A Predictive Maintenance Model Using Recurrent Neural Networks

Rivas, Alberto; Fraile, Jesús M.; Chamoso, Pablo; González‐Briones, Alfonso; Sittón, Inés; Corchado, Juan M.

doi:10.1007/978-3-030-20055-8_25

Cited by 33 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Average F-Score (%) Gradient boosting decision tree (GBDT) [5] 94.59 Recurrent neural networks (RNN) [13] 86.00 Support vector machine (SVM) [14] 85.00 Support vector machine (SVM) [15] 81.00 LSTM autoencoders [17] 94.20 LSTM 93.34 The proposed hybrid CNN-LSTM 97.48…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance

Nasser

Al-Khazraji

2022

IJECE

View full text Add to dashboard Cite

<p>Predictive maintenance (PdM) is a successful strategy used to reduce cost by minimizing the breakdown stoppages and production loss. The massive amount of data that results from the integration between the physical and digital systems of the production process makes it possible for deep learning (DL) algorithms to be applied and utilized for fault prediction and diagnosis. This paper presents a hybrid convolutional neural network based and long short-term memory network (CNN-LSTM) approach to a predictive maintenance problem. The proposed CNN-LSTM approach enhances the predictive accuracy and also reduces the complexity of the model. To evaluate the proposed model, two comparisons with regular LSTM and gradient boosting decision tree (GBDT) methods using a freely available dataset have been made. The PdM model based on CNN-LSTM method demonstrates better prediction accuracy compared to the regular LSTM, where the average F-Score increases form 93.34% in the case of regular LSTM to 97.48% for the proposed CNN-LSTM. Compared to the related works the proposed hybrid CNN-LSTM PdM approach achieved better results in term of accuracy.</p>

show abstract

Section: Methodsmentioning

confidence: 99%

“…The model is built and evaluated using Microsoft PdM dataset and the results shows the model obtained and 94.56% of average accuracy. Rivas et al [13] presented a deep learning model for estimating remaining useful life (RUL) for industrial equipment and using it for PdM. The model is based on recurrent neural networks RNN.…”

Section: Introductionmentioning

confidence: 99%

A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance

Nasser

Al-Khazraji

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…They mainly differ on the output that the user requires from the system. There are binary classification systems, in which typically the user only wants to understand whether an issue has been identified or not [12]. Clearly multiclass systems provide more knowledge about the state of the system, but are also more complex.…”

Section: Modelsmentioning

confidence: 99%

Anomaly Detection and Classification in Predictive Maintenance Tasks with Zero Initial Training

Morselli¹,

Bedogni

Mirani

et al. 2021

IoT

View full text Add to dashboard Cite

The Fourth Industrial Revolution has led to the adoption of novel technologies and methodologies in factories, making these more efficient and productive. Among the new services which are changing industry, there are those based on machine learning algorithms, which enable machines to learn from their past observations and hence possibly forecast future states. Specifically, predictive maintenance represents the opportunity to understand in advance possible machine outages due to broken parts and schedule the necessary maintenance operations. However, in real scenarios predictive maintenance struggles to be adopted due to a multitude of variables and the heavy customization it requires. In this work, we propose a novel framework for predictive maintenance, which is trained online to recognize new issues reported by the operators. Our framework, tested on different scenarios and with a varying number and several kinds of sensors, shows recall levels above 0.85, demonstrating its effectiveness and adaptability.

show abstract

“…Machine Learning algorithms provide greater insight into the information contained in large amounts of diverse data, making it possible for much more knowledgeable and precise decision-making than would ever be possible with manual data analyses [1], [2]. These algorithms allow us to detect behavioral patterns in a given data set and to identify the key variables that affect trends and cause changes in the pattern of the data [3], [4].…”

Section: Introductionmentioning

confidence: 99%

A Review of the Main Machine Learning Methods for Predicting Residential Energy Consumption

González‐Briones

Hernández

Pinto

et al. 2019

2019 16th International Conference on the European Energy Market (EEM)

Self Cite

View full text Add to dashboard Cite

The ability to predict future energy consumption is very important for energy distribution companies because it allows them to estimate energy needs and supply them accordingly. Consumption prediction makes it possible for those companies to optimize their processes by, for example, providing them with knowledge about future periods of high energy demand or by enabling them to adapt their tariffs to customer consumption. Machine Learning techniques allow to predict future energy consumption on the basis of the customers' historical consumption and several other parameters. This article reviews some of the main machine learning models capable of predicting energy consumption, in our case study we use a specific set of data extracted from a two-year-period of a shoe store. Among the evaluated methods, Gradient Boosting has obtained an 86.3% success rate in predicting consumption.

show abstract

A Predictive Maintenance Model Using Recurrent Neural Networks

Cited by 33 publications

References 10 publications

A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance

A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance

Anomaly Detection and Classification in Predictive Maintenance Tasks with Zero Initial Training

A Review of the Main Machine Learning Methods for Predicting Residential Energy Consumption

Contact Info

Product

Resources

About