To consider the failure correlation among key subsystems, based on the reliability allocation method of the series system, a wind turbine reliability allocation calculation method based on the vine copula correlation model is proposed. The reliability modeling method of the series system is adopted to model the reliability of each subsystem, combined with the copula function to model the correlation between the variables, and then, the multidimensional variable problem is converted into the two-dimensional variable problem through the vine copula function. The reliability calculation model of the copula function model, under the influence of factors such as the complexity, importance, and failure hazard of each subsystem, allocates the reliability of the key component systems of the wind turbine generator set. Finally, through three allocation methods based on the independent, multivariate copula function and vine copula function and other distribution methods, the calculation and analysis of the wind turbine generator set are performed. The results show that the allocated control system has the lowest reliability, and the tower has the highest reliability; compared with the assumption of the independent allocation method, the allocation result of this paper's method is lower; compared with the allocation method of the multidimensional copula function, the allocated failure rate is increased by more than 20%. This paper verifies that the proposed method is not only effective and reasonable but also more consistent with the actual situation.
To address traditional methods’ limitations in neglecting the interaction between random shock loads and progressive degradation, as well as failure correlations, this study proposes a dynamic reliability framework integrating Gamma processes, homogeneous Poisson processes (HPP), and mixed Copula functions. The framework develops a wind turbine gearbox reliability model under shock–degradation coupling while quantifying failure correlations. Gamma processes characterize continuous degradation, with parameters estimated from P-S-N curves. Based on stress–strength interference theory, random shocks within damage thresholds are integrated to form a coupled reliability model. A Gumbel–Clayton–Frank mixed Copula with a multi-layer nested algorithm quantifies failure correlations, with correlation parameters estimated via the RSS principle and genetic algorithms. Validation using a 2 MW gearbox’s planetary gear-stage system covers four scenarios: natural degradation, shock–degradation coupling, and both scenarios with failure correlations. The results show that compared to independent assumptions, the model accelerates reliability decline, increasing failure rates by >37%. Relative to natural degradation-only models, failure rates rise by >60%, validating the model’s effectiveness and alignment with real-world operational conditions.
Given the current reliability allocation problem of wind turbine generator systems, based on the reliability allocation method of series systems, a reliability allocation model based on an improved fuzzy analytic hierarchy process (FAHP) is proposed. A three-scale standard is adopted to comprehensively consider six influencing factors, such as technical level, working environment and importance, by determining the comprehensive allocation weight combined with an improved FAHP and entropy weight method. In this way, the reliability allocation calculation model for a wind turbine generator system is developed for the reliability allocation of the wind turbine generator system. Using the method developed in this study and other methods for the reliability allocation of a wind turbine generator system as examples, the allocation results are compared and analyzed. The results show that this method not only is effective but also obtains lower allocation results than those of other studies, which verifies the rationality of the present method.
To address the complex operating conditions and challenging dynamic characteristics of bearings in the main shaft transmission system of wind turbines, this study investigates a specific wind turbine model. By comprehensively considering factors such as main shaft structure, cumulative damage, and stochastic wind loads, we adopt a modular analysis framework integrating the wind field, aerodynamics, the structural response, and fatigue life prediction to establish a method for predicting the fatigue life of main shaft bearings under stochastic wind conditions. To verify this method, the fixed-end main shaft bearing of a 4.5 MW wind turbine was selected as a case study. The research results show the following: (1) Increases in both average wind speed and turbulence intensity significantly shorten the fatigue life of the bearing. (2) Higher turbulence intensity amplifies the dispersion of the speed and load of rolling elements, thereby increasing the probability of extreme operating conditions and exerting an adverse impact on fatigue life. (3) The average wind speed has a significant influence on the overall fatigue life: within a specific range, the fatigue failure probability of the main bearing increases as the average wind speed decreases. (4) The impact of wind speed fluctuations on the hub center load is much greater than that caused by rotational speed changes. (5) In addition, the modular design method adopted in this study calculates that the fatigue life of the fixed-end bearing is 28.8 years, with an overall error of only 0.8 years compared to the 29.6-year fatigue life obtained using Romax simulation software. This research provides important theoretical references and engineering value for improving the operational reliability of wind turbines and enhancing the accuracy of bearing fatigue life prediction.
To address the frequent occurrence of multiple fault types, the difficulty of feature extraction, and the susceptibility to noise interference in rolling bearings under complex operating conditions, this paper proposes a fault diagnosis method based on an improved one-dimensional convolutional neural network (1DCNN) integrated with a Transformer architecture. This approach leverages the 1DCNN to efficiently extract local impact and energy features from vibration signals, while the improved Transformer enables global modeling of long-range temporal dependencies, thereby significantly enhancing the recognition accuracy for multi-class fault signals and the generalization capability of the model. Experimental data are sourced from the Case Western Reserve University bearing fault dataset, with multi-channel vibration signals subjected to preprocessing and balanced sampling, and various types of simulated noise systematically introduced to comprehensively verify the noise robustness of the proposed model. Experimental results on the public dataset demonstrate that the improved 1DCNN-Transformer model achieves a classification accuracy of 99.43%, markedly outperforming traditional methods such as ANN, CNN, LeNet, and SVM. Further t-SNE visualizations and confusion matrix analyses reveal the method’s superior feature discrimination and high-precision performance across multiple fault categories. Tests under strong noise conditions further indicate that the model exhibits high robustness and excellent potential for engineering applications. In summary, the proposed method provides an efficient and reliable solution for intelligent fault diagnosis of rolling bearings in complex environments and lays a solid foundation for future model development and industrial deployment.
Accurate reliability assessment of wind turbine gears is important for reducing maintenance costs and improving the sustainability of wind turbine gearbox operation. This study proposes a reliability modeling framework centered on shock–degradation dependence and a time-varying degradation failure threshold. First, a mapping relationship between shock signals and stress is established. Subsequently, a state-dependent shock-induced degradation increment model is introduced to describe the bidirectional mechanism by which shocks accelerate degradation and degradation states amplify shock-induced damage. Furthermore, a time-varying degradation failure threshold model is developed to characterize the dynamic attenuation of the gear load-bearing boundary during service. On this basis, a hybrid Copula function is employed to establish the joint reliability model. A numerical case study was conducted on the sun gear of a 2 MW wind turbine gearbox. The results show that, under the specified numerical operating conditions and model parameter settings, the proposed model under the fixed-threshold condition predicts a relative increase of approximately 6.1% in failure probability compared with the model assuming independent shock and degradation processes. When the time-varying degradation failure threshold is considered, the failure probability shows a relative increase of approximately 30% compared with that under the fixed-threshold condition. The proposed model can effectively characterize the failure evolution of wind turbine gears under complex loading conditions and provide theoretical support for predictive maintenance.