Nowadays, the main challenge in maintenance is to model an optimized stochastic maintenance strategy which consider the probabilistic failure behavior of complex system, dynamic nature to adapt changes, multi-objective optimization and the influence of human error in failure modeling. Previous studies on maintenance model lacks one of the above stated criteria. This research proposed a comprehensive framework that integrate failure modeling techniques such as Bayesian network and Petri net to model failure dependency, linguistic fuzzy assessment to incorporate the likelihood and impact of human errors in system failure. Correspondingly, the study provided a novel type of multi-objective optimization technique to simultaneously minimize cost, maximize reliability, improve maintainability, and enhance system performance using three maintenance actions (i.e.,. inspection, repair and replacement). Hence, the objective of this work is to propose a new formalism for planning and optimization of maintenance policies for air jet loom machine of textile industry, it commences by identifying the objectives and literature gaps. Furthermore, the study employed analytic hierarchy process to identify critical machines, fault tree analysis for failure modelling, Fusel-Vesely measure for ranking critical components, Bayesian network for diagnostic inference, Petri net for modelling system behavior and Genetic algorithms to generate a set of Pareto optimal solutions that represent trade-offs between the objectives. The result of the failure modelling analysis revealed that the machine currently exhibits a failure rate of 0.64, reliability of 0.53, and availability of 0.40. The result of Bayesian network shows the failure probability of the machine is 0.44 per day and the comparison reveals that failure analysis for the system using Bayesian network is more precise than using fault tree, which decrease the error of failure probability from 49% to 44% and have 10.2% of reduction. The proposed Pareto optimal results obtained from the Genetic algorithm provided decision-makers with valuable insights into maintenance planning and facilitated informed decision-making. The decision-makers' attitude, whether optimistic or pessimistic, plays a crucial role in selecting the appropriate strategy. Based on the results of the optimization model the study provided some informed decisions and recommendations for selecting appropriate maintenance strategies. The maintenance decision made in this way is more consistent in engineering practice.