Application of a Predictive Model to Reduce Unplanned Downtime in Automotive Industry Production Processes: A Sustainability Perspective DOI Open Access

Juan Cristian Oliveira Ojeda,

João Gonçalves Borsato de Moraes,

Clídio Hort Filho

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(9), P. 3926 - 3926

Published: April 27, 2025

The automotive industry constantly seeks intelligent technologies to increase competitiveness, reduce costs, and minimize waste, in line with the advancements of Industry 4.0. This study aims implement analyze a predictive model based on machine learning within industry, validating its capability impact unplanned downtime. implementation process involved identifying central problem root causes using quality tools, prioritizing equipment through Analytic Hierarchy Process (AHP), selecting critical failure modes Risk Priority Number (RPN) derived from Failure Mode Effects Analysis (PFMEA). Predictive algorithms were implemented select best-performing error metrics. Data collected, transformed, cleaned for preparation training. Among five models trained, Random Forest demonstrated highest accuracy. was subsequently validated real data, achieving an average accuracy 80% predicting cycles. results indicate that can effectively contribute reducing financial caused by downtime, enabling anticipation preventive actions model’s predictions. highlights importance multidisciplinary approaches Production Engineering, emphasizing integration techniques as promising approach efficient maintenance production management reinforcing feasibility effectiveness contributing sustainability.

Language: Английский

Application of a Predictive Model to Reduce Unplanned Downtime in Automotive Industry Production Processes: A Sustainability Perspective DOI Open Access

Juan Cristian Oliveira Ojeda,

João Gonçalves Borsato de Moraes,

Clídio Hort Filho

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(9), P. 3926 - 3926

Published: April 27, 2025

The automotive industry constantly seeks intelligent technologies to increase competitiveness, reduce costs, and minimize waste, in line with the advancements of Industry 4.0. This study aims implement analyze a predictive model based on machine learning within industry, validating its capability impact unplanned downtime. implementation process involved identifying central problem root causes using quality tools, prioritizing equipment through Analytic Hierarchy Process (AHP), selecting critical failure modes Risk Priority Number (RPN) derived from Failure Mode Effects Analysis (PFMEA). Predictive algorithms were implemented select best-performing error metrics. Data collected, transformed, cleaned for preparation training. Among five models trained, Random Forest demonstrated highest accuracy. was subsequently validated real data, achieving an average accuracy 80% predicting cycles. results indicate that can effectively contribute reducing financial caused by downtime, enabling anticipation preventive actions model’s predictions. highlights importance multidisciplinary approaches Production Engineering, emphasizing integration techniques as promising approach efficient maintenance production management reinforcing feasibility effectiveness contributing sustainability.

Language: Английский

Citations

0