Intelligent fault-tolerant control method and device for abnormal operation performance of thermal generator set

Abstract

The invention relates to an intelligent fault-tolerant control method and device for operation performance abnormity of a thermal generator set, and the method comprises the steps: obtaining the current actual operation data of a target thermal generator set; analyzing the current actual operation data to obtain a corresponding analysis result, obtaining an actual abnormal score of the target thermal generator set based on the analysis result, and generating a corresponding abnormal signal based on the analysis result under the condition that the actual abnormal score is greater than a preset safety threshold value; and obtaining a corresponding abnormal type and an abnormal degree based on the abnormal signal, and generating a corresponding fault-tolerant strategy based on the abnormal type and the abnormal degree, so as to adjust the operation state of the target thermal generator set by using the fault-tolerant strategy. Therefore, the technical problems that in the related technology, an intelligent fault-tolerant system has large limitation and lacks adaptability for complex working conditions of the thermal power generating unit, so that the fault-tolerant capability of the thermal power generating unit is poor, and the operation efficiency of the thermal power generating unit is difficult to guarantee are solved.

Description

Technical Field

[0001] The present application relates to the field of thermal power generation technology, and in particular to an intelligent fault-tolerant control method and device for abnormal operating performance of a thermal power generating set. Background Art

[0002] As an important part of the power system, the operating performance of thermal power generating units directly affects the stability and efficiency of the entire power system. However, during the long-term operation of the units, various types of equipment will wear, age or fail due to complex working conditions such as high temperature and high pressure. These problems often lead to reduced operating performance of the units or even abnormal shutdowns. Traditional abnormal monitoring and fault handling systems are mostly based on preset rules and thresholds, relying on the operator's experience for judgment and processing. It is difficult to respond to complex and sudden abnormal conditions in a timely manner, and it is difficult to ensure the safe operation of the system under fault conditions.

[0003] In recent years, with the rapid development of artificial intelligence technology, the application of intelligent fault-tolerant control in power systems has gradually increased. In related technologies, intelligent fault-tolerant control systems can monitor the operating data of the unit in real time, identify anomalies using machine learning, data analysis and other technologies, and even make autonomous decisions when anomalies occur to ensure the continuous and stable operation of the system. However, the intelligent fault-tolerant system in related technologies still has certain limitations, such as insufficient algorithm accuracy and response speed, and lack of adaptability to complex operating conditions of thermal power generating units, making it difficult to comprehensively improve the fault-tolerant capability of thermal power generating units, which needs to be improved. Summary of the invention

[0004] The present application provides an intelligent fault-tolerant control method and device for abnormal operating performance of a thermal power generating set, in order to solve the technical problem in the related technology that the intelligent fault-tolerant system has great limitations and lacks adaptability to the complex operating conditions of the thermal power generating set, resulting in poor fault tolerance of the thermal power generating set and difficulty in ensuring the operating efficiency of the thermal power generating set.

[0005] The first aspect of the present application provides an intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set, comprising the following steps: acquiring current actual operating data of a target thermal power generator set; analyzing the current actual operating data to obtain a corresponding analysis result, and obtaining an actual abnormality score of the target thermal power generator set based on the analysis result, so as to generate a corresponding abnormal signal based on the analysis result when the actual abnormality score is greater than a preset safety threshold; obtaining a corresponding abnormality type and abnormality degree based on the abnormal signal, and generating a corresponding fault-tolerant strategy based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generator set using the fault-tolerant strategy.

[0006] Optionally, in one embodiment of the present application, obtaining the current actual operating data of the target thermal power generator set includes: determining whether the sensor data of multiple preset key parts of the target thermal power generator set meet preset acquisition conditions; when the sensor data of each preset key part meets the preset acquisition conditions, obtaining the current operating status of the target thermal power generator set, and determining a sampling frequency based on the current operating status to collect the current operating data of the target thermal power generator set based on the sampling frequency; and performing data processing on the current operating data to obtain the current actual operating data.

[0007] Optionally, in one embodiment of the present application, the current actual operating data is analyzed to obtain a corresponding analysis result, and an actual abnormality score of the target thermal power generator group is obtained based on the analysis result, so that when the actual abnormality score is greater than a preset safety threshold, a corresponding abnormal signal is generated based on the analysis result, including: normalizing the current actual operating data to obtain actual data; combining a long short-term memory network, historical sequence data of the target thermal power generator group and the actual data to obtain a first abnormality score of the target thermal power generator group; extracting local feature data that meets a preset change trend from the actual data based on the historical sequence data, and generating a second abnormality score of the target thermal power generator group based on the local feature data; integrating the first abnormality score and the second abnormality score to obtain the actual abnormality score.

[0008] Optionally, in one embodiment of the present application, it further includes: storing the current actual operation data and the corresponding data collection time, so as to update the historical sequence data using the current actual operation data and the corresponding data collection time.

[0009] Optionally, in one embodiment of the present application, the corresponding abnormality type and abnormality degree are obtained based on the abnormal signal, and a corresponding fault-tolerant strategy is generated based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generator set using the fault-tolerant strategy, including: obtaining a corresponding abnormality grade based on the abnormality type and abnormality degree, and determining the fault-tolerant control strategy based on the abnormality grade; determining key operating parameters of the target thermal power generator set based on the fault-tolerant control strategy, and controlling the target thermal power generator set using the key operating parameters; determining operating parameters of the cooling system of the target thermal power generator set based on the fault-tolerant control strategy, and controlling the cooling system using the operating parameters of the cooling system; determining the load reduction operating parameters of the target thermal power generator set based on the fault-tolerant control strategy, and controlling the target thermal power generator set based on the load reduction operating parameters; controlling the target thermal power generator set to enter an emergency shutdown state based on the fault-tolerant control strategy.

[0010] Optionally, in one embodiment of the present application, it also includes: after the fault-tolerant control strategy is executed for a preset time, a new abnormality score is calculated based on new operating data of the target thermal power generator set, and the fault-tolerant control strategy is optimized using the new abnormality score.

[0011] The second aspect of the present application provides an intelligent fault-tolerant control device for abnormal operating performance of a thermal power generator set, including: an acquisition module, used to acquire current actual operating data of a target thermal power generator set; a scoring module, used to analyze the current actual operating data to obtain a corresponding analysis result, and obtain an actual abnormal score of the target thermal power generator set based on the analysis result, so as to generate a corresponding abnormal signal based on the analysis result when the actual abnormal score is greater than a preset safety threshold; a control module, used to obtain a corresponding abnormal type and abnormal degree based on the abnormal signal, and generate a corresponding fault-tolerant strategy based on the abnormal type and abnormal degree, so as to adjust the operating state of the target thermal power generator set using the fault-tolerant strategy.

