A multi-dimensional risk assessment method and system for wind power equipment early warning information

Abstract

This application belongs to the field of intelligent operation and maintenance technology for wind power equipment, and provides a multi-dimensional risk assessment method and system for wind power equipment early warning information. The method includes: standardizing the failure mode classification of early warning information to obtain standardized classification labels; obtaining expert prior scores and historical case data for the corresponding failure mode categories based on the standardized classification labels; fusing and correcting the expert prior scores and the historical case data to obtain risk scores for multiple risk dimensions of the early warning information; using the analytic hierarchy process (AHP) to compare the relative importance of each risk dimension in pairs to obtain the weight of each risk dimension; weighted summing of the risk scores and weights of each risk dimension to obtain a comprehensive score; and mapping the comprehensive score to a preset threshold to obtain a risk level, thus achieving multi-dimensional risk assessment. This application can solve the technical problems of existing wind power early warning information assessments having a single dimension and lacking interpretability.

Description

Technical Field

[0001] This application belongs to the field of intelligent operation and maintenance technology of wind power equipment, specifically involving a multi-dimensional risk assessment method and system for wind power equipment early warning information. Background Technology

[0002] As the global energy structure accelerates its transition towards clean and low-carbon energy, wind power has become a crucial component of the renewable energy system. Because wind turbines are typically deployed in harsh environments such as remote mountainous areas and offshore locations, they endure complex environmental loads such as variable wind speeds, extreme temperatures, salt spray corrosion, and lightning strikes. Therefore, their operational reliability and maintenance efficiency have received widespread attention within the industry. To promptly monitor the operating status of the turbines, wind farms commonly deploy Supervisory Control and Data Acquisition (SCADA) systems and Condition Monitoring Systems (CMS) to collect turbine operating parameters and vibration signals in real time and trigger corresponding alarm messages based on preset thresholds, thereby achieving early detection of abnormal equipment conditions. In recent years, with the development of artificial intelligence and data analysis technologies, the industry has further introduced intelligent operation and maintenance methods. By analyzing the correlation of multi-source monitoring data, potential equipment defects are uncovered, driving a shift in operation and maintenance models from passive emergency repairs to proactive early warning. In terms of risk analysis, Failure Mode and Effects Analysis (FMEA), as a widely recognized risk assessment tool in the engineering field, typically assesses and ranks the risk priority of various faults using three factors: severity, occurrence, and detectability, providing a reference for the allocation of maintenance resources.

[0003] However, the aforementioned existing technologies still have significant shortcomings when applied to the processing and risk assessment of wind power equipment early warning information. Firstly, early warning information from wind farms often originates from records of different manufacturers, systems, and maintenance personnel, lacking a unified classification standard. This leads to inconsistencies in the descriptions of the same type of fault in different reports, resulting in fragmented data statistics and scattered samples, making it difficult to form a stable and effective knowledge accumulation. Secondly, traditional FMEA models lack adaptability in early warning scenarios: the early warning information does not correspond to faults that have already occurred, making its occurrence rate difficult to equate with actual risk; simultaneously, the model lacks a time dimension, failing to characterize the dynamic evolution characteristics of whether and how quickly a fault escalates; and many early warning cases lack key fields such as downtime and power loss, which, if forcibly included in calculations, can easily produce unstable and difficult-to-interpret results. Thirdly, existing risk assessment methods have relatively singular assessment dimensions, focusing primarily on the severity of the fault itself, with insufficient quantitative coverage of factors of concern to on-site decision-making, such as maintenance difficulty, evolution trends, and economic losses, resulting in a lack of accurate mapping between assessment results and on-site maintenance decisions. Fourth, existing intelligent early warning systems mostly use black-box models to output evaluation results, lacking transparent explanations of the scoring criteria. On-site maintenance personnel find it difficult to understand the reasons for the early warning ranking and the objects that should be prioritized, making it difficult for the model output to be effectively transformed into actual maintenance decisions. Summary of the Invention

