Method and system for predicting service life of gearbox of wind turbine generator
Through dynamic acquisition and weighting, a gearbox service life prediction model is constructed, which solves the problem of the accuracy of gearbox life prediction of wind turbine units, achieves more accurate health status evaluation and prediction, and improves wind turbine units reliability and economicality.
Patent Information
- Application Number
- CN202411373421.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2025-02-21
AI Technical Summary
The gearbox of the wind turbine unit is prone to wear, fatigue, corrosion and other problems in complex natural environments, resulting in a shortened service life and an increase in maintenance costs. The existing maintenance methods have limitations of regular maintenance and fault repair, and it is impossible to accurately predict the failure of the gearbox.
A method for predicting the life of the gearbox of the wind turbine is adopted to dynamically obtain the direct evaluation factors and indirect evaluation factors of the gearbox, and different weights are given according to the importance of the impact of each evaluation factor on the life of the gearbox, and a gearbox service life prediction model is constructed. Compute comprehensive scoring information to predict the remaining service life of the gearbox.
This method can more accurately evaluate the health status of the gearbox, improve prediction accuracy, reduce unnecessary maintenance activities, avoid downtime losses caused by failures, and improve the reliability and economicality of wind turbines.
Smart Images
Figure CN119493935A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of wind power generation, and in particular to a method and system for predicting the life of a gearbox of a wind turbine. Background Art
[0002] As an important part of the renewable energy field, wind turbines have been widely used and developed around the world. With the rapid expansion of the wind power industry, the reliability and economy of wind turbines have become one of the key factors in the operation of wind farms. As one of the core components of wind turbines, gearboxes are responsible for converting the rotational kinetic energy generated by the blades into a speed suitable for the generator. Therefore, the performance of the gearbox directly affects the stable operation and overall efficiency of the wind turbine.
[0003] However, since wind turbines usually work in complex and changeable natural environments, such as high wind speed, low temperature, high temperature, humidity changes, and salt spray corrosion, these environmental factors will have an adverse effect on the gearbox, causing various forms of wear, fatigue, corrosion, etc. These problems will not only affect the normal operation of the gearbox, but also shorten its service life, increase the cost of maintenance and replacement, and thus affect the operating efficiency and economic benefits of the entire wind turbine.
[0004] Traditional gearbox maintenance methods often adopt regular maintenance or post-failure repair. Although this method is simple and direct, it has certain limitations. Regular maintenance may lead to excessive maintenance and increase unnecessary costs; while post-failure repair may cause equipment downtime for a long time, affecting power generation, and even causing greater economic losses and safety hazards due to failure to detect faults in time.
[0005] In order to solve these problems, the maintenance of modern wind turbines has gradually turned to the condition-based maintenance (CBM) mode. The core idea of this mode is to use the data collected by sensors to evaluate the health of the equipment through real-time monitoring of the key components of the wind turbine, so as to predict potential failures and take maintenance measures in advance. This method can not only reduce unnecessary maintenance activities, but also intervene in time before failures occur to avoid major accidents, thereby improving the reliability and economy of wind turbines; however, this mode cannot accurately predict the operation of the gearbox, which may cause safety hazards in the operation of wind turbines. Summary of the invention
[0006] In order to overcome the deficiencies in the background technology, the present invention proposes a method for accurately predicting the service life of a wind turbine gearbox.
[0007] In order to achieve the above-mentioned invention object, the present invention adopts the following technical scheme:
[0008] A method for predicting the life of a wind turbine gearbox, comprising the following specific steps:
[0009] Dynamically obtain direct and indirect evaluation factors of gearbox;
[0010] Different weights are assigned to each evaluation factor according to its importance to the gearbox life;
[0011] Based on each evaluation factor and its corresponding weight, a gearbox service life prediction model is constructed;
[0012] The comprehensive scoring information is calculated based on the gearbox service life model to predict the remaining service life of the gearbox.
[0013] Preferably, the direct evaluation factors include mechanical wear factors, lubrication condition factors and bearing condition factors;
[0014] The indirect evaluation factors include environmental condition factors, operating condition factors and maintenance factors.
