Hybrid optimized control strategy for solid-state transformer-based electric locomotives integrating energy storage

Modern railway traction systems demand highly sophisticated power electronic architectures and robust control schemes that have the capability of delivering high efficiency, reliability and resilience, when operating in severe conditions. Here, electric locomotives using solid-state transformers (SST) in materials combined with hybrid energy storage systems (HESS) have become a possible solution, but at the same time, these systems produce significant nonlinear control and energy management challenges. This paper introduces a hybrid optimized control system to a SST-fed electric locomotive, a nonlinear controlled approach with intelligent metaheuristic optimization to improve the traction performance and energy consumption. Four control methods are systematically explored which include Proportional-Integral (PI), classical Sliding Mode Control (SMC), Integral Sliding Mode Control (ISMC), Super-Twisting Sliding Mode Control (STSMC), and Adaptive Neuro-Fuzzy Inference System (ANFIS) control methods to regulate the traction current where, dynamic changes in the load, regenerative braking transient, and grid-side disturbances occur. An Improved Whale Optimization Algorithm (IWOA) is implemented, which is used to optimally tune parameters to remove any manual gain tuning, and to provide fair performance comparison between heterogeneous controller structures. The proposed IWOA not only accelerates the convergence rate but also increases the diversity of solutions which makes it achieve better transient response and disturbance rejection. It has been shown through extensive MATLAB/Simulink simulations with enhanced controller-in-the-loop (CIL) validation that the IWOA-tuned STSMC is more robust, with up to 38% reduction in settling time and 45% suppression of current ripple are better than classical SMC and classical ISMC under the same operating conditions. ANFIS-based controller has a high adaptability to system nonlinearities and uncertainties and offers a smoother steady-state response and a higher tracking fidelity whereas PI controller offers a base line stability with limited robustness. The energy-related analysis also help to confirm an increased efficiency of the utilization of the HESS and a lower load on the storage elements during realistic conditions in locomotive duty cycles. In general, the suggested IWOA-optimized nonlinear control framework will allow deployable and energy-efficient operation of SST-based electric locomotives on a scalable and real-time basis. This work offers a viable and scalable design of next-generation electrification and energy storage integration of solid-state transformer-based electric locomotives, through the combination of advanced nonlinear control, intelligent optimization and hardware-aware verification.