Thermal power generation rotary auxiliary machine equipment state maintenance decision-making method based on risk assessment

Abstract

The invention discloses a thermal power generation rotary auxiliary machine equipment state maintenance decision-making method based on risk assessment, and belongs to the technical field of equipment maintenance. According to the method, the problem that the prior art depends on experience and feeling to judge the operation state of the equipment, and large subjectivity and uncertainty exist is solved, the operation state of the equipment is predicted by constructing the neural network model, and a differentiated maintenance strategy is formulated in combination with risk scores; key equipment and high-risk equipment can be overhauled and maintained in time, the failure rate of the key equipment is reduced, and normal operation of a thermal power generation system is ensured; and secondly, the equipment is subjected to priority ranking according to importance, key equipment and equipment with high risk indexes are ensured to be maintained preferentially, common equipment and equipment with low risk indexes are ensured to be maintained at proper time, the reasonable arrangement of maintenance sequence and mode is effectively realized, resource waste caused by excessive maintenance is avoided, and the maintenance cost is balanced.

Description

Technical Field

[0001] The invention relates to the technical field of equipment maintenance, and in particular to a risk assessment-based decision method for condition maintenance of rotating auxiliary equipment of thermal power generation. Background Art

[0002] Thermal power generation rotating auxiliary equipment usually refers to the equipment responsible for assisting the main engine in a thermal power plant. Their main function is to improve the efficiency of the main engine and ensure the safe and stable operation of the power generation system. This type of equipment plays a vital role in power plants. If any equipment fails or is damaged, it may cause problems in the entire power generation system. Therefore, thermal power plants are one of the most important components of the power system, and their operating status is directly related to the safety and stability of the power grid. However, during long-term operation, thermal power units will generate a lot of friction and wear, causing failures and damage to the units. Therefore, it is very important to regularly perform status inspections on thermal power units.

[0003] Traditional condition-based maintenance mainly relies on experience and feeling to judge the operating status of equipment, which is subject to great subjectivity and uncertainty.

[0004] Therefore, it does not meet the existing needs. In this regard, we propose a condition maintenance decision-making method for rotating auxiliary equipment in thermal power generation based on risk assessment. Summary of the invention

[0005] The purpose of the present invention is to provide a condition maintenance decision method for rotating auxiliary equipment of thermal power generation based on risk assessment. By constructing a neural network model to predict the operating status of the equipment, differentiated maintenance strategies are formulated in combination with risk scoring; key equipment and high-risk equipment can be inspected and maintained in time to reduce the failure rate of key equipment and ensure the normal operation of the thermal power generation system; secondly, the equipment is prioritized according to its importance to ensure that key equipment and equipment with high risk indicators are maintained first, and ordinary equipment and equipment with low risk indicators are maintained at appropriate times, which effectively realizes the reasonable arrangement of maintenance sequence and methods, avoids the waste of resources caused by excessive maintenance, balances maintenance costs, and solves the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A risk assessment-based condition maintenance decision method for thermal power generation rotating auxiliary equipment includes the following steps:

[0008] Step 1: Obtain the historical operation data of the equipment and pre-process the historical operation data of the equipment as a historical data sample; the pre-processing includes: cleaning the historical operation data and extracting feature information from the historical operation data;

[0009] Step 2: Build a neural network model, and train and test the neural network model based on historical operation data. The successfully tested neural network model is used to predict the operating status of the equipment.

[0010] Step 3: Based on the prediction results of historical operation data, formulate indicator scores for equipment under different operating conditions to assess the failure risk of equipment;

[0011] Step 4: Obtain the attributes of the rotating auxiliary equipment of thermal power generation, and prioritize different equipment according to their importance; formulate differentiated maintenance strategies based on the different fault index scores of the equipment to ensure that key equipment and equipment with high risk indicators are maintained first, and ordinary equipment and equipment with low risk indicators are maintained at appropriate times to balance maintenance costs;

[0012] Step 5: Monitor the running status of the equipment in real time, including the vibration, temperature and lubricating oil condition of the equipment during operation; specifically, this is achieved through vibration diagnosis technology, oil analysis technology, infrared equipment diagnosis technology and ultrasonic leakage monitoring technology;

[0013] Step 6: Based on the real-time monitoring results of the equipment, implement the equipment maintenance plan according to the differentiated maintenance strategy.

