Method and device for identifying risk information of hydroelectric power generation equipment

Abstract

The invention provides a risk information identification method and device for hydroelectric power generation equipment. The method comprises the following steps: determining a multi-dimensional effective feature set of the hydroelectric power generation equipment through multi-dimensional operation data of the hydroelectric power generation equipment in an operation process; further determining a running state track of the hydroelectric power generation equipment in a state transition process and a state evolution trend of the hydroelectric power generation equipment in a performance evolution process, and determining a space-time risk situation of the hydroelectric power generation equipment through the running state track and the state evolution trend; determining the risk influence characteristics of each component in the hydroelectric power generation equipment in the operation process, and determining the risk assessment level of each component under the coupling effect according to the space-time risk situation and all the risk influence characteristics; and dynamically identifying the operation risk of the hydroelectric power generation equipment in the operation process according to all the risk assessment levels. By adopting the scheme of the invention, the risk of the hydroelectric power generation equipment can be dynamically tracked based on the coupling effect among the components in the hydroelectric power generation equipment.

Description

Technical Field

[0001] This application relates to the field of risk information identification technology, and more specifically, to a method and apparatus for identifying risk information in hydropower equipment. Background Technology

[0002] Risk information identification is the first step in a risk management system. It refers to the process of proactively identifying potential or existing risks and their characteristics (such as risk sources, scope of impact, probability of occurrence, and evolution patterns) in a system, equipment, process, or environment by systematically collecting, analyzing, and evaluating relevant information.

[0003] As hydropower equipment upgrades towards larger capacity and higher parameters, the coupling relationship between its internal mechanical structure and the external hydrological environment becomes increasingly complex. During long-term operation, the equipment is subjected to the continuous effects of internal physical processes such as fatigue vibration of the turbine blades and wear of the main shaft system, as well as dynamic interference from external factors such as fluctuations in inflow and water temperature stratification in the reservoir area. Currently, risk monitoring in the industry mostly relies on real-time monitoring of single parameters (such as vibration amplitude and oil temperature), which makes it difficult to capture the gradual deterioration of equipment performance over time and to quantify the impact of the interaction of multiple internal and external factors on the safety boundary of the equipment. This results in risk warnings often lagging behind the actual failure evolution process. Therefore, how to dynamically track the risks of hydropower equipment based on the coupling effect between various components in the equipment has become a problem faced by the industry. Summary of the Invention

[0004] This application provides a method and apparatus for identifying risk information of hydropower equipment, which can dynamically track the risks of hydropower equipment based on the coupling effect between various components in the hydropower equipment.

[0005] In a first aspect, this application provides a method for identifying risk information of hydropower equipment, wherein the hydropower equipment includes multiple components, and the method includes the following steps: Collect multi-dimensional operational data of hydropower equipment during operation, wherein the multi-dimensional operational data includes operational status data, environmental impact data, and operational status data of the hydropower equipment; Extract the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operational data; Based on the multi-dimensional effective feature set and the historical multi-dimensional operation data of the hydropower equipment, the operation state trajectory of the hydropower equipment during the state transition process and the state evolution trend of the hydropower equipment during the performance evolution process are determined. Through the operation state trajectory and the state evolution trend, the spatiotemporal correlation analysis of the operation risk of the hydropower equipment within a preset time period is performed to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. The risk impact characteristics of each component in the hydropower equipment during operation are determined. Based on the spatiotemporal risk situation and all risk impact characteristics, a multi-dimensional correlation analysis is conducted on the risk status of each component in the hydropower equipment to obtain the risk assessment level of each component under the coupling effect. The operational risks of the hydropower equipment during operation are dynamically identified based on all risk assessment levels.

[0006] In some embodiments, extracting the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operational data specifically includes: The multi-dimensional operational data is subjected to noise removal to obtain noise-removed multi-dimensional operational data. The noise-removed multi-dimensional running data is subjected to categorical feature extraction to obtain multi-dimensional feature data of each type; Feature filtering is performed on all multi-dimensional feature data to obtain the multi-dimensional effective feature set of the hydropower equipment.

[0007] In some embodiments, determining the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend during the performance evolution process of the hydropower equipment based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment specifically includes: Obtain historical multi-dimensional operating data of the hydroelectric power generation equipment; Extract the historical state feature set of the hydropower equipment's state transition and the historical performance feature set of the equipment's performance from the historical multi-dimensional operational data; The operating state trajectory of the hydropower equipment during the state transition process is determined based on the historical state feature set and the multi-dimensional effective feature set. The state evolution trend of the hydropower equipment's performance evolution process is determined based on the historical performance feature set and the multi-dimensional effective feature set.

[0008] In some embodiments, the spatiotemporal correlation analysis of the operational risk of the hydropower equipment within a preset time period is performed using the operational state trajectory and the state evolution trend to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period, specifically including: Determine the preset time period; The preset time period is divided into multiple time windows; The hydroelectric power generation equipment is divided into multiple spatial units; Calculate the time risk index of each spatial unit in each time window based on the operational status trajectory and the state evolution trend; By performing correlation analysis on all time risk indices, the spatiotemporal risk situation of the hydropower equipment in the spatiotemporal distribution assessment of risk within a preset time period is obtained.

[0009] In some embodiments, determining the risk impact characteristics of each component in the hydroelectric power generation equipment during operation specifically includes: Select one component from the hydroelectric power generation equipment as the selected component, and obtain the performance parameters of the selected component during operation; Based on the performance parameters, determine the performance impact characteristics of the selected component during the operation of the hydropower equipment; Based on the performance impact characteristics, determine the risk impact characteristics of selected components in the hydropower equipment during operation; Continue to determine the risk impact characteristics of the remaining components in the hydroelectric power generation equipment during operation.

