ABSTRACT
The integration of advanced technologies in the manufacturing process led to the rise of Industry 4.0. The proposed system aims at the detection of image anomaly detection using deep learning techniques to enhance the quality control process. The optimization of the overall process is done using a genetic algorithm. They extract the information from complex patterns and visual data. Traditional quality control method lags in the proper identification of irregularities in intricate components that affects the quality. The proposed system helps to overcome the constraints through optimization algorithms. They provide accurate and reliable result analysis. These real-time analysis helps in the recognition of defects with a reduction of downtime with human intervention. This helps in reducing human errors to achieve a higher level of product quality. The integration of the genetic algorithm forms as a catalyst for fine-tuning the hyperparameters of the manufacturing process. Through iteratively refining the model parameters using the genetic algorithms, the system may adapt to the normal and anomalous conditions which helps in obtaining precision in defect detection. The accommodation of deep learning techniques provides predictive maintenance. They learn from historical data with real-time analysis for deterioration. Thus the proposed approach helps manufacturers to address various issues which helps to reduce the overall maintenance cost.
