Information fusion method of electrical automation system

Abstract

The invention relates to the technical field of electrical automation systems, in particular to an information fusion method of an electrical automation system. The method comprises the following steps: constructing a simulation model of the wind-driven generator by acquiring configuration data of an electrical automation system so as to simulate the operation performance of the wind-driven generator under different environmental conditions; performing fan blade over-rotation operation simulation by using historical wind power data of a regional environment, analyzing potential damage of the fan blade over-rotation operation to a bearing, and further estimating bearing damage data; based on the bearing damage data, predicting the fault trend of the wind-driven generator, and estimating the energy loss condition; performing information fusion on the fault trend data and the energy loss data to form comprehensive fault prediction information; based on an electrical automation system, a control strategy is optimized, and efficient operation and timely fault processing of the system are ensured. According to the method, the electrical automation system is optimized, so that the electrical automation system can identify faults more efficiently and quickly.

Description

Technical Field

[0001] The present invention relates to the technical field of electric automation systems, and in particular to an information fusion method for electric automation systems. Background Art

[0002] Electrical automation systems, such as generators, often face various faults and performance degradation problems during operation, such as blade fatigue, bearing wear, and electrical failures. These problems affect the operating efficiency of the generator. Therefore, it is particularly important to identify and handle these faults in a timely manner. Information fusion technology, as an effective method for integrating multi-source data, can play an important role in the monitoring and management of wind turbines. By integrating information from sensors, monitoring systems, and historical operating data, the electrical automation system can achieve a comprehensive analysis of the status of wind turbines. Information fusion methods can analyze the operating data of wind turbines in real time and identify potential failure modes through data mining and machine learning algorithms. For example, the vibration data, temperature data, and wind speed data of the blades can be comprehensively analyzed to help engineers predict the degradation trend of the equipment. By establishing a fault prediction model, the system can provide early warning to ensure the normal operation of the equipment. However, the information fusion method of the traditional electrical automation system has the problem of inaccurate prediction of wind turbine faults and inaccurate prediction of wind turbine power generation efficiency attenuation. Summary of the invention

[0003] Based on this, it is necessary to provide an information fusion method for an electrical automation system to solve at least one of the above technical problems.

[0004] To achieve the above object, an information fusion method for an electrical automation system comprises the following steps:

[0005] Step S1: Acquire electrical automation system configuration data; construct a wind turbine simulation model according to the electrical automation system configuration data to obtain a wind turbine simulation model;

[0006] Step S2: Acquire historical wind data of the regional environment; simulate the over-rotation operation of the blades of the regional environmental historical wind data based on the wind turbine simulation model to obtain the over-rotation operation data of the blades of the wind turbine; estimate the bearing damage according to the over-rotation operation data of the blades of the wind turbine to obtain the bearing damage data of the wind turbine;

[0007] Step S3: predicting the fault trend of the wind turbine generator based on the wind turbine generator bearing damage data to obtain the fault trend data of the wind turbine generator; estimating the energy loss of the wind turbine generator based on the wind turbine generator fault trend data based on the wind turbine generator simulation model to obtain the energy loss data of the wind turbine generator;

[0008] Step S4: Perform information fusion on the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data; perform fault prediction optimization on the wind turbine information fusion data based on the electrical automation system to obtain electrical automation system fault prediction optimization data; perform control strategy optimization based on the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

[0009] The present invention can realize accurate simulation of wind turbines by acquiring electrical automation system configuration data and constructing a wind turbine simulation model, and provides a reliable analysis platform. This process enables a deeper understanding of the equipment operation status and can identify potential operational problems. At the same time, the over-rotation operation simulation of the fan blades is combined with the historical wind data of the regional environment, which can effectively predict the operating performance of the fan blades under different wind speed conditions, which provides an important basis for evaluating the structural safety and life of the fan blades. By analyzing the over-rotation operation data, the risk of bearing damage can be discovered in advance, thereby providing a reference for maintenance and reducing the probability of sudden failures. By predicting the fault trend of the bearing damage data, the equipment status can be monitored in real time, and the maintenance strategy can be adjusted in time, thereby reducing equipment downtime and maintenance costs. In addition, energy loss estimation based on fault trend data can identify inefficient links in equipment operation and provide data support for further optimizing power generation efficiency. Information fusion integrates fault trends and energy loss data to form a comprehensive view of equipment operation, making the decision-making process more scientific and accurate. Relying on the electrical automation system for fault prediction optimization can achieve dynamic management and early warning, timely identify potential fault hazards, and further improve the reliability and safety of the system. The optimization of the control strategy can ensure that the equipment operates in the best state, thereby maximizing the power generation efficiency. Through this series of steps, the performance of wind turbines can be effectively improved, maintenance costs can be reduced, and the development of sustainable energy can be promoted. Therefore, the present invention is an optimization of the information fusion method of the traditional electrical automation system, which solves the problem of inaccurate fault prediction of wind turbines and inaccurate prediction of wind turbine power generation efficiency attenuation in the information fusion method of the traditional electrical automation system, and improves the accuracy of wind turbine fault prediction and wind turbine power generation efficiency attenuation prediction.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire electrical automation system configuration data;

[0012] Step S12: collecting the electrical structure of the wind turbine generator according to the electrical automation system configuration data to obtain the electrical structure data of the wind turbine generator;

[0013] Step S13: extracting the mechanical structure of the wind turbine generator according to the electrical automation system configuration data to obtain the mechanical structure data of the wind turbine generator;

[0014] Step S14: constructing a wind turbine simulation model according to the mechanical structure data and the electrical structure data of the wind turbine to obtain a wind turbine simulation model.

[0015] The present invention can lay a foundation for the analysis and optimization of wind turbines by acquiring the configuration data of the electrical automation system. The acquisition of this data ensures the accuracy and completeness of the information required for the subsequent steps. The electrical structure acquisition based on these configuration data can provide a detailed understanding of the electrical components and connection methods of the wind turbine, which provides an important basis for the performance evaluation and fault diagnosis of the equipment. At the same time, the extraction of the mechanical structure helps to analyze the physical characteristics and dynamic behavior of the wind turbine, which is crucial for understanding its operating mechanism. Combining the mechanical structure data and electrical structure data of the wind turbine to build a simulation model can form a highly accurate virtual model to simulate the performance of the equipment under different operating conditions. This simulation model provides engineers with a testing and verification environment, so that the performance and potential problems of the equipment can be predicted before actual operation, reducing the cost and time of the experiment. Through this model, optimization decisions can be made in the design stage and the operation stage to ensure the safety and efficiency of the wind turbine under various working conditions, thereby providing strong support for improving power generation efficiency and extending the life of the equipment.

[0016] Preferably, step S14 comprises the following steps:

[0017] Step S141: collecting electrical connection mode data of the wind turbine generator electrical structure to obtain electrical connection mode data of the wind turbine generator;

[0018] Step S142: extracting blade shape according to the mechanical structure data of the wind turbine generator to obtain blade shape data of the wind turbine generator;

[0019] Step S143: measuring the bending degree of the blades according to the blade shape data of the wind turbine generator to obtain the bending degree data of the blades of the wind turbine generator;

[0020] Step S144: Calculating the wind energy capture efficiency according to the bending degree data of the wind turbine blades to obtain the wind energy capture efficiency data of the turbine blades;

[0021] Step S145: constructing a wind power generator simulation model based on the wind energy capture efficiency data of the generator blades and the electrical connection mode data of the wind power generator to obtain a wind power generator simulation model.

[0022] The present invention can obtain detailed information about the electrical layout of the generator and the relationship between its components by collecting the electrical connection mode of the electrical structure data of the wind power generator. This provides an important basis for subsequent performance evaluation and fault diagnosis, ensuring that potential problems and their influencing factors can be accurately identified during electrical analysis. At the same time, the acquired electrical connection mode data can provide guidance for optimizing electrical design and promote the improvement of the overall efficiency of the system. In terms of mechanical structure, extracting the blade shape based on the mechanical structure data of the wind power generator helps to establish a more comprehensive understanding of the physical properties of the fan blades. The shape of the fan blade directly affects its ability to capture energy in the wind, so it is crucial to analyze the shape of the fan blade in detail. Subsequently, by measuring the degree of bending of the fan blade, the force applied to the fan blade during operation can be evaluated, and then the stability and reliability of its long-term operation can be judged. This data is of great value for predicting the fatigue life and structural damage of the fan blade. By calculating the wind energy capture efficiency of the fan blade, its performance under different wind speed conditions can be quantified to help identify deficiencies in the design. This efficiency data provides an empirical basis for optimizing blade design, enabling engineers to better balance the relationship between wind energy capture and structural strength in future designs, thereby improving power generation efficiency. A wind turbine simulation model is built based on the wind energy capture efficiency data and electrical connection data of the generator blades, providing an integrated perspective for the analysis of the entire system. The simulation model can be tested under different operating conditions, predict the performance and potential failures of the equipment, and provide data support for subsequent maintenance decisions.

