Holographic Sensing-Based Fatigue Cumulative Prediction Method and System for Hydroelectric Generating Units

Abstract

The present invention discloses a method and system for predicting fatigue accumulation of hydro-generator units based on holographic perception, which relates to the technical field of hydro-generator unit management. The method includes: using a holographic sensor array to perform real-time perception on a target hydro-generator unit; performing data preprocessing; traversing the operation data processing information set to extract key features of fatigue accumulation; performing digital twin modeling to construct a fatigue accumulation prediction model for the target hydro-generator unit; performing simulated operation of the target hydro-generator unit and performing fatigue assessment according to a preset fatigue accumulation mechanism; updating the first fatigue accumulation prediction result based on the second assessment result to obtain the second fatigue accumulation prediction result. It solves the technical problem that it is difficult to obtain sufficient and accurate operation data of giant hydro-generator units in the existing fatigue accumulation prediction of hydro-generator units, resulting in large errors in the fatigue accumulation prediction results, and achieves the technical effect of improving the accuracy and reliability of the fatigue accumulation prediction of hydro-generator units.

Description

Technical Field

[0001] This application relates to the field of hydro-generator unit management technology, and specifically relates to a method and system for predicting fatigue accumulation of hydro-generator units based on holographic perception. Background Art

[0002] As a pillar industry of the national economy, the safety and stability of the power industry have received increasing attention. As the core equipment of hydropower generation, the operating conditions of hydro-generator units are directly related to the stable operation of the entire power system. With the long-term operation of large-scale hydropower stations, under the influence of multiple factors such as water flow impact, mechanical wear, and electromagnetic force, fatigue accumulation inevitably occurs in hydro-generator units, which will lead to problems such as a decline in unit performance and an increase in failure rates. Traditional fatigue accumulation prediction methods are often based on empirical formulas or simplified models, which are difficult to accurately reflect the actual operating conditions and fatigue accumulation process of the units, difficult to obtain sufficient and accurate data to support decision-making, and the fatigue accumulation process of large-scale hydro-generator units is complex, involving the interaction of multiple factors.

[0003] Therefore, in the current related technologies of fatigue accumulation prediction for hydro-generator units, there are technical problems that it is difficult to obtain sufficient and accurate operating data of large-scale hydro-generator units, resulting in large errors in fatigue accumulation prediction results. Summary of the Invention

[0004] This application provides a method and system for predicting fatigue accumulation of hydro-generator units based on holographic perception. By using technical means such as holographic perception, feature identification, and prediction model construction, it solves the technical problems existing in the existing fatigue accumulation prediction of hydro-generator units, that is, it is difficult to obtain sufficient and accurate operating data of large-scale hydro-generator units, resulting in large errors in fatigue accumulation prediction results, and achieves the technical effect of improving the accuracy and reliability of fatigue accumulation prediction of hydro-generator units.

[0005] The present application provides a fatigue accumulation prediction method for a hydropower unit based on holographic perception. The method includes: using a holographic sensor array to perform real-time perception on a target hydropower unit to obtain a real-time operation status data set; performing data preprocessing on the real-time operation status data set to obtain an operation data processing information set; traversing the operation data processing information set for fatigue feature identification, and extracting key fatigue accumulation features according to the identification result; performing digital twin modeling based on the key fatigue accumulation features to construct a fatigue accumulation prediction model for the target hydropower unit; performing simulated operation on the target hydropower unit based on the fatigue accumulation prediction model, performing fatigue evaluation on the simulated operation result according to a preset fatigue accumulation mechanism, performing fatigue accumulation prediction on the target hydropower unit according to the first evaluation result, and outputting a first fatigue accumulation prediction result; performing secondary fatigue evaluation on the simulated operation result through the preset fatigue accumulation mechanism to generate a second evaluation result, and updating the first fatigue accumulation prediction result based on the second evaluation result to obtain a second fatigue accumulation prediction result.

[0006] In a possible implementation, when using a holographic sensor array to perform real-time perception on a target hydropower unit to obtain a real-time operation status data set, the following processing is also performed: determining array layout parameters based on the operation scenario of the target hydropower unit; constructing the holographic sensor array, arranging the holographic sensor array according to the array layout parameters, and performing holographic perception testing to obtain a perception test result; adjusting the holographic sensor array according to the perception test result, performing multi-dimensional perception on the target hydropower unit based on the adjustment information to obtain multi-dimensional operation perception information; integrating the multi-dimensional operation perception information for real-time update to generate the real-time operation status data set.

[0007] In a possible implementation, when traversing the operation data processing information set for fatigue feature identification and extracting key fatigue accumulation features according to the identification result, the following processing is performed: retrieving a historical operation fatigue data record file, traversing the operation data processing information set to match with the historical operation fatigue data record file to generate a matching data set, where the matching data set includes fatigue features; determining multiple fatigue degree data of the operation data processing information set based on the fatigue features; dividing multiple fatigue levels according to the multiple fatigue degree data; identifying multiple fatigue features of the operation data processing information set based on the multiple fatigue levels to obtain the identification result.

[0008] In a possible implementation, digital twin modeling is performed according to the key fatigue accumulation features to construct a fatigue accumulation prediction model for the target hydropower unit, and the following processing is executed: based on the key fatigue accumulation features, the operation data processing information set is divided according to the prediction time scale to generate a training data set, a supervision data set, and a verification data set; through the training data set and the supervision data set, the fatigue accumulation prediction model is trained based on digital twin technology; the output result of the fatigue accumulation prediction model is verified and evaluated according to the verification data set, and the fatigue accumulation prediction model is iteratively optimized according to the evaluation result. When the continuous iteration times meet the preset requirements, it is regarded as convergence, and the fatigue accumulation prediction model is output.

