Production System Efficiency Optimization Using Sensor Data, Machine Learning-based Simulation and Genetic Algorithms

In modern industries, there is a significant repository of sensor data, which contains large amount information. Unfortunately, this rich source information undervalued and underutilized, its full potential not fully exploited by day manufacturers. the Industry 4.0 era, exploiting these powerful datasets becoming critical for manufacturers’ survival competitiveness in age artificial intelligence. Cooperative mutual efforts between academia industrial sector to take advantage have reap extraordinary benefits business, economy society. Applying latest intelligence methods could increase production efficiencies reduce environmental impacts. view availability amounts data lack utilization, research proposes an solution that combines envelopment analysis (DEA), machine learning-based simulation genetic algorithms optimize efficiency systems through recommendations optimal model settings. First, DEA used identify efficient inefficient states system, input second step build learning makes predictions simulations scenarios. Then, algorithm scenario with corresponding The main contribution proposed unique combination models algorithms.