[0012] Optionally, in one embodiment of the present application, the acquisition module includes: a judgment unit, used to judge whether the sensor data of multiple preset key parts of the target thermal power generator group meet the preset acquisition conditions; an acquisition unit, used to acquire the current operating status of the target thermal power generator group when the sensor data of each preset key part meets the preset acquisition conditions, and determine the sampling frequency based on the current operating status to collect the current operating data of the target thermal power generator group based on the sampling frequency; a first processing unit, used to perform data processing on the current operating data to obtain the current actual operating data.

[0013] Optionally, in one embodiment of the present application, the scoring module includes: a second processing unit, used to normalize the current actual operation data to obtain actual data; a first scoring unit, used to combine the long short-term memory network, the historical sequence data of the target thermal power generator group and the actual data to obtain a first anomaly score of the target thermal power generator group; a second scoring unit, used to extract local feature data that meets a preset change trend from the actual data based on the historical sequence data, and generate a second anomaly score of the target thermal power generator group based on the local feature data; a fusion unit, used to integrate the first anomaly score and the second anomaly score to obtain the actual anomaly score.

[0014] Optionally, in one embodiment of the present application, it further includes: a storage module, used to store the current actual operation data and the corresponding data collection time, so as to update the historical sequence data using the current actual operation data and the corresponding data collection time.

[0015] Optionally, in one embodiment of the present application, the control module includes: a determination unit, used to obtain a corresponding abnormality grade based on the abnormality type and the degree of abnormality, and determine the fault-tolerant control strategy based on the abnormality grade; a first control unit, used to determine the key operating parameters of the target thermal power generator set based on the fault-tolerant control strategy, and use the key operating parameters to control the target thermal power generator set; a second control unit, used to determine the operating parameters of the cooling system of the target thermal power generator set based on the fault-tolerant control strategy, so as to control the cooling system using the operating parameters of the cooling system; a third control unit, used to determine the load reduction operating parameters of the target thermal power generator set based on the fault-tolerant control strategy, and control the target thermal power generator set based on the load reduction operating parameters; a fourth control unit, used to control the target thermal power generator set to enter an emergency shutdown state based on the fault-tolerant control strategy.

[0016] Optionally, in one embodiment of the present application, it also includes: an optimization module, which is used to calculate a new anomaly score based on the new operating data of the target thermal power generator group after the fault-tolerant control strategy is executed for a preset period of time, and use the new anomaly score to optimize the fault-tolerant control strategy.

[0017] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set as described in the above embodiment.

[0018] The fourth aspect of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set as described in the above embodiment.

[0019] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set.

[0020] The embodiment of the present application can analyze the current actual operation data of the target thermal power generating unit, and obtain the actual abnormality score of the target thermal power generating unit based on the analysis result, so that when the actual abnormality score is greater than the preset safety threshold, the corresponding abnormality type and abnormality degree are determined based on the analysis result, and then the corresponding fault-tolerant strategy is generated to adjust the operation state of the target thermal power generating unit by using the fault-tolerant strategy, that is, by applying intelligent algorithms and adaptive fault-tolerant mechanisms, the operation state of the thermal power generating unit is monitored, analyzed and abnormalities are handled in real time, so as to ensure the stable and safe operation of the unit under various working conditions and minimize the impact of abnormalities on the performance of the unit. Thus, the technical problem that the intelligent fault-tolerant system has great limitations in the related technology and lacks adaptability to the complex working conditions of the thermal power generating unit, which makes the fault-tolerant ability of the thermal power generating unit poor and it is difficult to ensure the operation efficiency of the thermal power generating unit is solved.

[0021] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0023] Figure 1 A flowchart of an intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating set provided according to an embodiment of the present application;

[0024] Figure 2 It is a schematic diagram of the principle of an intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating set according to an embodiment of the present application;

[0025] Figure 3 It is a schematic diagram of the principle of an intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating set according to another embodiment of the present application;

[0026] Figure 4 A schematic diagram of a data collection process according to an embodiment of the present application;

[0027] Figure 5 A schematic diagram of an abnormality detection process according to an embodiment of the present application;

[0028] Figure 6 A schematic diagram of a fault-tolerant control process according to an embodiment of the present application;

[0029] Figure 7 Schematic diagram of the principle of an intelligent fault-tolerant control method for abnormal operation performance of a thermal power generating set according to another embodiment of the present application

[0030] Figure 8It is a structural schematic diagram of an intelligent fault-tolerant control device for abnormal operating performance of a thermal power generating set provided according to an embodiment of the present application;

[0031] Fig. 9 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0033] The following describes the intelligent fault-tolerant control method and device for abnormal operation performance of a thermal power generator set according to an embodiment of the present application with reference to the accompanying drawings. In view of the technical problem that the intelligent fault-tolerant system has great limitations in the related technologies mentioned in the above background technology, and lacks adaptability to the complex working conditions of the thermal power generator set, so that the fault-tolerant ability of the thermal power generator set is poor, and it is difficult to ensure the operation efficiency of the thermal power generator set, the present application provides an intelligent fault-tolerant control method for abnormal operation performance of a thermal power generator set, in which the current actual operation data of the target thermal power generator set can be analyzed, and the actual abnormality score of the target thermal power generator set can be obtained based on the analysis result, so that when the actual abnormality score is greater than the preset safety threshold, the corresponding abnormality type and abnormality degree are determined based on the analysis result, and then the corresponding fault-tolerant strategy is generated, so as to adjust the operation state of the target thermal power generator set by using the fault-tolerant strategy, that is, by applying the intelligent algorithm and the adaptive fault-tolerant mechanism, the operation state of the thermal power generator set is monitored, analyzed and abnormality is handled in real time, so as to ensure the stable and safe operation of the unit under various working conditions, and minimize the impact of the abnormality on the performance of the unit. Thereby, the technical problem in the related technology that the intelligent fault-tolerant system has great limitations and lacks adaptability to the complex working conditions of thermal power generating units, resulting in poor fault tolerance of thermal power generating units and difficulty in ensuring the operating efficiency of thermal power generating units is solved.

[0034] Specifically, Figure 1 A flow chart of an intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating set provided in an embodiment of the present application.

[0035] like Figure 1 As shown, the intelligent fault-tolerant control method for abnormal operation performance of the thermal power generating set includes the following steps:

[0036] In step S101, the current actual operation data of the target thermal power generating unit is obtained.