[0009] In a possible implementation, based on the fatigue accumulation prediction model, the simulation operation of the target hydropower unit is carried out, and the fatigue evaluation is carried out on the simulation operation result according to the preset fatigue accumulation mechanism. The following processing is also executed: the simulation operation conditions are set for the target hydropower unit, and the simulation operation conditions include the simulation operation environment, the simulation workload, and the simulation operation time; based on the simulation operation environment, the fatigue accumulation prediction model is started to carry out the simulation operation of the target hydropower unit according to the simulation workload, and it is judged whether the simulation operation duration reaches the simulation operation time. When the simulation operation time is reached, a stop instruction is generated, and the simulation operation is stopped according to the stop instruction to generate a simulation operation result; based on the simulation operation result, the fatigue accumulation index is set, the preset fatigue accumulation mechanism is constructed according to the fatigue accumulation index, and the fatigue accumulation trend analysis of the target hydropower unit is carried out through the preset fatigue accumulation mechanism to generate the fatigue accumulation rate; the fatigue evaluation is carried out according to the fatigue accumulation rate to generate the first evaluation result.

[0010] In a possible implementation, according to the first evaluation result, the fatigue accumulation prediction of the target hydropower unit is carried out, and the first fatigue accumulation prediction result is output. The following processing is also executed: the fatigue accumulation trend is extracted by using the first evaluation result, and the fatigue accumulation trend graph is drawn according to the fatigue accumulation trend; the historical operation data of the target unit is retrieved, and the fatigue prediction value is set based on the fatigue accumulation trend graph; the fatigue accumulation prediction is carried out according to the fatigue prediction value to obtain the fatigue accumulation prediction trend graph; the first fatigue accumulation prediction result of the target hydropower unit is output according to the fatigue accumulation prediction trend graph.

[0011] In a possible implementation, the simulated operation results are secondarily fatigue-evaluated through the preset fatigue accumulation mechanism to generate a second evaluation result. The first fatigue accumulation prediction result is updated based on the second evaluation result to obtain a second fatigue accumulation prediction result, and the following processing is also performed: dynamic impact monitoring and analysis are carried out based on the target hydropower unit to obtain a dynamic impact data set, where the dynamic impact data set includes material change impact data and operating condition change impact data; the simulated operation results are secondarily fatigue-evaluated through the preset fatigue accumulation mechanism based on the material change impact data and the operating condition change impact data to generate a second evaluation result; the second evaluation result and the first evaluation result are traversed and compared for correction to obtain a fatigue accumulation update rate and fatigue accumulation potential risk points; the first fatigue accumulation prediction result is updated based on the fatigue accumulation update rate and the fatigue accumulation potential risk points to generate the second fatigue accumulation prediction result.

[0012] This application also provides a fatigue accumulation prediction system for hydropower units based on holographic perception, including:

[0013] A real-time hydropower unit perception module, which is used to obtain a real-time operation state data set by using a holographic sensor array to perform real-time perception on the target hydropower unit;

[0014] A key feature extraction module, which is used to perform data preprocessing on the real-time operation state data set to obtain an operation data processing information set, traverse the operation data processing information set for fatigue feature identification, and extract fatigue accumulation key features according to the identification results;

[0015] A fatigue accumulation prediction model construction module, which is used to perform digital twin modeling according to the fatigue accumulation key features to construct a fatigue accumulation prediction model for the target hydropower unit;

[0016] A hydropower unit fatigue evaluation module, which is used to perform simulated operation on the target hydropower unit based on the fatigue accumulation prediction model, perform fatigue evaluation on the simulated operation results according to a preset fatigue accumulation mechanism, and perform fatigue accumulation prediction on the target hydropower unit according to the first evaluation result, and output a first fatigue accumulation prediction result;

[0017] A second fatigue accumulation prediction result acquisition module, which is used to secondarily fatigue-evaluate the simulated operation results through the preset fatigue accumulation mechanism to generate a second evaluation result, update the first fatigue accumulation prediction result based on the second evaluation result, and obtain a second fatigue accumulation prediction result.

[0018] A method and system for predicting fatigue accumulation of a hydropower unit based on holographic perception proposed in this application uses a holographic sensor array to perform real-time perception on a target hydropower unit; performs data preprocessing; traverses the operation data processing information set to extract key features of fatigue accumulation; performs digital twin modeling to construct a fatigue accumulation prediction model for the target hydropower unit; performs simulated operation of the target hydropower unit and conducts fatigue assessment according to a preset fatigue accumulation mechanism; updates the first fatigue accumulation prediction result based on the second assessment result to obtain the second fatigue accumulation prediction result. It solves the technical problem that it is difficult to obtain sufficient and accurate operation data of a giant hydropower unit in the existing fatigue accumulation prediction of hydropower units, resulting in a large error in the fatigue accumulation prediction result, achieves the technical effect of improving the accuracy of fatigue accumulation prediction of hydropower units, solves the technical problem that it is difficult to obtain sufficient and accurate operation data of a giant hydropower unit in the existing fatigue accumulation prediction of hydropower units, resulting in a large error in the fatigue accumulation prediction result, and achieves the technical effect of improving the accuracy and reliability of fatigue accumulation prediction of hydropower units. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in order. Instead, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0020] Figure 1 It is a schematic flowchart of the method for predicting fatigue accumulation of a hydropower unit based on holographic perception provided by an embodiment of the present application;

[0021] Figure 2 It is a schematic structural diagram of the system for predicting fatigue accumulation of a hydropower unit based on holographic perception provided by an embodiment of the present application.

[0022] Description of reference numerals: The real-time perception module 10 of the hydropower unit, the key feature extraction module 20, the fatigue accumulation prediction model construction module 30, the fatigue assessment module 40 of the hydropower unit, and the second prediction result acquisition module 50. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically presents the detailed embodiments of this application.

