This study proposes EvoDeep-Quality, a closed-loop hybrid framework integrating deep learning-based perception with multi-objective evolutionary optimization for adaptive quality control in smart manufacturing. The architecture combines a CNN-LSTM network for real-time spatiotemporal quality prediction with an NSGA-III-based optimization unit to balance conflicting objectives of quality, cost, and energy efficiency. A continuous adaptive learning loop addresses concept drift and process variability. Evaluated on an industrial-inspired synthetic dataset of textile blends (N = 5000) and validated on the real-world SECOM semiconductor manufacturing dataset, the framework demonstrates strong predictive capability (R2 = 0.947 ± 0.012, MAE = 0.035 ± 0.003) and significant manufacturing performance improvements, including a 23.5% quality enhancement and an 8.7–12.3% operational cost reduction compared to traditional and standalone AI models. Statistical significance testing (paired t-test, p < 0.01) confirms the superiority of the proposed approach. This deep-evolutionary framework advances proactive quality assurance and adaptive process control, offering a scalable solution aligned with Industry 4.0 and 5.0 paradigms.
Sorour et al. (Wed,) studied this question.