The main objective of this paper is the extension of the clustering-based identification approach to Multi-Input Multi-Output (MIMO) PieceWise Affine systems (PWA). This approach is performed by three main steps which are data clustering, parameters matrices estimation and regions computing. Data clustering is the most important step because the performances depend on the results given by the used clustering algorithm. In the case of MIMO PWA systems, we should cluster matrices of parameters which are considered high dimensional data. However, most of the conventional clustering algorithms are not efficient since the similarity assessment which is based on the distances between objects is fruitless in high dimension space. Therefore, we propose an extension of the DBSCAN (Density Based Spatial Clustering of Applications with Noise) clustering technique to identify MIMO PWA systems. The simulation results presented in this paper illustrate the performance of the proposed method. An application to an industrial dryer of Di-Calcium Phosphate (DCP) is also presented in order to strengthen the simulation results.
GambierAWellenreutherABadreddinE. A new approach to design multi-loop control systems with multiple controllers. In: Proceedings of the 45th IEEE conference on decision and control, San Diego, CA, 2006, pp. 1828–1833. Piscataway, NJ: IEEE.
2.
JensenNFisherDShahS. Interaction analysis in multivariable control systems. AIChE J1986; 32(6): 959–970.
3.
KinnaertM. Interaction measures and pairing of controlled and manipulated variables for multiple-input multiple-output systems: a survey. Journal A1995; 36(4): 15–23.
4.
ZhengQChenZGaoZ. A practical approach to disturbance decoupling control. Control Eng Pract2009; 17(9): 1016–1025.
5.
DingFLiuYBaoB. Gradient-based and least-squares-based iterative estimation algorithms for multi-input multi-output systems. Proc IMechE, Part I: J Systems Control Engineering2012; 226(1): 43–55.
6.
DingF. Coupled-least-squares identification for multivariable systems. IET Control Theory Appl2013; 7(1): 68–79.
7.
WanLDingF. Decomposition-and gradient-based iterative identification algorithms for multivariable systems using the multi-innovation theory. Circ Syst Signal Process2019; 38: 2971–2991.
8.
WangYDingF. A filtering based multi-innovation gradient estimation algorithm and performance analysis for nonlinear dynamical systems. IMA J Appl Math2017; 82(6): 1171–1191.
9.
PanJJiangXWanX, et al. A filtering based multi-innovation extended stochastic gradient algorithm for multivariable control systems. Int J Control Autom Syst2017; 15: 1189–1197.
10.
MaPDingFZhuQ. Decomposition-based recursive least squares identification methods for multivariate pseudo-linear systems using the multi-innovation. Int J Syst Sci2018; 49(5): 920–928.
11.
ZhouLLiXXuH, et al. Multi-innovation stochastic gradient method for harmonic modelling of power signals. IET Signal Process2016; 10(7): 737–742.
12.
WangYDingF. Novel data filtering based parameter identification for multiple-input multiple-output systems using the auxiliary model. Automatica2016; 71: 308–313.
13.
DingFChenHXuLDaiJLiQHayatT. A hierarchical least squares identification algorithm for hammerstein nonlinear systems using the key term separation. J Frank Inst2018; 355(8): 3737–3752.
14.
WangDLiLJiY, et al. Model recovery for hammerstein systems using the auxiliary model based orthogonal matching pursuit method. Appl Math Model2018; 54: 537–550.
15.
WangDYanYLiuY, et al. Model recovery for hammerstein systems using the hierarchical orthogonal matching pursuit method. J Comput Appl Math2019; 345: 135–145.
16.
WangD. Hierarchical parameter estimation for a class of MIMO hammerstein systems based on the reframed models. Appl Math Lett2016; 57: 13–19.
WangDQLiuHBDingF. Highly efficient identification methods for dual-rate hammerstein systems. IEEE Trans Control Syst Technol2015; 23(5): 1952–1960.
19.
ZhouLLiXShanL, et al. Hierarchical recursive least squares parameter estimation of non-uniformly sampled hammerstein nonlinear systems based on kalman filter. J Frank Inst2017; 354(10): 4231–4246.
20.
WangDZhangZXueB. Decoupled parameter estimation methods for hammerstein systems by using filtering technique. IEEE Access2018; 6: 66612–66620.
21.
BakoLYahyaO. Piecewise affine system identification: A least harmonic mean approach. In: 58th Conference on Decision and Control (CDC), Nice, France, 11–13 December 2019, pp. 2660–2665. Piscataway, NJ: IEEE.
22.
KimYM. Robust fault detection of piecewise affine ARX systems. J Control Decis2020; 7(3): 403–417.
23.
PaolettiSSavelliIGarulliA, et al. A bilevel programming framework for piecewise affine system identification. In: 2019 IEEE 58th conference on decision and control (CDC), Nice, France, 2019, pp. 7376–7381. Piscataway, NJ: IEEE.
24.
ThuanLOvan den BoomTBaldiS. Online identification of continuous bimodal and trimodal piecewise affine systems. In: 2016 European control conference (ECC), Aalborg, Denmark, 2016, pp. 1075–1070. Piscataway, NJ: IEEE.
25.
BemporadAGarulliAPaolettiS, et al. A greedy approach to identification of piecewise affine models. In: 6th International Workshop on Hybrid Systems: Computation and Control, Prague Czech Republic, 3–5 April 2003, Vol. 1, pp. 97–112. Berlin: Springer-Verlag.
26.
BemporadAGarulliAPaolettiS, et al. A bounded-error approach to piecewise affine system identification. IEEE Trans Autom Control2005; 50(10): 1567–1580.
