Multi-dimensional electrical equipment stability evaluation method and device for new energy power grid connection

Abstract

The application relates to the technical field of electrical equipment evaluation, in particular to a multi-dimensional electrical equipment stability evaluation method and device for new energy power grid connection, which comprises the following steps: based on a multi-dimensional evaluation index system, collecting multi-dimensional index data of a target electrical equipment, performing feature enhancement processing, and generating processed enhanced features; based on a grid connection power fluctuation coefficient and an equipment operation stage coefficient of the target electrical equipment, adjusting the weight proportion of each dimension and corresponding indexes in the multi-dimensional index data to obtain dynamic weights; inputting the processed enhanced features and the dynamic weights into an evaluation model combining fuzzy comprehensive evaluation and Markov chain prediction, performing stability evaluation on the target electrical equipment for new energy power grid connection, and outputting a stability evaluation result of the target electrical equipment. Therefore, the problems that in the related art, prospective decision support cannot be provided for preventive maintenance and grid connection scheduling, and it is difficult to guarantee the safe and stable operation of the power grid under high-proportion new energy access are solved.

Description

Technical Field

[0001] This application relates to the field of electrical equipment evaluation technology, and in particular to a multi-dimensional electrical equipment stability evaluation method and device for grid connection of new energy power. Background Technology

[0002] The large-scale grid connection of new energy sources (such as photovoltaic and wind power) has brought significant volatility and intermittency to the power system, posing a severe challenge to the stable operation of key electrical equipment at the grid connection point, such as transformers, inverters, and switchgear.

[0003] Equipment stability assessment in related technologies often relies on threshold monitoring of single electrical parameters such as voltage and current. However, this is a static, isolated, and passive monitoring method that cannot fully reflect the true health status of equipment under complex operating conditions. It is even more difficult to quantify the multi-dimensional coupled effects of new energy power fluctuations, environmental factors, and equipment aging.

[0004] Therefore, the equipment stability assessment methods in related technologies cannot provide forward-looking decision support for preventive maintenance and grid-connected dispatch, which reduces the accuracy and practicality of electrical equipment stability assessment and makes it difficult to ensure the safe and stable operation of the power grid under a high proportion of new energy access, which urgently needs to be addressed. Summary of the Invention

[0005] This application provides a multi-dimensional electrical equipment stability assessment method and apparatus for grid connection of new energy power, in order to solve the problem that related technologies cannot provide forward-looking decision support for preventive maintenance and grid connection dispatch, which reduces the accuracy and practicality of electrical equipment stability assessment and makes it difficult to ensure the safe and stable operation of the power grid under high proportion of new energy access.

[0006] The first aspect of this application provides a method for multi-dimensional stability assessment of electrical equipment connected to the grid of new energy power, comprising the following steps: based on a pre-constructed multi-dimensional assessment index system, collecting multi-dimensional index data of the target electrical equipment, and performing feature enhancement processing on the multi-dimensional index data to generate enhanced features; based on the grid-connected power fluctuation coefficient and equipment operation stage coefficient of the target electrical equipment, adjusting the weight ratio of each dimension and corresponding index in the multi-dimensional index data to obtain the dynamic weight of each dimension and corresponding index; inputting the enhanced features and the dynamic weight of each dimension and corresponding index into a pre-constructed assessment model that integrates fuzzy comprehensive evaluation and Markov chain prediction, and using the fuzzy comprehensive evaluation module and the Markov chain prediction module to perform stability assessment on the target electrical equipment connected to the grid of new energy power, so as to output the stability assessment result of the target electrical equipment.

[0007] Based on the above technical means, the embodiments of this application can improve the accuracy and practicality of evaluating the stability of grid-connected electrical equipment for new energy sources by integrating interpretable enhanced features with dynamic weights that are adaptive to operating conditions, and combining fuzzy comprehensive evaluation and Markov chain prediction, thereby effectively ensuring the safe and stable operation of the power grid under a high proportion of new energy access.

[0008] Optionally, in one embodiment of this application, after outputting the stability assessment result of the target electrical equipment, the method further includes: determining the current stability level and the stability trend within a preset future time period of the target electrical equipment based on the stability assessment result; linking the current stability level and the stability trend within the preset future time period with the new energy grid-connected scheduling system to generate operation and maintenance suggestions and grid-connected parameter adjustment strategies for the target electrical equipment.

[0009] Based on the above technical means, the embodiments of this application can automatically generate targeted operation and maintenance suggestions and grid connection parameter optimization strategies by integrating stability level and trend prediction into the scheduling system, thereby improving the safety, reliability and intelligence level of new energy grid connection.

[0010] Optionally, in one embodiment of this application, before collecting the multi-dimensional index data of the target electrical equipment, the method further includes: constructing a multi-dimensional evaluation index system for the target electrical equipment based on electrical parameter dimensions, grid connection adaptation dimensions, environmental impact dimensions, and equipment health dimensions; wherein, the core evaluation index of the electrical parameter dimension is at least one of voltage deviation, current distortion rate, active power fluctuation, and reactive power compensation response speed; the auxiliary evaluation index of the electrical parameter dimension is at least one of insulation resistance, temperature rise rate, and harmonic content; the core evaluation index of the grid connection adaptation dimension is frequency response speed, phase tracking accuracy, islanding detection sensitivity, and grid connection... The evaluation indicators for the impact suppression effect are at least one of the following: voltage ride-through capability and power factor adjustment range; the core evaluation indicators for the environmental impact dimension are at least one of temperature and humidity compatibility coefficient, wind and dust erosion degree, and electromagnetic interference intensity; the auxiliary evaluation indicators for the environmental impact dimension are at least one of altitude correction coefficient and diurnal temperature difference influence value; the core evaluation indicators for the equipment health dimension are at least one of component aging rate, mechanical vibration amplitude, insulation aging degree, and cooling system efficiency; and the auxiliary evaluation indicators for the equipment health dimension are at least one of historical failure frequency and maintenance cycle compliance rate.

[0011] Based on the above technical means, the embodiments of this application comprehensively cover electrical performance, grid connection behavior, environmental adaptability and equipment health status through a multi-dimensional evaluation index system, taking into account both core operating indicators and auxiliary status parameters, significantly improving the systematicness and engineering practicality of stability evaluation of new energy grid-connected equipment.

[0012] Optionally, in one embodiment of this application, the step of collecting multi-dimensional indicator data of the target electrical equipment based on a pre-constructed multi-dimensional evaluation indicator system includes: detecting whether the grid-connected power fluctuation coefficient is greater than or equal to a preset fluctuation threshold based on a target hierarchical sampling strategy; when the grid-connected power fluctuation coefficient is detected to be greater than or equal to the preset fluctuation threshold, collecting the core evaluation indicators of the electrical parameter dimension and the core evaluation indicators of the grid-connected adaptation dimension using a target high-frequency sampling mode; when the grid-connected power fluctuation coefficient is detected to be less than the preset fluctuation threshold, collecting the core evaluation indicators and auxiliary evaluation indicators of the electrical parameter dimension, the core evaluation indicators and auxiliary evaluation indicators of the grid-connected adaptation dimension, the core evaluation indicators and auxiliary evaluation indicators of the environmental impact dimension, and the core evaluation indicators and auxiliary evaluation indicators of the equipment health dimension using a target conventional sampling mode.

[0013] Based on the above technical means, the embodiments of this application dynamically adjust the sampling mode according to the grid-connected power fluctuation based on the hierarchical sampling strategy. When the fluctuation is high, the key indicators are focused to improve the response sensitivity, and when the fluctuation is low, multi-dimensional data is collected in a balanced manner to ensure the comprehensiveness of the evaluation, effectively taking into account the system's real-time performance, resource efficiency and evaluation accuracy.

[0014] Optionally, in one embodiment of this application, the step of performing feature enhancement processing on the multi-dimensional indicator data to generate processed enhanced features includes: extracting the time-series features of each dimension indicator in the multi-dimensional indicator data to obtain the trend features, peak features, and abrupt change features of each dimension indicator data; calculating the correlation strength between the core evaluation indicators of each dimension based on the Pearson correlation coefficient and mutual information entropy to form strongly correlated indicator pairs; fusing the strongly correlated indicator pairs to generate cross-dimensional composite features, wherein the cross-dimensional composite features include electrical-grid-connection adaptation composite features and environmental-equipment health composite features; and fusing the trend features, peak features, and abrupt change features of each dimension indicator data with the cross-dimensional composite features to generate the processed enhanced features.

[0015] Based on the above technical means, the embodiments of this application can integrate the nonlinear correlation between single-dimensional time-series dynamic characteristics and cross-dimensional indicators to construct composite features with physical meaning, which significantly improves the feature's ability to characterize and distinguish the stability state of the equipment.