[0015] Preferably, the mechanical wear factor is evaluated by checking the wear degree of the gear surface, and the specific evaluation formula is:
[0016] I 机械 =100-(wear percentage*100);
[0017] The wear percentage refers to the degree of wear of the gear relative to its original state.
[0018] Preferably, the lubrication condition factor is evaluated based on the quality of the oil product, and the specific evaluation formula is:
[0019] I 润滑 =100-(|VV opt |*10)-(C*5)-(P*5);
[0020] Where V is the actual viscosity of the lubricating oil, V opt is the ideal viscosity value of the lubricating oil, C is the proportion of excess water content, and P is the particle contamination level.
[0021] Preferably, the bearing condition factor is evaluated by horizontal vibration and temperature of the bearing, and the specific evaluation formula is:
[0022] I 轴承 =100-(V rms -V threshold )*10-(T 轴承 -T 轴承opt ) 2 ;
[0023] Among them, Vrms is the effective value of the bearing vibration, V threshold is the vibration threshold, T 轴承 is the bearing temperature, T 轴承opt is the ideal operating temperature of the bearing.
[0024] Preferably, the environmental condition factors are evaluated by temperature, humidity and salt spray, and the specific evaluation formula is:
[0025] I 环境 =100-|T 环境 -T 环境opt |*5-|HH opt |*5-S*10;
[0026] Among them, T 环境 is the ambient temperature, T 环境opt is the optimal operating temperature of the gearbox, H is the ambient humidity, H opt is the optimal working humidity of the gearbox, and S is the salt spray pollution level.
[0027] Preferably, the operating condition factor is evaluated based on load change and start-up times, and the specific evaluation formula is:
[0028] I 运行 =100-L*5-F*5;
[0029] Wherein, L is the load variation index of the wind turbine generator set, and F is the starting frequency of the wind turbine generator set.
[0030] Preferably, the maintenance factor is evaluated based on the degree of compliance with the maintenance plan and the maintenance quality, and the specific evaluation formula is:
[0031] I 维护 =100-M*10-Q*10;
[0032] Among them, M is the number of days of maintenance delay, and Q is the maintenance quality score.
[0033] Preferably, the weight of the mechanical wear factor is 0.3, the weights of the lubrication condition factor and the bearing condition factor are 0.2 respectively, and the weights of the environmental condition factor, the operating condition factor and the maintenance factor are 0.1 respectively.
[0034] A wind turbine gearbox life prediction system, comprising:
[0035] A sensor detection module is used to detect the gear status, lubricating oil status and bearing status of the gearbox;
[0036] A data acquisition module is used to obtain environmental data, operating condition data and maintenance data of wind turbines;
[0037] An information processing module is used to receive data information from the sensor detection module and the data acquisition module, and process the data information according to the gearbox service life model to obtain scoring information;
[0038] The scoring judgment module is used to judge the usage of the gearbox according to the scoring information and predict the remaining service life of the gearbox.
[0039] Due to the adoption of the above technical solution, the present invention has at least the following beneficial effects:
[0040] The present invention discloses a method and system for predicting the life of a wind turbine gearbox, which can effectively reduce the energy consumption of implementing the method by dynamically acquiring various evaluation factors;
[0041] In addition, the combination of direct and indirect evaluation factors can more comprehensively evaluate the health status of the gearbox, thereby improving the accuracy of the prediction; and by assigning different weights to each evaluation factor according to its importance in affecting the life of the gearbox, the model can more objectively reflect the actual situation;
[0042] In addition, the environmental condition factor evaluation formula can meet the evaluation of wind turbines in different environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 The present invention is a schematic flow chart of a method. DETAILED DESCRIPTION
[0044] The technical solution of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention:
[0045] Embodiment 1 is:
[0046] Combined with Figure 1 The wind turbine gearbox life prediction method comprises the following specific steps:
[0047] Dynamically obtain direct and indirect evaluation factors of gearbox;
[0048] The dynamic acquisition process is as follows: when the predicted gearbox life is in a good state, interval acquisition can be adopted, but when the predicted gearbox life is in a poor state, continuous acquisition is required to ensure the timely and accurate prediction of the gearbox life;
[0049] Different weights are assigned to each evaluation factor according to its importance to the gearbox life;
[0050] Based on each evaluation factor and its corresponding weight, a gearbox service life prediction model is constructed;
[0051] After obtaining the comprehensive scoring information based on the gearbox service life model, the remaining service life of the gearbox is predicted.
