Improving energy efficiency in electric drive systems is vital for sustainable manufacturing. Despite their potential, metaheuristic optimizations are rarely used in industrial virtual commissioning (VC) due to high computational demands and lack of reliability metrics. This paper presents a statistically validated genetic algorithm (GA) framework designed to bridge this gap, enabling high-speed deployment within practical VC workflows. The framework optimizes target speed, acceleration, and deceleration across three objectives: minimizing energy consumption, maximizing efficiency, and reducing losses. Comparative evaluations show that the GA achieves near-optimal solutions with a significant speedup, reducing optimization time from hours to minutes. Extensive statistical validation (100 independent runs) confirms high reliability and feasibility for multi-run industrial strategies. Furthermore, the study introduces a novel post hoc normalized analysis to quantify trade-offs between competing objectives. Validated on two physical testbeds (belt and strap conveyors), the methodology demonstrates cross-system generalizability and significant energy improvements. Implemented via IEC 61131-3 compliant programming, this eco-efficient automation system directly supports global sustainable development goals (SDGs 7 and 9) by enabling sustainable-by-design industrial automation.
Bysko et al. (Wed,) studied this question.