No abstract

No abstract

<div class="section abstract"><div class="htmlview paragraph">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.</div></div>

In the early stage of dynamic system development which has a multi-disciplinary and hierarchical structure, system requirements need to be cascaded down to target values of each component so that engineers can collaborate efficiently and concurrently. The purpose of this paper is to propose a novel set-based concurrent engineering method for a dynamic system by using machine learning. In the practice of the target setting study for concurrent engineering, both hierarchical simulations between system and component level and a solution to solve inverse problems using the simulation are required. The proposed method composes of two machine learning methods that satisfy these requirements. The first one is physics-informed long short-term memory (PI-LSTM) which enhances the mechanical modeling of component behavior. By applying the proposed PI-LSTM to where mechanical modeling is difficult, the adaptive range of mechanical modeling can be expanded. The PI-LSTM surrogate the dynamic behavior of the component model and can be used inside the system-level simulation. The other one is Bayesian active learning (BAL) applied to inverse problems to solve feasible regions where all system requirements are satisfied. In the proposed BAL, Gaussian process models are trained from the system-level simulation, and an acquisition function is evaluated and maximized to generate new sampling candidates. The set-based design using BAL has an advantage in the decoupling ability of design problems because feasible regions of each discipline sub-problem can be studied concurrently. To show the effectiveness of the proposed method, a numerical example of a vehicle design problem which has a hierarchical structure is demonstrated.