[0037] During the actual execution process, the embodiment of the present application can collect the current actual operating data of the thermal power generating set, such as key operating parameters in real time. These parameters may include temperature, pressure, speed, current, voltage, flow, etc.

[0038] The operating environment of thermal power generating units is complex, and the system is high temperature and high pressure, which places high demands on the accuracy, sampling frequency and anti-interference of sensors. To this end, the embodiment of the present application can adopt a dynamic sampling method based on fuzzy filtering. This method can reduce the sampling frequency during stable operation to reduce the amount of data; when the system detects parameter fluctuations, it will automatically increase the sampling frequency to ensure that key data changes are captured.

[0039] The embodiment of the present application can also realize multi-point data synchronous collection through a distributed sensor network. Each sensor node is equipped with a high-precision anti-interference sensor and a low-power data processing chip, which can perform local filtering and pre-processing on the collected data to remove environmental noise and occasional fluctuations.

[0040] Furthermore, the embodiment of the present application can also process the data after the parameters are collected to filter out abnormal values ​​and remove noise, distinguish normal fluctuations from abnormal fluctuations of the unit, and make subsequent abnormality detection more accurate.

[0041] Optionally, in one embodiment of the present application, obtaining the current actual operating data of the target thermal power generator set includes: determining whether the sensor data of multiple preset key parts of the target thermal power generator set meet preset acquisition conditions; when the sensor data of each preset key part meets the preset acquisition conditions, obtaining the current operating status of the target thermal power generator set, and determining the sampling frequency based on the current operating status to collect the current operating data of the target thermal power generator set based on the sampling frequency; and performing data processing on the current operating data to obtain the current actual operating data.

[0042] As a possible implementation method, the embodiment of the present application can first confirm whether the sensor data of multiple key parts of the target thermal power generator unit meets the requirements, that is, whether the sensors of multiple key parts are reasonably arranged and whether they are initialized after arrangement. For example, the embodiment of the present application can arrange high-precision sensors at the key parts of the unit, including temperature sensors, pressure sensors, flow sensors, current and voltage sensors, etc. Each sensor is initialized after installation to calibrate the acquisition accuracy to ensure that environmental parameters can be accurately recorded. The initialization process includes signal zeroing, calibration range setting and noise suppression setting to adapt to high temperature and high pressure industrial environments.

[0043] Furthermore, the embodiments of the present application can adjust the data collection frequency according to the different operating conditions of the unit after ensuring the data collection of key parts. Specifically, when the unit is running stably, the embodiments of the present application can adopt a lower sampling frequency to reduce the amount of data; when the data fluctuation is monitored to exceed the preset threshold, the embodiments of the present application can automatically switch to the high-frequency sampling mode. This process is controlled by a dynamic sampling frequency adjustment algorithm, which determines whether the sampling frequency needs to be changed by real-time analysis of data fluctuations to ensure that important abnormal changes can be captured in a timely manner. The preset threshold can be set by technicians in this field according to actual conditions, and no specific restrictions are made here;

[0044] Furthermore, the embodiments of the present application can pre-process the collected data to remove noise and outliers, using Kalman filtering and wavelet denoising algorithms. Kalman filtering is used to smooth data and reduce the impact of environmental noise, while wavelet denoising is used to detect and suppress occasional abnormal signals. The goal of data pre-processing is to ensure the authenticity and stability of sensor data and provide clean data input for subsequent anomaly detection;

[0045] Furthermore, the embodiments of the present application can perform distributed data processing on the pre-processed data. Preliminary data processing, including denoising, data integration and preliminary judgment, is performed on each sensor node to reduce the load on the central processing unit. Distributed data processing is implemented through low-power chips, so that sensors can directly perform simple data analysis and initial screening of abnormalities, thereby screening out obviously abnormal data points at an early stage and improving detection efficiency.

[0046] Optionally, in one embodiment of the present application, it also includes: storing current actual operation data and corresponding data collection time, so as to update historical sequence data using the current actual operation data and corresponding data collection time.

[0047] The embodiment of the present application can also store the aggregated data and archive it in time series for subsequent analysis. When storing, a multi-layer index structure can be used. The embodiment of the present application can also classify each data and add event tags, so that subsequent data calls can be quickly retrieved according to time, data type or event tags. When storing, the embodiment of the present application can also support hierarchical storage of real-time and offline data, and can prioritize real-time data according to importance to ensure that key data is available at any time.

[0048] In step S102, the current actual operation data is analyzed to obtain corresponding analysis results, and the actual abnormality score of the target thermal power generating unit is obtained based on the analysis results, so that when the actual abnormality score is greater than a preset safety threshold, a corresponding abnormal signal is generated based on the analysis results.

[0049] As a possible implementation method, the embodiment of the present application can perform intelligent analysis on the real-time operating data of the thermal power generating unit, identify potential abnormal conditions, and provide early warning so that the fault-tolerant control module can respond in time and take appropriate countermeasures.

[0050] It is understandable that the operating data of a thermal power generating set often contains multiple parameters, and has the characteristics of nonlinearity, multi-dimensionality and time series. Therefore, the embodiment of the present application needs to have the ability to respond quickly to complex operating conditions.

[0051] The embodiments of the present application can compare a large amount of historical data and real-time data through intelligent algorithms to ensure accurate detection in different abnormal situations, thereby ensuring the stable operation of thermal power generating units, solving the shortcomings of existing anomaly detection methods in terms of data complexity, response speed and detection accuracy, and providing comprehensive and real-time anomaly detection support for the system.

[0052] The embodiment of the present application can also use a time series analysis method based on a long short-term memory network to process complex time series data, have the ability to remember long time series information, and can identify the operating mode of the system under normal working conditions. In actual operation, the embodiment of the present application can generate an abnormal score and issue an early warning once a trend that deviates from the normal mode is detected by analyzing and comparing the current operating data with the historical sequence data in real time.

[0053] In order to more effectively detect short-term mutations and local anomalies in data, the embodiments of the present application can also introduce a convolutional neural network to extract local features, analyze local changes in multi-dimensional data, and have higher sensitivity and accuracy in detecting sudden anomalies such as instantaneous fluctuations in key parameters, such as pressure or temperature.