[0014] Furthermore, it also includes:

[0015] Step 7. During the maintenance process, continuously collect the equipment's operating data and update the equipment status information in a timely manner. Continuously optimize and maintain differentiated maintenance strategies based on the equipment's real-time operating data and operating status to ensure long-term and stable operation of the equipment.

[0016] Furthermore, in step 2, a neural network model is constructed, and the neural network model is trained and tested based on historical operation data, which specifically includes the following steps:

[0017] The historical operation data is divided into a training set and a test set, and a neural network model is constructed; the training set is imported into the neural network model for training to establish the feature layer of the neural network model, and the training results are output; the test set is then imported into the neural network model for testing, and the test results are output; the test results are compared with the training results to verify whether the neural network model accurately predicts the equipment operation status.

[0018] Furthermore, in step three, according to the prediction results of historical operation data, the index scores of the equipment under different operating conditions are formulated, which specifically includes the following steps:

[0019] Obtain different prediction results for the equipment, sort them by risk level, and obtain risk indicators of different levels; define scoring standards for risk indicators of different levels based on actual scenarios to ensure that each level of risk indicators has an exclusive scoring range.

[0020] Furthermore, in step 4, different devices are prioritized according to their importance, which specifically includes the following steps:

[0021] The tasks performed and locations of different equipment in the thermal power generation rotating auxiliary equipment are obtained. According to the role and impact of the equipment in the thermal power generation system, the equipment is divided into key equipment and common equipment, and the geographical location of each type of equipment is marked.

[0022] Furthermore, in step 4, a differentiated maintenance strategy is formulated in combination with different fault indicator scores of the equipment, specifically including the following steps:

[0023] Develop a priority maintenance plan for critical equipment and equipment with higher risks, carry out emergency repairs when necessary, and increase the frequency of maintenance; develop a general maintenance plan for critical equipment and equipment with higher risks, set reasonable maintenance time points based on the equipment's working hours, and carry out the maintenance at the designated time points.

[0024] Furthermore, after verifying whether the neural network model predicts the equipment operating status accurately, the following steps are specifically included:

[0025] If the test results are consistent with the output of the training results, the prediction ability of the neural network model is judged to be accurate; if the test results are inconsistent with the output of the training results, the prediction ability of the neural network model is judged to be inaccurate, and the historical operation data is sorted out and redivided into training sets and test sets, and then imported into the neural network model for training and testing until the test results are consistent with the output of the training results, and the optimized neural network model is obtained.

[0026] Furthermore, in step 1, the historical operation data of the equipment is preprocessed, which specifically includes the following steps:

[0027] By using descriptive statistics, such as mean, median, standard deviation, quartile, etc., the distribution of historical operation data can be obtained; and by using charts, such as histograms, box plots, scatter plots, etc., the characteristics of historical operation data can be intuitively displayed to identify possible outliers and trends in historical operation data; data with large areas of missing values ​​in historical operation data can be deleted, and the mean filling method can be selected to supplement data with a small amount of missing values; unique identifiers or a combination of multiple fields can be used to determine whether there are duplications in historical operation data, and duplicate records can be deleted or merged to ensure that only one record is retained, and the remaining duplicates can be deleted, or the information of duplicate records can be merged according to business logic; data conversion and unified standardization of historical operation data can be performed to ensure the correctness of data types, such as converting strings to date formats, or converting numerical data to categorical data; data can be standardized uniformly and standardized according to needs, such as z-score standardization to put data on the same scale; through the above steps, the equipment operation data can be effectively cleaned to ensure the accuracy and completeness of the data, providing a reliable basis for subsequent data analysis and decision-making.

[0028] Furthermore, before preprocessing the historical operation data of the equipment, the following steps are specifically included:

[0029] Apply for access to the thermal power plant archive system. After obtaining access rights to the archive system, use web crawler technology to obtain multiple sets of historical operating data of the equipment in different time periods.