27.
Ferrari-TrecateGMuselliMLiberatiD, et al. A clustering technique for the identification of piecewise affine systems. Automatica2003; 39(2): 205–217.
28.
JuloskiAWeilandSHeemelsW. A Bayesian approach to identification of hybrid systems. IEEE Trans Autom Control2005; 50(10): 1520–1533.
29.
TianYFloquetTBelkouraL, et al. Algebraic switching time identification for a class of linear hybrid systems. Nonlinear Analy Hybrid Syst2011; 5(2): 233–241.
30.
BianchiFFalsoneAPiroddiL, et al. A constrained clustering approach to bounded-error identification of switched and piecewise affine systems. Automatica2022; 146: 110589.
31.
Ferrari-TrecateGMuselliM. Single-linkage clustering for optimal classification in piecewise affine regression. IFAC Proc Vol2003; 36(6): 33–38.
32.
LassouedZAbderrahimK (2014) Pwarx model identification based on clustering approach. In: ZhuQAzarAT (eds.) Complex system modelling and control through intelligent soft computations’ by Studies in Fuzziness and Soft Computing. Germany: Springer-Verlag.
33.
LassouedZAbderrahimK. An experimental validation of a novel clustering approach to PWARX identification. Eng Appl Artif Intell2014; 28: 201–209.
34.
LassouedZAbderrahimK. Identification and control of nonlinear systems using piecewise auto-regressive exogenous models. Trans Inst Meas Control2019; 41(14): 4050–4062.
35.
WangL. Support vector machines: Theory and applications. Berlin, Germany: Springer, 2005.
36.
SteinbachMErtözLKumarV. The challenges of clustering high dimensional data. In: WileLT (ed.) New directions in statistical physics. Berlin, Germany: Springer, pp. 273–309, 2004.
37.
BakoLLauerFBlochG, et al. Identification of mimo switched state-space models. In: 2013 American control conference, Washington, DC, 2013, pp. 71–76. Piscataway, NJ: IEEE.
38.
MejariMNaikVVPigaD, et al. Identification of hybrid and linear parameter-varying models via piecewise affine regression using mixed integer programming. Int J Robust Nonlinear Control2020; 30(15): 5802–5819.
39.
VerdultVVerhaegenM. Subspace identification of piecewise linear systems. In: 2004 43rd IEEE conference on decision and control (CDC)(IEEE Cat. No. 04CH37601), Nassau, Bahamas, 2004, Vol. 4, pp. 3838–3843. Piscataway, NJ: IEEE.
40.
BreschiVBemporadAPigaD. Identification of hybrid and linear parameter varying models via recursive piecewise affine regression and discrimination. In: 2016 European Control Conference (ECC), Aalborg, Denmark, 2016, pp. 2632–2637. Piscataway, NJ: IEEE.
41.
HureNVašakM (2017) Clustering-based identification of mimo piecewise affine systems. In: 2017 21st international conference on process control (PC), Strbske Pleso, Slovakia, 2017, pp. 404–409. Piscataway, NJ: IEEE.
42.
VasakMKlanjcicDPericN. Piecewise affine identification of MIMO processes. In: Conference on computer aided control system design, 2006 IEEE international conference on control applications, 2006 IEEE international symposium on intelligent control, Munich, Germany, 2006, pp. 1493–1498. Piscataway, NJ: IEEE.
43.
Ferrari-TrecateGMuselliMLiberatiD, et al. A clustering technique for the identification of piecewise affine systems. Hybrid Syst Comput Control2003; 39: 205–217
44.
RustamZNadhifaFAcarM. Comparison of SVM and FSVM for predicting bank failures using chi-square feature selection. J Phys Conf Ser2018; 1108: 012115.
45.
BenabdellahACBenghabritABouhaddouI. A survey of clustering algorithms for an industrial context. Proc Comput Sci2019; 148: 291–302.
46.
EzugwuAEIkotunAMOyeladeOO, et al. A comprehensive survey of clustering algorithms: state-of-the-art machine learning applications, taxonomy, challenges, and future research prospects. Eng Appl Artif Intell2022; 110: 104743.
47.
BhattacharjeePMitraP. A survey of density based clustering algorithms. Front Comput Sci2021; 15(1): 1–27.
48.
HassanSISamadAAhmadO, et al. Partitioning and hierarchical based clustering: a comparative empirical assessment on internal and external indices, accuracy, and time. Int J Inform Technol2020; 12(4): 1377–1384.
49.
CampelloRJKrögerPSanderJ, et al. Density-based clustering. Wiley Interdiscip Rev Data Min Knowl Discov2020; 10(2): e1343.
50.
ErmanJMahantiAArlittMF. Traffic classification using clustering algorithms. In: Proceedings of the 2006 SIGCOMM workshop on mining network data, Pisa, Italy, 15 September 2006, pp. 281–286.
51.
LassouedZAbderrahimK. New results on PWARX model identification based on clustering approach. Int J Autom Comput2014; 11(2): 180–188.
52.
Walters-WilliamsJLiY. Comparative study of distance functions for nearest neighbors. In: ElleithyK (ed.) Advanced techniques in computing sciences and software engineering. Berlin, Germany: Springer, pp. 79–84, 2010.
53.
PavithraMParvathiR. A survey on clustering high dimensional data techniques. Int J Appl Eng Res2017; 12(11): 2893–2899.
54.
AggarwalCCHinneburgAKeimDA. On the surprising behavior of distance metrics in high dimensional space. In: International conference on database theory. Berlin, Germany: Springer, 2001, pp. 420–434.
