Real-time Analytics · Risk Management
Ordos needed a repeatable way to modernize hundreds of fragmented coal mines, but operators lacked shared standards, interoperable data, scalable AI infrastructure, and reusable models for safety, efficiency, and low-labor mining operations.
Reported impact
Ordos turned smart-mining AI into a reusable regional platform that improved recognition accuracy, cut model-adaptation effort, and created a standardized rollout path across demonstration mines and future enterprise participants.
Ordos City built a regional coal-industry internet platform on Huawei Cloud Stack using a hybrid "industry center cloud + mine edge cloud" architecture. The center platform standardizes industrial data collection, data fusion, AI services, and industry sharing for 96 mining work scenarios across tunneling, coal cutting, and main haulage, while three standardized edge-access patterns connect individual mine enterprises to the shared platform. Huawei's AI infrastructure and the Pangu mining large model provide visual and predictive capabilities, and a MaaS application marketplace links local solutions with the Huawei Cloud marketplace so mines can reuse AI products instead of building siloed systems. The operating loop follows "center training, edge inference, cloud-edge collaboration, learning while using, and continuous optimization," allowing pre-trained models to be adapted with small volumes of site data and rolled out across regional mines as a standardized smart-mining service.
Mine operational data is collected and fused in the center-cloud platform, where models are trained and managed, then pushed to edge clouds at participating mines for local inference. Outputs and reusable apps flow back through the shared marketplace and regional industrial internet platform for rapid rollout to new sites.
"Based on Huawei Cloud Stack, the program also built a one-stop MaaS application market and linked the local marketplace with the Huawei Cloud marketplace. (original: 基于华为云Stack，通过"三统一"架构（统一标准、统一架构、统一数据规范），集约化建设。同时构建一站式MaaS（模型即服务）的企业应用市场，打通本地应用市场与华为云商城的互联互通，共享生态，简化AI产品与解决方案的交易成本。)"
"Ordos used an "industry center cloud + mine edge cloud" architecture to build a coal industrial internet platform for 96 scenarios across tunneling, mining, and main transport. (original: 鄂尔多斯基于行业中心云+厂矿边缘云的架构，统一建设煤矿工业互联网平台，针对煤炭生产主要涉及掘进、采煤、主运等96个细分作业场景。)"
"The platform combines industrial data collection, data fusion, AI, and industry sharing, plus three standardized edge-access schemes that connect mines to the center platform for rapid replication. (original: 采用中心平台工业数采+数据融合+人工智能+行业共享方案，以及三套边缘矿企标准接入方案，打通矿企与中心平台，实现区域矿端的标准化快速复制。)"
"The platform has already launched 5 demonstration mines covering more than 40 AI scenarios and aims to serve more than 260 enterprises within 3 years while saving more than 90% of labeling work. (original: 落地5家示范矿，覆盖40+AI场景，未来3年将实现服务超过260家企业。... 节省超过90%的数据样本标注工作量。)"
"Using the Pangu mining large model, Ordos adopted a "center training, edge inference, cloud-edge collaboration, learning while using, continuous optimization" mechanism, lifting average recognition accuracy by more than 20%. (original: 依托盘古矿山大模型，构建"中心训练、边缘推理、云边协同、边用边学、持续优化"训练机制，平均识别精度提升20%以上。)"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample Modified · Oct 7, 2026 SensoRy AI SensoRy AI needed to convert complex wildfire sensor readings into clear, immediate guidance for responders because detecting a fire is only useful if firefighters and officials can understand the situation quickly… answers in seconds ChatGPT · ChatGPT Voice 
Microsoft Sample Sep 28, 2026 NASA NASA had decades of scientific and operational data spread across open repositories, academic sources, engineering reviews, safety analyses, and mission systems, making it difficult for scientists, planners, and flight… More than 500 employees signed up Earth Copilot · Hydrology Copilot · Microsoft Copilot 
Huawei Cloud Sample Archived · May 11, 2026 Yunnan Communications Investment and Construction Group Yunnan Jiaotou needed a transport-domain AI system that could handle complex mountain highway construction, maintenance, operations, and safety workflows, but no mature transportation large model, no high-quality domain… accuracy greater than 90% AI platform toolchain · Green Beautiful Corridor transportation large model · Huawei Cloud Stack 