Fuzzy Clustering and Nonlinear Regression Imputation for Incomplete Data of Tunnel Boring Machine

doi:10.3901/JME.2023.12.028

Abstract

Abstract: The integrity and reliability of the in-situ data are the necessary prerequisites and key factors to promote the development of various industries in the era of industrial big data. As a key equipment of tunnel engineering, tunnel boring machine (TBM) has the characteristics of complex system structure and high relationship between the attributes, and it is a national tool for urban underground construction in national strategies such as “One Belt and One Road”. However, in the process of TBM operation, missing values frequently occurs in the acquisition of measured data of TBM due to various reasons, such as environmental interference, acquisition interruption, equipment failure, which seriously reduces the quality and reliability of data and affects the progress of the project. According to the characteristics of measured data of TBM, a high-precision missing value imputation algorithm based on fuzzy clustering and nonlinear regression is proposed. Firstly, the measured data under different working conditions are divided into several linear subsets by fuzzy clustering method. Then, a linear regression model is established for each subset, and an alternating learning strategy is used to solve the model parameters, which effectively mines the correlation between attributes. Experimental results show that the proposed method performs well both in clustering incomplete data and imputation missing data. The proposed data imputation algorithm can effectively solve the problem of data division and recovery, and provides a reliable foundation for the actual big data mining of shield machine.

Key words: tunnel boring machine, in-situ data, incomplete data imputation, fuzzy clustering, data modeling

CLC Number:

TP311
TH17

WANG Yitang, PANG Yong, ZHANG Liyong, SHI Yanjun, SUN Wei, SONG Xueguan. Fuzzy Clustering and Nonlinear Regression Imputation for Incomplete Data of Tunnel Boring Machine[J]. Journal of Mechanical Engineering, 2023, 59(12): 28-37.

References

[1] LAKSHMINARAYAN K,HARP S A,SAMAD T. Imputation of missing data in industrial databases[J]. Applied Intelligence,1999,11:259-275.
[2] 陈帅,赵明,郭栋,等. 基于SVD-KDR算法的工业监测数据插补技术[J]. 机械工程学报,2021,57(2):30-38. CHEN Shuai,ZHAO Ming,GUO Dong,et al. Missing data imputation using SVD-KDR algorithm in industrial monitoring data[J]. Journal of Mechanical Engineering,2021,57(2):30-38.
[3] ZHANG S. Nearest neighbor selection for iteratively KNN imputation[J]. Journal of Systems and Software,2012,85(11):2541-2552.
[4] TIAN Y,ZHANG K,LI J Y,et al. LSTM-based traffic flow prediction with missing data[J]. Neurocomputing,2018,318:297-305.
[5] MEEYAI S. Logistic regression with missing data:A comparison of handing methods,and effects of percent missing values[J]. Journal of Traffic and Logistics Engineering,2016,4(2):128-134.
[6] YANG K,LI J,WANG C. Missing values estimation in microarray data with partial least squares regression[C]//Computational Science-ICCS,2006,3992:662-669.
[7] DEMPSTER A P,LAIRD N M,RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of Royal Statistical Society. Series B,1977,39(1):1-22.
[8] GAJAWADA S,TOSHNIWAL D. Missing value imputation method based on clustering and nearest neighbors[J]. International Journal of Future Computer and Communication,2012,1(2):206-208.
[9] 郝胜轩,宋宏,周晓锋. 一种基于双聚类的缺失数据填补方法[J]. 计算机应用研究,2015,32(3):674-678. HAO Shengxuan,SONG Hong,ZHOU Xiaofeng. Novel approach for missing data imitation based on biclustering[J]. Application Research of Computers,2015,32(3):674-678.
[10] 马永军,汪睿,李亚军,等. 利用聚类分析和离群点检测的数据填补方法[J]. 计算机工程与设计,2019,48(15):90-95. MA Yongjun,WANG Rui,LI Yajun,et al. Data filling using cluster analysis and outlier detection[J]. Computer Engineering and Design,2019,48(15):90-95.
[11] DUNN J C. A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters[J]. Journal of Cybernetics,1973,3(3):32-57.
[12] MING L K,KIONG L C,SOONG L W. Autonomous and deterministic supervised fuzzy clustering with data imputation capabilities[J]. Applied Soft Computing,2011,11(1):1117-1125.
[13] AYDILEK I B,ARSLAN A. A hybrid method for imputation of missing values using optimized fuzzy c-means with support vector regression and a genetic algorithm[J]. Information Sciences,2013,233:25-35.
[14] TAKAGI T,SUGENO M. Fuzzy identification of systems and its applications to modeling and control[J]. IEEE Transactions on Systems Man and Cybernetics,1985,15(1):116-132.
[15] FANTUZZI C,ROVATTI R. On the approximation capabilities of the homogeneous Takagi-Sugeno model[C]//Proceedings of IEEE 5th International Fuzzy Systems. Los Angeles:New Orleans,1996,2:1067-1072.
[16] HATHAWAY A J,BEZDEK J C. Fuzzy c-means clustering of incomplete data[J]. IEEE Transactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2001,31(5):735-744.
[17] FILIPPONE M,CAMASTRA F,MASULLI F,et al. A survey of kernel and spectral methods for clustering[J]. Pattern Recognition,2008,41(1):176-190.
[18] 舒星,刘永刚,申江卫,等. 基于改进最小二乘支持向量机与Box-Cox变换的锂电子电池容量预测[J]. 机械工程学报,2021,57(14):118-128. SHU Xing,LIU Yonggang,SHEN Jiangwei,et al. Capacity prediction for lithium-ion batteries based on improved least squares support vector machine and Box-Cox transformation[J]. Journal of Mechanical Engineering,2021,57(14):118-128.
[19] 杨武,刘莉,周思达,等. 移动最小二乘的时变结构模态参数辨识[J]. 机械工程学报,2016,52(3):79-85. YANG Wu,LIU Li,ZHOU Sida,et al. Model parameter identification of time-varying structures via moving least square method[J]. Journal of Mechanical Engineering,2016,52(3):79-85.
[20] SI L C. Least square method that based on relative error[J]. Application of Statistics and Management,2003,22(4):36-45.
[21] PAL N R,BEZDEK J C. On cluster validity for the fuzzy c-means model[J]. IEEE Transactions on Fuzzy Systems,1995,3(3):370-379.
[22] WU K L. Analysis of parameter selections for fuzzy c-means[J]. Pattern Recognition,2012,45(1):407-415.
[23] SHI M,ZHANG L,SUN W,et al. A fuzzy c-means algorithm guided by attribute correlations and its application in the big data analysis of tunnel boring machine[J]. Knowledge Based Systems,2019,182:104859.