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be construed as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0025] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first / second" are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0026] Embodiments of this application provide a method for predicting the fatigue accumulation of a hydropower unit based on holographic perception, as Figure 1 shown, the method includes:

[0027] Step S100, using a holographic sensor array to perform real-time perception on a target hydropower unit to obtain a real-time operating state data set. Using a holographic sensor array to perform real-time perception on a target hydropower unit to obtain a real-time operating state data set mainly means collecting all-round and real-time data on the hydropower unit through a series of advanced holographic sensor devices. A holographic sensor array is a network of devices integrating multiple sensors that can capture and record various operating parameters of the hydropower unit, including temperature sensors, pressure sensors, vibration sensors, flow sensors, etc. They can real-time perceive key information such as the temperature, pressure, vibration, and flow of the hydropower unit, reflecting the real-time operating state of the hydropower unit, including its operating efficiency, energy consumption, and equipment health status.

[0028] In a possible implementation, step S100 further includes step S110 of determining the array layout parameters based on the operating scenario of the target hydropower unit. According to the actual operating environment and conditions of the hydropower unit, determine the layout and configuration parameters of the holographic sensor array to ensure that the sensor array can effectively sense and collect the operating status data of the hydropower unit. Specifically, the operating scenario may include the location, working environment, climate conditions, unit type, scale, and operating characteristics of the hydropower unit. For example, the holographic sensor array may be arranged in a circumferential ring layout or a matrix layout. The circumferential ring layout evenly arranges the holographic sensors on circumferences with different radii, and the matrix layout arranges the holographic sensors in a rectangular pattern. Different operating scenarios have different requirements for the layout and configuration of the sensor array. For example, in areas with harsh climate conditions, characteristics such as waterproof, dustproof, and resistance to high and low temperatures of the sensors may need to be considered; in the case of a large unit scale or a complex operating environment, the number and density of sensors may need to be increased to improve the accuracy and comprehensiveness of perception. It further includes step S120 of constructing the holographic sensor array, arranging the holographic sensor array according to the array layout parameters, and conducting a holographic perception test to obtain the perception test results. According to the pre-determined array layout parameters, actually build and configure the holographic sensor array, and conduct actual operation tests on the array to verify its perception effect and data collection ability, and obtain the perception test results. Specifically, select appropriate sensor types, design and manufacture sensor brackets or fixing devices, and install and connect the sensors according to the pre-determined layout parameters, including determining the distance, angle, and direction between the sensors, and fixing the sensors at appropriate positions on the hydropower unit according to the pre-determined positions and directions. In the actual operating environment, start the holographic sensor array and collect data through the sensors. It further includes step S130 of adjusting the holographic sensor array according to the perception test results, and performing multi-dimensional perception on the target hydropower unit based on the adjustment information to obtain multi-dimensional operating perception information. After the preliminary holographic perception test, optimize and adjust the holographic sensor array according to the test results to improve the accuracy and comprehensiveness of perception, and then realize multi-dimensional perception of the target hydropower unit to obtain more accurate multi-dimensional operating status perception information. Specifically, the process of adjusting the holographic sensor array according to the perception test results involves careful analysis of the test data. For example, if it is found that the data of some sensors is deviated or unstable, the positions, angles, or calibration parameters of these sensors need to be adjusted; if some key parameters cannot be effectively sensed, new sensors need to be added. Based on the adjusted holographic sensor array, multi-dimensional perception can be performed on the target hydropower unit to obtain more comprehensive and accurate multi-dimensional operating perception information. It further includes step S140 of integrating the multi-dimensional operating perception information for real-time update to generate the real-time operating status data set.The multi-dimensional operation perception information obtained through multi-dimensional perception is collected, integrated, and updated in real time, and finally a data set comprehensively reflecting the multi-dimensional and real-time operation status of the target hydropower unit is generated, including perception data such as temperature, pressure, vibration, and flow. Specifically, the multi-dimensional perception information is integrated, and the latest perception information is continuously added to the data set in a real-time update manner to ensure the timeliness and accuracy of the data set.

[0029] Step S200: Perform data preprocessing on the real-time operation status data set to obtain an operation data processing information set. After obtaining the real-time operation status data set, a series of data preprocessing operations need to be performed on it, including cleaning data, eliminating noise, filling missing values, converting data formats, standardizing data, etc. Specifically, remove duplicate data, abnormal data, or obviously incorrect data points. For example, some sensors may generate abnormal values due to faults or interference; for the missing values in the data set, select appropriate processing strategies according to the specific situation. For example, use methods such as mean, median, or interpolation to fill the missing values; map the data to a specific range or distribution to eliminate the scale differences between different features and improve the accuracy of data analysis. Thus, a more standardized, accurate, and useful operation data processing information set is obtained.

[0030] Step S300: Traverse the operation data processing information set to perform fatigue feature identification, and extract key fatigue accumulation features according to the identification results. Traverse the preprocessed operation data processing information set to identify features related to fatigue and perform level identification, and further extract key features that can reflect fatigue accumulation. Specifically, identify features related to the fatigue state of the hydropower unit according to the operation data processing information set. For example, the temperature change trend, vibration frequency and amplitude, and operation stability of the hydropower unit during operation. During the long-term operation of the hydropower unit, its vibration characteristics may change. Vibration amplitude and vibration frequency are important fatigue features. For example, if the vibration amplitude gradually increases, it may mean that some components inside the unit have fatigue or damage; if the temperature of the unit suddenly rises or shows abnormal fluctuations during normal operation, it may indicate that some components generate heat accumulation due to friction, wear, etc., resulting in fatigue; operation stability includes pressure stability, rotational speed stability, output power volatility, etc. Perform level identification according to the fatigue degree, and extract key fatigue accumulation features according to the identification results, that is, extract the key features that can best reflect the fatigue accumulation situation from multiple identified fatigue features.