[0016] Optionally, in one embodiment of this application, the step of using a fuzzy comprehensive evaluation module and a Markov chain prediction module to perform a stability assessment on the target electrical equipment for grid connection of the new energy power, and outputting the stability assessment result of the target electrical equipment, includes: establishing fuzzy membership functions for each indicator using the fuzzy comprehensive evaluation module, and determining fuzzy evaluation vectors for each dimension based on the fuzzy membership functions of each indicator; performing weighted fusion of the fuzzy evaluation vectors for each dimension based on the dynamic weights, and obtaining the current comprehensive fuzzy evaluation result using fuzzy synthesis matrix operations; constructing a state transition matrix using the Markov chain prediction module in conjunction with the historical stability assessment results of the target electrical equipment, and predicting the stability state transition probability of the target electrical equipment within a future preset time period based on the state transition matrix and the current comprehensive fuzzy evaluation result; and combining the current comprehensive fuzzy evaluation result with the state transition probability to output the stability assessment result of the target electrical equipment.

[0017] Based on the above technical means, the embodiments of this application can integrate the precise characterization of the current state by fuzzy comprehensive evaluation with the learning ability of Markov chains to learn the laws of historical evolution, so as to achieve the synergistic output of stability status determination and trend prediction, and significantly improve the comprehensiveness, foresight and decision support capabilities of the evaluation results.

[0018] A second aspect of this application provides a multi-dimensional electrical equipment stability assessment device for grid-connected new energy power, comprising: a data acquisition module, configured to acquire multi-dimensional index data of a target electrical equipment based on a pre-constructed multi-dimensional assessment index system, and perform feature enhancement processing on the multi-dimensional index data to generate processed enhanced features; an acquisition module, configured to adjust the weight ratio of each dimension and corresponding index in the multi-dimensional index data based on the grid-connected power fluctuation coefficient and the equipment operation stage coefficient of the target electrical equipment, so as to obtain the dynamic weight of each dimension and corresponding index; and an assessment module, configured to input the processed enhanced features and the dynamic weight of each dimension and corresponding index into a pre-constructed assessment model that integrates fuzzy comprehensive evaluation and Markov chain prediction, and use the fuzzy comprehensive evaluation module and the Markov chain prediction module to perform stability assessment on the target electrical equipment for grid-connected new energy power, so as to output the stability assessment result of the target electrical equipment.

[0019] Based on the above technical means, the embodiments of this application can improve the accuracy and practicality of evaluating the stability of grid-connected electrical equipment for new energy sources by integrating interpretable enhanced features with dynamic weights that are adaptive to operating conditions, and combining fuzzy comprehensive evaluation and Markov chain prediction, thereby effectively ensuring the safe and stable operation of the power grid under a high proportion of new energy access.

[0020] Optionally, in one embodiment of this application, the apparatus further includes: a determining module, configured to determine the current stability level and the stability trend within a preset future time period of the target electrical equipment based on the stability assessment result after outputting the stability assessment result of the target electrical equipment; and a generating module, configured to link the current stability level and the stability trend within the preset future time period with the new energy grid-connected scheduling system after outputting the stability assessment result of the target electrical equipment, to generate operation and maintenance suggestions and grid connection parameter adjustment strategies for the target electrical equipment.

[0021] Based on the above technical means, the embodiments of this application can automatically generate targeted operation and maintenance suggestions and grid connection parameter optimization strategies by integrating stability level and trend prediction into the scheduling system, thereby improving the safety, reliability and intelligence level of new energy grid connection.

[0022] Optionally, in one embodiment of this application, the apparatus further includes: a construction module, configured to construct a multi-dimensional evaluation index system for the target electrical equipment based on electrical parameter dimensions, grid connection adaptation dimensions, environmental impact dimensions, and equipment health dimensions before collecting multi-dimensional index data of the target electrical equipment; wherein, the core evaluation index of the electrical parameter dimension is at least one of voltage deviation, current distortion rate, active power fluctuation, and reactive power compensation response speed; the auxiliary evaluation index of the electrical parameter dimension is at least one of insulation resistance, temperature rise rate, and harmonic content; and the core evaluation index of the grid connection adaptation dimension is frequency response speed, phase tracking accuracy, and islanding. The evaluation indicators for the grid connection adaptation dimension are at least one of the following: detection sensitivity and grid connection impact suppression effect; the auxiliary evaluation indicators for the grid connection adaptation dimension are at least one of the following: voltage ride-through capability and power factor adjustment range; the core evaluation indicators for the environmental impact dimension are at least one of the following: temperature and humidity adaptation coefficient, wind and dust erosion degree, and electromagnetic interference intensity; the auxiliary evaluation indicators for the environmental impact dimension are at least one of the following: altitude correction coefficient and diurnal temperature difference influence value; the core evaluation indicators for the equipment health dimension are at least one of the following: component aging rate, mechanical vibration amplitude, insulation aging degree, and cooling system efficiency; the auxiliary evaluation indicators for the equipment health dimension are at least one of the following: historical failure frequency and maintenance cycle compliance rate.

[0023] Based on the above technical means, the embodiments of this application comprehensively cover electrical performance, grid connection behavior, environmental adaptability and equipment health status through a multi-dimensional evaluation index system, taking into account both core operating indicators and auxiliary status parameters, significantly improving the systematicness and engineering practicality of stability evaluation of new energy grid-connected equipment.

[0024] Optionally, in one embodiment of this application, the acquisition module includes: a detection unit, configured to detect whether the grid-connected power fluctuation coefficient is greater than or equal to a preset fluctuation threshold based on a target hierarchical sampling strategy; a first acquisition unit, configured to acquire, using a target high-frequency sampling mode, the core evaluation indicators of the electrical parameter dimension and the core evaluation indicators of the grid-connected adaptation dimension when the grid-connected power fluctuation coefficient is detected to be greater than or equal to the preset fluctuation threshold; and a second acquisition unit, configured to acquire, using a target conventional sampling mode, the core evaluation indicators and auxiliary evaluation indicators of the electrical parameter dimension, the core evaluation indicators and auxiliary evaluation indicators of the grid-connected adaptation dimension, the core evaluation indicators and auxiliary evaluation indicators of the environmental impact dimension, and the core evaluation indicators and auxiliary evaluation indicators of the equipment health dimension when the grid-connected power fluctuation coefficient is detected to be less than the preset fluctuation threshold.

[0025] Based on the above technical means, the embodiments of this application dynamically adjust the sampling mode according to the grid-connected power fluctuation based on the hierarchical sampling strategy. When the fluctuation is high, the key indicators are focused to improve the response sensitivity, and when the fluctuation is low, multi-dimensional data is collected in a balanced manner to ensure the comprehensiveness of the evaluation, effectively taking into account the system's real-time performance, resource efficiency and evaluation accuracy.

[0026] Optionally, in one embodiment of this application, the acquisition module includes: an extraction unit, configured to extract the time-series features of each dimension indicator in the multi-dimensional indicator data to obtain the trend features, peak features, and abrupt change features of each dimension indicator data; a calculation unit, configured to calculate the correlation strength between the core evaluation indicators of each dimension based on the Pearson correlation coefficient and mutual information entropy, so as to form strongly correlated indicator pairs; a generation unit, configured to perform feature fusion on the strongly correlated indicator pairs to generate cross-dimensional composite features, wherein the cross-dimensional composite features include electrical-grid-connection adaptation composite features and environmental-equipment health composite features; and a fusion unit, configured to fuse the trend features, peak features, and abrupt change features of each dimension indicator data with the cross-dimensional composite features to generate the processed enhanced features.

[0027] Based on the above technical means, the embodiments of this application can integrate the nonlinear correlation between single-dimensional time-series dynamic characteristics and cross-dimensional indicators to construct composite features with physical meaning, which significantly improves the feature's ability to characterize and distinguish the stability state of the equipment.

[0028] Optionally, in one embodiment of this application, the evaluation module includes: an establishment unit, configured to establish fuzzy membership functions for each indicator using a fuzzy comprehensive evaluation module, and determine fuzzy evaluation vectors for each dimension based on the fuzzy membership functions of each indicator; a weighted fusion unit, configured to perform weighted fusion of the fuzzy evaluation vectors for each dimension based on the dynamic weights, and obtain the current comprehensive fuzzy evaluation result using fuzzy synthesis matrix operations; a prediction unit, configured to construct a state transition matrix using a Markov chain prediction module combined with the historical stability evaluation results of the target electrical equipment, and predict the stability state transition probability of the target electrical equipment within a future preset time period based on the state transition matrix and the current comprehensive fuzzy evaluation result; and an evaluation unit, configured to combine the current comprehensive fuzzy evaluation result with the state transition probability, and output the stability evaluation result of the target electrical equipment.

[0029] Based on the above technical means, the embodiments of this application can integrate the precise characterization of the current state by fuzzy comprehensive evaluation with the learning ability of Markov chains to learn the laws of historical evolution, so as to achieve the synergistic output of stability status determination and trend prediction, and significantly improve the comprehensiveness, foresight and decision support capabilities of the evaluation results.

[0030] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the multi-dimensional electrical equipment stability assessment method for new energy power grid connection as described in the above embodiments.

[0031] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for evaluating the stability of electrical equipment connected to the grid for new energy power.

[0032] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, is used to implement the above-mentioned multi-dimensional electrical equipment stability assessment method for grid connection of new energy power.

