Quasi 1D CNN-based Fault Diagnosis of Induction Motor Drives

Mukhopadhyay, R.; Panigrahy, Parth Sarathi; Misra, Gaurab; Chattopadhyay, Paramita

doi:10.1109/epecs.2018.8443552

Cited by 12 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new approach named CapNET based on a CNN has been proposed thanks to thermal analysis and gives relatively good results [43,55], but the high cost of thermal sensors does not encourage their application. The analysis by the stator current also gives good results with a CNN; the method proposed by [32] with a Q1DCNN gives medium performance while Sun et al [54] proposes a HCNN which remains a disadvantage because of the large storage capacity it requires for a model implementation in a microcontroller board. Table 9.…”

Section: Resultsmentioning

confidence: 99%

“…The data preprocessing coming from the sensors is essential, it consists of extracting information from raw signals among a large data volume, making their manipulation difficult to manipulate. The concept is to convert the vibration frequency signal into an image [30,32] of pixel size M M, ´a color outline is appended to the image representing the motor temperature value. Let's consider the 1D vibration signal L i ( ) of a faultless motor of length 1024 points such:…”

Section: D Data Into a 2d Image Conversionmentioning

confidence: 99%

“…Usually, signals are represented by one-dimensional (1D) vectors, so a conversion to a two-dimensional (2D) signal is necessary to exploit the fault signatures from the converted images [20,[25][26][27]. It allows the direct extraction of the electrical machine's vibratory characteristics [28], propose an intelligent fault diagnosis method using 2D images as an SVM classifier input [29], present an implementation of the Global dominant Neighborhood Structure (GNS) based 2D fault diagnosis method for an induction motor [30], propose a method for bearing fault diagnosis without feature extraction using vibration images from 1D signal to 2D image conversion using CNN for fault classification [31], propose a method to extract features from converted 2D images and eliminate any effect of handcrafted features [32], presents a study focusing on motor fault diagnosis using simplified images appropriate to real-time applications.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhanced motor fault detection system based on a dual-signature image classification method using CNN

2023

View full text Add to dashboard Cite

This paper proposes a new Motor Image Classification (MIC) approach based on a multi-signal conversion technique using Convolutional Neural Network (CNN). In this regard, two one-dimensional (1D) signals are combined and converted into a (2D) color image with motor information pixels. Initially, the vibration signal is converted into the frequency domain. Each point of this signal is firstly assigned a color according to its amplitude and then placed successively on a specific column to obtain a pixilated image. An outline is added to the image representing the internal motor temperature. Therefore, the vibratory and thermal situation of the engine is clearly represented in a Dual-Signature Image (DSI). Our system proves the efficiency of the color compared to grayscale images. It ensures fast and effective prevention, which results in a long service lifetime and maximum motor availability. The diagnostic success rate of our system is 99.93%.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: D Data Into a 2d Image Conversionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced motor fault detection system based on a dual-signature image classification method using CNN

2023

View full text Add to dashboard Cite

show abstract

“…It has been found that a proper choice for the PMSM prototypes used during the experiments is to trigger the operation of the condition monitoring algorithm above the minimum operating speed ω min = 42 rad/s = 400 rpm, less than 0.1 ⋅ Ω m,N . In turn, that choice leads to a minimum kernel length M min = 187, M k = 300 and M = 5000, according to (17) and the related discussion.…”

Section: Min ≥ π P ω Min T C ð17þmentioning

confidence: 99%

“…Promising results were reported in Refs. [17,18], in which a CNN was applied on induction motors in order to identify different types of fault. The main focus was on the transformation of a current sequence into a 2D image, in order to use a traditional 2D CNN as it is usually applied to image recognition.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive approach to convolutional neural networks‐based condition monitoring of permanent magnet synchronous motor drives

Pasqualotto

Zigliotto

2021

IET Electric Power Appl

View full text Add to dashboard Cite

The increasing complexity of modern industrial systems calls for automatic and innovative predictive maintenance techniques. As suggested by the Industry 4.0 process, this demand translates in the need of more-intelligent drives. Herein, the use of a special kind of neural networks to interpret the data from motor currents for diagnostic purposes is described. The early detection of possible faults in the electrical motor allows programmed maintenance and reduces the risk of unplanned shutdowns. The innovation is in the overall approach to the neural network training, which does not call anymore for a large set of faulty motors. A large training dataset generated using a combination of tuned motor models and some data augmentation techniques is proposed. The result is a comprehensive and effective motor condition monitoring algorithm, whose hearth is a convolutionary neural network trained by a safe and cheap simulation-based dataset. The details of the design are fully reported here. The method has been implemented in the laboratory and fully tested on both healthy and faulty permanent magnet synchronous motors. The generality of the proposed method also paves the way for the detection of other failures and the application to different electrical motors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

A novel approach for detection of consciousness level in comatose patients from EEG signals with 1-D convolutional neural network

Altıntop

Latifoğlu

Akın

et al. 2022

Biocybernetics and Biomedical Engineering

View full text Add to dashboard Cite

Quasi 1D CNN-based Fault Diagnosis of Induction Motor Drives

Cited by 12 publications

References 14 publications

Enhanced motor fault detection system based on a dual-signature image classification method using CNN

Enhanced motor fault detection system based on a dual-signature image classification method using CNN

A comprehensive approach to convolutional neural networks‐based condition monitoring of permanent magnet synchronous motor drives

A novel approach for detection of consciousness level in comatose patients from EEG signals with 1-D convolutional neural network

Contact Info

Product

Resources

About