[0010] In some embodiments, a multi-dimensional correlation analysis is performed on the risk status of each component in the hydropower equipment based on the spatiotemporal risk situation and all risk impact characteristics to obtain the risk assessment level of each component under coupling effects, specifically including: Risk correlation analysis is performed on each risk impact characteristic to obtain the risk correlation degree of each component; Select a component as the selected component, and determine the initial risk value of the selected component based on the spatiotemporal risk situation and the risk correlation degree of the selected component; Obtain the structural diagram of the hydroelectric power generation equipment; The initial risk value is corrected based on the structural diagram to obtain the component risk value; The risk assessment level of the selected component under coupling effect is determined by the risk value of the component. Continue to determine the risk assessment level of the remaining components under coupling effects.

[0011] In some embodiments, the dynamic identification of operational risks of the hydropower equipment during operation based on all risk assessment levels specifically includes: Obtain a risk identification system for the hydropower equipment during operation; Based on the risk identification system, the risk assessment levels of each risk are identified to obtain the operational risk status of the hydropower equipment during operation.

[0012] Secondly, this application provides a risk information identification device for hydropower equipment, comprising: The data acquisition module is used to collect multi-dimensional operational data of the hydropower equipment during operation. The multi-dimensional operational data includes the operating status data, environmental impact data, and operational status data of the hydropower equipment. The processing module is used to extract the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operating data; The processing module is further configured to determine the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend during the performance evolution process of the hydropower equipment based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment. Through the operating state trajectory and the state evolution trend, the module performs spatiotemporal correlation analysis on the operating risk of the hydropower equipment within a preset time period to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. The processing module is also used to determine the risk impact characteristics of each component in the hydropower equipment during operation, and to perform multi-dimensional correlation analysis on the risk status of each component in the hydropower equipment based on the spatiotemporal risk situation and all risk impact characteristics, so as to obtain the risk assessment level of each component under the coupling effect. The execution module is used to dynamically identify the operational risks of the hydropower equipment during operation based on all risk assessment levels.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described method for identifying risk information of hydropower equipment.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for identifying risk information of hydropower equipment.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The method and apparatus for identifying risk information of hydropower equipment provided in this application first collect multi-dimensional operational data of the hydropower equipment during operation. This multi-dimensional operational data includes operational status data, environmental impact data, and operational status data of the hydropower equipment. A multi-dimensional effective feature set of the hydropower equipment is extracted from the multi-dimensional operational data. Based on the multi-dimensional effective feature set and the historical multi-dimensional operational data of the hydropower equipment, the operational status trajectory of the hydropower equipment during state transition and the state evolution trend during the performance evolution process are determined. The operational risk of the hydropower equipment within a preset time period is analyzed using the operational status trajectory and the state evolution trend to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. The risk impact characteristics of each component in the hydropower equipment during operation are determined. Based on the spatiotemporal risk situation and all risk impact characteristics, the risk status of each component in the hydropower equipment is analyzed using multi-dimensional correlation to obtain the risk assessment level of each component under coupling effects. The operational risk of the hydropower equipment during operation is dynamically identified based on all risk assessment levels.

[0016] Therefore, in the process of identifying risk information for hydropower equipment, this application firstly collects multi-dimensional operational data including equipment operating status, environmental impact, and operational status, comprehensively covering key influencing factors related to the coupling effects of various components, and avoiding the omission of coupling risk information due to the lack of single-dimensional data; secondly, it extracts effective feature sets from multiple dimensions and combines them with historical multi-dimensional operational data to construct the operational status trajectory of the equipment's state transition process and the state evolution trend of the performance evolution process, providing data support for dynamically capturing the risk change patterns in the component coupling process; thirdly, based on the operational status trajectory and state evolution trend, it conducts a risk spatiotemporal correlation analysis within a preset time period to identify the risk of each component in the spatiotemporal dimension. The coupling effect between components leads to the transmission and superposition of risks, forming a precise spatiotemporal risk situation. Subsequently, a multi-dimensional correlation analysis is conducted between the spatiotemporal risk situation and the risk impact characteristics of each component to identify the risk interaction effects of each component under the coupling effect and determine the risk assessment level of each component. Finally, dynamic identification of equipment operation risks is achieved through all risk assessment levels. This solves the problem of risk tracking lag and assessment bias caused by the difficulty of considering the coupling effect between components in traditional methods, improves the real-time, accuracy, and comprehensiveness of risk identification for hydropower equipment, provides a reliable technical basis for equipment safety operation monitoring and maintenance strategy formulation, reduces the probability of equipment failure caused by coupling risks, and ensures the stable operation of the power generation system. Using the scheme in this application, the risks of hydropower equipment can be dynamically tracked based on the coupling effect between various components in the hydropower equipment. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of a method for identifying risk information of hydropower equipment according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of a multi-dimensional effective feature set according to some embodiments of this application; Figure 3 This is an exemplary flowchart illustrating the determination of risk impact characteristics according to some embodiments of this application; Figure 4 This is a structural schematic diagram of a risk information identification device for hydropower equipment according to some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing a method for identifying risk information of hydropower equipment, according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1 The figure is an exemplary flowchart of a method for identifying risk information of hydropower equipment according to some embodiments of this application. The method for identifying risk information of hydropower equipment mainly includes the following steps: In some embodiments, the hydropower generation equipment includes multiple components, each of which specifically includes: a water intake component responsible for receiving and guiding water flow; a core power component that realizes the conversion of water energy into mechanical energy; a power generation component that converts mechanical energy into electrical energy; a power transformation and control component that ensures the safe output of electrical energy; an auxiliary component that maintains the stable operation of the equipment; and an automation component that realizes overall monitoring and operation. These components work together to complete the entire process of hydropower generation.

[0020] In step 101, multi-dimensional operational data of the hydropower equipment during operation is collected, including operational status data, environmental impact data, and operational status data of the hydropower equipment.

