Hydropower station equipment operation state analysis method and device, equipment, storage medium and computer program product

Abstract

The invention relates to the technical field of hydropower station intelligent operation and maintenance, in particular to a hydropower station equipment operation state analysis method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: synchronously calibrating and preprocessing original monitoring data of to-be-processed hydropower station equipment to obtain equipment state data and environment parameter data; based on a preset edge calculation component, extracting a running state feature value in the equipment state data, and fusing the running state feature value with the environment parameter data to generate a fused feature data set; performing association analysis on the fused feature data set based on a preset edge calculation component, and determining an association relationship between the environmental parameters and the equipment operation state; and the target operation state is determined based on the incidence relation and the current environment parameters, and the reliability of intelligent operation and maintenance of the hydropower station is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent operation and maintenance of hydropower stations, and in particular to a hydropower station equipment operation state analysis method, device, equipment, storage medium and computer program product. BACKGROUND

[0002] As an important part of the energy system, the stability and safety of the equipment operation of a hydropower station directly affect the power generation efficiency and power supply reliability. With the increase in installed capacity and automation level of hydropower stations, the types of equipment and monitoring parameters gradually increase, and the equipment operating environment is complex and changeable. Various factors such as water temperature, water pressure, flow, humidity, and silt content can all affect the performance and service life of the equipment. Therefore, how to realize real-time monitoring and intelligent analysis of the operation state of the equipment of a hydropower station has become an important research direction for ensuring safe operation and realizing fine operation and maintenance. In the prior art, the state monitoring of the equipment of a hydropower station mainly relies on a central server or a cloud platform for data collection and analysis. Although this mode can centrally process massive data, in actual operation, the monitoring data needs to be transmitted to the cloud or the central control system through the network before processing can be completed, resulting in high delay, which is not conducive to rapid response to faults, and there is a lack of effective correlation modeling between different equipment and environmental data, which makes it difficult for the analysis results to reflect the real operating state, resulting in poor reliability of intelligent operation and maintenance of a hydropower station. Therefore, how to improve the reliability of intelligent operation and maintenance of a hydropower station has become a technical problem to be solved. SUMMARY

[0003] The main purpose of the present application is to provide a hydropower station equipment operation state analysis method, device, equipment, storage medium and computer program product, which aims to solve the technical problem of how to improve the reliability of intelligent operation and maintenance of a hydropower station.

[0004] To achieve the above-mentioned purpose, the present application provides a hydropower station equipment operation state analysis method, which comprises the following steps: synchronously calibrating and preprocessing the original monitoring data of a hydropower station equipment to be processed to obtain equipment state data and environmental parameter data; based on a preset edge computing component, extracting the operation state characteristic value in the equipment state data, and fusing the operation state characteristic value with the environmental parameter data to generate a fusion feature data set; based on the preset edge computing component, performing correlation analysis on the fusion feature data set to determine the correlation between the environmental parameters and the equipment operation state; determining a target operation state based on the correlation and the current environmental parameters.

[0005] In an embodiment, the step of synchronously calibrating and preprocessing the original monitoring data of the water power plant equipment to be processed to obtain equipment state data and environmental parameter data comprises: Calibrating the time stamp of the original monitoring data and performing time axis alignment according to a preset sampling period to obtain an original synchronous data set; Performing range mapping and zero-point deviation correction on the original synchronous data set based on preset calibration parameters and historical drift records to obtain a calibrated data set; Formatting and channel dividing the calibrated data set to obtain the equipment state data and the environmental parameter data.

[0006] In an embodiment, the step of performing range mapping and zero-point deviation correction on the original synchronous data set based on preset calibration parameters and historical drift records to obtain a calibrated data set comprises: Determine the upper and lower limits of the range, the sensitivity coefficient and the zero-point reference of each sensor based on the preset calibration parameters, and generate a corresponding calibration reference model in combination with the historical drift records; Based on the range interval of the calibration reference model, the sampling values in the original synchronous data set are normalized and mapped to obtain synchronous data; Based on the time sequence change of the zero-point deviation in the historical drift record, the synchronous data is compensated and dynamically smoothed to obtain the calibrated data set.

[0007] In an embodiment, the step of extracting the running state feature value in the equipment state data based on the preset edge computing component, and fusing the running state feature value with the environmental parameter data to generate a fused feature data set comprises: Based on the preset edge computing component, the equipment state data is signal-decomposed and feature candidate-identified to determine a plurality of dynamic characteristic signal segments, and each dynamic characteristic signal segment is assigned a feature extraction task parameter; Based on the feature extraction task parameter, the dynamic characteristic signal segment is subjected to multi-dimensional feature operation to obtain a running state feature value, and the running state feature value is identified according to time sequence and sampling channel sequence to obtain an equipment feature data set; The equipment feature data set and the environmental parameter data are registered, and the registration result is standardized and feature splicing processed to obtain the fused feature data set.

[0008] In an embodiment, the step of performing correlation analysis on the fused feature data set based on the preset edge computing component to determine the correlation between the environmental parameters and the equipment running state comprises: The association analysis model is loaded into the preset edge computing component, and the parameters of the association analysis model are initialized based on the dimensional features of the fused feature dataset. Based on the correlation analysis model after parameter initialization, the correlation of multidimensional features in the fused feature dataset is calculated to obtain the correlation coefficient or feature weight between different environmental parameters and operating status feature values. Based on the correlation coefficient or feature weight, the influence intensity of each environmental parameter is sorted, and the main associated parameter set is selected based on the sorting results. The mapping relationship between the main associated parameters in the main associated parameter set and the corresponding operating state feature value is taken as the association relationship between the environmental parameter and the equipment operating state.

[0009] In one embodiment, the step of determining the target operating state based on the correlation and current environmental parameters includes: The current environmental parameters are matched with the association, and a state input set mapping real-time environmental inputs to historical associations is constructed based on the matching results. Based on the state input set and the preset edge computing component, the state labels corresponding to the operating characteristics of the hydropower station equipment to be processed are inferred, and a multi-dimensional state label determination result is generated. The target operating state is determined based on the multidimensional state label determination results.

