1
|
Nguimfack-Ndongmo JDD, Harrison A, Alombah NH, Kuate-Fochie R, Ajesam Asoh D, Kenné G. Adaptive terminal synergetic-backstepping technique based machine learning regression algorithm for MPPT control of PV systems under real climatic conditions. ISA TRANSACTIONS 2024; 145:423-442. [PMID: 38057172 DOI: 10.1016/j.isatra.2023.11.040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/22/2023] [Revised: 10/14/2023] [Accepted: 11/24/2023] [Indexed: 12/08/2023]
Abstract
This paper deals with a comparative evaluation of nonlinear controllers based on the linear regression technique, which is a machine learning algorithm for maximum power point tracking. In the past decade, most photovoltaic systems have been equipped with classical algorithms such as perturb and observe, hill climbing, and incremental conductance. The simplicity of these techniques and their ease of implementation were seen as the main reasons for their utilization in photovoltaic systems. However, researchers' attention has recently been attracted by artificial intelligence-based techniques such as linear regression, which offer better performance within the bounds of the nonlinearity of photovoltaic system characteristics. An adaptive terminal synergetic backstepping controller is developed in this paper for a single-ended primary inductance converter. This control scheme is based on the combination of a non-singular terminal synergetic technique with an integral backstepping technique and equally a neural network for the approximation of unmeasured or inaccessible variables that guarantees the finite-time convergence. The proposed controller was further verified under virtual and real environmental conditions, and the numerical results obtained from Matlab/Simulink software under various test conditions, including load variations, show that the adaptive terminal synergetic backstepping controller gives satisfactory performance compared to the adaptive integral backstepping controller used in the same climatic conditions.
Collapse
Affiliation(s)
- Jean de Dieu Nguimfack-Ndongmo
- Department of Electrical and Power Engineering, Higher Technical Teacher Training College (HTTTC), University of Bamenda, Bambili, P.O. Box 39, Bamenda, North-West, Cameroon; Unité de Recherche d'Automatique et d'Informatique Appliquée (UR-AIA), Département de Génie Électrique, IUT FOTSO Victor Bandjoun, Université de Dschang, B.P. 134 Bandjoun, Ouest, Cameroon.
| | - Ambe Harrison
- Department of Electrical and Electronics Engineering, College of Technology (COT), University of Buea, P.O. Box Buea 63, South-West, Cameroon.
| | - Njimboh Henry Alombah
- Department of Electrical and Electronics Engineering, College of Technology (COLTECH), University of Bamenda, P.O. Box 39, Bambili, North-West, Cameroon.
| | - René Kuate-Fochie
- Unité de Recherche d'Automatique et d'Informatique Appliquée (UR-AIA), Département de Génie Électrique, IUT FOTSO Victor Bandjoun, Université de Dschang, B.P. 134 Bandjoun, Ouest, Cameroon.
| | - Derek Ajesam Asoh
- Department of Electrical and Power Engineering, Higher Technical Teacher Training College (HTTTC), University of Bamenda, Bambili, P.O. Box 39, Bamenda, North-West, Cameroon; Department of Electrical and Electronic Engineering, National Higher Polytechnic Institute (NAHPI), University of Bamenda, Bambili, P.O. Box 39, Bamenda, North-West, Cameroon; Laboratoire de Génie Electrique, Mécatronique et Traitement du Signal, ENSPY, Université de Yaoundé I, Ngoa-Ekelle, Yaoundé, B.P. 337, Centre, Cameroon.
| | - Godpromesse Kenné
- Unité de Recherche d'Automatique et d'Informatique Appliquée (UR-AIA), Département de Génie Électrique, IUT FOTSO Victor Bandjoun, Université de Dschang, B.P. 134 Bandjoun, Ouest, Cameroon.
| |
Collapse
|
2
|
Guo K, Zheng DD, Li J. Optimal Bounded Ellipsoid Identification With Deterministic and Bounded Learning Gains: Design and Application to Euler-Lagrange Systems. IEEE TRANSACTIONS ON CYBERNETICS 2022; 52:10800-10813. [PMID: 33872169 DOI: 10.1109/tcyb.2021.3066639] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
This article proposes an effective optimal bounded ellipsoid (OBE) identification algorithm for neural networks to reconstruct the dynamics of the uncertain Euler-Lagrange systems. To address the problem of unbounded growth or vanishing of the learning gain matrix in classical OBE algorithms, we propose a modified OBE algorithm to ensure that the learning gain matrix has deterministic upper and lower bounds (i.e., the bounds are independent of the unpredictable excitation levels in different regressor channels and, therefore, are capable of being predetermined a priori). Such properties are generally unavailable in the existing OBE algorithms. The upper bound prevents blow-up in cases of insufficient excitations, and the lower bound ensures good identification performance for time-varying parameters. Based on the proposed OBE identification algorithm, we developed a closed-loop controller for the Euler-Lagrange system and proved the practical asymptotic stability of the closed-loop system via the Lyapunov stability theory. Furthermore, we showed that inertial matrix inversion and noisy acceleration signals are not required in the controller. Comparative studies confirmed the validity of the proposed approach.
Collapse
|
3
|
Abstract
The stability and robustness of quadrotors are always influenced by unknown or immeasurable system parameters. This paper proposes a novel adaptive parameter estimation technology to obtain high-accuracy parameter estimation for quadrotors. A typical mathematical model of quadrotors is first obtained, which can be used for parameter estimation. Then, an expression of the parameter estimation error is derived by introducing a set of auxiliary filtered variables. Moreover, an augmented matrix is constructed based on the obtained auxiliary filtered variables, which is then used to design new adaptive laws to achieve exponential convergence under the standard persistent excitation (PE) condition. Finally, a simulation and an experimental verification for a typical quadrotor system are shown to illustrate the effectiveness of the proposed method.
Collapse
|