[0033] This application embodiment can collect multi-dimensional index data of target electrical equipment based on a multi-dimensional evaluation index system, perform feature enhancement processing to generate enhanced features, and then adjust the weight ratio of each dimension and corresponding index in the multi-dimensional index data based on the grid-connected power fluctuation coefficient and equipment operation stage coefficient to obtain dynamic weights. Next, the processed enhanced features and dynamic weights are input into an evaluation model that integrates fuzzy comprehensive evaluation and Markov chain prediction to conduct a stability evaluation of the target electrical equipment connected to the grid with new energy power, outputting the stability evaluation results of the target electrical equipment. This effectively improves the evaluation accuracy and practicality, and provides a scientific basis for grid-connected scheduling optimization and equipment operation and maintenance. Therefore, it solves the problem in related technologies that cannot provide forward-looking decision support for preventive maintenance and grid-connected scheduling, making it difficult to ensure the safe and stable operation of the power grid under a high proportion of new energy access.

[0034] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0035] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a multi-dimensional electrical equipment stability assessment method for grid connection of new energy power, according to an embodiment of this application. Figure 2 A flowchart illustrating a multi-dimensional electrical equipment stability assessment method for new energy power grid connection according to a specific embodiment of this application; Figure 3 This is a schematic diagram of a multi-dimensional electrical equipment stability assessment device for new energy power grid connection provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0036] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0037] The following describes a method and apparatus for multi-dimensional stability assessment of electrical equipment for new energy power grid connection, based on embodiments of the present application, with reference to the accompanying drawings. Addressing the problem mentioned in the background section of the related technologies that cannot provide forward-looking decision support for preventative maintenance and grid-connected dispatch, making it difficult to ensure the safe and stable operation of the power grid under high-proportion new energy access, this application provides a method for multi-dimensional stability assessment of electrical equipment for new energy power grid connection. In this method, multi-dimensional indicator data of the target electrical equipment is collected based on a multi-dimensional assessment index system, and feature enhancement processing is performed to generate enhanced features. Then, based on the grid-connected power fluctuation coefficient and the equipment operation stage coefficient, the weight ratio of each dimension and corresponding indicator in the multi-dimensional indicator data is adjusted to obtain dynamic weights. Next, the enhanced features and dynamic weights are input into an assessment model that integrates fuzzy comprehensive evaluation and Markov chain prediction to assess the stability of the target electrical equipment for new energy power grid connection, outputting the stability assessment results of the target electrical equipment. This effectively improves the assessment accuracy and practicality, and provides a scientific basis for grid-connected dispatch optimization and equipment operation and maintenance. Therefore, it solves the problem in the related technologies that cannot provide forward-looking decision support for preventative maintenance and grid-connected dispatch, making it difficult to ensure the safe and stable operation of the power grid under high-proportion new energy access.

[0038] Specifically, Figure 1 This is a flowchart illustrating a multi-dimensional electrical equipment stability assessment method for grid connection of new energy power, provided in an embodiment of this application.

[0039] like Figure 1 As shown, the multi-dimensional electrical equipment stability assessment method for grid-connected new energy power includes the following steps: In step S101, based on the pre-constructed multi-dimensional evaluation index system, multi-dimensional index data of the target electrical equipment are collected, and feature enhancement processing is performed on the multi-dimensional index data to generate enhanced features.

[0040] In this embodiment of the application, the target electrical equipment is a multi-dimensional electrical equipment for grid connection of new energy power that requires stability assessment.

[0041] It is understood that the embodiments of this application can collect multi-dimensional indicator data of the target electrical equipment based on a multi-dimensional evaluation indicator system. For example, the embodiments of this application can pre-construct the multi-dimensional evaluation indicator system in the following steps, wherein the multi-dimensional evaluation indicator system covers electrical parameter dimension, grid connection adaptation dimension, environmental impact dimension, and equipment health dimension, and each dimension is configured with core evaluation indicators and auxiliary evaluation indicators. Next, the embodiments of this application can collect indicator data of each dimension based on the dynamic data collection of the grid connection characteristics of new energy, and collect the index data of each dimension through the hierarchical sampling strategy in the following steps, taking into account the inherent characteristics of the volatility and intermittency of photovoltaic grid connection and wind power grid connection, and simultaneously collect and record the grid power fluctuation coefficient and grid frequency deviation, wherein the recorded data provides the basis for the hierarchical sampling execution and dynamic weight allocation in the following steps.

[0042] Secondly, the embodiments of this application can perform feature enhancement processing on multi-dimensional indicator data in the following steps. For example, the embodiments of this application can perform anomaly removal, time sequence alignment and standardization processing on the collected multi-dimensional data, and use the correlation feature extraction algorithm to mine the potential correlation features of cross-dimensional indicators to generate the processed enhanced features, which effectively improves the feasibility of multi-dimensional electrical equipment stability assessment for new energy power grid connection.

[0043] Optionally, in one embodiment of this application, before collecting multi-dimensional indicator data of the target electrical equipment, the method further includes: constructing a multi-dimensional evaluation indicator system for the target electrical equipment based on electrical parameter dimensions, grid connection adaptation dimensions, environmental impact dimensions, and equipment health dimensions; wherein, the core evaluation indicators of the electrical parameter dimension are at least one of voltage deviation, current distortion rate, active power fluctuation, and reactive power compensation response speed; the auxiliary evaluation indicators of the electrical parameter dimension are at least one of insulation resistance, temperature rise rate, and harmonic content; and the core evaluation indicators of the grid connection adaptation dimension are frequency response speed, phase tracking accuracy, islanding detection sensitivity, and [other parameters not specified in the original text]. At least one of the following is considered in the grid impact suppression effect; at least one of the following is considered in the auxiliary evaluation indicators of grid connection adaptation dimension: voltage ride-through capability and power factor adjustment range; at least one of the following is considered in the core evaluation indicators of environmental impact dimension: temperature and humidity adaptation coefficient, degree of wind and dust erosion and electromagnetic interference intensity; at least one of the following is considered in the auxiliary evaluation indicators of environmental impact dimension: altitude correction coefficient and diurnal temperature difference influence value; at least one of the following is considered in the core evaluation indicators of equipment health dimension: component aging rate, mechanical vibration amplitude, degree of insulation aging and cooling system efficiency; at least one of the following is considered in the auxiliary evaluation indicators of equipment health dimension: historical failure frequency and maintenance cycle compliance rate.

[0044] For example, embodiments of this application can pre-construct a multi-dimensional evaluation index system, which covers electrical parameter dimensions, grid connection adaptation dimensions, environmental impact dimensions, and equipment health dimensions. Each dimension is configured with core evaluation indicators and auxiliary evaluation indicators. Among them, the core evaluation indicators of the electrical parameter dimension are voltage deviation, current distortion rate, active power fluctuation, and reactive power compensation response speed. The calculation method of the core evaluation indicators of the electrical parameter dimension is as follows: Voltage deviation = (Measured voltage - Rated voltage) / Rated voltage; Current distortion rate = total effective value of harmonic current / effective value of fundamental current; Active power fluctuation = (maximum active power - minimum active power) / average active power; Reactive power compensation response speed = the time required from the occurrence of reactive power deviation to the point where compensation reaches the target.

[0045] Next, the auxiliary evaluation indicators for the electrical parameters dimension are insulation resistance, temperature rise rate, and harmonic content; the core evaluation indicators for the grid connection adaptation dimension are frequency response speed, phase tracking accuracy, islanding detection sensitivity, and grid connection impact suppression effect; among them, the frequency response speed of the grid connection adaptation dimension can be determined by applying grid frequency disturbances when the grid power fluctuation coefficient is in a medium fluctuation range, and recording the response time of the equipment from frequency deviation to recovery to the allowable range; the phase tracking accuracy is the absolute value of the difference between the phase of the equipment output voltage and the phase of the grid voltage.

[0046] Secondly, the auxiliary evaluation indicators for grid connection adaptability are voltage ride-through capability and power factor adjustment range; the core evaluation indicators for environmental impact are temperature and humidity adaptability coefficient, wind and dust erosion degree, and electromagnetic interference intensity; the auxiliary evaluation indicators for environmental impact are altitude correction coefficient and diurnal temperature difference impact value; the core evaluation indicators for equipment health are component aging rate, mechanical vibration amplitude, insulation aging degree, and cooling system efficiency; and the auxiliary evaluation indicators for equipment health are historical failure frequency and maintenance cycle compliance rate. Therefore, the multi-dimensional evaluation indicator system in this application embodiment, by integrating electrical performance, grid connection behavior, environmental adaptability, and equipment health status, comprehensively covers the key influencing factors of the stability of new energy grid-connected equipment, significantly improving the foresight of the evaluation.

[0047] Optionally, in one embodiment of this application, multi-dimensional indicator data of the target electrical equipment are collected based on a pre-constructed multi-dimensional evaluation indicator system, including: detecting whether the grid-connected power fluctuation coefficient is greater than or equal to a preset fluctuation threshold based on a target hierarchical sampling strategy; when the grid-connected power fluctuation coefficient is detected to be greater than or equal to the preset fluctuation threshold, collecting core evaluation indicators of the electrical parameter dimension and core evaluation indicators of the grid-connected adaptation dimension using a target high-frequency sampling mode; when the grid-connected power fluctuation coefficient is detected to be less than the preset fluctuation threshold, collecting core evaluation indicators and auxiliary evaluation indicators of the electrical parameter dimension, core evaluation indicators and auxiliary evaluation indicators of the grid-connected adaptation dimension, core evaluation indicators and auxiliary evaluation indicators of the environmental impact dimension, and core evaluation indicators and auxiliary evaluation indicators of the equipment health dimension using a target conventional sampling mode.

