1.Institute of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
2.Beijing Research Institute of Precise Mechatronics and Controls, Beijing 100076, China
Abstract：For the delay problem in industrial process system, which lead to not soft sensor modeling in real-time or the lower accuracy of measurement, a modeling method for dynamic soft measurement based on a new algorithm (T-LSSVR) which combines the system delay (T) and least squares support vector regression (LSSVR) was presented.In order to achieve the best estimate of the auxiliary variables, the “static response delay” and “dynamic response delay” can be identified by cross-correlation function and the first order difference algorithm during modeling to the leading variables by the means of soft measurement to predict variables in the method.The soft measurement model was applied to a system with such double-delayed nature of a chemical company and the results show that its prediction achieved good results in terms of both dynamic and steady-state data.
［1］Cao Pengfei, Luo Xionglin. Modeling of soft sensor for chemical process［J］. CIESC Journal, 2013, 64(3): 788-800.
［2］Yu J J, Zhou C H. Soft-sensing techniques in process control［J］. Control Theory and Applications, 1996, 13(2): 137-144.
［3］Sheridan T B. Space teleoperation through time delay: review and prognosis［J］. Robotics and Automation, IEEE Transactions on, 1993, 9(5): 592-606.
［4］曹丽芳, 赵朋程, 陈颖,等.改进LMD和LS-SVM在小电流接地故障选线中的应用［J］.计量学报, 2016, 37(6):632-637.
Cao L F, Zhao P C , Chen Y, et al. Improved local mean decomposition and least squares support vector machines applied in fault selection for small current grounding system ［J］. Acta Metrologica Sinica, 2016, 37(6):632-637.
［5］Shu Yunxing. Research on fault diagnosis and quality prediction using support vector machines in cement burning system［D］.Wuhan: Wuhan University of Technology, 2008.
［6］杨景明, 郭秋辰, 孙浩,等.基于改进果蝇算法与最小二乘支持向量机的轧制力预测算法研究［J］.计量学报, 2016, 37(5):505-508.
Yang J M, Guo Q C, Sun H, et al. Research on the predictive algorithm of rolling force based on the improved fruit flies optimization algorithm with LSSVM［J］ . Acta Metrologica Sinica, 2016, 37(5):505-508.
［7］David M H. Accounts of experiences in the application of artificial neural networks in chemical engineering［J］.Industrial & Engineering Chemistry Research, 2008, 47(16): 5782-5796.
［8］Song Yunxia, Zhu Xuefeng. Control Methods and Application for the Process with Large Time Delay［J］.Control and Instruments in Chemical Industry, 2001, 28(4):9-15.
［9］Galicia H J, He Q P, Wang J. A reduced order soft sensor approach and its application to a continuous digester［J］. Journal of Process Control, 2011, 21(4): 489-500.
［10］Wu Yao, Luo Xionglin, Yuan Zhihong. Soft sensor modeling with dynamic interpolation neutral network for multirate system［J］. Chemical Industry and Engineering Progress, 2009, 28(8): 1323-1327.
［11］Wang Junyan, Huang Dexian. Time delay estimation of soft-sensor model based on hybrid differential evolution algorithm［J］. CIESC Journal, 2008, 59(8): 2058-2064.
［12］李成志, 邵富群, 阚哲.基于广义倒谱的相关算法在声学温度检测系统中的应用［J］.计量学报, 2013, 34(1): 22-26.
Li C Z, Shao F Q, Kan Z. Application in acoustic pyrometer system based on generalized cepstrum correlation algorithm［J］. Acta Metrologica Sinica, 2013, 34(1): 22-26.
［13］Ionescu C M, Hodrea R, De Keyser R. Variable time-delay estimation for anesthesia control during intensive care［J］.Biomedical Engineering, IEEE Transactions on, 2011, 58(2): 363-369.
［14］张靖悉, 胡勇, 李玥.QPSK调制多载波信号时延在线测量技术［J］.计量学报, 2016, 37(6):649-652.
Zhang J X, Hu Y, Li Y. A technology of on-line measurement of QPSK multicarrier signal delay［J］. Acta Metrologica Sinica, 2016, 37(6):649-652.
［15］Gedalyahu K, Eldar Y C. Time-delay estimation from low-rate samples: A union of subspaces approach［J］.Signal Processing, IEEE Transactions on, 2010, 58(6): 3017-3031.
2019, Vol. 40 