[0010] Furthermore, to achieve the above objectives, this application also proposes a hydropower station equipment operation status analysis device, which includes: The preprocessing module is used to simultaneously calibrate and preprocess the raw monitoring data of the hydropower station equipment to be processed, so as to obtain equipment status data and environmental parameter data. The fusion module is used to extract the operating status feature values ​​from the device status data based on a preset edge computing component, and fuse the operating status feature values ​​with the environmental parameter data to generate a fused feature dataset; The correlation analysis module is used to perform correlation analysis on the fused feature dataset based on the preset edge computing component to determine the correlation between environmental parameters and device operating status. The target module is used to determine the target's operating status based on the aforementioned relationship and current environmental parameters.

[0011] In addition, to achieve the above objectives, this application also proposes a hydropower station equipment operation status analysis device, the device comprising: a memory, a processor, and a hydropower station equipment operation status analysis program stored in the memory and executable on the processor, the hydropower station equipment operation status analysis program being configured to implement the steps of the hydropower station equipment operation status analysis method described above.

[0012] In addition, to achieve the above objectives, this application also proposes a storage medium storing a hydropower station equipment operation status analysis program, which, when executed by a processor, implements the steps of the hydropower station equipment operation status analysis method described above.

[0013] In addition, to achieve the above objectives, this application also proposes a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the hydropower station equipment operation status analysis method described above.

[0014] This application obtains equipment status data and environmental parameter data by simultaneously calibrating and preprocessing the raw monitoring data of hydropower station equipment. Based on a pre-set edge computing component, it extracts operational status feature values ​​from the equipment status data and fuses these feature values ​​with the environmental parameter data to generate a fused feature dataset. Using the pre-set edge computing component, it performs correlation analysis on the fused feature dataset to determine the relationship between environmental parameters and equipment operational status. Based on this correlation and the current environmental parameters, it determines the target operational status. This application ensures consistency of multi-source data in terms of time and numerical dimensions through simultaneous calibration and preprocessing of the raw monitoring data of hydropower station equipment. By extracting operational status feature values ​​and fusing them with environmental parameter data using a pre-set edge computing component, it achieves real-time processing of multi-source information at the edge. Correlation analysis of the fused feature dataset establishes a correspondence between environmental parameters and equipment operational status. Determining the target operational status based on this correlation and the current environmental parameters allows for dynamic updates in status identification as the environment changes. This creates a closed-loop process of data unification, feature fusion, correlation modeling, and status determination within the edge computing framework, enabling real-time and accurate analysis of equipment operational status and improving the reliability of intelligent operation and maintenance of hydropower stations. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the first embodiment of the hydropower station equipment operation status analysis method of this application; Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the hydropower station equipment operation status analysis method of this application; Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the hydropower station equipment operation status analysis method of this application; Figure 4 This is a schematic diagram of the module structure of the hydropower station equipment operation status analysis device according to an embodiment of this application; Figure 5This is a schematic diagram of the equipment structure of the hardware operating environment involved in the hydropower station equipment operation status analysis method in this application embodiment.

[0016] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0018] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0019] It is important to note that hydropower stations, as a crucial component of energy systems, directly impact power generation efficiency and supply reliability due to the stability and safety of their equipment operation. With the increasing installed capacity and automation levels of hydropower stations, the types of equipment and monitoring parameters are gradually increasing, and the operating environment is becoming increasingly complex and variable. Factors such as water temperature, water pressure, flow rate, humidity, and sediment content can all affect equipment performance and lifespan. Therefore, how to achieve real-time monitoring and intelligent analysis of the operating status of hydropower station equipment has become a crucial research direction for ensuring safe operation and achieving refined operation and maintenance. In existing technologies, the status monitoring of hydropower station equipment mainly relies on central servers or cloud platforms for data collection and analysis. While this model can centrally process massive amounts of data, in actual operation, monitoring data must be transmitted to the cloud or central control system via network before processing can be completed, resulting in high latency. This hinders rapid fault response, and the lack of effective correlation modeling between data from different equipment and environments makes it difficult for the analysis results to reflect the true operating status, leading to poor reliability of intelligent operation and maintenance of hydropower stations. Therefore, improving the reliability of intelligent operation and maintenance of hydropower stations has become an urgent technical problem to be solved.

[0020] The main solution of this application is as follows: synchronously calibrate and preprocess the raw monitoring data of the hydropower station equipment to be processed to obtain equipment status data and environmental parameter data; based on a preset edge computing component, extract the operating status feature values ​​from the equipment status data, and fuse the operating status feature values ​​with the environmental parameter data to generate a fused feature dataset; perform correlation analysis on the fused feature dataset based on the preset edge computing component to determine the correlation between environmental parameters and equipment operating status; and determine the target operating status based on the correlation and the current environmental parameters.

[0021] This application ensures the consistency of multi-source data in terms of time and numerical dimensions by synchronously calibrating and preprocessing the raw monitoring data of hydropower station equipment; it extracts operating status feature values ​​based on preset edge computing components and fuses them with environmental parameter data, realizing real-time processing of multi-source information at the edge; it establishes a correspondence between environmental parameters and equipment operating status by performing correlation analysis on the fused feature dataset; and it determines the target operating status based on the correlation and current environmental parameters, enabling the status recognition to be dynamically updated with environmental changes. This forms a closed-loop process of data unification, feature fusion, correlation modeling, and status determination under the edge computing framework, realizing real-time and accurate analysis of equipment operating status, thereby improving the reliability of intelligent operation and maintenance of hydropower stations.

[0022] It should be noted that the executing entity of the method in this embodiment can be a computing service device with data processing, network communication, and program execution functions, or it can be the aforementioned hydropower station equipment operation status analysis device with the same or similar functions. This embodiment and the following embodiments will be described using a hydropower station equipment operation status analysis device as an example.

[0023] Based on this, a first embodiment of the hydropower station equipment operation status analysis method of this application is proposed. Please refer to [the relevant documentation]. Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the hydropower station equipment operation status analysis method of this application.

