Paper Title
Monte Carlo Simulation, Particle Swarm Optimization Based on New Multivariate Bayesian Control Chart for Impeding Failure by Incorporating Simultaneously Two Types of Data: Key Quality Control Measurement And Condition Equipment Parameters: A Study Case Application Atoxmill Equipment

Abstract
Conditional-based Maintenance (CBM) modeling is seen as an important strategy for predicting failure and an effective maintenance decision making. Often new technologies introduce additional types of information that may not have been fully exploited. Maintenance within industry with new technologies needs to emphasis also on monitoring the condition of the production system and the quality of product. The herein proposed model presents a leading challenge to integrate new information into maintenance modeling. The primary objective of this paper is to develop a new conceptual integrated model for predicting failures of AtoxMill equipment. The model combines a Bayesian control chart and CBM, incorporating simultaneously two types of data: key quality control measurement and condition equipment parameters. This new model provides to decision-maker more accurate information on equipment health asset. A Monte Carlo simulation and a Particle swarm algorithm are used to optimize bound constrained continuous optimization problem in order to find the best value of upper control limit and interval monitoring that minimize the maintenance cost of the AtoxMill’ equipment. Keywords - Bayesian control chart, Condition-based Maintenance, Delay Time Concept, optimization and simulation.