Real-time fault diagnosis using deep fusion of features extracted by parallel long short-term memory with peephole and convolutional neural network

Abstract

Analysis of one-dimensional vibration signals is the most common method used for safety analysis and health monitoring of rotary machines. How to effectively extract features involved in one-dimensional sequence data is crucial for the accuracy of real-time fault diagnosis. This article aims to develop more effective means of extracting useful features potentially involved in one-dimensional vibration signals. First, an improved parallel long short-term memory called parallel long short-term memory with peephole is designed by adding a peephole connection before each forget gate to prevent useless information transferring in the cell. It can not only solve the memory bottleneck problem of traditional long short-term memory for long sequence but also can make full use of all possible information helpful for feature extraction. Second, a fusion network with new training mechanism is designed to fuse features extracted from parallel long short-term memory with peephole and convolutional neural network, respectively. The fusion network can incorporate two-dimensional screenshot image into comprehensive feature extraction. It can provide more accurate fault diagnosis result since two-dimensional screenshot image is another form of expression for one-dimensional vibration sequence involving additional trend and locality information. Finally, real-time two-dimensional screenshot image is fed into convolutional neural network to secure a real-time online diagnosis which is the primary requirement of the engineers in health monitoring. Validity of the proposed method is verified by fault diagnosis for rolling bearing and gearbox.

Federated Learning Based Fault Diagnosis Driven by Intra-Client Imbalance Degree

“…where lr denotes the learning rate. Then the cost-sensitive loss function loss k,s using the imbalanced dataset X k of kth client in the sth round of federations on W g,s+1,B can be obtained by Equation (6).…”

“…As a key component of a motor, fault diagnosis research on rolling bearings plays an important role in ensuring the safe and stable operation of the motor [ 1 , 2 , 3 ]. As an effective data-driven fault diagnosis approach, deep learning is not limited by a precise physical model or adequate expert knowledge and can automatically extract fault features from raw data [ 4 , 5 , 6 ]. Therefore, the fault diagnosis methods based on deep learning have received widespread attention.…”

Modeling adaptive preview time of driver model for intelligent vehicles based on deep learning

“…The LSTM layer is a type of recurrent neural network (RNN) that can learn long-term dependencies between time steps of sequence data. 35 It was developed to overcome the vanishing and exploding gradient problem of RNN. 36 LSTM layer consists of four components, namely, input gate i l , forget gate f l , output gate o l and cell candidate g l , which control the cell state c l and hidden state h l of the layer.…”

Research on federated learning method for fault diagnosis in multiple working conditions

“…The BN technique is adopted in DNN training. Taking the two hidden layers as an example, the layer-by-layer feature extraction using BN can be formulated as Equation ( 6) (6) Where x is the input sequence data, W i,1 and W i,2 represent the weight between the input and output of the ith DNN, b i,1 and b i,2 are the corresponding biases, and f(•) is the nonlinear activation function Relu.…”

“…Deep learning is a data-driven fault diagnosis method. According to the variance of network structure, it can be classified into four categories: convolutional neural network (CNN)-based methods, long short-term memory network (LSTM)-based methods, deep neural network (DNN)-based methods, and DBN-based methods [4][5][6][7] . DNN and its variations have become some of the most commonly used methods for bearing fault diagnosis due to their simple structure and advantages in processing sequence data.…”