[0004] This application addresses the technical problem that existing wind power early warning information assessments have a single dimension and lack interpretability, by providing a multi-dimensional risk assessment method and system for wind power equipment early warning information.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, a multi-dimensional risk assessment method for wind power equipment early warning information includes: Obtain early warning information for wind power equipment; The warning information is processed by standardized failure mode classification to obtain standardized classification labels; Based on the standardized classification labels, obtain the expert prior scores and historical case data for the corresponding failure mode categories, and perform fusion and correction processing on the expert prior scores and the historical case data to obtain the risk scores for multiple risk dimensions of the early warning information. The relative importance of each risk dimension is compared in pairs using the analytic hierarchy process (AHP) to obtain the weight of each risk dimension. The risk scores and weights of each risk dimension are weighted and summed to obtain a comprehensive score. The comprehensive score is then mapped to a preset threshold to obtain the risk level, thereby achieving multi-dimensional risk assessment.

[0006] In some implementations, the multiple risk dimensions include a severity dimension, a maintenance difficulty dimension, an evolution risk dimension, and an economic impact dimension.

[0007] In some implementations, the step of standardizing the failure mode classification of the early warning information to obtain standardized classification labels includes: Based on the fields representing the faulty components and fault types in the warning information, the warning information is mapped to the corresponding failure mode categories in the preset failure mode classification system to obtain the standardized classification labels; The failure mode classification system includes failure modes corresponding to the blades, gearboxes, generators, converters, pitch systems, yaw systems, wind measurement systems, braking systems, and control systems of wind turbines.

[0008] In some implementations, the process of fusing and correcting the expert prior scores with the historical case data to obtain risk scores for multiple risk dimensions of the early warning information includes: Based on the historical downtime records of the corresponding failure mode categories in the historical case data, the expert prior score of the severity dimension is corrected to obtain the risk score of the severity dimension; Based on the historical handling time of the corresponding failure mode category in the historical case data, the expert prior score of the maintenance difficulty dimension is corrected to obtain the risk score of the maintenance difficulty dimension. Based on the statistical probability of failure escalation of the corresponding failure mode category within a preset time window in the historical case data, the expert prior score of the evolutionary risk dimension is corrected to obtain the risk score of the evolutionary risk dimension. Obtain the power curve of the wind turbine, calculate the power loss based on the power curve and the expected downtime corresponding to the early warning information, and obtain a risk score for the economic impact dimension based on the power loss.

[0009] In some implementations, after mapping the comprehensive score to a preset threshold to obtain the risk level, the method further includes: The risk scores for each of the aforementioned risk dimensions are combined with a pre-built knowledge base to generate explanatory text, resulting in explanatory outputs corresponding to each of the aforementioned risk dimensions.

[0010] In some implementations, after using the analytic hierarchy process (AHP) to perform pairwise comparisons of the relative importance of each risk dimension to obtain the weight of each risk dimension, the method further includes: After updating the historical case data during the operation of the wind turbine, the expert prior scores and weights of each risk dimension are backtested and corrected to obtain the updated expert prior scores and weights.

[0011] Secondly, a multi-dimensional risk assessment system for early warning information of wind power equipment includes: The data acquisition module is used to acquire early warning information from wind power equipment; The classification processing module is used to perform standardized failure mode classification processing on the warning information to obtain standardized classification labels; The scoring engine module is used to obtain the expert prior scores and historical case data of the corresponding failure mode category according to the standardized classification labels, and to perform fusion and correction processing on the expert prior scores and the historical case data to obtain the risk scores of multiple risk dimensions of the early warning information. The weight calculation module is used to perform pairwise comparisons of the relative importance of each of the risk dimensions using the analytic hierarchy process (AHP) to obtain the weight of each of the risk dimensions. The comprehensive assessment module is used to perform a weighted summation of the risk scores and weights of each risk dimension to obtain a comprehensive score, and then map the comprehensive score to a preset threshold to obtain a risk level, thereby realizing multi-dimensional risk assessment.

[0012] Thirdly, a computer device includes: a processor and a computer-readable storage medium; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements a multi-dimensional risk assessment method for early warning information of wind power equipment as described above.

[0013] Fourthly, a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed as described in the multi-dimensional risk assessment method for early warning information of wind power equipment.

