Cloud-Based Machine Learning Application for Predicting Energy Consumption in Automotive Spot Welding

Abstract

The energy consumption of production processes is increasingly becoming a concern for the industry, driven by the high cost of electricity, the growing concern for the environment and the greenhouse emissions. It is necessary to develop and improve energy efficiency systems, to reduce the ecological footprint and production costs. Thus, in this work, a system is developed capable of extracting and evaluating useful data regarding production metrics and outputs. With the extracted data, machine learning-based models were created to predict the expected energy consumption of an automotive spot welding, proving a clear insight into how the input values can contribute to the energy consumption of each product or machine, but also correlate the real values to the ideal ones and use this information to determine if some process is not working as intended. The method is demonstrated in real-world scenarios with robotic cells that meet Volkswagen and Ford standards. The results are promising, as models can accurately predict the expected consumption from the cells and allow managers to infer problems or optimize schedule decisions based on the energy consumption. Additionally, by the nature of the conceived architecture, there is room to expand and build additional systems upon the currently existing software.