[0023] Preferably, step S2 comprises the following steps:

[0024] Step S21: Acquire historical wind data of regional environment;

[0025] Step S22: performing a blade over-rotation simulation on the historical wind data of the regional environment based on the wind turbine simulation model to obtain the blade over-rotation data of the wind turbine;

[0026] Step S23: performing abnormal vibration detection on the wind turbine blades over-rotation operation data and the regional environmental historical wind data according to the wind turbine simulation model to obtain abnormal vibration data of the turbine blades;

[0027] Step S24: performing blade fatigue analysis based on the abnormal vibration data of the generator blades and the over-rotation operation data of the wind turbine generator blades to obtain the wind turbine generator blade fatigue data;

[0028] Step S25: Predict bearing damage based on wind turbine blade fatigue data and generator blade abnormal vibration data to obtain wind turbine bearing damage data.

[0029] The present invention can provide real basic information for subsequent simulation and analysis by acquiring historical wind data of regional environment. These data not only cover the wind speed and wind direction in different time periods, but also reflect the climate characteristics in the region, making the performance evaluation of wind turbine generators more accurate. Based on these historical data, the over-rotation operation simulation of the fan blades can effectively predict the operating state of the fan blades under strong wind conditions, thereby identifying potential safety hazards. The results of this simulation provide engineers with important insights into the performance of the fan blades under extreme conditions, helping to evaluate the rationality and safety of the design. Based on the over-rotation operation simulation of the fan blades, the abnormal vibration detection of the fan blades is performed using the simulation model of the wind turbine generator, and the abnormal vibration of the fan blades during operation can be timely identified. By monitoring the vibration data, problems can be discovered in time to avoid mechanical failure or damage to the equipment caused by excessive vibration. This process can not only improve the reliability of the equipment, but also extend its service life. Further analysis of the abnormal vibration data and over-rotation operation data of the generator fan blades can quantitatively evaluate the fatigue condition of the fan blades in long-term operation. This analysis result provides engineers with a scientific basis for judging whether the fan blades need to be replaced or maintained, which helps to optimize maintenance strategies. Combining the fan blade fatigue data with the abnormal vibration data to estimate the bearing damage can provide a comprehensive assessment of the overall health of the wind turbine. This estimate can identify potential bearing problems in advance, and then take corresponding preventive measures to reduce the risk of unexpected downtime caused by bearing damage.

[0030] Preferably, step S23 includes the following steps:

[0031] Step S231: performing regional airflow fluctuation detection according to regional environmental historical wind data to obtain regional airflow fluctuation data;

[0032] Step S232: measuring the regional airflow variation amplitude according to the regional airflow fluctuation data to obtain the regional airflow variation amplitude data;

[0033] Step S233: performing blade unbalanced load detection on the regional airflow variation amplitude data according to the wind turbine simulation model to obtain blade unbalanced load data;

[0034] Step S234: calculating the speed change rate of the wind turbine blade over-speed operation data to obtain the speed change rate data of the turbine blade;

[0035] Step S235: Perform abnormal vibration detection on the fan blades according to the unbalanced load data on the fan blades and the speed change rate data on the generator fan blades to obtain abnormal vibration data on the generator fan blades.

[0036] The present invention can obtain important information closely related to the operating environment of the wind turbine generator by performing regional airflow fluctuation detection based on the historical wind data of the regional environment. This detection not only reveals the airflow characteristics in the region, but also helps to identify the factors that affect the performance of the generator under different climatic conditions. This provides a scientific basis for the subsequent airflow change amplitude measurement, making the establishment of the model more accurate and reliable. In the regional airflow change amplitude measurement, the degree of airflow fluctuation can be quantified. This data is crucial for evaluating the performance of wind turbines under different airflow conditions, because the change of airflow directly affects the force of the fan blades and the power generation efficiency. By mastering the airflow change amplitude, the operating state of the generator can be better predicted, and countermeasures can be taken in time to ensure that the equipment operates in the best state. Based on the regional airflow change amplitude data, the fan blade unbalanced load detection can effectively identify the different load conditions borne by the fan blade under complex airflow conditions. This test result provides important data support for subsequent fatigue analysis and maintenance decisions, helping engineers optimize design and maintenance strategies, and ensuring the stability and safety of wind turbine generators. When the speed change rate is calculated for the over-rotation operation data of the fan blades of the wind turbine generator, the dynamic changes of the fan blades can be monitored. This data reflects the risks faced by the fan blades during wind speed changes and helps identify potential overspeed problems. By analyzing the speed change rate, the operational safety of the fan blades can be more accurately assessed, reducing the risk of damage caused by overspeed. Combining the fan blade unbalanced load data and the generator fan blade speed change rate data to detect abnormal fan blade vibration can identify vibration anomalies that lead to equipment failures at an early stage. This detection is crucial to improving the reliability of wind turbines and helps reduce equipment downtime.

[0037] Preferably, step S24 comprises the following steps:

[0038] Step S241: Calculating the peak speed of the blades according to the over-speed operation data of the wind turbine blades to obtain the peak speed data of the blades;

[0039] Step S242: Calculating the wind overload of the fan blades according to the peak speed data of the fan blades to obtain the wind overload data of the fan blades;

[0040] Step S243: performing a wind plastic deformation test on the fan blade wind overload data to obtain the wind plastic deformation data of the fan blade;

[0041] Step S244: performing blade stress growth calculation on the blade wind plastic deformation data and the generator blade abnormal vibration data to obtain blade stress growth data;

[0042] Step S245: dividing the stress concentration area according to the blade stress growth data to obtain the blade stress growth concentration area data;

[0043] Step S246: Perform blade fatigue analysis based on the blade stress concentration growth area data to obtain wind turbine blade fatigue data.

[0044] The present invention can obtain the operating limit of the blade under extreme working conditions by calculating the peak speed of the blade according to the over-rotation operation data of the wind turbine blade. This data not only reveals the performance of the blade under high load, but also provides an important reference for the subsequent wind overload calculation, thereby ensuring that the blade can effectively cope with the load change in an environment with large wind speed fluctuations. When calculating the wind overload of the blade, it is possible to evaluate whether the wind force borne by the blade exceeds the design limit under different wind speed conditions. This calculation result helps to identify potential structural risks in a timely manner, prevent damage and safety hazards caused by wind overload, thereby improving the reliability and service life of the equipment. Subsequently, plastic deformation detection is performed on the wind overload data of the blade, which can effectively identify the permanent deformation of the blade under overload conditions. This detection is crucial for understanding the fatigue performance of the material and ensuring the stability of the blade under high-intensity wind conditions, and helps to formulate reasonable maintenance and repair strategies to avoid further damage caused by deformation. By performing stress growth calculation on the wind plastic deformation data of the blade and the abnormal vibration data of the generator blade, the stress changes of the blade during operation can be deeply analyzed. This calculation can reveal the stress state of the fan blades under different working conditions. By dividing the stress concentration area according to the fan blade stress growth data, the weaknesses in the fan blade design or materials can be clearly pointed out. This information is of great guiding significance for optimizing design, improving material selection and improving manufacturing processes. It can effectively reduce the failure rate of fan blades in actual operation. Performing fan blade fatigue analysis based on stress concentration growth area data helps to evaluate the reliability and safety of fan blades in long-term operation. Through this analysis, failures and fatigue problems can be predicted in advance, providing a decision-making basis for equipment maintenance and management.

[0045] Preferably, step S25 comprises the following steps:

[0046] Step S251: Perform bearing load dynamic transfer detection according to wind turbine blade fatigue data to obtain generator bearing load dynamic transfer data;

[0047] Step S252: analyzing the bearing resonance phenomenon according to the abnormal vibration data of the generator blades to obtain the generator bearing resonance data;

[0048] Step S253: estimating abnormal torque changes according to the generator bearing load dynamic transfer data and the generator bearing resonance data to obtain bearing torque abnormal change data;

[0049] Step S254: performing friction force growth calculation according to the bearing torque abnormal change data and the generator bearing load dynamic transfer data to obtain bearing friction force growth data;

[0050] Step S255: performing bearing wear aggravation detection according to the bearing friction force growth data to obtain bearing wear aggravation data;

[0051] Step S256: performing bearing damage estimation on the bearing wear aggravation data and the bearing torque abnormal change data to obtain the wind turbine bearing damage data.