[0021] It should be noted that the operational status data in this application specifically includes the turbine's rotational speed, main shaft vibration acceleration, guide vane opening, flow rate, and inlet / outlet pressure; the generator's terminal voltage, stator / rotor current, and active / reactive power; the transformer's oil temperature and insulation resistance; and data such as bearing temperature and seal leakage. This operational status data represents the physical state and operating parameters of each component of the equipment during the process of converting water energy into mechanical energy and then into electrical energy, reflecting the equipment's own health status, the operational stability of core components, and energy conversion efficiency. Environmental impact data specifically includes the reservoir's water level, water temperature, sediment content, water pH value, and the plant's... The surrounding environmental data, such as temperature, humidity, wind speed, rainfall, earthquake intensity, and flood warning level, represent the objective conditions of the external environment in which the equipment operates, reflecting the potential interference and damage risks to the equipment. The operational status data specifically includes start / stop commands from maintenance personnel, load adjustment range, maintenance records, as well as records of the action of protection devices in the automatic control system and records of PID parameter adjustments in the speed control system. The operational status data represents the intervention behavior and parameter settings of human or automatic systems on the equipment operation, reflecting the rationality and standardization of the intervention and its impact on the equipment's operating status.

[0022] In step 102, the multi-dimensional effective feature set of the hydropower generation equipment is extracted from the multi-dimensional operating data.

[0023] In some embodiments, reference Figure 2 As shown, this figure is an exemplary flowchart of determining a multi-dimensional effective feature set in some embodiments of this application. In this embodiment, the extraction of the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operational data can be achieved by the following steps: First, in step 1021, noise is removed from the multi-dimensional operational data to obtain noise-removed multi-dimensional operational data; Secondly, in step 1022, the multi-dimensional running data after noise removal is subjected to categorized feature extraction to obtain multi-dimensional feature data of each type; Finally, in step 1023, feature filtering is performed on all the multi-dimensional feature data to obtain the multi-dimensional effective feature set of the hydropower generation equipment.

[0024] In specific implementation, noise removal is performed on the multi-dimensional operational data to obtain the noise-removed multi-dimensional operational data. This can be achieved in the following ways: mechanical noise is removed from the operational status data in the multi-dimensional operational data; abnormal jumps are removed from the environmental impact data in the multi-dimensional operational data; and word segmentation and invalid character removal are performed on the operational status data in the multi-dimensional operational data to obtain the noise-removed multi-dimensional operational data. For example, for high-frequency vibration signals in the operational status data, wavelet threshold filtering is used, and the signal is decomposed into 5 levels using the db4 wavelet basis. The high-frequency coefficients obtained from the decomposition are processed with soft thresholding to reconstruct the signal and remove random impact noise in mechanical vibration. For slowly varying data such as temperature and pressure in the environmental impact data, moving average filtering is used, with the window size set to 5-10 sampling points. The mean of the data within the window is used to replace the original value to smooth short-term fluctuations. Other methods can be used for noise removal in other embodiments, which are not limited here.

[0025] In specific implementation, the multi-dimensional operational data after noise removal is subjected to categorized feature extraction to obtain multi-dimensional feature data of each type. This can be achieved in the following way: the multi-dimensional operational data after noise removal is processed according to data attribute differences; time-domain features and frequency-domain features are extracted from the time-series data in the operational status data, such as time-domain features including peak value, peak-to-peak value, variance, and kurtosis; frequency-domain features include performing a fast Fourier transform on the vibration signal, taking 1024 sampling points, and extracting the amplitudes corresponding to the 1st, 2nd, and 3rd harmonics to reflect the harmonic characteristics of the rotating component; trend features and threshold features are extracted from the environmental impact data, such as trend features including using least squares... The multiplication method performs linear fitting on the daily average data, and the slope is calculated to reflect the weekly / monthly trend. Threshold features include the percentage of time when the sand content exceeds 3 kg / m³ and the ambient humidity exceeds 85%. Statistical and correlation features are extracted from the operation status data. For example, statistical features include calculating the monthly start-up and shutdown frequency and the average maintenance interval. Correlation features include the number of load adjustments within one hour before the protection device is activated. All the features obtained above are used as multi-dimensional feature data of the corresponding type. The multi-dimensional feature data represents the feature information of various types of data during equipment operation. Other extraction methods can be used in other embodiments, which are not limited here.

[0026] In specific implementation, feature filtering is performed on all multi-dimensional feature data to obtain the effective multi-dimensional feature set of the hydropower equipment. This can be achieved in the following way: Historical fault records of the hydropower equipment are obtained, where historical fault records represent records of faults occurring in the hydropower equipment. The correlation coefficient between each multi-dimensional feature data and the historical fault records is calculated, for example, using the Pearson correlation coefficient. Features with an absolute correlation coefficient ≥ 0.5 are retained. Choosing 0.5 as a threshold essentially filters out features with moderate or higher correlation. This threshold avoids being too stringent (e.g., using 0.8 would miss a large number of moderately correlated features associated with latent faults, such as the change rate of turbine guide vane opening and efficiency reduction faults). The correlation coefficient is usually between 0.55 and 0.65, which avoids being too lenient (e.g., taking 0.3 would retain a large number of weakly correlated redundant features, such as the correlation coefficient between ambient humidity and generator stator faults, which is about 0.35, but actually contributes very little to fault identification and increases the amount of calculation instead). Then, low-discrimination features are removed by variance analysis, the variance of each feature is calculated, and features with variance ≤ 0.01 are removed. The size of the variance directly corresponds to the fluctuation range of the feature value. When the variance is 0.01, its standard deviation is 0.1, which means that the fluctuation range of the feature in the interval [0,1] is only about ±0.1, indicating that the value of the feature is in a stable range for a long time with almost no significant change. Finally, all the features obtained after screening are combined into a multi-dimensional effective feature set.

