Manli Huang

Quasi-Static Electromagnetic Forming (QSEF) technology utilizes stable magnetic fields generated by long-pulse flat-top currents to achieve non-contact, high-precision forming of large-scale integral aerospace components. To meet the immense energy demands of large-scale component forming, the drive system requires instantaneous power output capabilities at the Gigawatt level. Consequently, the precise regulation of ultra-high flat-top current waveforms becomes a critical challenge for ensuring forming quality. However, traditional meta-heuristic methods, such as Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO), exhibit limited adaptability and robustness when addressing strong geometric nonlinearities induced by workpiece deformation and the performance degradation of pulsed power modules. To address engineering challenges such as capacitor degradation, inductance drift, and module failures, this paper proposes a Staged Deep Reinforcement Learning (Staged-DQN) adaptive current control framework. This framework decouples the discharge scheduling into “heuristic rapid rise” and “DQN fine compensation” stages, adaptively optimizing triggering timing to suppress plateau oscillations and compensate for energy deficits caused by faults. Simulation results demonstrate that under typical high-energy operating conditions, the proposed method achieves superior tracking accuracy compared to traditional PSO in fault-free scenarios. In extreme scenarios involving 25 faulty modules, the Mean Absolute Percentage Error (MAPE) is maintained between 1.13% and 1.80%, significantly lower than the 2.65–3.52% of the baseline DQN. This study validates the effectiveness of the proposed method in enhancing waveform quality and system fault tolerance, offering a reliable intelligent control solution for large-scale electromagnetic manufacturing equipment.