[0024] In this embodiment, the method for analyzing the operating status of hydropower station equipment includes the following steps: S1: Simultaneously calibrate and preprocess the raw monitoring data of the hydropower station equipment to be processed to obtain equipment status data and environmental parameter data; It should be noted that raw monitoring data refers to the unprocessed time-series data continuously collected by status sensors and environmental sensors deployed on hydropower station equipment (such as turbines, generators, and bearings), including vibration, temperature, displacement, acoustic data, as well as data on water temperature, pressure, flow rate, sediment content, and humidity. Synchronous calibration refers to aligning the timestamps of data from different sampling sources under a unified time reference and performing standardization processing such as scale / zero point based on the calibration parameters of each channel, enabling comparison between channels on the same time axis and a unified measurement scale. Preprocessing refers to performing common processing procedures such as time-domain / frequency-domain transformation, filtering, noise reduction, and standardization on the raw monitoring data at the edge to reduce noise interference and standardize data specifications. Equipment status data refers to the set of sensor data (such as vibration, temperature, displacement, and acoustic data) that characterizes the operating status of the equipment after synchronous calibration and preprocessing. Environmental parameter data refers to the set of sensor data (such as water temperature, pressure, flow rate, sediment content, and humidity) that reflects external operating conditions after synchronous calibration and preprocessing.

[0025] Specifically, after acquiring raw monitoring data from multiple types of sensors on the equipment and environmental sides, the timestamps of each channel are calibrated based on a unified clock, and the multi-source data are synchronized on a unified time axis. Subsequently, scale mapping and zero-point correction are performed on the samples of each channel according to the channel calibration information. Combined with abnormal sample identification and general data governance strategies, missing and noisy samples are reasonably replaced and standardized to form a synchronized calibration result dataset that is comparable in time and measurement dimensions.

[0026] Furthermore, a preprocessing process is performed on the above result dataset at the edge computing node, including time-domain / frequency-domain transformation, filtering, denoising and standardization of different channels as requested, and unifying the data format, units and sampling steps; after completing the processing and channel classification, the channel data that can characterize the device operating status is output as device status data, and the channel data that reflects the external operating conditions is output as environmental parameter data.

[0027] By aligning the timestamps of multiple channels under a unified time reference and performing calibration and general preprocessing on the data at the edge, the data entering the subsequent analysis chain is kept consistent in terms of time, scale, and quality. It is also standardized into equipment status data and environmental parameter data, thereby providing a unified, comparable, and noise-controlled input basis for subsequent feature extraction, fusion, and correlation analysis, reducing the analysis bias caused by asynchrony and mismatch, and supporting the stability and consistency of operation status judgment.

[0028] S2: Based on a preset edge computing component, extract the operating status feature values ​​from the device status data, and fuse the operating status feature values ​​with the environmental parameter data to generate a fused feature dataset; It should be noted that the pre-deployed edge computing component is a computing node with computing and storage capabilities, pre-positioned at the hydropower station site. It is used to perform localized processing such as feature extraction, fusion, and analysis near the data acquisition point. Operating status feature values ​​refer to quantitative indicators extracted from equipment status data that reflect the health or operating condition of the equipment. Environmental parameter data refers to monitoring data reflecting the external operating conditions of the equipment. The fused feature dataset refers to a composite data set formed by unifying the operating status feature values ​​and corresponding environmental parameters through temporal and spatial alignment, used for subsequent correlation analysis and modeling.

[0029] Specifically, within the edge computing component, multi-dimensional feature analysis is performed on the preprocessed device status data. Based on the signal attributes of various sensors, frequency domain transformation, statistical analysis, or pattern recognition operations are executed to extract numerical parameters that characterize the dynamic features of device operation, such as vibration spectrum peak values, energy concentration, or signal morphological characteristics. The extracted feature parameters are then indexed according to channel number and sampling time to form a preliminary feature dataset reflecting the device's operational characteristics.

[0030] Furthermore, the feature dataset and environmental parameter data are matched under a unified time base and spatial identifier to align the equipment operation characteristics and environmental change parameters within the same time period. Through feature fusion algorithms or rule mapping, the equipment features and environmental parameters are combined in the same feature space to obtain a fused feature dataset that can simultaneously reflect the internal state of the equipment and the external environmental conditions, providing a consistent multi-source input basis for subsequent correlation analysis.

[0031] By extracting operational status features and fusing environmental parameter data on edge computing components, the internal state of the equipment and external environmental conditions are uniformly expressed in the same data space, thus avoiding information gaps and biases caused by analysis from a single data source. This step not only improves the real-time performance and completeness of edge-side feature analysis but also provides a structured, spatiotemporally consistent input foundation for subsequent correlation modeling and state recognition, enhancing the accuracy and reliability of hydropower station equipment operational status analysis at the system level.

[0032] S3: Based on the preset edge computing component, perform correlation analysis on the fused feature dataset to determine the correlation between environmental parameters and device operating status; It should be noted that association analysis refers to the analysis of relationships between different feature variables in a fused feature dataset using computational models, rules, or statistical methods, thereby revealing the coupling patterns between environmental parameters and equipment operating status. The association relationship refers to the mapping relationship or quantitative indicator determined through association analysis that reflects the degree and direction of the impact of changes in environmental parameters on equipment operating status.

[0033] Specifically, a lightweight correlation analysis model is loaded into the preset edge computing component, and the correspondence between input and output variables is determined based on the feature dimensions of the fused feature dataset. The model may include a rule-based logic engine or a machine learning-based structured model, with its input being a fused sample of device operating status features and environmental parameters. Subsequently, the edge computing component performs batch or sliding window processing on the input data, performs preliminary matching and summarization of the changing trends between different parameter combinations, and generates a set of correlation indicators for each feature dimension.

[0034] Furthermore, after acquiring the correlation indicators, the system measures and filters the correlation strength between environmental parameters and equipment operating status characteristics based on preset thresholds or weight rankings, extracts the parameter combinations with significant impact, and establishes a corresponding mapping relationship between the main environmental parameters and target operating characteristics. The final output correlation relationship can be used for subsequent status determination and trend prediction, forming analysis results that can be directly executed at the edge, realizing real-time correlation identification between environmental factors and equipment status.