[0031] In a possible implementation, step S300 further includes step S310 of retrieving the historical operation fatigue data record file, traversing and matching the operation data processing information set with the historical operation fatigue data record file to generate a matching data set, where the matching data set contains fatigue characteristics. The historical operation fatigue data record file usually contains data related to fatigue recorded during the past operation of the unit. These data may be collected in real time by sensors and processed, or obtained through regular inspections, maintenance, or experiments. By matching the data in the operation data processing information set with the historical operation fatigue data record file, and comparing the current data with the historical data, those characteristics similar to the past fatigue states can be identified, generating a matching data set. The matching data set contains fatigue characteristics, that is, it contains the feature information extracted from the operation data processing information set that matches the historical fatigue data. It further includes step S320 of determining multiple fatigue degree data of the operation data processing information set based on the fatigue characteristics. By using the fatigue characteristics matched from the historical operation fatigue data record file, the current operation data processing information set is analyzed to obtain multiple fatigue degree data, which may include fatigue degree values at different time points, the change trend of the fatigue degree, the comparison of the fatigue degrees of different components or systems, etc. It further includes step S330 of dividing multiple fatigue levels according to the multiple fatigue degree data. The multiple fatigue degree data are divided into multiple fatigue levels. For example, according to the amplitude of abnormal temperature fluctuations, different ranges of vibration amplitude or vibration frequency, changes in pressure stability, changes in rotational speed stability, and the magnitude of output power fluctuations, the data are divided into different levels such as mild fatigue, moderate fatigue, and severe fatigue. It further includes step S340 of identifying multiple fatigue characteristics of the operation data processing information set based on the multiple fatigue levels to obtain the identification result.

[0032] Step S400, perform digital twin modeling according to the fatigue accumulation key characteristics to construct a fatigue accumulation prediction model for the target hydropower unit. Using digital twin technology and combining the obtained fatigue accumulation key characteristics, a model capable of predicting the fatigue accumulation of the target hydropower unit is established. Specifically, the fatigue accumulation prediction model can accurately reflect the law of fatigue accumulation of the hydropower unit. By inputting the operation data of the hydropower unit, it can predict the future fatigue accumulation state. The model is verified using historical data, and according to the verification results, necessary adjustments and optimizations are made to the model to ensure the accuracy and reliability of its prediction results.

[0033] In a possible implementation, step S400 further includes step S410 of partitioning the operation data processing information set according to the prediction time scale based on the fatigue accumulation key features to generate a training data set, a supervision data set, and a validation data set. Using the known fatigue accumulation key features, according to the predicted time scale, the operation data processing information set is partitioned according to the prediction time scale to construct data sets for model training, supervision, and validation. Among them, the prediction time scale may include short-term prediction, medium-term prediction, long-term prediction, etc. Specifically, according to the operation mode and change trend of the fatigue accumulation key features, the operation data processing information set is reasonably partitioned according to the requirements of the prediction time scale to ensure that the partitioned data sets can fully reflect the fatigue accumulation characteristics of the unit, generating a training data set, a supervision data set, and a validation data set. The training data set is used to train the prediction model; the supervision data set is used to provide real-time feedback and adjustment during the model training process to ensure that the model can accurately fit the data; the validation data set is used to evaluate the performance and fatigue accumulation prediction ability of the model. It further includes step S420 of training the fatigue accumulation prediction model based on the digital twin technology through the training data set and the supervision data set. It further includes step S430 of verifying and evaluating the output result of the fatigue accumulation prediction model according to the validation data set, and iteratively optimizing the fatigue accumulation prediction model according to the evaluation result. When the number of consecutive iterations meets the preset requirements, it is regarded as converged, and the fatigue accumulation prediction model is output. Specifically, the output result of the fatigue accumulation prediction model is verified and evaluated using the validation data set, and the fatigue accumulation prediction model is iteratively optimized according to the verification and evaluation result. For example, if the prediction error is large or the accuracy is low, the model needs to be adjusted, including adjusting the model parameters, changing the model structure, increasing or decreasing input features, etc. When the number of consecutive iterations meets the preset requirements, the model is considered to have converged, and its output is used as the final fatigue accumulation prediction model.

[0034] Step S500: Based on the fatigue accumulation prediction model, perform a simulation operation on the target hydropower unit, conduct a fatigue assessment on the simulation operation results according to a preset fatigue accumulation mechanism, and perform a fatigue accumulation prediction on the target hydropower unit according to the first assessment result, and output the first fatigue accumulation prediction result. Specifically, use the constructed and optimized fatigue accumulation prediction model to perform a simulation operation on the target hydropower unit, that is, simulate the operation status of the unit under specific conditions to obtain data and information related to fatigue accumulation. After the simulation operation ends, conduct a fatigue assessment on the simulation operation results according to the preset fatigue accumulation mechanism. The preset fatigue accumulation mechanism is determined based on the design characteristics, operation experience, and fatigue accumulation characteristics of the unit, and reflects the fatigue accumulation law during the operation of the target hydropower unit to obtain the first assessment result. Based on the first assessment result, use the fatigue accumulation prediction model to predict the fatigue accumulation of the target hydropower unit, and output the predicted fatigue accumulation situation as the first fatigue accumulation prediction result, including the fatigue accumulation degree information of the unit at a certain future time point or time period.