[0027] It should be noted that the multi-dimensional effective feature set in this application represents effective feature information closely related to equipment operation risks, fault states, and performance evolution, and can be used to analyze the operating status of hydropower equipment.

[0028] In step 103, the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend during the performance evolution process of the hydropower equipment are determined based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment. The operating state trajectory and the state evolution trend are used to perform spatiotemporal correlation analysis on the operating risk of the hydropower equipment within a preset time period to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period.

[0029] In some embodiments, determining the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend of the hydropower equipment during the performance evolution process, based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment, can be achieved by the following steps: Obtain historical multi-dimensional operating data of the hydroelectric power generation equipment; Extract the historical state feature set of the hydropower equipment's state transition and the historical performance feature set of the equipment's performance from the historical multi-dimensional operational data; The operating state trajectory of the hydropower equipment during the state transition process is determined based on the historical state feature set and the multi-dimensional effective feature set. The state evolution trend of the hydropower equipment's performance evolution process is determined based on the historical performance feature set and the multi-dimensional effective feature set.

[0030] This includes obtaining historical multi-dimensional operational data of hydropower equipment. For example, operational status data, environmental impact data, and operational status data for the past 3 to 5 years can be retrieved from the time-series database of the equipment operation and maintenance system to obtain historical multi-dimensional operational data of hydropower equipment.

[0031] In specific implementation, extracting the historical state feature set of the hydropower equipment's state transition and the historical performance feature set of the equipment from the historical multi-dimensional operational data can be achieved in the following way: For the historical state feature set, combining historical fault records and the experience of operation and maintenance experts, the equipment state is divided into four levels: normal, slightly abnormal, moderately abnormal, and severely abnormal. Then, features are extracted from the historical operational data corresponding to each level. For example, the vibration signal is extracted using a fast Fourier transform to extract the first and second harmonic amplitudes, and the peak value, variance, and duration ratio of temperature and pressure data are calculated to form the historical state feature set corresponding to each state level. Among these features, the historical state... The state feature set represents the set of equipment characteristics under different operating conditions. For the historical performance feature set, indicators reflecting the long-term performance of the equipment are selected, such as the vibration characteristics corresponding to generator efficiency and turbine runner wear. The monthly average value of the indicator is extracted from the historical multi-dimensional operating data, and the least squares method is used to linearly fit the monthly average data to calculate the fitting slope. At the same time, the number of times the performance indicator exceeds the rated threshold is counted to form the historical performance feature set. The historical performance feature set represents the feature set of long-term performance changes of the equipment, reflecting the decay or stabilization law of equipment performance over time. Other methods can be used to extract the features in other embodiments, which are not limited here.

[0032] In addition, in specific implementation, the determination of the operating state trajectory of the hydropower equipment during the state transition process based on the historical state feature set and the multi-dimensional effective feature set can be achieved in the following way: calculate the Euclidean distance between each feature in the multi-dimensional effective feature set and each level feature in the historical state feature set. The smaller the distance, the higher the similarity. Determine the current state of the equipment. For example, feature matching can be used. Serialize the current states of consecutive time periods in chronological order. At the same time, verify the rationality of the state transition by combining the historical state transition probability matrix. If the current state jumps from normal to severe abnormality and the corresponding transition probability is <1%, it is judged as data fluctuation and needs to be re-matched. For example, the historical state transition probability matrix can be obtained by statistically analyzing the frequency of state transitions from normal to slight abnormality, slight abnormality to moderate abnormality, etc. in historical data. For example, if the probability of normal to slight abnormality is 15%, a continuous operating state trajectory is finally formed. The historical state transition probability matrix represents the matrix of the possibility of transition between different states, reflecting the historical pattern and probability distribution of equipment state transitions.

[0033] It should be noted that the operating status trajectory in this application represents the trajectory of the real-time state sequence of hydropower equipment connected in chronological order, reflecting the dynamic changes of the equipment during the state transition process, and can be used to analyze the operating status of hydropower equipment.

[0034] Furthermore, determining the state evolution trend of the hydropower equipment's performance evolution process based on the historical performance feature set and the multi-dimensional effective feature set can be achieved in the following way: First, select performance-related features from the multi-dimensional effective feature set, such as active power and stator temperature characteristics corresponding to generator efficiency, and compare them with similar features from the historical performance feature set. Fit the change curve of the current feature, for example, a linear regression model can be used, with time as the independent variable and feature value as the dependent variable. Combine the fitting slope from the historical performance feature set to calculate the change rate of the current feature. For example, if the current efficiency decreases by 0.08% per month, determine the direction of performance evolution. If the current rate is greater than the historical average rate, it is an accelerated degradation; if it is close, it is a slow degradation; if it is less than the historical average rate and tends to be stable, it is stable. At the same time, refer to the threshold data from the historical performance feature set to predict whether the feature value will reach the threshold within a preset period in the future, and finally form the state evolution trend of the equipment performance.

[0035] It should be noted that the state evolution trend in this application represents the trend of the long-term change direction and rate of hydropower equipment performance, reflecting the future evolution trend of equipment performance, and can be used to predict and analyze the performance state of hydropower equipment.

[0036] In some embodiments, the spatiotemporal correlation analysis of the operational risk of the hydropower equipment within a preset time period using the operational state trajectory and the state evolution trend can be performed to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. This can be achieved through the following steps: Determine the preset time period; The preset time period is divided into multiple time windows; The hydroelectric power generation equipment is divided into multiple spatial units; Calculate the time risk index of each spatial unit in each time window based on the operational status trajectory and the state evolution trend; By performing correlation analysis on all time risk indices, the spatiotemporal risk situation of the hydropower equipment in the spatiotemporal distribution assessment of risk within a preset time period is obtained.