[0048] In actual implementation, the embodiments of this application can detect whether the grid-connected power fluctuation coefficient is greater than or equal to the preset fluctuation threshold based on the target hierarchical sampling strategy. When the grid-connected power fluctuation coefficient is detected to be greater than or equal to the preset fluctuation threshold, sampling is performed during high fluctuation periods, that is, a high-frequency sampling mode is adopted, with a sampling frequency higher than that during low fluctuation periods. The core evaluation indicators of electrical parameter dimension and grid-connected adaptation dimension are collected. The preset fluctuation threshold is set in combination with the rated power of the equipment and the grid tolerance range.

[0049] When the grid-connected power fluctuation coefficient is detected to be less than the preset fluctuation threshold, sampling is performed during low fluctuation periods. That is, the conventional sampling mode is adopted to collect data of various dimensions in a balanced manner, such as the core and auxiliary evaluation indicators of electrical parameters, the core and auxiliary evaluation indicators of grid-connected adaptability, the core and auxiliary evaluation indicators of environmental impact, and the core and auxiliary evaluation indicators of equipment health.

[0050] Furthermore, the embodiments of this application can also include a sampling synchronization mechanism, which uses GPS (Global Positioning System) timestamps to achieve data synchronization of multi-source acquisition devices and perform data association marking, that is, each piece of acquired data is bound to a grid-connected scenario label, a power fluctuation range label and a device operating status label, and the grid-connected scenario label covers photovoltaic grid connection, wind power grid connection and hybrid grid connection.

[0051] Optionally, in one embodiment of this application, feature enhancement processing is performed on multi-dimensional indicator data to generate enhanced features, including: extracting the time-series features of each dimension indicator in the multi-dimensional indicator data to obtain the trend features, peak features, and abrupt change features of each dimension indicator data; calculating the correlation strength between the core evaluation indicators of each dimension based on the Pearson correlation coefficient and mutual information entropy to form strongly correlated indicator pairs; fusing the strongly correlated indicator pairs to generate cross-dimensional composite features, wherein the cross-dimensional composite features include electrical-grid-connection adaptation composite features and environmental-equipment health composite features; and fusing the trend features, peak features, and abrupt change features of each dimension indicator data with the cross-dimensional composite features to generate enhanced features.

[0052] In the embodiments of this application, the processed enhanced features include extracted single-dimensional features and cross-dimensional composite features.

[0053] As one possible approach, this embodiment can first perform single-dimensional feature extraction, that is, extract time-series features from the indicator data of each dimension to obtain trend features, peak features, and abrupt change features. Next, this embodiment can perform cross-dimensional correlation analysis, that is, calculate the correlation strength between core evaluation indicators of different dimensions based on Pearson correlation coefficient and mutual information entropy, and select strongly correlated indicator pairs. Then, feature fusion is performed on the strongly correlated indicators to generate cross-dimensional composite features, including electrical-grid-connection adaptation composite features and environmental-equipment health composite features. Furthermore, this embodiment can also perform dimensionality reduction optimization on the fused features, i.e., the high-dimensional fused features, using principal component analysis (PCA) to reduce the dimensionality of the high-dimensional fused features, retaining principal component features with a cumulative contribution rate that meets the requirements. The cumulative contribution rate is determined by combining feature discriminability and computational efficiency. This effectively improves the discriminative power, robustness, and computational efficiency of the features, laying a data foundation for subsequent high-precision stability assessment.

[0054] In step S102, based on the grid-connected power fluctuation coefficient and the equipment operation stage coefficient of the target electrical equipment, the weight ratio of each dimension and corresponding indicator in the multi-dimensional indicator data is adjusted to obtain the dynamic weight of each dimension and corresponding indicator.

[0055] It is understood that the embodiments of this application can combine the grid-connected power fluctuation coefficient and the equipment operation stage, and dynamically adjust the weight ratio of each dimension and indicator through an improved analytic hierarchy process. First, the weight allocation factor is determined, which includes the grid-connected power fluctuation coefficient, the equipment operation stage coefficient, and the indicator correlation strength coefficient. Next, the operation stage is divided into the start-up stage, the stable operation stage, the high load stage, and the shutdown stage, with each stage corresponding to a specific stage coefficient. Second, the improved analytic hierarchy process is performed. Based on the importance judgment matrix of each dimension indicator, the weight allocation factor is introduced to correct the judgment matrix. After consistency verification, the dynamic weights of each dimension and indicator are obtained.

[0056] Furthermore, this embodiment of the application can also perform real-time weight updates. When the weight update cycle or the change in the grid-connected power fluctuation coefficient meets the fluctuation range, the weight allocation process is restarted. The weight update cycle and fluctuation range are set in conjunction with the new energy power fluctuation cycle and equipment response characteristics. Thus, this embodiment of the application can achieve adaptive adjustment and real-time updating of weights through an improved analytic hierarchy process, significantly improving the sensitivity and adaptability of the evaluation model to different operating states of the equipment.

[0057] Therefore, the embodiments of this application can design a hierarchical sampling strategy based on the characteristics of new energy power fluctuations, thereby achieving the accuracy and efficiency of evaluation data collection. Through the correlation feature extraction and dynamic weight allocation mechanism, it can deeply explore the potential relationship between cross-dimensional indicators and dynamically adjust the evaluation focus according to the real-time operating conditions (power fluctuations, equipment stages), so that the evaluation model has adaptive capabilities.

[0058] In step S103, the processed enhanced features and the dynamic weights of each dimension and corresponding index are input into the pre-constructed evaluation model that integrates fuzzy comprehensive evaluation and Markov chain prediction. The fuzzy comprehensive evaluation module and the Markov chain prediction module are used to evaluate the stability of the target electrical equipment for grid connection of new energy power, so as to output the stability evaluation results of the target electrical equipment.

[0059] It is understood that, in this application embodiment, the enhanced features processed in the above steps and the dynamic weights of each dimension and corresponding index can be input into the evaluation model that integrates fuzzy comprehensive evaluation and Markov chain prediction constructed in the following steps. The fuzzy comprehensive evaluation module and the Markov chain prediction module are used to evaluate the stability of the target electrical equipment for grid connection of new energy power, so as to output the stability evaluation results of the target electrical equipment, such as the current stability level of the electrical equipment and the stability trend within a preset time period. Thus, this application embodiment can improve the stability of multi-dimensional electrical equipment evaluation for grid connection of new energy power, and effectively ensure the safe and stable operation of the power grid under high proportion of new energy access.

[0060] Therefore, it can be seen that the embodiments of this application, by integrating fuzzy comprehensive evaluation and Markov chain prediction, can not only output the current accurate stability level, but also make probabilistic predictions of future trends. The evaluation results form a closed-loop linkage with the operation and maintenance and scheduling system, which can automatically generate targeted equipment maintenance suggestions and grid connection parameter adjustment instructions, and feed the effects back to the evaluation model for continuous optimization.

[0061] Optionally, in one embodiment of this application, after outputting the stability assessment results of the target electrical equipment, the method further includes: determining the current stability level and the stability trend within a preset time period of the target electrical equipment based on the stability assessment results; linking the current stability level and the stability trend within a preset time period with the new energy grid-connected scheduling system to generate operation and maintenance suggestions and grid-connected parameter adjustment strategies for the target electrical equipment.

[0062] In some embodiments, the embodiments of this application can determine the current stability level and the stability trend of the target electrical equipment within a preset time period based on the stability assessment results, link the assessment results with the new energy grid-connected scheduling system, generate equipment operation and maintenance suggestions and grid-connected parameter adjustment strategies, and form a closed-loop optimization mechanism.

[0063] The stability level can be categorized as extremely stable, stable, basically stable, critically unstable, or unstable. When the stability level is basically stable or below, key influencing indicators and related dimensions are identified. Next, grid connection parameters are adjusted, i.e., based on the evaluation results of the grid connection adaptation dimension, power regulation, phase calibration, reactive power compensation optimization, and other parameter adjustment instructions are output to the new energy grid connection dispatch system. Finally, in the next evaluation cycle, the changes in indicators corresponding to the optimization measures are monitored to verify the effectiveness of the evaluation results and optimization measures.

[0064] Optionally, in one embodiment of this application, a fuzzy comprehensive evaluation module and a Markov chain prediction module are used to perform a stability assessment on the target electrical equipment for grid connection of new energy power, so as to output the stability assessment result of the target electrical equipment. This includes: using the fuzzy comprehensive evaluation module to establish fuzzy membership functions for each index, and determining the fuzzy evaluation vector for each dimension based on the fuzzy membership functions of each index; weighting and fusing the fuzzy evaluation vectors for each dimension based on dynamic weights, and using fuzzy synthesis matrix operations to obtain the current comprehensive fuzzy evaluation result; using the Markov chain prediction module to construct a state transition matrix in combination with the historical stability assessment results of the target electrical equipment, and predicting the stability state transition probability of the target electrical equipment within a future preset time period based on the state transition matrix and the current comprehensive fuzzy evaluation result; and combining the current comprehensive fuzzy evaluation result with the state transition probability to output the stability assessment result of the target electrical equipment.

