflect the fault judgment; Fault parameter library: used to match corresponding fault judgments based on the environmental parameters recorded by the sensor under various fault conditions of electrical equipment.

[0029] The positive interference completion module is set up because all the above-mentioned sensors will inevitably cause electromagnetic interference due to electromagnetic radiation in the environment of the electrical station, which will then affect the signals output by all sensors. The environmental parameters emitted by the sensors that have been interfered with are then complemented / repaired so that they can return to the state before the electromagnetic interference. The simulated environmental parameters that are not affected by electromagnetic interference are then compared with the environmental parameters in the fault parameter library, and then the corresponding fault judgment is matched, so as to reduce or even eliminate the impact of electromagnetic radiation in the electrical station on the environmental parameters transmitted by the sensors.

[0030] Preferably, the positive interference complement module is used to simulate and complement the environmental parameters to the state before electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, match them with the fault parameter library, and reflect the method of fault judgment, including the following steps: The electrical measurement module extracts several electrical devices when there is no electromagnetic interference, and the electrical measurement module extracts several electrical devices when there is electromagnetic interference to obtain normalized spectrum analysis data 1 and spectrum analysis data 2 respectively; Use spectrum analysis data 1 as a training set to mark spectrum features under normal and fault conditions; Select a random forest regression model and train it using the training set to learn the noise spectrum data patterns under normal and fault conditions; The spectrum analysis data 2 is taken as input, and the trained random forest regression model is used for prediction to obtain the completed spectrum analysis data 2; The completed spectrum analysis data is reversely converted to environmental parameters, and the variance is calculated with the fault parameter library, the closest fault parameters are obtained by comparison, and the fault judgment is output.

[0031] Preferably, the prediction model also includes a negative interference completion module; Negative interference completion module: used to simulate and complete the fault parameter library to the state after electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, so that the two match and reflect the fault judgment.

[0032] The setting of the negative interference complement module is used for the same purpose as the positive interference complement module, which is to reduce or even eliminate the interference of the environmental parameters emitted by the sensor due to the electromagnetic radiation in the electrical station. However, the means adopted are opposite to those of the positive interference complement module. By simulating the interference caused by the electromagnetic radiation in the electrical station, the fault parameter library is simulated by itself to form a fault parameter library after interference, so that it can be compared with the environmental parameters emitted by the sensor under the same conditions, making the match between the two more reasonable, and finally giving an accurate fault judgment, thereby improving the accuracy of the system.

[0033] Preferably, the negative interference complement module is used to simulate and complement the fault parameter library to the state after electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, so that the two are matched, and the method for reflecting the fault judgment includes the following steps: The fault parameter library and the electrical measurement module extract a number of electrical devices during electromagnetic interference to obtain normalized spectrum analysis data 3 and spectrum analysis data 4 respectively; Extract statistical features from spectrum analysis data, including frequency peak, frequency bandwidth, time domain characteristics, power spectrum density, etc.; Analyze interference characteristics using spectrum analysis data and establish an electromagnetic interference model; Generate simulated interference signals according to electromagnetic interference models; Combining the simulated interference signal with the spectrum analysis data 3, and adjusting the spectrum analysis data 3 to a state after electromagnetic interference; The completed spectrum analysis data is reversely converted to the environmental parameters of the state after electromagnetic interference, and the variance is calculated with the environmental parameters transmitted by the electrical measurement module, and the closest fault parameters are obtained by comparison, and the fault judgment is output.

[0034] It should be noted that the transformations of spectrum analysis data 1, spectrum analysis data 2, spectrum analysis data 3, and spectrum analysis data 4 are all performed using the Fourier transform formula; The method for establishing the electromagnetic interference model includes the following steps: Extract key features that are helpful in describing interference characteristics from spectrum analysis data 4, including peak frequency: the frequency with the largest amplitude in the interference signal, frequency bandwidth: the frequency range covered by the interference signal, power spectrum density: describes the power distribution within a unit frequency band, and time domain characteristics: such as pulse width, rise time, etc. Perform statistical analysis on the extracted features, including calculating statistical parameters such as mean, variance, skewness, kurtosis, etc., analyzing the distribution characteristics of the interference signal to determine whether it obeys Gaussian distribution; Use time-frequency analysis tools to study the time-frequency characteristics of interference signals, including short-time Fourier transform (STFT), wavelet transform (CWT), etc. Take the spectrum analysis data four times to train the autoregressive (AR) model, and finally get the electromagnetic interference model.

