An Intelligent Model for Self-compensation and Self-validation of Sensor Measurements

This article presents a hybrid system for self-compensation and self-validation of intelligent industrial instruments that combines a Neuro-Fuzzy model, based on the ANFIS architecture, capable of compensating errors caused by non-calibrated instruments, and a validation model based on Fuzzy Logic that provides the level of confidence of measurements. The proposed system indicates to the specialist when a new calibration must be performed. The hybrid system is tested with a differential pressure instrument, used in mining for level and pressure controls.

[1]  Gui Yun Tian,et al.  A Fieldbus-based intelligent sensor , 2000 .

[2]  Mohamed Abdelrahman,et al.  Hardware Implementation of Automated Sensor Self-Validation System for Cupola Furnaces , 2001, The 9th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'01).

[3]  Mohamed Abdelrahman,et al.  An intelligent signal validation system for a cupola furnace. I. Methodology , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[4]  Mohamed Abdelrahman,et al.  Fuzzy rules for automated sensor self-validation and confidence measure , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

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