[0030] Furthermore, after data conversion and unified standardization, the following steps are specifically included:

[0031] Extract effective feature information from historical operation data based on the tasks performed by the equipment, and convert the feature information into digital features suitable for learning by the neural network model; store the preprocessed historical operation data in the database to ensure that subsequent data processing and analysis can use high-quality data.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention predicts the operating status of equipment by constructing a neural network model, and formulates differentiated maintenance strategies in combination with risk scoring; key equipment and high-risk equipment can be inspected and maintained in a timely manner, the failure rate of key equipment can be reduced, and the normal operation of the thermal power generation system can be ensured; secondly, the equipment is prioritized according to its importance, ensuring that key equipment and equipment with high risk indicators are maintained first, and ordinary equipment and equipment with low risk indicators are maintained at appropriate times, effectively realizing the reasonable arrangement of maintenance sequence and methods, avoiding waste of resources caused by excessive maintenance, and balancing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The present invention is a flow chart of the risk assessment-based condition maintenance decision-making method for thermal power generation rotating auxiliary equipment. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention 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, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] In order to solve the technical problem that the current technology mainly relies on experience and feeling to judge the operating status of the equipment, this method has great subjectivity and uncertainty, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0037] A risk assessment-based condition maintenance decision method for thermal power generation rotating auxiliary equipment includes the following steps:

[0038] Step 1: Obtain the historical operation data of the equipment and pre-process the historical operation data of the equipment as a historical data sample; the pre-processing includes: cleaning the historical operation data and extracting feature information from the historical operation data; specifically, the following steps are included:

[0039] Apply for access to the thermal power plant archive system. After obtaining access to the archive system, use web crawler technology to obtain multiple sets of historical operating data of the equipment in different time periods; by using descriptive statistics, such as: using the mean method to obtain the distribution of historical operating data, so as to obtain the level of operating parameters of each device, and judge the operating pressure and usage frequency of each device based on the operating parameters, so as to provide data support for the subsequent prioritization of equipment; and use charts, such as: the histogram method to intuitively display the characteristics of historical operating data, so as to identify possible outliers and trends in historical operating data; delete data with large areas of missing values ​​in historical operating data, and select the mean filling method to supplement data with a small amount of missing values, so as to ensure the validity of operating parameters; use unique identifiers or combine multiple fields to determine whether there are duplications in historical operating data, and delete or merge duplicate records to ensure that only one record is retained, delete the remaining duplicates, or based on The business logic merges the information of duplicate records to ensure the uniqueness of the operating parameters; converts and standardizes the historical operating data to ensure the correctness of the data type, such as converting a string into a date format, or converting numeric data into categorical data; standardizes the data uniformly and standardizes it according to the needs, such as using the z-score standardization method to standardize the parameter data so that the data is on the same scale; extracts valid feature information from the historical operating data based on the tasks performed by the equipment, and converts the feature information into digital features suitable for learning by the neural network model, so as to facilitate the subsequent training and testing of the neural network model; stores the preprocessed historical operating data in the database to ensure that high-quality data can be used for subsequent data processing and analysis; through the above steps, the equipment operation data can be effectively cleaned to ensure the accuracy and completeness of the data, providing a reliable basis for subsequent data analysis and decision-making.

[0040] Step 2: Build a neural network model, and train and test the neural network model based on historical operation data. The successfully tested neural network model is used to predict the operating status of the equipment. Specifically, the following steps are included:

[0041] The historical operation data is divided into a training set and a test set, and a neural network model is constructed; the training set is imported into the neural network model for training to establish the feature layer of the neural network model and output the training results; the test set is then imported into the neural network model for testing and the test results are output; the test results are compared with the training results to verify whether the neural network model accurately predicts the operating status of the equipment; if the test results are consistent with the output of the training results, the prediction ability of the neural network model is judged to be accurate; if the test results are inconsistent with the output of the training results, the prediction ability of the neural network model is judged to be inaccurate, and the historical operation data is sorted out and re-divided into training sets and test sets, and then imported into the neural network model for training and testing until the test results are consistent with the output of the training results, and the optimized neural network model is obtained. ; Specifically, by dividing the preprocessed historical operation data into a training set and a test set, the training set is first imported into the neural network model for training, and the training result, i.e., the preliminary prediction result of the equipment operation status, is output; then the corresponding test set is imported into the trained neural network model for testing, and the test result, i.e., the secondary prediction result of the equipment operation status, is output; such as: if the preliminary prediction result of the equipment operation status shows that the equipment operation status is normal, the secondary prediction result of the equipment operation status must also show that the equipment operation status is normal before the current neural network model can be judged as an optimized model; if the secondary prediction result of the equipment operation status shows that the equipment operation status is abnormal, the training process is regarded as a failure; and the training set and the test set are re-divided, and then re-imported into the neural network model for prediction according to the above steps until the two results are consistent.

[0042] The beneficial effects achieved by the above content are as follows: Through the above operations, the neural network model is optimized and trained based on the historical operating parameters of the equipment, thereby obtaining an optimized neural network model, so as to more accurately predict the failure risk of the equipment, evaluate the operating status of the equipment, and obtain a suitable maintenance method.

[0043] Step 3: Based on the prediction results of historical operation data, formulate indicator scores for equipment under different operating conditions to assess the failure risk of equipment; specifically, the following steps are included:

[0044] Obtain different prediction results of the equipment, sort them according to the risk level in the prediction results, and obtain risk indicators of different levels; define scoring standards for risk indicators of different levels according to actual scenarios to ensure that each level of risk indicators has an exclusive scoring range; specifically, by dividing the different prediction results of the equipment into levels according to the frequency of risk occurrence, such as: the main equipment of the rotating auxiliary equipment of thermal power generation is the steam turbine, which has the largest operating power and the longest operating time. Therefore, the prediction results show that the greater the risk probability during the operation of the steam turbine, the higher the risk level of the steam turbine can be regarded as the highest level; such as: the oil system is an auxiliary equipment in the rotating auxiliary equipment of thermal power generation, and its operating power is relatively low. Therefore, the prediction results show that the smaller the risk probability during the operation of the oil system, the lower the risk level of the oil system can be regarded as the lowest level, and so on, so as to formulate a risk score for the equipment according to the operating status of the equipment.

[0045] Step 4: Obtain the attributes of the rotating auxiliary equipment of thermal power generation, and prioritize different equipment according to their importance; formulate differentiated maintenance strategies based on the different fault index scores of the equipment to ensure that key equipment and equipment with high risk indicators are maintained first, and ordinary equipment and equipment with low risk indicators are maintained at appropriate times to balance maintenance costs; the specific steps include:

[0046] Obtain the tasks and locations of different equipment in the thermal power generation rotating auxiliary equipment, divide the equipment into key equipment and common equipment according to their role and impact in the thermal power generation system, and indicate the geographical location of each type of equipment; formulate a priority maintenance plan for key equipment and equipment with higher risks, carry out emergency repairs when necessary, and increase the frequency of maintenance; formulate a general maintenance plan for key equipment and equipment with higher risks, formulate reasonable maintenance time points based on the working hours of the equipment, and carry out the maintenance at the designated time points; Specifically, the thermal power generation rotating auxiliary equipment mainly includes: the steam turbine is the core equipment of the thermal power plant, which is mainly used to convert steam into power, drive the steam turbine impeller to rotate, and drive the generator to generate electricity. It can be regarded as a first-level key equipment; the reducer is used to connect the steam turbine and the generator, and its main function is to reduce the speed of the steam turbine, The function of increasing torque and transmitting power can be regarded as the second-level key equipment; the feed water pump is responsible for pumping the high-temperature and high-pressure steam-water mixture generated by the boiler to the front of the steam turbine for cooling, and can be regarded as the third-level key equipment; the condensate pump is responsible for pumping the low-temperature and low-pressure steam-water mixture discharged from the steam turbine back to the boiler for heating, and can be regarded as the first-level ordinary equipment; the deaerator is mainly responsible for removing the oxygen dissolved in the water from the feed water to prevent corrosion of the equipment and affect the power generation effect, and can be regarded as the second-level ordinary equipment; the soot blower is mainly used to remove dust accumulated on the surface of the blade to prevent the blade from overheating and damage due to dust accumulation, and can be regarded as the third-level ordinary equipment; the oil system provides lubricating oil for the steam turbine to prevent damage due to friction, and can be regarded as the fourth-level ordinary equipment; based on this, different equipment are prioritized according to their importance to facilitate the subsequent planning of the maintenance process.

