Analysis and countermeasures of ten 'pain points' of intelligent coal mine
-
摘要: 基于我国煤矿智能化发展现状，提出了“一朵云+一张融合网+三级平台+N个应用模块”的智能化煤矿建设总体技术架构，分析了基于微服务架构的智能化综合管控平台构建思路，形成技术架构统一、功能模块有增减、硬件参数有差异的智能化煤矿统一采购、统一建设、综合运维模式。系统分析了我国煤矿智能化发展存在的认识与理念不统一、智能化发展不平衡、5G应用场景不成熟、“透明地质”技术保障支撑能力不足、采掘失衡与掘支失衡、对复杂条件适应性差、智能化巨系统兼容协同困难、井上下智能机器人发展不成熟、管理与人才储备不足、投入保障不足等10个方面的问题，从理论创新、技术创新、装备创新、管理模式创新、人才体系创新等方面指出了我国煤矿智能化建设需要开展的科技攻关方向，提出了构建智能绿色煤炭产业新体系的发展方向与措施。Abstract: Based on the current situation of the development of intelligent coal mines in China, the overall technical architecture of intelligent coal mine construction of 'one cloud + one converged network + three-level platform + N application modules' is proposed. The study analyzes the idea of building an intelligent integrated control platform based on micro-service architecture. The idea is to construct the intelligent coal mine platform of unified procurement, unified construction and integrated operation and maintenance model with unified technical architecture, functional modules increasing or decreasing and varied hardware parameters. This paper systematically analyzes ten pain points in the development of intelligent coal mines in China, including unified understanding and concepts, unbalanced development of intelligent mines, immature 5G application scenarios, insufficient technical support for 'transparent geology', unbalanced development and extraction and unbalanced extraction and support, poor adaptability to complex conditions, difficulties in compatibility and coordination of intelligent giant systems, immature development of intelligent robots above and below mines, insufficient management and talent reserves and insufficient investment guarantee. From the aspects of theoretical innovation, technological innovation, equipment innovation, management model innovation and talent system innovation, this study points out the direction of scientific and technological research that needs to be carried out for the intelligent construction of coal mines in China, and proposes the development direction and measures for building a new system of intelligent and green coal industry.
-
-
期刊类型引用(9)
1. 高翼飞，张晓航，畅明，葛帅帅，陈伟. 基于时空图卷积网络的瓦斯体积分数预警效果研究. 中国安全生产科学技术. 2024(01): 58-64 . 
百度学术
2. 张玲，杨超宇. 基于注意力机制的ResNet-LSTM煤矿瓦斯浓度预测模型. 煤炭技术. 2024(08): 208-213 . 百度学术
3. 朱艺轩. 基于机器学习的成都市空气质量预测. 信息记录材料. 2024(07): 160-162 . 百度学术
4. 殷建华，戴冠正，丁宁，辛晓钢，张谦，杜荣华. 基于STL-Informer-BiLSTM-XGB模型的供热负荷预测. 科学技术与工程. 2024(21): 8942-8949 . 百度学术
5. 胡青松，郑硕，李世银，孙彦景. 基于改进TCN-TimeGAN的矿井瓦斯浓度智能预测方法. 煤炭科学技术. 2024(S2): 321-330 . 百度学术
6. 李洪晨，张志强. 全国国民图书阅读率会超过60%吗？——基于ARIMA模型的全国国民阅读调查预测研究. 图书情报工作. 2023(09): 72-80 . 百度学术
7. 金秀章，陈佳政，李阳峰. 基于ARIMA-OSELM的火电厂SCR入口NO_x浓度预测建模研究. 计量学报. 2023(09): 1458-1466 . 百度学术
8. 曹梅，杨超宇. 基于小波的CNN-LSTM-Attention瓦斯预测模型研究. 中国安全生产科学技术. 2023(09): 69-75 . 百度学术
9. 曹梅，杨超宇. 基于双向长短期记忆网络的煤矿瓦斯浓度预测. 绥化学院学报. 2023(12): 156-160 . 百度学术
其他类型引用(11)
计量
- 文章访问数: 604
- HTML全文浏览量: 40
- PDF下载量: 121
- 被引次数: 20
下载:
