摘要
生产过程中的测量数据是许多技术工作的基础和出发点，它的可靠性和正确性直接影响着研究和决策工作的质量。但由于测量中不可避免的误差，测量值不能精确地符合生产过程中一些内在的物理和化学规律，如化学反应计量关系、物料平衡和热量平衡关系等等。这种误差又分为随机误差和显著误差两大类。数据校正的目的就是综合应用统计、辨识和优化技术，对实测数据进行调整，消除数据中包含的随机误差和显著误差，去掉明显错误的或不可靠的测量数据，从而提高测量数据的质量。
通过对以往数据协调和显著误差检测方法的分析研究，同时将理论研究同生产过程中的实际情况相结合，本文对以前的一些数据校正技术在实际情况中碰到的若干具体问题进行了剖析，并提出来相应的解决方案。具体包括以下几个方面：
1．通过大量的中外文献阅读，对数据协调及显著误差检测技术的发展和研究方向做了一个较为系统完整的阐述。
2．通过构造一个基于测量值比例关系的F统计量，并与约束残差统计量相结合，对稳态过程中出现的显著误差进行检测。这种方法即避免了基于测量残差的检测方法会将显著误差分散到各个测量值中去的缺陷；又避免了基于约束残差的检测方法只能对节点的平衡性进行判断，而无法确定显著误差的具体发生位置的缺陷。仿真研究结果表明：此方法对显著误差十分敏感，其各项性能指标均符合实际工业要求，具有较高的可信度和可应用性。
3．针对传统数据协调模型的缺陷，通过添加一组基于测量值比例关系上下限的约束条件，并利用罚函数的概念将物料平衡的约束条件以软约束的形式表示，由此建立了一种新的数据协调模型。改进后的数据协调模型只会对含有显著误差的测量值给予较大的协调量，而使得显著误差对其他测量值协调结果的影响较小，具有较高的鲁棒性。仿真试验证明：基于该改进模型的协调结果，可直接利用测量残差检测法进行显著误差检测，具有较高的错误检出率，且“虚警”的错误率较低。
4．详细叙述了上述改进数据协调模型在炼油厂连续催化重整装置中的实际应用情况。实际结果表明：本文所提出的数据协调和显著误差检测技术具有显著的应用价值。
Measurement data from industrial processes are the basis of much technical work, and data reliability and accuracy will directly affect the results of research and decision-making. However, the original measurement data often contain various errors, so the basic balanced relations, such as energy balance or conservation of mass, cannot be satisfied. Measurement errors can be mainly divided into two types: random error and gross error. Data rectification is a modern technique to improve the quality of measurement data, and its main purpose is to eliminate the random errors and gross errors included in original data by making use of applied statistics, identification, optimization and other techniques.
Base on the existing techniques of data reconciliation and gross error detection, this thesis presented some new problems from real industrial processes and proposed the corresponding schemes. The main contributions include:
1. Review the development and the state-of-the-art of the techniques in data reconciliation and gross error detection
2. For the existing test based on measurement residual, the main problem is that the data reconciliation procedure tends to spread the gross errors overall the measurements, which results in the detection failure. For the methods based on constraint residual, they can be used to only tell which node is imbalance but cannot identify where the gross error is. In order to avoid these problems, this thesis proposed a new test method. The new method combines an F-statistic with constraint residual statistic to detect gross errors in steady state processes. Simulation results show that the new method is very sensitive to the presence of gross errors and has a great probability of correctly finding one or several gross errors.
3. In order to avoid the drawback of the traditional data reconciliation model, an improved model is proposed in this thesis. Some new constraints for the ratio of measurement data are added to the new model, and the constraints of mass balance are transformed into soft constraints by using the method of penalty function. The data reconciliation procedure based on the improved model tends to make the measurements having gross errors get more modification than the others. Therefore, the new data reconciliation model is much more robust than the traditional. Besides, the results of the new
model can be used to detect gross errors directly. Simulation results show that the gross error detection based on the new model is very sensitive to the presence of gross errors.