[0037] In practical implementation, when determining the preset time period, the commonly used industry standard of 7 days or 30 days is selected based on the operation and maintenance cycle of hydropower equipment and the needs of risk early warning. For example, for the high-incidence period of equipment failure during the flood season, the preset time period is set to 7 days to improve the speed of early warning response. At the same time, the start time of the time period is clearly defined as the current time, and the end time is the current time plus the preset duration. When dividing the preset time period into multiple time windows, the granularity of the window is determined based on the data update frequency of the multi-dimensional effective feature set: if the component's operating data is updated every 10 minutes, the corresponding time window is set to 10 minutes / window; if the component's data is updated every hour, the corresponding time window is set to 1 hour / window, ensuring that complete component operating feature data can be obtained within each window. When dividing the hydropower equipment into multiple spatial units, it is split according to the equipment's functional structure and the scope of risk impact, specifically divided into water diversion system unit, turbine unit, generator unit, substation unit, and auxiliary system unit. Each spatial unit clearly corresponds to specific components and associated operating feature data.

[0038] In addition, in specific implementation, the time risk index of each spatial unit in each time window can be calculated based on the operational status trajectory and the state evolution trend in the following manner: First, assign a value to the operational status level of each spatial unit, such as 1 point for normal state, 3 points for slight abnormality, 5 points for moderate abnormality, and 7 points for severe abnormality. Extract the status level of the spatial unit in the corresponding time window from the operational status trajectory and obtain the base score; then, determine the performance impact coefficient in combination with the state evolution trend. If the performance of the spatial unit is accelerating its degradation, the performance impact coefficient is 1.2; if it is slowly degrading, the performance impact coefficient is 1.0; if the performance is stable, the performance impact coefficient is 0.8; finally, calculate the performance impact coefficient by weighted summation. The time risk index can be calculated using the formula: Time Risk Index = Base Score × Performance Impact Coefficient × Component Importance Weight. The component importance weight can be determined using the Analytic Hierarchy Process (AHP), such as by constructing a component importance judgment matrix, performing a consistency check (CR < 0.1), and calculating a weight vector to obtain the component importance weight. This yields the time risk index for each spatial unit in each time window. The time risk index represents the immediate risk level of the spatial unit within the corresponding time window, reflecting that the turbine is in a medium to high risk state during that period. It also reflects that the accelerated performance degradation further amplifies the risk level. Other methods can be used to calculate the risk in other embodiments, which are not limited here.

[0039] Furthermore, in practical implementation, the spatiotemporal risk situation of the hydropower equipment in the risk spatiotemporal distribution assessment within a preset time period can be obtained by performing correlation analysis on all time risk indices, as follows: First, correlate all time risk indices along the time dimension. For each spatial unit, concatenate its time risk indices sequentially according to time windows, and smooth the time risk index curves, such as using a moving average method for smoothing. Identify the time nodes where the time risk index continuously rises, such as the time risk index of the water diversion system unit rising from 2.1 to 4.5 in the 12th-15th time windows. Then, correlate them along the spatial dimension. Within each time window, compare the time risk indices of each spatial unit, and mark the spatial units with indices ≥5. Simultaneously, considering the coupling relationships between components, such as the coupling coefficient of 0.8 between the turbine unit and the generator unit, the risk transmission value from the high-risk unit to the associated unit is calculated. For example, if the turbine unit index is 5.2 in a certain time window, its transmission value to the generator unit is 5.2 × 0.8 = 4.16. Finally, the spatiotemporal correlation results are integrated and visualized using a heatmap. The horizontal axis represents the time window sequence, and the vertical axis represents the spatial unit. The darker the color, the higher the risk index. Key risk information is also marked. For example, in the 20th-25th time window, the turbine unit risk index is ≥5.5, and the risk transmission value to the generator unit exceeds 4.0, forming a spatiotemporal risk situation within a preset time period. Other methods can also be used in other embodiments, which are not limited here.

[0040] It should be noted that the spatiotemporal risk situation in this application represents the spatial distribution pattern, temporal change trend, and risk coupling effect between components of hydropower equipment within a preset time period. It can be used to locate high-risk components and track the trend of risk change over time and the spatial propagation path.

[0041] In step 104, the risk impact characteristics of each component in the hydropower equipment during operation are determined. Based on the spatiotemporal risk situation and all risk impact characteristics, a multi-dimensional correlation analysis is performed on the risk status of each component in the hydropower equipment to obtain the risk assessment level of each component under the coupling effect.

[0042] In some embodiments, reference Figure 3 As shown, this figure is an exemplary flowchart of determining risk impact characteristics in some embodiments of this application. In this embodiment, determining the risk impact characteristics of each component in the hydroelectric power generation equipment during operation can be achieved by the following steps: First, in step 1041, a component of the hydroelectric power generation equipment is selected as the selected component, and the performance parameters of the selected component during operation are obtained; Secondly, in step 1042, the performance impact characteristics of the selected component during the operation of the hydropower equipment are determined based on the performance parameters; Then, in step 1043, the risk impact characteristics of selected components in the hydropower equipment during operation are determined based on the performance impact characteristics; Finally, in step 1044, the risk impact characteristics of the remaining components in the hydroelectric power generation equipment during operation are further determined.

[0043] In practice, the performance parameters of the selected component during operation are obtained. Real-time operating parameters, such as the flow area of ​​the impeller, the pressure difference between the inlet and outlet, the surface wear, and the rotational eccentricity, are collected from the equipment sensor network. Historical performance parameters, such as the annual wear detection data for the past three years and the flow efficiency after overhaul, are retrieved from the operation and maintenance management system. At the same time, rated performance parameters, such as the design flow efficiency of 95% and the maximum allowable wear of 0.5 mm, are extracted from the equipment design manual to obtain the performance parameters of the selected component during operation.