[0052] Embodiment 2 is:
[0053] Based on Example 1, the evaluation factors are further limited, that is, the evaluation factors include direct evaluation factors and indirect evaluation factors, wherein the direct evaluation factors include mechanical wear factors, lubrication condition factors and bearing condition factors;
[0054] Indirect evaluation factors include environmental conditions, operating conditions and maintenance factors.
[0055] In particular, the mechanical wear factor is evaluated by checking the wear degree of the gear surface, and the specific evaluation formula is:
[0056] I 机械 =100-(wear percentage*100);
[0057] The wear percentage refers to the degree of wear of the gear relative to its original state; for example, if 10% of the surface of a gear is slightly worn, the wear percentage is 0.1 and the mechanical wear score is 90 points;
[0058] Alternatively, the percentage of gear wear can be determined using a non-contact sensor such as an ultrasonic probe or a laser rangefinder to measure the wear on the gear surface.
[0059] The lubrication condition factor is evaluated based on the quality of the oil, and the specific evaluation formula is:
[0060] I 润滑 =100-(|VV oot |*10)-(C*5)-(P*5);
[0061] Where V is the actual viscosity of the lubricating oil, V opt is the ideal viscosity value of the lubricating oil, C is the percentage of excess water content, and P is the particle contamination level;
[0062] In addition, oil quality sensors can be used to monitor the viscosity, moisture content and particle contamination level parameters of the lubricating oil. It should be noted that the proportion of moisture content exceeding the standard refers to the proportion of moisture content in the lubricating oil to the total lubricating oil, which exceeds the threshold value of moisture content in the lubricating oil.
[0063] The bearing condition factor is evaluated by the horizontal vibration and temperature of the bearing. The specific evaluation formula is:
[0064] I 轴承 =100-(V rms -V threshold )*10-(T轴承 -T 轴承opt ) 2 ;
[0065] Among them, V rms is the effective value of the bearing vibration, V threshold is the vibration threshold, T 轴承 is the bearing temperature, T 轴承opt is the ideal operating temperature of the bearing;
[0066] In addition, the vibration data of the bearing, that is, the effective value of the bearing vibration, is collected by a vibration sensor installed on the bearing to monitor the vibration level of the bearing, and the operating temperature of the bearing is monitored by a temperature sensor installed near the bearing.
[0067] The environmental condition factors are evaluated by temperature, humidity and salt spray, and the specific evaluation formula is:
[0068] I 环境 =100-|T 环境 -T 环境opt |*5-|HH opt |*5-S*10;
[0069] Among them, T 环境 is the ambient temperature, T 环境opt is the optimal operating temperature of the gearbox, H is the ambient humidity, H opt is the optimal working humidity of the gearbox, and S is the salt spray pollution level;
[0070] The ambient temperature and humidity are monitored by the temperature sensor and humidity sensor installed on the outer wall of the gearbox respectively, while the salt spray pollution level is monitored by the salinity sensor installed on the outer wall of the gearbox, which is generally enabled when the wind turbine is installed in coastal areas.
[0071] The operating condition factors are evaluated based on load changes and the number of starts. The specific evaluation formula is:
[0072] I 运行 =100-L*5-F*5;
[0073] Among them, L is the load change index of the wind turbine, and 0 means stable load, and the larger the value, the more drastic the load change; F is the starting frequency of the wind turbine, and 0 means rarely starting, and the larger the value, the more frequent starting; these two parameters can be obtained from the operating data of the wind turbine.
[0074] The maintenance factor is evaluated based on the degree of compliance with the maintenance plan and the quality of maintenance. The specific evaluation formula is:
[0075] I 维护 =100-M*10-Q*10;
[0076] Among them, M is the number of days of maintenance delay, and 0 means on-time maintenance, and the larger the value, the longer the delay; Q is the maintenance quality score, and 0 means the highest quality, and the larger the value, the worse the quality. These two parameters can also be obtained from the operating data of the wind turbine.
[0077] As an example, an embodiment of weight distribution of evaluation factors is given, that is, the weight of the mechanical wear factor is 0.3, the weights of the lubrication condition factor and the bearing condition factor are 0.2 respectively, and the weights of the environmental condition factor, the operating condition factor and the maintenance factor are 0.1 respectively.