4. The above improved model has been applied to practical data reconciliation for a continuous catalytic reforming unit in an oil refinery. Application results show that the improved data reconciliation model is very effective and can be widely used in industrial processes.
引文
Albuquerque, J.S. and L.T.Biegler (1996). Data reconciliation and gross error detection for dynamic systems. AIChE J., 42(10):2841-2856.
Almasy, G.A. and T.Sztano(1975). Checking and correction of measurements on the basis of linear system model. Problems of Control and Information Theory, 4(1):57-69.
Almasy, G.A., and R.S.H.Mah(1984). Estimation of measurement error variances from process data. Ind. Eng. Chem. Proc. Des. Dev, 23:779-804.
Amand, T., G.Heyen and B.Kalitventzeff(2001). Plant monitoring and fault detection synergy between data reconciliation and principal component analysis. Comp. Chem. Eng. 25:501-507.
Bagajewicz, M.J(1994). On the probability distribution and reconciliation of process plant data. Comp. Chem. Eng., 20:813-819.
Bagajewicz, M.J. and Qiyou Jiang(1997). Integral approach to plant linear dynamic reconciliation. AIChE J., 43:2546-2558.
Bagajewicz, M.J. and Qiyou Jiang(1998). Gross error modeling and detection in plant linear dynamic reconciliation. Comp. Chem. Eng., 22:1789-1809.
Bagajewicz, M.J. and M.C.Sanchez(1999). Design and upgrade of nonredundant and redundant linear sensor networks. AIChE J., 45(9):1927-1938.
Bagajewicz, M.J. and Qiyou Jiang(2000). Comparison of steady state and integral dynamic data reconciliation. Comp. Chem. Eng., 24:2367-2383.
Bakshi, B.R., P.Bansal and M.N.Nounou(1997). Multiscale rectification of random errors without fundamental process models. Comp. Chem. Eng., 21:1167-1172.
Bossen, B.S. et al. (1994). Simulation optimization and data reconciliation of industrial chemical processes. Chemical Engineering Research & Design, Part A, Transactions of the Institute of Chemical Engineers, 72(A3):376-381.
Bussani, G., M.Chiari, M.G.. Grottoli, S.Pierucci, T.Faravelli, G.Ricci and G.Gioventu (1995). Application of data reconciliation and optimization procedure to hydrogen plant. Computers Chem. Eng., 19, Suppl.:299-304.
Chen Xue-yu, R.W.Pike, T.A.Hertwig and J.R.Hopper(1998). Optimal implementation of on-line optimization. Comp. Chem. Eng., 22, Suppl., 435-442.
Chiari, M., G.Bussani, M.G.Grottoli and S.Pierucci(1997). On-line data reconciliation and optimization: refinery applications. Comp. Chem. Eng., 21, Suppl.:1185-1190
Crowe, C.M., A.Hrymak and Y.A.C.Garcia(1983). Reconciliation of process flow rates by matrix projection: Part Ⅰ. linear case. AIChE J., 29:881-888.
Crowe, C.M(1986). Reconciliation of process flow rates by matrix projection, Part Ⅱ, the nonlinear case. AIChE J., 32(4):616-623.
Crowe, C.M.(1989). Test of maximum power for detection of gross error in process constraints. AIChE J., 35(5):869-872.
Crowe, C.M.(1996). Formulation of linear data reconciliation using information theory. Chemical Engineering Science, 51(12), 3359-3366.
Darouache, M., J.Ragot, J.Fayolle, D.Maquin(1988). Data validation in large scale steady state linear systems. 12th World Congress on Scientific Computation IMACS, Paris, July 18-22.
Darouache, M. and M.Zasadzinski(1991). Data reconciliation in generalized linear dynamic systems. AIChE J., 37:193—201.
Dovi, V.G., A.D.Borghi(2001). Rectification of flow measurements in continuous processes subject to fluctuations. Chem. Engng. Sci., 56:2851-2857.
