Dynamic evaluation method and system for life extension of wind turbine generator based on multi-source data fusion

Abstract

The invention discloses a wind turbine generator life extension dynamic evaluation method and system based on multi-source data fusion, and belongs to the technical field of new energy. According to the method, multi-modal detection is carried out on key parts such as blades, a gearbox, a generator and a tower by collecting multi-source data such as basic parameters, historical operation data, environmental data and design files of a wind turbine generator, and residual life evaluation is carried out based on material performance, operation data and numerical simulation. And performing economic evaluation by combining cost-benefit analysis and investment payback period analysis, and finally comprehensively giving a life extension dynamic evaluation conclusion. The method solves the problems of data island, insufficient dynamic prediction capability, lack of economic analysis, low detection efficiency and the like in a traditional evaluation method, provides a scientific and comprehensive basis for the decision-making of the life extension of the wind turbine generator, and has remarkable economic benefits and engineering application values.

Description

Technical Field

[0001] The present invention belongs to the field of new energy technology, and in particular relates to a method and system for dynamically evaluating the life extension of a wind turbine generator set based on multi-source data fusion. Background Art

[0002] With the rapid growth of global wind power installations, a large number of early-operating wind turbines are nearing the end of their design lifespans (typically 20 years). Directly decommissioning and replacing these turbines is costly and wasteful, while blindly extending their lifespans can pose safety risks. According to statistics, between 2020 and 2030, over 33,000 wind turbines in China will be retired, and by 2025, over 10,000 kW of wind turbines will be nearing or reaching their design lifespans. This large number of turbines faces the decision to retire, and extending their lifespans can prevent the waste of assets caused by premature retirement. With the full marketization of wind power pricing, onshore wind power is leaving the era of fixed electricity prices and entering a market-based trading phase. Extending the operating life of onshore wind turbines to 25 years is considered a key path to improving asset returns. For example, using a typical 100 MW onshore wind farm as an example, extending the lifespan to 25 years can reduce the levelized cost of electricity (LCE) by 14% and increase the internal rate of return by 1.7 percentage points.

[0003] Currently, several standards have been issued for wind turbine life extension assessment, such as T / CSEE 0373-2023 "Technical Specifications for Onshore Wind Turbine Life Extension Assessment," T / JSREA 01-2022 "Technical Guidelines for Wind Turbine Life Extension Assessment," and T / JSREA 02-2022 "Detailed Methods for Wind Turbine Life Extension Assessment." Currently, wind turbine life extension assessment faces the following technical bottlenecks: 1) Data silo problem: Traditional methods rely on single-dimensional operating data or component inspection results, and lack systematic integrated analysis of multi-source data such as unit design parameters, environmental conditions, and historical maintenance records, resulting in one-sided evaluation results.

[0004] 2) Insufficient dynamic prediction capabilities: Existing remaining life models are mostly based on static load assumptions, without considering the dynamic cumulative effect of complex alternating loads on material fatigue damage during actual operation, resulting in large prediction errors.

[0005] 3) Lack of economic analysis: Life extension decisions must take into account both technical feasibility and economic rationality, but existing technologies lack quantitative coupled analysis of maintenance costs, power generation revenue, and investment payback period.

[0006] 4) Low detection efficiency: Traditional manual inspections and offline detection methods are time-consuming and costly, and have limited ability to identify hidden faults such as internal defects in blades and early wear of gearboxes. Summary of the Invention

