Power Extraction Research Articles

Grid-connected double-stage PV system with space vector PWM inverter and MPPT

Because of the increasing demand for non-conventional energy sources, photovoltaic system integration into the electrical grid is becoming more crucial. It is advised to employ a double-stage grid-connected PV system. This can be employed with the main parts boost converter, which helps to boost the DC output from the PV channels. And next one is the space vector pulse width modulation (SVPWM) inverter which can provide better harmonic performance and higher efficiency compared to traditional PWM methods. The SVPWM technique is employed to modulate the inverter output, generating a sinusoidal AC waveform that matches the grid frequency and voltage. By adjusting the pulse width to achieve effective and trustworthy grid integration. To maximize power extraction takes place by using maximum power point tracking (MPPT). The SVPWM inverter is crucial in converting DC power to AC power and enabling grid connection. Utilizing SVPWM allows exact control of voltage magnitude, frequency, and phase angle to provide high-quality sinusoidal AC output voltage. The power quality of the electricity pumped into the grid is improved by this precise management, which also ensures adherence to grid standards and reduces harmonic interference.

Evaluate Multi-Objective Optimization Model for Product Supply Chain Inventory Control Based on Grey Wolf Algorithm

Enterprise supply chain inventory control plays a critical role in modern enterprise management. Yet achieving multi-objective optimization remains challenging. This paper proposes a deep learning integrated model based on grey wolf optimization (GWO-DLIM) aimed at optimizing inventory holding costs, stockout costs, and order costs. The model integrates multi-layer perceptron (MLP), DeBERTa, and GWO, leveraging the powerful predictive and feature extraction capabilities of deep learning models, combined with the global optimization ability of the grey wolf algorithm, to achieve multi-objective optimization. These results demonstrate that the GWO-DLIM model significantly outperforms other comparative models across all metrics, exhibiting lower prediction errors and root mean square errors, as well as higher service levels. This study provides an effective multi-objective optimization solution for supply chain inventory management, holding significant theoretical and practical implications.

Modeling and Control of Dual Active Bridge‐Modular Multilevel Converter‐Based Solid State Transformer for Grid Integration of SPV and Battery Energy Storage

ABSTRACTThis article deals with the modeling and control of a solid‐state transformer (SST) based on a dual active bridge (DAB) and modular multilevel converter (MMC) for integrating solar photovoltaic (SPV) and battery energy storage (BES) systems into the grid. SST uses DABs for bidirectional DC‐DC conversion and an MMC for DC‐AC conversion. A hybrid control method is developed in this study, which combines proportional‐integral (PI) controllers and model predictive control (MPC) to achieve the multiple objectives of the SST. The DABs' control system uses PI controllers for power extraction from the SPV system and to regulate the charging and discharging of the BES according to power generation and demand fluctuations. MPC is applied to control the active power injection, regulate the DC‐link and sub‐module capacitor voltages of the MMC. Moreover, the developed hybrid control method ensures reliable SST performance even under adverse conditions like grid voltage distortion, unbalance, and frequency variations. An energy management strategy is developed based on total power generation, reference active power injection, and the state of charge of the BES. This strategy ensures accurate reference power injection to the grid despite dynamic changes in operating conditions. The article also presents a detailed mathematical model of the DAB and MMC components, and the stability of the control algorithm is analyzed theoretically. The effectiveness of the SST and the proposed hybrid control scheme is demonstrated through MATLAB/Simulink simulations and hardware‐in‐the‐loop experimental results under various operating conditions.

Advanced Control Scheme Optimization for Stand-Alone Photovoltaic Water Pumping Systems