[0054] By combining the long short-term memory network with the convolutional neural network, and then automatically calling the local feature analysis after detecting the progressive anomaly through the fusion algorithm to comprehensively judge the nature and severity of the anomaly, the embodiment of the present application can effectively avoid false positives or false negatives. To ensure the stability of the system under complex working conditions, the embodiment of the present application can also integrate the Bayesian optimization method to achieve adaptive tuning of hyperparameters, and further improve the response speed and accuracy by dynamically adjusting key parameters.

[0055] Optionally, in one embodiment of the present application, the current actual operating data is analyzed to obtain corresponding analysis results, and the actual abnormality score of the target thermal power generator group is obtained based on the analysis results, so that when the actual abnormality score is greater than a preset safety threshold, a corresponding abnormal signal is generated based on the analysis result, including: normalizing the current actual operating data to obtain actual data; combining the long short-term memory network, the historical sequence data of the target thermal power generator group and the actual data to obtain a first abnormality score of the target thermal power generator group; extracting local feature data that meets a preset change trend from the actual data based on the historical sequence data, and generating a second abnormality score of the target thermal power generator group based on the local feature data; integrating the first abnormality score and the second abnormality score to obtain the actual abnormality score.

[0056] Specifically, the embodiment of the present application can preprocess and normalize the received current actual operation data to ensure the accuracy and consistency of the input data.

[0057] For example, the embodiment of the present application can use the minimum-maximum scaling method to normalize different types of sensor data, convert it to the [0,1] interval, eliminate the dimensional differences of different parameters such as temperature, pressure, and current, so that subsequent model analysis can be more efficient and accurate. In addition, the embodiment of the present application can also filter out outliers and noise through a denoising algorithm, such as using a sliding average method or a Kalman filter method to suppress environmental noise. For discontinuous discrete data, interpolation processing can also be performed to generate a continuous data stream to ensure the integrity of the input data. The preprocessed data provides high-quality input for subsequent anomaly detection;

[0058] After completing the data preprocessing, the embodiment of the present application can input the normalized actual data into the long short-term memory network model. The long short-term memory network learns the multi-parameter operation mode of the thermal power generator under normal conditions by analyzing the historical sequence of data. In specific operations, the long short-term memory network will compare the parameter data at the current moment with the historical data within a certain time window, that is, the historical sequence data, and use its unique memory structure to automatically retain important information and filter out irrelevant details. When certain parameters such as temperature or pressure continue to deviate from the normal range, the embodiment of the present application can generate an abnormality score based on the degree of deviation and compare it with the preset alarm threshold. Once the score exceeds the threshold, the long short-term memory network will be judged as a potential progressive abnormality and trigger a warning signal, thereby providing an early warning for possible hidden dangers, wherein the alarm threshold can be set accordingly by technical personnel in this field according to the actual situation, and no specific limitation is made here;

[0059] Furthermore, for sudden anomalies in real-time data, the embodiments of the present application can perform local feature extraction through a convolutional neural network. The convolutional neural network first uses a convolution operation to extract local change patterns from multi-dimensional parameter data and identify drastic fluctuations in a short period of time. The convolution operation will slide through the data in sequence to generate local feature maps, and downsample in the pooling layer to reduce the amount of data and highlight key features. For example, in the event of a sudden increase in temperature or pressure, the convolutional neural network can immediately identify such drastic changes and mark them as abnormal signals. For multi-parameter high-dimensional data, the convolutional neural network will combine the local features of different parameters and generate anomaly scores. This process ensures that the module can respond quickly to emergencies in a short period of time and effectively capture harmful changes;

[0060] The embodiments of the present application can integrate the results of the long short-term memory network and the convolutional neural network through a fusion algorithm to improve the accuracy of detection. First, the long short-term memory network and the convolutional neural network each independently analyze the real-time data. After detecting a progressive anomaly, the long short-term memory network will automatically trigger the convolutional neural network to perform a more refined local feature detection on the data segment to determine whether the anomaly is a short-term fluctuation. This fusion process is controlled by specific algorithm rules, and different weights are assigned to different detection results to obtain a more comprehensive judgment result. At the same time, the output results of the two algorithms are combined in an anomaly score for subsequent judgment and processing. This fusion strategy makes anomaly detection more flexible, which can not only capture progressive anomalies, but also keenly identify short-term mutations, ensuring the comprehensiveness and accuracy of detection;

[0061] In order to adapt to the changes in different operating conditions of thermal power generating units, the embodiment of the present application can also integrate the Bayesian optimization method to improve the accuracy and adaptability of the model by dynamically adjusting the key hyperparameters of the long short-term memory network and the convolutional neural network. Bayesian optimization continuously updates the optimal hyperparameter configuration by analyzing historical data and feedback from detection results, and automatically adjusts key parameters such as the learning rate, convolution kernel size, and time window length. For example, when an increase in false alarms or missed alarms is detected, the Bayesian optimization algorithm can be triggered to re-evaluate and optimize related parameters to ensure the best state during operation. The optimized parameters are dynamically applied to the model to enhance the detection stability and accuracy of the system, so that the embodiment of the present application has a stronger ability to adapt to working conditions;

[0062] After the aforementioned processing steps, the embodiment of the present application will generate a comprehensive anomaly score for quantifying the current operating status of the thermal power generator set. The score superimposes the comprehensive judgment results of the long short-term memory network and the convolutional neural network to ensure that the score can fully reflect the abnormal conditions of the system. When the anomaly score exceeds the preset safety threshold, the module will immediately trigger an alarm and generate an alarm signal containing abnormal information, that is, an abnormal signal. At this time, in addition to triggering subsequent fault-tolerant control, the abnormal signal can also be stored. Not only can the score details be stored, but also the abnormal characteristics and data of key parameters can be synchronously recorded to facilitate subsequent fault analysis and improvement.

[0063] In step S103, the corresponding abnormality type and abnormality degree are obtained based on the abnormal signal, and the corresponding fault-tolerant strategy is generated based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generating set by using the fault-tolerant strategy.

[0064] In the actual implementation process, the embodiment of the present application can quickly take measures to perform fault-tolerant operations when an abnormality is found during the operation of the target thermal power generator set, so as to avoid or reduce the impact of the abnormal state on the overall operation of the generator set. By responding to abnormal signals in real time, according to the specific abnormal type and severity, the appropriate control strategy is automatically selected and executed, thereby achieving effective management of the unit's operating status. Through automatic adjustment, real-time intervention and feedback control, the losses caused by abnormalities can be effectively reduced.