[0014] Fifthly, a computer program product comprising a computer program that, when executed by a processor, implements the multi-dimensional risk assessment method for wind power equipment early warning information as described above.

[0015] Compared with the prior art, this application has the following beneficial effects: This application obtains standardized classification labels by standardizing the failure mode classification of the early warning information, thus grouping early warning information from mixed sources and with inconsistent descriptions into a unified failure mode category, providing a unified entry point and stable foundation for subsequent scoring. It obtains risk scores for multiple risk dimensions of the early warning information by fusing and correcting the expert prior scores with historical case data, enabling the scores to characterize risks from multiple dimensions based on expert experience and historical data correction, maintaining score stability even in early warning scenarios with sparse historical data. It uses the analytic hierarchy process (AHP) to compare the relative importance of each risk dimension in pairs to obtain the weights of each risk dimension, transforming the qualitative judgment of the relative importance of each dimension into quantitative weights. Finally, it obtains a comprehensive score through weighted summation, maps the comprehensive score to a preset threshold to obtain the risk level, and outputs a unified comprehensive score and risk level that can be used for priority ranking, thereby achieving efficient multi-dimensional risk assessment and classification of early warning information.

[0016] Furthermore, by defining the multiple risk dimensions, including severity, maintenance difficulty, evolution risk, and economic impact, the risk assessment is conducted from four aspects: safety, maintenance cost, evolution, and economy. This covers a variety of risk factors that are of concern to maintenance personnel. Compared with the method of measuring risk by a single severity, the assessment results are more in line with the actual needs of on-site maintenance decisions and are more practical.

[0017] Furthermore, by mapping the warning information to the corresponding failure mode categories in a preset failure mode classification system based on the fields representing the faulty components and failure types in the warning information, and specifying the system as corresponding to the failure modes of blades, gearboxes, generators, converters, pitch systems, yaw systems, wind measurement systems, braking systems, and control systems respectively, the classification mapping has a clear and unified basis and coverage, solving the problems of inconsistent warning information descriptions and scattered statistical standards from different manufacturers and systems, and providing a stable classification basis for sample collection and knowledge accumulation of similar events.

[0018] Furthermore, by defining the correction criteria for the four dimensions of scoring respectively—namely, the severity dimension is corrected based on historical outage records, the maintenance difficulty dimension is corrected based on historical handling time, the evolution risk dimension is corrected based on the statistical probability of fault escalation within a preset time window, and the economic impact dimension is obtained by calculating the lost electricity based on the power curve and the expected outage time—the scoring of each dimension is based on available historical technical data and unit operation data, thereby improving the objectivity and robustness of the scoring of each dimension. Among them, the evolution risk dimension introduces the statistical probability of fault escalation within a preset time window, so that the score can reflect the possibility of fault evolution over time.

[0019] Furthermore, after obtaining the weights, the historical case data is updated during the operation of the wind turbine, and the expert prior scores and weights of each risk dimension are backtested and corrected to obtain updated expert prior scores and weights. This allows the scoring benchmark and dimension weights to be continuously updated with the accumulation of historical case data, forming an iterative closed-loop optimization, thereby enabling the evaluation model to adapt to the data characteristics of different sites and different stages. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a multi-dimensional risk assessment method for wind power equipment early warning information provided in this application embodiment; Figure 2 A structural diagram of a multi-dimensional risk assessment system for early warning information of wind power equipment provided in this application embodiment; Figure 3 A computer device diagram provided for an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] In one embodiment of this application, such as Figure 1 As shown, a multi-dimensional risk assessment method for wind power equipment early warning information is provided, including: S1, obtain early warning information for wind power equipment; This step involves acquiring early warning information from the wind power equipment. This early warning information is generated by the data acquisition and monitoring control system and condition monitoring system deployed at the wind farm when collecting wind turbine operating parameters and vibration data and triggering alarms based on preset thresholds. The early warning information includes fields representing the system to which the fault belongs, fields representing the fault type, and the early warning level. In one embodiment, the early warning information is a level-two warning for abnormal temperature in the generator's non-drive end bearing, or a level-two warning for radial damage at the generator's non-drive end.