[0035] Preferably, the identification module also includes a manual collection module; Manual collection module: It is used to sort out and eliminate the fault information based on the manual feedback of the fault parameter library. After the fault core is determined, the fault problem library is formed using the fault core.

[0036] By setting up the manual collection module, a fault problem library is formed for fault core matching. The fault problem library can be used for subsequent fault judgment matching and provide a reference for the automatic judgment of the parameter collection module, so that the fault judgment accuracy of the final output of the parameter collection module remains high.

[0037] Preferably, the manual collection module is used to sort out and eliminate the fault information fed back by the manual fault parameter library, and after the fault core is obtained, the method of forming a fault problem library using the fault core includes the following steps: Manually divide the fault information fed back by the fault parameter library into long sentences, word segmentation, stop word removal, and part-of-speech tagging; Calculate the frequency of each word in each long sentence; Calculate the inverse document frequency of each word in each long sentence; Multiply the word frequency by the inverse document frequency to get the weight value of each word; Extract the words with the weight values ​​sorted at the end of each long sentence to form the fault core; The fault core is stored to form a fault problem library.

[0038] Preferably, the screening module also includes a final case collection module; Final case collection module: It is used to sort out and eliminate the correct fault judgment information based on the manual feedback of the fault judgment output by the prediction model, and enter the fault problem library after the fault core is determined.

[0039] The setting of the final case collection module is an output of the actual correct fault judgment after the maintenance engineer obtains the screening information and completes the maintenance. This fault judgment is extremely reliable and is entered into the fault problem library to expand the reference between the fault problem library and the environmental parameters, so that as the number of maintenance increases, the fault judgment accuracy of the system output will continue to increase at any time.

[0040] Preferably, the final case collection module is used to sort out and eliminate the information based on the correct fault judgment feedback output by the prediction model, and after the fault core is determined, the method of entering the fault problem library includes the following steps: The correct fault judgments of the fault judgment feedback output by the prediction model are manually divided into long sentences, word segmentation, stop words removal, and part-of-speech tagging; Calculate the frequency of each word in each long sentence; Calculate the inverse document frequency of each word in each long sentence; Multiply the word frequency by the inverse document frequency to get the weight value of each word; Extract the words with the weight values ​​sorted at the end of each long sentence to form the fault core; Store the fault core in the fault problem library.

[0041] Preferably, the fault modules include a generator fault module, a steam turbine fault module, a cooling system fault module, and a control system fault module.

[0042] An embodiment of the present application provides a computer-readable storage medium, on which a global equipment information management system of a station is stored.

[0043] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A global equipment information management system for a station, characterized in that: Including fault module: used to judge the fault problem according to the information fed back by the identification module; Identification module: used to extract environmental parameters in real time according to the parameter collection template, predict fault judgment, and feedback identification information; Parameter collection module: It is used to extract the environmental parameters of electrical equipment in real time according to the electrical measurement module, match the problem using the prediction model, and feedback the fault judgment; Electrical measurement module: used to extract environmental parameters of electrical equipment in real time based on sensors and transmit them to parameter collection module for problem matching; The prediction model includes a positive interference completion module; Positive interference completion module: used to simulate and complete the environmental parameters to the state before electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, match them with the fault parameter library, and reflect the fault judgment; Fault parameter library: used to match the corresponding fault judgment according to the environmental parameters recorded by the sensor under various fault conditions of electrical equipment; The positive interference complement module is used to simulate and complement the environmental parameters to the state before electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, match them with the fault parameter library, and reflect the method of fault judgment, including the following steps: The electrical measurement module extracts several electrical devices when there is no electromagnetic interference, and the electrical measurement module extracts several electrical devices when there is electromagnetic interference to obtain normalized spectrum analysis data 1 and spectrum analysis data 2 respectively; Use spectrum analysis data 1 as a training set to mark spectrum features under normal and fault conditions; Select a random forest regression model and train it using the training set to learn the noise spectrum data patterns under normal and fault conditions; The spectrum analysis data 2 is taken as input, and the trained random forest regression model is used for prediction to obtain the completed spectrum analysis data 2; The completed spectrum analysis data is reversely converted to environmental parameters, and the variance is calculated with the fault parameter library, the closest fault parameters are obtained by comparison, and the fault judgment is output.