[0065] The embodiments of the present application can adopt a combination of multiple control strategies to ensure that the best response measures can be taken in abnormal situations of different types and severity. To deal with progressive anomalies, the embodiments of the present application can adjust the operating parameters in real time through adaptive proportional-integral-differential control to ensure that stability can be maintained when slight deviations occur. For sudden or severe anomalies, the embodiments of the present application can use fuzzy logic control and expert systems to determine emergency control measures through fast decision-making algorithms. At the same time, the embodiments of the present application can also evaluate the effectiveness of fault-tolerant measures through feedback loops and state monitoring, and make strategy adjustments when necessary. In addition, the embodiments of the present application can also perform data logging and store the executed fault-tolerant strategies for subsequent analysis and optimization.

[0066] Optionally, in one embodiment of the present application, a corresponding abnormality type and abnormality degree are obtained based on the abnormal signal, and a corresponding fault-tolerant strategy is generated based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generator set using the fault-tolerant strategy, including: obtaining a corresponding abnormality grade based on the abnormality type and abnormality degree, and determining a fault-tolerant control strategy based on the abnormality grade; determining key operating parameters of the target thermal power generator set based on the fault-tolerant control strategy, and controlling the target thermal power generator set using the key operating parameters; determining operating parameters of a cooling system of the target thermal power generator set based on the fault-tolerant control strategy, and controlling the cooling system using the operating parameters of the cooling system; determining load reduction operating parameters of the target thermal power generator set based on the fault-tolerant control strategy, and controlling the target thermal power generator set based on the load reduction operating parameters; and controlling the target thermal power generator set to enter an emergency shutdown state based on the fault-tolerant control strategy.

[0067] In some embodiments, the abnormality level can be divided according to the abnormality score in the abnormal signal, such as three abnormality levels of general, severe and urgent, and then the corresponding fault-tolerant control strategy is adjusted according to the abnormality level.

[0068] In other embodiments, the current abnormal state may be comprehensively judged based on the abnormality type and the abnormality degree, and the abnormality level may be classified to determine the corresponding fault-tolerant control strategy.

[0069] For example, after receiving an abnormal signal, the embodiment of the present application can identify and parse the signal content. By analyzing the abnormality score, abnormality type (progressive or sudden), severity and other information, the current abnormal state is comprehensively judged. The identification process is performed by a built-in decision engine to ensure accurate and rapid classification and identification of different types of abnormal signals. After completing the signal identification, the embodiment of the present application can select appropriate preliminary response measures based on the pre-defined mapping table of abnormality types and response strategies;

[0070] When a progressive or minor abnormality is detected, the embodiment of the present application may call an adaptive proportional-integral-differential control strategy. Adaptive proportional-integral-differential control can adjust the operating parameters of the unit, such as temperature, pressure, etc., in real time according to the abnormal deviation, and gradually restore the deviated parameters to the normal range. Adaptive proportional-integral-differential control automatically adjusts the control gain according to the change of abnormal deviation to ensure the appropriateness of the control action. For example, when the temperature gradually rises but does not exceed the dangerous threshold, the adaptive proportional-integral-differential control will slowly reduce the heat output to ensure the stable operation of the system;

[0071] For some complex abnormal situations, the embodiments of the present application can apply fuzzy logic control strategies according to the abnormal characteristics to cope with multi-variable and nonlinear control requirements. Fuzzy logic control can quickly determine the direction and degree of adjustment under abnormal conditions and adjust the multi-dimensional parameters of the unit to a safe range. The specific process is to first input the abnormal parameters into the fuzzy control system, and determine the appropriate control intensity and response method through fuzzy rule reasoning. For example, when the pressure and temperature are both high and the rate of change is fast, the fuzzy logic control will combine the deviations of the two and perform appropriate load reduction or power reduction operations, thereby avoiding the risks brought by sudden abnormalities;

[0072] When the abnormal situation reaches an emergency level, the embodiment of the present application can activate the expert system and directly call the emergency strategy to respond. The emergency strategy of the expert system is based on pre-defined control rules and empirical data, and can take effect quickly in abnormal conditions. The expert system matches the control measures of similar historical situations according to the current unit parameters and environmental conditions, and performs emergency control as soon as possible. For example, if a sudden increase in pressure and an abnormal increase in temperature are detected, the expert system will immediately implement load reduction or shutdown measures to ensure the safety of the system. The calling process of this emergency strategy is highly automated, ensuring that the fault-tolerant control module can implement an effective response in a very short time;

[0073] Optionally, in one embodiment of the present application, it also includes: after the fault-tolerant control strategy is executed for a preset time, a new anomaly score is calculated based on new operating data of the target thermal power generating unit, and the new anomaly score is used to optimize the fault-tolerant control strategy.

[0074] After executing the fault-tolerant control measures, the embodiment of the present application can continuously monitor the state of the unit and feedback and evaluate the fault-tolerant effect. By collecting the adjusted operating parameters in real time, the embodiment of the present application can analyze the change trend and response time of each parameter to determine the effectiveness of the current fault-tolerant control strategy. If it is monitored that the adjustment effect is not ideal or a new abnormality occurs, the embodiment of the present application can automatically adjust the fault-tolerant control strategy or switch to other strategies according to the latest parameter status. This process forms a dynamic feedback closed-loop control to ensure that the fault-tolerant measures can be continuously optimized according to the actual situation to achieve optimal stability.

[0075] Combination Figures 2 to 7 As shown, the working principle of the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating set according to an embodiment of the present application is described in detail by taking an embodiment as an example.

[0076] like Figure 2 and Figure 3As shown, it is a schematic diagram of the principles of an embodiment of the present application. The embodiment of the present application can collect the current operating data through the data acquisition module, analyze the current operating data and detect anomalies through the anomaly detection module, determine the corresponding fault-tolerant control strategy through the fault-tolerant control module, and rely on intelligent algorithms to realize data processing and function calls, and realize the same storage and call of data through the data storage unit for feedback adjustment. The modules realize information interaction and feedback through data flow to form a closed-loop control mechanism.

[0077] The embodiments of the present application can achieve efficient real-time monitoring, timely identification and response to abnormal situations, thereby improving the safety and reliability of operation; and relying on deep learning and machine learning technology, it has intelligent decision support, automatically identifies complex abnormal patterns and reduces the need for manual intervention, significantly improving decision efficiency; combined with adaptive proportional-integral-differential control, fuzzy logic control and expert systems, it provides multi-level fault-tolerant control strategies for different types of abnormal situations, ensuring that abnormalities can be quickly and effectively responded to in various operating environments. The adaptive learning ability of the intelligent algorithm enables the system to continuously optimize detection and control strategies based on historical data and real-time feedback, maintaining long-term stability and efficiency.

