Resilient AFE Drive Control using Neural Networks with Tracking Guarantees

TL;DR

This work proposes using reference-tracking Performance Boosting (rPB) to improve the resilience of standard AFE control to faults and concludes that this neural-network control framework provides a principled way to optimize transient performance while preserving the steady-state tracking properties of AFE-based drives.

Abstract

Industrial installations across several sectors have seen a dramatic increase in productivity, accuracy and efficiency over the last decade due to expanded utilization of medium voltage, variable speed power electronic converters to drive their processes. Specifically, active front-end (AFE) drives have become popular due to their ability to deliver power while maintaining safe electrical setpoints. However, under abnormal grid conditions such as phase loss, conventional AFE control may fail to enforce safety constraints, potentially leading to drive shutdown and significant financial losses. In this work, we propose using reference-tracking Performance Boosting (rPB) to improve the resilience of standard AFE control to faults. This neural-network control framework provides a principled way to optimize transient performance while preserving the steady-state tracking properties of AFE-based drives. By carefully shaping the input signals to the rPB controller, we ensure that it activates only during grid faults, leaving nominal operation unaffected. Simulation results show that the proposed approach successfully maintains the DC bus voltage and the grid current within safe limits during single-phase loss events.