[0035] By performing correlation analysis on the fused feature dataset within the edge computing component, the relationship between equipment operating status characteristics and environmental parameters can be quantified and identified locally, avoiding the latency and uncertainty caused by traditional solutions that rely on centralized cloud analysis. This step establishes a dynamic mapping relationship between environmental parameters and equipment status, providing a basis for subsequent operating status determination, and enabling rapid parsing of coupling characteristics between multi-source data. This enhances the real-time performance and relevance of equipment status analysis, and improves the reliability of intelligent operation and maintenance of hydropower stations.

[0036] S4: Determine the target operating status based on the aforementioned correlation and current environmental parameters.

[0037] It should be noted that the current environmental parameters refer to the operating condition data collected by environmental sensors at the current moment during the real-time operation of the equipment. The target operating state refers to the current operating status of the equipment determined based on the current environmental parameters and existing correlations.

[0038] Specifically, the preset edge computing component receives real-time environmental parameter data and matches it with previously established correlations between environmental parameters and device operating states. Based on the matching results, an input feature set is constructed, containing combinations of feature variables corresponding to the current operating condition. The system then invokes a state determination model at the edge, mapping the input feature set to the corresponding operating state space and calculating the matching degree or confidence value for each candidate state.

[0039] Furthermore, based on the matching results output by the model, the operating status of the equipment is classified and judged to determine the target operating status that best matches the current environmental parameters. Subsequently, the judgment result is bound with the equipment identifier, timestamp, and judgment criteria to facilitate subsequent recording, traceability, and collaborative processing. At this point, the step of determining the target operating status based on the correlation and current environmental parameters is completed, realizing dynamic updating and on-site judgment of the operating status.

[0040] By combining current environmental parameters with established correlations, the target operating status is determined directly at the edge, enabling real-time and adaptive equipment status identification. This step allows the status determination to dynamically adjust with environmental changes, reducing misjudgments and delays caused by environmental fluctuations or fixed thresholds. Simultaneously, the determination results are generated instantly at the edge, providing a rapid decision-making basis for subsequent alarms, control, or cloud analysis, thereby improving the reliability and stability of hydropower station equipment operation monitoring and intelligent operation and maintenance processes.

[0041] This embodiment obtains equipment status data and environmental parameter data by synchronously calibrating and preprocessing the raw monitoring data of the hydropower station equipment. Based on a preset edge computing component, it extracts operational status feature values ​​from the equipment status data and fuses these feature values ​​with the environmental parameter data to generate a fused feature dataset. Using the preset edge computing component, it performs correlation analysis on the fused feature dataset to determine the relationship between environmental parameters and equipment operational status. Based on this correlation and the current environmental parameters, it determines the target operational status. This embodiment ensures consistency of multi-source data in terms of time and numerical dimensions through synchronous calibration and preprocessing of the raw monitoring data of the hydropower station equipment. By extracting operational status feature values ​​and fusing them with environmental parameter data using the preset edge computing component, it achieves real-time processing of multi-source information at the edge. Correlation analysis of the fused feature dataset establishes a correspondence between environmental parameters and equipment operational status. The determination of the target operational status based on this correlation and the current environmental parameters enables dynamic updates to status recognition as the environment changes. This creates a closed-loop process of data unification, feature fusion, correlation modeling, and status determination within the edge computing framework, achieving real-time and accurate analysis of equipment operational status and thus improving the reliability of intelligent operation and maintenance of hydropower stations.

[0042] Based on the first embodiment described above, a second embodiment of the hydropower station equipment operation status analysis method of this application is proposed. Please refer to... Figure 2 , Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the hydropower station equipment operation status analysis method of this application.

[0043] like Figure 2 As shown, in this embodiment, step S1 includes: S11: The timestamps of the original monitoring data are calibrated, and the time axis is aligned according to the preset sampling period to obtain the original synchronous dataset; S12: Based on preset calibration parameters and historical drift records, range mapping and zero-point deviation correction are performed on the original synchronization dataset to obtain the calibration dataset; S13: Format and divide the calibration dataset into channels to obtain the device status data and the environmental parameter data.

[0044] It should be noted that timestamp calibration refers to adjusting the time stamp of data collected by different sensors according to a unified time base or reference clock, so that multi-source data are aligned on the same time axis. Preset sampling period refers to the pre-set sampling interval of the data acquisition device per unit time. Preset calibration parameters refer to the correction coefficients or range mapping parameters pre-set to ensure the accuracy of sensor measurements. Historical drift records refer to drift data or deviation records accumulated during long-term sensor operation, used for dynamically correcting measured values. Range mapping refers to the process of mapping the sensor's raw sampled values ​​to the range of standard physical quantities according to preset calibration parameters. Zero-point deviation correction refers to compensating for the sensor's output deviation when there is no signal input, in order to restore the true measurement baseline. Formatting and channel division refers to the structured organization and classification of calibrated data according to data type and acquisition source, so that different categories of monitoring data correspond to equipment status data and environmental parameter data respectively.

[0045] Specifically, the acquired raw monitoring data is timestamped and calibrated. Based on a unified system clock or synchronization signal source, the acquisition times of different sampling channels are compared and corrected, and the time axis is aligned according to a preset sampling period, thus forming a raw synchronous dataset with continuous time and consistent sampling intervals. Subsequently, the calibration parameters and historical drift records corresponding to the sensors are called to perform range mapping and zero-point deviation correction on the samples of each channel in the raw synchronous dataset, eliminating measurement deviations caused by differences in sensor characteristics and time drift, and generating a calibration dataset with unified dimensions and a stable benchmark.

[0046] Furthermore, after obtaining the calibration dataset, data formatting and channel segmentation are performed, and the calibrated data are structured according to sampling source, monitoring object, and physical attributes. For channel data reflecting equipment operating conditions, equipment status data is extracted and summarized; for channel data reflecting external operating conditions, environmental parameter data is extracted and summarized. The segmented dataset serves as input for subsequent feature extraction and analysis steps, completing the data preprocessing flow of "synchronization—calibration—classification output".