[0047] For example, steam turbines and reducers are first-level key equipment and second-level key equipment. At the same time, steam turbines and reducers are high-risk equipment. The daily maintenance frequency of these two types of equipment can be set to once every 8 hours to ensure the normal operation of the two types of equipment and the normal process of the thermal power generation system. For another example, soot blowers and oil systems are third-level ordinary equipment and fourth-level ordinary equipment. At the same time, they are low-risk equipment. The maintenance frequency of these two types of equipment can be set to once a day, thereby ensuring the normal operation of the equipment, reducing the maintenance frequency, and avoiding waste of resources caused by excessive maintenance.

[0048] Step 5: Monitor the operating status of the equipment in real time, including the vibration, temperature and lubricating oil condition of the equipment during operation. Step 6: Implement equipment maintenance plans based on differentiated maintenance strategies based on the real-time monitoring results of the equipment. Specifically, this is achieved through vibration diagnosis technology, oil analysis technology, infrared equipment diagnosis technology and ultrasonic leakage monitoring technology, which are mainly used to obtain various parameters of the equipment during operation, so as to make risk predictions for the operating data of the current equipment through neural network models, thereby obtaining the current risk prediction results of the equipment, and then planning maintenance strategies in advance for equipment that may be at risk, reducing the failure rate of key equipment, and ensuring the normal operation of the thermal power generation system.

[0049] Step 7. During the maintenance process, continuously collect the equipment's operating data and update the equipment status information in a timely manner. Continuously optimize and maintain differentiated maintenance strategies based on the equipment's real-time operating data and operating status to ensure long-term stable operation of the equipment. Specifically, continuously collect the current equipment's operating parameters and status information to continuously enrich the diversity of data samples, so as to iteratively update the neural network model through different data sets, thereby ensuring the diversity of the feature set predicted by the neural network model, and further ensuring the accuracy of the neural network model in predicting the equipment's operating status.

[0050] The beneficial effects achieved by the above content: Through the above operations, the maintenance sequence and method are effectively arranged reasonably, the waste of resources caused by excessive maintenance is avoided, the maintenance cost is balanced, and the reliability and safety of the equipment are improved.

[0051] Working principle: By building a neural network model to predict the operating status of the equipment, differentiated maintenance strategies are formulated in combination with risk scores; key equipment and high-risk equipment can be inspected and maintained in a timely manner to reduce the failure rate of key equipment and ensure the normal operation of the thermal power generation system; secondly, the equipment is prioritized according to its importance to ensure that key equipment and equipment with high risk indicators are maintained first, and ordinary equipment and equipment with low risk indicators are maintained at appropriate times.

[0052] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0053] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations may be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A risk assessment-based decision-making method for condition maintenance of rotating auxiliary equipment in thermal power generation, characterized in that: The following steps are involved: Step 1: Obtain historical operation data of the equipment, and pre-process the historical operation data of the equipment as historical data samples; Preprocessing includes: cleaning historical operation data and extracting characteristic information from historical operation data; Step 2: Build a neural network model, and train and test the neural network model based on historical operation data. The successfully tested neural network model is used to predict the operating status of the equipment. Step 3: Based on the prediction results of historical operation data, formulate indicator scores for equipment under different operating conditions to assess the failure risk of equipment; Step 4: Obtain the attributes of the rotating auxiliary equipment of thermal power generation, and prioritize different equipment according to their importance; formulate differentiated maintenance strategies based on the different fault index scores of the equipment to ensure that key equipment and equipment with high risk indicators are maintained first, and ordinary equipment and equipment with low risk indicators are maintained at appropriate times to balance maintenance costs; Step 5: Monitor the running status of the equipment in real time, including the vibration, temperature and lubricating oil condition of the equipment during operation; Step 6: Based on the real-time monitoring results of the equipment, implement the equipment maintenance plan according to the differentiated maintenance strategy.

