Thermal power plant steam turbine bearing temperature adjusting method, system, equipment and medium

Abstract

The invention relates to the technical field of turbine bearing temperature regulation, in particular to a thermal power plant turbine bearing temperature regulation method, system and equipment and a medium. According to the method, the temperature data and the working condition parameters are firstly collected and preprocessed, then the temperature change trend is predicted by using the preset deep learning model, the similar working condition data in the historical database are queried to optimize the early warning characteristics, and finally the adjustment strategy is determined according to the optimized judgment result. According to the method, the bearing temperature change trend is accurately predicted, the early warning result can be optimized by referring to historical operation experience, then a more reasonable adjustment strategy is formulated, and the accuracy and reliability of bearing temperature control are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of temperature regulation of steam turbine bearings, and in particular to a method, system, equipment and medium for regulating the temperature of steam turbine bearings in a thermal power plant. Background Art

[0002] The steam turbine of a thermal power plant is the core equipment of the power generation system. The stability of its bearing temperature is directly related to the safe operation of the unit. As the generator sets develop towards large capacity and high parameters, the monitoring and regulation of bearing temperature is particularly important. Effective bearing temperature regulation can not only extend the life of the equipment, but also improve power generation efficiency and reduce operation and maintenance costs.

[0003] At present, the main method used is to set temperature thresholds for real-time monitoring. When the bearing temperature exceeds the warning value, an alarm signal is issued. At the same time, automatic adjustment technologies such as PID control are used to control the bearing temperature by adjusting the cooling oil flow, and regular inspection and maintenance are combined to ensure that the bearing is in good operating condition.

[0004] The existing technology relies on a single temperature threshold and a simple control algorithm, which cannot adapt to complex temperature changes and easily causes control lag and untimely adjustment, affecting the safe operation of the bearing. This situation needs to be further improved. Summary of the invention

[0005] In order to solve the problem that the existing method of adjusting the bearing temperature by relying on a single temperature threshold and a simple control algorithm easily causes control lag and untimely adjustment, thus affecting the safe operation of the bearing, the present application provides a method, system, equipment and medium for adjusting the bearing temperature of a steam turbine in a thermal power plant, adopting the following technical solutions: In a first aspect, the present application provides a method for regulating the temperature of a steam turbine bearing in a thermal power plant, comprising the following steps: Collect temperature data of turbine bearing temperature sensor and bearing operating condition parameters, and perform preprocessing to obtain processed data; Analyze the processed data based on a preset deep learning model, predict the change trend of the bearing temperature, and obtain temperature warning features; Query the bearing operation history database to obtain historical operation data under similar working conditions; Based on the historical operation data, the temperature warning feature is optimized to obtain an optimized temperature abnormality judgment result; According to the optimized temperature abnormality judgment result, the adjustment strategy of the bearing cooling system is determined.

[0006] By adopting the above technical scheme, since the temperature control of the turbine bearings in thermal power plants is crucial to the safe operation of the equipment, the existing control system often finds it difficult to accurately predict the changing trend of the bearing temperature when facing complex working conditions, such as rapid load increase and decrease of the unit, drastic fluctuations in ambient temperature, etc.; the present application first collects and preprocesses temperature data and operating parameters, and then uses a preset deep learning model to predict the temperature change trend, queries similar operating condition data in the historical database to optimize the early warning features, and finally determines the adjustment strategy based on the optimized judgment results; it achieves accurate prediction of the bearing temperature change trend, and can draw on historical operating experience to optimize the early warning results, and then formulate a more reasonable adjustment strategy, which significantly improves the accuracy and reliability of bearing temperature control.

[0007] Optionally, the bearing operating condition parameters include metal temperature of the upper and lower bearing pads, speed data, load data, vibration data, cooling oil temperature, oil pressure and oil level.

[0008] By adopting the above-mentioned technical scheme, the present application integrates key parameters such as the metal temperature of the upper and lower bearing pads, speed data, load data, vibration data, cooling oil temperature, oil pressure and oil level into the analysis scope to more comprehensively evaluate the operating status of the bearing; it can identify abnormal conditions caused by the coupling of multiple parameters, greatly improving the warning accuracy and fault diagnosis capability of abnormal bearing temperature.

[0009] Optionally, the processed data is analyzed based on a preset deep learning model to predict the change trend of the bearing temperature and obtain the temperature warning feature, which specifically includes the following steps: Based on a preset deep learning model, time series feature extraction is performed on the processed data to obtain temperature change trend features and temperature fluctuation features of the bearing; Based on the temperature change trend characteristics and temperature fluctuation characteristics, combined with a preset temperature alarm threshold, a temperature warning characteristic of the bearing is generated.