[0035] In a possible implementation, step S500 further includes step S510 of setting simulation operating conditions for the target hydropower unit. The simulation operating conditions include a simulated operating environment, a simulated workload, and a simulated operating time. Before performing the simulation operation of the target hydropower unit, a series of conditions need to be set to simulate various situations that the unit may encounter during actual operation, so as to more realistically reflect the operating environment and load characteristics of the unit, in order to more accurately predict its fatigue accumulation situation. Among them, the simulated operating environment refers to the external conditions in which the target hydropower unit is located during operation. For example, environmental factors such as water temperature, water quality, atmospheric pressure, humidity, and temperature; the simulated workload refers to the tasks and workloads that the target hydropower unit needs to bear during operation. For example, different modes such as high load, low load, and periodic load can be set to observe the fatigue performance of the unit under different loads; the simulated operating time refers to the length of time for the simulated unit to operate continuously, several hours, several days or even longer, to observe the fatigue accumulation trend and variation law of the unit in different time periods. It further includes step S520 of starting the fatigue accumulation prediction model to perform the simulation operation of the target hydropower unit according to the simulated workload based on the simulated operating environment, determining whether the simulated operation duration reaches the simulated operating time, generating a stop instruction when the simulated operating time is reached, stopping the simulation operation according to the stop instruction, and generating a simulation operation result. It further includes step S530 of setting a fatigue accumulation index based on the simulation operation result, constructing the preset fatigue accumulation mechanism according to the fatigue accumulation index, and performing fatigue accumulation trend analysis on the target hydropower unit through the preset fatigue accumulation mechanism to generate a fatigue accumulation rate. Among them, the fatigue accumulation index is a parameter or standard used to quantitatively evaluate the fatigue accumulation situation of the target hydropower unit, reflecting the fatigue accumulation state of the target hydropower unit during the simulation operation. After setting the fatigue accumulation index, a preset fatigue accumulation mechanism is constructed according to the fatigue accumulation index to perform fatigue accumulation trend analysis on the simulation operation result of the target hydropower unit, identify the fatigue accumulation law and rate of the target hydropower unit during the simulation operation, and generate a fatigue accumulation rate. The fatigue accumulation rate is a quantitative index describing the speed of fatigue accumulation of the target hydropower unit. By analyzing the simulation operation result, the fatigue accumulation rate of the unit in different time periods can be calculated, the severity of the unit's fatigue accumulation can be judged, and thus the future fatigue accumulation situation can be predicted. It further includes step S540 of performing fatigue assessment according to the fatigue accumulation rate and generating the first assessment result. Using the obtained fatigue accumulation rate, the fatigue state of the target hydropower unit is evaluated and judged, and the first assessment result is generated accordingly.

[0036] In a possible implementation, step S500 further includes step S550 of extracting the fatigue accumulation trend by using the first evaluation result and drawing a fatigue accumulation trend graph according to the fatigue accumulation trend. Based on the first evaluation result, the fatigue accumulation trend of the target hydropower unit is extracted and a fatigue accumulation trend graph is drawn to visually display the change of fatigue accumulation over time or other variables. For example, a line graph or a bar graph is used. It also includes step S560 of retrieving the historical operation data of the target unit and setting a fatigue prediction value based on the fatigue accumulation trend graph. The historical operation data of the target unit is retrieved, and the fatigue prediction value is set in combination with the fatigue accumulation trend graph. The fatigue prediction value is an estimate of the fatigue accumulation of the target hydropower unit in the future for a period of time. It also includes step S570 of performing fatigue accumulation prediction according to the fatigue prediction value and obtaining a fatigue accumulation prediction trend graph. By using the set fatigue prediction value and combining the operation characteristics of the unit, environmental factors, etc., the fatigue accumulation prediction of the target hydropower unit is carried out, and the prediction result is graphically displayed to form a fatigue accumulation prediction trend graph. It also includes step S580 of outputting the first fatigue accumulation prediction result of the target hydropower unit according to the fatigue accumulation prediction trend graph. Based on the generated fatigue accumulation prediction trend graph, the future fatigue accumulation state of the target hydropower unit is predicted and the prediction result is output to form the first fatigue accumulation prediction result. For example, a concise written description such as "It is predicted that the fatigue accumulation of the unit will show an upward trend in the next three months". By outputting the prediction result in a timely manner, the future fatigue accumulation of the target hydropower unit can be understood in a timely manner, and corresponding measures and strategies can be formulated to ensure the safe and stable operation of the unit.

[0037] Step S600: Perform a secondary fatigue evaluation on the simulation operation result through the preset fatigue accumulation mechanism to generate a second evaluation result, and update the first fatigue accumulation prediction result based on the second evaluation result to obtain a second fatigue accumulation prediction result. By using the preset fatigue accumulation mechanism and combining the simulation operation data, a secondary fatigue evaluation is performed on the simulation operation result, that is, a more refined division and quantification of the fatigue accumulation of each component of the target hydropower unit is carried out, considering more factors that may affect fatigue accumulation to more accurately capture the fatigue accumulation characteristics of the unit during the simulation operation, and a second evaluation result is generated. For example, the material properties, fatigue states of different components, and the distribution of fatigue accumulation, etc. Based on the second evaluation result, the first fatigue accumulation prediction result is updated and optimized to generate a second fatigue accumulation prediction result, which is more accurate than the first prediction result.