2. A station global equipment information management system according to claim 1, characterized in that: The prediction model also includes a negative interference completion module; Negative interference completion module: used to simulate and complete the fault parameter library to the state after electromagnetic interference according to the environmental parameters transmitted by the electrical measurement module, so that the two match and reflect the fault judgment.

3. A station global equipment information management system according to claim 2, characterized in that: The negative interference complement module is used to simulate and complement the fault parameter library to the state after electromagnetic interference according to the environmental parameters transmitted by the electric measurement module, so that the two are matched and the method of reflecting the fault judgment includes the following steps: The fault parameter library and the electrical measurement module extract a number of electrical devices during electromagnetic interference to obtain normalized spectrum analysis data 3 and spectrum analysis data 4 respectively; Extract statistical features from spectrum analysis data, including frequency peak, frequency bandwidth, time domain characteristics, power spectrum density, etc.; Analyze interference characteristics using spectrum analysis data and establish an electromagnetic interference model; Generate simulated interference signals according to electromagnetic interference models; Combining the simulated interference signal with the spectrum analysis data 3, and adjusting the spectrum analysis data 3 to a state after electromagnetic interference; The completed spectrum analysis data is reversely converted to the environmental parameters of the state after electromagnetic interference, and the variance is calculated with the environmental parameters transmitted by the electrical measurement module, and the closest fault parameters are obtained by comparison, and the fault judgment is output.

4. A station global equipment information management system according to claim 1, characterized in that: The screening module also includes a manual collection module; Manual collection module: It is used to sort out and eliminate the fault information based on the manual feedback of the fault parameter library. After the fault core is determined, the fault problem library is formed using the fault core.

5. A station global equipment information management system according to claim 4, characterized in that: The manual collection module is used to sort out and eliminate the fault information fed back by the fault parameter library manually, and after the fault core is obtained, the method of forming a fault problem library using the fault core includes the following steps: Manually divide the fault information fed back by the fault parameter library into long sentences, word segmentation, stop word removal, and part-of-speech tagging; Calculate the frequency of each word in each long sentence; Calculate the inverse document frequency of each word in each long sentence; Multiply the word frequency by the inverse document frequency to get the weight value of each word; Extract the words with the weight values ​​sorted at the end of each long sentence to form the fault core; The fault core is stored to form a fault problem library.

6. A station global equipment information management system according to claim 4, characterized in that: The screening module also includes a final case collection module; Final case collection module: It is used to sort out and eliminate the correct fault judgment information based on the manual feedback of the fault judgment output by the prediction model, and enter the fault problem library after the fault core is determined.

7. A station global equipment information management system according to claim 6, characterized in that: The final case collection module is used to sort out and eliminate the information based on the correct fault judgment feedback output by the artificial prediction model, and after the fault core is determined, the method of entering it into the fault problem library includes the following steps: The correct fault judgments of the fault judgment feedback output by the prediction model are manually divided into long sentences, word segmentation, stop words removal, and part-of-speech tagging; Calculate the frequency of each word in each long sentence; Calculate the inverse document frequency of each word in each long sentence; Multiply the word frequency by the inverse document frequency to get the weight value of each word; Extract the words with the weight values ​​sorted at the end of each long sentence to form the fault core; Store the fault core in the fault problem library.

8. A station global equipment information management system according to claim 1, characterized in that: The fault modules include a generator fault module, a steam turbine fault module, a cooling system fault module, and a control system fault module, and the electrical measurement module includes a voltage sensor, a current sensor, a temperature sensor, a sound sensor, and a smoke sensor.

Images