Du, YG, J.Thibault and D.Hodouin (1997). Data reconciliation for simulated flotation process. Artificial Intelligence in Engineering, 11,357-364
段东勇，陈丙珍，何小荣(1998)。稳态过程的数据校正和大误差侦破方法的集成研究。计算机与应用化学，15(5)：285—290。
Heyen, G., B.Vrielynck and B.Kalitventzeff(1998). Application of C.A.P.E. techniques to the revamping of existing electrical power plants, an example of interdisciplinary collaboration. Comp. Chem. Eng., 22, Suppl., 239-246.
Iordache, C., R.S.H.Mah and A.C.Tamhane(1985). Performance studies of the measurement test for detection of gross errors in process data. AIChE J., 31(7):1187-1201.
Jang, S., B.Joseph and H.Mukai(1986). Comparison of two approaches to on-line parameter and state estimation of nonlinear systems. Ind. Eng. Chem. Process Des. Dev. 25(3):809-813.
Ishida, Y. and Tokimasa(1996). Data reconciliation combined with data evaluation by sensor networks. Proceeding of the 35th Conference on Decision and Control, Kobe, Japan, December, 285-290.
Ishii, N., A.Iwata, and N.Suzumura(1979). Segmentation of non-stationary time
series. Int J Systems Sci, 10:883-894
Islam, K.A., G.H.Weiss and J.A.Romagnoli(1994). Nonlinear data reconciliation for an industrial pyrolysis reactor. Comp. Chem. Eng., 18, Suppl.:217-221.
Johnston, L.P.M. and M.A.Kramer(1995). Maximum likelihood data rectification: steady-state systems. AIChE J., 41(11),2415-2426.
Kao, C.S., A.C.Tamhane and R.S.H.Mah(1990). Gross error detection in serially correlated process data. Ind. Eng. Chem. Res., 29(6):1004-1012.
Kao, C.S. and R.S.H.Mah(1992a). A general prewhitening procedure for process and measurement noises. Chem. Eng. Comm., 118:49-57.
Kao, C.S., A.C.Tamhane and R.S.H.Mah(1992b). Gross error detection in serially correlated process data. Ind. Eng. Chem. Res., 31(1):254-262.
Karjala T.W., M.H.David and M.Risto (1992). Data rectification using recurrent(Elman) neural networks. International Joint Conference on Neural Networks, 2:901-906.
Karjala, T.W. and D.M.Himmelblau(1994). Dynamic data rectification by recurrent neural networks vs. traditional methods. AIChE J., 40:1865—1874.
Keller, J.Y., M.Darouach and G.Krzakala(1996). Fault detection of multiple biases or process leaks in linear steady state systems. Comp. Chem. Eng. 18:1001-1004.
Kelly, J.D.(1999). Reconciliation of process data using other projection matrices. Comp. Chem. Eng., 23:785-789.
Kim, I.W., M.J.Liebman and T.F.Edgar, (1990). Robust Error in Variable Estimation Using Nonlinear Programming Techniques. AIChE J., 36(7):985-93.
Kim, M.S.K., S.W.Park, and T.F.Edgar(1997). Robust data reconciliation and gross error detection: the modified MIMT using NLP. Comp. Chem. Eng. 21(7):775-782.
Knepper, J.C. and J.W.Gorman(1980). Statistical analysis of constrained data sets. AIChE J., 26(2):260-264
Kong Mingfang, CHEN Bingzhen, LI Bo(2000a). An integral approach to dynamic data rectification. Comp. Chem. Eng., 24:749-753.
孔明放，陈丙珍，李博(2000b)．数据协调与过失误差侦破的鲁棒估计同步方法．清华大学学报(自然科学版)，40(2)：46—50．
Kretsovalis A. and R.S.H.Mah(1987). Observability and redundancy classification in multicomponent process networks. AIChE J. 33:70-82.
Kuehn, D.R. and H.Davidson(1961). Computer control Ⅱ, mathematics of control.