[0065] As one possible implementation, this application embodiment can receive preprocessed multi-dimensional index data, i.e., processed enhanced features and dynamic weights, at the input layer of the evaluation model. Next, a fuzzy membership function for each index is established using a fuzzy comprehensive evaluation module. The fuzzy evaluation vector for each dimension is calculated using dynamic weights, and a comprehensive fuzzy evaluation result is obtained through matrix operations. Then, a state transition matrix is ​​constructed based on historical stability assessment results using a Markov chain prediction module. Combined with the current comprehensive fuzzy evaluation result, the stability state transition probability within a preset time period is predicted, where the preset time period is set in conjunction with the operation and maintenance scheduling decision cycle. Finally, the comprehensive fuzzy evaluation result is combined with the state transition probability to output the stability level and trend prediction result, thereby achieving an integrated and highly reliable assessment of the current status and future trends of the stability of new energy grid-connected electrical equipment, effectively supporting proactive operation and maintenance and scheduling decisions.

[0066] It should be noted that the fuzzy membership function in this embodiment adopts a combination of triangular membership function and trapezoidal membership function. The core evaluation index corresponds to the triangular membership function, and the auxiliary evaluation index corresponds to the trapezoidal membership function. The update period of the state transition matrix is ​​consistent with the weight update period, and each update is based on the latest historical evaluation data and equipment operation status data.

[0067] For example, the working principle of the embodiments of this application will be described in detail below with a specific example.

[0068] Step S201: Construct a multi-dimensional evaluation index system, which covers electrical parameter dimension, grid connection adaptation dimension, environmental impact dimension and equipment health dimension.

[0069] Step S202: Dynamic data acquisition (layered sampling / synchronous recording). In other words, the embodiments of this application can collect data of various dimensions of indicators through a layered sampling strategy to take into account the inherent characteristics of the volatility and intermittency of photovoltaic grid connection and wind power grid connection, and synchronously collect and record the grid power fluctuation coefficient and grid frequency deviation.

[0070] Step S203: Data preprocessing and feature enhancement. In other words, the embodiments of this application can perform anomaly removal, time sequence alignment and standardization on the collected multi-dimensional data, and use the correlation feature extraction algorithm to mine the potential correlation features of cross-dimensional indicators.

[0071] Step S204: Dynamic weight allocation (improved analytic hierarchy process), that is, the embodiments of this application can combine the grid-connected power fluctuation coefficient and the equipment operation stage, and dynamically adjust the weight ratio of each dimension and indicator through the improved analytic hierarchy process.

[0072] Step S205: Stability grading assessment (fuzzy comprehensive and Markov prediction), that is, the embodiments of this application can construct an assessment model that integrates fuzzy comprehensive evaluation and Markov chain prediction, and output the current stability level of electrical equipment and the stability trend within a preset time period in the future.

[0073] Step S206: Result feedback and closed-loop optimization (linking operation and maintenance with scheduling system). In other words, the embodiments of this application can link the evaluation results with the new energy grid-connected scheduling system to generate equipment operation and maintenance suggestions and grid-connected parameter adjustment strategies, forming a closed-loop optimization mechanism.

[0074] For example, the embodiments of this application are applied to a photovoltaic-wind power hybrid grid-connected system in an industrial park, involving core electrical equipment including 2 110kV transformers, 15 photovoltaic inverters, 8 wind power converters, 12 high-voltage switchgear cabinets, and 3 sets of reactive power compensation devices. Based on this, the embodiments of this application will be further described through the following steps.

[0075] I. Hardware Deployment Data acquisition layer: One set of electrical parameter sensors is deployed on each of the high and low voltage sides of the transformer, a load status monitor is deployed at the output end of the inverter / converter, environmental sensors and contact status monitors are deployed inside the switch cabinet, and a frequency / voltage monitoring device is deployed at the grid-connected bus. All acquisition devices have industrial-grade protection capabilities and real-time data transmission functions. Data processing layer: Deploy 3 industrial-grade servers as core processing nodes, configured with multi-core processors and large-capacity memory, supporting parallel computing and multi-task scheduling; Storage layer: A distributed time-series database cluster is used to store the collected raw data, preprocessed data, feature sets, evaluation results and historical logs, supporting high-concurrency read and write and data backtracking; Communication layer: Adopts a hybrid communication architecture of industrial Ethernet + wireless private network. Data acquisition equipment and processing nodes are transmitted via wired industrial Ethernet, while wind power equipment in remote areas is transmitted via wireless private network. Application layer: Connects to the industrial park's new energy grid connection scheduling system and equipment operation and maintenance management platform, and realizes data interaction and command issuance through standardized interfaces.

[0076] II. Software Environment Operating system: It adopts the Linux industrial operating system, which supports multi-threaded concurrent processing and high-reliability operation; Data processing framework: Developed based on Python, integrating NumPy and Pandas libraries for data preprocessing, and Scikit-learn library for feature extraction and algorithm computation; Evaluation Model Platform: Based on the TensorFlow framework, it builds fusion prediction models that support model training, iteration, and real-time inference; Communication protocol: MQTT (Message Queuing Telemetry Transport) is used to realize data transmission between acquisition devices and processing nodes, and IEC61850 protocol is used to realize linkage with grid-connected scheduling system.

[0077] 1. Monitoring of core evaluation indicators for electrical parameters: Voltage deviation is calculated by collecting measured voltages from high and low voltage side voltage sensors on the transformer and combining them with the rated voltage of the equipment; Current distortion rate is calculated by collecting current signals from current sensors at the inverter output terminal, separating the fundamental and harmonic components through Fourier transform; Active power fluctuation is calculated by collecting real-time active power from power sensors at the grid bus, statistically analyzing the fluctuation range; Reactive power compensation response speed is calculated by recording the time of deviation occurrence and the time of compensation reaching the target through the control module of the reactive power compensation device, and calculating the time difference. For monitoring auxiliary evaluation indicators of electrical parameters: insulation resistance is collected periodically by an insulation resistance tester to collect equipment insulation data; temperature rise rate is collected by a surface temperature sensor to collect temperature change data; and harmonic content is collected by a current / voltage sensor and the proportion of each harmonic is analyzed.

[0078] 2. Monitoring of core evaluation indicators for grid connection adaptation: Frequency response speed: frequency signals are collected by a grid-connected bus frequency monitoring device, and the recovery time after disturbance is recorded; Phase tracking accuracy: the phase difference between the output voltage of the device and the grid voltage is collected by a phase detector and the difference is calculated; Islanding detection sensitivity: the response time of the detection device is recorded by simulating islanding conditions; Grid connection surge suppression effect: the suppression effect is evaluated by monitoring the voltage / current surge peak at the moment of grid connection. For auxiliary evaluation indicators monitoring in grid connection adaptation: voltage ride-through capability is recorded by simulating voltage drop conditions and recording the continuous operating status of the equipment; power factor adjustment range is collected by a power factor meter to collect the range of power factor changes during equipment operation.

[0079] 3. Monitoring of core assessment indicators for environmental impact: Temperature and humidity compatibility coefficient: Data is collected from temperature and humidity sensors in the equipment deployment area, and the compatibility is calculated in combination with the equipment's allowable operating range; Wind and dust erosion level: Dust concentration is collected from dust sensors, and the erosion risk is assessed in combination with the equipment's protection level; Electromagnetic interference intensity: Electromagnetic signal intensity around the equipment is collected using an electromagnetic interference tester. For monitoring auxiliary assessment indicators of environmental impact: the altitude correction coefficient is calculated by combining the altitude of the industrial park with the rated altitude parameters of the equipment; the diurnal temperature difference impact value is analyzed by continuously monitoring diurnal temperature changes to analyze the impact on equipment operating parameters.

[0080] 4. Monitoring of core assessment indicators for equipment health: Component aging rate is comprehensively assessed by analyzing equipment operating years, load rate, and historical fault data; mechanical vibration amplitude is collected by vibration sensors installed on the equipment body; insulation aging degree is assessed by combining insulation resistance test data and operating years; cooling system efficiency is assessed by monitoring the inlet and outlet air temperature and flow rate of the cooling device to evaluate the heat dissipation effect. For monitoring auxiliary assessment indicators of equipment health: historical failure frequency is counted by querying equipment operation and maintenance logs; maintenance cycle compliance rate is calculated by comparing the actual maintenance cycle with the recommended maintenance cycle.

