Data Quality in Hybrid Neuro-Fuzzy based Soft-Sensor Models An Experimental Study.docVIP

IAENG International Journal of Computer Science, 37:1, IJCS_37_1_08 ______________________________________________________________________________________ Data Quality in Hybrid Neuro-Fuzzy based Soft-Sensor Models: An Experimental Study S. Jassar, Student Member, IEEE, Z. Liao, Member, ASHRAE, L. Zhao, Senior Member, IEEE ? Neural Network Abstract— Soft sensor models 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 sensor models. 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 soft sensor model that is designed to estimate the average air temperature in distributed heating systems. The average air temperature is estimated based upon the available information, ? Fuzzy Logic ? Adaptive Neuro-Fuzzy Inference System (ANFIS) Recent research demonstrates the use of ANFIS in the development of a soft sensor model that estimated the average air temperature in a distributed heating system [2]. The estimated average air temperature allows for a closed-loop boiler control scheme (see the feedback loop through dashed line in Fig. 1), resulting in higher energy efficiency and improved comfort. In the current practice , due to the absence of economic and technically reliable method for measuring the overall comfort level in the buildings, the boilers are normally controlled to maintain the supply water temperature as a predefined level that normally does not reflect the heating demand of the buildings (see the solid feedback loop in Fig. 1) [3]. including