Rolling bearings, as important parts on supporting rotating shafts, frequently suffer from fatigue failures. If these rolling bearing failures are not found in time, it will have a huge impact on the whole mechanical system’s operating safety and operating life. To improve the diagnosis of different faults as well as different degrees of faults, a fault diagnosis method based on the multifractal detrended fluctuation analysis (MFDFA) method-singularity power spectrum (SPS) with extreme learning machine (ELM) is proposed. First, MFDFA and SPS analyses are performed on vibration acceleration signals with different faults and different degrees of damage under the same operating conditions, the spectral parameters of stability and quantitative description of differentiation are selected for feature extraction, and then the selected six feature parameters are put into the extreme learning machine for fault classification. The effectiveness of the MFDFA-SPS feature extraction method is demonstrated by analyzing and testing the measured bearing signals. The fault diagnosis accuracy of the bearing fault signals can reach 99.2% based on the MFDFA-SPS with ELM method by using the Case Western Reserve database. The improvements are 6.79% and 18.42% compared to the fault diagnosis methods based on MFDFA with ELM and SPS with ELM. Compared with the methods based on MFDFA-SPS with LSSVM classifier and SVM classifier, the accuracy improvements are 3.54% and 4.25%, respectively. The results show that the method proposed in this paper can achieve the diagnosis of bearing faults and the method based on MFDFA-SPS with ELM is more efficient than the methods based on MFDFA-SPS with LSSVM and SVM classifiers, which is suitable for practical engineering problem-solving.

The prerequisite for improving radar detection capability is to reduction of sea clutter from interfering with the target, and the accurate prediction of sea clutter is an essential prerequisite for effective suppression. To achieve an accurate prediction of sea clutter, a model for sea clutter prediction combination of the salp’s swarm algorithm, prediction using extreme learning machine after performing parameter search, which improves the prediction performance of ELM and backpropagation (BP) neural network. The convergence speed and accuracy are improved, and the overall prediction The IPIX radar sea clutter prediction reaches an accuracy of more than 99% and the prediction results of this model are better than that when only using ELM or BP neural network prediction.

Wind turbines are more prone to faults due to long operation in harsh environments. It is necessary to implement fault diagnosis for wind turbines to ensure the stability and reliability of the circuit system safety as well as to reduce the probability of faults. In this paper, a fault detection method based on Wavelet Leaders (WL) and limit learning machine is proposed to achieve fault prediction for fault-prone bearings. The WL algorithm is first applied to analyze the multiple fractality of several different states of faulty bearings, select the stable fault parameter features for extraction and finally use the ELM classification tool to achieve the classification of faults. The experimental results demonstrate that this method achieves fault classification detection and provides a new idea for faulty bearing detection.

Due to the harsh environment in which wind turbines work for long periods of time, the internal drive train is prone to fatigue failure. Rolling bearings are an important component within wind turbines, so it is essential to implement condition detection and fault diagnosis of rolling bearings. This paper proposes a fault signal feature extraction method based on VMD and Tsallis entropy. Firstly, the bearing signals of four different states are decomposed using VMD decomposition, and the IMF components generated after the decomposition are quantitatively characterized using Tsallis entropy, and the features with stability and differentiation are selected to form the feature vector of the fault and input to a support vector machine for classification. The experimental results show that the proposed method can distinguish different fault bearing signals and has some improvement in classification effect compared with KNN, fine tree and intermediate tree classifiers. The proposed method presents a new idea for the fault diagnosis of rolling bearings in wind turbines.