[0010] By adopting the above technical scheme, since the temperature of the turbine bearing in a thermal power plant will show different change patterns over time, such as the temperature climbing process at startup, the temperature response when the load changes, and the periodic fluctuations during normal operation, it is difficult to accurately reflect the dynamic development process of temperature anomalies by simply relying on static threshold judgment; the present application first uses a deep learning model to extract time series features from the processed data, and simultaneously obtains the temperature change trend characteristics and fluctuation characteristics, and then combines these two types of features with the preset temperature alarm threshold to generate a more predictive temperature warning feature; it is worth noting that by introducing bearing operating condition parameters (such as speed, load, oil pressure, etc.) as model input, the temperature anomaly judgment is made more interpretable and accurate. For example, the same amplitude of temperature increase may be a normal response when the load suddenly increases, but may indicate a bearing abnormality when the load is stable; the present application can not only capture the gradual trend of the bearing temperature, but also identify abnormal temperature fluctuation patterns. Through the dual analysis of trend characteristics and fluctuation characteristics, the accuracy and predictability of temperature anomaly warning are significantly improved.

[0011] Optionally, query the bearing operation history database to obtain historical operation data under similar working conditions, which specifically includes the following steps: Query the historical operation database and mark the temperature alarm level of the bearing in the previous time period; Based on the mark, historical operation data corresponding to the temperature alarm level is obtained.

[0012] By adopting the above technical solution, the present application first marks the temperature alarm level of the operating data in the historical database, and quickly retrieves the historical operating data corresponding to the current operating conditions based on these marks; by establishing an association mechanism between the temperature alarm level and the historical data, not only the retrieval efficiency of the historical data is improved, but also it is ensured that the historical data obtained has a high degree of similarity with the current situation, providing a reference basis for subsequent temperature anomaly judgments.

[0013] Optionally, based on the historical operation data, the temperature warning feature is optimized to obtain an optimized temperature anomaly judgment result, which specifically includes the following steps: Based on the historical operation data, obtaining the temperature alarm level and historical adjustment measures of the bearing; Compare the current temperature warning characteristics with the historical temperature alarm levels, and mark the situations with similar comparison results as similar working conditions; Based on the historical adjustment measures of the same working conditions, adjust the temperature adjustment curve of the corresponding bearing; Based on the adjusted temperature regulation curve, the temperature warning characteristics corresponding to the similar working conditions are optimized to obtain an optimized temperature anomaly judgment result.

[0014] By adopting the above technical scheme, since the temperature control of the turbine bearings in thermal power plants needs to be continuously optimized and dynamically adjusted, it is impossible to achieve accurate matching and continuous improvement of the control strategy by simply relying on historical data for simple comparison; this application first obtains the temperature alarm level and adjustment measures in the historical operating data, and then identifies similar operating conditions by comparing the current warning characteristics and historical alarm levels, adjusts the temperature adjustment curve based on the historical adjustment experience under similar operating conditions, and finally optimizes the temperature warning characteristics of the current operating conditions; by establishing a closed-loop optimization mechanism of warning characteristics, operating condition matching and adjustment strategy, not only the effective use of historical experience is achieved, but also the control strategy can be continuously optimized according to the actual operating results, which significantly improves the accuracy and adaptability of bearing temperature control.

[0015] Optionally, the method further comprises the following steps: Based on the temperature adjustment curve and the preset system linkage rules, the bearing cooling system is linked with the bearing lubrication system and the bearing sealing system to obtain a linkage control scheme; Generate the estimated maintenance time of the bearing temperature control related systems based on the preset maintenance cycle of each system; According to the unit operation plan, the estimated maintenance time is adjusted to obtain the actual maintenance time; Based on the adjusted actual maintenance time, regular maintenance and inspection are carried out on the bearings and their temperature regulation related systems.

[0016] By adopting the above technical scheme, the stability of the bearing temperature of the turbine in a thermal power plant not only depends on the cooling system, but is also closely related to the coordinated operation of multiple related systems such as the lubrication system and the sealing system. The existing control schemes often separate the systems and manage them independently; the present application first establishes a linkage control scheme between systems based on the temperature adjustment curve, and then generates an estimated maintenance time according to the maintenance cycle of each system, and then determines the actual maintenance time in combination with the unit operation plan, and finally implements regular maintenance; a collaborative management mechanism for the cooling system, lubrication system and sealing system is established, which not only realizes the linkage control of multiple systems, but also establishes a scientific maintenance plan, which significantly improves the systematicness and reliability of the bearing temperature control.