[0078] At the same time, the embodiment of the present application can also record detailed data of each abnormality handling process, provide rich reference data for subsequent performance evaluation and optimization, and assist in fault analysis and decision-making. Ultimately, by timely detecting and handling abnormalities, the failure risk and maintenance cost of the thermal power generating unit are effectively reduced, and the overall operating efficiency is improved.

[0079] Specifically, the data acquisition module can be used to obtain various operating data from the thermal power generating set in real time, including parameters such as temperature, pressure, speed, flow, etc., and transmit the data to the abnormality detection module through sensors and data transmission equipment.

[0080] The anomaly detection module receives the data transmitted by the data acquisition module, preprocesses the data, extracts features, and calculates the anomaly score and classification results through a specific algorithm model to identify potential abnormal conditions, and generates an alarm signal when necessary, which is fed back to the fault-tolerant control module.

[0081] The fault-tolerant control module receives the abnormal signal from the abnormality detection module, selects the appropriate fault-tolerant strategy according to the type and severity of the abnormality, and executes a variety of control measures, including adjusting operating parameters and emergency shutdown operations, to ensure the stability and safety of the system.

[0082] Intelligent algorithm support is responsible for the system's self-learning and model optimization, receiving data feedback from each module, and optimizing the anomaly detection and fault-tolerant control models through adaptive learning and deep learning algorithms to improve the system's adaptability and control accuracy.

[0083] The data storage unit is used to record and store various types of data during system operation, including real-time data, anomaly detection results, control strategies and feedback information, to provide support for data analysis and model optimization, and to realize data traceability and archiving functions.

[0084] The embodiments of the present application may include the following steps:

[0085] Step S1: Data acquisition: The data acquisition module obtains the current operating data from the target thermal power generating unit, including parameters such as temperature, pressure, flow, etc., and after preprocessing and summarizing, transmits the obtained current actual operating data to the abnormality detection module.

[0086] Specifically, Figure 4 As shown, the workflow of the data acquisition module includes the following steps:

[0087] Step S401: Sensor placement and initialization: Sensors are placed at key locations of the target thermal power generating unit and initialized to ensure the accuracy and stability of data collection.

[0088] Step S402: Data sampling and frequency control. By controlling the sampling frequency, the data of each sensor is collected at a set frequency to ensure the real-time and reliability of data collection.

[0089] Step S403: Data preprocessing and filtering: The collected data is preprocessed and filtered to remove noise and outliers to ensure the cleanliness and validity of the data.

[0090] Step S404: Distributed data processing: Distributed data processing technology is used to distribute the pre-processed data to different processing units for preliminary analysis to improve data processing efficiency.

[0091] Step S405: Data aggregation and transmission: The distributed processed data is aggregated and transmitted to the anomaly detection module to provide support for subsequent anomaly detection and control decisions.

[0092] Step S406: Data storage and management. The collected and processed data is stored in a data storage unit, classified and managed for subsequent analysis and system optimization.

[0093] Step S2: Anomaly detection and scoring. The anomaly detection module normalizes the received current actual operation data, analyzes the data through the long short-term memory network and convolutional neural network, and generates anomaly scores. If the score exceeds the safety threshold, an abnormal signal is triggered and transmitted to the fault-tolerant control module.

[0094] Specifically, Figure 5As shown, the workflow of the anomaly monitoring module includes the following steps:

[0095] Step S501: Data preprocessing and normalization. The anomaly detection module first preprocesses the received current actual operation data, using normalization and denoising algorithms to ensure the accuracy and consistency of the input data and provide high-quality data for subsequent analysis.

[0096] Step S502: Long short-term memory network analysis. The pre-processed data is input into the long short-term memory network to analyze the historical sequence of the data, learn the normal operation mode of the thermal power generating unit, generate anomaly scores, and perform early warning.

[0097] Step S503: Convolutional neural network local feature extraction. For sudden anomalies in real-time data, a convolutional neural network is used to extract local features, identify drastic fluctuations in a short period of time, and ensure a rapid response to emergencies.

[0098] Step S504: Application of fusion algorithm: The detection results of the long short-term memory network and the convolutional neural network are integrated through the fusion algorithm to form a comprehensive anomaly score to improve the accuracy and comprehensiveness of the detection.

[0099] Step S505: Bayesian optimization hyperparameter tuning. The Bayesian optimization method is used to dynamically adjust the model hyperparameters to adapt to changes in different working conditions and improve the accuracy and stability of system detection.

[0100] Step S506: Abnormal score and alarm. Generate a comprehensive abnormal score and compare it with the threshold. When the score exceeds the threshold, an alarm is triggered, an abnormal signal is sent to the fault-tolerant control module, and different levels of warning are issued according to the score.

[0101] Step S3: Fault-tolerant control and emergency response. The fault-tolerant control module executes appropriate fault-tolerant strategies according to the type and degree of abnormality, such as adjusting operating parameters or initiating emergency shutdown, to ensure system safety.

[0102] like Figure 6 As shown, the workflow of the fault-tolerant control module includes the following steps:

[0103] Step S601: Abnormal signal reception and identification. After receiving the abnormal signal, the signal content is identified and analyzed. By analyzing the abnormal score, abnormal type (gradual or sudden), severity and other information, the current abnormal state is comprehensively judged.

[0104] Step S602: Adaptive proportional-integral-derivative control strategy. When a progressive or slight abnormality is detected, the adaptive proportional-integral-derivative control strategy is called. The adaptive proportional-integral-derivative control automatically adjusts the control gain according to the change of the abnormal deviation to ensure the appropriateness of the control action. For example, when the temperature gradually increases but does not exceed the dangerous threshold, the adaptive proportional-integral-derivative control will slowly reduce the heat output to ensure the stable operation of the system.

[0105] Step S603: Application of fuzzy logic control strategy. For some complex abnormal situations, fuzzy logic control strategy is applied according to the abnormal characteristics to cope with multivariable and nonlinear control requirements. For example, when the pressure and temperature are both high and the rate of change is fast, fuzzy logic control will integrate the deviations of the two and perform appropriate load reduction or power reduction operations to avoid the risks brought by sudden abnormalities.

[0106] Step S604: Calling the expert system emergency strategy. When the abnormal situation reaches the emergency level, the fault-tolerant control module will activate the expert system and directly call the emergency strategy to respond. For example, when a sudden increase in pressure and abnormal increase in temperature are detected, the expert system will immediately implement load reduction or shutdown measures to ensure the safety of the system. The calling process of the emergency strategy is highly automated, ensuring that the fault-tolerant control module can implement an effective response in a very short time.