[0052] The present invention can obtain the load change of the bearing under different working conditions by performing bearing load dynamic transfer detection on the fatigue data of the wind turbine blade. This detection result helps to understand the influence of blade fatigue on bearing performance, and then provides a basis for formulating a reasonable maintenance strategy to ensure the reliability and safety of the equipment. Further analyzing the abnormal vibration data of the generator blade to analyze the bearing resonance phenomenon can timely identify potential resonance problems. Resonance causes excessive vibration of the bearing during operation, thereby accelerating wear and damage. By monitoring these resonance phenomena, preventive measures can be taken before the failure occurs to improve the stability of the system. On this basis, the torque abnormal change is estimated based on the bearing load dynamic transfer data and the bearing resonance data, which helps to evaluate the torque change borne by the bearing during operation. This estimate can reveal the potential risks in the operation of the equipment and ensure that measures can be taken in time to avoid equipment failures caused by abnormal torque. Combining the bearing torque abnormal change data with the load dynamic transfer data to calculate the friction force growth, the friction of the bearing during operation can be clearly understood. This calculation is of great significance for understanding the operating efficiency and performance stability of the bearing, and helps to guide the lubrication and maintenance of the bearing and reduce the energy loss caused by friction. Subsequently, the bearing wear aggravation detection is carried out based on the friction force growth data, and the bearing wear status can be monitored in real time. Through this detection, wear problems can be discovered in time, and equipment failures and shutdowns caused by excessive bearing wear can be avoided, thereby improving the operating efficiency of wind turbines. By comprehensively analyzing the bearing wear aggravation data and torque abnormal change data, bearing damage can be estimated. This estimation helps predict the remaining service life of the bearing, provides a basis for equipment maintenance and replacement, thereby reducing the risk of unexpected shutdowns caused by bearing damage and improving the overall reliability and stability of the system.

[0053] Preferably, step S3 comprises the following steps:

[0054] Step S31: performing turbine load transfer detection on the wind turbine bearing damage data to obtain turbine load transfer data;

[0055] Step S32: predicting the turbine degradation trend according to the turbine load transfer data to obtain turbine degradation trend data;

[0056] Step S33: predicting the fault trend of the wind turbine generator according to the turbine degradation trend data and the generator blade fatigue data to obtain the fault trend data of the wind turbine generator;

[0057] Step S34: Based on the wind turbine simulation model, the turbine degradation trend data and the wind turbine failure trend data are subjected to wind turbine energy loss simulation to obtain wind turbine energy loss data.

[0058] The present invention can identify the impact of bearing damage on turbine performance by performing turbine load transfer detection on wind turbine bearing damage data. This detection can provide load distribution information of the turbine under different working conditions, which helps engineers evaluate the risks faced by the equipment in actual operation, thereby laying the foundation for subsequent maintenance and optimization strategies. By predicting the turbine degradation trend based on the turbine load transfer data, the operating status of the turbine and its gradually declining performance can be effectively monitored. This trend prediction can detect potential faults in advance and formulate preventive maintenance measures to reduce maintenance costs and downtime, ensuring the long-term stable operation of the equipment. Subsequently, the wind turbine fault trend prediction is performed in combination with the turbine degradation trend data and the generator blade fatigue data, and the overall health status of the wind generator system can be comprehensively evaluated. By correlating the status of the turbine and the blades, the multiple fault risks existing in the system can be identified. This comprehensive fault trend prediction provides management with deeper insights, enabling them to better allocate resources, optimize operating strategies, and improve the efficiency of wind power generation. Based on the wind turbine simulation model, energy loss simulation of turbine degradation trend data and wind turbine fault trend data can accurately calculate the energy loss caused by equipment degradation. This simulation not only helps identify current energy loss situations, but also provides an important basis for future energy efficiency optimization. By timely adjusting and optimizing operating strategies, the overall efficiency of wind turbines will be significantly improved, promoting the sustainable development of renewable energy.

[0059] Preferably, step S34 includes the following steps:

[0060] Step S341: Calculate the increase of the wind response time of the generator according to the fault trend data of the wind power generator to obtain the increase data of the wind response time of the generator;

[0061] Step S342: performing turbine output power attenuation prediction on the turbine degradation trend data to obtain turbine output power attenuation data;

[0062] Step S343: performing turbine performance attenuation detection according to the turbine output power attenuation data to obtain turbine performance attenuation data;

[0063] Step S344: Calculate the power generation efficiency reduction based on the turbine performance attenuation data and the generator wind response time growth data to obtain the wind power generator power generation efficiency reduction data;

[0064] Step S345: calculating the energy conversion efficiency of the wind turbine generator according to the fault trend data of the wind turbine generator to obtain energy conversion efficiency reduction data;

[0065] Step S346: Based on the wind turbine simulation model, the energy conversion efficiency reduction data and the wind turbine power generation efficiency reduction data are subjected to a wind turbine energy loss simulation to obtain the wind turbine energy loss data.

[0066] The present invention can quantify the response capability of the generator under different wind speed conditions by calculating the growth of the wind turbine response time based on the fault trend data of the wind turbine. This data provides a basis for optimizing the control system of the wind turbine, helps to improve the real-time adjustment strategy, and enhances the adaptability of the generator in a changing wind speed environment, thereby achieving higher power generation efficiency. Next, the turbine output power attenuation prediction is performed on the turbine degradation trend data, and the risk of turbine performance degradation can be identified in advance. This prediction helps the operation and maintenance team to take corresponding measures before the problem becomes serious, such as adjusting the maintenance plan or replacing parts to ensure the continued efficient operation of the turbine. Further, the turbine performance attenuation detection is performed based on the turbine output power attenuation data, which can accurately evaluate the actual performance of the turbine under specific operating conditions. This detection provides data support for the overall performance analysis of the wind turbine, so that engineers can adjust the operating parameters and maintenance strategies in a targeted manner to optimize the power generation efficiency. Subsequently, by combining the turbine performance attenuation data with the generator wind response time growth data, the power generation efficiency reduction calculation is performed, and the efficiency loss caused by equipment degradation can be clearly identified. This calculation provides important performance indicators for the wind power generation system, allowing management to formulate optimization measures to improve the overall power generation efficiency. Next, the energy conversion efficiency is calculated based on the wind turbine fault trend data to quantify the loss of the equipment during the energy conversion process. This provides data support for subsequent technical improvements and investment decisions. Based on the wind turbine simulation model, the energy loss of the wind turbine is simulated based on the energy conversion efficiency reduction data and the power generation efficiency reduction data, which can effectively identify the energy loss caused by poor equipment status. This simulation result provides a scientific basis for the operation and management of wind turbines, making related decisions more targeted and effective.

[0067] Preferably, step S4 comprises the following steps:

[0068] Step S41: fusing the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data;

[0069] Step S42: performing abnormality detection on the wind turbine generator according to the information fusion data of the wind turbine generator to obtain abnormal power generation data of the wind turbine generator;

[0070] Step S43: performing fault prediction optimization on abnormal power generation data of the wind turbine generator based on the electrical automation system to obtain fault prediction optimization data of the electrical automation system;

[0071] Step S44: Optimizing the control strategy according to the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

[0072] The present invention fuses the fault trend data and energy loss data of wind turbines, and firstly, can integrate multi-dimensional information to form a more comprehensive analysis perspective. This fusion can reveal potential problems in the operation of the equipment and identify the correlation between the fault mode and the energy loss, thereby laying the foundation for subsequent abnormal detection. On this basis, abnormal detection is performed by using the information fusion data of wind turbines, so that the operating status of the equipment can be monitored in real time and the power generation abnormality can be quickly identified. This process not only improves the timeliness of fault discovery, but also reduces the risk of production stagnation caused by equipment failure, and provides an accurate basis for decision-making. Furthermore, based on the electrical automation system, the power generation abnormality data is optimized for fault prediction, and advanced algorithms and models can be applied to predict future faults. This optimization process enables the maintenance team to formulate preventive maintenance plans more efficiently, reduce the probability of unexpected downtime, and improve the overall reliability and availability of the equipment. By optimizing the control strategy of the fault prediction optimization data of the electrical automation system, the operating parameters of the equipment can be dynamically adjusted to cope with the changing environment and load conditions. This strategy optimization can not only improve the operating efficiency of wind turbines, but also effectively reduce operating costs and extend the service life of the equipment.

