Neuro-fuzzy modelling is a promising method to deal with large-scale and nonlinear dynamic systems. It can avoid the physical modelling and only deal with the measurements of inputs and outputs of the system. Generally, neuro-fuzzy modelling is composed of the selection of model structure, parameters and model validation. The quality of the model is largely dependent on the quality of the training data. How to select the input and output variables in the model is quite important. In this paper, not only the selection of sensor input in the model is discussed but faults can be diagnosed with the developed model. Sensor measurement plays a key role in system monitoring. Once a sensor fault occurs in the system, it should be detected immediately in case major catastrophe happens. A cooling coil subsystem in HVAC is used as a case study for input parameter selection in the model and fault diagnosis.
WuY. and DexterA.L., Modelling Capabilities of Fuzzy Relational Models. The 12th IEEE International Conference on Fuzzy Systems, 1, 2003, pp, 430–435.
2.
LaukonenE.G. and PassinoK.M., Training fuzzy systems to perform estimation and identification, Engineering Applications of Artificial Intelligence8(5) (1995), 499–514.
3.
ZhouY. and DexterA., Off-line identification of nonlinear, dynamic systems using a neuro-fuzzy modelling technique, Fuzzy Sets and Systems225 (2013), 74–92.
4.
SingC.H. and PostlethwaiteB., Identification of Fuzzy Relational Models from unevenly distributed data using optimization methods, Chemical Engineering Research and Design, Transactions of the Institute of Chemical Engineers, Part A78(4) (2000), 522–527.
5.
BraunM.W., RiveraD.E. and StenmanA., A ‘model-on-demand’ identification methodology for non-linear process systems, International Journal of Control74(18) (2001), 1708–1717.
6.
BuragohainM. and MahantaC., A novel approach for ANFIS modelling based on full factorial design, Applied Soft Computing Journal8(1) (2008), 609–625.
7.
TanA.H. and GodfreyK.R., An improved routine for designing multi-level multi-harmonic signals. Proc UKACC Int Conf Control, University of Bath, UK, ID-027, 2004.
8.
HongX. and HarrisC.J., Variable selection algorithm for the construction of MIMO operating point dependent neurofuzzy networks, IEEE Transactions on Fuzzy Systems9(1) (2001), 88–101.
9.
LeeM.F.R., StanleyK., et al., Implementation of sensor selection and fusion using fuzzy logic, Vancouver, BC, Canada, 1, 2001, pp. 328–333.
10.
WangL., Kannatey-AsibuE.Jr., et al., A method for sensor selection in reconfigurable process monitoring, Journal of Manufacturing Science and Engineering, Transactions of the ASME125(1) (2003), 95–99.
11.
MuellerP.C. and WeberH.I., Analysis and optimization of certain qualities of controllability and observability for linear dynamical systems, Automatica8(3) (1972), 237–246.
12.
BalasG.J. and YoungP.M., Sensor selection via closed-loop control objectives, IEEE Transactions on Control Systems Technology7(6) (1999), 692–705.
13.
KuwaharaM. and KawajiS., Some Remarks on Optimal Sensor Selection Problem. SICE-ICASE International Joint Conference, Bexco, Busan, Korea, 2006, pp. 93–98.
14.
LiZ., ZolotasA.C., JaimoukhaI.M., GrigoriadisK.M., MichailK. and PearsonJ.T., Output selection under control and fault detectability considerations, Mediterranean Conference on Control & Automation, 2007, pp. 1–6.
15.
ZhouY. and ZolotasA., Sensor selection in neuro-fuzzy modeling for fault diagnosis, IEEE International Symposium on Industrial Electronics, Italy, 2010, pp. 322–327.
16.
MuskeK.R., A Methodology for Optimal Sensor Selection in Chemical Processes. Proceedings of the American Control Conference, 5, 2002, pp. 4274–4278.
17.
JoshiS. and BoydS., Sensor selection via Convex Optimization, IEEE Trans On Signal Processing57(2) (2009), 451–462.
18.
WangX., LiangQ., WangW. and ZhangB., Sensor selection schemes in smart grid, IEEE Innovative Smart Grid Technologies-Asia, Tianjin, China, 2012, pp. 1–5.
19.
DeboukR., LafortuneS. and TeneketzisD., On an optimization problem in sensor selection, Discrete Event Dynamic Systems: Theory and Applications12(4) (2002), 417–445.
20.
JagerB.D., WalM.V.D. and KamidiR., Large-scale rigorous actuator and sensor selection, Proceedings of the IEEE Conference on Decision and Control4 (1998), 4314–4319.
21.
WalM.V.D. and JagerB.D., A review of methods for input/output selection, Automatica37(4) (2001), 487–510.
22.
YagerR.R. and FilevD.P., Essentials of Fuzzy Modelling and Control. John Wiley, NY, 1994.
