Safe optimization with grey-box information: Application to composites autoclave processing improvement on the fly

In the manufacture of aerospace-grade composites in the autoclave, the curing process plays a crucial role as it directly governs the quality of the final parts. Maintaining the part’s thermal history, namely, thermal lag and exotherm, under predetermined thresholds as well as achieving a uniform degree of cure throughout the material thickness can result in the desired product quality. Currently, for many such manufacturing applications, the optimization of the curing process (often conducted via trial-and-error) is highly expensive and time-consuming and occasionally leads to failed products. In order to address this problem, in this paper, a Safe Optimization approach is proposed. The suggested framework allows for the on-the-fly optimization of curing process configurations while avoiding interruptions typically encountered during trials. In other words, the proposed algorithm is capable of consistently yielding “pass” products as it navigates toward the optimal configuration. In particular, we introduce a hybrid optimization framework that combines a genetic algorithm, namely NSGA-II, using inexpressive stimulation (white-box) data for finding a safe initial starting point and then, the (black-box) safe logarithmic barrier method for enhancing the product quality presumably using experimental data on-the-fly. Herein, however, as proof of concept, we employ synthetic data throughout the framework in a case study.