ABSTRACT 

Numerous problems in manufacturing systems can be expressed as decision-making processes that determine the best allocation of resources to tasks over time in concert with big data. Among optimization problems, scheduling of machines automatically and routing of robots for material handling are becoming more important in manufacturing systems. Such problems can be formulated as production scheduling or vehicle routing problems, which find the best schedules for a set of machines or vehicles to process a given set of jobs or transportation requests. To reduce human intervention and increase the level of automation, shorter computation times for scheduling and routing problems are required by learning both implicit and explicit knowledge from given solutions. Thus, further research on machine learning applications to those problems is a significant step towards increasing the possibilities and potentialities of field application. 

In order to create truly intelligent systems, new frameworks for scheduling and routing are proposed to utilize machine learning (ML) techniques. First, the dynamic single-machine scheduling problem for minimization of total weighted tardiness is addressed. For extraction of dispatching rules from existing or good schedules, a decision-tree-based approach called Generation of Rules Automatically with Feature construction and Tree-based learning (GRAFT) is designed. In addition to the single-machine scheduling problem, the flexible job-shop scheduling problem with release times for minimizing the total weighted tardiness is addressed. In order to address the problem efficiently, a random-forest-based approach called Random Forest for Obtaining Rules for Scheduling (RANFORS) is constructed. Finally, an optimisation problem for routing of autonomous robots are analysed by decomposing it into sub-problems. To solve the problems, a comprehensive framework for minimising total tardiness of transportation requests with consideration of conflicts between routes is proposed. Also, a new local search algorithm called COntextual-Bandit-based Adaptive Local search with Tree-based regression (COBALT) that incorporates the contextual bandit problem into operator selection is developed.