This study introduces a novel method for controlling an autonomous photovoltaic pumping system by integrating a Maximum Power Point Tracking (MPPT) control scheme with variable structure Sliding Mode Control (SMC) alongside Perturb and Observe (P&O) algorithms. The stability of the proposed SMC method is rigorously analyzed using Lyapunov’s theory. Through simulation-based comparisons, the efficacy of the SMC controller is demonstrated against traditional P&O methods. Additionally, the SMC-based system is experimentally implemented in real time using dSPACE DSP1104, showcasing its robustness in the presence of internal and external disturbances. Robustness tests reveal that the SMC controller effectively tracks Maximum Power Points (MMPs) despite significant variations in load and solar irradiation, maintaining optimal performance even under challenging conditions. The results indicate that the SMC system can achieve up to a 70% increase in water flow rates compared with systems without MPPT controllers. Furthermore, SMC demonstrated high sensitivity to sudden changes in environmental conditions, ensuring efficient power extraction from the photovoltaic panels. This study highlights the advantages of integrating SMC into Photovoltaic Water Pumping Systems (PV-WPSs), providing enhanced control capabilities and optimizing system performance. The findings contribute to the development of sustainable water supply solutions, particularly in remote areas with limited access to the electrical grid.

Dual MPPT Algorithm Implementation in Solar Charge Controller

The implementation of a Dual Maximum Power Point Tracking (MPPT) algorithm in a solar charge controller is aimed at enhancing the efficiency of solar energy utilization. This algorithm optimizes power extraction from solar panels by dynamically adjusting the operating point to track the maximum power output under varying environmental conditions. By utilizing two MPPT trackers, the controller can efficiently handle scenarios with multiple peaks in the power-voltage curve, common in partially shaded or non-uniformly illuminated panels. This implementation involves real-time monitoring of panel voltages and currents, coupled with intelligent algorithms to swiftly respond to changes in irradiance levels. Through advanced control strategies, such as Perturbation and Observation (P&O) or Incremental Gradient (Incgrad), the system maximizes energy harvest, improving overall system performance and reliability.

Data-centric predictive control with tuna swarm optimization-backpropagation neural networks for enhanced wind turbine performance

Wind energy is a significant renewable resource, but its efficient harnessing requires advanced control systems. This study presents a Data-Centric Predictive Control (DPC) system, enhanced by a Tuna Swarm Optimization-Backpropagation Neural Network (TSO-BPNN) for predictive wind turbine control. It's like a smart tool that uses innovative fusion of deep learning, predictive Control, and reinforcement learning. Unlike traditional control methods, the proposed approach uses real-time data to optimize turbine performance in response to fluctuating wind conditions.The system is validated using simulations on the FAST platform, which demonstrate its superior performance in two critical operational regions. Specifically, in Region II, where the objective is to maximize power extraction from the wind, the DPC achieves a 1.07 % reduction in overshoot and an improvement of 36.14 units in steady-state error compared to traditional methods. The response time remains comparable to existing Model Predictive Control (MPC) strategies, ensuring real-time applicability without sacrificing efficiency. In Region III, where maintaining constant power output is crucial, the DPC outperforms both the baseline and MPC methods, reducing overshoot by 0.58 % and improving accuracy by 17.27 units compared to the baseline method. These results highlight the effectiveness of the proposed DPC system in optimizing turbine performance under variable wind conditions, offering a significant improvement over traditional methods in both accuracy and control precision.

Capabilities of cellebrite universal forensics extraction device in mobile device forensics

The powerful digital forensics tool cellebrite universal forensics extraction device (UFED) extracts and analyzes mobile device data, helping investigators solve criminal and cybersecurity cases. Advanced methods and algorithms allow Cellebrite UFED to recover data from erased or obscured devices. Cellebrite UFED can pull data from call logs, texts, emails, and social media, providing valuable evidence for investigations. The use of smartphones and tablets in personal and professional settings has spurred the development of mobile device forensics. The intuitive user interface speeds up data extraction and analysis, revealing crucial information. It can decrypt encrypted data, recover deleted files, and extract data from multiple devices. The sector's best data extraction functionality, Cellebrite UFED, helps forensic analysts gather crucial evidence for investigations. Legal and ethical considerations are crucial in mobile device forensics. Legal considerations include allowing access to data, protecting privacy, and adhering to chain of custody protocols. Ethics include transparency, defamation, and information exploitation protection. Using Cellebrite UFED, researchers can navigate complex data on mobile devices more efficiently and precisely. Artificial intelligence (AI) and machine learning (ML) algorithms may automate data extraction in future tools. Examiners must train, maintain, and establish clear protocols for using Cellebrite UFED in forensic investigations.