[0073] The beneficial effects of the present invention are as follows: by acquiring the configuration data of the electrical automation system and constructing a simulation model of a wind turbine, the present invention can realize accurate simulation of a wind turbine and provide a reliable analysis platform. This process enables a deeper understanding of the operation of the equipment and can identify potential operational problems. At the same time, the over-rotation operation simulation of the fan blades is performed in combination with the historical wind data of the regional environment, which can effectively predict the operating performance of the fan blades under different wind speed conditions, which provides an important basis for evaluating the structural safety and life of the fan blades. By analyzing the over-rotation operation data, the risk of bearing damage can be discovered in advance, thereby providing a reference for maintenance and reducing the probability of sudden failures. By predicting the fault trend of the bearing damage data, the equipment status can be monitored in real time, and the maintenance strategy can be adjusted in time, thereby reducing equipment downtime and maintenance costs. In addition, energy loss estimation based on fault trend data can identify inefficient links in equipment operation and provide data support for further optimizing power generation efficiency. Information fusion integrates fault trends and energy loss data to form a comprehensive view of equipment operation, making the decision-making process more scientific and accurate. Relying on the electrical automation system for fault prediction optimization can achieve dynamic management and early warning, timely identify potential fault hazards, and further improve the reliability and safety of the system. The optimization of the control strategy can ensure that the equipment operates in the best state, thereby maximizing the power generation efficiency. Through this series of steps, the performance of wind turbines can be effectively improved, maintenance costs can be reduced, and the development of sustainable energy can be promoted. Therefore, the present invention is an optimization of the information fusion method of the traditional electrical automation system, which solves the problem of inaccurate fault prediction of wind turbines and inaccurate prediction of wind turbine power generation efficiency attenuation in the information fusion method of the traditional electrical automation system, and improves the accuracy of wind turbine fault prediction and wind turbine power generation efficiency attenuation prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of the steps of an information fusion method for an electrical automation system;

[0075] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0076] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0077] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0078] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0079] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0080] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0081] To achieve this, please refer to Figures 1 to 3 , an information fusion method for an electrical automation system, comprising the following steps:

[0082] Step S1: Acquire electrical automation system configuration data; construct a wind turbine simulation model according to the electrical automation system configuration data to obtain a wind turbine simulation model;

[0083] Step S2: Acquire historical wind data of the regional environment; simulate the over-rotation operation of the blades of the regional environmental historical wind data based on the wind turbine simulation model to obtain the over-rotation operation data of the blades of the wind turbine; estimate the bearing damage according to the over-rotation operation data of the blades of the wind turbine to obtain the bearing damage data of the wind turbine;

[0084] Step S3: predicting the fault trend of the wind turbine generator based on the wind turbine generator bearing damage data to obtain the fault trend data of the wind turbine generator; estimating the energy loss of the wind turbine generator based on the wind turbine generator fault trend data based on the wind turbine generator simulation model to obtain the energy loss data of the wind turbine generator;

[0085] Step S4: Perform information fusion on the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data; perform fault prediction optimization on the wind turbine information fusion data based on the electrical automation system to obtain electrical automation system fault prediction optimization data; perform control strategy optimization based on the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

[0086] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of an information fusion method for an electrical automation system of the present invention. In this example, the information fusion method for an electrical automation system includes the following steps:

[0087] Step S1: Acquire electrical automation system configuration data; construct a wind turbine simulation model according to the electrical automation system configuration data to obtain a wind turbine simulation model;

[0088] In the embodiment of the present invention, in the process of obtaining the configuration data of the electrical automation system, the system configuration database is first connected through a standardized data interface. This interface can extract various configuration information in real time, including the type, specification, connection method, etc. of electrical components. Subsequently, the data is used to build a simulation model of the wind turbine. During the construction process, the physical modeling method is used to combine the electrical components with the mechanical structure to ensure that the model can accurately reflect the dynamic characteristics of the system. Finally, the simulation model includes the electrical structure, mechanical parameters and control logic.

[0089] Step S2: Acquire historical wind data of the regional environment; simulate the over-rotation operation of the blades of the regional environmental historical wind data based on the wind turbine simulation model to obtain the over-rotation operation data of the blades of the wind turbine; estimate the bearing damage according to the over-rotation operation data of the blades of the wind turbine to obtain the bearing damage data of the wind turbine;

[0090] In an embodiment of the present invention, in the process of obtaining historical wind data of the regional environment, firstly, meteorological data such as historical wind speed and wind direction are extracted from the meteorological monitoring system. These data are cleaned and processed to ensure their integrity and accuracy. Next, based on the simulation model of the wind turbine, the historical wind data are simulated by the method of numerical calculation for the over-rotation operation of the fan blades. The simulation performs real-time calculation of the changes in wind speed and blade angle, and outputs the operating status of the fan blades at different wind speeds. At the same time, the obtained over-rotation operation data of the fan blades is used to evaluate the stress condition of the bearing, estimate the bearing damage, and judge the health status of the bearing by comparing the vibration data of the normal and abnormal states.

[0091] Step S3: predicting the fault trend of the wind turbine generator based on the wind turbine generator bearing damage data to obtain the fault trend data of the wind turbine generator; estimating the energy loss of the wind turbine generator based on the wind turbine generator fault trend data based on the wind turbine generator simulation model to obtain the energy loss data of the wind turbine generator;

[0092] In the embodiment of the present invention, when predicting the fault trend of a wind turbine bearing damage data, firstly, the historical fault records and real-time monitoring data are used to calculate the frequency and trend of the faults using statistical analysis methods. By establishing a time series model, the changing pattern of the fault data can be effectively captured. Subsequently, based on the wind turbine simulation model and combined with the fault trend data, the energy loss is estimated, and the energy balance method is used to evaluate the energy output loss under different fault conditions.

[0093] Step S4: Perform information fusion on the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data; perform fault prediction optimization on the wind turbine information fusion data based on the electrical automation system to obtain electrical automation system fault prediction optimization data; perform control strategy optimization based on the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

[0094] In an embodiment of the present invention, when fusing the fault trend data of wind turbine generators with the energy loss data of wind turbine generators, a weighted average method is used to comprehensively consider the importance and relevance of various types of data to form a unified data set. This process requires defining the weight of each data type to reflect its impact on the overall performance. Based on this information fusion data, by applying the fault tree analysis method, fault prediction optimization is implemented to identify potential fault modes and classify them. Finally, the prediction results are combined with the operating strategy of the control system, and the control strategy optimization is implemented to ensure that the electrical automation system can respond in time and adjust the operating parameters when a fault occurs.

[0095] Preferably, step S1 comprises the following steps:

[0096] Step S11: Acquire electrical automation system configuration data;

[0097] Step S12: collecting the electrical structure of the wind turbine generator according to the electrical automation system configuration data to obtain the electrical structure data of the wind turbine generator;

[0098] Step S13: extracting the mechanical structure of the wind turbine generator according to the electrical automation system configuration data to obtain the mechanical structure data of the wind turbine generator;

[0099] Step S14: constructing a wind turbine simulation model according to the mechanical structure data and the electrical structure data of the wind turbine to obtain a wind turbine simulation model.

[0100] In an embodiment of the present invention, when acquiring the configuration data of the electrical automation system, firstly, the main controller of the electrical automation system is connected through an industrial standard protocol such as Modbus or OPC UA. This process requires reading the configuration information through the network interface, including the model, specification, wiring mode and system operating parameters of each electrical component. To ensure the accuracy of the data, a data verification mechanism, such as CRC verification, is used to confirm that the data is not damaged during the transmission process. The acquired data is organized into a structured format, and when the electrical structure of the wind power generator is collected according to the acquired electrical automation system configuration data, the components related to the electrical system are identified, including the frequency converter, the generator, the controller and their interconnection relationship. The electrical structure data is extracted by analyzing the technical documents and circuit diagrams of the electrical components. This process includes measuring and recording the parameters of each electrical component, such as the rated voltage, the rated current and the maximum power. When extracting the mechanical structure of the wind power generator, the mechanical design drawings of the wind power generator are collected, including the structural drawings and the parts list. The drawings are parsed by CAD software to extract key mechanical parameters, such as blade length, diameter, material strength and bearing position. The extraction process of these data depends on the accuracy and standardization of the drawings. After the extraction is completed, the mechanical structure data is sorted and stored in a dedicated mechanical parameter database. When building a wind turbine simulation model, the obtained electrical structure data needs to be integrated with the mechanical structure data. Use system simulation tools (such as MATLAB / Simulink) to import these data and establish a coupled model of the electrical and mechanical parts. This process includes defining the mathematical expressions and behaviors of each component in the model to ensure that it can accurately reflect the actual working state. The model should include key parameters such as the motor speed, torque, wind input and their mutual relationship. Through preliminary verification of the model, it is ensured that it can accurately simulate the operating characteristics of the wind turbine under normal and fault conditions, and finally output a complete wind turbine simulation model.