Chem. Eng. Prog., 57(6):44-47.
Lee, S.J., M.H.Lee, K.S.Chang and C.Han(1998). Hierarchical on-line data reconciliation and optimization for an industrial utility plant. Comp. Chem. Eng., 22(Suppl.):247-254.
李博，陈丙珍，段东勇，孔明放(2000)。基于时间冗余度侦破过失误差的修正系数法。清华大学学报(自然科学版)，40(10)：65-69．
李红军，秦永胜，徐用懋(1997a)。数据校正在精馏塔系中的应用。化工自动化及仪表，24(1)：30-36。
李红军，秦永胜，徐用懋(1997b)．化工过程中的数据协调及显著误差检测．化工自动化和仪表，24(2)：25-32．
Liebman, M.J., T.F.Edgar and L.S.Lasdon(1992).Efficient data reconciliation and estimation for dynamic process using nonlinear programming techniques. Comp. Chem. Eng., 16:963-986.
林孔元，刘正光，郭爱民，方惠如(1996)。重油催化裂化稳态过程数据协调与检测。天津大学学报，29(4)：631-636。
Madron, T., V.Veverka and V.Venecek(1977). Statistical analysis of material balance of a chemical reactor. AIChE J., 23:482-486.
Madron, F. and V.Veverka(1992). Optimal selection of measuring points in complex plants by linear models. AIChE J., 38:227-236.
Mah, R.S.H. and A.C.Tamhane(1982). Detection of gross errors in process data. AIChE J., 28:828-830.
Tamhane A C, R.S.H.Mah(1985). Data reconciliation and gross error detection in chemical process networks. Technometrics, 27(4):409-422
Mayer, M., B.Koehret and M.Enjalbert(1993). Data reconciliation on multi-component network process. Comp. Chem. Eng., 17(8):807-817.
Mcbrayer, K.F., T.A.Soderstrom, T.F.Edgar and R.E.Young(1998). The application of nonlinear dynamic data reconciliation to plant data. Comp. Chem. Eng., 22(12):1907-1911.
Meert, K.(1998) A real-time recurrent learning network structure for data reconciliation. Artificial Intelligence in Engineering, 12(3):213-218.
Menendez, A., F.Biscarri and A.Gomez(1998). Balance equations estimation with bad measurements detection in a water supply net. Flow Measurement and Instrumentation, 9(1):193-198.
Mukai H. and S.S.Jang, S.S.(1986)., Comparison of two approaches to on-line parameter and state estimation of nonlinear systems. Ind. Eng. Chem. Process
Des. Dev., 25:809-819.
Mukherjee, J. and S.Narasimhan(1996). Leak detection in networks of pipelines by the generalized Likelihood ratio method. Ind. Eng. Chem. Res., 35:1886-1893
Murthy, A.K.S(1973). Material balance around a chemical reactor I. Ind. Eng. Chem. Proc. Des. Dev., 12(3):246-248.
Narasimhan, S., R.S.H.Mah and A.C.Tamhane(1986). A composite statistical test for detecting changes of steady states. AIChE J., 32(9):1409-1418.
Narasimhan, S., R.S.H.Mah and A.C.Tamhane(1987a). Detecting changes of steady states using the mathematical theory of evidence. AIChE J., 33(11):1930-1933.
Narasimhan, S. and R.S.H.Mah(1987b). Generalized likelihood ratio method for gross error identification. AIChE J., 33:1514-1521.
Narasimhan, S. and R.S.H.Mah(1988). Generalized likelihood ratios for gross error identification in dynamic processes. AIChE J., 34(8):1321-1330.
Narasimhan, S. and P.Harikumar(1993). A method to incorporate bounds in data reconciliation and gross error detection-Ⅰ The bounded data reconciliation problem. Comp. Chem. Eng., 17:1115—1120.
Nikolaos, G.V., C.T.Kiranoudis and M.K.Dimitrios(1999). Greek refinery uses data reconciliation to calibrate instruments. Oil and Gas Journal, 97(1):33-36.
