Methodology of advanced data validation and reconciliation application in industrial thermal processes

Data validation and reconciliation is a technique that uses process information and mathematical methods in order to correct measurements in thermal industrial processes. On the need to measurements data validation and reconciliation (DVR) in order to use them for further calculations is indicated in the Association of German Engineers guidelines - VDI 2048. Moreover, the necessity of removing measurement errors, in the international standard for the integration of enterprise and control systems ISA-95 is recommended. The paper presents in a comprehensive manner methodology of advanced DVR application in computer systems supporting supervising of the industrial thermal processes. The necessity of preliminary measurement data validation has been indicated. The problems of detection and identification of measurements with a gross error were presented. A method that enables the detection of steady and unsteady states in thermal processes has been shown. The statistical tests for control the assumed accuracy of measurements after advanced DVR calculations have been displayed. A comprehensive analysis of the usefulness of these statistical tests used in the detection and identification of gross measurement errors in the advanced DVR method was carried out. The presented computational example illustrating the use of statistical methods for the detection and identification of gross measurement errors clearly shows that the use of these methods does not solve the problem in the case of advanced DVR tasks with the non-linear form of conditional equations. In this case, the additional methods presented in the article must be used. An overall methodology of applying the generalized advanced DVR method in distributed control systems of thermal processes in the industry was developed. Based on that, a block diagram of the worked-out methodology of the application mentioned DVR method in the industrial thermal processes has been elaborated. The developed overall methodology and aggregated block diagram enable an integrated approach to the generalized advanced DVR method in industrial thermal processes. (C) 2020 Published by Elsevier Ltd.