Dynamic feature and context enhancement network for faster detection of small objects

While traditional object detection methods have achieved significant success in recent years, their performance in detecting small objects in aerial remote sensing images remains unsatisfactory. Small objects often occupy only a few pixels, leading to a loss of fine-grained information. This paper proposes a dynamic feature and context enhancement network (DFCE) to address noise and pixel-level region weighting issues in small object detection. The DFCE network effectively detects small objects by dynamically selecting features within regions and establishing connections between local and global contextual information. The introduced dynamic multi-dimensional attention (DMA) module selects key information via a crossover mechanism and assigns different weights to highlight important features. Based on DMA, the regional feature processing (RFP) module and multi-dimensional pool transformer (MPT) module are developed to capture key information and contextual information, respectively. Experimental results demonstrate that the DFCE network improves average precision (AP) by 3.1%, 9%, and 2.2% on two remote sensing datasets and one conventional dataset, achieving an inference speed of 30 frames per second (FPS). Given these advancements, the DFCE model’s powerful key feature extraction and contextual association capabilities show strong potential for broader applications, including sign language recognition, defect detection in industrial settings, and more.

A GAN-based cyclic iterative unsupervised change detection network

ABSTRACT Remote sensing image change detection has significant applications across various fields. In recent years, the powerful feature extraction capability of deep learning technology has introduced innovative approaches to change detection methodologies. However, the accuracy of convolutional neural network algorithms hinges heavily on labelled data, necessitating substantial manpower and resources to generate labelled samples. Therefore, this paper proposes an unsupervised change detection model called CIUCD. This model operates on the fundamental premise of unsupervised change detection, employing a generator and a segmenter for iterative training. During each iteration, the generator and segmenter update and optimize their parameters, with the segmenter leveraging the generated change images as labels for training purposes. This iterative labelling process circumvents the need for manually labelled data, thereby mitigating the difficulty of obtaining change detection labels for actual remote sensing images. To validate the efficacy of the proposed model, we conducted experiments using actual remotely sensed images from the 2023 Turkey earthquake and the 2022 Afghanistan earthquake events. The results show that our method enhances the F1, Pr, Re and OA by 5.98%, 2.05%, 11.82% and 8.50% (Turkey earthquake), and by 9.54%, 5.87%, 4.52% and 11.34% (Afghanistan earthquake), respectively, when compared to the unsupervised change detection algorithm KPCA-Mnet. Experiments on real remote sensing images of 1000 × 1000 pixels showed that the CIUCD algorithm not only accurately detect larger change areas but is also capable of identifying changes in subtle objects such as solar panels. Additionally, the CIUCD algorithm is resilient to natural environmental factors like the angle of illumination, enabling precise predictions of changes in the actual remote sensing images and yielding clearer detection results. The performance of the CIUCD algorithm remains outstanding even when applied to larger images with a resolution of 3000 × 3000 pixels.

A hybrid BiLSTM-CNN deep learning model for Chinese sentiment analysis of online car reviews

Although sentiment analysis with datasets in English has achieved significant progress, there are still relatively few studies on sentiment analysis in the area of Chinesecar review texts. In addition, the existing Chinese text sentiment analysis methods cannot simultaneously extract the contextual features and the local semantic information from the review texts. To address the above issues, a hybrid deep learning model namely BiLSTM-CNN was designed and validated with Chinese car review texts. We trained word vectors with the CBOW model by combining the Chinese Wikipedia corpus with other open-source car-related corpora. Such word vectors include car-specific vocabulary, which improves sentimental classification accuracy. Experimental results show that the performance indices of the deep learning models (CNN, LSTM, BiLSTM) are much better than the KNN, SVM, Naïve Bayes, and RF model, which is attributed to deep learning's powerful feature extraction ability and nonlinear fitting ability. Furthermore, when compared to deep learning models such as CNN, LSTM, BiLSTM, and LSTM-CNN, the suggested hybrid BiLSTM-CNN model outperformed the others. The results may provide references for consumers to buy a car and for car companies to optimize their products.

