Improved Multi-objective Genetic Algorithm Used to Optimizing Power Consumption of an Integrated System for Flexible Manufacturing

The efficient management of energy consumption is an essential concern in the manufacturing industry, with farreaching implications for both financial management and environmental sustainability. This paper proposes a new approach regarding the conceptualization and implementation of techniques for optimizing energy consumption in a production flow. In the first stage, an energy consumption monitoring system was developed, which is capable of collecting the energy consumption data for different production scenarios. The collected data represented the basis for evaluating and testing an optimization algorithm called the improved genetic algorithm (IGA), which is conceptually subordinated to the structure of the standard genetic algorithm (GA). The improved multi-objective genetic algorithm featured a high performance in terms of execution time and optimization of energy consumption. Thus, in the framework of the IGA algorithm, a layered approach to the optimization process was proposed by successively employing two genetic algorithms in the MATLAB programming environment. The first genetic algorithm identified the value of the minimum energy consumption, and the second GA adjusted the parameters of the first GA iteratively, in order to obtain the minimum consumption. Comparing the results obtained by employing the IGA algorithm with those obtained for the Non-dominated Sorting Genetic Algorithm (NSGA-II) in terms of real-time execution time, it can be noticed that a significant improvement was achieved from 25.7 s for the standard NSGA-II to 0.0527 for the IGA without any change in the performance of IGA with regard to the minimization of power consumption. By harnessing the inherent capabilities of the GA, the aim of this paper is to increase the energy efficiency for the analysed production system, thereby contributing both to cost savings and to reducing the environmental impact of manufacturing processes.