[0081] Secondly, for the implementation of the stratified sampling strategy, the fluctuation threshold is first determined by combining the rated power of core equipment such as transformers and inverters with the grid tolerance range, analyzing the impact of power fluctuations on equipment operation by statistically analyzing historical grid-connected power data, and determining the fluctuation threshold. Next, sampling during periods of high fluctuation: When the grid-connected power fluctuation coefficient reaches the fluctuation threshold, a high-frequency sampling mode is triggered. The sampling frequency of the core evaluation indicators of the electrical parameter dimension and the grid-connected adaptation dimension is automatically increased, focusing on sampling indicators directly related to grid-connected stability, such as voltage deviation and frequency response speed. Secondly, sampling during low fluctuation periods: when the grid-connected power fluctuation coefficient does not reach the fluctuation threshold, a conventional sampling mode is adopted to collect core and auxiliary evaluation indicators of each dimension in a balanced manner. Secondly, sampling synchronization is achieved: all acquisition devices are integrated with GPS modules, and time-series synchronization of multi-source data is achieved through GPS timestamps; Finally, data association and labeling: Each piece of collected data is automatically bound to a grid-connected scenario label, a power fluctuation range label, and an equipment operating status label. The grid-connected scenario label covers photovoltaic grid connection, wind power grid connection, and hybrid grid connection. The power fluctuation range label covers low fluctuation, medium fluctuation, and high fluctuation. The equipment operating status label covers startup, stable operation, high load, and shutdown.

[0082] Furthermore, for anomaly removal in data preprocessing: the 3σ criterion is used to detect anomalies in the data of each dimension, the mean and standard deviation of the data are calculated, and data exceeding the mean ± 3 times the standard deviation are identified as outliers and removed; for data in the environmental impact dimension such as wind and sand dust concentration and electromagnetic interference intensity that are easily affected by sudden factors, interpolation is used to supplement the data by combining data from adjacent time nodes. For time alignment in data preprocessing: using GPS timestamps as a reference, time alignment is performed on multi-source data from different acquisition devices, and non-isochronous data is interpolated into an isochronous sequence; For standardization in data preprocessing: Z-score standardization is used to normalize the data of each indicator to eliminate the differences in the units of measurement of different indicators.

[0083] Secondly, correlation feature extraction is performed. First, single-dimensional feature extraction is carried out: for electrical parameter dimension data, the sliding window method is used to extract trend features, peak features, and abrupt change features; for environmental impact dimension data, statistical methods are used to extract features such as mean and variance; and for equipment health dimension data, trend fitting is used to extract aging trend features. Secondly, cross-dimensional correlation analysis: the linear correlation strength between the core evaluation indicators of the electrical parameter dimension and the grid connection adaptation dimension is calculated based on the Pearson correlation coefficient, and the non-linear correlation strength between the core evaluation indicators of the environmental impact dimension and the equipment health dimension is calculated based on mutual information entropy. Indicator pairs with the required correlation strength are selected as strongly correlated indicator pairs. Secondly, feature fusion generation: The strongly correlated indicators are fused using methods such as weighted summation and multiplication to generate composite features of electrical-grid-connection adaptation and composite features of environment-equipment health. Finally, feature dimensionality reduction optimization can be performed: Principal component analysis algorithm is used to reduce the dimensionality of high-dimensional fusion features, calculate the contribution rate of each principal component, and retain the principal component features whose cumulative contribution rate meets the requirements.

[0084] Furthermore, the weighting factor can be determined for the grid-connected power fluctuation coefficient: calculated based on the preprocessed active power data, reflecting the degree of fluctuation of the current grid-connected power; For equipment operation phase coefficients: determined based on equipment operation status labels, the coefficients for startup and high load phases are higher than those for stable operation and shutdown phases; Regarding the correlation strength coefficient of indicators: Based on the results of cross-dimensional correlation analysis, the correlation strength coefficient of strongly correlated indicator pairs is higher than that of weakly correlated indicator pairs.

[0085] In addition, the improved analytic hierarchy process first determines the matrix construction: based on the importance of each dimension and indicator, an initial judgment matrix is ​​constructed, and the importance comparison between the electrical parameter dimension and the grid connection adaptation dimension is adjusted based on the degree of fluctuation in grid connection conditions. Judgment matrix correction: The initial judgment matrix is ​​corrected by introducing a weight allocation factor. During periods of high volatility, the weight of the grid connection adaptation dimension is increased, and during periods of high load, the weight of the device health dimension is increased. Consistency check: The corrected judgment matrix is ​​checked for consistency using a random consistency index. If the check fails, the elements of the judgment matrix are readjusted until the consistency requirements are met. Weight calculation: The eigenvector corresponding to the largest eigenvalue of the judgment matrix is ​​calculated by eigenvalue decomposition, and the dynamic weights of each dimension and indicator are obtained after normalization. Weight update trigger: When the weight update cycle is reached or the change in grid-connected power fluctuation coefficient meets the fluctuation range, the weight allocation process will be automatically re-executed.

[0086] Furthermore, for the construction of the integrated evaluation model, the first priority for the fuzzy comprehensive evaluation module is as follows: the core evaluation indicators adopt triangular membership functions, and the auxiliary evaluation indicators adopt trapezoidal membership functions, with parameters determined based on equipment technical specifications and power grid connection standards; the triangular membership functions of the core evaluation indicators are based on the allowable range of indicators for the equipment, dividing the intervals into five stability levels, and constructing membership curves with the midpoint of each interval as the vertex; the trapezoidal membership functions of the auxiliary evaluation indicators add flat-top intervals to the triangular membership functions to adapt to the smooth characteristics of the auxiliary indicators' impact on stability; firstly, the measured data of each indicator are substituted into the corresponding membership functions to obtain the single-indicator membership vector, and then the membership vectors of the core evaluation indicators and auxiliary evaluation indicators are weighted and summed according to dynamic weights to obtain the fuzzy evaluation vectors of each dimension; finally, the fuzzy evaluation vectors of each dimension are multiplied by the weight matrix formed by the dynamic weights of the dimensions to obtain the global comprehensive fuzzy evaluation vector; For the Markov chain prediction module: collect at least 12 months of historical stability assessment data, count the number of transitions from each stability state to other states, calculate the proportion of each transition path as the transition probability, construct a 5×5 state transition matrix, where rows represent the current state, columns represent future transition states, matrix elements are the corresponding transition probabilities, and the sum of all row elements is 1; consider the seasonal fluctuations of new energy grid connection conditions, and perform seasonal correction on the state transition matrix; take the level with the highest membership degree in the current comprehensive fuzzy evaluation vector as the current state, and combine it with the state transition matrix to calculate the probability of the current state transitioning to the other four states.

[0087] Finally, the embodiments of this application can output stability levels and trends, that is, based on the global comprehensive fuzzy evaluation vector, the current stability level is determined by the maximum membership degree principle; if two or more levels have the same membership degree value and are the highest, a second judgment is made in combination with the membership degree value of the core evaluation index, and the level with the higher membership degree of the core evaluation index is selected first. In addition, the path with the highest transition probability is selected as the main trend, and the probability distribution of each stability level within the preset time period is output simultaneously, and the trend credibility is marked. The credibility is calculated based on the historical prediction accuracy and the complexity of the current working condition. Finally, the results are standardized for output, meaning that the stability level and trend prediction results are output in a unified format, including information such as equipment number, evaluation time, current level, trend description, core influencing factors, probability distribution, and credibility. The output format is adapted to the data interaction requirements of the new energy grid-connected dispatch system and the equipment operation and maintenance management platform.

[0088] Furthermore, the embodiments of this application can perform evaluation result analysis, that is, locate key influencing indicators: when the stability level is basically stable or below, extract the indicators with high weight and low membership in the comprehensive fuzzy evaluation results as key influencing indicators; it can also perform influence path analysis: combine cross-dimensional correlation features to analyze the coupling influence of key influencing indicators on other indicators and clarify the correlation logic between each indicator.

[0089] Next, maintenance recommendations are generated: differentiated maintenance recommendations are formulated for key influencing indicators, specifying the implementing entity, operation content, and execution sequence; for example, when the key influencing indicator is the degree of insulation aging, recommendations are generated to shorten the insulation resistance testing cycle and to carry out special maintenance on the equipment insulation layer. Grid connection parameter adjustment: Based on the evaluation results of grid connection adaptation dimension, output parameter adjustment instructions to the new energy grid connection dispatch system. The instruction format conforms to the IEC61850 protocol specification. For example, when the frequency response speed is insufficient, output instructions to adjust the inverter frequency regulation coefficient and optimize the frequency response strategy of the wind power converter.

[0090] Finally, in the next evaluation cycle, focus on the changes in key impact indicators and related indicators, and improve their collection frequency and monitoring accuracy; compare the stability level and indicator data under the same operating conditions before and after optimization. If the stability level improves or the membership of key impact indicators increases, the optimization measures are deemed effective; if the expected results are not achieved, the evaluation results are re-analyzed, and the operation and maintenance recommendations and grid connection parameters are adjusted until the stability level meets the requirements.

[0091] It should be noted that the voltage deviation calculation in this application embodiment is as follows: the measured voltage is continuously collected by the high and low voltage side voltage sensors of the transformer, a set of data is recorded in each collection cycle, the average value of the measured voltage in that cycle is taken, and the voltage deviation calculation formula is substituted into it. The result is retained to two decimal places. Current distortion rate calculation: The three-phase current signal is collected by the current sensor at the inverter output terminal, and the signal is transmitted to the data processing node. After Fourier transform, it is decomposed into the fundamental current and each harmonic current, and the ratio of the total effective value of the harmonic current to the effective value of the fundamental current is calculated. Active power fluctuation calculation: Real-time active power data is collected by power sensors at the grid-connected bus, the maximum and minimum active power values ​​within an assessment period are statistically analyzed, and the values ​​are substituted into the active power fluctuation calculation formula to calculate the average value, which is the arithmetic mean of all active power data within that period. Reactive power compensation response speed calculation: The reactive power deviation is monitored in real time by the control module of the reactive power compensation device, and the time point when the deviation occurs and the time point when the standard is met are recorded. The time difference between the two is the reactive power compensation response speed.

