A Hybrid Multi-Objective Evolutionary Algorithm-Based Semantic Foundation for Sustainable Distributed Manufacturing Systems

Rising energy prices, increasing maintenance costs, and strict environmental regimes have augmented the already existing pressure on contemporary manufacturing environment. Although decentralization of supply chain has led to rapid advancements in systems, finding an efficient supplier simultaneously from pool available ones as per customer requirement enhancing process planning scheduling functions are predominant approaches still needed be addressed. Therefore, this paper aims address issue by considering a set gear industries located across India case study. An integrated classifier-assisted evolutionary multi-objective approach is proposed for solving objectives makespan, consumption, increased service utilization rate, interoperability, reliability. To execute initially, text-mining-based supervised machine-learning models, namely Decision Tree, Naïve Bayes, Random Forest, Support Vector Machines (SVM) were adopted classification suppliers into task-specific suppliers. Following this, with identified input, problem was formulated Mixed-Integer Linear Programming (MILP) model. We then Hybrid Multi-Objective Moth Flame Optimization algorithm (HMFO) optimize functions. Numerical experiments been carried out 10 different instances, along comparison results Non-Dominated Sorting Genetic Algorithm (NSGA-II) illustrate feasibility approach.