Data-Driven Set Based Concurrent Engineering Method for Multidisciplinary Design Optimization

In the development of multi-disciplinary systems, many experts in different discipline fields need to collaborate with each other to identify a feasible design where all multidisciplinary constraints are satisfied. This paper proposes a novel data-driven set-based concurrent engineering method for multidisciplinary design optimization problems by using machine learning techniques. The proposed set-based concurrent engineering method has two advantages in the concurrent engineering process. The first advantage is the decoupling ability of multidisciplinary design optimization problems. By introducing the probabilistic representation of multidisciplinary constraint functions, feasible regions of each discipline sub-problem can be decoupled by the rule of product. The second advantage is an efficient concurrent study to explore feasible regions. A batch sampling strategy is introduced to find feasible regions based on Bayesian Active Learning (BAL). In the batch BAL, Gaussian Process models of each multi-disciplinary constraint are trained. Based on the posterior distributions of trained Gaussian Process models, an acquisition functions that combine Probability of Feasibility and Entropy Search are evaluated. In order to generate new sampling points in and around feasible regions, optimization problems to maximize the acquisition function are solved by assuming that the constraint function is Lipschitz continuous. To show the effectiveness of the proposed method, a practical numerical example of a multi-disciplinary vehicle design problem is demonstrated.