Validation of artificial neural networks to model the acoustic behaviour of induction motors

Jiménez-Romero, F.J.; Guijo-Rubio, David; Lara-Raya, F.R.; Heredia-Larrubia, J.R.; Hervás-Martínez, C.

doi:10.1016/j.apacoust.2020.107332

Cited by 10 publications

(7 citation statements)

References 33 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we used a shallow neural network that was limited by the number of data available for training (constrained by practical limitations of the experimental protocol). This approach was inspired by recent works in other domains (Jiménez-Romero et al, 2020; Ma et al, 2017; Steinbach & Altinsoy, 2019) that also used such type of ANN. Any choice in this type of ANN could be discussed, such as the network architecture, the number of layers and neurons per layer, the weights, learning rate, and so on.…”

Section: Discussionmentioning

confidence: 99%

“…This kind of network consists of layers of interconnected neurons including activation functions, and all the connections have some mathematical expressions associated to weights. Similarly to previous works (Jiménez-Romero et al, 2020; Ma et al, 2017; Steinbach & Altinsoy, 2019), we selected this classical type of neural network because of the heterogeneous nature of the input data, and the low number of examples that could be used for training. In this study, x was the set of variables collected during each trial (postural, anthropometric and environmental variables, as described in Table 1).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Neural Networks Approach to Determine Factors Associated With Self-Reported Discomfort in Picking Tasks

et al. 2021

View full text Add to dashboard Cite

Objective A neural networks approach has been proposed to handle various inputs such as postural, anthropometric and environmental variables in order to estimate self-reported discomfort in picking tasks. An input reduction method has been proposed, reducing the input variables to the minimum data required to estimate self-reported discomfort with similar accuracy as the neural network fed with all variables. Background Previous works have attempted to explore the relationship between several factors and self-reported discomfort using observational methods. The results showed that this relationship was not a simple linear relationship. Another study used neural networks to model the function returning reported discomfort according to static posture, age, and anthropometrics variables. The results demonstrated the model’s ability to predict reported discomfort. But all the available variables were used to design the neural network. Method Eleven subjects carried-out picking tasks with various masses (0, 1, 3 kg) and imposed duration (5, 10, or 15 s). Continuous REBA score, anthropometric and environmental data were computed, and subjects’ discomfort were collected. The data set of this work consisted in the computed continuous REBA score, anthropometric, environmental data and collected subjects’ discomfort. Results The results showed that the correlation between the estimated and experimental tested data was equal to 0.775 when using all the 14 available variables. After data reduction, only 6 variables were left, with a very close performance when predicting discomfort. Conclusion A neural network approach has been proposed to estimate self-reported discomfort according to a minimum set of postural, anthropometric and environmental variables in picking tasks. Application This method has the potential to support ergonomists in workstation designing processes, by adding discomfort prediction to virtual manikins’ behaviors in simulation tools.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

A Neural Networks Approach to Determine Factors Associated With Self-Reported Discomfort in Picking Tasks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, these experts cannot determine the type of fault. Acoustic signal analysis is a useful method for detecting faults, as demonstrated through deep analysis of the acoustic quality of IMs (Jime´nez-Romero et al, 2020). Different fault diagnosis techniques based on acoustic signals have been proposed for three-phase IMs, including healthy, broken rotor bar, and faulty ring of squirrel-cage cases (Glowacz, 2018).…”

Section: Introductionmentioning

confidence: 99%

Comparison of acoustic signal–based fault detection of mechanical faults in induction motors using image classification models

Boztas

2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

This study presents a novel deep neural network–based method for fault detection in induction motors. The focus was on identifying five types of mechanical cases: normal operation, shaft/load breakage, misalignment, mounting bolt looseness, and cooling fan problems. To increase the realism of the results, a laboratory-collected dataset of stereo microphone recordings was augmented with real factory noise. The audio data was transformed into image data using Mel-frequency cepstral coefficients as the feature extraction method and then processed with image-based classifiers. A comparison was made among 12 different networks in terms of accuracy and number of parameters, revealing that Mobilenet_v2, EfficientNetV2B0, and NASNetMobile had the best performance in terms of both network size and accuracy.

show abstract

“…Many ML methods have been evaluated for classification in combination with acoustic feature extraction. Examples include discriminant analysis [15], extreme learning machines [16,17], nearest neighbour classifiers [8], support vector machines [10,18], random forest classifiers [19], neural networks [20], deep graph convolutional networks [9], and others. A comparative analysis of various ML-based classifiers was presented in [21], and a good overview of various natural computing algorithms for mechanical systems research is given in [22].…”

Section: Introductionmentioning

confidence: 99%

Condition classification of heating systems valves based on acoustic features and machine learning

Potočnik

Olmos

Vodopivec³

et al. 2021

Applied Acoustics

View full text Add to dashboard Cite

Validation of artificial neural networks to model the acoustic behaviour of induction motors

Cited by 10 publications

References 33 publications

A Neural Networks Approach to Determine Factors Associated With Self-Reported Discomfort in Picking Tasks

A Neural Networks Approach to Determine Factors Associated With Self-Reported Discomfort in Picking Tasks

Comparison of acoustic signal–based fault detection of mechanical faults in induction motors using image classification models

Condition classification of heating systems valves based on acoustic features and machine learning

Contact Info

Product

Resources

About