[0024] S2, perform standardized failure mode classification processing on the warning information to obtain standardized classification labels; This step maps the warning information to corresponding failure mode categories in a preset failure mode classification system based on the fields representing the faulty components and failure types in the warning information, thus obtaining standardized classification labels for the warning information. The failure mode classification system includes failure modes corresponding to the blades, gearboxes, generators, converters, pitch systems, yaw systems, wind measurement systems, braking systems, and control systems of wind turbines. By uniformly mapping warning information from different manufacturers, systems, and maintenance records to the above failure mode categories, warning information with inconsistent descriptions and scattered statistical definitions is grouped into a unified entry point, resulting in unified standardized classification labels and providing a unified basis for scoring in subsequent steps.

[0025] In one implementation, based on the fault system field and the warning information field in the warning information, the secondary warning information of abnormal temperature of the non-drive end bearing of the generator is mapped to the failure mode category corresponding to the generator, and the corresponding standardized classification label is obtained.

[0026] S3. Based on the standardized classification labels, obtain the expert prior scores and historical case data for the corresponding failure mode categories, and perform fusion and correction processing on the expert prior scores and the historical case data to obtain the risk scores of multiple risk dimensions of the early warning information. This step obtains the expert prior score and historical case data of the failure mode category corresponding to the standardized classification label, and then performs fusion and correction processing on the expert prior score and the historical case data to obtain the risk score of the warning information under multiple risk dimensions.

[0027] The expert prior score is a pre-configured scoring benchmark for each failure mode category across each risk dimension; the historical case data includes downtime, handling records, and evolution path information for similar events of the corresponding failure mode category in the historical case database. The risk scores for each risk dimension adopt a preset numerical range, which, in one embodiment, is 1 to 10.

[0028] The multiple risk dimensions include severity, maintenance difficulty, evolution risk, and economic impact. The severity dimension characterizes the impact of the fault corresponding to the warning information on the safety and key functions of the wind turbine. The maintenance difficulty dimension characterizes the time and resources required to locate and handle the fault. The evolution risk dimension characterizes the possibility and speed at which the fault develops into a more serious state. The economic impact dimension characterizes the power generation loss of the wind turbine caused by the fault.

[0029] In one implementation, the fusion correction process includes: determining an expert prior score for the severity dimension based on the warning level carried by the warning information and a preset failure mode severity scoring benchmark, and correcting the expert prior score based on historical downtime records of the corresponding failure mode category in the historical case data to obtain a risk score for the severity dimension; correcting the expert prior score for the maintenance difficulty dimension based on the historical handling time of the corresponding failure mode category in the historical case data to obtain a risk score for the maintenance difficulty dimension; correcting the expert prior score for the evolution risk dimension based on the statistical probability of the corresponding failure mode category escalating into a more severe failure within a preset time window in the historical case data to obtain a risk score for the evolution risk dimension; acquiring the power curve of the wind turbine, calculating the lost power based on the power curve and the expected downtime corresponding to the warning information, and obtaining a risk score for the economic impact dimension based on the lost power.

[0030] Taking the secondary warning information of abnormal temperature in the non-drive end bearing of the generator as an example, in one implementation, the severity dimension is based on the risk that the abnormal bearing temperature may be caused by poor lubrication, wear, or electrical problems, and there is a risk of more serious failures such as bearing seizure. Combined with the secondary warning level of the warning information and the preset failure mode severity scoring benchmark, the risk score is 6.1. The economic impact dimension is based on the unit power curve and the estimated downtime of 4.5 hours, which estimates the power loss to be 4709 kWh, and the risk score is 5.8. The evolution risk dimension is based on the statistical probability that similar temperature abnormality events will escalate into downtime failures within 7 days in historical case data, which is about 9%, and the maintenance difficulty dimension is based on the fact that the preliminary diagnosis can be completed through online monitoring data, and the risk score is 1.5.

