3rd ICAI 2024

International Conference on Automotive Industry 2024

Mladá Boleslav, Czech Republic

dry battery assembly, battery formation and battery finishing. It should be noted that the mentioned operations are conducted using energy-consuming technologies such as; casting, tunnel drying, chamber seasoning, resistance welding, electric forming and other less energy-consuming technologies. The battery forming operation in particular presents difficulties due to the lack of linearity in power demand over time. The process experiences periodic and long-lasting increased power consumption, which, against the background of conducting dozens of formation processes simultaneously, makes accurate power planning by simple methods impossible. Therefore, in this study we would like to propose a simple solution to enable the prediction of active power at the micro-scale of an enterprise based on production schedules for future periods. Figure 1 shows a simplified diagram of the starter battery manufacturing process. The blocks of the diagram marked with a red outline represent processes that use copious amounts of energy.

Figure 1: Simplifide starter battery production diagram

Source: Own elaboration

2.1 Model and Data This subsection will present the model and the data used for the analysis. The model that will be described is based on a list of 32 variables, 6 of which are dependent variables. Among these variables, 9 are continuous variables, while the rest are binary variables. There are clearly distinguished groups of variables, which are divided according to their characteristics. An additional aspect that characterizes the data is the operation of two sources of electricity supplying distinct groups of equipment. During modeling, no attempt was made to split variables by power source. This is motivated by the desire to obtain a general model less sensitive to the limited number of variables and to the fact that it is possible to power individual devices within groups from alternate sources. In the context of electricity usage, the discussed variables play a crucial role in the analysis and optimization of energy consumption. The continuous variables representing energy-intensive devices with low power deviation over time can be important for monitoring and forecasting energy consumption over a longer time horizon in connection to high power demand over the year. By analyzing these variables, it is possible to identify trends in energy consumption and detect any abnormalities in the operation of these devices, enabling corrective or optimization actions to be taken. On the other hand, the binary variables characterizing devices with high deviation over time – working/not working, are significant in the context of operational management. Their work status can be crucial for planning and scheduling

80