[0101] Preferably, step S14 comprises the following steps:

[0102] Step S141: collecting electrical connection mode data of the wind turbine generator electrical structure to obtain electrical connection mode data of the wind turbine generator;

[0103] Step S142: extracting blade shape according to the mechanical structure data of the wind turbine generator to obtain blade shape data of the wind turbine generator;

[0104] Step S143: measuring the bending degree of the blades according to the blade shape data of the wind turbine generator to obtain the bending degree data of the blades of the wind turbine generator;

[0105] Step S144: Calculating the wind energy capture efficiency according to the bending degree data of the wind turbine blades to obtain the wind energy capture efficiency data of the turbine blades;

[0106] Step S145: constructing a wind power generator simulation model based on the wind energy capture efficiency data of the generator blades and the electrical connection mode data of the wind power generator to obtain a wind power generator simulation model.

[0107] In an embodiment of the present invention, when collecting the electrical connection mode of a wind power generator, the electrical structure data must first be analyzed to determine the connection mode between each electrical component. By using electrical drawings and technical documents, the main electrical components, such as frequency converters, generators, sensors and controllers, are identified, and their connection types (such as series, parallel or mixed connections) are recorded. Electrical engineering software tools (such as AutoCAD Electrical) are used to visualize the electrical connection and convert it into structured data to form electrical connection mode data. When extracting the blade shape, the geometric parameters of the fan blade need to be extracted from the mechanical structure data of the wind power generator. This process depends on the analysis of the mechanical design drawings and CAD models, mainly including the length, width, thickness and curvature of the blade. The model is analyzed using CAD software (such as SolidWorks) to extract the specific shape data of the fan blade, including the cross-sectional shape and contour features of the fan blade. Accurate measurements are performed by digital instruments to ensure that the geometric shape of the fan blade is accurately recorded to form the fan blade shape data of the system. When measuring the degree of bending of the fan blade, the measurement point needs to be selected based on the fan blade shape data. Precision measuring tools such as strain gauges or laser rangefinders are used to monitor the bending of the fan blades under different load conditions in real time. By comparing the measured data with the theoretical design value, the bending degree of the fan blade under a specific wind speed and load is calculated. The process should include data acquisition, processing and analysis to obtain the bending degree data of the fan blade. When calculating the wind energy capture efficiency based on the bending degree data of the fan blade, an aerodynamic performance model of the fan blade needs to be established. Using the principles of fluid mechanics, the state of wind flow passing through the surface of the fan blade is analyzed, and its wind energy capture efficiency is calculated. The fan blade efficiency under different wind speeds and angles of attack is obtained through wind tunnel tests or numerical simulations (such as CFD analysis). The measured bending degree is combined with the theoretical model to calculate the wind energy capture efficiency data of the fan blade. In the process of building the simulation model of the wind turbine generator, the electrical connection method data is integrated with the wind energy capture efficiency data. Using the system simulation tool, these data are input into the simulation environment to establish an interaction model between the fan blade and the electrical system. This process involves defining the performance parameters and operating status of each component to ensure that the model can accurately reflect the actual working conditions. By verifying and optimizing the model, a complete wind turbine simulation model is finally formed.

[0108] Preferably, step S2 comprises the following steps:

[0109] Step S21: Acquire historical wind data of regional environment;

[0110] Step S22: performing a blade over-rotation simulation on the historical wind data of the regional environment based on the wind turbine simulation model to obtain the blade over-rotation data of the wind turbine;

[0111] Step S23: performing abnormal vibration detection on the wind turbine blades over-rotation operation data and the regional environmental historical wind data according to the wind turbine simulation model to obtain abnormal vibration data of the turbine blades;

[0112] Step S24: performing blade fatigue analysis based on the abnormal vibration data of the generator blades and the over-rotation operation data of the wind turbine generator blades to obtain the wind turbine generator blade fatigue data;

[0113] Step S25: Predict bearing damage based on wind turbine blade fatigue data and generator blade abnormal vibration data to obtain wind turbine bearing damage data.

[0114] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0115] Step S21: Acquire historical wind data of regional environment;

[0116] In the embodiment of the present invention, in the process of obtaining the historical wind data of the regional environment, firstly, the time series data of wind speed and wind direction are collected from the meteorological monitoring station. These data are usually recorded in hours or minutes and contain many years of historical information. The raw data are processed to remove abnormal values ​​and missing values ​​using a data cleaning tool. The cleaned data are stored in a database, and the wind speed is statistically analyzed using data analysis software (such as the Pandas library of MATLAB or Python) to obtain wind distribution characteristics and maximum wind speed values.

[0117] Step S22: performing a blade over-rotation simulation on the historical wind data of the regional environment based on the wind turbine simulation model to obtain the blade over-rotation data of the wind turbine;

[0118] In an embodiment of the present invention, when simulating the over-rotation operation of the fan blades based on the historical wind data of the regional environment based on the simulation model of the wind turbine generator, it is first necessary to set the physical parameters of the wind turbine generator in the simulation environment, including the geometric shape, material properties and dynamic characteristics of the fan blades. Then, the obtained historical wind data is input into the simulation model to simulate the effect of wind speed on the fan blades under different working conditions. Through numerical calculation, the fan blade operation data under the over-rotation condition is obtained, with special attention paid to the rotation speed, vibration characteristics and load changes of the fan blades. Finally, the simulation results are recorded as the over-rotation operation data of the fan blades of the wind turbine generator.

[0119] Step S23: performing abnormal vibration detection on the wind turbine blades over-rotation operation data and the regional environmental historical wind data according to the wind turbine simulation model to obtain abnormal vibration data of the turbine blades;

[0120] In an embodiment of the present invention, when abnormal vibration detection of fan blades is performed, the vibration signal of the fan blades is first extracted from the obtained over-speed operation data. Acceleration sensors are used to collect field data at different positions of the fan blades, and spectrum analysis tools (such as FFT transformation) are used to perform frequency domain analysis on the vibration signal. The analysis results are compared with the normal vibration mode to identify abnormal vibration frequencies that exceed the preset threshold. Combined with historical wind power data, the abnormal vibration data of the generator fan blades is finally formed.

[0121] Step S24: performing blade fatigue analysis based on the abnormal vibration data of the generator blades and the over-rotation operation data of the wind turbine generator blades to obtain the wind turbine generator blade fatigue data;

[0122] In an embodiment of the present invention, when performing fatigue analysis of the fan blades, it is first necessary to determine the stress state of the fan blades under different vibration conditions based on the abnormal vibration data of the fan blades obtained. A finite element model of the fan blades is established through fatigue analysis software (such as ANSYS or FEA tools), and the material properties and working load conditions of the fan blades are input. The fatigue limit and stress-life curve are determined using fatigue test data. The simulation results are processed to evaluate the fatigue damage of the fan blades under normal and overspeed conditions, and finally the fatigue data of the wind turbine blades are obtained.

[0123] Step S25: Predict bearing damage based on wind turbine blade fatigue data and generator blade abnormal vibration data to obtain wind turbine bearing damage data.

[0124] In an embodiment of the present invention, when estimating bearing damage based on blade fatigue data and abnormal vibration data, it is first necessary to analyze the effect of blade fatigue on bearing force. A structural mechanics analysis method is used to combine fatigue data with vibration data to establish a bearing force model. The working condition of the bearing is evaluated by calculating the dynamic load applied by the blades to the bearing. Using the bearing life prediction model, the obtained load data and operating time are input, and finally the damage probability and expected service life of the bearing are predicted to generate wind turbine bearing damage data.

[0125] Preferably, step S23 includes the following steps:

[0126] Step S231: performing regional airflow fluctuation detection according to regional environmental historical wind data to obtain regional airflow fluctuation data;

[0127] Step S232: measuring the regional airflow variation amplitude according to the regional airflow fluctuation data to obtain the regional airflow variation amplitude data;

[0128] Step S233: performing blade unbalanced load detection on the regional airflow variation amplitude data according to the wind turbine simulation model to obtain blade unbalanced load data;

[0129] Step S234: calculating the speed change rate of the wind turbine blade over-speed operation data to obtain the speed change rate data of the turbine blade;

[0130] Step S235: Perform abnormal vibration detection on the fan blades according to the unbalanced load data on the fan blades and the speed change rate data on the generator fan blades to obtain abnormal vibration data on the generator fan blades.

