Deep Neural Network-based Black-box Modeling of Power Electronic Converters Using Transfer Learning

Qashqai, Pouria; Al‐Haddad, Kamal; Zgheib, Rawad

doi:10.1109/ecce50734.2022.9947749

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, adaptive-based approaches are proposed with higher efficiency in challenging cases considering their flexibility and better outcomes. Some of the most recent adaptive controllers used for power converters are listed here: Neural Network-based adaptive [18,19], adaptive predictive [20], optimized adaptive sliding mode [21,22], and Lyapunovbased adaptive [23] strategies. The main benefits presented by these approaches are effectiveness in ill-defined models, higher robustness in uncertainties, and faster dynamical operation.…”

Section: Introductionmentioning

confidence: 99%

Design of a novel robust type‐2 fuzzy‐based adaptive backstepping controller optimized with antlion algorithm for buck converter

Khavari

Ghamari

Abdollahzadeh

et al. 2023

IET Control Theory & Appl

View full text Add to dashboard Cite

A type‐2 fuzzy logic‐based adaptive backstepping control (T2F‐ABSC) approach is presented for a DC/DC Buck converter. Lyapunov‐based backstepping control (BSC), which can guarantee convergence along with asymptotic stability of the system. Also, the black‐box technique is applied for the proposed system, which does not require an accurate mathematical model resulting in a lower computational burden, easy implementation, and lower dependency on the states of the model. On the other hand, for wider ranges of disturbances, including parametric variations, load uncertainty, supply voltage variation, and noise, this approach shows an unsuitable practical application based on its fixed gain values; therefore, the control parameters need to be optimized again to provide ideal operations. Type‐2 fuzzy structure is adopted here to optimize the gains of the ABSM in challenging conditions. Type‐2 fuzzy (T2F) has higher efficiency and faster dynamics with more adaptability to the system. To enhance the performance of the T2F, antlion optimization (ALO) has been used in this structure. ALO is a modern nature‐inspired algorithm, and it has some advantages over other optimizing algorithms. Furthermore, it has ability to find optimal answers in a shorter time, more accurately in contrast to the other optimization algorithms and is used to tune the membership function parameters of the (T2F) under the diverse search spaces. To depict the strength of the designed work, fuzzy‐PID and backstepping schemes proposed to carry out an analysis with this work.

show abstract

Section: Introductionmentioning

confidence: 99%

Design of a novel robust type‐2 fuzzy‐based adaptive backstepping controller optimized with antlion algorithm for buck converter

Khavari

Ghamari

Abdollahzadeh

et al. 2023

IET Control Theory & Appl

View full text Add to dashboard Cite

show abstract

A Model-Free Switching and Control Method for Three-Level Neutral Point Clamped Converter Using Deep Reinforcement Learning

Qashqai,

Babaie,

Zgheib

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper presents a novel model-free switching and control method for three-level neutral point clamped (NPC) converter using deep reinforcement learning (DRL). In this method, voltage balancing, and selection of optimal switches are achieved using a reward function which is calculated based on various signals measured as observations of the DRL agent. Since the action space is discrete, a deep Q-network (DQN) agent is utilized. DQN is used due to its capability of handling high-dimensional state spaces. In order to highlight its pros and cons, the proposed method is compared with model predictive control (MPC), which is another popular non-linear control method for power electronic converters. The proposed method is evaluated and compared with the MPC method in grid-connected mode using simulations in Matlab/Simulink. To evaluate the practical performance of the DRL method, various experimental results are obtained. The simulation and experimental results demonstrate that the proposed method effectively achieves accurate voltage balancing and ensures steady operation even in the presence of various dynamic changes, including variations in the reference currents and grid voltage. Additionally, the method successfully handles uncertainties, such as sensor measurement noise, and accommodates parameter variations, such as changes in the capacity of the DC-link capacitors and line impedance. The results demonstrate that this method exhibits superior adaptability to real-time changes and uncertainties, delivering more robust performance compared to similar conventional methods like MPC. Thus, this method can be considered a promising approach for intelligent control of power electronic converters, especially when conventional methods such as MPC face challenges in performance and accuracy under severe parameter variations and uncertainties.

show abstract

Black-Box Wiener-Hammerstein Model With Polytopic Dynamic Structure for Highly Non-Linear DC-DC Power Electronic Converters

Perez,

Frances,

Uceda

2024

IEEE Access

View full text Add to dashboard Cite

Deep Neural Network-based Black-box Modeling of Power Electronic Converters Using Transfer Learning

Cited by 3 publications

References 13 publications

Design of a novel robust type‐2 fuzzy‐based adaptive backstepping controller optimized with antlion algorithm for buck converter

Design of a novel robust type‐2 fuzzy‐based adaptive backstepping controller optimized with antlion algorithm for buck converter

A Model-Free Switching and Control Method for Three-Level Neutral Point Clamped Converter Using Deep Reinforcement Learning

Black-Box Wiener-Hammerstein Model With Polytopic Dynamic Structure for Highly Non-Linear DC-DC Power Electronic Converters

Contact Info

Product

Resources

About