[0044] In addition, in specific implementation, determining the performance impact characteristics of selected components during the operation of the hydropower equipment based on the performance parameters can be achieved in the following way: Analyze the correlation between performance parameters and the overall operating indicators of the hydropower equipment (such as power generation efficiency and unit output). For example, Pearson correlation coefficient can be used for analysis, and parameters with an absolute value of correlation coefficient ≥ 0.6 are retained and defined as key performance parameters. Then, determine the normal fluctuation range of key performance parameters. For example, it can be determined by the 3σ criterion. For example, the normal range of runner wear is 0-0.3mm, and exceeding this range is judged as a performance abnormality. At the same time, analyze the impact of changes in key performance parameters on the overall operating indicators of the hydropower equipment. For example, linear regression can be used for analysis. For example, for every 0.1mm increase in wear, the power generation efficiency decreases by 1.2%. Integrate these to form performance impact characteristics. The performance impact characteristics represent the specific impact relationship of changes in the performance parameters of the hydropower equipment on the component's own function or the core operating indicators of the whole machine. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0045] In addition, in specific implementation, the risk impact characteristics of selected components in the hydropower equipment during operation can be determined based on the performance impact characteristics in the following way: A mapping relationship between performance anomalies and risk associations is constructed by combining historical fault records; the potential fault types corresponding to the performance impact characteristics are analyzed and sorted out. For example, fault tree analysis can be used, such as runner wear exceeding 0.3mm leading to cavitation in the flow components and excessive unit vibration. The frequency of faults caused by this performance anomaly and the downtime caused by the fault in the past 5 years are statistically analyzed, and the probability of fault occurrence and the degree of fault loss are calculated. At the same time, the impact of performance anomalies on related components is analyzed, such as excessive runner vibration leading to increased wear of the main shaft bearing. The degree of impact is quantified using a coupling coefficient (such as a risk coupling coefficient of 0.7 between the runner and the main shaft bearing), and finally, risk impact characteristics are formed. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0046] It should be noted that the risk impact characteristics in this application represent the specific form and severity of component performance abnormalities transforming into actual operational risks, and can be used to reflect the propagation path and coupling effects of risks within the equipment.

[0047] In some embodiments, the risk status of each component in the hydropower equipment is analyzed in a multi-dimensional correlation based on the spatiotemporal risk situation and all risk impact characteristics to obtain the risk assessment level of each component under coupling effects. This can be achieved by the following steps: Risk correlation analysis is performed on each risk impact characteristic to obtain the risk correlation degree of each component; Select a component as the selected component, and determine the initial risk value of the selected component based on the spatiotemporal risk situation and the risk correlation degree of the selected component; Obtain the structural diagram of the hydroelectric power generation equipment; The initial risk value is corrected based on the structural diagram to obtain the component risk value; The risk assessment level of the selected component under coupling effect is determined by the risk value of the component. Continue to determine the risk assessment level of the remaining components under coupling effects.

[0048] In specific implementation, risk correlation analysis is performed on each risk impact characteristic to obtain the risk correlation degree of each component. This can be achieved in the following way: Based on the equipment's historical fault records, the number of co-occurrence faults between any two components is counted, that is, the number of times component B fails simultaneously or within the following 12 hours when component A fails; then, the coupling coefficient of component A to component B is extracted from the risk impact characteristics of component A; the number of co-occurrence faults is multiplied by the coupling coefficient to obtain the weighted co-occurrence count; finally, the ratio of the weighted co-occurrence count to the total number of faults of component A is used as the risk correlation degree of A to B, and the co-occurrence fault ratio of B to A is also counted to form a two-way risk correlation degree matrix, where the matrix elements are the correlation degree values ​​between components, and finally the risk correlation degree of each component is obtained. Here, the risk correlation degree represents the probability and strength of risk transmission between components; other methods can also be used to determine this in other embodiments, which are not limited here.

[0049] In addition, in specific implementation, the initial risk value of the selected component can be determined based on the spatiotemporal risk situation and the risk correlation of the selected component in the following way: extract the average time risk index of the component within a preset time period from the spatiotemporal risk situation, and combine it with the failure probability and failure loss degree in its risk impact characteristics. For example, a weighted summation calculation can be used: Initial risk value = average time risk index × index weight + failure probability × probability weight + failure loss degree × loss weight, to obtain the initial risk value of the selected component, where the initial risk value represents the initial risk level of the component under its own independent operating state; other methods can also be used to determine it in other embodiments, which are not limited here.

[0050] The process involves obtaining a structural diagram of the hydropower equipment, such as a CAD structural diagram of the hydropower equipment, clarifying the physical connections and functional dependencies of each component, and identifying the directly related components of the selected component to obtain the structural diagram of the hydropower equipment. The structural diagram represents the CAD structural relationship diagram of the hydropower equipment, clearly marking the physical connections and functional dependencies of each component, and reflecting the spatial and functional relationship logic between the components.

[0051] In addition, in specific implementation, the initial risk value is corrected according to the structure diagram to obtain the component risk value. This can be achieved in the following way: extract the directly related components of the selected component from the structure diagram; then retrieve the constructed two-way risk correlation matrix to obtain the risk correlation degree of each directly related component to the selected component; then obtain the initial risk value of each directly related component; then calculate the coupling correction value by weighted summation, the formula being: Coupling correction value = Σ(initial risk value of directly related component × risk correlation degree of the component to the selected component); finally, set the coupling influence weight, and complete the correction by component risk value = initial risk value of selected component + coupling correction value × coupling influence weight, and finally obtain the component risk value of the selected component. Here, the component risk value represents the actual risk level of the component after considering the risk transmission influence of other related components. In other embodiments, other methods can also be used to determine the risk value, which are not limited here.