[0031] Taking the secondary warning information of radial damage at the non-drive end of the generator as an example, in another implementation, the severity dimension is based on the warning information clearly indicating that the bearing has moderate damage and poses a significant threat to equipment safety and operational reliability. Combined with the secondary warning level of the warning information, a risk score of 7.6 is obtained. The evolution risk dimension is based on the statistical probability of similar damage warnings escalating into more serious faults within 30 days, which is 31% in historical case data, resulting in a risk score of 4.5. The maintenance difficulty dimension is based on the condition monitoring system providing damage location and clear diagnosis, while repair requires shutdown to replace the bearing and involves hoisting and professional operations, resulting in a risk score of 1.5. The economic impact dimension is based on the estimated power loss of 4709 kWh for the expected shutdown duration of 8 hours, resulting in a risk score of 5.8.

[0032] S4. The relative importance of each risk dimension is compared in pairs using the analytic hierarchy process (AHP) to obtain the weight of each risk dimension. This step employs the Analytic Hierarchy Process (AHP) to construct pairwise comparison matrices based on the pairwise comparisons of the relative importance of each risk dimension. These pairwise comparison results represent the judgment data on the relative importance of each risk dimension, which is then converted into quantitative weight parameters using the AHP.

[0033] In one implementation, the weights of the severity dimension, economic impact dimension, maintenance difficulty dimension, and evolution risk dimension are 0.37, 0.28, 0.19, and 0.14, respectively.

[0034] S5, the risk scores and weights of each risk dimension are weighted and summed to obtain a comprehensive score, and the comprehensive score is mapped to a preset threshold to obtain a risk level, thereby realizing multi-dimensional risk assessment.

[0035] This step involves weighted summation of the risk scores for each risk dimension and their corresponding weights to obtain a comprehensive score for the warning information. Based on the mapping relationship between the comprehensive score and a preset threshold, the risk level of the warning information is determined, thus achieving a multi-dimensional risk assessment of the warning information. The risk level is divided into several grades according to the mapping relationship between the comprehensive score and the preset threshold. In one embodiment, the risk levels include medium (concerned) and high (severe).

[0036] Taking the level-two early warning information of abnormal temperature of the non-drive end bearing of the generator as an example, in one implementation, the comprehensive score is 6.1×0.37+5.8×0.28+1.5×0.19+2.7×0.14=4.70. According to the mapping relationship between the comprehensive score and the preset threshold, the risk level corresponding to the comprehensive score of 4.70 is medium (attention).

[0037] Taking the secondary warning information of radial damage at the non-driving end of the generator as an example, in another implementation, the comprehensive score is 7.6×0.37+5.8×0.28+1.5×0.19+4.5×0.14=6.42. According to the mapping relationship between the comprehensive score and the preset threshold, the risk level corresponding to the comprehensive score of 6.42 is high (severe).

[0038] In one implementation, after obtaining the risk level in step S5, the method further includes: performing explanatory text generation processing on the risk scores of each risk dimension and a pre-set knowledge base to obtain explanatory outputs corresponding to each risk dimension. The explanatory outputs are used to explain the scoring basis of each risk dimension and the key risk points of the warning information. The output format of the explanatory outputs includes overview tags and detailed descriptions, and includes handling suggestions for the warning information.

[0039] Taking a level-two early warning message of abnormal bearing temperature at the non-drive end of a generator as an example, in one implementation, the interpretive output includes: a severity score of 6.1, indicating that abnormal bearing temperature may indicate poor lubrication, wear, or electrical problems, with a risk of more serious failures such as bearing seizure; an economic impact score of 5.8, indicating that if left unaddressed, it is estimated to result in a loss of approximately 4709 kWh of power generation; an evolution risk score of 2.7, indicating that there is approximately a 9% probability of escalation, requiring close monitoring; and a maintenance difficulty score of 1.5, indicating that the initial diagnosis and inspection are relatively easy. The recommended action is to immediately shut down the generator for inspection, focusing on checking the bearing lubrication status and the accuracy of the temperature sensor. For this early warning message, a shutdown inspection is arranged according to the recommended action. The inspection results show insufficient bearing grease; after replenishing lubrication, the temperature returns to normal.

