Energy Estimation and Production Scheduling in Job Shop Using Machine Learning

Abstract

Energy efficiency has become a significant challenge for manufacturing companies. Although it is possible to improve efficiency by applying new and more efficient machines, decision makers tend to look for less expensive alternatives. Furthermore, the current reality of manufacturing companies, brought about by Industry 4.0, requires more flexibility of production systems and increase the complexity off machine rescheduling without compromising sustainable requirements. This study contributes to the subject by applying machine learning techniques in a job shop to reduce the makespan and estimate the total energy consumption. First, an artificial neural network (ANN) was trained to estimate the total electrical energy consumption in the system. A new input variable for the network was defined to assist in energy estimation. This variable is called the Priority Factor (PF) and helps capture the different patterns in the job shop. Second, as the ANN was trained, a Genetic Algorithm (GA) was used to reduce the makespan. Therefore, it is possible to reduce the makespan and know in advance the total electricity consumption in production. This solution supports a more sustainable manufacturing process, and is completely developed in a digital manufacturing environment.

Keywords

• Artificial neural network
• digital manufacturing
• energy estimation
• genetic algorithm
• industry 4.0
• job shop