[0052] In addition, in specific implementation, the risk assessment level of the selected component under coupling effect can be determined by the component risk value in the following way: preset a level threshold (0-2.0 is level 1, 2.0-4.0 is level 2, 4.0-6.0 is level 3, 6.0-8.0 is level 4, and 8.0-10.0 is level 5), compare the component risk value with the preset level threshold to obtain the risk assessment level of the selected component under coupling effect; other methods can also be used in other embodiments, which are not limited here.

[0053] It should be noted that the risk assessment level in this application represents the assessment level of the severity of the risk of components during the operation of hydropower equipment, which can provide an intuitive basis for operation and maintenance personnel to formulate targeted control strategies.

[0054] In step 105, the risks of the hydroelectric power generation equipment during operation are dynamically identified by all risk assessment levels.

[0055] In some embodiments, the dynamic identification of operational risks of the hydropower equipment during operation based on all risk assessment levels can be achieved through the following steps: Obtain a risk identification system for the hydropower equipment during operation; Based on the risk identification system, the risk assessment levels of each risk are identified to obtain the operational risk status of the hydropower equipment during operation.

[0056] In practical implementation, when acquiring the risk identification system during the operation of hydropower equipment, industry standards such as the "Guidelines for Condition-Based Maintenance of Hydropower Generator Units" (DL / T 1573-2016) and historical equipment operation and maintenance data can be referenced to construct the core framework of the system. This system includes four parts: First, risk assessment levels and risk type mapping rules, such as component risk assessment levels 1 to 2 corresponding to low risk at the equipment level, levels 3 to 4 corresponding to medium risk at the system level, and level 5 corresponding to high risk at the whole machine level; Second, dynamic identification cycle, with the risk assessment level of core components updated every 10 minutes and the risk identification of the whole machine performed every 30 minutes, matching the data update frequency of multi-dimensional effective feature sets; Third, early warning threshold setting, such as triggering a warning if ≥3 core components within the whole machine range are simultaneously at risk level 3 or above, or if 1 core component is at risk level 5 for 1 hour. The system includes four parts: First, a corresponding early warning system; second, a weighting table that assigns weights to the risk assessment levels of each component. Core components such as turbine runners and generator stators are weighted at 0.2, while auxiliary components such as cooling systems are weighted at 0.05. The consistency coefficient CR is calculated to be less than 0.1 to ensure reasonable weighting. For example, CR = CI / RI, where CI is the consistency index and RI is the random consistency index. The risk identification system is a structured framework built for hydropower equipment to standardize the risk identification process. It serves as the basis for integrating risk assessment levels and achieving dynamic risk identification, reflecting the standardized and systematic logic of risk identification for hydropower equipment, and ensuring that the identification process is repeatable and the results are comparable.

[0057] In addition, in specific implementation, the risk assessment level of each component is identified based on the risk identification system to obtain the risk status of the hydropower equipment during operation. This can be achieved in the following way: First, the latest risk assessment level of all components is retrieved in real time through the equipment data acquisition system; second, the overall risk value of the whole machine is calculated according to the weight allocation table, with the formula being: Overall Risk Value = Σ (Component Risk Assessment Level Quantification Value × Component Weight); then, based on the risk assessment level and risk type mapping rules, the risk type corresponding to the current overall risk value is determined; next, the warning threshold is compared; finally, the fluctuation of the overall risk value is smoothed, for example, by using the moving average method to smooth it, to determine the final operating risk status. For example, if the whole machine is currently at a low risk level at the equipment level, the risk trend is stable, and no warning is triggered, the identification results are uploaded to the operation and maintenance monitoring platform in real time, and the change trajectory of the risk assessment level of each component is recorded synchronously to complete the identification of the risk status of the hydropower equipment during operation.

[0058] It should be noted that the operational risk status in this application includes information such as the current risk type (e.g., low risk at the equipment level, medium risk at the system level), risk change trend (e.g., stable, rising), and whether an early warning has been triggered. This reflects the overall risk level, potential risk direction, and short-term risk evolution probability of the hydropower equipment in the current operational phase, providing an intuitive and real-time basis for operation and maintenance personnel to determine whether control measures need to be taken.

[0059] In another aspect, in some embodiments, this application provides a risk information identification device for hydropower equipment, with reference to... Figure 4 The figure is a schematic diagram of the structure of a risk information identification device for hydropower equipment according to some embodiments of this application. The risk information identification device 400 for hydropower equipment includes: a data acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire multi-dimensional operating data of the hydropower equipment during operation. The multi-dimensional operating data includes the operating status data, environmental impact data, and operation status data of the hydropower equipment. Processing module 402, in this application, is used to extract the multi-dimensional effective feature set of the hydropower generation equipment from the multi-dimensional operating data; It should be noted that the processing module 402 in this application is also used to determine the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend during the performance evolution process of the hydropower equipment based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment. Through the operating state trajectory and the state evolution trend, the spatiotemporal correlation analysis of the operating risk of the hydropower equipment within a preset time period is performed to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. In addition, it should be noted that the processing module 402 in this application is also used to determine the risk impact characteristics of each component in the hydropower equipment during operation, and to perform multi-dimensional correlation analysis on the risk status of each component in the hydropower equipment based on the spatiotemporal risk situation and all risk impact characteristics, so as to obtain the risk assessment level of each component under the coupling effect. The execution module 403 in this application is mainly used to dynamically identify the operational risks of the hydropower equipment during operation based on all risk assessment levels.

[0060] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described method for identifying risk information of hydropower equipment.

[0061] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device for implementing a risk information identification method for hydropower equipment according to some embodiments of this application. The risk information identification method for hydropower equipment in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0062] Processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0063] The communication bus 502 can be used to transmit information between the aforementioned components.

[0064] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0065] The memory 503 stores program code for executing the scheme of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. The method used in the above embodiments can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0066] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0067] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0068] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0069] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for identifying risk information of hydropower equipment.

