Good Shandong | Coal blending ratio verification for coking reduced from 2-3 days to 1 minute! The world's first intelligent AI model for the energy industry

If a miner does not wear a safety helmet, the system will issue a warning until the worker wears the helmet before entering the mining area; The originally 3-day supervision process for anti impact and pressure relief construction was shortened to 10 minutes after using the AI large model.

If a miner does not wear a safety helmet, the system will issue a warning until the worker wears the helmet before entering the mining area; The originally 3-day supervision process for anti impact and pressure relief construction was shortened to 10 minutes after using the AI large model... This is the smart feature of the world's first AI large model for commercial use in the energy industry, which was learned by New Yellow River reporters at the 2023 multinational company and China themed exhibition site on October 10th.

This is the world's first commercial AI big model for the energy industry, jointly developed by Shandong Energy Group, Huawei, and Yunding Technology - the Pangu Mining Big Model.

As one of the representative exhibition areas of the Shandong section of this exhibition, the model of Shandong Energy Group attracted many exhibitors to watch.

Ren Xingshen, an AI development engineer at Shanneng Yunding Technology, told the New Yellow River reporter that currently, the model covers 21 scenarios in 9 majors, including coal mining, excavation, main transportation, auxiliary transportation, lifting, safety supervision, anti erosion, washing, and coking, solving the problem of difficult implementation of artificial intelligence in the mining field.

From the on-site demonstration of the intelligent application scenario of coking coal blending, the use of AI large models can improve the efficiency of coke quality prediction, achieve the optimal ratio, and ensure that the average prediction accuracy of coke quality is higher than 95%.

Based on tens of thousands of empirical data from the past, we continuously train AI large models to analyze the coal blending ratio in coking and improve the efficiency of coke quality prediction. Originally, it took 2-3 days to verify from a small coke oven, and with the use of an intelligent coal blending system in coking, coke quality can be accurately predicted within 1 minute. While improving efficiency, we optimize benefits, saving more than 3 yuan/ton compared to manual blending, "Ren Xingshen told New Yellow River reporters.

Reporter: Huang Min Photography: Huang Min Camera: Zhang Wenlong Editing: Zhang Wenlong Editor: Lv Bing Proofreading: Li Li

Disclaimer: The content of this article is sourced from the internet. The copyright of the text, images, and other materials belongs to the original author. The platform reprints the materials for the purpose of conveying more information. The content of the article is for reference and learning only, and should not be used for commercial purposes. If it infringes on your legitimate rights and interests, please contact us promptly and we will handle it as soon as possible! We respect copyright and are committed to protecting it. Thank you for sharing.(Email:[email protected])