[0092] For the core evaluation index test of grid-connected adaptation dimension in the embodiments of this application, such as frequency response speed test: when the grid-connected power fluctuation coefficient is in the medium fluctuation range, a step disturbance is applied to the power grid through the grid-connected dispatch system, and the monitoring equipment is monitored from the frequency deviating from the allowable range to the recovery to the allowable range. The response start time and recovery completion time are recorded, and the time difference between the two is the frequency response speed. Phase tracking accuracy test: The phase signals of the device output voltage and the grid voltage are simultaneously acquired by a phase detector. Two sets of phase data at the same time point are acquired and recorded synchronously. The absolute value of the difference between the two is calculated. The test is performed continuously for multiple cycles, and the average value is taken as the phase tracking accuracy index value.

[0093] In addition, the determination of the fuzzy membership function parameters in the embodiments of this application includes: Triangular membership function: Taking voltage deviation as an example, extremely stable corresponds to the optimal operating deviation range of the equipment, stable corresponds to the allowable operating deviation range of the equipment, and basically stable, critically unstable, and unstable levels correspond to progressively expanding deviation intervals. The midpoint of each interval is used as the vertex to construct a triangular membership function. Trapezoidal membership function: Taking insulation resistance as an example, extremely stable corresponds to the high value range of insulation resistance, in which the membership degree is always 1. Stable, basically stable, critically unstable, and unstable levels correspond to insulation resistance ranges that decrease sequentially. A trapezoidal membership function with a flat top is constructed.

[0094] Secondly, the construction and updating of the state transition matrix includes: Initial matrix construction: Based on historical stability assessment data, the number of transitions from each stability level to other levels is counted, the transition probability is calculated, and an initial state transition matrix is ​​constructed; Matrix update: The update period of the state transition matrix is ​​consistent with the weight update period. Each time it is updated, the stability level transition data of the latest period is included, the transition probability is recalculated, and the corresponding elements in the matrix are replaced.

[0095] In summary, the embodiments of this application provide an electrical equipment stability assessment method with dynamic adjustment capabilities and trend prediction functions, which improves the assessment accuracy and practicality, and provides a scientific basis for grid-connected scheduling optimization and equipment operation and maintenance.

[0096] The multi-dimensional electrical equipment stability assessment method for new energy power grid connection proposed in this application can collect multi-dimensional index data of target electrical equipment based on a multi-dimensional assessment index system, perform feature enhancement processing to generate enhanced features, and then adjust the weight ratio of each dimension and corresponding index in the multi-dimensional index data based on the grid-connected power fluctuation coefficient and equipment operation stage coefficient to obtain dynamic weights. Next, the enhanced features and dynamic weights are input into an assessment model that integrates fuzzy comprehensive evaluation and Markov chain prediction to assess the stability of the target electrical equipment for new energy power grid connection, and output the stability assessment results of the target electrical equipment. This effectively improves the assessment accuracy and practicality, and provides a scientific basis for grid-connected dispatch optimization and equipment operation and maintenance. Therefore, it solves the problem in related technologies that cannot provide forward-looking decision support for preventive maintenance and grid-connected dispatch, making it difficult to ensure the safe and stable operation of the power grid under high-proportion new energy access.

[0097] Next, referring to the accompanying drawings, a multi-dimensional electrical equipment stability assessment device for new energy power grid connection is described according to an embodiment of this application.

[0098] Figure 3 This is a block diagram of a multi-dimensional electrical equipment stability assessment device for new energy power grid connection according to an embodiment of this application.

[0099] like Figure 3 As shown, the multi-dimensional electrical equipment stability assessment device 10 for new energy power grid connection includes: a data acquisition module 100, an acquisition module 200, and an assessment module 300.

[0100] Specifically, the acquisition module 100 is used to acquire multi-dimensional indicator data of the target electrical equipment based on a pre-built multi-dimensional evaluation indicator system, and to perform feature enhancement processing on the multi-dimensional indicator data to generate enhanced features.

[0101] The acquisition module 200 is used to adjust the weight ratio of each dimension and corresponding indicator in the multi-dimensional indicator data based on the grid-connected power fluctuation coefficient and equipment operation stage coefficient of the target electrical equipment, so as to obtain the dynamic weight of each dimension and corresponding indicator.

[0102] The evaluation module 300 is used to input the processed enhanced features and the dynamic weights of each dimension and corresponding index into the pre-built evaluation model that integrates fuzzy comprehensive evaluation and Markov chain prediction. The fuzzy comprehensive evaluation module and the Markov chain prediction module are used to evaluate the stability of the target electrical equipment for grid connection of new energy power, so as to output the stability evaluation results of the target electrical equipment.

[0103] Optionally, in one embodiment of this application, the apparatus 10 of this application embodiment further includes: a determining module and a generating module.

[0104] The determination module is used to determine the current stability level and future stability trend of the target electrical equipment based on the stability assessment results after outputting the stability assessment results.

[0105] The generation module is used to link the current stability level and the stability trend within a preset time period with the new energy grid-connected scheduling system after outputting the stability assessment results of the target electrical equipment, and generate operation and maintenance suggestions and grid connection parameter adjustment strategies for the target electrical equipment.

[0106] Optionally, in one embodiment of this application, the apparatus 10 of this application embodiment further includes: a construction module.

[0107] The construction module is used to build a multi-dimensional evaluation index system for the target electrical equipment based on electrical parameter dimensions, grid connection adaptation dimensions, environmental impact dimensions, and equipment health dimensions before collecting multi-dimensional index data of the target electrical equipment. Among them, the core evaluation indicators of the electrical parameter dimension are at least one of voltage deviation, current distortion rate, active power fluctuation and reactive power compensation response speed; the auxiliary evaluation indicators of the electrical parameter dimension are at least one of insulation resistance, temperature rise rate and harmonic content. The core evaluation indicators for grid-connected adaptation are at least one of frequency response speed, phase tracking accuracy, islanding detection sensitivity, and grid-connected surge suppression effect; the auxiliary evaluation indicators for grid-connected adaptation are at least one of voltage ride-through capability and power factor adjustment range. The core assessment indicators for the environmental impact dimension are at least one of the following: temperature and humidity adaptability coefficient, wind and dust erosion degree, and electromagnetic interference intensity; the auxiliary assessment indicators for the environmental impact dimension are at least one of the following: altitude correction coefficient and diurnal temperature range impact value. The core assessment indicators for the equipment health dimension are at least one of the following: component aging rate, mechanical vibration amplitude, insulation aging degree, and cooling system efficiency; the auxiliary assessment indicators for the equipment health dimension are at least one of the following: historical failure frequency and maintenance cycle compliance rate.

[0108] Optionally, in one embodiment of this application, the acquisition module 100 includes: a detection unit, a first acquisition unit, and a second acquisition unit.

[0109] The detection unit is used to detect whether the grid-connected power fluctuation coefficient is greater than or equal to a preset fluctuation threshold based on the target hierarchical sampling strategy.

[0110] The first acquisition unit is used to acquire the core evaluation indicators of the electrical parameter dimension and the core evaluation indicators of the grid connection adaptation dimension using the target high-frequency sampling mode when the grid-connected power fluctuation coefficient is detected to be greater than or equal to the preset fluctuation threshold.

[0111] The second acquisition unit is used to collect core and auxiliary evaluation indicators of electrical parameters, grid-connection adaptability, environmental impact, and equipment health in a balanced manner using the target conventional sampling mode when the grid-connected power fluctuation coefficient is detected to be less than the preset fluctuation threshold.

[0112] Optionally, in one embodiment of this application, the acquisition module 100 includes: an extraction unit, a calculation unit, a generation unit, and a fusion unit.

[0113] The extraction unit is used to extract the time-series features of each dimension indicator in the multi-dimensional indicator data, so as to obtain the trend features, peak features and mutation features of each dimension indicator data.

[0114] The calculation unit is used to calculate the correlation strength between the core evaluation indicators of each dimension based on the Pearson correlation coefficient and mutual information entropy, so as to form strongly correlated indicator pairs.

[0115] The generation unit is used to fuse strongly correlated index pairs to generate cross-dimensional composite features, including electrical-grid-connection adaptation composite features and environmental-equipment health composite features.

[0116] The fusion unit is used to fuse the trend features, peak features, and mutation features of each dimension's indicator data with cross-dimensional composite features to generate the processed enhanced features.

[0117] Optionally, in one embodiment of this application, the evaluation module 300 includes: a setup unit, a weighted fusion unit, a prediction unit, and an evaluation unit.

[0118] The establishment unit is used to establish the fuzzy membership function of each indicator using the fuzzy comprehensive evaluation module, and to determine the fuzzy evaluation vector of each dimension based on the fuzzy membership function of each indicator.