Determination of I-V curves for photovoltaic generator by an analytical method; Akbaba model

In order to maximize the amount of electrical energy generated and ensure effective use, the conventional I-V or V-I characteristics derived from the diode model of Photovoltaic (PV) Solar Panels are important. Unfortunately, these features cannot be extracted using linear equations. It follows that the answer requires extremely drawn-out, time-consuming procedures. Many studies focus on calculating maximum power extraction. The analytical solutions to these equations are also nonexistent. Programming on computers can assist in solving the equations. The Akbaba Model was created specifically for the PVG to address these challenges. The Akbaba Model relies heavily on coefficients A, B, and C in this equation. The diode model serves as the true model in this case, and the coefficients A, B, and C are calculated. Another advantage of this model is that, because its qualities have partially deteriorated with time, the genuine I-V characteristics of the PV Panels can be recovered by measuring again.

Digital signal detection and recognition in the communication field combining DAEN and CNN

In communication, the detection and recognition of digital signals have always faced problems such as low adaptability and high misclassification rate. To address these issues, this study innovatively fused the deep auto-encoder network with convolutional neural networks to construct a novel digital signal detection and recognition model. Firstly, this study utilized the powerful feature extraction capabilities of the deep auto-encoder network to extract key feature information from massive amounts of data. Then these features were combined with convolutional neural networks to construct a detection and recognition model. These results confirmed that the constructed digital signal detection and recognition model had values of 93.75% and 94.18% in data detection recognition rate and average classification accuracy, respectively. Meanwhile, this model also performed well in terms of data processing accuracy and recall. In the comparison of data processing, the accuracy and recall rates were 93.59% and 94.67%, respectively, and the performance of data detection and recognition was better than that of the comparison methods. This indicates that the constructed digital signal detection and recognition model can significantly improve the reliability and robustness of signal detection and recognition. This paper brings new breakthroughs to the development of digital signal detection and recognition technology in communication.

A novel Beluga Whale Optimization for maximum power tracking in photovoltaic systems under shading and non-shading conditions

Partial shading poses a significant challenge for PV systems as it introduces multiple peaks in the panel output characteristics, making the power extraction process more complex. Efficiently locating the global maximum power from such a complex, non-linear curve is crucial for optimal system performance. Conventional MPPT techniques often fail to achieve this, resulting in reduced efficiency. Moreover, many metaheuristic algorithms struggle to balance tracking accuracy, convergence time, oscillations, and computational complexity. Therefore, this manuscript proposes a novel natural-inspired Beluga Whale Optimization (BWO) technique that effectively track the global maximum power without compromising its performance. This iteration-based algorithm integrates effective exploration through twin equations, incorporating the influence of both the best and neighboring position with levy flight function to enhance effective exploitation, and additional particle updation using the whale fall process ensures simultaneous diverse searching phenomenon in complex search spaces resulting in smooth and faster convergence. The algorithm was extensively examined under USC and five PSCs on a 250 W panel using MATLAB 2021a Simulink platform. The effectiveness of the technique was benchmarked against state-of-the-art MPPT techniques such as PO, CSO, PSO, and GWO. The rating-based approach confirms that BWO outperformed these techniques with an average MPPT efficiency of 99.98 %, a tracking time of 0.3195 s, transient state oscillations of 10.85 %, and steady-state oscillations of just 0.000453 % within 4–5 iterations, and other related aspects. Finally, the hardware demonstration using Solar Array Simulator (SAS) validated the performance of the proposed algorithm in the real-time environment, guaranteed the suitability towards practical applications.

LDF-BNN: A Real-Time and High-Accuracy Binary Neural Network Accelerator Based on the Improved BNext.

Significant progress has been made in industrial defect detection due to the powerful feature extraction capabilities of deep neural networks (DNNs). However, the high computational cost and memory requirement of DNNs pose a great challenge to the deployment of industrial edge-side devices. Although traditional binary neural networks (BNNs) have the advantages of small storage space requirements, high parallel computing capability, and low power consumption, the problem of significant accuracy degradation cannot be ignored. To tackle these challenges, this paper constructs a BNN with layered data fusion mechanism (LDF-BNN) based on BNext. By introducing the above mechanism, it strives to minimize the bandwidth pressure while reducing the loss of accuracy. Furthermore, we have designed an efficient hardware accelerator architecture based on this mechanism, enhancing the performance of high-accuracy BNN models with complex network structures. Additionally, the introduction of multi-storage parallelism alleviates the limitations imposed by the internal transfer rate, thus improving the overall computational efficiency. The experimental results show that our proposed LDF-BNN outperforms other methods in the comprehensive comparison, achieving a high accuracy of 72.23%, an image processing rate of 72.6 frames per second (FPS), and 1826 giga operations per second (GOPs) on the ImageNet dataset. Meanwhile, LDF-BNN can also be well applied to defect detection dataset Mixed WM-38, achieving a high accuracy of 98.70%.

