This study presents an intelligent, digital-twin-driven device that leverages computer vision, machine learning (ML), and genetic algorithms as a cyber-physical system (CPS) to achieve high-quality products—benchmarks that companies must strive for in the current competitive milieu. For precision and quality manufacturing, companies have the opportunity to exploit the advantages of such digitalization to prevent errors in line with zero-defect strategies. The proposed design is for a flow-production environment, where feature data is retrieved contactlessly through a system comprising both hardware and software. The hardware module captures product images and stores them on an edge computing device, while the software extracts image-feature data, identifies patterns, and determines correlations between the feature data and production-process parameters using ML. Overall, the designed system has the potential to revolutionize product quality assurance in the era of Industry 4.0 by providing an efficient, reliable, and cost-effective solution, that is, also customizable for product manufacturing. The proposed model is further validated in an automotive component CPS factory. The system operates on a two-stage intelligence principle: (1) a real-time pass/fail classification based on surface-quality thresholds and (2) a root-cause analysis and prevention loop that uses a hybrid AI pipeline (GLCM feature extraction, KSOM validation, and GA optimization) to derive and feedback optimal process parameters to the production line. The novelty of the CPS solution lies in its integrated, low-cost AI, which drastically reduces the cost burden of the inspection vision system, making it suitable for manufacturing on varied scales, and hence, bestowing potential and possibility for widespread adoption.
Ghosh et al. (2026) studied this question.