液压支架实时压力数据自动提取与动态分析方法研究  

A method for automatic extraction and dynamic analysis of real-time pressure data of hydraulic support

作　　者：卢国志[1] 胡斐 李鑫 姚春卉 LU Guozhi;HU Fei;LI Xin;YAO Chunhui(Shandong University of Science and Technology,Qingdao 266000,China;Shandong Zeming Energy Technology Co.,Ltd.,Taian 271000,China;The Fifth Exploration Team of Shandong Provincial Bureau of Coal Geology,Taian 271000,China)

机构地区：[1]山东科技大学能源与矿业工程学院,山东青岛266000 [2]山东泽明能源科技有限公司,山东泰安271000 [3]山东省煤炭地质局第五勘探队,山东泰安271000

出　　处：《煤炭工程》2023年第3期120-126,共7页Coal Engineering

摘　　要：针对目前液压支架电液控系统压力数据量大,干扰信息多从而造成仅仅依靠人工分析难以完成数据提取与动态分析的情况,设计了一种能够对支架压力数据自动提取循环周期、预测以及来压区域划分的方法。首先针对液压支架的工作特点,设计规则,提取正常工作状态下的压力数据作为循环数据,随后通过聚类的方法,结合每个支架压力数据划分出显著来压区域,最后采用LSTM算法对循环压力数据进行预测分析。通过实践证实了该方法的可行性,为矿山压力规律研究及安全开采提供思路。Aiming at the situation that the current electrohydraulic control system for hydraulic supports has a large amount of pressure data and a large amount of interference information,which makes it difficult to complete data extraction and dynamic analysis only relying on manual analysis,a method that can automatically extract cycle cycles,predict,and partition weighting regions from the support pressure data is designed.Firstly,according to the working characteristics of the hydraulic support,the rules are designed,and the pressure data under normal working conditions is extracted as the cycle data.Then,through the clustering method,combining with the pressure data of each support,the significant pressure area is divided.Finally,the LSTM algorithm is used to predict and analyze the cycle pressure data.The feasibility of this method is proved by practice,which provides ideas for the study of mine pressure law and safe mining.

关 键 词：支架压力 循环周期 来压预测 聚类分析 

分 类 号：TD355.4[矿业工程—矿井建设]