[0007] In response to technical bottlenecks in existing wind turbine life extension assessments, such as data silos, insufficient dynamic prediction capabilities, lack of economic analysis, and low detection efficiency, a dynamic assessment method and system for wind turbine life extension based on multi-source data fusion is provided to achieve a comprehensive, accurate, and economical assessment of wind turbine life extension, provide a scientific basis for wind turbine life extension decisions, avoid asset waste caused by premature retirement, and ensure the safe operation of the unit.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions: A dynamic evaluation method for extending the life of a wind turbine generator system based on multi-source data fusion includes the following steps: Step 1: Multi-source data collection of wind turbines: Obtain basic parameters, historical operating data, environmental data, and design documents of the turbines; Step 2: Multimodal testing of key components of wind turbines: damage diagnosis and performance evaluation of blades, gearboxes, generators, and towers; Step 3: Remaining life assessment of key components of wind turbines: Based on material performance assessment, operation data assessment, and numerical simulation assessment results, collaboratively assess the remaining life of key components of wind turbines; Step 4, economic analysis and evaluation: Conduct cost-benefit analysis and investment payback period analysis; Step 5, comprehensive evaluation of life extension: Combining the multi-source data collection results, multi-modal detection results of key components, remaining life prediction of key components and economic analysis and evaluation, a comprehensive analysis and evaluation is conducted to give a dynamic evaluation conclusion on the life extension of the wind turbine.

[0009] A further improvement of the present invention is that the specific method of multi-source data collection of wind turbines in step 1 is as follows: Collect and analyze basic information of wind turbines, including: model, manufacturer, date of manufacture, rated power, rated wind speed, cut-in wind speed, and cut-out wind speed parameters; Collect and analyze historical operating data, including operating status data and environmental data. Use operating status data to analyze actual power curves to determine whether the unit's power generation efficiency is normal. Use operating status data to analyze the frequency and development trends of various faults to identify frequently faulty components and potential fault hazards. Collect and analyze environmental data to analyze the effects of high temperature, salt spray, and extreme wind speeds on accelerated aging of components; Collect unit design documents, clarify the unit's design life, design load standards, material performance indicators and performance parameter requirements of each component, and provide a basis for subsequent unit life extension evaluation.

[0010] A further improvement of the present invention is that the specific method of multi-modal detection of key components of the wind turbine generator set in step 2 is as follows: Blade inspection: perform appearance inspection, non-destructive testing and aerodynamic performance evaluation on blades; Gearbox inspection: vibration monitoring, seal inspection and oil inspection of the gearbox; Generator testing: Conduct insulation testing, winding core inspection and electrical performance testing on the generator; Tower inspection: Perform visual inspection, ultrasonic testing and vibration testing on the tower.

[0011] A further improvement of the present invention is that the appearance inspection of the blades is a combination of manual inspection and drone inspection.

[0012] A further improvement of the present invention is that the non-destructive testing of the blades is to detect internal defects of the blades using ultrasonic testing technology and to detect internal defects of the blades using infrared thermal imaging technology.

[0013] A further improvement of the present invention is that the aerodynamic performance evaluation is to measure the pressure distribution at different positions of the blade using a pressure sensor installed on the blade surface, compare the measured value with the design value, and evaluate the aerodynamic performance of the blade.

[0014] A further improvement of the present invention is that the vibration monitoring of the gearbox is to install vibration sensors at key positions of the gearbox, perform time domain analysis on the collected vibration signals, and determine whether the vibration is normal.

[0015] A further improvement of the present invention is that the specific method for evaluating the remaining life of key components of the wind turbine in step 3 is as follows: Material performance evaluation: Representative material samples are taken from key components such as blades, gearbox gears, and generator windings. Tensile, fatigue, and creep mechanical performance tests are conducted in a laboratory environment simulating high temperature, high humidity, and fatigue loads. A model of how material performance changes over time and load is constructed based on the test data. The residual strength and life of the material are predicted based on the actual load spectrum and duration of the components during operation. Based on operational data evaluation, reliability analysis methods are used to process historical unit operation and failure statistics. Component failure times are fitted using an exponential distribution probability model to determine model parameters and obtain reliability functions and failure probability density functions. Future component failure probabilities are predicted based on the reliability model, and the acceptable failure probability threshold is set to determine whether components require replacement or repair, providing support for optimizing maintenance strategies. Based on numerical simulation evaluation, finite element models of key components of wind turbines such as blades, gearboxes, and towers are constructed to accurately simulate the geometric shape, material properties, boundaries, and load conditions of each component. Finite element analysis software is used to solve the model and calculate the stress and strain distribution of the components under actual operating loads. The fatigue analysis module is used to calculate fatigue damage and remaining fatigue life based on the material SN curve and component stress spectrum. Multi-physics field coupling analysis is carried out to consider the impact of temperature field and flow field on component performance.

