A neural network‐based selective harmonic elimination scheme for five‐level inverter

Recurrent neural networks (RNN) emerged as powerful tools to model and analyze the nonlinear behavior of electronic circuits accurately and quickly.Efforts to improve the accuracy of RNN will lead to the design of better-quality products, which is essential in various fields such as the design of energy harvesting (EH) systems. EH techniques can provide the electrical energy needed for low-power electronics without the need for a battery or with minimal dependency. Due to the importance of the active voltage balancing circuit in EH systems, we have proposed a new macromodeling method called dropout local-feedback deep recurrent neural network (Dropout-LFDRNN) to model and analyze this circuit along with two other nonlinear circuits asexamples. This technique is an advance over the LFDRNN macromodeling method, and based on the obtained results from the measurements, we were able to build a fast macromodel for the active balancing circuit, which outperforms conventional deep recurrent neural network modeling method in terms of accuracy without sacrificing speed. It is worth mentioning that this proposed technique in this paper can be considered a viable approach for modeling and analysis of nonlinear electronic components and circuits. In addition to the advantage of generating a more accurate model, the model based on the Dropout-LFDRNN approach is much faster than the existing transistor-level models.

Section: Structure Of Solar Energy Harvestingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Modeling and implementation of a novel active voltage balancing circuit using deep recurrent neural network with dropout regularization

Noohi

Faraji

Sadrossadat

et al. 2022

“…In Panda et al, 9 a selective harmonic elimination (SHE) method has been presented for a multilevel inverter to enhance the output voltage harmonics. In literature, [10][11][12][13][14][15] also, the SHE/SHM method is used to cope with some loworder harmonics in CHB multilevel inverters. The SHE and selective harmonic mitigation (SHM) methods have been combined in Sharifzadeh et al 16 to reduce output voltage harmonics in three-level NPC inverters.…”

Section: Introductionmentioning

confidence: 99%

Analysis and suppression of switching‐frequency harmonics in variable‐output‐voltage inverters

Farhadi‐Kangarlu,

Khiavi,

Neyshabouri

2023

SummaryIn many practical applications such as motor drives, the inverter is required to produce a variable output voltage within a wide range (e.g., 0.1 to 1 pu). In such cases, when the inverter operates in low modulation index (low output voltage), the harmonic distortion of the output voltage increases due to considerable reduction in the magnitude of the fundamental component. Also, the ratio of the switching losses to the output power will be high in the low modulation index. In this paper, a simple solution is proposed to overcome the problems. The principle of the proposed solution is to adjust the DC‐link voltage so that the modulation index of the inverter remains within a specific high range. Different practical ways of obtaining controlled DC‐link voltage are presented. Also, for operation of the DC‐DC converter used for DC‐link voltage control, three strategies are proposed. The proposed solution is simple, and it is very effective and feasible to implement. To the best of the authors' knowledge, the idea has not been presented in this form previously. In order to verify the proposed solution, the simulation and experimental results are presented and discussed.

“…Solving the nonlinear equations has made the SHM method more challenging, and there are several algorithms to solve such equations. In Toubal Maamar et al, 33 the artificial neural network (ANN) is used for the SHE control. The Newton‐Raphson, sequential homotropy‐based computation, resultant theory, the genetic algorithm (GA), particle swarm optimization (PSO), ant colony, bee algorithm, and so forth have been introduced in recent years to surmount the challenge mentioned above.…”

Section: Introductionmentioning

confidence: 99%

SHM‐PWM technique in a cascaded H‐bridge multilevel inverter with adjustable DC‐link for wide voltage range applications

Pourdadashnia

Farhadi‐Kangarlu

Tousi

et al. 2022

In this paper, a new method for achieving high-quality voltage in multilevel inverters is presented. The method is based on the selective harmonic mitigation pulse width modulation (SHM-PWM) technique applied on a cascaded Hbridge multilevel inverter (CHBMLI), which employs a variable DC-link voltage to reduce the amount of the total harmonic distortion (THD) in the output waveform. The variable DC sources in a CHBMLI can increase the modulation index to an acceptable range in the low output voltage values and also increase the number of harmonics to be eliminated in the SHM technique due to increasing the number of voltage levels. In the proposed method, the optimal switching angles are calculated by the particle swarm optimization (PSO) algorithm and the switching angles are stored in lookup tables (LUTs). Implementing the proposed method allows the CHB inverter to improve the performance in producing a high-quality voltage compared with conventional methods. As an applicable example, a single-phase CHBMLI, fed by two isolated DC sources, is examined in this paper. The analysis presented in this paper shows a significant improvement in the quality of the output voltage, especially for low output voltage conditions. The simulation and experimental results are presented to confirm the proposed approach.