[0131] In an embodiment of the present invention, when performing regional airflow fluctuation detection, it is first necessary to obtain the historical wind data of the regional environment, including the time series of wind speed and wind direction. The historical wind data is statistically analyzed using data processing software (such as MATLAB or Python) to extract the change pattern of wind speed and wind direction. The sliding window technology is applied to analyze the data in each time period to detect the fluctuation of the airflow. By setting the fluctuation threshold, the period of abnormal fluctuation is identified, and the regional airflow fluctuation data is generated. When the airflow change amplitude is measured according to the regional airflow fluctuation data, the identified airflow fluctuation needs to be quantitatively analyzed. The difference between the maximum and minimum values ​​of the fluctuation is calculated by the algorithm to obtain the change amplitude of the airflow. In this process, the data visualization tool is used to display the airflow fluctuation trend so as to observe the change more intuitively. The generated regional airflow change amplitude data needs to be input into the wind turbine simulation model when the blade unbalanced load detection is performed according to the airflow change amplitude data. According to the blade structure and aerodynamic characteristics defined in the simulation model, the load applied to the blade by different airflow change amplitudes is calculated. Using numerical analysis tools, simulations are performed for different airflow patterns to obtain the stress state of the fan blades under various working conditions. The obtained fan blade unbalanced load data is used to calculate the speed change rate of the wind turbine fan blade over-rotation operation data, and the fan blade speed data under over-rotation conditions needs to be extracted. Using data processing tools, the speed difference between each time point is calculated, and the speed change rate is calculated based on the time interval. The speed change trend is displayed using chart tools to more intuitively understand the speed fluctuation. When performing abnormal vibration detection of the fan blade, the generated generator fan blade speed change rate data needs to be combined with the fan blade unbalanced load data and the speed change rate data for analysis. The vibration sensor is used to monitor the vibration signal of the fan blade in real time and compare it with the theoretical calculated value. Through spectrum analysis and time domain analysis, it is determined whether there is an abnormal frequency component in the vibration signal. The obtained fan blade unbalanced load data is combined with the speed change rate data to evaluate the amplitude and frequency changes of the vibration signal, and finally the abnormal vibration data of the generator fan blade is obtained.

[0132] Preferably, step S24 comprises the following steps:

[0133] Step S241: Calculating the peak speed of the blades according to the over-speed operation data of the wind turbine blades to obtain the peak speed data of the blades;

[0134] Step S242: Calculating the wind overload of the fan blades according to the peak speed data of the fan blades to obtain the wind overload data of the fan blades;

[0135] Step S243: performing a wind plastic deformation test on the fan blade wind overload data to obtain the wind plastic deformation data of the fan blade;

[0136] Step S244: performing blade stress growth calculation on the blade wind plastic deformation data and the generator blade abnormal vibration data to obtain blade stress growth data;

[0137] Step S245: dividing the stress concentration area according to the blade stress growth data to obtain the blade stress growth concentration area data;

[0138] Step S246: Perform blade fatigue analysis based on the blade stress concentration growth area data to obtain wind turbine blade fatigue data.

[0139] In the embodiment of the present invention, when calculating the peak speed of the fan blade, it is first necessary to extract the real-time speed information of the fan blade from the over-speed operation data of the wind power generator. Use a data analysis tool to perform time series analysis on the speed data to find the maximum value of the speed. By calculating the change in speed in each time period, the peak speed of the fan blade in the over-speed state is determined. The obtained peak speed data of the fan blade is used to calculate the wind overload of the fan blade, and the peak speed data obtained is combined with the wind speed information for calculation. According to wind energy theory, a formula is used to calculate the wind force received by the fan blade, including factors such as air density, wind speed and the windward area of ​​the fan blade. The specific operation includes using a computing software (such as MATLAB) to establish a wind calculation model, and inputting relevant parameters to calculate the wind overload data at each time point, and obtain the wind overload data of the fan blade. When performing the wind plastic deformation detection of the fan blade, the obtained wind overload data needs to be input into the material mechanics model. The stress-strain relationship of the material is used to analyze the degree of plastic deformation of the fan blade material under overload conditions. Finite element analysis software is used to build a three-dimensional model of the fan blade, and wind overload is applied to simulate the plastic deformation process. By analyzing the deformed structure, the wind plastic deformation data of the fan blade is obtained. In the calculation of the stress growth of the fan blade, the plastic deformation data and the abnormal vibration data of the generator fan blade are combined to establish a stress analysis model. The stress analysis theory in material mechanics is used to calculate the influence of plastic deformation on the stress distribution of the fan blade. The specific operation includes inputting deformation data and vibration frequency, using calculation software to calculate stress increment, and obtaining the stress growth data of the fan blade. When dividing the stress concentration area of ​​the fan blade stress growth data, it is necessary to analyze the obtained stress growth data and identify the stress concentration area. Use heat map or contour map to represent the stress distribution, and combine the yield strength of the material to determine the location and size of the stress concentration area. Use graphical analysis tools to visualize the stress data to help determine the potential fatigue failure area, so as to obtain the data of the stress growth concentration area of ​​the fan blade. When performing fatigue analysis of the fan blade, it is necessary to rely on the data of the divided stress concentration area, use the fatigue analysis model, consider factors such as stress amplitude and number of cycles, and calculate the fatigue damage rate. Using the fatigue life prediction model, the stress in the stress concentration area is compared with the fatigue strength of the material to evaluate the fatigue life of the fan blade. Through the data analysis software, a fatigue analysis report is generated, and finally the fatigue data of the wind turbine fan blade is obtained.

[0140] Preferably, step S25 comprises the following steps:

[0141] Step S251: Perform bearing load dynamic transfer detection according to wind turbine blade fatigue data to obtain generator bearing load dynamic transfer data;

[0142] Step S252: analyzing the bearing resonance phenomenon according to the abnormal vibration data of the generator blades to obtain the generator bearing resonance data;

[0143] Step S253: estimating abnormal torque changes according to the generator bearing load dynamic transfer data and the generator bearing resonance data to obtain bearing torque abnormal change data;

[0144] Step S254: performing friction force growth calculation according to the bearing torque abnormal change data and the generator bearing load dynamic transfer data to obtain bearing friction force growth data;

[0145] Step S255: performing bearing wear aggravation detection according to the bearing friction force growth data to obtain bearing wear aggravation data;

[0146] Step S256: performing bearing damage estimation on the bearing wear aggravation data and the bearing torque abnormal change data to obtain the wind turbine bearing damage data.

[0147] In an embodiment of the present invention, when the dynamic transfer detection of the bearing load is performed, the corresponding load information is first extracted from the fatigue data of the blades of the wind turbine. A dynamic signal analysis tool is applied to monitor the load transfer between the blades and the bearings in real time. The load data is collected by the sensor installed on the bearing, and the spectrum analysis is performed to identify the instantaneous changes in the load transfer. During the analysis process, special attention is paid to the influence of the instantaneous load change on the bearing, and the dynamic transfer data of the generator bearing load is obtained. In the analysis of the bearing resonance phenomenon, the abnormal vibration data of the wind turbine blade is used to identify the resonant frequency in the vibration signal. The time domain vibration signal is converted into a frequency domain signal by the FFT (Fast Fourier Transform) algorithm, and the resonant frequency is extracted. The bearing is subjected to dynamic vibration monitoring to determine its resonance characteristics under different working conditions, and the influence of the resonance phenomenon on the running stability of the generator is evaluated to obtain the generator bearing resonance data. When the abnormal torque change is estimated, the obtained dynamic transfer data of the bearing load needs to be combined with the bearing resonance data. A mathematical model is applied to calculate the real-time change of the torque by establishing a relationship between the torque, the load and the speed. The numerical simulation method is used to analyze the torque changes under different loads, identify abnormal fluctuations, and obtain the abnormal change data of the bearing torque. When calculating the friction growth, the friction of the bearing is calculated based on the abnormal torque change data and the dynamic transfer data of the bearing load. Applying the principle of tribology, the known torque and bearing speed are substituted into the friction formula to obtain the corresponding friction data. By comparing the friction changes under different working conditions, the growth trend is analyzed to obtain the bearing friction growth data. When detecting the aggravation of bearing wear, it is necessary to analyze based on the friction growth data. By monitoring the friction heat and temperature changes of the bearing during operation, combined with the friction data, the signs of wear can be identified. Using temperature sensors and infrared imaging technology, the surface temperature changes of the bearing are monitored in real time, the high temperature area is identified and combined with the friction data to obtain the aggravation of bearing wear data. When estimating the bearing damage based on the aggravation of bearing wear data and the abnormal change of bearing torque data, the two sets of data are input into the damage prediction model. Using the cumulative damage theory, combined with the service life and actual operating conditions of the bearing, the relationship between the current wear state and historical data is analyzed. Using the data fitting method, the damage probability and predicted life are calculated, and finally the wind turbine bearing damage data is obtained.