2. According to the risk assessment-based decision method for condition maintenance of thermal power generation rotating auxiliary equipment according to claim 1, it is characterized by: Also includes: Step 7. During the maintenance process, continuously collect the equipment's operating data and update the equipment status information in a timely manner, and continuously optimize and maintain differentiated maintenance strategies based on the equipment's real-time operating data and operating status.

3. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 1 is characterized in that: In the step 2, a neural network model is constructed, and the neural network model is trained and tested based on historical operation data, which specifically includes the following steps: The historical operation data is divided into a training set and a test set, and a neural network model is constructed; the training set is imported into the neural network model for training to establish the feature layer of the neural network model, and the training results are output; the test set is then imported into the neural network model for testing, and the test results are output; the test results are compared with the training results to verify whether the neural network model accurately predicts the equipment operation status.

4. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 1 is characterized in that: In step 3, according to the prediction results of historical operation data, the index scores of the equipment under different operating conditions are formulated, which specifically includes the following steps: Obtain different prediction results for the equipment, sort them by risk level, and obtain risk indicators of different levels; define scoring standards for risk indicators of different levels based on actual scenarios to ensure that each level of risk indicators has an exclusive scoring range.

5. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 1 is characterized in that: In step 4, different devices are prioritized according to their importance, which specifically includes the following steps: The tasks performed and locations of different equipment in the thermal power generation rotating auxiliary equipment are obtained. According to the role and impact of the equipment in the thermal power generation system, the equipment is divided into key equipment and common equipment, and the geographical location of each type of equipment is marked.

6. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 1 is characterized in that: In step 4, a differentiated maintenance strategy is formulated based on different fault index scores of the equipment, which specifically includes the following steps: Develop a priority maintenance plan for critical equipment and equipment with higher risks, carry out emergency repairs when necessary, and increase the frequency of maintenance; develop a general maintenance plan for critical equipment and equipment with higher risks, set reasonable maintenance time points based on the equipment's working hours, and carry out the maintenance at the designated time points.

7. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 3 is characterized by: After verifying whether the neural network model accurately predicts the equipment operating status, the following steps are included: If the test results are consistent with the output of the training results, the prediction ability of the neural network model is judged to be accurate; if the test results are inconsistent with the output of the training results, the prediction ability of the neural network model is judged to be inaccurate, and the historical operation data is sorted out and redivided into training sets and test sets, and then imported into the neural network model for training and testing until the test results are consistent with the output of the training results, and the optimized neural network model is obtained.

8. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 1 is characterized in that: In the step 1, the historical operation data of the equipment is preprocessed, which specifically includes the following steps: Obtain the distribution of historical operation data by using descriptive statistics; display the characteristics of historical operation data through charts and identify possible outliers and trends in historical operation data; delete data with missing values ​​in historical operation data, and select the mean filling method to supplement data with a small amount of missing values; use unique identifiers or combine multiple fields to determine whether there are duplications in historical operation data, and delete or merge duplicate records; perform data conversion and unified standardization on historical operation data to ensure the correctness of data type.

9. A risk assessment-based condition maintenance decision method for thermal power generation rotating auxiliary equipment according to claim 8, characterized in that: Before preprocessing the historical operation data of the equipment, the following steps are specifically included: Apply for access to the thermal power plant archive system. After obtaining access rights to the archive system, use web crawler technology to obtain multiple sets of historical operating data of the equipment in different time periods.

10. The method for decision-making on condition maintenance of rotating auxiliary equipment of thermal power generation based on risk assessment according to claim 8, characterized in that: After data conversion and unified standardization, the following steps are included: Extract effective feature information from historical operation data based on the tasks performed by the equipment, and convert the feature information into digital features suitable for learning by the neural network model; store the preprocessed historical operation data in the database to ensure that subsequent data processing and analysis can use high-quality data.

Images