Structural Design Synthesis Research Articles

Discrete Structural Design Synthesis: A Hierarchical-Inspired Deep Reinforcement Learning Approach Considering Topological and Parametric Actions

Abstract Structural design synthesis considering discrete elements can be formulated as a sequential decision process solved using deep reinforcement learning, as shown in prior work. By modeling structural design synthesis as a Markov decision process (MDP), the states correspond to specific structural designs, the discrete actions correspond to specific design alterations, and the rewards are related to the improvement in the altered design’s performance with respect to the design objective and specified constraints. Here, the MDP action definition is extended by integrating parametric design grammars that further enable the design agent to not only alter a given structural design’s topology, but also its element parameters. In considering topological and parametric actions, both the dimensionality of the state and action space and the diversity of the action types available to the agent in each state significantly increase, making the overall MDP learning task more challenging. Hence, this paper also addresses discrete design synthesis problems with large state and action spaces by significantly extending the network architecture. Specifically, a hierarchical-inspired deep neural network architecture is developed to allow the agent to learn the type of action, topological or parametric, to apply, thus reducing the complexity of possible action choices in a given state. This extended framework is applied to the design synthesis of planar structures considering both discrete elements and cross-sectional areas, and it is observed to adeptly learn policies that synthesize high performing design solutions.

Design Synthesis of Structural Systems as a Markov Decision Process Solved With Deep Reinforcement Learning

Abstract Recently, it was demonstrated that the design synthesis of truss structures can be modeled as a Markov decision process (MDP) and solved using a tabular reinforcement learning method. In this setting, each state corresponds to a specific design configuration represented as a finite graph. However, when the structural design domain is relatively large, and depending on the constraints, the dimensionality of the state space becomes quite large rendering tabular reinforcement learning algorithms inefficient. Hence, in this study, the design synthesis MDP framework is significantly extended to solve structural design problems with large state spaces, by integrating deep reinforcement learning (DRL) into the general MDP framework. This is beneficial because with DRL, a deep neural network can be used to approximate the state-action value function, such that the network has much fewer parameters than the cardinality of the state space. This parameterization relies upon a problem relevant set of features and reward function. Thus, for this extended DRL design synthesis (DRLDS) framework, a compact set of features and a reward function are devised that are suitable for structural design problems where structural configurations are represented as finite graphs. Through the application of seven different structural design synthesis examples, the DRLDS framework is demonstrated to be capable of adeptly learning optimal policies that synthesize high, if not the highest, performing design solutions more frequently. The DRLDS framework does this with fewer finite element model evaluations than other considered alternative methods, further demonstrating the effectiveness of the developed set of features and reward function.

Structural Design Synthesis of Aircraft Engine Pylons at Certification Level of Detail

Structural optimization technology, as advanced as it has become, is still not used to fully automate the design of airframe components at a level of analysis detail that would be acceptable for certification by regulatory agencies. It is part of the development of certifiable structures but is still just a part, requiring significant manual labor invested by stress engineers working with empirical and semi-empirical methods for detail analysis periodically along the design path. The Paper presents an attempt to apply an integrated model-based systems engineering philosophy, fully automated, to the process of designing and certifying aircraft structures with a level of detail and scope of modeling that would meet certification requirements. The Paper presents comparisons, not available until now, between the cost and time required by current design methods practiced in industry and required for certification and by an integrated model-based design method in the case of a particular and important aerospace structural system: the engine pylon. Weight and the development costs of the resulting designs are compared. It allows for the first time an examination of the benefits of product weight performance of the integrated model-based approach as well as engineering effort in a highly realistic certification-driven structural design case. The Paper also describes technical modeling and design automation innovations required to build the practical certification level integrated design optimization platform used here.

Parametric, grammatical, and perceptual iterations on structural design synthesis

AbstractThis paper presents a computational design method to analyze and synthesize representation mechanisms in structural design. The role of shape grammar schemas in analyzing parametric and grammatical structural analysis is discussed, and a set of schema to generate novel structural topology is provided.

A general-purpose programming system for optimum structural design.

A new general-purpose computer program for optimum structural design synthesis is developed. Its principal components are, in general terms, optimizer and analyzer routines. The analyzer routine provides considerable flexibility and efficiency in the computational treatment of structural design problems. Special processor interfacing of the analyzer to the optimizer is composed in the system. By applying this programming system, an optimum design problem on the framed structure of the motor cycle to find the framed structure that will maximize the torsional rigidity subject to the constant volume, is studied.