[0016] A further improvement of the present invention is that the specific method of economic analysis and evaluation in step 4 is as follows: Cost-benefit analysis and evaluation include: life extension cost calculation and economic benefit calculation. Life extension cost calculation includes equipment maintenance cost, component replacement cost and technical transformation cost; economic benefit calculation includes the increase in power generation income and the reduction in equipment replacement cost. The payback period analysis includes: calculating the net cash flow of the life extension investment, and calculating the payback period based on the discounted net cash flow; conducting a sensitivity analysis to analyze the impact of changes in life extension costs, increased power generation, and on-grid electricity prices on the payback period.

[0017] A wind turbine life extension dynamic assessment system based on multi-source data fusion, including: Wind turbine multi-source data acquisition unit, which acquires basic parameters, historical operating data, environmental data and design documents of the unit; Multi-modal detection unit for key components of wind turbines, which performs damage diagnosis and performance evaluation on blades, gearboxes, generators, and towers; The wind turbine key component remaining life assessment unit collaboratively assesses the remaining life of wind turbine key components based on material performance assessment, operation data assessment, and numerical simulation assessment results; Economic Analysis and Evaluation Unit, which conducts cost-benefit analysis and payback period analysis; The comprehensive life extension assessment unit combines the results of multi-source data collection, multi-modal detection results of key components, remaining life prediction of key components and economic analysis and assessment, and comprehensively analyzes and evaluates to give a dynamic assessment conclusion on the life extension of the wind turbine.

[0018] Compared with the prior art, the present invention has at least the following beneficial technical effects: 1) Multi-source data fusion for more comprehensive and accurate assessments: By collecting multi-source data, including basic unit parameters, historical operating data, environmental data, and design documents, and conducting a systematic fusion analysis, this approach overcomes the shortcomings of traditional methods that rely on single-dimensional data. It comprehensively considers all factors affecting wind turbine lifespan, making assessment results more accurate and reliable. For example, combining material performance indicators in design documents with actual operating environmental data allows for a more precise assessment of the impact of environmental conditions on component aging.

[0019] 2) Dynamic prediction model to improve prediction accuracy: The remaining life assessment method, based on material performance evaluation, operational data evaluation, and numerical simulation evaluation, fully considers the dynamic cumulative effect of complex alternating loads on material fatigue damage during actual operation. This constructs a remaining life model that better matches actual operating conditions, effectively reducing prediction errors and providing a more scientific basis for unit maintenance and replacement decisions. For example, in the numerical simulation evaluation, multi-physics field coupling analysis considers the impact of temperature and flow fields on component performance, making the remaining life prediction more accurate.

[0020] 3) Improved economic analysis and more rational decision-making: Through cost-benefit analysis and payback period analysis, the costs and benefits of life extension are quantified, balancing technical feasibility and economic rationality, helping decision-makers strike a balance between extending unit life and improving economic efficiency. For example, by calculating the net cash flow of life extension investments and conducting sensitivity analysis, the impact of different factors on the payback period can be clearly understood, leading to more rational life extension decisions.

[0021] 4) Advanced detection technology, improved efficiency and accuracy: The use of advanced detection methods such as a combination of manual inspection and drone inspection, ultrasonic detection, infrared thermal imaging technology, vibration sensors, etc. has improved detection efficiency and reduced labor costs. At the same time, it has enhanced the ability to identify hidden faults such as internal defects in blades and early wear of gearboxes, and can promptly detect potential problems of the unit, providing more accurate detection data for life extension assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 The present invention is a flow chart of a method for dynamically evaluating the life extension of a wind turbine generator system based on multi-source data fusion.