Nogita, S.(1972). Statistical test and adjustment of process data. Industrial and Engineering Chemical Process Design and Development, 11:197-200.
Nounou, M.N. and B.R.Bakshi(1999). On-line multiscale filtering of random and gross errors without process models. AIChE J., 45(5):1041-1058.
Pierucci, S., M.Rovaglio, T.Faravelli and D.Stahl(1991). Crude unit by ORO package, on-line reconciliation & optimization. Computer-Oriented Process Engineering, Amsterdam, 159-164.
Placido, J. and L.V.Loureiro(1998). Industrial application for data reconciliation. Comp. Chem. Eng., 22, Suppl., 1035-1038.
Ragot, J., D.Maquin and D.Sauter(1992). Data validation using orthogonal filters. IEE Proceedings-D, 139(1):47-52.
Ramamurthi, Y., R.B.Sistu and B.W.Bequette(1998), Control-relevant dynamic data reconciliation and parameter estimation. Comp. Chem. Eng., 22(12):1907-1911.
Rao, R.R. and S.Narasimhan(1996). Comparison of techniques for data reconciliation of multi-component processes. Ind. Eng. Chem. Res., 35:
1362-1368.
Romagnoli, J.A. and G.Stephanopoulos(1980). On the rectification of measurement errors for complex chemical plants. Comp. Chem. Engng., 35:1067-1081.
Romagnoli, J.A. and G.Stephanopoulos(1981). Rectification of process measurement data in the presence of gross errors. Chemical Engineering Science, 36:1849-1863.
Rollins, D.K. and J.F.Davis(1992). Unbiased estimation of gross errors in process measurements. AIChE J., 38(4):563-572.
Rollins, D.K. and S.Devanathan(1993a). Unbiased estimation in dynamic data reconciliation. Proc. Sys. Eng., 39:1330-1334.
Rollins, D.K. and J.F.Davis(1993b). Gross error detection when variance-covariance matrices are unknown. AIChE J., 39(8):1335-1341.
Romagnoli, I. and G.Stephanpoulos(1980). On the rectification of measurement errors for complex chemical plants. Chem. Eng. Sci., 35:1067-1081.
Rosenberg, J., R.S.H.Mah and C.Iordache(1987). Evaluation of schemes for detecting and identifying gross errors in process data. Ind. Eng. Chem. Res., 26:555-564.
Sanchez, M., A.Bandoni and J.Romagnoli(1992). PLADAT: A package for process variable classification. Comp. Chem. Eng., 16(Suppl.):499-506.
Schraa, O.J. and C.M.Crowe(1996). The numerical solution of bilinear data reconciliation problem using unconstrained optimization methods. Comp. Chem. Eng., 20:727-732.
Schraa, O.J. and C.M.Crowe(1998). The numerical solution of bilinear data reconciliation problem using unconstrained optimization methods. Comp. Chem. Eng., 22(9):1215-1228.
Serth, R.W. and W.A.Heenan(1986). Gross error detection and data reconciliation in steam-metering systems. AIChE J., 32:733-741.
Serth, R.W. and W.A.Heenan(1987), Detection of gross errors in nonlinear constrained data: a case study. Chem. Eng. Comm., 51:89-104.
Simpson, D.E. and M.G.Everett(1988). Reducing the number of unknowns in constrained minimization problem-an application to material balances. Appl. Math. Modeling, 12:204-212.
Stanley, G.M. and R.S.H.Mah(1977). Estimation of flows and temperatures in process networks. AIChE J., 23:642-650.
Stanley, G.M. and R.s.H.Mah(1981). Observability and redundancy classification
in process networks: theorems and algorithms. Chem. Eng. Sci., 36(12):1941-1954.
Stephenson, G.R. and C.F.Shewchuk(1986). Reconciliation of process data with process simulation. AIChE J., 32(2):247-254.