[0038] In a possible implementation, step S600 further includes step S610 of performing dynamic impact monitoring and analysis on the target hydropower unit to obtain a dynamic impact data set, where the dynamic impact data set includes material change impact data and operating condition change impact data. Real-time monitoring and analysis of various dynamic factors during the operation of the target hydropower unit are carried out to obtain a data set reflecting the change of the unit's operating state, constituting the dynamic impact data set, including changes in material properties, changes in operating conditions, etc. Among them, the material change impact data reflects the change of the material properties of the target hydropower unit during operation, including material aging, crack propagation of the material, and change in material hardness, etc.; the operating condition change impact data reflects the operating state of the target hydropower unit under different operating conditions, including vibration characteristics under different loads, the impact of flow rate change on the unit performance, the impact of temperature fluctuation on the unit stability, etc. It further includes step S620 of performing a secondary fatigue assessment on the simulated operation result based on the material change impact data and the operating condition change impact data through the preset fatigue accumulation mechanism to generate a second assessment result. It further includes step S630 of traversing and comparing and correcting the second assessment result with the first assessment result to obtain a fatigue accumulation update rate and fatigue accumulation potential risk points. Comparing and correcting the second assessment result with the first assessment result includes comparing evaluation indicators, numerical magnitudes, change trends, etc., eliminating or reducing the error between the two assessment results, improving the accuracy of the assessment, and further obtaining the fatigue accumulation update rate and fatigue accumulation potential risk points. The fatigue accumulation update rate refers to calculating the change rate of the fatigue accumulation amount between different time points to judge whether the fatigue state of the unit is deteriorating rapidly or slowing down; the fatigue accumulation potential risk point refers to the part or condition where the fatigue accumulation of the unit may accelerate or suddenly increase during operation, for example, weak links in the unit structure, unreasonable setting of operating parameters, negative impacts of environmental factors, etc. It further includes step S640 of updating the first fatigue accumulation prediction result based on the fatigue accumulation update rate and the fatigue accumulation potential risk points to generate the second fatigue accumulation prediction result. Updating and optimizing the first fatigue accumulation prediction result according to the fatigue accumulation update rate and the fatigue accumulation potential risk points to generate the second fatigue accumulation prediction result, improving the accuracy and reliability of the future fatigue accumulation prediction of the target hydropower unit, and ensuring the safe and stable operation of the target hydropower unit.

[0039] In the foregoing, reference is made to Figure 1 The method for predicting fatigue accumulation of a hydropower unit based on holographic perception according to an embodiment of the present invention is described in detail. Next, reference will be made to Figure 2 Describe a system for predicting fatigue accumulation of a hydropower unit based on holographic perception according to an embodiment of the present invention.

[0040] A hydro-generator unit fatigue accumulation prediction system based on holographic perception according to an embodiment of the present invention is used to solve the technical problem that it is difficult to obtain sufficient and accurate operation data of giant hydro-generator units in the existing fatigue accumulation prediction of hydro-generator units, resulting in large errors in the fatigue accumulation prediction results, and achieves the technical effect of improving the accuracy and reliability of the fatigue accumulation prediction of hydro-generator units. The hydro-generator unit fatigue accumulation prediction system based on holographic perception includes: a hydro-generator unit real-time perception module 10, a key feature extraction module 20, a fatigue accumulation prediction model construction module 30, a hydro-generator unit fatigue evaluation module 40, and a second prediction result acquisition module 50.

[0041] The hydro-generator unit real-time perception module 10 is configured to use a holographic sensor array to perform real-time perception on a target hydro-generator unit and obtain a real-time operation status data set.

[0042] The key feature extraction module 20 is configured to perform data preprocessing on the real-time operation status data set to obtain an operation data processing information set, traverse the operation data processing information set for fatigue feature identification, and extract fatigue accumulation key features according to the identification results.

[0043] The fatigue accumulation prediction model construction module 30 is configured to perform digital twin modeling according to the fatigue accumulation key features and construct a fatigue accumulation prediction model of the target hydro-generator unit.

[0044] The hydro-generator unit fatigue evaluation module 40 is configured to perform simulation operation of the target hydro-generator unit based on the fatigue accumulation prediction model, perform fatigue evaluation on the simulation operation results according to a preset fatigue accumulation mechanism, perform fatigue accumulation prediction on the target hydro-generator unit according to the first evaluation result, and output a first fatigue accumulation prediction result.

[0045] The second prediction result acquisition module 50 is configured to perform secondary fatigue evaluation on the simulation operation results through the preset fatigue accumulation mechanism, generate a second evaluation result, update the first fatigue accumulation prediction result based on the second evaluation result, and obtain a second fatigue accumulation prediction result.

[0046] Next, the specific configuration of the real-time perception module 10 of the hydropower unit will be described in detail. The real-time perception module 10 of the hydropower unit may further include: determining the array layout parameters based on the operating scenario of the target hydropower unit; constructing the holographic sensor array, arranging the holographic sensor array according to the array layout parameters, and performing a holographic perception test to obtain a perception test result; adjusting the holographic sensor array according to the perception test result, performing multi-dimensional perception on the target hydropower unit based on the adjustment information, and obtaining multi-dimensional operating perception information; integrating the multi-dimensional operating perception information for real-time update to generate the real-time operating state data set.

[0047] Next, the specific configuration of the key feature extraction module 20 will be described in detail. The key feature extraction module 20 further includes: retrieving the historical operation fatigue data record file, traversing the operation data processing information set and matching it with the historical operation fatigue data record file to generate a matching data set, where the matching data set contains fatigue features; determining multiple fatigue degree data of the operation data processing information set based on the fatigue features; dividing multiple fatigue levels according to the multiple fatigue degree data; and identifying multiple fatigue features of the operation data processing information set based on the multiple fatigue levels to obtain the identification result.

[0048] Next, the specific configuration of the fatigue accumulation prediction model construction module 30 will be described in detail. The fatigue accumulation prediction model construction module 30 may further include: dividing the operation data processing information set according to the prediction time scale based on the key features of fatigue accumulation to generate a training data set, a supervision data set, and a verification data set; training the fatigue accumulation prediction model based on the digital twin technology through the training data set and the supervision data set; verifying and evaluating the output result of the fatigue accumulation prediction model according to the verification data set, and iteratively optimizing the fatigue accumulation prediction model according to the evaluation result. When the continuous iteration times meet the preset requirements, it is regarded as convergence, and the fatigue accumulation prediction model is output.

