基于改进DBSCAN-GMM的设备健康量化建模与应用
Quantitative Model and Application of Equipment Health State Data Based on Improved DBSCAN-GMM
曾宪利 1徐华志 2李波波2
作者信息
- 1. 江西都昌金鼎钨钼矿业有限公司
- 2. 江西理工大学机电工程学院
- 折叠
摘要
设备的健康状态对于现代工业的生产安全和生产效率有着重要的影响,为了准确感知设备的健康状态,实现设备状态从定性分析到定量分析的过渡,提出了一种带噪声基于密度的聚类算法(DBSCAN),通过与高斯混合模型(GMM)进行结合,前者实现数据的分类,后者实现数据的建模,建立了基于改进DBSCAN-GMM的设备健康状态数据量化模型,并结合现场棒磨设备历史运行数据进行了实例分析,验证了该模型的有效性.
Abstract
The health status of equipments has an important impact on the production safety and pro-duction efficiency of modern industry.In order to accurately perceive the health status of equipment and real-ize the transition from qualitative analysis to quantitative analysis of equipment status,a density-based spa-tial clustering of applications with noise(DBSCAN)is proposed and combined with Gaussian mixture model(GMM),the former realizes the classification of data,and the latter realizes the modeling of data.A quantita-tive model of equipment health status data based on improved DBSCAN-GMM is established,and an exam-ple analysis is carried out with the historical operation data of rod mill equipment,which verifies the effec-tiveness of the model.
关键词
设备健康状态/DBSCAN/高斯混合模型/数据感知模型Key words
health status of equipments/DBSCAN/Gaussian mixture model/data-aware mode引用本文复制引用
出版年
2024
NETL
NSTL
万方数据