[0017] Optionally, the method further comprises the following steps: Obtain the temperature distribution data of the upper and lower bearing pads; Collect temperature data of parts adjacent to the bearing; Correlate and analyze the bearing temperature distribution data with the temperature data of adjacent parts to identify the transmission law of abnormal bearing temperature; The temperature anomaly judgment result is optimized based on the transfer law, and the adjusted cooling control strategy is sent to the relevant system for execution.

[0018] By adopting the above technical solution, the present application first obtains the temperature distribution data of the upper and lower bearings, and collects the temperature data of adjacent parts at the same time, and then identifies the spatial transmission law of temperature anomalies through correlation analysis, and finally optimizes the temperature anomaly judgment results based on these laws and executes corresponding control strategies; it realizes all-round monitoring of bearing temperature anomalies, and can accurately grasp the propagation trend of temperature anomalies, which significantly improves the accuracy and foresight of bearing temperature control.

[0019] In a second aspect, the present application provides a thermal power plant steam turbine bearing temperature control system, comprising: The data acquisition module is used to collect the temperature data of the turbine bearing temperature sensor and the bearing operating condition parameters, and perform preprocessing to obtain processed data; A temperature warning feature acquisition module is used to analyze the processed data based on a preset deep learning model, predict the change trend of the bearing temperature, and obtain the temperature warning feature; The historical operation data acquisition module is used to query the bearing operation history database and obtain the historical operation data under similar working conditions; A temperature warning feature optimization module, used to optimize the temperature warning feature based on the historical operation data to obtain an optimized temperature anomaly judgment result; The cooling adjustment strategy determination module is used to determine the adjustment strategy of the bearing cooling system according to the optimized temperature abnormality judgment result.

[0020] In a third aspect, 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 implements the steps of the above-mentioned method for regulating the temperature of a turbine bearing in a thermal power plant when executing the computer program.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for regulating the temperature of a steam turbine bearing in a thermal power plant are implemented.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application first collects temperature data and operating parameters and pre-processes them, then uses a preset deep learning model to predict the temperature change trend, queries similar operating condition data in the historical database to optimize the warning features, and finally determines the adjustment strategy based on the optimized judgment results; it achieves accurate prediction of the bearing temperature change trend, and can draw on historical operating experience to optimize the warning results, and then formulate a more reasonable adjustment strategy, which significantly improves the accuracy and reliability of bearing temperature control; 2. Since the temperature of the turbine bearings in thermal power plants will show different change patterns over time, such as the temperature climbing process during startup, the temperature response during load changes, and the periodic fluctuations during normal operation, it is difficult to accurately reflect the dynamic development process of temperature anomalies by simply relying on static threshold judgments; this application first uses a deep learning model to extract time series features from the processed data, and simultaneously obtains the temperature change trend features and fluctuation features, and then combines these two types of features with the preset temperature alarm threshold to generate a more predictive temperature warning feature; it is worth noting that by introducing bearing operating condition parameters (such as speed, load, oil pressure, etc.) as model input, the temperature anomaly judgment is made more interpretable and accurate. For example, the same amplitude of temperature increase may be a normal response when the load suddenly increases, but may indicate bearing abnormality when the load is stable; this application can not only capture the gradual trend of bearing temperature, but also identify abnormal temperature fluctuation patterns. Through the dual analysis of trend features and fluctuation features, the accuracy and predictability of temperature anomaly warning are significantly improved; 3. Since the temperature control of turbine bearings in thermal power plants requires continuous optimization and dynamic adjustment, simply relying on historical data for simple comparison cannot achieve accurate matching and continuous improvement of control strategies; this application first obtains the temperature alarm level and adjustment measures in the historical operating data, and then identifies similar operating conditions by comparing the current warning characteristics and historical alarm levels, adjusts the temperature adjustment curve based on historical adjustment experience under similar operating conditions, and finally optimizes the temperature warning characteristics of the current operating conditions; by establishing a closed-loop optimization mechanism of warning characteristics, operating condition matching and adjustment strategies, not only the effective use of historical experience is achieved, but also the control strategy can be continuously optimized according to the actual operating results, which significantly improves the accuracy and adaptability of bearing temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a method for regulating the temperature of a steam turbine bearing in a thermal power plant according to an embodiment of the present application; Figure 2 It is a flow chart of step S120 in a method for adjusting the temperature of a steam turbine bearing in a thermal power plant according to an embodiment of the present application; Figure 3 It is a flow chart of step S130 in a method for adjusting the temperature of a steam turbine bearing in a thermal power plant according to an embodiment of the present application; Figure 4 It is a flow chart of step S140 in a method for adjusting the temperature of a steam turbine bearing in a thermal power plant according to an embodiment of the present application; Figure 5 It is a flow chart of system linkage control in a method for regulating the temperature of a steam turbine bearing in a thermal power plant according to an embodiment of the present application; Figure 6It is a schematic flow chart of adjusting the cooling strategy in a method for regulating the temperature of a steam turbine bearing in a thermal power plant according to an embodiment of the present application; Figure 7 It is a module schematic diagram of a steam turbine bearing temperature control system for a thermal power plant according to an embodiment of the present application; Figure 8 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0025] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0026] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0027] In the first aspect, the present application provides a method for regulating the temperature of a turbine bearing in a thermal power plant, referring to Figure 1 , including the following steps: S110, collecting temperature data of the turbine bearing temperature sensor and bearing operating condition parameters, and performing preprocessing to obtain processed data.