[0078] In addition, the life prediction model of the gearbox is I 综合 =W1*I 机械 +W2*I 润滑 +W3*I 轴承 +W4*I 环境 +W5*I 运行 +W6*I 维护 , where W1, W2, W3, W4, W5 and W6 are the weights corresponding to each evaluation factor, and the sum of all weights is 1;
[0079] Through the calculation of the prediction model, the prediction score representing the remaining service life of the gearbox can be obtained, and then different levels can be divided according to the prediction score, such as:
[0080] Total score above 90: Excellent, the gearbox has a long remaining life and no special maintenance is required;
[0081] 70-89 points: Good, the remaining life of the gearbox is relatively long, and regular inspection is recommended;
[0082] 50-69 points: Generally, the remaining life of the gearbox is short and needs attention and enhanced maintenance;
[0083] 30-49 points: poor, the remaining life of the gearbox is short, and detailed inspection and necessary repairs are required immediately;
[0084] 0-29 points: Severe damage, must be shut down for repair or replacement;
[0085] In the excellent and good stages, the evaluation factors can be obtained at intervals, while in the remaining stages, the evaluation factors need to be obtained continuously.
[0086] This method covers a variety of factors that affect the life of the gearbox, and comprehensively evaluates the health of the gearbox from multiple dimensions such as mechanical wear, lubrication status, and operating conditions. Through multi-angle evaluation, it can more accurately reflect the actual status of the gearbox and avoid the deviation caused by a single indicator.
[0087] Moreover, by assigning corresponding weights to different evaluation factors, this method can scientifically and reasonably reflect the influence of various factors on the life of the gearbox. The setting of weights is based on a large amount of experimental data and accumulated experience, which makes the prediction results closer to the actual situation and improves the scientificity and reliability of the prediction.
[0088] In addition, this method allows the weights and evaluation criteria to be adjusted according to actual conditions, so that it can adapt to different operating environments and conditions. For example, in certain specific environments, environmental factors may have a greater impact on the gearbox. At this time, the weight of environmental factors can be appropriately increased to make the prediction model more flexible and practical;
[0089] The specific adjustment formula of weight is:
[0090]
[0091] where ω i is the current weight, α is the learning rate, which controls the step size of each update, is the loss function with respect to weight ω i The partial derivative of .
[0092] In addition, by building a service life prediction model, operation and maintenance personnel can make a quick assessment based on real-time monitoring data, so as to take timely measures to extend the service life of the gearbox. At the same time, this method can also help formulate a more reasonable maintenance plan and reduce unnecessary maintenance costs.
[0093] Based on the comprehensive scoring information, the remaining service life of the gearbox can be predicted as needed, and potential failure risks can be warned in advance. This allows preventive maintenance to be performed before problems occur, avoiding downtime losses caused by sudden failures and improving the availability and economic benefits of wind turbines.
[0094] In particular, this method usually combines big data analysis technology to use historical data and real-time monitoring data for prediction. Data-driven methods can continuously optimize the prediction model, and the prediction accuracy will continue to improve as the amount of data grows and the algorithm is iterated.
[0095] On the other hand, by accurately predicting the remaining service life of the gearbox, precise maintenance decisions can be made to avoid over-maintenance or under-maintenance, thereby effectively reducing maintenance costs and extending the overall service life of the gearbox.
[0096] Predicting potential gearbox problems in advance helps to take timely measures to prevent safety accidents caused by gearbox failures and ensure the safe operation of wind turbines and the entire wind farm.
[0097] A wind turbine gearbox life prediction system, comprising:
[0098] Sensor detection module, used to detect the gear status, lubricating oil status, bearing status and environmental data of the gearbox;
[0099] A data acquisition module is used to obtain the operating condition data and maintenance data of the wind turbine;
[0100] An information processing module is used to receive data information from the sensor detection module and the data acquisition module, and process the data information according to the gearbox service life model to obtain scoring information;
[0101] A scoring judgment module is used to judge the usage of the gearbox based on the scoring information and predict the remaining service life of the gearbox;
[0102] In addition, the system can also have a dynamic adjustment module, which can adjust the scoring criteria and weights in a timely manner as time and experience accumulate to reflect the latest maintenance needs and technological advances.
