Sensor Drifting Fault Diagnosis Based RS and ANN

Abstract:

A strategy based on rough set (RS) and artificial neural network (ANN) is developed to detect and diagnose sensor drifting faults. The reduced information is used to develop classification rules and train the neural network to infer appropriate parameters. The differences between measured thermodynamic states and predicted states obtained from models for normal performance (residuals) are used as performance indices for sensor fault detection and diagnosis. Simultaneous temperature sensor drifting faults of the supply chilled water (SCW) and return chilled water (RCW) can be diagnosis successfully.

• Periodical: Advanced Materials Research (Volumes 204-210)
• Pages: 1848-1851
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.204-210.1848
• Online since: February 2011
• Authors: Zhi Jian Hou, Huan Xin Chen
• Keywords: Artificial Neural Network (ANN), Data Mining (DM), Rough Set (RS), Sensor Drifting Fault

References

[1] Boukhris A, Giuliani S, Mourot G. Rainfall-runoff multi-modeling for sensor fault diagnosis. Control Eng Pract , Vol. 9 (2001), p.659–671.

DOI: 10.1016/s0967-0661(01)00022-3

[2] Dunia R, Qin SJ. Joint diagnosis of process and sensor faults using principal component analysis. Control Eng Pract Vol. 6(1998), p.457–69.

DOI: 10.1016/s0967-0661(98)00027-6

[3] Wang S, Xiao F. AHU sensor fault diagnosis using principal component analysis method. Energy Build Vol. 36(2004), p.147–60.

DOI: 10.1016/j.enbuild.2003.10.002

[4] Pranatyasto TN, Qin SJ. Sensor validation and process fault diagnosis for FCC units under MPC feedback. Control Eng Pract Vol. 9(2001), pp.77-88.

DOI: 10.1016/s0967-0661(01)00055-7