[0028] Among them, the operating parameters of the bearing include the metal temperature of the upper and lower bearings, speed data, load data, vibration data, cooling oil temperature, oil pressure and oil level. The thermal power plant turbine bearing temperature control system collects bearing temperature and operating data in real time, and uses a distributed data acquisition system to transmit the data to the central control system through the field bus. The system pre-processes the collected raw data, including outlier removal, missing value filling and data standardization, to ensure the data quality of subsequent analysis.

[0029] Specifically, during the preprocessing process, the 3σ principle was used to eliminate outliers, the linear interpolation method was used to process missing data, and the maximum and minimum value normalization method was used to unify data of different dimensions into the [0,1] interval to facilitate subsequent modeling and analysis.

[0030] S120, analyzing the processed data based on a preset deep learning model, predicting the change trend of the bearing temperature, and obtaining temperature warning features.

[0031] In this embodiment, the deep learning model adopts a long short-term memory network structure. The model input is the preprocessed temperature data and operating parameter time series. The output is the temperature change trend prediction result within a certain time window in the future, and a temperature warning feature is generated based on the prediction result.

[0032] Specifically, historical operation data is used for model training, and mean square error is used as the loss function.

[0033] S130, querying the bearing operation history database to obtain historical operation data under similar working conditions.

[0034] In this embodiment, the system establishes a bearing operation history database to record the operation data and corresponding adjustment measures under different working conditions. Through the similarity calculation method, the historical operation data similar to the current working condition is retrieved from the history database to provide a reference for subsequent optimization.

[0035] Specifically, the Euclidean distance is used to calculate the similarity of working conditions, and the similarity threshold is set to filter out the historical operation data under similar working conditions. The system also records the adjustment measures taken under these working conditions and their effects, including the temperature change trend before and after the adjustment, adjustment parameters and other information.

[0036] S140. Based on historical operation data, optimize the temperature warning characteristics to obtain an optimized temperature anomaly judgment result.

[0037] In this embodiment, the system optimizes the current temperature warning characteristics based on the processing experience of similar working conditions in the historical operating data.

[0038] Specifically, the system compares the current temperature warning characteristics with the characteristics of similar historical working conditions, and uses the weighted average method to correct the warning characteristics. The weight coefficient is dynamically adjusted according to the similarity of the working conditions. At the same time, combined with the effect evaluation results of historical adjustment measures, the threshold setting for temperature anomaly judgment is optimized.

[0039] S150. Determine an adjustment strategy for the bearing cooling system according to the optimized temperature abnormality judgment result.

[0040] Among them, the system automatically generates an adjustment strategy based on the optimized temperature anomaly judgment results and the characteristics of the bearing cooling system. The adjustment strategy includes adjustment plans for parameters such as cooling oil flow and temperature.

[0041] Specifically, the regulation strategy adopts a hierarchical control method, setting different regulation levels according to the degree of temperature abnormality. For example, when the temperature slightly exceeds the standard, the cooling oil flow rate is appropriately increased; when the temperature rises rapidly, the cooling oil temperature and flow rate are adjusted at the same time. The system realizes automatic adjustment of cooling parameters through the PID controller, and the control parameters are dynamically optimized according to the actual operation effect.

[0042] In one embodiment, referring to Figure 2 In step S120, the processed data is analyzed based on the preset deep learning model to predict the change trend of the bearing temperature and obtain the temperature warning feature, which specifically includes the following steps: S121. Extract time series features of the processed data based on a preset deep learning model to obtain temperature change trend characteristics and temperature fluctuation characteristics of the bearing.

[0043] In this embodiment, the system uses a deep learning model including a time convolution module to extract features from the time series data of bearing temperature and operating parameters, and captures short-term and long-term temperature change features, including temperature rise / fall trends, fluctuation cycles and amplitudes. The input of the model is preprocessed multidimensional time series data, and the key features of the temperature sequence are extracted through multi-layer convolution operations and pooling operations.