[0148] Preferably, step S1 comprises the following steps:

[0149] Step S31: performing turbine load transfer detection on the wind turbine bearing damage data to obtain turbine load transfer data;

[0150] Step S32: predicting the turbine degradation trend according to the turbine load transfer data to obtain turbine degradation trend data;

[0151] Step S33: predicting the fault trend of the wind turbine generator according to the turbine degradation trend data and the generator blade fatigue data to obtain the fault trend data of the wind turbine generator;

[0152] Step S34: Based on the wind turbine simulation model, the turbine degradation trend data and the wind turbine failure trend data are subjected to wind turbine energy loss simulation to obtain wind turbine energy loss data.

[0153] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0154] Step S31: performing turbine load transfer detection on the wind turbine bearing damage data to obtain turbine load transfer data;

[0155] In the embodiment of the present invention, when performing turbine load transfer detection, relevant parameters are first extracted from the wind turbine bearing damage data. The load condition of the turbine is monitored in real time using load sensors, which can capture the load changes of the turbine under different working conditions. The acquired data is transmitted to the data processing unit, and the signal processing algorithm is applied to analyze the load fluctuation and identify the change trend of the load transfer. By comparing the data of different time periods, the turbine load transfer data is finally obtained.

[0156] Step S32: predicting the turbine degradation trend according to the turbine load transfer data to obtain turbine degradation trend data;

[0157] In the embodiment of the present invention, in the prediction of turbine degradation trend, firstly, a degradation prediction model is established based on the obtained turbine load transfer data. The model is based on the relationship between historical operation data and current load state, and predicts the degradation trend of the turbine in future operation through time series analysis technology. Statistical software is used to perform data fitting and regression analysis to calculate the degradation rate of each component of the turbine. Finally, the turbine degradation trend data is obtained.

[0158] Step S33: predicting the fault trend of the wind turbine generator according to the turbine degradation trend data and the generator blade fatigue data to obtain the fault trend data of the wind turbine generator;

[0159] In an embodiment of the present invention, a wind turbine fault trend prediction is carried out based on turbine degradation trend data and generator blade fatigue data. First, the blade fatigue data is combined with the turbine degradation trend, and a fault prediction model is established using a multivariate regression analysis method. By introducing correlation analysis, the influencing factors between turbine and blade fatigue are identified, and their contribution to the overall system failure is evaluated. The wind turbine fault trend data is finally generated.

[0160] Step S34: Based on the wind turbine simulation model, the turbine degradation trend data and the wind turbine failure trend data are subjected to wind turbine energy loss simulation to obtain wind turbine energy loss data.

[0161] In the embodiment of the present invention, when simulating energy loss based on the wind turbine simulation model, the obtained turbine degradation trend data and wind turbine fault trend data are first summarized. The dynamic model of the wind turbine is constructed using simulation software, and the degradation and fault trend data are input to simulate the energy conversion efficiency under different working conditions. By running the simulation, the change of energy loss is monitored and its impact on power generation efficiency is analyzed. Finally, the energy loss data of the wind turbine is obtained.

[0162] Preferably, step S34 includes the following steps:

[0163] Step S341: Calculate the increase of the wind response time of the generator according to the fault trend data of the wind power generator to obtain the increase data of the wind response time of the generator;

[0164] Step S342: performing turbine output power attenuation prediction on the turbine degradation trend data to obtain turbine output power attenuation data;

[0165] Step S343: performing turbine performance attenuation detection according to the turbine output power attenuation data to obtain turbine performance attenuation data;

[0166] Step S344: Calculate the power generation efficiency reduction based on the turbine performance attenuation data and the generator wind response time growth data to obtain the wind power generator power generation efficiency reduction data;

[0167] Step S345: calculating the energy conversion efficiency of the wind turbine generator according to the fault trend data of the wind turbine generator to obtain energy conversion efficiency reduction data;

[0168] Step S346: Based on the wind turbine simulation model, the energy conversion efficiency reduction data and the wind turbine power generation efficiency reduction data are subjected to a wind turbine energy loss simulation to obtain the wind turbine energy loss data.

[0169] In an embodiment of the present invention, the process of calculating the increase in response time of the generator to wind includes extracting characteristic parameters related to wind force changes from the fault trend data of the wind power generator. The historical fault data is analyzed in time series by using a data analysis tool to identify the response time of the wind power generator under different wind speed conditions. By establishing a statistical model, the relationship between the response time and the wind speed change is analyzed, so as to calculate the increase in the response time of the generator under a specific wind speed. The prediction of turbine output power attenuation adopts a regression analysis method based on historical operation data, extracts key parameters such as load, speed and temperature from the turbine degradation trend data, and analyzes the relationship between these parameters and the turbine output power through a linear or nonlinear regression model. The model is trained using historical data to obtain a trend prediction of output power changes over time. The turbine output power attenuation data is obtained, and the step of turbine performance attenuation detection includes comparative analysis using the turbine output power attenuation data and real-time monitoring data, setting a monitoring system to obtain the output power, speed and temperature of the turbine in real time, and comparing it with the predicted output power. The performance attenuation degree of the turbine is evaluated by calculating the difference between the actual output power and the predicted value. The data analysis software can help generate a performance attenuation report and obtain turbine performance attenuation data. The steps of turbine performance degradation detection include comparative analysis using turbine output power degradation data and real-time monitoring data, setting up a monitoring system to obtain data such as turbine output power, speed and temperature in real time, and comparing them with the predicted output power. The performance degradation degree of the turbine is evaluated by calculating the difference between the actual output power and the predicted value. The calculation of power generation efficiency reduction is based on a comprehensive analysis of turbine performance degradation data and generator response time growth data. By constructing a calculation model, inputting turbine output power degradation data and generator response time data, the change in power generation efficiency is calculated using a formula. This process involves comprehensive consideration of multiple influencing factors, such as wind speed, turbine speed and fault status. The power generation efficiency reduction data of the wind turbine is obtained, and the energy conversion efficiency calculation of the wind turbine is based on the fault trend data of the wind turbine, combined with the actual power generation capacity for analysis, extracting the actual data of the input wind energy and output electric energy of the wind turbine, and calculating the energy conversion efficiency. This process includes analyzing historical operation data, identifying the change in conversion efficiency under different fault conditions, and summarizing the energy loss under different working conditions by induction. The process of obtaining energy conversion efficiency reduction data and simulating the energy loss of the wind turbine uses a simulation model for data input and processing. Based on the obtained data on the reduction of energy conversion efficiency and power generation efficiency, the dynamic model of the wind turbine generator is constructed using simulation software. After inputting the required parameters, the simulation program is run to observe the energy loss under different working conditions. By comparing the simulation results with the actual operating data, the energy loss of the wind turbine generator under various operating conditions is analyzed, and finally the energy loss data of the wind turbine generator is obtained.

[0170] Preferably, step S4 comprises the following steps:

[0171] Step S41: fusing the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data;

[0172] Step S42: performing abnormality detection on the wind turbine generator according to the information fusion data of the wind turbine generator to obtain abnormal power generation data of the wind turbine generator;

[0173] Step S43: performing fault prediction optimization on abnormal power generation data of the wind turbine generator based on the electrical automation system to obtain fault prediction optimization data of the electrical automation system;

[0174] Step S44: Optimizing the control strategy according to the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

[0175] In an embodiment of the present invention, the process of information fusion of the fault trend data and energy loss data of the wind turbine generator is realized by data integration technology. In this process, firstly, relevant fault trend data including the operation history, fault frequency and energy loss record of the generator are extracted from the database. Then, the two sets of data are weighted and integrated by using a data fusion algorithm, such as Kalman filtering or Bayesian inference. By calculating the weights of different data sources, they are merged into a set of comprehensive data to obtain the information fusion data of the wind turbine generator. The step of performing anomaly detection according to the information fusion data of the wind turbine generator involves the application of multiple algorithms, and a machine learning algorithm, such as a support vector machine or a neural network, is used to train the model to identify typical features under normal operating conditions. By inputting the fusion data, the deviation between the model and the normal features is detected, and the anomaly score is calculated. If the score exceeds the set threshold, it is determined to be power generation abnormality. The whole process needs to be carried out through a data processing platform to ensure efficient analysis and real-time monitoring, and obtain the abnormal power generation data of the wind turbine generator. The electrical automation system performs fault prediction optimization on the abnormal power generation data of the wind turbine generator, adopts a data-driven method to obtain abnormal data from the abnormal detection step, and establishes a fault prediction model in combination with historical fault records. Using machine learning methods, such as random forests or decision trees, input power generation abnormality data for training. Improve the accuracy of the model through cross-validation to ensure that the probability and time of potential faults can be accurately predicted. After optimization, the fault prediction optimization data of the electrical automation system is obtained. The steps for optimizing the control strategy are based on the fault prediction optimization data of the electrical automation system. The fault prediction results are compared with the current control strategy to identify existing problems and potential risks. Adaptive control methods in control theory are used to dynamically adjust control parameters based on fault prediction data to improve the response speed and stability of the system. Combined with real-time monitoring data, a closed-loop control strategy is implemented to ensure early intervention before abnormalities occur. Finally, the optimized control strategy optimization data of the electrical automation system is obtained.

