With the increase in the installed capacity of wind power systems, the fault diagnosis and condition monitoring of wind turbines (WT) has attracted increasing attention. In recent years, machine learning (ML) has played a crucial role as an emerging technology for fault diagnosis in wind power systems has played a crucial role. Even though ML methods have shown great potential in dealing with the issues related to the fault diagnosis of WT, there are still some challenges encountered in many aspects. In this paper, typical fault diagnosis methods based on ML methods for wind power systems are thoroughly reviewed in terms of both theoretical fundamentals and industrial applications, including traditional machine learning (TML), artificial neural networks (ANN), deep learning (DL) and transfer learning (TL), in the development line of ML technologies. The advantages and disadvantages of various methods are analyzed and discussed. Meanwhile, a distribution diagram is provided for the discussions of ML methods applied for WT fault diagnosis, and the existing challenges on the applications for fault diagnosis based on ML for wind power generation systems are presented. Moreover, some prospects for future research directions are provided.

The vibration signals extracted from gearbox are usually masked in heavy background noise. Analyzing the feature components of these signals is challenging and crucial to incipient fault diagnosis. Kurtogram has been verified as a very powerful and practical tool in mechanical fault diagnosis due to its advantages in detecting and characterizing transients in signals. However, the accuracy of kurtogram is limited because it is based on short-time Fourier transform (STFT) or FIR filter in extracting transient characteristics from a noisy signal. Therefore, it is necessary to develop a more accurate filter to overcome its shortcomings and further improve its fault detection accuracy. Wavelet transform has been widely applied in the past as a powerful tool to analyze the non-stationary signals, and alpha-stable distribution model is often used to describe the statistical features of non-Gaussian signals. In this paper, a Morlet wavelet filter is optimized based on kurtogram and the alpha parameter of the alpha-stable distribution model. Through the analysis of simulation signals at different fault degrees and operating conditions, it can be concluded that alpha-stable distribution has better performance than kurtosis in measuring non-Gaussian characteristics of an impulsive gear fault signal. The results obtained from simulation and practical experiments confirm the superiority of the proposed method for incipient gear fault diagnosis.

Pedicle drilling is an important step in pedicle screw fixation and the most significant challenge in this operation is how to determine a key point in the transition region between cancellous and inner cortical bone. The purpose of this paper is to find a method to achieve the recognition for the key point. After acquiring acoustic emission (AE) signals during the drilling process, this paper proposed a novel frequency distribution-based algorithm (FDB) to analyze the AE signals in the frequency domain after certain processes. Then we select a specific frequency domain of the signal for standard operations and choose a fitting function to fit the obtained sequence. Characters of the fitting function are extracted as outputs for identification of different bone layers. The results, which are obtained by detecting force signal and direct measurement, are given in the paper. Compared with the results above, the results obtained by AE signals are distinguishable for different bone layers and are more accurate and precise. The results of the algorithm are trained and identified by a neural network and the recognition rate reaches 84.2%. The proposed method is proved to be efficient and can be used for bone layer identification in pedicle screw fixation.

Intelligent fault diagnosis for a single wind turbine is hindered by the lack of sufficient useful data, while multi-turbines have various faults, resulting in complex distributions. Collaborative intelligence can better solve these problems. Therefore, a peer-to-peer network is constructed with one node corresponding to one wind turbine in a cluster. Each node is equivalent and functional replicable with a new federated transfer learning method, including model transfer based on multi-task learning and model fusion based on dynamic adaptive weight adjustment. Models with convolutional neural networks are trained locally and transmitted among the nodes. A solution for the processes of data management, information transmission, model transfer and fusion is provided. Experiments are conducted on a fault signal testing bed and bearing dataset of Case Western Reserve University. The results show the excellent performance of the method for fault diagnosis of a gearbox in a wind turbine cluster.

As one of the most important components in rotating machinery, if bearings fail, serious disasters may occur. Therefore, the remaining useful life (RUL) prediction of bearings is of great significance. Health indicator (HI) construction and early fault detection play a crucial role in data-driven RUL prediction. Unfortunately, most existing HI construction methods require prior knowledge and preset trends, making it difficult to reflect the actual degradation trend of bearings. And the existing early fault detection methods rely on massive historical data, yet manual annotation is time-consuming and laborious. To address the above issues, a novel deep convolutional auto-encoder (CAE) based on envelope spectral feature extraction is developed in this work. A sliding value window is defined in the envelope spectrum to obtain initial health indicators, which are used as preliminary labels for model training. Subsequently, CAE is trained by minimizing the composite loss function. The proposed construction method can reflect the actual degradation trend of bearings. Afterwards, the autoencoder is pre-trained through contrast learning (CL) to improve its discriminative ability. The model that has undergone offline pre-training is more sensitive to early faults. Finally, the HI construction method is combined with the early fault detection method to obtain a comprehensive network for online health assessment and fault detection, thus laying a solid foundation for subsequent RUL prediction. The superiority of the proposed method has been verified through experiments.