[0044] S122. Based on the temperature change trend characteristics and the temperature fluctuation characteristics, combined with the preset temperature alarm threshold, generate the temperature warning characteristics of the bearing.

[0045] In this embodiment, a multi-level early warning mechanism is established based on the extracted temperature features. The system sets three early warning levels, corresponding to slight abnormalities, moderate abnormalities, and severe abnormalities. The temperature change trend feature is used to determine the rate and duration of temperature change, and the temperature fluctuation feature is used to evaluate the stability of temperature. The system compares these features with the preset temperature alarm threshold and comprehensively generates an early warning signal.

[0046] In one embodiment, referring to Figure 3 In step S130, query the bearing operation history database to obtain historical operation data under similar working conditions, which specifically includes the following steps: S131. Query the historical operation database and mark the temperature alarm level of the bearing in the previous time period.

[0047] This embodiment builds a time series feature database to record the temperature alarm records and corresponding operating condition information of the bearing at different operating stages. The system divides the historical data into time windows, each window is 24 hours long, and the overlap rate of adjacent windows is 50%. In each time window, the operating status of the bearing is graded and marked according to the temperature change characteristics and alarm rules, including normal operation, slight abnormality, moderate abnormality and severe abnormality.

[0048] Specifically, the system uses a hybrid marking method based on rules and statistics. For example, when the mean value of the bearing temperature in a certain time window is 47°C, the standard deviation is 0.8°C, and the maximum temperature does not exceed 50°C, it is marked as normal operation; when the temperature continues to rise and the amplitude exceeds the preset threshold, the time period is marked as the corresponding abnormal level according to the rising rate and duration.

[0049] S132. Based on the tag, obtain historical operation data corresponding to the temperature alarm level.

[0050] In this embodiment, the system establishes a data retrieval mechanism based on similarity to quickly obtain historical operating data similar to the current operating conditions. The system first performs a preliminary screening based on the temperature alarm level, and then calculates the similarity of the operating parameters, including key factors such as bearing load, speed, and ambient temperature. By setting the similarity threshold, the most valuable historical data can be screened out.

[0051] In one embodiment, referring to Figure 4 In step S140, based on the historical operation data, the temperature warning characteristics are optimized to obtain the optimized temperature abnormality judgment result, which specifically includes the following steps: S141. Based on historical operation data, obtain the temperature alarm level and historical adjustment measures of the bearing.

[0052] In this embodiment, the system extracts bearing temperature alarm events and corresponding processing measures records from the historical database, classifies and organizes the historical data, and associates and stores information such as temperature alarm level, alarm duration, adjustment measure type and adjustment effect to form an experience knowledge base.

[0053] Specifically, the system divides historical adjustment measures into multiple categories according to the adjustment method, such as adjusting cooling oil flow, adjusting oil temperature, adjusting oil pressure, etc. Each adjustment measure record contains specific parameter adjustment values, adjustment timing and effect evaluation indicators.

[0054] S142. Compare the current temperature warning characteristics with the historical temperature alarm levels, and mark situations with similar comparison results as similar operating conditions.

[0055] In this embodiment, a pattern matching algorithm is used to compare and analyze the current temperature warning features with the temperature alarm levels in the historical data. The system evaluates the similarity of the working conditions by calculating the distance between the feature vectors and sets a similarity threshold to classify the working conditions. If the similarity exceeds the threshold, the system marks it as a similar working condition.

[0056] Specifically, the system uses a dynamic time warping algorithm to calculate the similarity of temperature curves, while considering the matching degree of key parameters such as load rate and ambient temperature.

[0057] S143. Based on historical adjustment measures for similar working conditions, adjust the temperature adjustment curve of the corresponding bearing.

[0058] In this embodiment, based on the historical adjustment experience of similar working conditions, a temperature adjustment optimization model is constructed, and by analyzing the effectiveness of historical adjustment measures, adjustment parameters and timing characteristics in successful cases are extracted to optimize the temperature adjustment curve of the current working condition. Specifically, the system establishes a piecewise linear temperature adjustment curve based on historical adjustment experience.

[0059] S144. Based on the adjusted temperature regulation curve, the temperature warning characteristics corresponding to the same working conditions are optimized to obtain an optimized temperature anomaly judgment result.

[0060] In this embodiment, based on the optimized temperature adjustment curve, the temperature warning characteristics are re-evaluated, and the warning threshold and judgment rules are dynamically adjusted in combination with the historical adjustment effects and the current working conditions to improve the accuracy and timeliness of temperature anomaly judgment.