Evaluation of Echinacea purpurea Extracts as Immunostimulants: Impact on Macrophage Activation.

Echinacea purpurea has been traditionally used to strengthen the immune system. Therefore, herein, we investigated the potential of E. purpurea aqueous extracts (AEs) obtained from flowers (F), leaves (L), or roots (R) as an immune booster in human primary monocyte-derived macrophages (hMDMs). Additionally, to identify the main class of compounds (phenolic/carboxylic acids vs. alkylamides) responsible for the bioactivity, the three AEs were fractioned by semi-preparative high-performance liquid chromatography (HPLC). The AEs and the isolated phenolic/carboxylic acidic fractions were not cytotoxic for hMDMs for all tested concentrations, as confirmed by the metabolic activity and DNA content assays. Moreover, AE drastically induced the production of the interleukin (IL)-6 and tumor necrosis factor (TNF)-α, with a minimal effect on IL-1β and prostaglandin E2 (PGE2), supporting their potential for macrophage activation. Interestingly, in the presence of the phenolic/carboxylic acidic fractions, this efficacy considerably decreased, suggesting a complementary effect between compounds. AE also triggered the phosphorylation of the extracellular signal-regulated kinase (ERK) 1/2 and p38 signaling pathways and upregulated the cyclooxygenase (COX)-2 expression in hMDMs. Overall, AE-F was demonstrated to be the most powerful immunostimulant extract that can be related to their higher number in identified bioactive compounds compared to AE-L and AE-R. These results highlight the efficiency of E. purpurea AE to enhance the function of a key cell type of the immune system and their potential as immunostimulant formulations for patients with a compromised immune system due to certain diseases (e.g., acquired immunodeficiencies) and treatments (e.g., chemotherapy).

Wave-to-wire modelling and hydraulic PTO optimization of a dense point absorber WEC array

We investigate the hydrodynamic interactions and power extraction efficiency of a dense array of Point Absorber (PA) Wave Energy Converters (WECs) clustered around the fixed pillar of a wind turbine –the Ocean Grazer device– with a standard hydraulic Power Take-Off (PTO) system. Using potential flow theory, a detailed wave-to-wire model is developed in WEC-Sim with four distinct hydraulic PTO designs: i) Multi PTO-with individual hydraulic PTO systems for each buoy, ii) Shared PTO V1-with a unified PTO system for the entire array, iii) Shared PTO V2-with the accumulator volume split into two segments, and iv) Shared PTO V3-with four strategically distributed segments. Key parameters such as the diameter of the hydraulic pistons, volume and pre-charged pressure of the high-pressure accumulators, hydraulic motor displacement and the speed of the electric generator are optimized with a genetic algorithm and a parametric analysis across various sea states. The results highlight that strategically allocating the accumulators across the floaters of a dense WEC array can yield significantly higher power production and should be considered at the early design stages.

BIF-Net: Boundary information fusion network for abdominal aortic aneurysm segmentation

