This paper presents a design of MANFIS (Multiple Adaptive Neuro Fuzzy Inference System) based sensor Fault Detection and Isolation (FDI) scheme for a three interacting tank system. Three pairs of dedicated observers are designed to estimate the three states of the system. The observers designed are fuzzy systems whose optimal membership functions and rule base are determined by neural networks. The difference between the estimated and measured value is called as residuals. Decision functions are determined from the residuals. These functions are compared to a threshold value, when the value of these functions exceed a particular threshold, the presence of fault is indicated. The FDI designed is implemented to detect sensor bias, abrupt sensor failure, sensor drift and sensor freeze types of sensor faults.

 

Published In : IJCSN Journal Volume 2, Issue 6

Date of Publication : 01 December 2013

Pages : 37 - 46

Figures : 15

Tables : 04

Publication Link : ijcsn.org/IJCSN-2013/2-6/IJCSN-2013-2-6-124.pdf

 

 

 

C. Amritha : Bachelor of Engineering(Electronics and Instrumentation), Masters (Electronics and Instrumentation). Currently working as Assistant professor in VelTech Technical University .Research interest includes nano_sensors and control engineering.

U. Sabura Banu : Masters,PhD. Currently working as an associate professor in B. S. Abdur Rehman University. Cuurent area of research includes fractional order controllers and biomedical instruments.

 

 

 

 

 

 

 

Bias fault

Sensor freeze

Sensor drift

Abrupt sensor failure

Fault detection and isolation

 

 

 

EACP provides better lifetime for nodes compared to SEP and CBRP. In addition to reducing energy dissipation, EACP successfully distributes energy-usage among the nodes in the network such that the nodes die randomly and at essentially the same rate. We have used only residual energy for head selection procedure. Presently, EACP consumes higher computational power due to reporting and cluster head selection. The second limitation is that the performances have been compared with standard SEP and CBRP algorithm. Performance of other sensor network head selection like PEGASIS, EEHC, TEEN etc. have not been considered. We only considered energy heterogeneity in future; we take computation heterogeneity as well as link heterogeneity and test the result how it improves the lifetime of system.

 

 

 

 

 

 

 

 

 

[1] Isermann, R., 1984. “Process Fault Detection based on Modeling and Estimation methods – A survey” ,Automatica,20(4): 387-404.

[2] C. Join, J.-C. Ponsart, D. Sauter, and D. Theilliol.” Nonlinear filter design for fault diagnosis: application to the three-tank system”. IEE Proceedings Control Theory and Applications, 152(1):55–64, 2005.

[3] Akhenak, M. Chadli, D. Maquin, and J. Ragot.” State estimation via multiple observer the three-tank system”. In 5th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, pages 1227–1232, Washington DC, USA, 2003.

[4] M. Rodrigues, D. Theilliol, M.A. Medina, and D. Sauter.” A fault detection and isolation scheme for industrial systems based on multiple operating models”. Control Engineering Practice, 16(2):225–239, 2008.

[5] D. Koenig, S. Nowakowski, and T. Cecchin. ”An original approach for actuator and component fault detection and isolation”. In 3rd IFAC Symposium on Fault Detection Supervision and Safety for Technical Processes, pages 95–105, Hull, UK, 1997.

[6] T. Marcu, M.H. Matcovschi, and P.M. Frank. “Neural observer-based approach to fault-tolerant control of a three-tank system”. In Proceedings of the European Control Conference, Karlsruhe, Germany, 1999. CD-Rom.

[7] J.M. Koscielny. “Application of fuzzy logic for fault isolation in a three-tank system”. In 14th IFAC World Congress, pages 73–78, Beijing, R.P. China, 1999.

[8] C.J. Lopez and R.J. Patton. “Takagi-sugeno fuzzy fault-tolerant control for a non-linear system”. In Proceedings of the IEEE Conference on Decision and Control, pages 4368–4373, Phoenix, Arizona, USA, 1999.C.J. Lopez and R.J. Patton. “Takagi-sugeno fuzzy fault-tolerant control for a non-linear system”. In Proceedings of the IEEE Conference on Decision and Control, pages 4368–4373, Phoenix, Arizona, USA, 1999.

[9] S.Nagarajan,J.Shanmugam,T.R.Rangaswamy,”MANFIS Observer Based Sensor Fault Detection and Identification in Interacting Level Process with NN Based Threshold Generator”, International Journal of Soft computing 3(5):344-354,2008.

[10] Patton, R.J., Uppal F.J., and Lopez-Toribio C.J.(2000).”Soft computing approaches to fault diagnosis for dynamic systems: a survey.” Proceedings of IFAC Symposium on Fault Detection,Supervision and Safety for Technical Processes 2000, Budapest, Hungary,vol. 1,303-315.