Light-Weight CNN Enabled Edge-Based Framework for Machine Health Diagnosis

Mukherjee, Indrani; Tallur, Siddharth

doi:10.1109/access.2021.3088237

Cited by 15 publications

(15 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from sensor precision, another factor that contributes to the low classification accuracy in case (d) is the significant overlap in mean peak frequency (MPF) for healthy (H) and ball bearing fault (BB), as seen in Figure 2. MPF is a key time-frequency domain feature that increases sharply with advancing defects in machines 33 .…”

Section: Resultsmentioning

confidence: 99%

“…For further details on the experimental setup, please refer report by Qiu et al 32 . Since the IMS-bearing data set is an unlabelled data set, the mean peak frequency (MPF) of the spectrogram was used to label the healthy and faulty data, in accordance with the strategy presented by Mukherjee et al 33 .…”

Section: Description Of Experimental Data Setsmentioning

confidence: 99%

“…Thus, the TL-CNNs may have to be retrained with a small number of samples from healthy and faulty operating conditions. To emulate this scenario, we utilised the TL model performance on the run-to-failure IMS data set that possesses a large number of healthy samples as compared to faulty samples and used MPF as the signature for assigning labels, using the method described by Mukherjee et al 33 . Figure 4 presents the accuracy of the deep TL-CNN for a varying number of samples used for retraining the convolutional layers.…”

Section: Impact Of the Size Of Target Domain Data Setmentioning

confidence: 99%

See 2 more Smart Citations

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Asutkar

Tallur

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Automated fault diagnosis algorithms based on vibration sensor recordings play an important role in determining the state of health of the machines. Data-driven approaches require a large number of supervised and labelled samples to build reliable models. The performance of such lab-trained models when deployed in practical use cases largely depends on their domain generalisation capability towards distinct distribution target domain datasets. These challenges are addressed to some extent by conventional parameter-based transfer learning techniques that fine-tune deeper (dense) layer parameters of the pre-trained networks when lower (convolutional) layers can capture more domain-specific information concerning the changing target domain distribution. In this work, we present a novel deep transfer learning strategy that utilises fine-tuning the parameters of convolutional layers and transfer of knowledge in the dense layers from the source domain for efficient domain generalisation and fault classification. The performance of this strategy is evaluated with two different target domain data sets, by studying the sensitivity of fine-tuning individual layers in the networks using time-frequency representations of the vibration signals (scalograms) as inputs. We observe that this strategy yields near-perfect accuracy, even for use cases where low-precision sensors are used for data collection, and unlabelled run-to-failure data with a limited number of training samples.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Description Of Experimental Data Setsmentioning

confidence: 99%

Section: Impact Of the Size Of Target Domain Data Setmentioning

confidence: 99%

See 1 more Smart Citation

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Asutkar

Tallur

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Grezmak et al [24] took the vibration signal as the time series data, which converted it into a spectrum image through wavelet transform, classified it with CNN finally. Mukherjee et al [25] proposed a light-weight CNN which utilizes vibration sensor measurements for fault event estimation of machines. Kumar et al [26] adopted a CNN model which combined adaptive gradient optimizer and BN to optimize the performance of fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A convolutional neural network method based on Adam optimizer with power-exponential learning rate for bearing fault diagnosis

Wang¹,

Zhao²,

Cao³

2022

J. vibroeng.

View full text Add to dashboard Cite

The extraction of early fault features from time-series data is very crucial for convolutional neural networks (CNNs) in bearing fault diagnosis. To address this problem, a CNN framework based on identity mapping and Adam optimizer is presented for learning temporal dependencies and extracting fault features. The introduction of four identity mappings allows the deep layers to directly learn the data from the shallow layers, which alleviates the gradient disappearance problem caused by the increase of network depth. A new Adam optimizer with power-exponential learning rate is proposed to control the iteration direction and step size of CNN method, which solves the problems of local minima, overshoot or oscillation caused by the fixed values of the learning rates during the updating of network parameters. Compared to existed methods, the identification accuracy of the proposed method outperformed that of other methods for bearing fault diagnosis.

show abstract

“…Therefore, deep learning methods are one of the most popular technologies in data processing. For example, the convolutional neural network (CNN) method can change weights to adjust for its learning ability and achieves flexible structure for fault diagnosis [ 6 , 7 , 8 , 9 ]. To improve the self-learning ability of CNN, adaptive deep convolution neural network (ADCNN) methods have been applied to the training and testing of large data, identifying the target states for monitoring systems [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Image-Based Diagnosis Method Using Improved DCGAN for Rotating Machinery

Gao

Piltan

Kim

2022

Sensors

View full text Add to dashboard Cite

Rotating machinery plays an important role in industrial systems, and faults in the machinery may damage the system health. A novel image-based diagnosis method using improved deep convolutional generative adversarial networks (DCGAN) is proposed for the feature recognition and fault classification of rotating machinery. First, vibration signal data from the rotating machinery is transformed into time–frequency feature 2-D image data by a continuous wavelet transform and used for fault classification with the neural network method. The adaptive deep convolution neural network (ADCNN) is then combined with the generative adversarial networks (GANs) to improve the performance of the feature self-learning ability from input data. Compared with different fault diagnosis methods, the proposed method has better performance for image feature classification in rotating machinery.

show abstract

Light-Weight CNN Enabled Edge-Based Framework for Machine Health Diagnosis

Cited by 15 publications

References 42 publications

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

A convolutional neural network method based on Adam optimizer with power-exponential learning rate for bearing fault diagnosis

A Novel Image-Based Diagnosis Method Using Improved DCGAN for Rotating Machinery

Contact Info

Product

Resources

About