[0047] By sequentially performing timestamp calibration, calibration correction, and channel segmentation, the raw monitoring data is unified and standardized in terms of time, range, and type. This step ensures the temporal synchronization and measurement consistency of multi-source data, effectively eliminating errors caused by sensor drift and zero-point deviation. It provides an accurate and reliable data foundation for subsequent feature extraction and correlation analysis, thereby improving the stability and accuracy of hydropower station equipment operation status analysis.

[0048] Based on the first embodiment described above, in this embodiment, step S12 includes: S121: Based on the preset calibration parameters, determine the upper and lower limits of the range, sensitivity coefficient and zero point reference of each sensor, and generate the corresponding calibration reference model by combining the historical drift records. S122: Based on the range of the calibration reference model, normalize and map the sampled values ​​in the original synchronization dataset to obtain synchronization data; S123: Based on the time series changes of zero-point deviation in the historical drift record, zero-point offset compensation and dynamic smoothing adjustment are performed on the synchronization data to obtain the calibration dataset.

[0049] It should be noted that the upper and lower limits of the measurement range refer to the minimum and maximum values ​​of the signal that the sensor can accurately acquire within its physical measurement range. The sensitivity coefficient refers to the proportionality between changes in the sensor's input and output. The zero-point reference refers to the ideal reference value that the sensor should output when there is no input signal. The calibration reference model refers to a correction model established based on the sensor's calibration parameters and historical drift records. Normalization mapping refers to converting sampled values ​​from different ranges or units to a unified standard scale. Zero-point offset compensation refers to dynamically correcting the zero-point drift accumulated in the sensor output over time. Dynamic smoothing adjustment refers to smoothing the corrected data based on the changing trends of the time series, reducing abrupt changes and noise interference.

[0050] Specifically, within the edge computing component, the upper and lower limits of the measurement range, sensitivity coefficients, and zero-point references of various sensors are determined based on preset calibration parameters. Combined with statistical information reflecting long-term sensor deviations from historical drift records, a corresponding calibration reference model is generated. This model describes the calibration relationships of each sensor within different time periods and measurement intervals, providing a parameterized basis for subsequent numerical corrections. Subsequently, based on the measurement ranges defined in the calibration reference model, normalization mapping is performed on each sampled value in the original synchronous dataset, transforming data with different dimensions and ranges to a unified standard scale, resulting in synchronous data that can be compared within a uniform range.

[0051] Furthermore, after completing the range mapping, the system utilizes the time-series changes in zero-point deviation from historical drift records to perform zero-point offset compensation and dynamic smoothing adjustment on the synchronization data. By modeling the drift trend of each channel in the time dimension, the system dynamically corrects the zero-point offset at different sampling periods and employs a smoothing algorithm to suppress short-term fluctuations. Finally, the compensated and adjusted result data is output as a stable and accurate calibration dataset for subsequent analysis modules.

[0052] By combining calibration parameters with historical drift records to establish a calibration reference model, and then performing range normalization, zero-point compensation, and dynamic smoothing on this model, long-term consistency and measurement accuracy of data from different sensors are maintained at a unified scale. This step effectively eliminates systematic errors caused by differences in sensor characteristics and time drift, providing high-quality, stable, and reliable data input for subsequent feature extraction and condition analysis, thereby improving the accuracy and reliability of the equipment condition analysis process.

[0053] This embodiment obtains equipment status data and environmental parameter data by synchronously calibrating and preprocessing the raw monitoring data of the hydropower station equipment. Based on a preset edge computing component, it extracts operational status feature values ​​from the equipment status data and fuses these feature values ​​with the environmental parameter data to generate a fused feature dataset. Using the preset edge computing component, it performs correlation analysis on the fused feature dataset to determine the relationship between environmental parameters and equipment operational status. Based on this correlation and the current environmental parameters, it determines the target operational status. This embodiment ensures consistency of multi-source data in terms of time and numerical dimensions through synchronous calibration and preprocessing of the raw monitoring data of the hydropower station equipment. By extracting operational status feature values ​​and fusing them with environmental parameter data using the preset edge computing component, it achieves real-time processing of multi-source information at the edge. Correlation analysis of the fused feature dataset establishes a correspondence between environmental parameters and equipment operational status. The determination of the target operational status based on this correlation and the current environmental parameters enables dynamic updates to status recognition as the environment changes. This creates a closed-loop process of data unification, feature fusion, correlation modeling, and status determination within the edge computing framework, achieving real-time and accurate analysis of equipment operational status and thus improving the reliability of intelligent operation and maintenance of hydropower stations.

[0054] Based on the second embodiment described above, a third embodiment of the hydropower station equipment operation status analysis method of this application is proposed. Please refer to... Figure 3 , Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the hydropower station equipment operation status analysis method of this application.

[0055] In this embodiment, step S2 includes: S21: Based on the preset edge computing component, perform signal decomposition and feature candidate recognition on the device status data, determine multiple dynamic characteristic signal segments, and assign feature extraction task parameters to each dynamic characteristic signal segment; S22: Based on the feature extraction task parameters, perform multi-dimensional feature operations on the dynamic characteristic signal segment to obtain the operating state feature value, and identify the operating state feature value according to the time order and the sampling channel order to obtain the equipment feature dataset; S23: Register the device feature dataset with the environmental parameter data, and standardize and perform feature splicing on the registration result to obtain the fused feature dataset.

[0056] It should be noted that signal decomposition refers to the separation of multiple scales or frequency components from the original equipment status signal. Feature candidate identification refers to the selection of representative or significant signal feature regions from the signal decomposition results. Dynamic characteristic signal segments refer to time-series signal segments that, after signal decomposition and candidate identification, can reflect the changing patterns of equipment operating status. Feature extraction task parameters refer to the set of analytical and computational parameters set for different signal segments. Multidimensional feature operation refers to the comprehensive operation of signals in multiple dimensions such as the time domain, frequency domain, and statistical domain, thereby extracting multiple types of feature values ​​representing the operating status. Equipment feature dataset refers to the data set consisting of operating status feature values ​​and their corresponding time and channel identifiers. Registration refers to the process of aligning data from different sources in time and spatial coordinates. Standardization and feature splicing refer to the unification of dimensions and structural combination of features from different dimensions based on the aligned data, generating a fused multi-source feature set.

