Real-time acquisition, pre-processing and mining of energy consumption data for forging workshop based on data-driven and IOT

The forging industry is a high-energy consumption and energy-intensive sector. Currently, the green level of forging workshop is not high, and sustainable production capacity is low. Aiming at the problems of the fuzzy energy-using mode of equipment in forging workshop and the not obvious green value information, we have studied real-time acquisition, pre-processing, and mining of energy consumption data. Firstly, a real-time data acquisition architecture based on IoT is designed and the energy consumption data is pre-processed. Secondly, the K-shape clustering algorithm and FP-growth association algorithm are used to mine the energy consumption data of six types of forging equipment. Finally, we develop an energy management system for the forging workshop, which improved the informatization level of the workshop. The results show that a considerable portion of the equipment involved in large component forging exhibits abnormal energy usage, with equipment like regenerative quenching furnaces having the greatest impact on other equipment and the total energy consumption of the workshop. According to the method proposed in this paper, more precise energy efficiency analysis can be achieved for large component forging workshops, providing a theoretical basis for formulating strategies to reduce energy consumption in the forging workshop.