A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method

By Long Wen, Xinyu Li, Liang Gao, Yuyan Zhang. IEEE transactions on industrial electronics (1982. Print), 2018

1,795 citations recorded by the source corpus.

Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.

Subfields: Control and Systems Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/04fd278c01df1564e741b4c6e052fc1c5924ab8d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

In Industrial and Manufacturing Engineering

Citations in the corpus

Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application (2018, background): “…models, including stacked auto-encoder (SAE) [15], deep belief networks (DBN) [16] and, in particular, convolutional neural networks (CNN) [17]-[23], have gained much popularity and success in mechanical fault diagnosis issues, showing an extraordinary feature learning and fitting capacity.”
Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks (2020, background): “CNN, deep belief network (DBN), stacked autoencoder (SAE), and other deep learning models [17]–[22]”
Remaining Useful Life Prediction Based on a Double-Convolutional Neural Network Architecture (2019, methodology): “CNN based on LeNet-5 is proposed for fault diagnosis, which converts signals into two-dimensional (2-D) images and then extracts features from these images to eliminate the effect of handcrafted features [21].”
Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Comprehensive Review (2019, methodology): “For example, a CNN based on LeNet-5 is applied in [108], which contains 2 alternating convolutionalpooling layers and a 2 fully-connected layers.”
Understanding and Learning Discriminant Features based on Multiattention 1DCNN for Wheelset Bearing Fault Diagnosis (2020, methodology): “The eight deep learning networks are Wen-CNN [18], adaptive deep convolution neural network (ADCNN) [26] based on the 2DCNN, deep convolutional neural networks with wide ﬁrst-layer kernels (WDCNN) [17], residual convolution neural network (ResCNN) [23] based on the 1DCNN, gated recurrent unit (GRU),”
A comprehensive review on convolutional neural network in machine fault diagnosis (2020, background): “-sensor vibration signals into RGB color images to refine features and enlarge the differences between different types of fault signals. Then, an improved LeNet-5 was designed for fault diagnosis. In [60], raw mechanical signals were transformed into a square matrix through non-overlapping cutting a”
A transfer convolutional neural network for fault diagnosis based on ResNet-50 (2019, methodology): “As one of the most successful DL methods, CNN methods have also been widely studied for fault diagnosis [27–29].”
Deep Learning Algorithms for Bearing Fault Diagnosticsx—A Comprehensive Review (2019, methodology): “Many variations of CNN are also employed to tackle the bearing fault diagnosis challenge [109]–[116] using the CWRU dataset to obtain more desirable characteristics than conventional CNN.”
An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network (2020, neutral): “Therefore, the DBN is widely applied in fault classiﬁcation [9]–[14].”