Intelligent Control System for Low-Carbon Operation of Energy Intensive Equipment


Process industry in China mainly include raw material industry such as petrochemicals, steel, nonferrous metals, building materials, mining, and energy industry such as electric power. The scale of China's process industry is the largest in the world. It serves as an important basic support industry for China. However, its energy consumption accounts for more than half of China's total energy consumption. Improving energy efficiency is essential for reducing carbon dioxide emission intensity. Therefore, saving industrial electricity has become an important means to realize low-carbon industry. Energy intensive equipment are commonly used in the above-mentioned industries. Due to the comprehensive complexity of energy intensive equipment, it is difficult to use the existing modelling, control and optimization methods to realize its operational optimized control. Therefore, manual operational control methods are adopted in the energy intensive equipment. The manual operational control method is a key reason for the high energy consumption of energy intensive equipment. Realizing the operational optimized control of energy intensive equipment, and achieving energy saving and emission reduction are the keys to its low-carbon operation.


CPS provides new research ideas for realizing low-carbon operational control of energy intensive equipment. Industrial Artificial Intelligence (AI) provides a new technical foundation for realizing low-carbon operational control of energy intensive equipment. With the development of mobile internet represented by 5G, edge computing, cloud computing and cloud platform software, the Industrial Internet has been born. Industrial Internet creates conditions for obtaining industrial big data. The end-edge-cloud collaboration technology of Industrial Internet creates conditions for the realization of big data-driven industrial AI algorithms. The synergy of industrial AI and Industrial Internet creates conditions for realization of intelligent control for low-carbon operation of energy intensive equipment. Based on the analysis of the operational control behavior of operation experts of energy intensive equipment, this talk proposes an intelligent control method for low-carbon operation by combining mechanism analysis with deep learning, control and optimization with prediction. The method makes the energy consumption per ton as small as possible within the target range. It consists of setpoint control, self-optimized tuning and tracking control. An intelligent control system for low-carbon operation is developed by adopting end-edge-cloud collaboration technology of Industrial Internet. The system is successfully applied to the fused magnesium furnace and achieves remarkable results in reducing carbon emissions.