A Bi-level Optimization Approach for Historical Data-Driven System Identification

被引:2
|
作者
Oulhiq, Ridouane [1 ,2 ]
Benjelloun, Khalid [1 ,3 ]
Kali, Yassine [4 ]
Saad, Maarouf [4 ]
机构
[1] Mohammed V Univ, Ecole Mohammadia Ingenieurs, EPTICAR, Rabat, Morocco
[2] Mohammed VI Polytech Univ, TechCell, Benguerir, Morocco
[3] Mohammed VI Polytech Univ, GTI, Benguerir, Morocco
[4] Ecole Technol Super, GREPCI Lab, Montreal, PQ H3C 1K3, Canada
关键词
Process identification; Historical data; Optimal estimation; Bi-level optimization; Data informativity; Industrial thickener; TIME-DELAY ESTIMATION; GENETIC ALGORITHM; CONDITION NUMBER;
D O I
10.1007/s40313-022-00951-w
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
System identification is the field of systems mathematical modeling from experimental data. In the modeling chain, experiments realization, model structure selection and parameter estimation are essential steps. However, performing tests for system identification is time-consuming and not always possible. Also, while in most modeling workflows model parameters are optimized, model structure is generally selected manually, and if optimized, data informativity is not considered. For these reasons, an approach using historical data with optimized selection of model's structure and parameters, considering data informativity, is proposed. Therefore, historical data is collected and data around the process operating point is selected. Then, data is prefiltered, resampled, cleaned, and normalized. Then, for modeling, a vector autoregressive with exogenous variables model structure is considered. To estimate the model's structural parameters and coefficients, a bi-level optimization algorithm is proposed. For the outer optimization, genetic algorithm, fireworks algorithm, particle swarm optimization, and simulated annealing algorithm are simulated and compared to conventional methods. Also, as normal operation data is used, a data informativity step is integrated to discard non-informative model structures. To estimate the model coefficients, ridge regression is used. In a case study, the approach is applied to model an industrial thickener. The obtained results show that the proposed approach outperforms conventional ones.
引用
收藏
页码:73 / 84
页数:12
相关论文
共 50 条
  • [21] Data-driven optimization of mixed-integer bi-level multi-follower integrated planning and scheduling problems under demand uncertainty
    Beykal, Burcu
    Avraamidou, Styliani
    Pistikopoulos, Efstratios N.
    COMPUTERS & CHEMICAL ENGINEERING, 2022, 156
  • [22] Data-Driven Sparse System Identification
    Fattahi, Salar
    Sojoudi, Somayeh
    2018 56TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2018, : 462 - 469
  • [23] Bi-Level Optimization for Eco-Traffic Signal System
    Jung, Hojin
    Choi, Saerona
    Park, Byungkyu Brian
    Lee, Haengju
    Son, Sang Hyuk
    2016 INTERNATIONAL CONFERENCE ON CONNECTED VEHICLES AND EXPO (ICCVE), 2016, : 29 - 35
  • [24] Bi-level Problem and SMD Assessment Delinquent for Single Impartial Bi-level Optimization
    Vadali, Srinivas
    Deekshitulu, G. V. S. R.
    Murthy, J. V. R.
    PROCEEDINGS OF SIXTH INTERNATIONAL CONFERENCE ON SOFT COMPUTING FOR PROBLEM SOLVING (SOCPROS 2016), VOL 1, 2017, 546 : 52 - 62
  • [25] Evolutionary multitasking in bi-level optimization
    Gupta, Abhishek
    Mandziuk, Jacek
    Ong, Yew-Soon
    COMPLEX & INTELLIGENT SYSTEMS, 2015, 1 (1-4) : 83 - 95
  • [26] Modeling and control system optimization for electrified vehicles: A data-driven approach
    Zhang, Hao
    Lei, Nuo
    Chen, Boli
    Li, Bingbing
    Li, Rulong
    Wang, Zhi
    ENERGY, 2024, 310
  • [27] Bi-level Optimization of Inventory and Production
    Stoilov, Todor
    Stoilova, Krasimira
    CYBERNETICS AND INFORMATION TECHNOLOGIES, 2025, 25 (01) : 126 - 141
  • [28] Evolutionary multitasking in bi-level optimization
    Abhishek Gupta
    Jacek Mańdziuk
    Yew-Soon Ong
    Complex & Intelligent Systems, 2015, 1 (1-4) : 83 - 95
  • [29] Bi-Level Optimization in a Transport Network
    Stoilov, Todor
    Stoilova, Krasimira
    Papageorgiou, Markos
    Papamichail, Ioannis
    CYBERNETICS AND INFORMATION TECHNOLOGIES, 2015, 15 (05) : 37 - 49
  • [30] BI-LEVEL DYNAMIC OPTIMIZATION WITH FEEDBACK
    Bernstein, Andrey
    Dall'Anese, Emiliano
    2017 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2017), 2017, : 553 - 557