Performance Comparison of Machine Learning Algorithms for Predictive Maintenance

Gęca, Jakub

doi:10.35784/iapgos.1834

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive maintenance solutions in the telecommunications industry have gained significant attention in recent years. Predictive maintenance involves the use of advanced analytics and machine learning techniques to predict equipment failures and proactively schedule maintenance activities, thereby reducing downtime and improving operational efficiency [5]. Machine learning has become of interest in the field of predictive maintenance.…”

Section: Related Workmentioning

confidence: 99%

Machine-Learning Based Prediction of Generator Runtime: A predictive maintenance solution for a telecommunications site

Muhammed,

Yinka-Banjo

2024

Preprint

View full text Add to dashboard Cite

The telecommunications industry has experienced significant growth and trans- formation in recent years, driven by technological advancements and the increasing demand for seamless connectivity. Maintaining the infrastructure that supports them becomes a critical challenge as communication networks expand and become more complex. There is a growing trend towards designing and implementing machine learning-based predictive maintenance solutions for telecommunications infrastructure to address this challenge. This study aims to develop and implement predictive models that can accurately predict the run- time of generators on telecommunication sites. This information is crucial for efficient planning and cost estimation purposes. The research collected data over three months and split it into training and testing datasets, with the training data accounting for 70% and the testing data accounting for 30%. Three models were used for prediction: the Ordinary Least Squares (OLS) method, the log- linear method, and the Vector Autoregression (VAR) model. The models were evaluated, and their fit was calculated. In this paper, a new model was proposed, namely the OLS model with negative clipping, to address the limitations of the OLS model. The results showed that the OLS model with negative clipping pro- vided the best prediction accuracy, with a root mean square error of 0.09. On the other hand, the Vector Autoregression model exhibited the least accuracy, with a root mean square error of 9.3385. These findings highlight the effectiveness of the proposed predictive maintenance solution in accurately predicting generator runtime on telecommunication sites.

show abstract

Section: Related Workmentioning

confidence: 99%

Machine-Learning Based Prediction of Generator Runtime: A predictive maintenance solution for a telecommunications site

Muhammed,

Yinka-Banjo

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Geca et al [15] which ones obtained better results, which are the reliable metrics and best practices to follow to obtain results in maintenance predictions. In a total of 34 articles analyzed, the most adopted models were Random Forest, Support Vector Machine, Artificial Neural Net-work and Decision Trees.…”

Section: State Of the Artmentioning

confidence: 99%

Fault Detection and Prediction for a Wood Chip Screw Conveyor

Henriques,

Farinha,

Mendes

2024

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

Equipment maintenance is a key aspect to maximize its availability. The present work focuses on data analysis of a screw conveyor of a biomass industry. The screw velocity and load were monitored and analysed, in order to detect and predict possible faults. A machine learning approach was used to detect anomalies, where different algorithms were tested with the data available, in order to train an anomaly classifier. The anomaly classifier was able to accurately identify most anomalies, based on historical data, temporal patterns and information of the maintenance interventions performed. The research carried out allowed to conclude that the Extra Trees Classifier algorithm achieved the best performance, among all algorithms tested, with 0.7974 F-score in the test set. The anomaly classifier has been shown to achieve remarkable accuracy in identifying anomalies. This research not only improves understanding of the performance of screw conveyors in biomass industries, but also highlights the practical utility of employing machine learning for proactive fault detection.

show abstract

Predicting Physical Disturbances in Organic Computing Systems Using Automated Machine Learning

Görlich-Bucher,

Heider,

Hähner

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Performance Comparison of Machine Learning Algorithms for Predictive Maintenance

Cited by 6 publications

References 22 publications

Machine-Learning Based Prediction of Generator Runtime: A predictive maintenance solution for a telecommunications site

Machine-Learning Based Prediction of Generator Runtime: A predictive maintenance solution for a telecommunications site

Fault Detection and Prediction for a Wood Chip Screw Conveyor

Predicting Physical Disturbances in Organic Computing Systems Using Automated Machine Learning

Contact Info

Product

Resources

About