Research on diagnosis method of series arc fault of three-phase load based on SSA-ELM

Arc fault in the three-phase load circuit may cause fire, resulting in production interruption and even worse, it will cause casualties. In order to effectively detect the arc fault in the three-phase circuit, series arc fault experiments of three-phase motor load and frequency converter were carried out under different current conditions. Firstly, variational mode decomposition (VMD) was performed for each cycle of A-phase current, and then the VMD energy entropy and sample entropy were calculated. Secondly, the noise-dominated component was removed according to the permutation entropy, then the average value after first-order difference of the half-cycle reconstructed signal was obtained. An arc fault diagnosis model of extreme learning machine (ELM) optimized by sparrow search algorithm (SSA) was established. The feature vectors were divided into training group and test group to train the model and test its fault diagnosis accuracy. Compared with GA-ELM, PSO-ELM, support vector machine (SVM) and SSA-SVM, the experimental results show that the proposed method can identify the series arc fault accurately and more quickly.

A hybrid deep-learning model for fault diagnosis of rolling bearings under strong noise environment

Aiming at the problem that the signal of rolling bearing is interfered by strong noise in practical engineering environment, which leads to the decline of the diagnosis accuracy of intelligent diagnosis model. This paper proposes a novel hybrid model (CDAE-BLCNN). First, the rolling bearing vibration signal containing noise was input into the Convolutional Denoising Auto-Encoder (CDAE), which denoises the signal through unsupervised learning, and then outputs the reconstructed data. Secondly, a hybrid neural network (BLCNN) composed of multi-scale wide convolution kernel block (MWCNN) and bidirectional long-short-term memory network (BiLSTM) was used to extract intrinsic fault features from the reconstructed signal and diagnose fault types. The analysis results demonstrate that the proposed hybrid deep learning model achieves higher detection accuracy even under different noise and various rotating speed. Compared with other models, there is a high fault recognition rate, robustness, and generalization ability, which may be favorable to practical applications.

Design of sEMG Acquisition Circuit and Its Adaptive EEMD Denosing Research

The Surface electromyography (sEMG) signal is a kind of electrical signal which generated by human muscles during contraction. It is prone to being affected by noise because of its small amplitude, so it is necessary to remove the noise in its original signal with an appropriate algorithm. Based on the traditional signal denoising indicators, a new complex indicator r has been proposed in this paper which combines three different indicator parameters, that is, Signal to Noise Ratio (SNR), correlation coefficient (R), and standard error (SE). At the same time, an adaptive ensemble empirical mode decomposition (EEMD) method named AIO-EEMD which based on the proposed indicator is represented later. To verify the effective of the proposed algorithm, an electromyography signal acquisition circuit is designed firstly for collecting the original sEMG signal. Then, the denosing performance from the designed method is been compared with empirical mode decomposition (EMD) method and wavelet transform noise reduction method, respectively. The experiment results shown that the designed algorithm can not only automatically get the numbers of the reconstructed signal numbers, but also obtain the best reduction performance.

Fault diagnosis of rolling bearings based on improved direct fast iterative filtering and spectral amplitude modulation

As the transient impulse components in early fault signals are weak and easily buried by strong background noise, the fault features of rolling bearings are difficult to be extracted effectively. Focusing on this issue, a novel method based on improved direct fast iterative filtering and spectral amplitude modulation (IDFIF-SAM) is presented for detecting the early fault of rolling bearings. First, the ratio of the average crest factor of autocorrelation envelope spectrum to the average envelope entropy is taken as the fitness function to search the optimal parameters of direct fast iterative filtering (DFIF) adaptively via particle swarm optimization (PSO). Then, the efficient kurtosis entropy (EKE) index is being employed to choose the suitable components to reconstruct the signal. Finally, the reconstructed signal is subjected to spectral amplitude modulation (SAM) to strengthen the impulse features. The superiority of improved direct fast iterative filtering (IDFIF) over fixed-parameter DFIF, fast iterative filtering (FIF), and hard thresholding fast iterative filtering (HTFIF) is clarified through the simulated signal. Moreover, the comparative experimental analysis shows that the proposed IDFIF-SAM method can identify the early fault feature of rolling bearings more effectively.

Fault Location with High Precision of Flexible DC Distribution System Using Wavelet Transform and Convolution Neural Network

Though flexible DC distribution system (FDCDS) is becoming a new hotspot in power systems lately because of the rapid development of power electronic devices and massive use of renewable energy, the failure to realize accurate fault location with high precision restricts its further application. Thus, a novel precise pole-to-ground fault location method of FDCDS based on wavelet transform (WT) and convolution neural network (CNN) is proposed in this paper for the limitation on the number of measuring points and high difficulty in extracting characteristics of FDCDS. The fault voltage signal is decomposed with multi-resolution by discrete wavelet transform (DWT), and then the transient energy function is constructed to select the frequency bands containing rich fault characteristics for signal reconstruction. The reconstructed signal forms two-dimensional time-frequency images through continuous wavelet transform (CWT), which are used as the input of CNN classifier after image enhancement to form the mapping relation between the fault feature and fault position using the powerful generalization ability of CNN, so as to complete fault location with high precision. The sample data on PSCAD/EMTDC verifies the accuracy and reliability of the proposed method, which can achieve fault location with positioning precision of 30 m. The proposed method overcomes the influence of the control strategy of the converter and the number of input capacitors of the bridge arm in the time-domain analysis, and still has strong robustness in the case that FDCDS is connected with many distributed generations (DGs) with output fluctuation. Furthermore, four other methods for fault location as comparisons are given to reflect the validity and anti-interference ability of proposed methods in various noises.

Error Minimization in ECG Signal Reconstruction Using Discrete Wavelet Transform

For clinical study and diagnosis, compression of Electro Cardio Gram (ECG) signal is a fundamental step for processing. However, the compression and reconstruction introduce errors in the signal. Therefore, error minimization is crucial before using these signals for analysis and diagnosis. This paper presents an efficient method to minimize the reconstruction error using the adaptive filtering technique. Better reconstruction was achieved based on higher value of Compression Ratio and lesser value of Percent Root mean squared difference. Daubechies Wavelet easily detects the signal spikes while keeping less error rate using Least Mean Squared Error algorithm. However, the percentage value of error appeared to be minimum when using Daubechies Wavelet because of its small coefficients other than Haar and Coiflet Wavelet. Therefore, it was concluded that Daubechies Wavelet should have been used for error minimization in the reconstructed signal.

Discrete Cosine Transform based ECG Signal Analysis and Processing

Cardiovascular disease (CADs) is considered the primary leading cause of death. Irregular activity of heart, these disease can be detected and classified by Electrocardiogram (ECG), which is constructed from using electrodes placed on human skin to record the electrical activity of the heart. Because QRS complex represents the basic part of the ECG signal, these components should be recognized in order to analysis the other characteristics of the signal. Different methods and algorithms are proposed to analysis and processing the ECG signal. In this paper, a new QRS complex recognition method are proposed based on discrete cosine transform (DCT) with variable adaptive threshold method, which is used to determine threshold based on characteristic of each ECG signal to detect upper and lower levels of threshold to detect the peak of the signal. At first, the DCT is applied to the ECG signal to isolate it into different coefficients and eliminate or reduce the noises of the signal based on processing of high frequency components of DCT coefficients, which have less information, then the ECG is reconstructed by cropping the most important coefficients to be used in threshold determination. The basic idea is that the reconstructed signal have high differences between the components of the signal, and this facilitates the process of calculating the threshold value, which is used later to find peaks of ECG signal. The proposed method is tested and its performance are determined based on three different datasets, which are MITBIH Arrhythmia dataset, (LTSTDB) and (EDB) and the performance are evaluated using different metrics, which are Detection rate, accuracy, specificity and sensitivity. The experimental results show that the proposed method is performed or outperformed other works, therefore it can be used in peak detection applications.

Research on compound fault diagnosis of rolling bearing based on intrinsic time scale decomposition and information fusion

In view of the difficulty to effectively extract compound faults of rolling bearing from aero-engine and precisely identify their types, the paper has proposed a method integrating signal separation algorithm and information fusion. Firstly, the method decomposes the vibration acceleration signals collected by sensors from different positions at the same moment based on intrinsic time scale decomposition algorithm. Secondly, cross correlation analysis is given to the proper rotation component (PRC) of the same layer, which are obtained after decomposition and correspond to the sensors from different positions and cross-correlation function is introduced to embody information fusion. Thirdly, signals are reconstructed according to cross-correlation function of each PRC. Finally, based on the frequency spectrum of reconstructed signal, extract the characteristics of rolling bearing and identify the type of faults under different sensor combinations and multiple compound fault types. The result shows, the proposed method can effectively extract the characteristics of compound faults of bearing and precisely identify the type of faults under different sensor combinations and multiple compound fault types of rolling bearing.

Intelligent Diagnosis of Rotating Machinery Based on Optimized Adaptive Learning Dictionary and 1DCNN

In the intelligent fault diagnosis of rotating machinery, it is difficult to extract early weak fault impact features of rotating machinery under the interference of strong background noise, which makes the accuracy of fault identification low. In order to effectively identify the early faults of rotating machinery, an intelligent fault diagnosis method of rotating machinery based on an optimized adaptive learning dictionary and one-dimensional convolution neural network (1DCNN) is proposed in this paper. First of all, based on the original signal, a redundant dictionary with impact components is constructed by K-singular value decomposition (K-SVD), and the sparse coefficients are solved by an optimized orthogonal matching pursuit (OMP) algorithm. The sparse representation of fault impact features is realized, and the reconstructed signal with a concise fault impact feature structure is obtained. Secondly, the reconstructed signal is normalized, and the experimental dataset is divided into samples. Finally, the training set is input into the 1DCNN model for model training, and the test set is input into the trained model for classification and detection to complete the intelligent fault classification diagnosis of rotating machinery. This method is applied to the fault diagnosis of bearing data of Case Western Reserve University and worm gear reducer data of Shanghai University of Technology. Compared with other methods and models, the results show that the diagnosis method proposed in this paper can achieve higher diagnosis accuracy and better generalization ability than other diagnosis models under different datasets.

Active Sonar Target Classification Method Based on Fisher’s Dictionary Learning

The marine environment is complex and changeable, and the interference of noise and reverberation seriously affects the classification performance of active sonar equipment. In particular, when the targets to be measured have similar characteristics, underwater classification becomes more complex. Therefore, a strong, recognizable algorithm needs to be developed that can handle similar feature targets in a reverberation environment. This paper combines Fisher’s discriminant criterion and a dictionary-learning-based sparse representation classification algorithm, and proposes an active sonar target classification method based on Fisher discriminant dictionary learning (FDDL). Based on the learning dictionaries, the proposed method introduces the Fisher restriction criterion to limit the sparse coefficients, thereby obtaining a more discriminating dictionary; finally, it distinguishes the category according to the reconstruction errors of the reconstructed signal and the signal to be measured. The classification performance is compared with the existing methods, such as SVM (Support Vector Machine), SRC (Sparse Representation Based Classification), D-KSVD (Discriminative K-Singular Value Decomposition), and LC-KSVD (label-consistent K-SVD), and the experimental results show that FDDL has a better classification performance than the existing classification methods.