[0061] In one embodiment, referring to Figure 5 , the method further comprises the following steps: S510: Based on the temperature adjustment curve and the preset system linkage rules, the bearing cooling system, the bearing lubrication system, and the bearing sealing system are linked and controlled to obtain a linkage control solution.

[0062] In this embodiment, a coordinated control model of bearing-related systems is constructed, and the cooling system, lubrication system and sealing system are controlled as a whole. The system analyzes the mutual influence relationship between the systems based on the preset linkage rule library, establishes a parameter linkage mechanism, ensures the coordinated operation of the systems, and jointly maintains the normal working state of the bearing.

[0063] Specifically, when the cooling system needs to be adjusted, the system automatically calculates the corresponding lubricating oil pressure and flow adjustment values. For example, when the cooling oil flow increases by 10%, the lubricating oil pressure is increased by 2%, and the sealing gas pressure is increased by 0.05MPa to ensure system balance. The linkage control scheme includes the adjustment parameters, adjustment sequence and safety limits of each system to ensure the safety and reliability of the adjustment process.

[0064] S520. Generate an estimated maintenance time for the bearing temperature regulation related system based on the preset maintenance cycle of each system.

[0065] In this embodiment, a maintenance cycle prediction model based on equipment status is established. The system collects information such as the operating time, load rate, and fault records of each relevant equipment, and calculates the expected maintenance time of each system in combination with the preset standard maintenance cycle. The model considers the wear status, operating environment, and historical maintenance records of the equipment to generate reasonable maintenance plan suggestions.

[0066] Specifically, the system sets basic maintenance cycles according to different equipment types, such as the bearing body is inspected every 8,000 operating hours, the cooling system is checked every 4,000 hours, and the lubrication system is maintained every 2,000 hours. The maintenance cycle is dynamically adjusted according to the actual operating conditions of the equipment. For example, when the vibration value of a certain equipment continues to increase, the system will arrange the maintenance time of the equipment in advance.

[0067] S530. According to the unit operation plan, the estimated maintenance time is adjusted to obtain the actual maintenance time.

[0068] In this embodiment, the system coordinates and adjusts the estimated maintenance time of each system according to the overall operation plan of the unit. The system considers the grid load demand, equipment maintenance resource allocation and seasonal factors, optimizes the maintenance time arrangement, and ensures that the maintenance work matches the unit operation plan.

[0069] Specifically, the system compares the maintenance plan with the annual maintenance plan of the unit and adjusts the specific maintenance time.

[0070] S540. Based on the adjusted actual maintenance time, perform regular maintenance on the bearings and their temperature regulation related systems.

[0071] In this embodiment, the system builds a maintenance management and quality control system, and formulates a detailed maintenance work plan based on the adjusted actual maintenance time. The system generates a standardized maintenance work list, including maintenance items, technical requirements, quality standards and safety precautions, to ensure the standardization and effectiveness of maintenance work.

[0072] In one embodiment, referring to Figure 6 , the method further comprises the steps of: S610, obtaining temperature distribution data of the upper and lower bearing pads.

[0073] In this embodiment, a distributed temperature sensing system is used to arrange multiple temperature measuring points at key positions of the upper and lower bearing bushes. The system collects temperature data from each measuring point in real time, constructs a bearing temperature distribution cloud map, and reflects the temperature change characteristics of various parts of the bearing.

[0074] Specifically, 5 measuring points are set on the upper bearing and 3 measuring points are set on the lower bearing, with a sampling frequency of 10Hz. For example, when the bearing is operating normally, the temperature of the upper bearing center measuring point is 48℃ and the temperature of the edge measuring point is 45℃, forming a reasonable temperature gradient distribution; when an abnormality occurs, the system can detect the abnormal increase of local temperature or the uneven temperature distribution in time.

[0075] S620, collecting temperature data of parts adjacent to the bearing.

[0076] In this embodiment, the system also establishes a bearing peripheral temperature monitoring network to monitor the temperature of adjacent parts such as the bearing seat, journal, oil groove, etc. The system selects representative monitoring points and collects temperature change data of these parts.

[0077] S630, performing correlation analysis on the bearing temperature distribution data and the temperature data of adjacent parts to identify the transmission law of the bearing temperature anomaly.

[0078] In this embodiment, a thermodynamic analysis method is used to study the diffusion path and transmission characteristics of the bearing temperature anomaly. The system calculates the correlation and time series variation of the temperature at each measuring point to establish a mathematical model for temperature anomaly transmission.

[0079] Specifically, the system uses a sliding time window analysis method with a window length of 30 minutes to calculate the cross-correlation coefficient of the temperature at each measuring point. For example, when it is found that the temperature of a certain point on the bearing increases, the system will analyze the delay time and degree of influence of the temperature change on the surrounding measuring points to determine the transmission direction and rate of the temperature anomaly.

