A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

Yang, Daoguang; Karimi, Hamid Reza; Gelman, Len

doi:10.3390/s22020671

Cited by 21 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A convolutional neural network (CNN) is a deep learning algorithm that extracts valuable features from time series data [15]. The CNN model is a reliable tool for spatially analyzing GWL data and extracting important patterns [16]. The long short-term memory (LSTM) neural network is another robust tool for temporal analysis of groundwater level (GWL) data [17].…”

Section: References Results Discussionmentioning

confidence: 99%

A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction

Ehteram,

Banadkooki

2023

Water

View full text Add to dashboard Cite

Groundwater level (GLW) prediction is essential for monitoring water resources. Our study introduces a novel model called convolutional neural network (CNN)–long short-term memory neural network (LSTM)–Multiple linear regression (MLR) for groundwater level prediction. We combine two deep learning models with the MLR model to predict GWL and overcome the limitations of the MLR model. The current paper has several innovations. Our study develops an advanced hybrid model for predicting groundwater levels (GWLs). The study also presents a novel feature selection method for selecting optimal input scenarios. Finally, an advanced method is developed to examine the impact of inputs and model parameters on output uncertainty. The current paper introduces the gannet optimization algorithm (GOA) for choosing the optimal input scenario. A CNN-LSTM-MLR model (CLM), CNN, LSTM, MLR model, CNN-MLR model (CNM), LSTM-MLR model (LSM), and CNN-LSTM model (CNL) were built to predict one-month-ahead GWLs using climate data and lagged GWL data. Output uncertainty was also decomposed into parameter uncertainty (PU) and input uncertainty (IU) using the analysis of variance (ANOVA) method. Based on our findings, the CLM model can successfully predict GWLs, reduce the uncertainty of CNN, LSTM, and MLR models, and extract spatial and temporal features. Based on the study’s findings, the combination of linear models and deep learning models can improve the performance of linear models in predicting outcomes. The GOA method can also contribute to feature selection and input selection. The study findings indicated that the CLM model improved the training Nash–Sutcliffe efficiency coefficient (NSE) of the CNL, LSM, CNM, LSTM, CNN, and MLR models by 6.12%, 9.12%, 12%, 18%, 22%, and 30%, respectively. The width intervals (WIs) of the CLM, CNL, LSM, and CNM models were 0.03, 0.04, 0.07, and, 0.12, respectively, based on IU. The WIs of the CLM, CNL, LSM, and CNM models were 0.05, 0.06, 0.09, and 0.14, respectively, based on PU. Our study proposes the CLM model as a reliable model for predicting GWLs in different basins.

show abstract

Section: References Results Discussionmentioning

confidence: 99%

A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction

Ehteram,

Banadkooki

2023

Water

View full text Add to dashboard Cite

show abstract

“…Yang et al [63] presented a comprehensible fuzzy fusion method to combine the output of CNN models that could assess the relevance of each classifier by looking at the interaction index between each classifier. Additionally, SoftPool and Mish activation features were added to conventional CNNs to improve their capacity for feature extraction.…”

Section: Deep Learningmentioning

confidence: 99%

Advances in Machine Learning for Sensing and Condition Monitoring

Ao¹,

Gelman²,

Karimi³

et al. 2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

In order to overcome the complexities encountered in sensing devices with data collection, transmission, storage and analysis toward condition monitoring, estimation and control system purposes, machine learning algorithms have gained popularity to analyze and interpret big sensory data in modern industry. This paper put forward a comprehensive survey on the advances in the technology of machine learning algorithms and their most recent applications in the sensing and condition monitoring fields. Current case studies of developing tailor-made data mining and deep learning algorithms from practical aspects are carefully selected and discussed. The characteristics and contributions of these algorithms to the sensing and monitoring fields are elaborated.

show abstract

“…However, they require the installation of expensive vibration sensors on the engine, making these methods invasive, inconvenient, and costly. vibration methods are well known and have been used for a long time to detect bearing damage [ 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 ]. vibration methods are still researched to achieve better damage diagnosis, mainly in terms of signal processing technique improvements.…”

Section: Introductionmentioning

confidence: 99%

Novel Investigation of Higher Order Spectral Technologies for Fault Diagnosis of Motor-Based Rotating Machinery

Ciszewski

Gelman

Ball

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

In the last decade, research centered around the fault diagnosis of rotating machinery using non-contact techniques has been significantly on the rise. For the first time worldwide, innovative techniques for the diagnosis of rotating machinery, based on electrical motors, including generic, nonlinear, higher-order cross-correlations of spectral moduli of the third and fourth order (CCSM3 and CCSM4, respectively), have been comprehensively validated by modeling and experiments. The existing higher-order cross-correlations of complex spectra are not sufficiently effective for the fault diagnosis of rotating machinery. The novel technology CCSM3 was comprehensively experimentally validated for induction motor bearing diagnosis via motor current signals. Experimental results, provided by the validated technology, confirmed high overall probabilities of correct diagnosis for bearings at early stages of damage development. The novel diagnosis technologies were compared with existing diagnosis technologies, based on triple and fourth cross-correlations of the complex spectra. The comprehensive validation and comparison of the novel cross-correlation technologies confirmed an important non-traditional novel outcome: the technologies based on cross-correlations of spectral moduli were more effective for damage diagnosis than the technologies based on cross-correlations of the complex spectra. Experimental and simulation validations confirmed a high probability of correct diagnosis via the CCSM at the early stage of fault development. The average total probability of incorrect diagnosis for the CCSM3 for all experimental results of 8 tested bearings, estimated via 6528 diagnostic features, was 1.475%. The effectiveness gains in the total probability of incorrect diagnosis for the CCSM3 in comparison with the CCCS3 were 26.8 for the experimental validation and 18.9 for the simulation validation. The effectiveness gains in the Fisher criterion for the CCSM3 in comparison with the CCCS3 were 50.7 for the simulation validation and 104.7 for the experimental validation.

show abstract

A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

Cited by 21 publications

References 41 publications

A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction

A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction

Advances in Machine Learning for Sensing and Condition Monitoring

Novel Investigation of Higher Order Spectral Technologies for Fault Diagnosis of Motor-Based Rotating Machinery

Contact Info

Product

Resources

About