[0049] Next, the specific configuration of the hydropower unit fatigue assessment module 40 will be described in detail. The hydropower unit fatigue assessment module 40 may further include: setting simulated operating conditions for the target hydropower unit, where the simulated operating conditions include a simulated operating environment, a simulated workload, and a simulated operating time; based on the simulated operating environment, starting the fatigue accumulation prediction model to perform a simulated operation of the target hydropower unit according to the simulated workload, determining whether the simulated operation duration reaches the simulated operating time, and when it reaches the simulated operating time, generating a stop instruction, stopping the simulated operation according to the stop instruction, and generating a simulated operation result; setting a fatigue accumulation index based on the simulated operation result, constructing the preset fatigue accumulation mechanism according to the fatigue accumulation index, performing a fatigue accumulation trend analysis on the target hydropower unit through the preset fatigue accumulation mechanism, and generating a fatigue accumulation rate; performing a fatigue assessment according to the fatigue accumulation rate to generate the first assessment result.

[0050] Next, the specific configuration of the hydropower unit fatigue assessment module 40 will be further described in detail. The hydropower unit fatigue assessment module 40 may further include: extracting the fatigue accumulation trend using the first assessment result, and drawing a fatigue accumulation trend graph according to the fatigue accumulation trend; retrieving the historical operation data of the target unit, and setting a fatigue prediction value based on the fatigue accumulation trend graph; performing a fatigue accumulation prediction according to the fatigue prediction value to obtain a fatigue accumulation prediction trend graph; and outputting the first fatigue accumulation prediction result of the target hydropower unit according to the fatigue accumulation prediction trend graph.

[0051] Next, the specific configuration of the second prediction result acquisition module 50 will be described in detail. The second prediction result acquisition module 50 may further include: performing dynamic impact monitoring and analysis based on the target hydropower unit to obtain a dynamic impact data set, where the dynamic impact data set includes material change impact data and operating condition change impact data; performing a secondary fatigue assessment on the simulated operation result based on the material change impact data and the operating condition change impact data through the preset fatigue accumulation mechanism to generate a second assessment result; traversing and comparing and correcting the second assessment result with the first assessment result to obtain a fatigue accumulation update rate and a fatigue accumulation potential risk point; and updating the first fatigue accumulation prediction result based on the fatigue accumulation update rate and the fatigue accumulation potential risk point to generate the second fatigue accumulation prediction result.

[0052] The hydropower unit fatigue accumulation prediction system based on holographic perception provided by the embodiments of the present invention can execute the hydropower unit fatigue accumulation prediction method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0053] Although this application makes various references to certain modules in the system according to the embodiments of this application, however, any number of different modules can be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and are not used to limit the protection scope of the present invention.

[0054] The above specific implementation manners do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A fatigue accumulation prediction method for hydropower units based on holographic perception, characterized in that: The method comprises: Use holographic sensor arrays to perceive the target hydropower units in real time and obtain real-time operating status data sets; Performing data preprocessing on the real-time operation status data set to obtain an operation data processing information set; Traversing the operation data processing information set to identify fatigue features, and extracting fatigue accumulation key features according to the identification results; Digital twin modeling is performed based on the key characteristics of fatigue accumulation to build a fatigue accumulation prediction model for the target hydropower unit; Performing a simulated operation of a target hydropower unit based on the fatigue accumulation prediction model, performing fatigue evaluation on the simulated operation result according to a preset fatigue accumulation mechanism, performing fatigue accumulation prediction on the target hydropower unit according to a first evaluation result, and outputting a first fatigue accumulation prediction result; Performing a secondary fatigue evaluation on the simulation operation result by using the preset fatigue accumulation mechanism to generate a second evaluation result, updating the first fatigue accumulation prediction result based on the second evaluation result, and obtaining a second fatigue accumulation prediction result; Based on the fatigue accumulation prediction model, simulated operation of the target hydropower unit is performed, and fatigue evaluation is performed on the simulated operation result according to the preset fatigue accumulation mechanism, the method comprising: Setting simulated operating conditions for the target hydropower unit, wherein the simulated operating conditions include a simulated operating environment, a simulated workload, and a simulated operating time; Based on the simulated operation environment, the fatigue accumulation prediction model is started to perform simulated operation of the target hydropower unit according to the simulated workload, and it is determined whether the simulated operation time reaches the simulated operation time. When the simulated operation time is reached, a stop instruction is generated, and the simulated operation is stopped according to the stop instruction, and a simulated operation result is generated; Based on the simulation operation result, a fatigue accumulation index is set, and the preset fatigue accumulation mechanism is constructed according to the fatigue accumulation index, and fatigue accumulation trend analysis is performed on the target hydropower unit through the preset fatigue accumulation mechanism to generate a fatigue accumulation rate; Perform fatigue assessment according to the fatigue accumulation rate to generate the first assessment result; According to the first evaluation result, fatigue accumulation prediction is performed on the target hydropower unit, and a first fatigue accumulation prediction result is output. The method includes: extracting a fatigue accumulation trend using the first evaluation result, and drawing a fatigue accumulation trend graph according to the fatigue accumulation trend; Retrieving historical operating data of the target unit and setting a fatigue prediction value based on the fatigue accumulation trend graph; Perform fatigue accumulation prediction according to the fatigue prediction value, and obtain a fatigue accumulation prediction trend graph; Outputting the first fatigue accumulation prediction result of the target hydropower unit according to the fatigue accumulation prediction trend graph; The method includes: performing a secondary fatigue evaluation on the simulation operation result by using the preset fatigue accumulation mechanism to generate a second evaluation result; updating the first fatigue accumulation prediction result based on the second evaluation result; and obtaining a second fatigue accumulation prediction result. Perform dynamic impact monitoring and analysis based on the target hydropower unit to obtain a dynamic impact data set, wherein the dynamic impact data set includes material change impact data and operating condition change impact data; Performing a secondary fatigue evaluation on the simulation operation result based on the material change impact data and the operating condition change impact data through the preset fatigue accumulation mechanism to generate a second evaluation result; Traversing the second evaluation result and comparing and correcting it with the first evaluation result to obtain fatigue accumulation update rate and fatigue accumulation potential risk points; The first fatigue accumulation prediction result is updated based on the fatigue accumulation update rate and the fatigue accumulation potential risk point to generate the second fatigue accumulation prediction result.

