A novel multi-information decision fusion based on improved random forests in HVCB fault detection application

Evaluating the mechanical state of high-voltage circuit breakers (HVCBs) based on vibration information has currently become an important research direction. In contrast to the unicity of the travel–time and current–time curves, the vibration information from the different positions is diverse. These differences are often overlooked in HVCB fault identification applications. Additionally, the fault recognition results based on different location information often vary, and conflicting diagnosis results directly cause the accurate identification of the fault type to fail. Therefore, in this paper, a novel multi-information decision fusion approach is proposed based on the improved random forest (RF) and Dempster-Shafer evidence theory. In the proposed method, the diagnostic distribution of all classification regression trees (CART) in the RF is considered to solve the conflicts among the multi-information diagnosis results. Experimental results show that the proposed method eases the contradiction of multi-position diagnostic results and improves the accuracy of fault identification. Furthermore, compared to the common classifiers and probability generation methods, the effectiveness and superiority of the proposed method are verified.

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

Earth fault detection in distributed power systems on the basis of artificial neural networks approach

Nowadays, the advancement of microgrids promises numerous economic and environmental advantages of renewable energies to nations and societies. The presence of decentralized energy units, however, makes serious technical challenges; for instance, criteria and procedure of fault recognition and diagnosis in this condition is entirely changing. This article, therefore, proposed a novel accurate and fast technique based on Artificial Neural Networks (ANN) for earth fault detection. A sample distributed power system considered for the proposed technique and different earth faults applied to this system consist of one phase, two phases and three phases faults. Also, any alteration of current and voltage signals of all phases is investigated at the fault occurrence moment. Analysis of simulation results demonstrates how the proposed technique could make faster responses and improve the reliability of the distributed power system by more accurate fault recognition in comparison with the other traditional methods such as the Wavelet Transformation technique. The proposed technique is likely to enhance the growth of renewable energy sources usage by decreasing operational risk factors and fault recognition delays.

Diagnosing the state of marine diesel engines by probabilistic fault recognition method

Diagnostics of marine diesel engines, during the navigation of the vessel, allows you to prevent the development of an accident, perform maintenance in a timely manner, eliminate the possibility of technical failures. The wear of parts is one of the main reasons for putting a diesel engine into repair. Timely detection of the occurrence of wear according to the indications of standard monitoring devices, allows you to prevent the negative consequences of wear, perform repairs in a timely manner, eliminate the possibility of an unplanned exit of the marine diesel engine from operation. If there is a need to operate a marine diesel engine in conditions different from those established by the manufacturer, diagnostics allows you to predict the temporary operational characteristics

An Intelligence Method for Recognizing Multiple Defects in Rail

Ultrasonic guided waves are sensitive to many different types of defects and have been studied for defect recognition in rail. However, most fault recognition algorithms need to extract features from the time domain, frequency domain, or time-frequency domain based on experience or professional knowledge. This paper proposes a new method for identifying many different types of rail defects. The segment principal components analysis (S-PCA) is developed to extract characteristics from signals collected by sensors located at different positions. Then, the Support Vector Machine (SVM) model is used to identify different defects depending on the features extracted. Combining simulations and experiments of the rails with different kinds of defects are established to verify the effectiveness of the proposed defect identification techniques, such as crack, corrosion, and transverse crack under the shelling. There are nine channels of the excitation-reception to acquire guided wave detection signals. The results show that the defect classification accuracy rates are 96.29% and 96.15% for combining multiple signals, such as the method of single-point excitation and multi-point reception, or the method of multi-point excitation and reception at a single point.

Core looseness fault identification model based on Mel spectrogram-CNN

In order to realize transformer voiceprint recognition, a transformer voiceprint recognition model based on Mel spectrum convolution neural network is proposed. Firstly, the transformer core looseness fault is simulated by setting different preloads, and the sound signals under different preloads are collected; Secondly, the sound signal is converted into a spectrogram that can be trained by convolutional neural network, and then the dimension is reduced by Mel filter bank to draw Mel spectrogram, which can generate spectrogram data sets under different preloads in batch; Finally, the data set is introduced into convolutional neural network for training, and the transformer voiceprint fault recognition model is obtained. The results show that the training accuracy of the proposed Mel spectrum convolution neural network transformer identification model is 99.91%, which can well identify the core loosening faults.

A fault diagnosis method based on low SNR vibration measurement used in casing cutter

In this paper, a fault diagnosis method for casing cutter was proposed, a vibration signal acquisition circuit used at high temperature environment was designed, and a casing cutter measurement model was established, including the model of the casing cutter in a trouble-free state and two other common fault states, the vibration characteristics of the model was analyzed. A fault feature enhancement model based on SNR enhancement and sparse representation, which effectively solves the fault diagnosis problem caused by the limited installation location and the limited performance of the vibration measurement at high-temperature was also designed. The MobieNet-V3- Small convolutional neural network (CNN) model is improved by reducing the basic blocks of the continuous homogeneous structure in the original model, the Squeeze and Excitation-SE structure is expanded to the global level to obtain a lightweight CNN fault recognition model. The effectiveness and efficiency of the proposed method are validated by various experiments.