NISCO and Huawei deploy world's first swarm-intelligence steel model at scale

NISCO has adopted Huawei’s Ascend, Kunpeng, Huawei Cloud Stack and Pangu models as part of its digital and intelligent foundation. YuanYe innovatively fuses multiple AI models with metallurgical mechanism models in a dual-drive architecture, described as featuring a “right brain” for probabilistic computing and a “left brain” for precise and scientific decision-making. Data from millions of operational technology points across 26 business domains is aggregated, and NISCO has achieved real-time digital twin mapping within its intelligent operations center, laying data and scenario foundations for YuanYe. This enables the steelmaking process to be visible, precisely controlled and intelligently assessed.

According to the announcement, 100 per cent of NISCO’s key equipment is now connected and digitally controlled, and by October 2026 the company had launched 25 business agents covering areas from visual quality inspection to production scheduling. In ironmaking, the model uses blast furnace sensor data and metallurgical analysis to perform real-time dynamic simulations; assisted by prediction and diagnosis models, operators can predict temperatures and identify issues two hours in advance with over 90 per cent accuracy. This shifts operations from reactive remediation to proactive control, increasing prime-grade molten iron yield by over 10 per cent while cutting unit energy consumption. In steel rolling, YuanYe’s rolling-force prediction model achieves millisecond-level response, narrowing thickness tolerance to ±0.2 mm and raising the rolling-force hit rate from 88 per cent to 98 per cent. For quality inspection, a smart metallographic inspection system built on YuanYe doubled inspection efficiency, shortening per-sample time from 10 minutes to 3–5 minutes and raising accuracy above 95 per cent. In energy and environmental control, a S-Link Intelligent Agent for Gas and Flue Gas Sulfur Control integrated 602 process parameters, issued precise sulfur-risk warnings one hour in advance and achieved sulfur prediction accuracy of over 95 per cent. It also slashed natural gas co-firing consumption by nearly 50 per cent, delivering more than CNY600,000 (approximately US$90,000) in annual economic benefits.

Li Jinyan, General Manager of NISCO’s Digital and Intelligent Integrated Development Department and Director of its AI Research Institute, said: "Digital and intelligent transformation is inherently human-centric. Its purpose is not to replace people, but to unleash human potential. Our goal is to lift employees out of the endless sea of data, empowering them to direct their creative energy toward work of higher value." To date, NISCO has deployed over 300 AI models alongside more than 1,000 low-code agents built by frontline employees. Cheng Yongfu, Senior Industrial Solution Expert at Huawei’s Steel and Non-ferrous Business Unit, said: "The real value of industrial AI can only be realized when it expands from single-point applications to comprehensive integration with production, operations, and management, which can unlock sustained, scalable empowerment."

Looking ahead, NISCO and Huawei plan to explore dedicated data centres for smart steel plants, centred on an AI-native three-tier architecture. NISCO aims to provide a replicable and scalable benchmark for digital and intelligent transformation of the global steel and manufacturing industries.

This article was supplied by Huawei.