Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks

İnce, Türker; Kıranyaz, Serkan; Eren, Levent; Askar, M.; Gabbouj, Moncef

doi:10.1109/tie.2016.2582729

Cited by 1,059 publications

(459 citation statements)

References 32 publications

Supporting

Mentioning

450

Contrasting

Unclassified

Order By: Relevance

“…As a result, BP algorithm given in [33] is used iteratively with the learning factor, , for scaling weight and bias.…”

Section: Adaptive 1d Cnnsmentioning

confidence: 99%

“…The proposed method does not require any form of transformation, feature extraction, and postprocessing. The feature extraction and feature-based classification phases of the bearing fault detection could be combined into a single learning body with 1D CNNs [32,33]. It can directly work over the raw data, that is, the motor current signal, to detect the anomalies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bearing Fault Detection by One-Dimensional Convolutional Neural Networks

Eren

2017

Mathematical Problems in Engineering

Self Cite

179

107

View full text Add to dashboard Cite

Bearing faults are the biggest single source of motor failures. Artificial Neural Networks (ANNs) and other decision support systems are widely used for early detection of bearing faults. The typical decision support systems require feature extraction and classification as two distinct phases. Extracting fixed features each time may require a significant computational cost preventing their use in realtime applications. Furthermore, the selected features for the classification phase may not represent the most optimal choice. In this paper, the use of 1D Convolutional Neural Networks (CNNs) is proposed for a fast and accurate bearing fault detection system. The feature extraction and classification phases of the bearing fault detection are combined into a single learning body with the implementation of 1D CNN. The raw vibration data (signal) is fed into the proposed system as input eliminating the need for running a separate feature extraction algorithm each time vibration data is analyzed for classification. Implementation of 1D CNNs results in more efficient systems in terms of computational complexity. The classification performance of the proposed system with real bearing data demonstrates that the reduced computational complexity is achieved without a compromise in fault detection accuracy.

show abstract

“…As a result, BP algorithm given in [33] is used iteratively with the learning factor, , for scaling weight and bias.…”

Section: Adaptive 1d Cnnsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bearing Fault Detection by One-Dimensional Convolutional Neural Networks

Eren

2017

Mathematical Problems in Engineering

Self Cite

179

107

View full text Add to dashboard Cite

show abstract

“…CNN structures in [15,16] show great performance in classification. However, with a small number of categories, CNN would not always have better results than traditional methods as shown in [17]. Most works only dealt with a small number of categories, which is not adequate in practical situations, while our approach deals with 52 fault categories.…”

Section: Results Comparisonmentioning

confidence: 89%

“…CNN has been applied in fault diagnosis in [14][15][16][17]. CNN structures in [15,16] show great performance in classification.…”

Section: Results Comparisonmentioning

confidence: 99%

Fault Diagnosis for Rotating Machinery Based on Convolutional Neural Network and Empirical Mode Decomposition

Xie

Zhang

2017

Shock and Vibration

View full text Add to dashboard Cite

The analysis of vibration signals has been a very important technique for fault diagnosis and health management of rotating machinery. Classic fault diagnosis methods are mainly based on traditional signal features such as mean value, standard derivation, and kurtosis. Signals still contain abundant information which we did not fully take advantage of. In this paper, a new approach is proposed for rotating machinery fault diagnosis with feature extraction algorithm based on empirical mode decomposition (EMD) and convolutional neural network (CNN) techniques. The fundamental purpose of our newly proposed approach is to extract distinguishing features. Frequency spectrum of the signal obtained through fast Fourier transform process is trained in a designed CNN structure to extract compressed features with spatial information. To solve the nonstationary characteristic, we also apply EMD technique to the original vibration signals. EMD energy entropy is calculated using the first few intrinsic mode functions (IMFs) which contain more energy. With features extracted from both methods combined, classification models are trained for diagnosis. We carried out experiments with vibration data of 52 different categories under different machine conditions to test the validity of the approach, and the results indicate it is more accurate and reliable than previous approaches.

show abstract

“…These kinds of signals do not have many disturbances. The recognition of electrical signals of motors was also described in the literature [30][31][32][33][34][35][36][37][38][39][40]. However more analyses are needed in this topic, to develop more efficient methods of fault diagnosis .…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Three Phase Induction Motor Using Current Signal, MSAF-Ratio15 and Selected Classifiers

Głowacz¹,

Głowacz²,

Głowacz³

et al. 2017

Archives of Metallurgy and Materials

View full text Add to dashboard Cite

A degradation of metallurgical equipment is normal process depended on time. Some factors such as: operation process, friction, high temperature can accelerate the degradation process of metallurgical equipment. In this paper the authors analyzed three phase induction motors. These motors are common used in the metallurgy industry, for example in conveyor belt. The diagnostics of such motors is essential. An early detection of faults prevents financial loss and downtimes. The authors proposed a technique of fault diagnosis based on recognition of currents. The authors analyzed 4 states of three phase induction motor: healthy three phase induction motor, three phase induction motor with 1 faulty rotor bar, three phase induction motor with 2 faulty rotor bars, three phase induction motor with faulty ring of squirrel-cage. An analysis was carried out for original method of feature extraction called MSAF-RATIO15 (Method of Selection of Amplitudes of Frequencies -Ratio 15% of maximum of amplitude). A classification of feature vectors was performed by Bayes classifier, Linear Discriminant Analysis (LDA) and Nearest Neighbour classifier. The proposed technique of fault diagnosis can be used for protection of three phase induction motors and other rotating electrical machines. In the near future the authors will analyze other motors and faults. There is also idea to use thermal, acoustic, electrical, vibration signal together.

show abstract

Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks

Cited by 1,059 publications

References 32 publications

Bearing Fault Detection by One-Dimensional Convolutional Neural Networks

Bearing Fault Detection by One-Dimensional Convolutional Neural Networks

Fault Diagnosis for Rotating Machinery Based on Convolutional Neural Network and Empirical Mode Decomposition

Fault Diagnosis of Three Phase Induction Motor Using Current Signal, MSAF-Ratio15 and Selected Classifiers

Contact Info

Product

Resources

About