2. The method for predicting fatigue accumulation of a hydropower unit based on holographic perception according to claim 1 is characterized in that: The holographic sensor array is used to sense the target hydropower unit in real time and obtain the real-time operation status data set. The method includes: Determine array layout parameters based on the operating scenario of the target hydropower unit; Constructing the holographic sensor array, laying out the holographic sensor array according to the array layout parameters, and performing a holographic perception test to obtain a perception test result; Adjusting the holographic sensor array according to the perception test result, performing multi-dimensional perception on the target hydropower unit based on the adjustment information, and acquiring multi-dimensional operation perception information; The multi-dimensional operation perception information is integrated for real-time updating to generate the real-time operation status data set.

3. The method for predicting fatigue accumulation of a hydropower unit based on holographic perception according to claim 1 is characterized in that: Traversing the operation data processing information set to identify fatigue features, and extracting fatigue accumulation key features according to the identification results, the method includes: Retrieving a historical operation fatigue data record file, traversing the operation data processing information set and matching it with the historical operation fatigue data record file to generate a matching data set, wherein the matching data set includes fatigue characteristics; determining a plurality of fatigue degree data of the operation data processing information set based on the fatigue characteristics; Dividing a plurality of fatigue levels according to the plurality of fatigue degree data; A plurality of fatigue features of the operation data processing information set are identified based on the plurality of fatigue levels to obtain the identification result.

4. The method for predicting fatigue accumulation of a hydropower unit based on holographic perception according to claim 1 is characterized in that: Digital twin modeling is performed according to the key characteristics of fatigue accumulation to build a fatigue accumulation prediction model for the target hydropower unit, and the method includes: Based on the fatigue accumulation key features, the operation data processing information set is divided according to the prediction time scale to generate a training data set, a supervision data set, and a verification data set; Using the training data set and the supervision data set, the fatigue accumulation prediction model is trained based on the digital twin technology; The output result of the fatigue accumulation prediction model is verified and evaluated according to the verification data set, and the fatigue accumulation prediction model is iteratively optimized according to the evaluation result. When the number of consecutive iterations meets the preset requirements, it is regarded as convergence and the fatigue accumulation prediction model is output.

5. The fatigue accumulation prediction system of hydropower units based on holographic perception is characterized by: The system is used to implement the fatigue accumulation prediction method of a hydropower unit based on holographic perception according to any one of claims 1 to 4, and the system comprises: A real-time sensing module for a hydropower unit, wherein the real-time sensing module for a hydropower unit is used to sense a target hydropower unit in real time by using a holographic sensor array to obtain a real-time operating status data set; A key feature extraction module, the key feature extraction module is used to perform data preprocessing on the real-time operation status data set to obtain an operation data processing information set, traverse the operation data processing information set to perform fatigue feature identification, and extract fatigue accumulation key features according to the identification results; A fatigue accumulation prediction model building module, wherein the fatigue accumulation prediction model building module is used to perform digital twin modeling according to the fatigue accumulation key features to build a fatigue accumulation prediction model of a target hydropower unit; A hydropower unit fatigue assessment module, the hydropower unit fatigue assessment module is used to simulate the operation of the target hydropower unit based on the fatigue accumulation prediction model, perform fatigue assessment on the simulation operation result according to a preset fatigue accumulation mechanism, perform fatigue accumulation prediction on the target hydropower unit according to the first assessment result, and output a first fatigue accumulation prediction result; A second fatigue accumulation prediction result acquisition module, the second fatigue accumulation prediction result acquisition module is used to perform a secondary fatigue evaluation on the simulation operation result through the preset fatigue accumulation mechanism, generate a second evaluation result, update the first fatigue accumulation prediction result based on the second evaluation result, and obtain a second fatigue accumulation prediction result; The fatigue assessment module of the hydropower unit further includes: setting simulated operation conditions for the target hydropower unit, wherein the simulated operation conditions include simulated operation environment, simulated workload, and simulated operation time; based on the simulated operation environment, starting the fatigue accumulation prediction model to perform simulated operation of the target hydropower unit according to the simulated workload, judging whether the simulated operation time reaches the simulated operation time, generating a stop instruction when the simulated operation time is reached, stopping the simulated operation according to the stop instruction, and generating a simulated operation result; setting a fatigue accumulation index based on the simulated operation result, constructing the preset fatigue accumulation mechanism according to the fatigue accumulation index, performing fatigue accumulation trend analysis on the target hydropower unit through the preset fatigue accumulation mechanism, and generating a fatigue accumulation rate; performing fatigue assessment according to the fatigue accumulation rate, and generating the first assessment result; Extracting fatigue accumulation trend by using the first evaluation result, and drawing fatigue accumulation trend graph according to the fatigue accumulation trend; retrieving historical operation data of the target unit, and setting fatigue prediction value based on the fatigue accumulation trend graph; performing fatigue accumulation prediction according to the fatigue prediction value, and obtaining fatigue accumulation prediction trend graph; outputting the first fatigue accumulation prediction result of the target hydropower unit according to the fatigue accumulation prediction trend graph; The second prediction result acquisition module further includes: performing dynamic impact monitoring and analysis based on the target hydropower unit to obtain a dynamic impact data set, wherein the dynamic impact data set includes material change impact data and operating condition change impact data; performing a secondary fatigue assessment on the simulation operation result based on the material change impact data and the operating condition change impact data through the preset fatigue accumulation mechanism to generate a second assessment result; traversing the second assessment result and comparing and correcting it with the first assessment result to obtain a fatigue accumulation update rate and fatigue accumulation potential risk points; updating the first fatigue accumulation prediction result based on the fatigue accumulation update rate and the fatigue accumulation potential risk points to generate a second fatigue accumulation prediction result.

Images