[0040] Taking a Level 2 early warning message indicating radial damage at the non-drive end of a generator as an example, in another implementation, the interpretive output includes: a severity score of 7.6, indicating that the Level 2 early warning message combined with bearing damage constitutes a significant threat to equipment safety and operational reliability; an evolution risk score of 4.5, indicating that based on historical data, this type of damage has a 31% probability of evolving into a more severe state; a maintenance difficulty score of 1.5, indicating that the diagnosis is clear, but location and repair involve shutdown and specialized operations; and an economic impact score of 5.8, indicating that if not handled promptly, it is estimated to result in a loss of approximately 4709 kWh of power generation. The recommended action is to prioritize this action and arrange for a shutdown to replace the bearing as soon as possible. This early warning message is marked as high risk and given the highest priority in the daily schedule. After arranging a shutdown to replace the bearing, the unit resumes normal operation.

[0041] In one implementation, after obtaining the weights of each risk dimension in step S4, the method further includes: updating the historical case data during the operation of the wind turbine, backtesting and correcting the expert prior scores and weights of each risk dimension to obtain updated expert prior scores and weights, and performing multidimensional risk assessment on the subsequently obtained early warning information based on the updated expert prior scores and weights.

[0042] In one embodiment of this application, such as Figure 2 As shown, a multi-dimensional risk assessment system for early warning information of wind power equipment is provided, including: The data acquisition module is used to acquire early warning information from wind power equipment; The classification processing module is used to perform standardized failure mode classification processing on the warning information to obtain standardized classification labels; The scoring engine module is used to obtain the expert prior scores and historical case data of the corresponding failure mode category according to the standardized classification labels, and to perform fusion and correction processing on the expert prior scores and the historical case data to obtain the risk scores of multiple risk dimensions of the early warning information. The weight calculation module is used to perform pairwise comparisons of the relative importance of each of the risk dimensions using the analytic hierarchy process (AHP) to obtain the weight of each of the risk dimensions. The comprehensive assessment module is used to perform a weighted summation of the risk scores and weights of each risk dimension to obtain a comprehensive score, and then map the comprehensive score to a preset threshold to obtain a risk level, thereby realizing multi-dimensional risk assessment.

[0043] Specific limitations regarding a multi-dimensional risk assessment system for wind power equipment early warning information can be found in the above-described limitations of a multi-dimensional risk assessment method for wind power equipment early warning information; the corresponding technical effects are equivalent and will not be repeated here. Each module in the aforementioned multi-dimensional risk assessment system for wind power equipment early warning information can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0044] Figure 3 An internal structural diagram of a computer device is shown in one embodiment. This computer device may specifically be a terminal or a server. Figure 3As shown, the computer device includes a processor, memory, network interface, display, camera, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a multi-dimensional risk assessment method for wind power equipment early warning information. The display screen can be an LCD screen or an e-ink display screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0045] As will be understood by those skilled in the art, computer equipment Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. Specific computing devices may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0046] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0047] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0048] In summary, the multi-dimensional risk assessment method, system, computer equipment, and storage medium for wind power equipment early warning information provided in this application embodiment unifies the assessment entry point for early warning information through standardized failure mode classification. It achieves stable scoring across multiple dimensions—severity, maintenance difficulty, evolutionary risk, and economic impact—through the fusion and correction of expert prior scoring and historical case data. Furthermore, it uses the analytic hierarchy process (AHP) to determine the weights of each dimension and then weights them to obtain a comprehensive score and risk level. This solves the problems of fragmented statistical scope, single risk assessment dimensions, and difficulty in aligning with on-site maintenance decisions in existing technologies, achieving a stable, multi-dimensional risk assessment that easily supports on-site maintenance decisions.