23.
BabuskaR. and VerbruggenH., Neuro-fuzzy methods for nonlinear system identification, Annual Reviews in Control27I (2003), 73–85.
24.
AmannP., PerronneM., GissingerG.L. and FrankP.M., Identification of fuzzy relational models for fault detection, Control Engineering Practice9(5) (2001), 555–562.
25.
EspinosaJ., VandewalleJ. and WertzV., Fuzzy logic, identification, and predictive control, London; New York, Springer, 2004.
26.
CostaB.P.J. and DenteJ.A., Fuzzy systems modeling in practice, Fuzzy Sets an Systems121(1) (2001), 73–93.
27.
FangC. and DeyunX., Process Recognition. Beijing, Tsinghua University Press, Chinese, 1988.
28.
SbergJ. and LjungL., Overtraining, regularization and searching for a minimum, with application to neural networks, International Journal of Control62(6) (1995), 1391–1407.
29.
PostlethwaiteB.E., BrownM. and SingC.H., A new identification algorithm for fuzzy relational models and its application in model-based control, Tans IChemE75(PART A) (1997), 453–458.
30.
LjungL., Theory and practice of recursive identification. Cambridge, Massachusetts London, England: The MIT Press, 1983.
31.
CampelloR.J.G.B. and AmaralW.C., Modeling and linguistic knowledge extraction from systems using fuzzy relational models, Fuzzy Sets and System121(1) (2001), 113–126.
32.
TanW.W. and DexterL.A., Properties of a fuzzy relational model, Oxford University Engineering Laboratory Internal Report, OUEL 2119-96, 1996.
33.
ThompsonR. and DexterL.A., A fuzzy decision-making approach to temperature control in air-conditioning systems, Control Engineering Practice13(6) (2005), 689–698.
34.
HussainM.A. and HoP.Y., Adaptive sliding mode control with neural network based hybrid models, Journal of Process Control14(2) (2004), 157–176.
35.
NgoD. and DexterL.A., Fault diagnosis in air-conditioning systems with generic model of the HVAC plant. Proceedings of the 5th International Conference on System Simulation in Buildings University of Liege, Liege, Belgium, 1998.
36.
ZhouY., Fault Identification in Non-linear Systems. DPhil Thesis, University of Oxford, 2008.
37.
KelkarB. and PostlethwaiteB., Enhancing the generality of fuzzy relational models for control, Fuzzy Sets Systems100 (1998), 117–129.
38.
GhiausC., ChicinasA. and InardC., Grey-box identification of air-handling unit elements, Control Engineering Practice15 (2007), 421–433.
39.
GhiausC., Fuzzy model and control of a fan-coil, Energy and Buildings33(6) (2001), 545–551.
40.
ZhouY., DexterA.L. and ZolotasA., Generating Training Data For Identifying Neuro-fuzzy Models Of Non-Linear Dynamic Systems, The 48th IEEE Conference on Decision and Control and 28th Chinese Control Conference, Shanghai, China, 2009, pp. 6738–6743.
41.
BuragohainM. and MahantaC., A novel approach for ANFIS modelling based on full factorial design, Applied Soft Computing Journal8(1) (2008), 609–625.
42.
WenX. and ZhouL., Analysis and Application of Fuzzy Logic Toolbox, Beijing, Science Publication, 2002.
BaiR., ChaiT. and MaE., A Novel Approach for Extraction of Fuzzy Rules Using the Neuro-fuzzy Network and Its Application in the Blending Process of Raw Slurry, ” Advances in Neural Networks – ISN2007, 362–370.
45.
ZhouY. and DexterA., Estimating the size of incipient faults in HVAC equipment, HVAC & Research15(1) (2009), 151–116.
46.
IsermannR., Model-based fault-detection and diagnosis - status and applications, Annual Reviews in Control29(1) (2005), 71–85.
47.
MichailK., ZhouY., ZolotasA., GoodallR. and HalikiasG., Optimised Sensor Configurations with Reduced Order Controllers Applied to an EMS System, The 29th Chinese Control Conference, Beijing, China, 2010, pp. 3595–3600.
48.
LeeP.S. and DexterA., A fuzzy approach to fault diagnosis in the presence of sensor bias, The 10th IEEE International Conference on Fuzzy Systems, Melbourne, 3, 2001, pp. 1585–1588.
49.
Vasant and Pandian, Handbook of Research on Artificial Intelligence Techniques and Algorithms (2 Volumes). IGI Global, 2015, pp. 1–873. Web. 22 Jun. 2015.
50.
Vasant and M. Pandian, Meta-Heuristics Optimization Algorithms in Engineering, Business, Economics, and Finance. IGI Global, 2013, pp. 1–734. Web. 22 Jun. 2015.