[0080] S640, optimizing the temperature abnormality judgment result based on the transfer law, and sending the adjusted cooling control strategy to the relevant system for execution.

[0081] In this embodiment, the original temperature anomaly judgment standard is optimized according to the identified temperature transfer law, and a targeted cooling control strategy is formulated according to the characteristics of different transfer paths to improve the response efficiency and control accuracy of the system.

[0082] Specifically, the system dynamically adjusts the cooling strategy according to the temperature transfer law. For example, when it detects that the temperature of a certain point on the upper bearing is abnormally high and the abnormality has a tendency to spread to the bearing seat, the system will increase the cooling oil volume in this area in advance and adjust the oil channel distribution ratio to enhance the cooling effect on the abnormal area.

[0083] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] In the second aspect, the present application provides a temperature control system for a steam turbine bearing in a thermal power plant. The temperature control system for a steam turbine bearing in a thermal power plant of the present application is described below in conjunction with the above-mentioned temperature control method for a steam turbine bearing in a thermal power plant.

[0085] Reference Figure 7 , a temperature regulating system for a steam turbine bearing in a thermal power plant, comprising: The data acquisition module is used to collect the temperature data of the turbine bearing temperature sensor and the bearing operating condition parameters, and perform preprocessing to obtain processed data; The temperature warning feature acquisition module is used to analyze the processed data based on the preset deep learning model, predict the change trend of the bearing temperature, and obtain the temperature warning features; The historical operation data acquisition module is used to query the bearing operation history database and obtain the historical operation data under similar working conditions; The temperature warning feature optimization module is used to optimize the temperature warning features based on historical operation data to obtain optimized temperature anomaly judgment results; The cooling adjustment strategy determination module is used to determine the adjustment strategy of the bearing cooling system according to the optimized temperature abnormality judgment result.

[0086] In one embodiment, the bearing operating condition parameters include metal temperature of the upper and lower bearing pads, speed data, load data, vibration data, cooling oil temperature, oil pressure and oil level.

[0087] In one embodiment, the temperature warning feature acquisition module specifically includes: A feature extraction unit is used to extract time series features from the processed data based on a preset deep learning model to obtain the temperature change trend features and temperature fluctuation features of the bearing; The feature generation unit is used to generate a temperature warning feature of the bearing based on the temperature change trend feature and the temperature fluctuation feature in combination with a preset temperature alarm threshold.

[0088] In one embodiment, the historical operation data acquisition module specifically includes: A data query unit is used to query the historical operation database and mark the temperature alarm level of the bearing in the previous time period; The data acquisition unit is used to acquire historical operation data corresponding to the temperature alarm level based on the tag.

[0089] In one embodiment, the temperature warning feature optimization module specifically includes: An alarm level acquisition unit, used to acquire the temperature alarm level and historical adjustment measures of the bearing based on historical operation data; The working condition comparison unit is used to compare the current temperature warning characteristics with the historical temperature alarm levels, and mark the situations with similar comparison results as similar working conditions; The regulation curve adjustment unit is used to adjust the temperature regulation curve of the corresponding bearing based on the historical regulation measures of similar working conditions; The warning feature optimization unit is used to optimize the temperature warning features corresponding to the same working conditions based on the adjusted temperature regulation curve to obtain an optimized temperature anomaly judgment result.

[0090] In one embodiment, the system further comprises: A linkage control module is used to link and control the bearing cooling system, the bearing lubrication system, and the bearing sealing system based on the temperature adjustment curve and the preset system linkage rules to obtain a linkage control solution; The maintenance time generation module is used to generate the estimated maintenance time of the bearing temperature control related systems based on the preset maintenance cycle of each system; The maintenance time adjustment module is used to adjust the estimated maintenance time according to the unit operation plan to obtain the actual maintenance time; The maintenance execution module is used to perform regular maintenance on the bearing and its temperature regulation related systems based on the adjusted actual maintenance time.

[0091] In one embodiment, the system further comprises: A temperature distribution data acquisition module is used to acquire temperature distribution data of the upper and lower bearing bushes; Adjacent temperature data acquisition module, used to collect temperature data of parts adjacent to the bearing; Temperature correlation analysis module, used to correlate the bearing temperature distribution data with the temperature data of adjacent parts and identify the transmission law of abnormal bearing temperature; The control strategy optimization module is used to optimize the temperature anomaly judgment results based on the transfer law, and send the adjusted cooling control strategy to the relevant system for execution.

[0092] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for regulating the temperature of a turbine bearing in a thermal power plant is implemented.