[0024] Figure 2 This is a structural block diagram of a wind turbine life extension dynamic assessment system based on multi-source data fusion according to the present invention. DETAILED DESCRIPTION

[0025] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0026] In the description of the present invention, it is to be understood that when used in this specification and the appended claims, the terms “include” and “comprise” indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0027] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0029] The accompanying drawings illustrate various schematic diagrams of structures according to embodiments disclosed herein. These figures are not drawn to scale; for clarity, some details are exaggerated and some details may be omitted. The shapes of the various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art may design regions / layers with different shapes, sizes, and relative positions as needed.

[0030] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0031] Example 1 like Figure 1 As shown, the present invention provides a dynamic evaluation method for extending the life of a wind turbine generator system based on multi-source data fusion, comprising: 1) Multi-source data collection of wind turbines: Collect basic information of the unit, including model, manufacturer, date of manufacture, rated power, rated wind speed, cut-in wind speed, cut-out wind speed and other parameters to provide basic data for subsequent evaluation.

[0032] Collect historical operating data, including operating status data and environmental data. Use operating status data to analyze actual power curves to determine whether the unit's power generation efficiency is normal; analyze the frequency and development trends of various faults to identify frequently faulty components and potential fault hazards.

[0033] Collect environmental data and analyze the impact of environmental factors such as high temperature, salt spray, and extreme wind speed on accelerated aging of components.

[0034] Collect unit design documents, clarify the unit's design life, design load standards, material performance indicators and performance parameter requirements of each component, and provide a design basis for life extension assessment.

[0035] 2) Multimodal detection of key components of wind turbines: Blade inspection: A combination of manual inspection and drone inspection is used for appearance inspection; ultrasonic detection technology and infrared thermal imaging technology are used for non-destructive detection of internal defects in the blades; pressure sensors installed on the blade surface are used to measure pressure distribution and compare it with the design value to evaluate aerodynamic performance.

[0036] Gearbox inspection: Install vibration sensors at key locations, perform time domain analysis on the collected vibration signals, and determine whether the vibration is normal; perform seal inspections and oil inspections to understand the sealing performance and oil status of the gearbox.

[0037] Generator inspection: Perform insulation inspection, winding core inspection and electrical performance test to ensure the electrical performance of the generator is normal.

[0038] Tower Inspection: Perform visual inspection, ultrasonic testing, and vibration testing to assess the tower's structural integrity and vibration.

[0039] 3) Remaining life assessment of key components of wind turbines: Based on material performance evaluation: For key components such as blades, gearbox gears, and generator windings, representative material samples are taken, and mechanical performance tests such as tensile, fatigue, and creep are carried out in the laboratory to simulate the service environment. A model of how material performance changes with time and load is constructed, and the residual strength and life of the material are predicted based on the actual operating load spectrum and duration of the components.

[0040] Evaluation based on operating data: Use reliability analysis methods to process the historical operation and failure statistics of the unit, use probability models such as exponential distribution to fit component failure time, determine model parameters, obtain reliability functions and failure probability density functions, predict future component failure probabilities, and provide support for maintenance strategies.

[0041] Evaluation based on numerical simulation: Construct finite element models of key components such as blades, gearboxes, and towers, simulate geometric shapes, material properties, boundaries, and load conditions, use finite element analysis software to solve the model, calculate stress and strain distribution, use fatigue analysis modules to calculate fatigue damage and remaining fatigue life, conduct multi-physics field coupling analysis, and accurately evaluate the remaining life of components.

[0042] 4) Economic analysis and evaluation: Cost-benefit analysis and evaluation: Calculate the life extension costs, including equipment maintenance costs, component replacement costs, and technical transformation costs; calculate the economic benefits, including increased power generation benefits, reduced equipment replacement costs, and other benefits.

[0043] Payback period analysis: Calculate the net cash flow of the life extension investment, calculate the payback period based on the discounted net cash flow, and conduct a sensitivity analysis to analyze the impact of factors such as life extension costs, increased power generation, and on-grid electricity prices on the payback period.

