The Influence of Handling Imbalance Classes on the Classification of Mechanical Faults Using Neural Networks

Ali, M. Tanseer; Bingamil, Ahmed Ameen; Jarndal, Anwar; Alsyouf, Imad

doi:10.1109/icmsao.2019.8880437

Cited by 8 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performance-wise, the proposed methodology is at least on a par with the existing works on the dataset [ 6 , 7 , 8 ]. If we neglect the different cross-validation strategies across studies, the accuracy obtained in the current work improves the state-of-the-art performance by above 1% in the absolute scale.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cost-Effective Vibration Analysis through Data-Backed Pipeline Optimisation

Sokolovsky

Hare²,

Mehnen

2021

Sensors

View full text Add to dashboard Cite

Vibration analysis is an active area of research, aimed, among other targets, at an accurate classification of machinery failure modes. The analysis often leads to complex and convoluted signal processing pipeline designs, which are computationally demanding and often cannot be deployed in IoT devices. In the current work, we address this issue by proposing a data-driven methodology that allows optimising and justifying the complexity of the signal processing pipelines. Additionally, aiming to make IoT vibration analysis systems more cost- and computationally efficient, on the example of MAFAULDA vibration dataset, we assess the changes in the failure classification performance at low sampling rates as well as short observation time windows. We find out that a decrease of the sampling rate from 50 kHz to 1 kHz leads to a statistically significant classification performance drop. A statistically significant decrease is also observed for the 0.1 s time window compared to the 5 s one. However, the effect sizes are small to medium, suggesting that in certain settings lower sampling rates and shorter observation windows might be worth using, consequently making the use of the more cost-efficient sensors feasible. The proposed optimisation approach, as well as the statistically supported findings of the study, allow for an efficient design of IoT vibration analysis systems, both in terms of complexity and costs, bringing us one step closer to the widely accessible IoT/Edge-based vibration analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In the second study by Ali et al [ 7 ], the authors intentionally use a shallow set of features together with SMOTE for class balancing and an MLP classifier reporting accuracy of 96.2%. The purpose of the study is to demonstrate the benefits of using SMOTE.…”

Section: Introductionmentioning

confidence: 99%

Cost-Effective Vibration Analysis through Data-Backed Pipeline Optimisation

Sokolovsky

Hare²,

Mehnen

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The Multi-Layer Perceptron (MLP) is one of the most versatile unidirectional Feed-Forward Neural Networks (FNNs) with one hidden layer. Its unique ability to dynamically create complex predictive functions proves its superiority in learning and modelling non-linear and complex relationships [28,30,31]. As a result, the MLP algorithm is being used in various research disciplines including fault classification [27][28][29].…”

Section: Multi-layer Perceptron (Mlp) Neural Networkmentioning

confidence: 99%

“…Based on the best three solutions obtained, the other search agents ( inclusive) are required to re-position with respect to the best search agents ( , and ) using the mathematical expressions shown in Eqs. (29)(30)(31).…”

Section: Grey Wolf Optimisation (Gwo) Algorithmmentioning

confidence: 99%

“…In the context of supervised ANN classifiers, the Multi-Layer Perceptron (MLP) neural network is among the most versatile algorithms used in various fault classification tasks [27][28][29]. Compared with other well-known classifiers, MLP has the unique ability to dynamically create complex predictive functions and emulate human thinking and has proven its superiority in learning and modelling non-linear and complex relationships [28,30,31]. In addition to that, MLP is known to be less affected by data imbalance than other classifiers [32].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel hybrid predictive maintenance model based on clustering, smote and multi-layer perceptron neural network optimised with grey wolf algorithm

et al. 2021

View full text Add to dashboard Cite

Considering the complexities and challenges in the classification of multiclass and imbalanced fault conditions, this study explores the systematic combination of unsupervised and supervised learning by hybridising clustering (CLUST) and optimised multi-layer perceptron neural network with grey wolf algorithm (GWO-MLP). The hybrid technique was meticulously examined on a historical hydraulic system dataset by first, extracting and selecting the most significant statistical time-domain features. The selected features were then grouped into distinct clusters allowing for reduced computational complexity through a comparative study of four different and frequently used categories of unsupervised clustering algorithms in fault classification. The Synthetic Minority Over Sampling Technique (SMOTE) was then employed to balance the classes of the training samples from the various clusters which then served as inputs for training the supervised GWO-MLP. To validate the proposed hybrid technique (CLUST-SMOTE-GWO-MLP), it was compared with its distinct modifications (variants). The superiority of CLUST-SMOTE-GWO-MLP is demonstrated by outperforming all the distinct modifications in terms of test accuracy and seven other statistical performance evaluation metrics (error rate, sensitivity, specificity, precision, F score, Mathews Correlation Coefficient and geometric mean). The overall analysis indicates that the proposed CLUST-SMOTE-GWO-MLP is efficient and can be used to classify multiclass and imbalanced fault conditions. Article Highlights The issue of multiclass and imbalanced class outputs is addressed for improving predictive maintenance. A multiclass fault classifier based on clustering and optimised multi-layer perceptron with grey wolf is proposed. The robustness and feasibility of the proposed technique is validated on a complex hydraulic system dataset.

show abstract