Swartz, C.L.E., K.H.Pang and V.S.Verneuil(1990). Refinery implementation of a data reconciliation scheme. Proceedings of the ISA/89 International Coference, Philadelphia, PA, USA, 749-764.
Tamhane, A.C. (1982) A note on the use of residuals for detecting an outlier in linear regression. Biometrika, 69:488-489.
Tamhane, A.C. and R.S.H.Mah(1985). Data reconciliation and gross error detection in chemical process networks. Thchometrics, 27:409-422
Tamhane, A.C., C.Iordache and R.S.H.Mah(1988). Foundation of computer-aided process operation. Chemometrics and Intel. Lab. Sys., 4:33-40.
Tjoa, I.B. and L.T.Biegler(1991). Simultaneous strategies for data reconciliation and gross error detection of nonlinear systems. Comp. Chem. Eng., 15(10):679-690.
Tong, H.W. and C.M.Crowe(1995). Detection of gross errors in data reconciliation by principal component analysis. AIChE J., 41:1712.
Tong, H.W. and C.M.Crowe(1996). Detecting persistent gross errors by sequential analysis of principal components. Comp. Chem. Eng., 20:733-738.
Tyler, A.S., M.H.David and F.E.Thomas(2001). A mixed integer optimization approach for simultaneous data reconciliation and identification of measurement bias. Control Engineering Practice., 9:869-876.
Ungarala, S. and B.R.Bakshi(2000). A multiscale Bayesian and error-in-variables approach for linear dynamic data rectification. Comp. Chem. Eng., 24:445-451.
Vachhani, P., R.Rengaswamy, and V.Venkatasubramanian(2001). A framework for integrating diagnostic knowledge with nonlinear optimization for data reconciliation and parameter estimation in dynamic Sytems. Chem. Engg. Sci., 56(6):2133-2148
Vaclavek, V. (1969). Studies on system engineering-Ⅲ optimal choice of the balance measurements in complicated chemical engineering systems. Chem. Eng. Sci., 24:947-955.
Vaclavek, V. and M.Loucka(1976). Selection of measurements necessary to achieve multi-component mass balances in chemical plant. Chem. Eng. Sci., 31:1199-1205.
Veverka, V.(1992). A method of reconciliation of measured data with nonlinear constraints. Applied Mathematics and Computation, 49(1):141-176.
王希若，荣冈(2000)。高置信度的显著误差综合检验法。仪器仪表学报，21(2)：17—22。
Willsky, A.S., H.L.Jones(1976). A generalized likelihood ratio approach to the detection and estimation of jumps in linear systems. IEEE Trans. on Automatic Control, 21:108-112.
Wold, S, K.Esbensen, and K.P.Geladi(1987). Principal component analysis. Chemometrics and Intelligent Laboratory Systems, 2:37-52.
Yamamura, K., M.Nakajima and H.Matsuyama(1988). Detection of Gross errors in process data using mass and energy balances. International Chemical Engineering., 28(1):91-98.
Yang YouQi, RongBo Ten and LuiQun Jao(1995). A study of gross error detection and data reconciliation in process industries. Comp. Chem. Eng., 19:217-222.
Yoshimura, K., R.K.Konish and T.Soeda(1980). Identification of unknown parameters in linear discrete time system by a modified extended Kalman filter. Int. J.System Sci., 11:97-103
袁永根，李华生。过程系统测量数据校正技术，中国石化出版社，1996年11月第一版。
张亚乐，徐博文(1998)。原油蒸馏过程中的数据协调与操作优化。清华大学学报，自然科学版，38(3)：49-53。
赵豫红，顾钟文(1999)。原油常减压蒸馏塔稳态过程的数据协调与过失误差检测。炼油设计，29(11)：46—50。
周传光，姚书勤(1998)。中型合成氨装置在线数据校正与模拟优化软件的设计与实现。青岛化工学院学报，19(1)：70-74。
周传光，金思毅，赵文(2000)。常减压蒸馏装置在线数据校正与优化控制。青岛化工学院学报，21(2)：134-138。