[0107] Step S605: Feedback monitoring and strategy adjustment. After executing the fault-tolerant control measures, the fault-tolerant control module will continuously monitor the unit status and provide feedback to evaluate the fault-tolerant effect. This process forms a dynamic feedback closed-loop control to ensure that the fault-tolerant measures can be continuously optimized according to the actual situation to achieve the best stability.

[0108] Step S4: Model optimization and data storage. Intelligent algorithms can dynamically optimize the detection and control models to enhance the adaptability of the system. The data storage unit records the operation data and control records of the entire process to provide data support for subsequent analysis and optimization.

[0109] like Figure 7 As shown, the usage process of the embodiment of the present application is explained in combination with specific cases.

[0110] In the case of abnormal temperature, the embodiment of the present application can collect abnormal data through the data acquisition module, and after analysis and judgment in the abnormal detection module, generate an abnormal signal and transmit it to the fault-tolerant control module. The fault-tolerant control module selects control strategies and executes measures to feed back the adjustment signal to the target thermal power generating unit to achieve real-time response and control.

[0111] According to the intelligent fault-tolerant control method for abnormal operation performance of a thermal power generator set proposed in the embodiment of the present application, the current actual operation data of the target thermal power generator set can be analyzed, and the actual abnormal score of the target thermal power generator set can be obtained based on the analysis result, so that when the actual abnormal score is greater than the preset safety threshold, the corresponding abnormal type and abnormal degree can be determined based on the analysis result, and then the corresponding fault-tolerant strategy can be generated to adjust the operation state of the target thermal power generator set using the fault-tolerant strategy, that is, by applying intelligent algorithms and adaptive fault-tolerant mechanisms, the operation state of the thermal power generator set is monitored, analyzed and abnormal processing is performed in real time, the stable and safe operation of the unit under various working conditions is ensured, and the impact of abnormalities on the performance of the unit is minimized. Thus, the technical problem that the intelligent fault-tolerant system has great limitations in the related art and lacks adaptability to the complex working conditions of the thermal power generator set, which makes the fault-tolerant ability of the thermal power generator set poor and it is difficult to ensure the operation efficiency of the thermal power generator set is solved.

[0112] Next, an intelligent fault-tolerant control device for abnormal operating performance of a thermal power generating set proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0113] Figure 8 It is a block diagram of an intelligent fault-tolerant control device for abnormal operating performance of a thermal power generating set according to an embodiment of the present application.

[0114] like Figure 8 As shown, the intelligent fault-tolerant control device 10 for abnormal operating performance of a thermal power generating set includes: an acquisition module 100, a scoring module 200 and a control module 300.

[0115] Specifically, the acquisition module 100 is used to acquire the current actual operation data of the target thermal power generating unit.

[0116] The scoring module 200 is used to analyze the current actual operation data to obtain corresponding analysis results, and obtain the actual abnormality score of the target thermal power generating unit based on the analysis results, so as to generate a corresponding abnormal signal based on the analysis results when the actual abnormality score is greater than a preset safety threshold.

[0117] The control module 300 is used to obtain the corresponding abnormality type and abnormality degree based on the abnormal signal, and generate a corresponding fault-tolerant strategy based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generating set by using the fault-tolerant strategy.

[0118] Optionally, in one embodiment of the present application, the acquisition module 100 includes: a judgment unit, a collection unit and a first processing unit.

[0119] Among them, the judgment unit is used to judge whether the sensor data of multiple preset key parts of the target thermal power generating unit meet the preset collection conditions.

[0120] The acquisition unit is used to obtain the current operating status of the target thermal power generating set when the sensor data of each preset key part meets the preset acquisition conditions, and determine the sampling frequency based on the current operating status to acquire the current operating data of the target thermal power generating set based on the sampling frequency.

[0121] The first processing unit is used to process the current operation data to obtain the current actual operation data.

[0122] Optionally, in one embodiment of the present application, the scoring module 200 includes: a second processing unit, a first scoring unit, a second scoring unit and a fusion unit.

[0123] The second processing unit is used to normalize the current actual operation data to obtain actual data.

[0124] The first scoring unit is used to combine the long short-term memory network, the historical sequence data of the target thermal power generating unit and the actual data to obtain a first abnormality score of the target thermal power generating unit.

[0125] The second scoring unit is used to extract local feature data that meets a preset change trend from the actual data based on the historical sequence data, and generate a second abnormality score of the target thermal power generating unit based on the local feature data.

[0126] The fusion unit is used to integrate the first anomaly score and the second anomaly score to obtain an actual anomaly score.

[0127] Optionally, in one embodiment of the present application, the intelligent fault-tolerant control device 10 for abnormal operating performance of a thermal power generating set further includes: a storage module.

[0128] The storage module is used to store the current actual operation data and the corresponding data collection time, so as to update the historical sequence data using the current actual operation data and the corresponding data collection time.

[0129] Optionally, in one embodiment of the present application, the control module 300 includes: a determination unit, a first control unit, a second control unit, a third control unit and a fourth control unit.

[0130] The determination unit is used to obtain a corresponding abnormality classification based on the abnormality type and the abnormality degree, and determine a fault-tolerant control strategy based on the abnormality classification.

[0131] The first control unit is used to determine the key operating parameters of the target thermal power generating set based on the fault-tolerant control strategy, and use the key operating parameters to control the target thermal power generating set.

[0132] The second control unit is used to determine the operating parameters of the cooling system of the target thermal power generating set based on the fault-tolerant control strategy, so as to control the cooling system using the operating parameters of the cooling system.

[0133] The third control unit is used to determine the load reduction operation parameters of the target thermal power generating set based on the fault-tolerant control strategy, and control the target thermal power generating set based on the load reduction operation parameters.

[0134] The fourth control unit is used to control the target thermal power generating unit to enter an emergency shutdown state based on a fault-tolerant control strategy.

[0135] Optionally, in one embodiment of the present application, the intelligent fault-tolerant control device 10 for abnormal operating performance of a thermal power generating set further includes: an optimization module.

[0136] Among them, the optimization module is used to calculate a new anomaly score based on the new operating data of the target thermal power generating unit after the fault-tolerant control strategy is executed for a preset time, and use the new anomaly score to optimize the fault-tolerant control strategy.

[0137] It should be noted that the aforementioned explanation of the embodiment of the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating set is also applicable to the intelligent fault-tolerant control device for abnormal operating performance of a thermal power generating set of this embodiment, and will not be repeated here.