[0044] 5) Comprehensive evaluation of life extension: Combining the results of multi-source data collection, multi-modal detection results of key components, remaining life prediction of key components and economic analysis and evaluation, a comprehensive analysis and evaluation is conducted to provide a dynamic evaluation conclusion of wind turbine life extension, providing a basis for unit life extension decision-making.

[0045] The present invention solves the data island problem in traditional methods through systematic fusion analysis of multi-source data, making the evaluation results more comprehensive; adopts a remaining life model that considers the dynamic cumulative effect of complex alternating loads on material fatigue damage, thereby improving dynamic prediction capabilities and reducing prediction errors; introduces a quantitative coupling analysis of maintenance costs, power generation income, and investment payback period to make up for the lack of economic analysis; uses advanced detection technologies and means to improve detection efficiency and the ability to identify hidden faults.

[0046] Example 2 Background of the embodiment: A wind turbine with a rated power of 2 MW in a typical onshore wind farm is selected as an evaluation object. The turbine has been in operation for 18 years and is approaching the end of its design life of 20 years, so a life extension evaluation is required.

[0047] Specific implementation steps: 1) Wind turbine multi-source data collection (step 1): Step 101: Collect basic information of the unit. The model of the unit is XX-2000, the manufacturer is XX Company, the production date is May 2007, the rated power is 2MW, the rated wind speed is 12m / s, the cut-in wind speed is 3m / s, the cut-out wind speed is 25m / s, etc.

[0048] Step 102: Collect historical operating data, including operating status data (such as power, speed, and temperature) and environmental data (such as wind speed, wind direction, temperature, humidity, and salt spray concentration) for the past five years. Analyzing the actual power curve using this operating status data revealed a slight decrease in the unit's actual power generation at rated wind speed compared to the design power. Further analysis of fault records revealed a high frequency of gearbox bearing failures, indicating a potential fault hazard.

[0049] Step 103: Analyze environmental data. The region experiences prolonged high temperatures in the summer and extreme wind speeds in the winter. Salt spray concentration is high in coastal areas. These environmental factors accelerate aging of components such as blades and gearboxes.

[0050] Step 104: Collect unit design documents to clarify that the unit has a design life of 20 years, that the design load standard complies with relevant industry specifications, and that material performance indicators include the tensile strength of blade composite materials and the fatigue limit of gearbox gears. Component performance parameter requirements include the insulation grade of the generator being H.

[0051] 2) Multimodal detection of key components of wind turbines (step 2): Step 201: Blade Inspection. A drone inspection conducted a preliminary inspection of the blade's overall appearance, revealing minor coating peeling and cracks on the blade surface. Manual inspections were then conducted to conduct detailed examinations of suspicious areas. Ultrasonic testing technology was used to inspect the interior of the blade, revealing a minor delamination defect within one blade. Infrared thermal imaging technology was used to further determine the location and extent of the internal defects. Pressure sensors mounted on the blade surface measured pressure distribution at various locations and compared it with the design value to assess the blade's aerodynamic performance, revealing a slight decrease in performance.

[0052] Step 202: Gearbox Inspection. Vibration sensors are installed at key locations on the gearbox, such as the input and output shafts. Vibration signals are collected and analyzed in the time domain. Abnormal impact frequencies are detected in the vibration signals, indicating possible gear wear or bearing failure. A seal inspection reveals slight oil leakage from the seal at the gearbox input end. An oil inspection, testing the oil's viscosity, impurity content, and metal content, reveals elevated iron content, indicating gear or bearing wear.

[0053] Step 203: Generator testing. An insulation test is performed, measuring the insulation resistance and absorption ratio of the windings. The results meet standard requirements. The winding core is inspected, revealing no obvious deformation, corrosion, or looseness. Electrical performance tests, including no-load and load tests, are performed, revealing normal parameters such as the generator's voltage, current, and power factor.

[0054] Step 204: Tower Inspection. A visual inspection revealed some deterioration of the tower's anti-corrosion coating, but no noticeable loosening of the tower's connecting bolts. Ultrasonic testing of the tower's welds revealed no cracks or other defects. A vibration test measured the tower's vibration frequency and amplitude at different wind speeds, confirming normal vibration.