[0070] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0071] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for identifying risk information of hydropower equipment, wherein, Hydropower equipment includes multiple components, characterized in that the method includes the following steps: Collect multi-dimensional operational data of hydropower equipment during operation, wherein the multi-dimensional operational data includes operational status data, environmental impact data, and operational status data of the hydropower equipment; Extract the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operational data; Based on the multi-dimensional effective feature set and the historical multi-dimensional operation data of the hydropower equipment, the operation state trajectory of the hydropower equipment during the state transition process and the state evolution trend of the hydropower equipment during the performance evolution process are determined. Through the operation state trajectory and the state evolution trend, the spatiotemporal correlation analysis of the operation risk of the hydropower equipment within a preset time period is performed to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. The risk impact characteristics of each component in the hydropower equipment during operation are determined. Based on the spatiotemporal risk situation and all risk impact characteristics, a multi-dimensional correlation analysis is conducted on the risk status of each component in the hydropower equipment to obtain the risk assessment level of each component under the coupling effect. The operational risks of the hydropower equipment during operation are dynamically identified based on all risk assessment levels.

2. The method as described in claim 1, characterized in that, Extracting the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operational data specifically includes: The multi-dimensional operational data is subjected to noise removal to obtain noise-removed multi-dimensional operational data. The noise-removed multi-dimensional running data is subjected to categorical feature extraction to obtain multi-dimensional feature data of each type; Feature filtering is performed on all multi-dimensional feature data to obtain the multi-dimensional effective feature set of the hydropower equipment.

3. The method as described in claim 1, characterized in that, Determining the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend of the hydropower equipment's performance evolution process based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment specifically includes: Obtain historical multi-dimensional operating data of the hydroelectric power generation equipment; Extract the historical state feature set of the hydropower equipment's state transition and the historical performance feature set of the equipment's performance from the historical multi-dimensional operational data; The operating state trajectory of the hydropower equipment during the state transition process is determined based on the historical state feature set and the multi-dimensional effective feature set. The state evolution trend of the hydropower equipment's performance evolution process is determined based on the historical performance feature set and the multi-dimensional effective feature set.

4. The method as described in claim 1, characterized in that, By performing a spatiotemporal correlation analysis on the operational risks of the hydropower equipment within a preset time period using the operational state trajectory and the state evolution trend, the spatiotemporal risk situation of the hydropower equipment in the spatiotemporal risk distribution assessment within the preset time period specifically includes: Determine the preset time period; The preset time period is divided into multiple time windows; The hydroelectric power generation equipment is divided into multiple spatial units; Calculate the time risk index of each spatial unit in each time window based on the operational status trajectory and the state evolution trend; By performing correlation analysis on all time risk indices, the spatiotemporal risk situation of the hydropower equipment in the spatiotemporal distribution assessment of risk within a preset time period is obtained.

5. The method as described in claim 1, characterized in that, Determining the risk impact characteristics of each component in the hydropower equipment during operation specifically includes: Select one component from the hydroelectric power generation equipment as the selected component, and obtain the performance parameters of the selected component during operation; Based on the performance parameters, determine the performance impact characteristics of the selected component during the operation of the hydropower equipment; Based on the performance impact characteristics, determine the risk impact characteristics of selected components in the hydropower equipment during operation; Continue to determine the risk impact characteristics of the remaining components in the hydroelectric power generation equipment during operation.

6. The method as described in claim 1, characterized in that, Based on the spatiotemporal risk situation and all risk impact characteristics, a multi-dimensional correlation analysis is performed on the risk status of each component in the hydropower equipment to obtain the risk assessment level of each component under the coupling effect, specifically including: Risk correlation analysis is performed on each risk impact characteristic to obtain the risk correlation degree of each component; Select a component as the selected component, and determine the initial risk value of the selected component based on the spatiotemporal risk situation and the risk correlation degree of the selected component; Obtain the structural diagram of the hydroelectric power generation equipment; The initial risk value is corrected based on the structural diagram to obtain the component risk value; The risk assessment level of the selected component under coupling effect is determined by the risk value of the component. Continue to determine the risk assessment level of the remaining components under coupling effects.

7. The method as described in claim 1, characterized in that, The dynamic identification of operational risks of the hydropower equipment during operation based on all risk assessment levels specifically includes: Obtain a risk identification system for the hydropower equipment during operation; Based on the risk identification system, the risk assessment levels of each risk are identified to obtain the operational risk status of the hydropower equipment during operation.

8. A risk information identification device for hydropower equipment, characterized in that, include: The data acquisition module is used to collect multi-dimensional operational data of the hydropower equipment during operation. The multi-dimensional operational data includes the operating status data, environmental impact data, and operational status data of the hydropower equipment. The processing module is used to extract the multi-dimensional effective feature set of the hydropower equipment from the multi-dimensional operating data; The processing module is further configured to determine the operating state trajectory of the hydropower equipment during the state transition process and the state evolution trend during the performance evolution process of the hydropower equipment based on the multi-dimensional effective feature set and the historical multi-dimensional operating data of the hydropower equipment. Through the operating state trajectory and the state evolution trend, the module performs spatiotemporal correlation analysis on the operating risk of the hydropower equipment within a preset time period to obtain the spatiotemporal risk situation in the risk spatiotemporal distribution assessment of the hydropower equipment within the preset time period. The processing module is also used to determine the risk impact characteristics of each component in the hydropower equipment during operation, and to perform multi-dimensional correlation analysis on the risk status of each component in the hydropower equipment based on the spatiotemporal risk situation and all risk impact characteristics, so as to obtain the risk assessment level of each component under the coupling effect. The execution module is used to dynamically identify the operational risks of the hydropower equipment during operation based on all risk assessment levels.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the risk information identification method for hydropower equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the risk information identification method for hydropower equipment as described in any one of claims 1 to 7.

Images