[0049] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0050] The above-described embodiments are merely preferred embodiments of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A multi-dimensional risk assessment method for early warning information of wind power equipment, characterized in that, include: Obtain early warning information for wind power equipment; The warning information is processed by standardized failure mode classification to obtain standardized classification labels; Based on the standardized classification labels, obtain the expert prior scores and historical case data for the corresponding failure mode categories, and perform fusion and correction processing on the expert prior scores and the historical case data to obtain the risk scores for multiple risk dimensions of the early warning information. The relative importance of each risk dimension is compared in pairs using the analytic hierarchy process (AHP) to obtain the weight of each risk dimension. The risk scores and weights of each risk dimension are weighted and summed to obtain a comprehensive score. The comprehensive score is then mapped to a preset threshold to obtain the risk level, thereby achieving multi-dimensional risk assessment.

2. The multi-dimensional risk assessment method for wind power equipment early warning information according to claim 1, characterized in that, The multiple risk dimensions include severity, maintenance difficulty, evolution risk, and economic impact.

3. The multi-dimensional risk assessment method for wind power equipment early warning information according to claim 1, characterized in that, The step of standardizing the failure mode classification of the early warning information to obtain standardized classification labels includes: Based on the fields representing the faulty components and fault types in the warning information, the warning information is mapped to the corresponding failure mode categories in the preset failure mode classification system to obtain the standardized classification labels; The failure mode classification system includes failure modes corresponding to the blades, gearboxes, generators, converters, pitch systems, yaw systems, wind measurement systems, braking systems, and control systems of wind turbines, respectively.

4. The multi-dimensional risk assessment method for wind power equipment early warning information according to claim 2, characterized in that, The process of fusing and correcting the expert prior scores with the historical case data yields risk scores for multiple risk dimensions of the early warning information, including: Based on the historical downtime records of the corresponding failure mode categories in the historical case data, the expert prior score of the severity dimension is corrected to obtain the risk score of the severity dimension; Based on the historical handling time of the corresponding failure mode category in the historical case data, the expert prior score of the maintenance difficulty dimension is corrected to obtain the risk score of the maintenance difficulty dimension. Based on the statistical probability of failure escalation of the corresponding failure mode category within a preset time window in the historical case data, the expert prior score of the evolutionary risk dimension is corrected to obtain the risk score of the evolutionary risk dimension. Obtain the power curve of the wind turbine, calculate the power loss based on the expected downtime corresponding to the power curve and the early warning information, and obtain a risk score for the economic impact dimension based on the power loss.

5. A multi-dimensional risk assessment method for wind power equipment early warning information according to claim 1, characterized in that, After mapping the comprehensive score to a preset threshold to obtain the risk level, the method further includes: The risk scores for each of the aforementioned risk dimensions are combined with a pre-built knowledge base to generate explanatory text, resulting in explanatory outputs corresponding to each of the aforementioned risk dimensions.

6. The multi-dimensional risk assessment method for wind power equipment early warning information according to claim 1, characterized in that, After using the analytic hierarchy process (AHP) to perform pairwise comparisons of the relative importance of each risk dimension to obtain the weight of each risk dimension, the method further includes: After updating the historical case data during the operation of the wind turbine, the expert prior scores and weights of each risk dimension are backtested and corrected to obtain the updated expert prior scores and weights.

7. A multi-dimensional risk assessment system for early warning information of wind power equipment, characterized in that, include: The data acquisition module is used to acquire early warning information from wind power equipment; The classification processing module is used to perform standardized failure mode classification processing on the warning information to obtain standardized classification labels; The scoring engine module is used to obtain the expert prior score and historical case data of the corresponding failure mode category according to the standardized classification label, and to perform fusion and correction processing on the expert prior score and the historical case data to obtain the risk score of multiple risk dimensions of the warning information. The weight calculation module is used to perform pairwise comparisons of the relative importance of each of the risk dimensions using the analytic hierarchy process (AHP) to obtain the weight of each of the risk dimensions. The comprehensive assessment module is used to perform a weighted summation of the risk scores and weights of each risk dimension to obtain a comprehensive score, and then map the comprehensive score to a preset threshold to obtain a risk level, thereby realizing multi-dimensional risk assessment.

8. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements a multi-dimensional risk assessment method for early warning information of wind power equipment as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 6, a multi-dimensional risk assessment method for wind power equipment early warning information.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements a multi-dimensional risk assessment method for early warning information of wind power equipment as described in any one of claims 1 to 6.

Images