[0093] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0095] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0096] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for regulating the temperature of a steam turbine bearing in a thermal power plant, characterized in that: The steps include: Collect temperature data of turbine bearing temperature sensor and bearing operating condition parameters, and perform preprocessing to obtain processed data; Analyze the processed data based on a preset deep learning model, predict the change trend of the bearing temperature, and obtain temperature warning features; Query the bearing operation history database to obtain historical operation data under similar working conditions; Based on the historical operation data, the temperature warning feature is optimized to obtain an optimized temperature abnormality judgment result; According to the optimized temperature abnormality judgment result, the adjustment strategy of the bearing cooling system is determined.

2. The method for regulating the temperature of a steam turbine bearing in a thermal power plant according to claim 1, characterized in that: The bearing operating condition parameters include the metal temperature of the upper and lower bearing pads, speed data, load data, vibration data, cooling oil temperature, oil pressure and oil level.

3. The method for regulating the temperature of a steam turbine bearing in a thermal power plant according to claim 1, characterized in that: The processed data is analyzed based on a preset deep learning model to predict the change trend of the bearing temperature and obtain the temperature warning feature, which specifically includes the following steps: Based on a preset deep learning model, time series feature extraction is performed on the processed data to obtain temperature change trend features and temperature fluctuation features of the bearing; Based on the temperature change trend characteristics and temperature fluctuation characteristics, combined with a preset temperature alarm threshold, a temperature warning characteristic of the bearing is generated.

4. The method for regulating the temperature of a steam turbine bearing in a thermal power plant according to claim 1, characterized in that: Query the bearing operation history database to obtain historical operation data under similar working conditions, which includes the following steps: Query the historical operation database and mark the temperature alarm level of the bearing in the previous time period; Based on the mark, historical operation data corresponding to the temperature alarm level is obtained.

5. The method for regulating the temperature of a steam turbine bearing in a thermal power plant according to claim 1, characterized in that: Based on the historical operation data, the temperature warning feature is optimized to obtain an optimized temperature abnormality judgment result, which specifically includes the following steps: Based on the historical operation data, obtaining the temperature alarm level and historical adjustment measures of the bearing; Compare the current temperature warning characteristics with the historical temperature alarm levels, and mark the situations with similar comparison results as similar working conditions; Based on the historical adjustment measures of the same working conditions, adjust the temperature adjustment curve of the corresponding bearing; Based on the adjusted temperature regulation curve, the temperature warning characteristics corresponding to the similar working conditions are optimized to obtain an optimized temperature anomaly judgment result.

6. The method for regulating the temperature of a steam turbine bearing in a thermal power plant according to claim 5, characterized in that: The method further comprises the steps of: Based on the temperature adjustment curve and the preset system linkage rules, the bearing cooling system is linked with the bearing lubrication system and the bearing sealing system to obtain a linkage control scheme; Generate the estimated maintenance time of the bearing temperature control related systems based on the preset maintenance cycle of each system; According to the unit operation plan, the estimated maintenance time is adjusted to obtain the actual maintenance time; Based on the adjusted actual maintenance time, regular maintenance and inspection are carried out on the bearings and their temperature regulation related systems.

7. The method for regulating the temperature of a steam turbine bearing in a thermal power plant according to claim 1, characterized in that: The method further comprises the steps of: Obtain the temperature distribution data of the upper and lower bearing pads; Collect temperature data of parts adjacent to the bearing; Correlate and analyze the bearing temperature distribution data with the temperature data of adjacent parts to identify the transmission law of abnormal bearing temperature; The temperature anomaly judgment result is optimized based on the transfer law, and the adjusted cooling control strategy is sent to the relevant system for execution.

8. A thermal power plant steam turbine bearing temperature control system, characterized in that: include: The data acquisition module is used to collect the temperature data of the turbine bearing temperature sensor and the bearing operating condition parameters, and perform preprocessing to obtain processed data; A temperature warning feature acquisition module is used to analyze the processed data based on a preset deep learning model, predict the change trend of the bearing temperature, and obtain the temperature warning feature; The historical operation data acquisition module is used to query the bearing operation history database and obtain the historical operation data under similar working conditions; A temperature warning feature optimization module, used to optimize the temperature warning feature based on the historical operation data to obtain an optimized temperature anomaly judgment result; The cooling adjustment strategy determination module is used to determine the adjustment strategy of the bearing cooling system according to the optimized temperature abnormality judgment result.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for regulating the temperature of a steam turbine bearing in a thermal power plant described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for regulating the temperature of a steam turbine bearing in a thermal power plant according to any one of claims 1 to 7 are implemented.

Images