This article is accepted for publication in IEEE Transactions on Control Systems Technology, 2014. The contents presented here are final as published in the journal. Optimal Control Approach for Turning Process Planning Optimization Ali Heydari, Student Member, IEEE, Robert G. Landers, Senior Member, IEEE, and S. N. Balakrishnan, Member, IEEE. Abstract This paper considers the optimal process planning of turning operations where the machining time is minimized subject to a variety of equipment and process constraints. A new approach is proposed, i.e., virtual dynamics are incorporated and the process planning problem is formulated as a time-optimal dynamic system control problem and optimal control tools are applied. The independent variable is changed from time to the instantaneous machined length to convert the time-optimal control problem to a finite-horizon control problem. Process and equipment constraints are incorporated using penalty terms in the cost function based on an approximation of the constrained variables. A recently developed method, called Finite-horizon State Dependent Riccati Equation, is utilized to solve the problem for the single tool turning process. Then, the developed method is extended and applied to parallel turning operations. Simulation studies are conducted to analyze the performance of the method for single tool and parallel tool turning operations, and the proposed method is shown to be very effective for solving such process planning problems. 1. Introduction Increasing manufacturing process productivity is typically conducted by optimizing production time, production cost, tool usage, etc. Minimization of the production cost was investigated in [1-3], and minimization of the production time was considered in [4,5]. In [6] both the production cost and time were considered as the performance criterion to be minimized. Different approaches have been used for solving the process planning optimization problem; e.g., nonlinear programming [1], dynamic programing [7], genetic algorithm [6,8], ant colony optimization [9], simulated annealing [6], artificial bee colony [10], and particle swarm optimization [2,4-6]. Process planning problems are very complex and not well-suited to traditional optimization techniques; hence, evolutionary algorithms such as genetic algorithms, simulated annealing, particle swarm optimization, ant colony optimization, and artificial bee colony have been utilized in many research studies since these powerful optimization tools