This paper studies the electrical properties (water absorption, dielectric strength) of (Epoxy) and Ethylene Propylene Rubber (EPR) blend with different content under different environment conditions at atmospheric te...
详细信息
ISBN:
(纸本)9781665408738
This paper studies the electrical properties (water absorption, dielectric strength) of (Epoxy) and Ethylene Propylene Rubber (EPR) blend with different content under different environment conditions at atmospheric temperature. the results of the test showed improvement in the dielectric strength with increasing the EPR content in the blends samples and a decrease in water absorption. artificial ecosystem-based optimization (AEO) and Manta ray foraging optimization (MRFO) are optimization approaches for solving optimization problems. They were used to determine the optimal value of the percentage of EPR in the Blend parameter for improving the electrical properties of Epoxy and EPR blend with different content under different environment conditions at atmospheric temperature. The AEO algorithm was a fast and effective method at finding the best values of the percentage of EPR in the Blend parameter comparing with the MRFO technique.
In this study, the performance of a solar thermoelectric air-conditioning system (STEACS) is predicted using advanced optimized artificial intelligence models. A STEACS powered by solar PV panels is experimentally tes...
详细信息
In this study, the performance of a solar thermoelectric air-conditioning system (STEACS) is predicted using advanced optimized artificial intelligence models. A STEACS powered by solar PV panels is experimentally tested under different cooling loads varying from 65.0 to 260 W. The obtained experimental data are used to train and test the model. The model consists of a random vector functional link (RVFL) network optimized by one metaheuristic optimizer such as jellyfish search algorithm (JFSA), artificial ecosystem-based optimization (AEO), manta ray foraging optimization (MRFO), and sine cosine algorithm (SCA). The inputs of the model were time, solar irradiance, ambient temperature, wind speed, and humidity. The predicted responses of the investigated system are the input current of PV, the average temperature of the air-conditioned room, the cooling capacity, and the coefficient of performance. The accuracy of the four models is evaluated using eight statistical measures. RVFL-JFSA outperformed the other models in predicting all responses with a correlation coefficient of 0.948-0.999 and, consequently, it is recommended to use it to model STEACS system.
This study proposes a two-step method for generating switching angles in renewable energy systems that use multi-level inverters (MLIs) to reduce low-order harmonics. The Selective Harmonic Elimination Pulse Width Mod...
详细信息
This study proposes a two-step method for generating switching angles in renewable energy systems that use multi-level inverters (MLIs) to reduce low-order harmonics. The Selective Harmonic Elimination Pulse Width Modulation (SHE-PWM) technique is used for MLI control, but it can be computationally intensive for real-time applications. To address this challenge, the proposed approach consists of a two-stage process. In the first stage, the SHE equations are solved offline using artificial ecosystem-based optimization (AEO). The obtained switching angles are then used to train an artificial neural network (ANN) prediction model in the second stage. The AEOANN-based SHE-PWM technique is applied to a reduced-switching, 3-phase, 7-level MLI. Simulations in MATLAB/SIMULINK show that the proposed method achieves accurate voltage control with less than 0.2% error, even for changing voltages, and reduces selected harmonics to less than 0.05%. The desired output voltage exhibits minimal total harmonic distortion (THD). This method offers a promising way to generate switching angles in renewable energy systems that use MLIs, improving power quality and reducing harmonic distortion.
Generally, skin cancer occurs due to anomalous growth of cells in human skin due to the activation of mutation by unusual Deoxyribonucleic Acid (DNA) damages. The survival rate of skin cancer is increased by providing...
详细信息
Generally, skin cancer occurs due to anomalous growth of cells in human skin due to the activation of mutation by unusual Deoxyribonucleic Acid (DNA) damages. The survival rate of skin cancer is increased by providing efficient and accurate treatment in time at an early stage. However, analysis of skin images manually is expensive and time-consuming, and it also encountered many challenges while detecting skin cancer from a complex background. In this research, a Jaya artificialecosystem -basedoptimization-LeNet (JAEO-LeNet) scheme is developed for skin cancer detection at the initial stages from skin images. The bilateral filter is used to denoise the input skin image, which is further allowed for skin lesion segmentation using TransUNet. The augmentation of segmented skin lesion images is accomplished and from the augmented image, various features are extracted. A deep learning model, LeNet is employed for skin cancer detection from the extracted features. The JAEO algorithm is proposed for tuning the weights of LeNet to enhance the detection performance more effectively. The SIIM-ISIC Melanoma classification database is used for the validation of skin cancer detection. In addition, the JAEO-LeNet attained maximum performance with accuracy, sensitivity, and specificity of 91.99 %, 90.95 %, and 92.13 %.
暂无评论