Zhao, Wenping | Search NASA

DOE OSTI2024

Deep reinforcement learning for optimal control of induction welding process

Optimizing induction welding (IW) process parameters for the application of joining thermoplastic composites is challenging as it requires achieving complex spatiotemporal thermal characteristics along the weld-line to obtain desired weld quality. We formulate an optimal control problem which captures these requirements and seeks to optimize the IW coil speed using a fast-acting dynamic IW process model. We develop a novel Deep Reinforcement Learning (DRL) framework to solve this computationally challenging control problem and demonstrate via simulation study that the learned DRL feedback control policy results in better spatiotemporal thermal characteristics as compared to the current state-of-the-art.

36 MATERIALS SCIENCE↗

NASA NTRS2018

Effectiveness of Surface Treatment Techniques for Composite Bonding with Different Contamination Levels

Various surface treatment techniques have been developed to promote adhesive bond performance for composite structural components in aerospace applications. The condition of the pre-bond surface is critical to achieving desirable bond quality. Contamination on bonding surfaces is well recognized as a major threat to ultimate bond performance. Variation in contamination level has brought additional challenges into manufacturing process control. High fidelity surface treatment techniques are required for effective removal of contaminants over a wide range of contamination levels. In this study, a common contaminant, i.e. silicone mold release, was introduced to pre-bond composite surfaces with different concentrations. Plasma and laser surface treatment techniques were performed and their effectiveness in restoring and enhancing desirable bond quality was investigated. Surface characterization techniques, including water contact angle goniometry, Fourier transform infrared spectroscopy and X-ray photoelectron spectroscopy, were conducted to assess the condition of contaminated surfaces and the improvement induced by plasma and laser surface treatments. Failure modes from a customized double cantilever beam test were investigated before and after surface treatments. Fundamental mechanisms of plasma and laser surface treatments on the composite bonding surfaces were also investigated.

Fang, Xiaomei↗