摘要
提出利用大数据平台收集设备运行状态数据并通过大数据建模分析实现设备预测性维护的创新思路,设计了大数据采集和分析平台,并基于有噪声密度聚类的多源状态估计方法,用于综采工作面的乳化液泵站智能化维护。实验结果表明,以乳化液泵站历史数据进行的模型训练和分析达到了预期目标。
This paper proposes an innovative way of using PHM and big data technology to realize predictive maintenance of equipment,and designs a multi-source state estimation method based on noisy density clustering.The model training was carried out with the data of the emulsion pumping station.The results show that the model has achieved the expected goal.
出处
《信息技术与标准化》
2020年第5期71-75,共5页
Information Technology & Standardization
关键词
综采工作面
智能化维护
乳化液泵站
PHM
大数据
多源状态估计技术
fully mechanized working face
intelligent maintenance
emulsion pump station
PHM
big data
multivariate state estimation techniques