[0055] 3) Remaining life assessment of key components of wind turbines (step 3): Step 301: Material Performance Evaluation. For the blade's composite materials, representative samples are taken and subjected to laboratory tests simulating high temperature, high humidity, and fatigue loading. Tensile and fatigue performance tests are conducted to construct the material's S-N curve and fatigue life model. The blade's residual strength and life are predicted based on the load spectrum and operating time during actual operation. For gearbox gears, gear material samples are taken and subjected to fatigue and creep testing. A model of material property variation over time is constructed to predict the gear's remaining life.

[0056] Step 302: Evaluate based on operating data. Reliability analysis methods are used to process historical unit operation and failure statistics. Assuming component failure times follow an exponential distribution, the maximum likelihood estimation method is used to fit the failure times of the gearbox bearings. Model parameters are determined to obtain a reliability function and a failure probability density function. Based on a set acceptable failure probability threshold (e.g., 5%), the future failure probability of the gearbox bearings is predicted to determine whether replacement or repair is necessary.

[0057] Step 303: Evaluation based on numerical simulation. Construct a finite element model of the blade, consider aerodynamic loads, centrifugal loads and gravity loads, and use finite element analysis software to calculate the stress and strain distribution of the blade under actual operating loads. With the help of the fatigue analysis module, calculate the fatigue damage and remaining fatigue life of the blade based on the SN curve of the material and the stress spectrum of the blade. Construct a finite element model for the gearbox, consider loads such as meshing force and bearing support force, and perform stress analysis and fatigue life calculation. At the same time, construct a finite element model for the tower, consider wind loads and seismic loads, calculate the stress and deformation of the tower, and evaluate the remaining life of the tower. During the analysis process, carry out multi-physical field coupling analysis, such as considering the influence of the blade aerodynamic heating temperature field on material properties, and the influence of the gearbox lubricating oil flow field on gear lubrication and heat dissipation.

[0058] 4) Economic Analysis and Evaluation (Step 4): Step 401: Cost-Benefit Analysis and Evaluation. Life extension cost calculation: Equipment maintenance costs, including blade coating repair, gearbox seal replacement, and oil replacement, are estimated at 500,000 yuan. Component replacement costs, such as replacing gearbox bearings, are estimated at 300,000 yuan. Technical modification costs, such as optimizing blade aerodynamic performance, are estimated at 800,000 yuan, for a total life extension cost of 1.6 million yuan. Economic benefit calculation: Based on the life extension assessment, the unit is expected to increase annual power generation by 500,000 kWh over its five-year extended service life. Based on a grid-connected electricity price of 0.5 yuan / kWh, this increased power generation yields an annual benefit of 250,000 yuan. Equipment replacement costs are reduced. Directly decommissioning and replacing the unit would have cost 20 million yuan, which can be avoided with the life extension. Other indirect benefits, such as reduced downtime, are estimated at 100,000 yuan per year. The total economic benefit is (25 + 10) × 5 = 1.75 million yuan, while equipment replacement costs of 20 million yuan are avoided.

[0059] Step 402: Payback Period Analysis. Calculate the net cash flow of the life extension investment. The initial investment is 1.6 million yuan, and the annual net cash inflow is 350,000 yuan (25 + 10). Assuming an 8% discount rate, calculate the present value of the net cash flow. Using the formula, the payback period is approximately 5.5 years. A sensitivity analysis is performed to examine the impact of factors such as a 10% increase in life extension costs, a 10% decrease in increased power generation, and a 5% reduction in the on-grid electricity price on the payback period. The results show that the payback period is sensitive to both the life extension cost and the increased power generation.