[0103] The parts of the present invention that are not described in detail are prior art. It is obvious to those skilled in the art that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention; therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the appended claims rather than the above description. Therefore, it is intended to include all changes within the meaning and scope of the equivalent elements of the claims in the present invention, and any figure marks in the claims should not be regarded as limiting the claims involved.
Claims
1. A method for predicting the life of a wind turbine gearbox, characterized by: include Dynamically obtain direct and indirect evaluation factors of gearbox; Different weights are assigned to each evaluation factor according to its importance to the gearbox life; Based on each evaluation factor and its corresponding weight, a gearbox service life prediction model is constructed; The comprehensive scoring information is calculated based on the gearbox service life model to predict the remaining service life of the gearbox.
2. The method for predicting the life of a wind turbine gearbox according to claim 1, wherein: The direct evaluation factors include mechanical wear factors, lubrication condition factors and bearing condition factors; The indirect evaluation factors include environmental condition factors, operating condition factors and maintenance factors.
3. The method for predicting the life of a wind turbine gearbox according to claim 2, characterized in that: The mechanical wear factor is evaluated by checking the wear degree of the gear surface. The specific evaluation formula is: I 机械 =100-(wear percentage*100); The wear percentage refers to the degree of wear of the gear relative to its original state.
4. The method for predicting the life of a wind turbine gearbox according to claim 2, wherein: The lubrication condition factor is evaluated based on the quality of the oil, and the specific evaluation formula is: I 润滑 =100-(|V-V opt |*10)-(C*5)-(P*5); Where V is the actual viscosity of the lubricating oil, V opt is the ideal viscosity value of the lubricating oil, C is the proportion of excess water content, and P is the particle contamination level.
5. The method for predicting the life of a wind turbine gearbox according to claim 2, wherein: The bearing condition factor is evaluated by the horizontal vibration and temperature of the bearing. The specific evaluation formula is: I 轴承 =100-(V rms -V threshold )*10-(T 轴承 -T 轴承opt ) 2 ; Among them, V rms is the effective value of the bearing vibration, V threshold is the vibration threshold, T 轴承 is the bearing temperature, T 轴承opt is the ideal operating temperature of the bearing.
6. The method for predicting the life of a wind turbine gearbox according to claim 2, wherein: The environmental condition factors are evaluated by temperature, humidity and salt spray, and the specific evaluation formula is: I 环境 =100-|T 环境 -T 环境opt |*5-|H-H opt |*5-S*10; Among them, T 环境 is the ambient temperature, T 环境opt is the optimal operating temperature of the gearbox, H is the ambient humidity, H opt is the optimal working humidity of the gearbox, and S is the salt spray pollution level.
7. The method for predicting the life of a wind turbine gearbox according to claim 2, wherein: The operating condition factors are evaluated based on load changes and the number of starts. The specific evaluation formula is: I 运行 =100-L*5-F*5; Wherein, L is the load variation index of the wind turbine generator set, and F is the starting frequency of the wind turbine generator set.
8. The method for predicting the life of a wind turbine gearbox according to claim 2, wherein: The maintenance factor is evaluated based on the degree of compliance with the maintenance plan and the quality of maintenance. The specific evaluation formula is: I 维护 =100-M*10-Q*10; Among them, M is the number of days of maintenance delay, and Q is the maintenance quality score.
9. The method for predicting the life of a wind turbine gearbox according to claim 2, characterized in that: The weight of the mechanical wear factor is 0.3, the weights of the lubrication condition factor and the bearing condition factor are 0.2 respectively, and the weights of the environmental condition factor, the operating condition factor and the maintenance factor are 0.1 respectively.
10. A wind turbine gearbox life prediction system, comprising: A sensor detection module is used to detect the gear status, lubricating oil status and bearing status of the gearbox; A data acquisition module is used to obtain environmental data, operating condition data and maintenance data of wind turbines; An information processing module is used to receive data information from the sensor detection module and the data acquisition module, and process the data information according to the gearbox service life model to obtain scoring information; The scoring judgment module is used to judge the usage of the gearbox according to the scoring information and predict the remaining service life of the gearbox.