[0176] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An information fusion method for an electrical automation system, characterized in that: The following steps are involved: Step S1: Acquire electrical automation system configuration data; construct a wind turbine simulation model according to the electrical automation system configuration data to obtain a wind turbine simulation model; Step S2: Obtaining historical wind data of the regional environment; Based on the wind turbine simulation model, the fan blade over-rotation operation simulation is performed on the historical wind data of the regional environment to obtain the wind turbine fan blade over-rotation operation data; the bearing damage is estimated based on the wind turbine fan blade over-rotation operation data to obtain the wind turbine bearing damage data; Step S3: performing wind turbine failure trend prediction on the wind turbine bearing damage data to obtain wind turbine failure trend data; Based on the wind turbine simulation model, the wind turbine energy loss is estimated based on the wind turbine fault trend data to obtain the wind turbine energy loss data; Step S4: Perform information fusion on the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data; perform fault prediction optimization on the wind turbine information fusion data based on the electrical automation system to obtain electrical automation system fault prediction optimization data; perform control strategy optimization based on the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

2. The information fusion method of the electrical automation system according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire electrical automation system configuration data; Step S12: collecting the electrical structure of the wind turbine generator according to the electrical automation system configuration data to obtain the electrical structure data of the wind turbine generator; Step S13: extracting the mechanical structure of the wind turbine generator according to the electrical automation system configuration data to obtain the mechanical structure data of the wind turbine generator; Step S14: constructing a wind turbine simulation model according to the mechanical structure data and the electrical structure data of the wind turbine to obtain a wind turbine simulation model.

3. The information fusion method of the electrical automation system according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: collecting electrical connection mode data of the wind turbine generator electrical structure to obtain electrical connection mode data of the wind turbine generator; Step S142: extracting blade shape according to the mechanical structure data of the wind turbine generator to obtain blade shape data of the wind turbine generator; Step S143: measuring the bending degree of the blades according to the blade shape data of the wind turbine generator to obtain the bending degree data of the blades of the wind turbine generator; Step S144: Calculating the wind energy capture efficiency according to the bending degree data of the wind turbine blades to obtain the wind energy capture efficiency data of the turbine blades; Step S145: constructing a wind power generator simulation model based on the wind energy capture efficiency data of the generator blades and the electrical connection mode data of the wind power generator to obtain a wind power generator simulation model.

4. The information fusion method of the electrical automation system according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Acquire historical wind data of regional environment; Step S22: performing a blade over-rotation simulation on the historical wind data of the regional environment based on the wind turbine simulation model to obtain the blade over-rotation data of the wind turbine; Step S23: performing abnormal vibration detection on the wind turbine blades over-rotation operation data and the regional environmental historical wind data according to the wind turbine simulation model to obtain abnormal vibration data of the turbine blades; Step S24: performing blade fatigue analysis based on the abnormal vibration data of the generator blades and the over-rotation operation data of the wind turbine generator blades to obtain the wind turbine generator blade fatigue data; Step S25: Predict bearing damage based on wind turbine blade fatigue data and generator blade abnormal vibration data to obtain wind turbine bearing damage data.

5. The information fusion method of the electrical automation system according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: performing regional airflow fluctuation detection according to regional environmental historical wind data to obtain regional airflow fluctuation data; Step S232: measuring the regional airflow variation amplitude according to the regional airflow fluctuation data to obtain the regional airflow variation amplitude data; Step S233: performing blade unbalanced load detection on the regional airflow variation amplitude data according to the wind turbine simulation model to obtain blade unbalanced load data; Step S234: calculating the speed change rate of the wind turbine blade over-speed operation data to obtain the speed change rate data of the turbine blade; Step S235: Perform abnormal vibration detection on the fan blades according to the unbalanced load data on the fan blades and the speed change rate data on the generator fan blades to obtain abnormal vibration data on the generator fan blades.

6. The information fusion method of the electrical automation system according to claim 4, characterized in that: Step S24 includes the following steps: Step S241: Calculating the peak speed of the blades according to the over-speed operation data of the wind turbine blades to obtain the peak speed data of the blades; Step S242: Calculating the wind overload of the fan blades according to the peak speed data of the fan blades to obtain the wind overload data of the fan blades; Step S243: performing a wind plastic deformation test on the fan blade wind overload data to obtain the wind plastic deformation data of the fan blade; Step S244: performing blade stress growth calculation on the blade wind plastic deformation data and the generator blade abnormal vibration data to obtain blade stress growth data; Step S245: dividing the stress concentration area according to the blade stress growth data to obtain the blade stress growth concentration area data; Step S246: Perform blade fatigue analysis based on the blade stress concentration growth area data to obtain wind turbine blade fatigue data.

7. The information fusion method of the electrical automation system according to claim 4, characterized in that: Step S25 includes the following steps: Step S251: Perform bearing load dynamic transfer detection according to wind turbine blade fatigue data to obtain generator bearing load dynamic transfer data; Step S252: analyzing the bearing resonance phenomenon according to the abnormal vibration data of the generator blades to obtain the generator bearing resonance data; Step S253: estimating abnormal torque changes according to the generator bearing load dynamic transfer data and the generator bearing resonance data to obtain bearing torque abnormal change data; Step S254: performing friction force growth calculation according to the bearing torque abnormal change data and the generator bearing load dynamic transfer data to obtain bearing friction force growth data; Step S255: performing bearing wear aggravation detection according to the bearing friction force growth data to obtain bearing wear aggravation data; Step S256: performing bearing damage estimation on the bearing wear aggravation data and the bearing torque abnormal change data to obtain the wind turbine bearing damage data.

8. The information fusion method of the electrical automation system according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing turbine load transfer detection on the wind turbine bearing damage data to obtain turbine load transfer data; Step S32: predicting the turbine degradation trend according to the turbine load transfer data to obtain turbine degradation trend data; Step S33: predicting the fault trend of the wind turbine generator according to the turbine degradation trend data and the generator blade fatigue data to obtain the fault trend data of the wind turbine generator; Step S34: Based on the wind turbine simulation model, the turbine degradation trend data and the wind turbine failure trend data are subjected to wind turbine energy loss simulation to obtain wind turbine energy loss data.

9. The information fusion method of the electrical automation system according to claim 8, characterized in that: Step S34 includes the following steps: Step S341: Calculate the increase of the wind response time of the generator according to the fault trend data of the wind power generator to obtain the increase data of the wind response time of the generator; Step S342: performing turbine output power attenuation prediction on the turbine degradation trend data to obtain turbine output power attenuation data; Step S343: performing turbine performance attenuation detection according to the turbine output power attenuation data to obtain turbine performance attenuation data; Step S344: Calculate the power generation efficiency reduction based on the turbine performance attenuation data and the generator wind response time growth data to obtain the wind power generator power generation efficiency reduction data; Step S345: calculating the energy conversion efficiency of the wind turbine generator according to the fault trend data of the wind turbine generator to obtain energy conversion efficiency reduction data; Step S346: Based on the wind turbine simulation model, the energy conversion efficiency reduction data and the wind turbine power generation efficiency reduction data are subjected to a wind turbine energy loss simulation to obtain the wind turbine energy loss data.

10. The information fusion method of the electrical automation system according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: fusing the wind turbine fault trend data and the wind turbine energy loss data to obtain wind turbine information fusion data; Step S42: performing abnormality detection on the wind turbine generator according to the information fusion data of the wind turbine generator to obtain abnormal power generation data of the wind turbine generator; Step S43: performing fault prediction optimization on abnormal power generation data of the wind turbine generator based on the electrical automation system to obtain fault prediction optimization data of the electrical automation system; Step S44: Optimizing the control strategy according to the electrical automation system fault prediction optimization data to obtain electrical automation system control strategy optimization data.

Images