[0057] Specifically, within the pre-defined edge computing component, signal decomposition processing is performed on the device status data. This involves multi-scale separation of signals collected from different sensor channels in both the frequency and time domains to obtain various components reflecting the device's operational dynamics. Based on a feature candidate recognition algorithm, the system identifies several representative dynamic characteristic signal segments and assigns corresponding feature extraction task parameters based on the segment's characteristic attributes (such as fluctuation amplitude and frequency band energy density) to guide subsequent feature calculations.

[0058] Furthermore, based on the allocated feature extraction task parameters, multi-dimensional feature operations are performed on each dynamic characteristic signal segment to calculate time-domain features (such as root mean square, skewness, etc.), frequency-domain features (such as main frequency amplitude, spectral energy distribution, etc.), and statistical features (such as kurtosis, variance, etc.). The obtained operating status feature values ​​are then labeled according to time order and sampling channel order to form a device feature dataset. Subsequently, this device feature dataset is registered with environmental parameter data on the time axis. The matching results are standardized and feature concatenation is performed to fuse features from different sources in a unified structure, ultimately outputting a fused feature dataset to provide input data for subsequent correlation analysis.

[0059] By performing signal decomposition, feature candidate identification, and multi-dimensional feature operations within the edge computing component, hierarchical analysis and dynamic feature extraction of equipment status data were achieved. Furthermore, through the registration and fusion of features with environmental parameters, a unified expression format for multi-source information was established. This step ensures that the internal operating characteristics of the equipment are consistent with external environmental conditions in time and space, forming highly correlated fused feature data. This provides more comprehensive and accurate data support for subsequent correlation analysis and operational status determination, thereby improving the accuracy and real-time performance of hydropower station equipment status identification.

[0060] Based on the second embodiment described above, in this embodiment, step S3 includes: S31: Load the correlation analysis model into the preset edge computing component, and initialize the parameters of the correlation analysis model based on the dimensional features of the fused feature dataset; S32: Based on the correlation analysis model after parameter initialization, perform correlation calculation on the multidimensional features in the fused feature dataset to obtain the correlation coefficient or feature weight between different environmental parameters and operating status feature values; S33: Based on the correlation coefficient or feature weight, sort the influence intensity of each environmental parameter, select the main associated parameter set based on the sorting result, and take the mapping relationship between the main associated parameters in the main associated parameter set and the corresponding operating state feature value as the association relationship between the environmental parameter and the equipment operating state.

[0061] It should be noted that the association analysis model refers to a mathematical or algorithmic model used to calculate the correlation or dependence between different feature variables. Dimensional features refer to multi-dimensional input variables integrated from the feature dataset, including time dimension, equipment feature dimension, and environmental parameter dimension. Parameter initialization refers to the initial assignment of weights, thresholds, or structural parameters in the model based on data characteristics before model execution to ensure the stability and convergence of the analysis results. Correlation coefficients or feature weights refer to index values ​​used to measure the strength of the linear or non-linear relationship between environmental parameters and equipment operating characteristics. The set of main correlated parameters refers to the set of environmental parameters that have a significant impact on the equipment operating status, selected after being sorted by correlation or weight. The mapping relationship refers to the correspondence established between the main correlated parameters and the operating status feature values.

[0062] Specifically, the system loads a correlation analysis model into a pre-defined edge computing component and matches and maps the model's input and output variables according to the dimensional structure of the fused feature dataset. The system initializes the model's core parameters based on the quantity, distribution, and type of data features, including feature dimension weights, learning rates, and threshold ranges, to ensure accurate convergence and adaptation to data characteristics in subsequent analyses. After parameter initialization, the system inputs the fused feature dataset into the model, preparing for correlation calculations.

[0063] Furthermore, during model execution, based on the initialized parameters, the correlation of multidimensional features in the fused feature dataset is calculated to obtain the correlation coefficients or feature weight sets between environmental parameters and operational status feature values. The influence intensity of environmental parameters is ranked according to the magnitude of the correlation coefficients or feature weights, and the set of main correlated parameters is selected. Subsequently, the system establishes a mapping relationship between the main correlated parameters and their corresponding operational status feature values ​​based on the ranking results. This mapping relationship is then used as the correlation between environmental parameters and equipment operational status and output to the subsequent status determination module.

[0064] By loading and initializing the correlation analysis model in the edge computing component, the model can quantitatively calculate and assess the relationships between multidimensional features based on a fused feature dataset. This step establishes a direct mapping relationship between environmental parameters and equipment operating status by calculating correlation coefficients or feature weights and selecting key correlation parameters, thereby achieving a quantifiable description of the impact of environmental factors on equipment operating behavior. This process not only improves the relevance and interpretability of the status analysis but also provides a reliable basis for subsequent status identification and prediction, enhancing the accuracy and reliability of the overall operating status analysis.

[0065] In this embodiment, step S4 includes: S41: Match the current environmental parameters with the association relationship, and construct a state input set that maps real-time environmental input to historical association based on the matching results; S42: Based on the state input set and the preset edge computing component, infer the state labels corresponding to the operating characteristics of the hydropower station equipment to be processed, and generate a multi-dimensional state label determination result. S43: Determine the target operating state based on the multidimensional state label determination result.

[0066] It should be noted that status labels refer to categories or identification information used to represent the operating status of a device. Multidimensional status label determination results refer to the determination output obtained within the edge computing component based on the status input set, consisting of multiple status labels or their corresponding scores. Target operating state refers to the current operating state of the device ultimately determined based on the multidimensional status label determination results.

[0067] Specifically, after obtaining the current environmental parameters, they are matched with existing associations. Based on the matching results, association entries corresponding to the current environmental quantities are selected, and the environmental quantities and their mapping items in the associations are organized to construct a state input set containing real-time environmental inputs and historical association mappings. In the state input set, different environmental quantities and their corresponding runtime feature mapping items are uniformly indexed and formatted to meet the input constraints of subsequent inference calculations, thus completing the process of "matching the current environmental parameters with the associations and constructing a state input set based on the matching results".