The accurate abdominal aortic aneurysm (AAA) segmentation is significant for assisting clinicians in diagnosis and treatment planning. However, existing segmentation methods exhibit a low utilization rate for the semantic information of vessel boundaries, which is disadvantageous for segmenting AAA with significant scale variability of vessel diameter (diameter ranges from 4 mm to 85 mm). To tackle this problem, we introduce a boundary information fusion network (BIF-Net) specially designed for AAA segmentation. BIF-Net initially constructs convolutional kernel functions based on Gabor and Sobel operators, enriching the global semantic features and localization information through the Gabor and Sobel dilated convolution (GSDC) module. Additionally, BIF-Net supplements lost boundary feature information during the sampling process through the guided filtering feature supplementation (GFFS) module and the channel-spatial attention module (CSAM), enhancing the ability to capture targets with shape diversity and boundary features. Finally, we introduce a boundary feature loss function to alleviate the impact of the imbalance between positive and negative samples. The results demonstrate that BIF-Net outperforms current state-of-the-art methods across multiple evaluation metrics, achieving the highest Dice similarity coefficient (DSC) accuracies of 93.29 % and 91.01 % on the preoperative and postoperative datasets, respectively. Compared to the state-of-the-art methods, BIF-Net improves DSC by 6.86 % and 3.85 %. Due to the powerful boundary feature extraction ability, the proposed BIF-Net is a competitive AAA segmentation method exhibiting significant potential for application in diagnosis and treatment processes of AAA.

Car detection algorithm in urban based on YOLOv5

Car detection is essential to promote the development of intelligent technologies such as autonomous driving and car forward collision warning. To deal with low detection accuracy, poor real-time performance and robustness of existing object detection algorithms, a YOLOv5-based car detection algorithm is used. The advanced structure design of Backbone, Neck and Head in YOLOv5 demonstrates powerful feature extraction and multi-scale object detection capabilities. The detection results reveal that the algorithm is able to quickly recognize cars in images in different urban scenes, and the detection accuracy can reach more than 95%, which can satisfy the application demands for real-time car detection.

Optimasi Metode Microwave-Assisted Extraction (MAE) untuk Menentukan Kadar Flavonoid Total Ekstrak Etanol Kulit Pisang Kepok (Musa Paradisiaca.L)

Indonesia is a country that has a lot of banana diversity. One of the banana plants that is widely found in Indonesia is the Kepok banana (Musa Paradisiaca.L). Kepok banana skin has a very high content of flavonoids and phenols. Flavonoids are known as good antioxidants because they can find reactive oxygen species with the phenolic hydroxyl group that flavonoids have. The aim of this research was to determine the results of the optimization of the Microwave-Assisted Extraction (MAE) method on the total flavonoid content of kapok banana peel ethanol extract. Microwave-Assisted Extraction (MAE) was done to extraction flavonoid from ethanol extract of kepok banana peel (Musa Paradisiaca.L). The sample collected from Widoro village, Karangsambung sub-district, Kebumen regency. Optimum extraction condition was determined by the Response Surface Methodology (RSM). The Box- Behnken design (BBD) was used to evaluate the influence of 3 factors with 3 levels extraction that is power level (10%, 30%, 50%), ethanol concentration (50, 70, 96%), and extraction time (3, 5 and 7 minutes) with 15 different runs. The research showed that optimum extraction condition was at 24,14 % of power level, 66,26% ethanol concentration, and time extraction of 3,52 minutes with calculations from the Design Expert program, the total flavonoid content response was 8.491 Mg QE/g. The total flavonoid content value obtained experimentally was 8,246 Mg QE/g under condition of 30 % power level, 70% ethanol concentration, and time extraction of 5 minutes. Based on the result, total flavonoid content can be significantly increased by optimizing the MAE process use RSM.

Performance evaluation of fuel cell based on a DC-DC boost converter through optimized MPPT controller

The current electric vehicle domain is increasingly focused on fuel cell technologies due to its flexibility, steady supply of power, low atmospheric pollution, increased startups, and rapid responses. Fuel cells exhibit nonlinear power versus current characteristics, making it challenging to extract maximum peak power from the fuel stack. To address this, this work introduces an adaptive Coati Optimization algorithm combined with a Tilt-integral-derivative (TID) controller (TID-ACOA) to find the maximum power point (MPP) of the fuel stack systems, ensuring maximum power extraction. The proposed MPPT controller is compared with other MPPT controller, including PI, TID, and TID-COA. Comprehensive evaluations are conducted on tracking current, voltage, maximum power extraction, MPPT controller efficiency, converter voltage settling time, and oscillations. The fuel stack’s low output voltages are enhanced using a boost DC-DC converter, and the entire fuel stack-fed boost converter systems is modeled using MATLAB/Simulink. Simulation result show that the TID-ACOA MPPT controller achieves higher MPP tracking efficiency compared to conventional controllers.