[0060] 5) Comprehensive evaluation of life extension (step 5): Combined with the results of multi-source data collection, the unit exhibited issues such as gearbox bearing wear and reduced blade aerodynamic performance, but the tower and generator were in good condition. Multimodal inspection of key components revealed minor defects within the blades and oil leakage from the gearbox seals. Remaining life predictions for key components indicated approximately three years for the gearbox bearings and five years for the blades. Economic analysis and assessment indicated a payback period of approximately 5.5 years for the extended lifespan, with significant economic benefits and the advantage of avoiding equipment replacement costs. Comprehensive analysis concluded that the wind turbine's lifespan extension was feasible, and recommended that the gearbox bearings be replaced, the blades be repaired and aerodynamic performance optimized, and regular inspection and maintenance be performed during the extended lifespan period to ensure safe and reliable operation and maximize economic benefits.

[0061] Example 3 like Figure 2 As shown, the present invention provides a wind turbine life extension dynamic assessment system based on multi-source data fusion, comprising: Wind turbine multi-source data acquisition unit, which acquires basic parameters, historical operating data, environmental data and design documents of the unit; Multi-modal detection unit for key components of wind turbines, which performs damage diagnosis and performance evaluation on blades, gearboxes, generators, and towers; The wind turbine key component remaining life assessment unit collaboratively assesses the remaining life of wind turbine key components based on material performance assessment, operation data assessment, and numerical simulation assessment results; Economic Analysis and Evaluation Unit, which conducts cost-benefit analysis and payback period analysis; The comprehensive life extension assessment unit combines the results of multi-source data collection, multi-modal detection results of key components, remaining life prediction of key components and economic analysis and assessment, and comprehensively analyzes and evaluates to give a dynamic assessment conclusion on the life extension of the wind turbine.

[0062] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from all points of view, the embodiments should be regarded as illustrative and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and range of equivalents of the claims are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim to which they relate.

[0063] In addition, it should be understood that although this specification describes the embodiments, not every embodiment contains only one independent technical solution. This description is for clarity only. Those skilled in the art should consider the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for the purpose of illustrating the technical concept of the present invention and cannot be used to limit the scope of protection of the present invention. Any changes made based on the technical solution in accordance with the technical concept proposed by the present invention fall within the scope of protection of the claims of the present invention.

Claims

1. A dynamic evaluation method for wind turbine life extension based on multi-source data fusion, characterized in that: The steps include: Step 1: Multi-source data collection of wind turbines: Obtain basic parameters, historical operating data, environmental data, and design documents of the turbines; Step 2: Multimodal testing of key components of wind turbines: damage diagnosis and performance evaluation of blades, gearboxes, generators, and towers; Step 3: Remaining life assessment of key components of wind turbines: Based on material performance assessment, operation data assessment, and numerical simulation assessment results, collaboratively assess the remaining life of key components of wind turbines; Step 4, economic analysis and evaluation: Conduct cost-benefit analysis and investment payback period analysis; Step 5, comprehensive evaluation of life extension: Combining the multi-source data collection results, multi-modal detection results of key components, remaining life prediction of key components and economic analysis and evaluation, a comprehensive analysis and evaluation is conducted to give a dynamic evaluation conclusion on the life extension of the wind turbine.

2. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 1, characterized in that: Step 1 The specific method of multi-source data collection of wind turbines is as follows: Collect and analyze basic information of wind turbines, including: model, manufacturer, date of manufacture, rated power, rated wind speed, cut-in wind speed, and cut-out wind speed parameters; Collect and analyze historical operating data, including operating status data and environmental data. Use operating status data to analyze actual power curves to determine whether the unit's power generation efficiency is normal. Use operating status data to analyze the frequency and development trends of various faults to identify frequently faulty components and potential fault hazards. Collect and analyze environmental data to analyze the effects of high temperature, salt spray, and extreme wind speeds on accelerated aging of components; Collect unit design documents, clarify the unit's design life, design load standards, material performance indicators and performance parameter requirements of each component, and provide a basis for subsequent unit life extension evaluation.

3. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 1, characterized in that: Step 2 The specific method of multi-modal detection of key components of wind turbines is as follows: Blade inspection: perform appearance inspection, non-destructive testing and aerodynamic performance evaluation on blades; Gearbox inspection: vibration monitoring, seal inspection and oil inspection of the gearbox; Generator testing: Conduct insulation testing, winding core inspection and electrical performance testing on the generator; Tower inspection: Perform visual inspection, ultrasonic testing and vibration testing on the tower.

4. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 3 is characterized in that: The appearance inspection of the blades is a combination of manual inspection and drone inspection.

5. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 3 is characterized in that: The non-destructive testing of the blades is to detect the internal defects of the blades using ultrasonic testing technology and to detect the internal defects of the blades using infrared thermal imaging technology.

6. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 3, characterized in that: The aerodynamic performance evaluation is to use pressure sensors installed on the blade surface to measure the pressure distribution at different positions of the blade, compare the measured values ​​with the design values, and evaluate the aerodynamic performance of the blade.

7. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 3 is characterized in that: The vibration monitoring of the gearbox is to install vibration sensors at key positions of the gearbox, perform time domain analysis on the collected vibration signals, and determine whether the vibration is normal.

8. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 1, characterized in that: Step 3: The specific method for evaluating the remaining life of key components of wind turbines is as follows: Based on material performance evaluation: For key components such as blades, gearbox gears, and generator windings, representative material samples are taken and subjected to tensile, fatigue, and creep mechanical performance tests in a laboratory environment simulating high temperature, high humidity, and fatigue loads; Based on the test data, a model of material performance changes over time and load is constructed. Combined with the actual operating load spectrum and duration of the component, the residual strength and life of the material are predicted. Based on operational data evaluation, reliability analysis methods are used to process historical unit operation and failure statistics. Component failure times are fitted using an exponential distribution probability model to determine model parameters and obtain reliability functions and failure probability density functions. Future component failure probabilities are predicted based on the reliability model, and the acceptable failure probability threshold is set to determine whether components require replacement or repair, providing support for optimizing maintenance strategies. Based on numerical simulation and evaluation, finite element models of key components of wind turbines, such as blades, gearboxes, and towers, are constructed to accurately simulate the geometry, material properties, boundary conditions, and load conditions of each component. Finite element analysis software is used to solve the model and calculate the stress and strain distribution of the components under actual operating loads. The fatigue analysis module is used to calculate the fatigue damage and remaining fatigue life based on the material SN curve and the component stress spectrum; multi-physical field coupling analysis is carried out to consider the impact of temperature field and flow field on component performance.

9. The method for dynamic evaluation of wind turbine life extension based on multi-source data fusion according to claim 1, characterized in that: The specific methods for economic analysis and evaluation in step 4 are as follows: Cost-benefit analysis and evaluation include: life extension cost calculation and economic benefit calculation. Life extension cost calculation includes equipment maintenance cost, component replacement cost and technical transformation cost; economic benefit calculation includes the increase in power generation income and the reduction in equipment replacement cost. The payback period analysis includes: calculating the net cash flow of the life extension investment, and calculating the payback period based on the discounted net cash flow; conducting a sensitivity analysis to analyze the impact of changes in life extension costs, increased power generation, and on-grid electricity prices on the payback period.

10. A wind turbine life extension dynamic assessment system based on multi-source data fusion, characterized in that: include: Wind turbine multi-source data acquisition unit, which acquires basic parameters, historical operating data, environmental data and design documents of the unit; Multi-modal detection unit for key components of wind turbines, which performs damage diagnosis and performance evaluation on blades, gearboxes, generators, and towers; The wind turbine key component remaining life assessment unit collaboratively assesses the remaining life of wind turbine key components based on material performance assessment, operation data assessment, and numerical simulation assessment results; Economic Analysis and Evaluation Unit, which conducts cost-benefit analysis and payback period analysis; The comprehensive life extension assessment unit combines the results of multi-source data collection, multi-modal detection results of key components, remaining life prediction of key components and economic analysis and assessment, and comprehensively analyzes and evaluates to give a dynamic assessment conclusion on the life extension of the wind turbine.

Images