Data Quality in ANFIS Based Soft Sensors

Soft sensor are used to infer the critical process variables that are otherwise difficult, if not impossible, to measure in broad range of engineering fields. Adaptive Neuro-Fuzzy Inference System (ANFIS) has been employed to develop successful ANFIS based inferential model that represents the dynamics of the targeted system. In addition to the structure of the model, the quality of the training as well as of the testing data also plays a crucial role in determining the performance of the soft sensor. This paper investigates the impact of data quality on the performance of an ANFIS based inferential model that is designed to estimate the average air temperature in distributed heating systems. The results of the two experiments are reported. The results show that the performance of ANFIS based sensor models is sensitive to the quality of data. The paper also discusses how to reduce the sensitivity by an improved mathematical algorithm.

[1]  F. R. Keller,et al.  Data Quality , 1990, Taxation and Labour Supply.

[2]  Robert J. Kauffman,et al.  Comparing the Modeling Performance of Regression and Neural Networks as Data Quality Varies: A Business Value Approach , 1993, J. Manag. Inf. Syst..

[3]  Qingzhong Liu,et al.  Predicting injection profiles using ANFIS , 2007, Inf. Sci..

[4]  Barbara D. Klein,et al.  Data Errors in Neural Network and Linear Regression Models: An Experimental Comparison , 1999, Data Qual..

[5]  Jun Wang,et al.  A feedforward neural network for multiple criteria decision making , 1992, Comput. Oper. Res..

[6]  Arthur L. Dexter,et al.  An experimental study on an inferential control scheme for optimising the control of boilers in multi-zone heating system , 2005 .

[7]  Lian Zhao,et al.  Adaptive neuro-fuzzy based inferential sensor model for estimating the average air temperature in space heating systems , 2009 .

[8]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[9]  Gary Montague,et al.  Soft-sensors for process estimation and inferential control , 1991 .

[10]  Arthur L. Dexter,et al.  A simplified physical model for estimating the average air temperature in multi-zone heating systems , 2004 .

[11]  Hannu Toivonen,et al.  TANE: An Efficient Algorithm for Discovering Functional and Approximate Dependencies , 1999, Comput. J..

[12]  Daniel E. O'Leary,et al.  The Impact of Data Accuracy on System Learning , 1993, J. Manag. Inf. Syst..