Recently, the China Communications Enterprises Association announced the results of the annual selection of typical practice cases for energy digital transformation. The case titled "Ultimate Energy Efficiency Improvement in Steel Enterprises Driven by Data" from Yonggang Group was successfully selected. This case addresses the high energy consumption issues in the steel production process through comprehensive governance and continuous improvement driven by data, achieving efficient energy utilization.

It is reported that the selection of this case focuses on key business content of energy digital transformation, such as computing power, innovation in information technology, green and low-carbon development, and integration with industrial internet. It evaluates from multiple dimensions including authenticity, innovativeness, typicality, effectiveness, and scalability, selecting typical cases to explore the construction achievements, innovative points, and promotion value of energy digital transformation. The aim is to sort out replicable and scalable experiences, play a leading role in demonstration, practice the concept of empowering with data, and promote the advancement of China's energy industry infrastructure and modernization of industrial chains.

Steel production is an energy-intensive process. Under the traditional model, due to the low efficiency of dynamic response in energy management, scheduling, and supervision, some residual heat and energy cannot be fully utilized, resulting in resource waste. To address this issue, Yonggang Steel introduced advanced industrial internet cloud platforms and big data analysis technologies, constructing an energy management system that covers the energy generation and consumption processes across various production lines. This system collects professional data from over ten thousand points, enabling comprehensive statistics and analysis of energy data.

By deeply analyzing energy data across dimensions such as time, processes, and energy medium systems, and integrating it with production plans, actual production performance, production process quality data, and equipment operation parameters, enterprises have established models based on big data and deep learning technologies. These models provide strong support for the full-process monitoring, scheduling, balance prediction, and optimization of production process parameters, driving the extreme energy efficiency potential across the entire process, all elements, all scenarios, and the entire value chain. Meanwhile, by collecting key operation parameters and production process parameters of energy-intensive equipment, real-time monitoring and early warning are achieved, effectively preventing energy waste caused by over-supply.

To more intuitively showcase the effectiveness of energy management, the enterprise has also established an energy performance dashboard. The dashboard dynamically monitors and displays key energy consumption, including process energy consumption, energy costs per ton of steel, electricity, gas, fresh water, carbon emissions, and other modules. Through daily, weekly, and monthly analysis functions, energy managers can promptly grasp the consumption of key energy resources such as water, electricity, and gas, and promptly conduct abnormal energy consumption analysis and improvement work.

Based on practical improvements, the enterprise has significantly reduced its annual comprehensive energy costs, cut carbon emissions by over 10,000 tons annually, created considerable economic value, and laid a solid foundation for sustainable development.