[0138] According to the intelligent fault-tolerant control device for abnormal operation performance of a thermal power generator set proposed in the embodiment of the present application, the current actual operation data of the target thermal power generator set can be analyzed, and the actual abnormal score of the target thermal power generator set can be obtained based on the analysis result, so that when the actual abnormal score is greater than the preset safety threshold, the corresponding abnormal type and abnormal degree can be determined based on the analysis result, and then the corresponding fault-tolerant strategy can be generated to adjust the operation state of the target thermal power generator set by using the fault-tolerant strategy, that is, by applying intelligent algorithms and adaptive fault-tolerant mechanisms, the operation state of the thermal power generator set can be monitored, analyzed and abnormalities can be handled in real time, so as to ensure the stable and safe operation of the unit under various working conditions and minimize the impact of abnormalities on the performance of the unit. Thus, the technical problem that the intelligent fault-tolerant system has great limitations in the related art and lacks adaptability to the complex working conditions of the thermal power generator set, which makes the fault-tolerant ability of the thermal power generator set poor and it is difficult to ensure the operation efficiency of the thermal power generator set is solved.

[0139] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0140] A memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .

[0141] When the processor 902 executes the program, the intelligent fault-tolerant control method for abnormal operating performance of the thermal power generating set provided in the above embodiment is implemented.

[0142] Furthermore, the electronic device further comprises:

[0143] The communication interface 903 is used for communication between the memory 901 and the processor 902 .

[0144] The memory 901 is used to store computer programs that can be executed on the processor 902 .

[0145] The memory 901 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0146] If the memory 901, the processor 902 and the communication interface 903 are implemented independently, the communication interface 903, the memory 901 and the processor 902 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0147] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.

[0148] The processor 902 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0149] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set as described above is implemented.

[0150] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set provided by an embodiment of the present invention.

[0151] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0152] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0153] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0154] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0155] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0156] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0157] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0158] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An intelligent fault-tolerant control method for abnormal operating performance of a thermal power generating unit, characterized in that: The following steps are involved: Obtain the current actual operation data of the target thermal power generating unit; Analyze the current actual operation data to obtain a corresponding analysis result, and obtain an actual abnormality score of the target thermal power generating unit based on the analysis result, so as to generate a corresponding abnormal signal based on the analysis result when the actual abnormality score is greater than a preset safety threshold; Based on the abnormal signal, a corresponding abnormal type and abnormal degree are obtained, and based on the abnormal type and abnormal degree, a corresponding fault-tolerant strategy is generated, so as to adjust the operating state of the target thermal power generating set by using the fault-tolerant strategy.

2. The method according to claim 1, characterized in that The obtaining of the current actual operation data of the target thermal power generating unit includes: Determining whether the sensor data of multiple preset key parts of the target thermal power generating unit meet the preset collection conditions; When the sensor data of each preset key part meets the preset collection condition, the current operating state of the target thermal power generating set is obtained, and a sampling frequency is determined based on the current operating state, so as to collect the current operating data of the target thermal power generating set based on the sampling frequency; The current operation data is processed to obtain the current actual operation data.

3. The method according to claim 1, characterized in that The analyzing the current actual operation data to obtain a corresponding analysis result, and obtaining an actual abnormality score of the target thermal power generating unit based on the analysis result, so as to generate a corresponding abnormal signal based on the analysis result when the actual abnormality score is greater than a preset safety threshold, includes: Normalizing the current actual operation data to obtain actual data; Combining the long short-term memory network, the historical sequence data of the target thermal power generating set and the actual data, obtaining a first abnormality score of the target thermal power generating set; extracting local feature data satisfying a preset change trend from the actual data based on the historical sequence data, and generating a second abnormality score for the target thermal power generating group based on the local feature data; The first anomaly score and the second anomaly score are integrated to obtain the actual anomaly score.

4. The method according to claim 3, characterized in that Also includes: The current actual operation data and the corresponding data collection time are stored to update the historical sequence data using the current actual operation data and the corresponding data collection time.

5. The method according to claim 1, characterized in that The method of obtaining a corresponding abnormality type and abnormality degree based on the abnormal signal, and generating a corresponding fault-tolerant strategy based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generating set by using the fault-tolerant strategy, includes: Obtaining a corresponding abnormality classification based on the abnormality type and abnormality degree, and determining the fault-tolerant control strategy based on the abnormality classification; Determining key operating parameters of the target thermal power generating set based on the fault-tolerant control strategy, and controlling the target thermal power generating set using the key operating parameters; Determining operating parameters of a cooling system of the target thermal power generating unit based on the fault-tolerant control strategy, so as to control the cooling system using the operating parameters of the cooling system; Determining a load reduction operation parameter of the target thermal power generating set based on the fault-tolerant control strategy, and controlling the target thermal power generating set based on the load reduction operation parameter; Based on the fault-tolerant control strategy, the target thermal power generating set is controlled to enter an emergency shutdown state.

6. The method according to claim 1, characterized in that Also includes: After the fault-tolerant control strategy is executed for a preset time, a new abnormality score is calculated based on new operating data of the target thermal power generating set, and the fault-tolerant control strategy is optimized using the new abnormality score.

7. An intelligent fault-tolerant control device for abnormal operating performance of a thermal power generating unit, characterized in that: include: An acquisition module is used to acquire the current actual operation data of the target thermal power generating unit; A scoring module, configured to analyze the current actual operation data to obtain a corresponding analysis result, and obtain an actual abnormality score of the target thermal power generating unit based on the analysis result, so as to generate a corresponding abnormal signal based on the analysis result when the actual abnormality score is greater than a preset safety threshold; The control module is used to obtain a corresponding abnormality type and abnormality degree based on the abnormal signal, and generate a corresponding fault-tolerant strategy based on the abnormality type and abnormality degree, so as to adjust the operating state of the target thermal power generating set by using the fault-tolerant strategy.

8. The device according to claim 7, characterized in that The acquisition module comprises: A judgment unit, used to judge whether the sensor data of multiple preset key parts of the target thermal power generating unit meet the preset collection conditions; A collection unit, used for obtaining the current operating state of the target thermal power generating set when the sensor data of each preset key part meets the preset collection condition, and determining a sampling frequency based on the current operating state to collect the current operating data of the target thermal power generating set based on the sampling frequency; A processing unit is used to perform data processing on the current operation data to obtain the current actual operation data.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set as described in any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the intelligent fault-tolerant control method for abnormal operating performance of a thermal power generator set as described in any one of claims 1 to 6.

Images