[0119] The weighted fusion unit is used to perform weighted fusion of fuzzy evaluation vectors of each dimension based on dynamic weights, and to obtain the current comprehensive fuzzy evaluation result by using fuzzy synthesis matrix operations.

[0120] The prediction unit is used to construct a state transition matrix by combining the historical stability assessment results of the target electrical equipment with the Markov chain prediction module, and predict the stability state transition probability of the target electrical equipment within a future preset time period based on the state transition matrix and the current comprehensive fuzzy evaluation results.

[0121] The evaluation unit combines the current comprehensive fuzzy evaluation results with the state transition probabilities to output the stability evaluation results of the target electrical equipment.

[0122] It should be noted that the explanation of the aforementioned embodiment of the multi-dimensional electrical equipment stability assessment method for grid connection of new energy power also applies to the multi-dimensional electrical equipment stability assessment device for grid connection of new energy power in this embodiment, and will not be repeated here.

[0123] The multi-dimensional electrical equipment stability assessment device for new energy power grid connection proposed in this application can collect multi-dimensional index data of target electrical equipment based on a multi-dimensional assessment index system, perform feature enhancement processing to generate enhanced features, and then adjust the weight ratio of each dimension and corresponding index in the multi-dimensional index data based on the grid-connected power fluctuation coefficient and the equipment operation stage coefficient to obtain dynamic weights. Next, the processed enhanced features and dynamic weights are input into an assessment model that integrates fuzzy comprehensive evaluation and Markov chain prediction to assess the stability of the target electrical equipment for new energy power grid connection, and output the stability assessment results of the target electrical equipment. This effectively improves the assessment accuracy and practicality, and provides a scientific basis for grid-connected dispatch optimization and equipment operation and maintenance. Therefore, it solves the problem in related technologies that cannot provide forward-looking decision support for preventive maintenance and grid-connected dispatch, making it difficult to ensure the safe and stable operation of the power grid under high-proportion new energy access.

[0124] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0125] When the processor 402 executes the program, it implements the multi-dimensional electrical equipment stability assessment method for new energy power grid connection provided in the above embodiments.

[0126] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0127] The memory 401 is used to store computer programs that can run on the processor 402.

[0128] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0129] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0130] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0131] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0132] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for evaluating the stability of electrical equipment connected to the grid for new energy power.

[0133] This embodiment also provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned multi-dimensional electrical equipment stability assessment method for grid connection of new energy power.

[0134] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0135] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0136] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0137] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0138] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0139] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0140] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0141] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A multi-dimensional stability assessment method for electrical equipment connected to the grid in new energy power, characterized in that, Includes the following steps: Based on a pre-constructed multi-dimensional evaluation index system, multi-dimensional index data of the target electrical equipment are collected, and feature enhancement processing is performed on the multi-dimensional index data to generate enhanced features. Based on the grid-connected power fluctuation coefficient and equipment operation stage coefficient of the target electrical equipment, the weight ratio of each dimension and corresponding indicator in the multi-dimensional indicator data is adjusted to obtain the dynamic weight of each dimension and corresponding indicator. The processed enhanced features and the dynamic weights of each dimension and corresponding index are input into a pre-constructed evaluation model that integrates fuzzy comprehensive evaluation and Markov chain prediction. The fuzzy comprehensive evaluation module and the Markov chain prediction module are used to evaluate the stability of the target electrical equipment for grid connection of the new energy power, so as to output the stability evaluation result of the target electrical equipment.

2. The method according to claim 1, characterized in that, After outputting the stability assessment results of the target electrical equipment, the following is also included: Based on the stability assessment results, determine the current stability level and the stability trend of the target electrical equipment within a preset future time period; The current stability level and the stability trend within the preset future time period are linked with the new energy grid-connected scheduling system to generate operation and maintenance suggestions and grid-connected parameter adjustment strategies for the target electrical equipment.

3. The method according to claim 1, characterized in that, Before collecting multi-dimensional indicator data of the target electrical equipment, the following steps are also included: A multi-dimensional evaluation index system for target electrical equipment is constructed based on electrical parameters, grid connection adaptability, environmental impact, and equipment health. Among them, the core evaluation indicators of the electrical parameter dimension are at least one of voltage deviation, current distortion rate, active power fluctuation and reactive power compensation response speed; the auxiliary evaluation indicators of the electrical parameter dimension are at least one of insulation resistance, temperature rise rate and harmonic content. The core evaluation indicators for grid-connected adaptation are at least one of frequency response speed, phase tracking accuracy, islanding detection sensitivity, and grid-connected surge suppression effect; the auxiliary evaluation indicators for grid-connected adaptation are at least one of voltage ride-through capability and power factor adjustment range. The core assessment indicators for the environmental impact dimension are at least one of temperature and humidity adaptability coefficient, wind and dust erosion degree, and electromagnetic interference intensity; the auxiliary assessment indicators for the environmental impact dimension are at least one of altitude correction coefficient and diurnal temperature difference impact value. The core assessment indicators for the equipment health dimension are at least one of component aging rate, mechanical vibration amplitude, insulation aging degree, and cooling system efficiency; the auxiliary assessment indicators for the equipment health dimension are at least one of historical failure frequency and maintenance cycle compliance rate.

4. The method according to claim 3, characterized in that, The method, based on a pre-constructed multi-dimensional evaluation index system, collects multi-dimensional index data of the target electrical equipment, including: Based on the target hierarchical sampling strategy, it is detected whether the grid-connected power fluctuation coefficient is greater than or equal to a preset fluctuation threshold. When the grid-connected power fluctuation coefficient is detected to be greater than or equal to the preset fluctuation threshold, the core evaluation indicators of the electrical parameter dimension and the core evaluation indicators of the grid-connected adaptation dimension are collected using the target high-frequency sampling mode. When the grid-connected power fluctuation coefficient is detected to be less than the preset fluctuation threshold, the core and auxiliary evaluation indicators of the electrical parameter dimension, the core and auxiliary evaluation indicators of the grid-connected adaptation dimension, the core and auxiliary evaluation indicators of the environmental impact dimension, and the core and auxiliary evaluation indicators of the equipment health dimension are collected in a balanced manner using the target conventional sampling mode.

5. The method according to claim 1, characterized in that, The step of performing feature enhancement processing on the multi-dimensional indicator data to generate enhanced features includes: Extract the time-series features of each dimension indicator from the multi-dimensional indicator data to obtain the trend features, peak features, and abrupt change features of each dimension indicator data; Based on Pearson correlation coefficient and mutual information entropy, the correlation strength between the core evaluation indicators of each dimension is calculated to form strongly correlated indicator pairs; The strongly correlated indicators are fused to generate cross-dimensional composite features, which include electrical-grid-connection adaptation composite features and environmental-equipment health composite features. The enhanced features are generated by integrating the trend features, peak features, and mutation features of each dimension's indicator data with the cross-dimensional composite features.

6. The method according to claim 1, characterized in that, The stability assessment of the target electrical equipment for grid connection of the new energy power using the fuzzy comprehensive evaluation module and the Markov chain prediction module, and the output of the stability assessment results of the target electrical equipment, includes: The fuzzy membership function of each indicator is established using the fuzzy comprehensive evaluation module, and the fuzzy evaluation vector of each dimension is determined based on the fuzzy membership function of each indicator. Based on the dynamic weights, the fuzzy evaluation vectors of each dimension are weighted and fused, and the current comprehensive fuzzy evaluation result is obtained by using fuzzy synthesis matrix operations. A state transition matrix is ​​constructed by using a Markov chain prediction module in conjunction with the historical stability assessment results of the target electrical equipment. Based on the state transition matrix and the current comprehensive fuzzy evaluation results, the stability state transition probability of the target electrical equipment within a future preset time period is predicted. The current comprehensive fuzzy evaluation result is combined with the state transition probability to output the stability evaluation result of the target electrical equipment.

7. A multi-dimensional electrical equipment stability assessment device for new energy power grid connection, characterized in that, include: The acquisition module is used to acquire multi-dimensional indicator data of the target electrical equipment based on a pre-built multi-dimensional evaluation indicator system, and to perform feature enhancement processing on the multi-dimensional indicator data to generate enhanced features. The acquisition module is used to adjust the weight ratio of each dimension and corresponding indicator in the multi-dimensional indicator data based on the grid-connected power fluctuation coefficient and equipment operation stage coefficient of the target electrical equipment, so as to obtain the dynamic weight of each dimension and corresponding indicator. The evaluation module is used to input the processed enhanced features and the dynamic weights of each dimension and corresponding index into a pre-constructed evaluation model that integrates fuzzy comprehensive evaluation and Markov chain prediction. The fuzzy comprehensive evaluation module and the Markov chain prediction module are used to evaluate the stability of the target electrical equipment for grid connection of the new energy power, so as to output the stability evaluation result of the target electrical equipment.

8. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the multi-dimensional electrical equipment stability assessment method for grid connection of new energy power as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the multi-dimensional electrical equipment stability assessment method for grid connection of new energy power as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed by a processor to implement the multi-dimensional electrical equipment stability assessment method for grid connection of new energy power as described in any one of claims 1-6.

Images