Over the last decade, multilevel inverter (MLI) has gained a global research paradigm in power electronics. The high-power application of multilevel inverters necessitates the safe and reliable operation of the inverter. Fault diagnosis of MLI is inevitable to enhance the reliability of the inverter. The real-time applications monitor the intricate switching process of the MLI using data from sensors like voltage, current, and temperature. Obtaining complementary fault features through conventional methods is difficult due to operating complexity and limited switch-fault samples. These methods heavily depend on prior knowledge. To deal with this problem, this paper proposes a new multiscale kernel convolution neural network (MKCNN) for fast fault diagnosis of cascaded MLI. Firstly, the proposed method necessitates using frequency domain samples instead of raw signals, which can leverage the power of a convolution neural network (CNN) to obtain hierarchical features from the images through a short-time Fourier transform (STFT). Secondly, the multiscale kernel convolution network model is constructed to capture and analyze low- to high-level fault features. This method improves the traditional CNN by extracting discriminative fault information through multiple convolution kernels of different scales with varying resolutions obtaining high diagnosis accuracy under single and multiple open circuit and short circuit faults. Finally, the softmax layer generates the output of the fault diagnosis results. Simulation results validate the effectiveness of the proposed model, demonstrating a high diagnosis accuracy rate of 98.3%. The model exhibits robustness in diagnosing single and multiple switch faults across different fault cases of an MLI. Comparison with other intelligent models further emphasizes the superiority of the proposed method.
27 September 2023 in International Transactions on Electrical Energy Systems
Recent research has been focussed on renewable energy due to the rising need for electrical energy. Renewable energy has a low environmental impact compared to other energy sources. As a result, renewable energy sources (RESs) are the best option for generating electricity. Solar photovoltaic is one of the largest renewable power generators. Solar photovoltaic (PV) is connected to the load via power electronic converters. Most PV installations need a two-stage conversion process consisting of a boost converter to increase the load voltage and an AC-to-DC voltage source inverter to power the load. The Z-source inverter (ZSI) can confront the shortcomings of VSI and two-stage conversions. ZSI connects the PV system to the load and is used to increase the system’s performance. This paper discusses the performance of various topologies of ZSI, such as traditional Z-source inverters (XZSIs); for integrating a PV source into a load, switched inductor Z-source inverters (SIZSIs) and transient Z-source inverters (TZSIs) are used. Also, artificial neural networks (ANNs), fuzzy logic controller (FLC), and adaptive neuro-fuzzy inference system (ANFIS)-based MPPT techniques are discussed for obtaining maximum power from PV panels. Based on the maximum power, the shoot-through duty ratio has been adjusted.
Maximum Power Point Tracking (MPPT) technique is used to extract maximum power from the photovoltaic system. This paper involves working on an enhanced Particle Swarm Optimization (PSO) based MPPT method for the photovoltaic (PV) system integrated through Z-Source inverter. The main benefit of the proposed method is the diminishing of the steady-state oscillation when the maximum power point (MPP) is located. Additionally, during an extreme environmental condition, such as partial shading and large fluctuations of irradiance and temperature, the proposed method has the capability to track the MPP. This algorithm is implemented in dspace 1104 controller. MATLAB simulations are carried out under varying irradiance and temperature conditions to evaluate its effectiveness. Its performance is compared with a conventional method like Perturb and observe (P&O) method.
This paper presents the photo-voltaic (PV) system based on simple boost Z-Source Inverter (ZSI) for three phase resistive load. Here PV cell and PV module model is developed from mathematical equations. Voltage of photovoltaic cell varies with temperature and irradiation. For most of the PV applications PV output voltage is not enough according to specific load requirement. So, the conventional Voltage Source Inverter (VSI) that has been the power conversion technology requires additional voltage boost converter for such applications. The ZSI implements voltage boost as well as voltage inversion simultaneously in a single-stage. Thus Z-source inverter eliminates the limitations of conventional boost converter interfaced with VSI. Simple boost control technique with sinusoidal pulse width modulation is used here for Z-source inverter. Inductor and capacitor values are calculated for Z-source network. In this paper performance of Z-source inverter topology over conventional boost converter interfaced with VSI topology is studied using MATLAB SIMULINK software.
Due to growth in the number of consumers and the development of high-power sectors, electricity need from the utility grid has grown dramatically over the past decade. Therefore, renewable energy resources such as solar and wind are more prevalent in the electricity system. Solar power generation relies primarily on the multilevel power conversion system, which is emerging as a promising solution for a variety of medium and high-power applications. For large-scale grid integrated photovoltaic applications, the cascaded h-bridge (CHB) and modular multilevel converter (MMC) are being considered as the best choice due to their exciting intrinsic advantages such as modularity, low voltage switching, fault-tolerant operations, higher efficiency, and improved output waveform. Despite its advantages, the CHB and MMC-based photovoltaic systems are facing issues like unbalanced power, circulating current control, robustness, and reliability of the system. This chapter examines the various types of MMC and CHB topologies utilized in PV applications, including the challenges facing in large-scale PV systems, the strength and drawbacks of each topology. Additionally, this review delves deeply into the modulation and control strategies for multilevel converters. Further, this study focused on the detailed state-of-the-art assessment of common electrical fault, fault detection, and fault-tolerant techniques with an emphasis on its diagnostic accuracy and reliability. Finally, the current research challenges and their future outcomes are highlighted.