摘要
针对煤矿气体泄漏事故频发、监测难度大、环境参数界定模糊、可靠性差等问题,提出了基于DBN模型的多传感器数据融合的煤矿事故预警系统设计。系统利用NB-IOT技术设计了矿井环境信息采集节点,实时采集矿井内氧气、二氧化碳、烷类气体浓度,通过深度信念网络对多个传感器数据进行融合,提取特征并分类,直接得到矿井内环境状态,有效降低了环境参数模糊造成的判断失误。实验表明,系统能够对矿井状态进行准确判断,对煤矿安全事故预警有较大的参考价值。
In view of the frequent occurrence of gas leakage accidents in coal mines, the difficulty of monitoring, fuzzy definition of environmental parameters, poor reliability and other issues, a design of multi-sensor data fusion based on DBN model for coal mine accident early warning system is proposed.The system uses NB-IOT technology to design the mine environment information collection module, real-time collection of oxygen, carbon dioxide, alkane gas concentration in the mine, through the depth belief network to fuse multiple sensor data, through the extraction of features and classification, directly get the mine environment state, effectively reduce the judgment error caused by the fuzzy environmental parameters. The experiment shows that the system can accurately judge the state of the coal mine and has a great reference value for the early warning of coal mine safety accidents.
作者
傅彬
FU Bin(Shaoxing Vocational and Technical College,Shaoxing 312000,China)
出处
《煤炭技术》
CAS
北大核心
2021年第4期133-136,共4页
Coal Technology
基金
浙江省高等教育十三五第一批教学改革研究项目(jg20180706)。