[0068] Furthermore, within the preset edge computing component, a state determination model is invoked, using the state input set as model input. The state labels corresponding to the operational characteristics of the hydropower station equipment to be processed are inferred, generating a multi-dimensional state label determination result containing multiple state labels or their corresponding scores. The multi-dimensional state label determination result is then merged and selected to determine the target operating state matching the current operating condition. This target operating state is then bound to the equipment identifier and time information, completing the process of "generating a determination result based on the state input set and the preset edge computing component, and determining the target operating state accordingly."

[0069] By first matching the current environmental parameters with existing relationships to form a state input set, and then inferring the state labels within the edge computing component to determine the target operating state, the state determination is based on real-time operating conditions as input and established mappings to complete closed-loop decision-making. This enables consistent and repeatable determination of the current operating state of the equipment without relying on external conditions, providing a standardized state output basis for subsequent operation and maintenance.

[0070] This embodiment obtains equipment status data and environmental parameter data by synchronously calibrating and preprocessing the raw monitoring data of the hydropower station equipment. Based on a preset edge computing component, it extracts operational status feature values ​​from the equipment status data and fuses these feature values ​​with the environmental parameter data to generate a fused feature dataset. Using the preset edge computing component, it performs correlation analysis on the fused feature dataset to determine the relationship between environmental parameters and equipment operational status. Based on this correlation and the current environmental parameters, it determines the target operational status. This embodiment ensures consistency of multi-source data in terms of time and numerical dimensions through synchronous calibration and preprocessing of the raw monitoring data of the hydropower station equipment. By extracting operational status feature values ​​and fusing them with environmental parameter data using the preset edge computing component, it achieves real-time processing of multi-source information at the edge. Correlation analysis of the fused feature dataset establishes a correspondence between environmental parameters and equipment operational status. The determination of the target operational status based on this correlation and the current environmental parameters enables dynamic updates to status recognition as the environment changes. This creates a closed-loop process of data unification, feature fusion, correlation modeling, and status determination within the edge computing framework, achieving real-time and accurate analysis of equipment operational status and thus improving the reliability of intelligent operation and maintenance of hydropower stations.

[0071] In one embodiment, after fusing equipment status data and environmental parameter data, a local analysis model is constructed using multiple edge computing nodes distributed across different units or stations. Each edge node independently performs correlation analysis and status determination tasks locally while periodically exchanging model weight information through a designated parameter synchronization channel. The system configures a global model coordination module in the cloud to perform weighted aggregation after receiving weights uploaded from multiple edge nodes, and generates a feedback gradient based on global statistical features. The optimized parameters are then downlinked and synchronized to each node to achieve consistent model updates across regions.

[0072] Furthermore, to mitigate performance degradation during long-term model operation, this embodiment incorporates a dynamic feature selection module in the edge computing nodes. This module monitors real-time changes in the variance and correlation drift of input features, adaptively reducing or eliminating feature channels with low contribution or high redundancy, and automatically supplementing newly detected significant feature dimensions. This allows the feature space structure to self-adjust as equipment ages and the environment changes. This mechanism maintains lightweight model computation while improving the long-term stability of correlations. During operation, each edge node periodically uploads its feature importance matrix and model confidence index to the cloud. The cloud, combined with global feature distribution trends, automatically identifies abnormal nodes and triggers remote model retraining. After retraining, the system allocates differentiated model parameters based on the similarity of node operating conditions, achieving differentiated deployment and collaborative optimization.

[0073] This application also provides a hydropower station equipment operation status analysis device. Please refer to... Figure 4 , Figure 4 This is a schematic diagram of the module structure of the hydropower station equipment operation status analysis device according to an embodiment of this application. The hydropower station equipment operation status analysis device includes: Preprocessing module 401 is used to synchronously calibrate and preprocess the raw monitoring data of the hydropower station equipment to be processed, so as to obtain equipment status data and environmental parameter data. The fusion module 402 is used to extract the operating status feature values ​​from the device status data based on a preset edge computing component, and fuse the operating status feature values ​​with the environmental parameter data to generate a fused feature dataset; The correlation analysis module 403 is used to perform correlation analysis on the fused feature dataset based on the preset edge computing component to determine the correlation between environmental parameters and device operating status. The target module 404 is used to determine the target's operating status based on the aforementioned correlation and current environmental parameters.

[0074] The hydropower station equipment operation status analysis device provided in this application embodiment adopts the hydropower station equipment operation status analysis method in the above embodiment, which can solve the technical problem of how to improve the reliability of intelligent operation and maintenance of hydropower stations. Compared with the prior art, the beneficial effects of the hydropower station equipment operation status analysis device provided in this application embodiment are the same as the beneficial effects of the hydropower station equipment operation status analysis method provided in the above embodiment, and other technical features in the hydropower station equipment operation status analysis device are the same as the features disclosed in the method of the above embodiment, and will not be repeated here.

[0075] This application provides a hydropower station equipment operation status analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the hydropower station equipment operation status analysis method described in the above embodiment.

[0076] The following is for reference. Figure 5 , Figure 5 This is a schematic diagram of the hardware operating environment involved in the hydropower station equipment operation status analysis method in the embodiments of this application. It shows a schematic diagram of the structure of the hydropower station equipment operation status analysis device suitable for implementing the embodiments of this application. Figure 5 The hydropower station equipment operation status analysis device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0077] like Figure 5As shown, the hydropower station equipment operation status analysis device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the hydropower station equipment operation status analysis device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the hydropower station equipment operation status analysis equipment to exchange data wirelessly or via wired communication with other devices. Although the figure shows a hydropower station equipment operation status analysis equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0078] In particular, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. When the computer program is executed by the processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0079] The hydropower station equipment operation status analysis device provided in this application, employing the hydropower station equipment operation status analysis method described in the above embodiments, can solve the technical problem of how to improve the reliability of intelligent operation and maintenance of hydropower stations. Compared with the prior art, the beneficial effects of the hydropower station equipment operation status analysis device provided in this application are the same as those of the hydropower station equipment operation status analysis method provided in the above embodiments, and other technical features of this hydropower station equipment operation status analysis device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0080] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0081] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0082] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the hydropower station equipment operation status analysis method in the above embodiments.

[0083] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the hydropower station equipment operation status analysis device, the hydropower station equipment operation status analysis device performs the following actions: synchronous calibration and preprocessing of the raw monitoring data of the hydropower station equipment to be processed, obtaining equipment status data and environmental parameter data; based on a preset edge computing component, extracting operation status feature values ​​from the equipment status data, and fusing the operation status feature values ​​with the environmental parameter data to generate a fused feature dataset; based on the preset edge computing component, performing correlation analysis on the fused feature dataset to determine the correlation between environmental parameters and equipment operation status; and based on the correlation and current environmental parameters, determining the target operation status. Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer through any type of network—including a local area network (LAN) or a wide area network (WAN)—or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0084] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0085] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0086] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described hydropower station equipment operation status analysis method, thereby solving the technical problem of how to improve the reliability of intelligent operation and maintenance of hydropower stations. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the hydropower station equipment operation status analysis method provided in the above embodiments, and will not be repeated here.

[0087] This application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the hydropower station equipment operation status analysis method described above.

[0088] The computer program product provided in this application can solve the technical problem of how to improve the reliability of intelligent operation and maintenance of hydropower stations. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the hydropower station equipment operation status analysis method provided in the above embodiments, and will not be repeated here.

[0089] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for analyzing the operating status of hydropower station equipment, characterized in that, The method includes: The raw monitoring data of the hydropower station equipment to be processed are simultaneously calibrated and preprocessed to obtain equipment status data and environmental parameter data; Based on a preset edge computing component, the operating status feature value is extracted from the device status data, and the operating status feature value is fused with the environmental parameter data to generate a fused feature dataset; Based on the preset edge computing component, the fused feature dataset is analyzed to determine the correlation between environmental parameters and device operating status. Based on the aforementioned correlation and current environmental parameters, the target operating status is determined.

2. The method as described in claim 1, characterized in that, The steps of synchronously calibrating and preprocessing the raw monitoring data of the hydropower station equipment to be processed to obtain equipment status data and environmental parameter data include: The timestamps of the original monitoring data are calibrated, and the time axis is aligned according to a preset sampling period to obtain the original synchronous dataset; Based on preset calibration parameters and historical drift records, the original synchronization dataset is range-mapped and zero-point deviation corrected to obtain the calibration dataset. The calibration dataset is formatted and divided into channels to obtain the device status data and the environmental parameter data.

3. The method as described in claim 2, characterized in that, The step of performing range mapping and zero-point deviation correction on the original synchronization dataset based on preset calibration parameters and historical drift records to obtain the calibration dataset includes: Based on the preset calibration parameters, the upper and lower limits of the range, sensitivity coefficient and zero point reference of each sensor are determined, and the corresponding calibration reference model is generated by combining the historical drift records. Based on the range of the calibration reference model, the sampled values ​​in the original synchronization dataset are normalized and mapped to obtain synchronization data. Based on the time series changes of zero-point deviation in the historical drift record, the synchronization data is subjected to zero-point offset compensation and dynamic smoothing adjustment to obtain the calibration dataset.

4. The method as described in claim 1, characterized in that, The step of extracting operating status feature values ​​from the device status data based on a preset edge computing component, and fusing the operating status feature values ​​with the environmental parameter data to generate a fused feature dataset includes: Based on the preset edge computing component, the device status data is decomposed into signals and feature candidate recognition is performed to determine multiple dynamic characteristic signal segments, and feature extraction task parameters are assigned to each dynamic characteristic signal segment. Based on the feature extraction task parameters, multi-dimensional feature operations are performed on the dynamic characteristic signal segment to obtain the operating state feature value, and the operating state feature value is identified according to the time order and the sampling channel order to obtain the equipment feature dataset; The device feature dataset is registered with the environmental parameter data, and the registration result is standardized and feature splicing is performed to obtain the fused feature dataset.

5. The method as described in claim 1, characterized in that, The step of performing correlation analysis on the fused feature dataset based on the preset edge computing component to determine the correlation between environmental parameters and device operating status includes: The association analysis model is loaded into the preset edge computing component, and the parameters of the association analysis model are initialized based on the dimensional features of the fused feature dataset. Based on the correlation analysis model after parameter initialization, the correlation of multidimensional features in the fused feature dataset is calculated to obtain the correlation coefficient or feature weight between different environmental parameters and operating status feature values. Based on the correlation coefficient or feature weight, the influence intensity of each environmental parameter is sorted, and the main associated parameter set is selected based on the sorting results. The mapping relationship between the main associated parameters in the main associated parameter set and the corresponding operating state feature value is taken as the association relationship between the environmental parameter and the equipment operating state.

6. The method as described in claim 1, characterized in that, The step of determining the target operating state based on the correlation and current environmental parameters includes: The current environmental parameters are matched with the association, and a state input set mapping real-time environmental inputs to historical associations is constructed based on the matching results. Based on the state input set and the preset edge computing component, the state labels corresponding to the operating characteristics of the hydropower station equipment to be processed are inferred, and a multi-dimensional state label determination result is generated. The target operating state is determined based on the multidimensional state label determination results.

7. A device for analyzing the operating status of hydropower station equipment, characterized in that, The device includes: The preprocessing module is used to simultaneously calibrate and preprocess the raw monitoring data of the hydropower station equipment to be processed, so as to obtain equipment status data and environmental parameter data. The fusion module is used to extract the operating status feature values ​​from the device status data based on a preset edge computing component, and fuse the operating status feature values ​​with the environmental parameter data to generate a fused feature dataset; The correlation analysis module is used to perform correlation analysis on the fused feature dataset based on the preset edge computing component to determine the correlation between environmental parameters and device operating status. The target module is used to determine the target's operating status based on the aforementioned relationship and current environmental parameters.

8. A computer device, characterized in that, The device includes: a memory, a processor, and a hydropower station equipment operation status analysis program stored in the memory and executable on the processor, wherein the hydropower station equipment operation status analysis program is configured to implement the steps of the hydropower station equipment operation status analysis method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a hydropower station equipment operation status analysis program, which, when executed by a processor, implements the steps of the hydropower station equipment operation status analysis method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the hydropower station equipment operation status analysis method as described in any one of claims 1 to 6.

Images