Among renewable energy sources, wind energy is regarded as one of the fastest-growing segments, which plays a key role in enhancing environmental quality. Wind turbines are generally located in remote and harsh environments. Bearings are a crucial component in wind turbines, and their failure is one of the most frequent reasons for system breakdown. Wind turbine bearing faults are usually very localized during their early stages which is precisely when they need to be detected. Hence, the early diagnosis of bearing faults holds paramount practical significance. In order to solve the problem of weak pulses being masked by noise in early failure signals of rolling element bearings, a novel fault diagnosis method is proposed based on the combination of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and an improved TFR demodulation method. Initially, the decomposition of vibration signals using CEEMDAN is carried out to obtain several intrinsic mode functions (IMFs). Subsequently, a novel KC indicator that combines kurtosis and the correlation function is designed to select the effective components for signal reconstruction. Finally, an innovative approach based on the continuous wavelet transform (CWT) for multi-scale demodulation analysis in the domain of time–frequency representation (TFR) is also introduced to extract the envelope spectrum. Further fault diagnosis can be achieved by the identification of the fault characteristic frequency (FCF). This study focuses on the theoretical exploration of bearing faults diagnosis algorithms, employing modeling and simulation techniques. The effectiveness and feasibility of the proposed method are validated through the analysis of simulated signals and experimental signals provided by the Center for Intelligent Maintenance Systems (IMS) of the University of Cincinnati and the Case Western Reserve University (CWRU) Bearing Data Center. The method demonstrates the capability to identify various types of bearing faults, including outer race and inner race faults, with a high degree of computational efficiency. Comparative analysis indicates a significant enhancement in fault diagnostic performance when compared to existing methods. This research contributes to the advancement of effective bearing fault diagnosis methodologies for wind turbines, thereby ensuring their reliable operation.

The safety of power transmission systems in wind turbines is crucial to the wind turbine’s stable operation and has attracted a great deal of attention in condition monitoring of wind farms. Many different intelligent condition monitoring schemes have been developed to detect the occurrence of defects via supervisory control and data acquisition (SCADA) data, which is the most commonly applied condition monitoring system in wind turbines. Normally, artificial neural networks are applied to establish prediction models of the wind turbine condition monitoring. In this paper, an alternative and cost-effective methodology has been proposed, based on the group method of data handling (GMDH) neural network. GMDH is a kind of computer-based mathematical modelling and structural identification algorithm. GMDH neural networks can automatically organize neural network architecture by heuristic self-organization methods and determine structural parameters, such as the number of layers, the number of neurons in hidden layers, and useful input variables. Furthermore, GMDH neural network can avoid over-fitting problems, which is a ubiquitous problem in artificial neural networks. The effectiveness and performance of the proposed method are validated in the case studies.

Offshore wind-turbine gearboxes operate under continuously varying speeds, while incipient planetary-gear fault signatures are weak, modulated, and difficult to recover without a tachometer. This study presents a tachometer-free framework that separates low- and high-oscillation components using adaptive oscillatory behavior signal decomposition, with its Q-factor and sparsity parameters selected by a convergence index and multi-scale periodic-modulation-intensity double loop. The integrated workflow uses existing gearbox vibration channels for phase estimation and order analysis when a tachometer signal is unavailable. Its contribution is the coupling of adaptive component selection, compact high-order time–frequency analysis and ridge-based resampling. A downsampled fourth-order synchrosqueezing transform (DSST4) produces a compact, concentrated time–frequency representation. Penalized global-path ridge extraction then estimates shaft speed, and segmented integral-approximation resampling converts the signal to the angle domain. For a simulated amplitude- and frequency-modulated signal at −5 dB, DSST4 reduces Rényi entropy from 7.35 to 5.65 and computation time from 4.959 s to 0.002 s, relative to the full-sampling fourth-order transform. In the University of Ottawa variable-speed bearing dataset, speed-estimation error is 18.67 rpm. For a 2 MW offshore wind turbine, order spectra identify a ring-gear component near order 0.714 in March, and an additional planet-gear component near 0.456 with modulation sidebands in April. Teardown confirmed spalling on both gears.