Prediction of Equipment Effectiveness using Hybrid Moving Average-Adaptive Neuro Fuzzy Inference System (MA-ANFIS) for decision support in Bus Body Building Industry

• Autor(a) principal: SIVAKUMAR,A.
• Data de Publicação: 2022
• Outros Autores: SINGH,N. BAGATH, ARULKIRUBAKARAN,D., RAJ,P. PRAVEEN VIJAYA
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Anais da Academia Brasileira de Ciências (Online)
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0001-37652022000801703
• topic: adaptive neuro-fuzzy inference system (ANFIS); moving average (MA) model; hybrid extremal-micro genetic algorithm (Ex-µGA); predictive analysis; equipment effectiveness

Abstract Managers are driven to accomplish significantly higher levels of operational performance due to the difficulty of today’s dynamic production environment. Typically, the precision of production facilities and the efficiency of manufacturing systems are significant variables in productivity. Thus, predicting machine performance has become an inevitable challenge for production managers. However, the question of how managers can reliably assess the effectiveness of equipments for resource allocation remains unaddressed properly. This issue has received little attention in previous research, but it is important in today’s manufacturing environment. This study introduces a hybrid moving average - adaptive neuro-fuzzy inference system (MA-ANFIS) to predict the possible effectiveness of equipment. Three real-world problems are considered when developing and evaluating three distinct equipment effectiveness prediction models. The evaluation confirms that the hybrid MA-ANFIS model based on Gaussian membership function outperforms other developed models. This comprehensive solution is packaged as a decision support system. This aids production managers in evaluating the equipment effectiveness, and effectively improving equipment’s performance to reduce time and cost of bus body building.