Nanjing Iron & Steel Co., Ltd. (NISCO) announced the commercial deployment of the world’s first steel model powered by swarm intelligence, the YuanYe Steel Large Model, across multiple scenarios at scale. Developed with Huawei and ecosystem partners, the model marks a shift in core steelmaking operations from reliance on human experience to data-driven intelligence, according to a press release distributed via Media OutReach Newswire. The implications extend beyond NISCO: the company reports annual cost reductions exceeding CNY100 million (approximately US$15 million), a new benchmark for digital transformation in the global steel and manufacturing industries.
Unlike general-purpose monolithic models, YuanYe fuses multiple AI models with metallurgical mechanism models to create a dual-drive, multi-model cluster architecture. This features a “right brain” for probabilistic computing and a “left brain” for precise decision-making. Powered by massive sensing data from millions of operational technology data points across 26 business domains, NISCO has achieved real-time digital twin mapping within its intelligent operations center. Now 100% of key equipment is connected and digitally controlled, and new product R&D cycles have been shortened by 50%. As of October 2026, NISCO had launched 25 business agents covering visual quality inspection, process optimization, production scheduling, and operations management.
The model has delivered breakthroughs in four core scenarios. In ironmaking, furnace temperature prediction and health diagnosis models allow operators to anticipate issues two hours in advance with over 90% accuracy, increasing prime-grade molten iron yield by over 10% while cutting unit energy consumption. In rolling, a rolling-force prediction model achieves millisecond-level response, narrowing thickness tolerance to ±0.2 mm and reducing thickness deviation to 1.9%, a world-leading standard. The rolling-force hit rate jumped from 88% to 98%, supporting steady annual output of over 2.5 million tons of steel plates and increasing overall yield rate by 0.5%.
In quality inspection, an integrated smart metallographic inspection system built on YuanYe has achieved full-process automation, raising inspection accuracy to over 95% and shortening per-sample inspection time from 10 minutes to 3–5 minutes, an 80% increase in overall inspection efficiency. In energy and environmental control, the S-Link Intelligent Agent for Gas and Flue Gas Sulfur Control integrates 602 process parameters and multi-modal capabilities to issue sulfur-risk warnings one hour in advance with over 95% accuracy. It slashes natural gas co-firing consumption by nearly 50%, reduces downtime caused by emission exceedance by over 25%, and delivers more than CNY600,000 (approximately US$90,000) in annual economic benefits.
Li Jinyan, General Manager of the Digital and Intelligent Integrated Development Department and Director of the AI Research Institute at NISCO, said digital and intelligent transformation is human-centric and aims to unleash human potential rather than replace people. NISCO has deployed over 300 AI models across its plants, alongside more than 1,000 low-code agents and lightweight applications built independently by frontline employees. Cheng Yongfu, Senior Industrial Solution Expert at Huawei’s Steel & Non-ferrous BU, noted that the real value of industrial AI is realized when it expands from single-point applications to comprehensive integration with production, operations, and management. Looking ahead, NISCO will team up with Huawei and other partners to explore dedicated data centers for smart steel plants, centered on an AI-native three-tier architecture and powered by YuanYe, aiming to provide a replicable benchmark for the global steel and manufacturing industries.
