基于PSO-LSTM和模糊控制的盾构机转速智能控制方法  

Intelligent Control Method of Shield Machine Rotating Speed Based on PSO-LSTM and Fuzzy Control

作　　者：柳世鸣 凌静秀 赵健 张浩 LIU Shiming;LING Jingxiu;ZHAO Jian;ZHANG Hao(The Key Laboratory of Intelligent Machining Technology and Equipment,Fujian University of Technology,Fuzhou 350118,China;Fujian University of Technology,Fuzhou 350118,China;CSCEC Strait Construction and Development Co,Ltd.,Fuzhou 350000,China)

机构地区：[1]福建理工大学福建省智能加工技术及装备重点实验室,福州350118 [2]福建理工大学机械与汽车工程学院,福州350118 [3]中建海峡建设发展有限公司,福州350000

出　　处：《机电技术》2024年第5期1-6,116,共7页Mechanical & Electrical Technology

基　　金：福建省自然科学基金资助项目(2022J01390)。

摘　　要：文章针对盾构隧道施工中土仓压力的控制问题,提出了一种基于PSO-LSTM深度神经网络和模糊控制的智能化控制方法。基于盾构现场数据,利用PSO-LSTM神经网络预测土仓压力,处理复杂的时序数据;利用WM算法从历史数据中提取规则并建立模糊规则库,实现了土仓压力值与螺旋机转速之间的模糊映射;最后设计了一套基于FOC控制算法的智能化控制装置,通过控制盾构操控室螺旋机转速旋钮的方式控制土仓压力。结果表明:平均绝对误差、均方误差分别为0.015 rpm和0.392%,决定系数R~2为0.95,预测精度和控制效果较高,为盾构隧道施工中的土仓压力智能化控制提供了新思路和技术手段。An intelligent control method based on PSO-LSTM deep neural network and fuzzy control is proposed for the con-trol of soil bin pressure in shield tunnel construction.Based on the shield tunnel field data,PSO-LSTM neural network is utilized to predict the soil bin pressure and process the complex time series data.The fuzzy mapping between the soil bin pressure value and the rotational speed of the screw machine is realized by using the WM algorithm to extract rules from historical data and estab-lish a fuzzy rule base.Finally,a set of intelligent control device based on FOC control algorithm was designed to control the soil bin pressure by controlling the rotational speed knob of the spiral machine in the shield manipulation room.The results show that the average absolute error,the mean square error is 0.015rpm and 0.392%,the R2 is 0.95,the prediction accuracy and control ef-fect are high,which provides a new idea and technical means for the intelligent control of soil bin pressure in shield tunnel con-struction.

关 键 词：PSO-LSTM 土仓压力 模糊控制 盾构机转速 智能控制 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] U455.43[自动化与计算机技术—控制科学与工程]