Search

The detection of faults in solar panels is essential for generating increased amounts of renewable green energy. Solar panels degrade over time due to physical damage, dust, or other faults. Numerous studies have been conducted to detect and monitor solar panel faults in real-time. This research examines the deployment of deep learning models for identifying these faults. In this research, we propose a novel deep learning model combining the InceptionV3-Net with U-Net architecture. The proposed architecture applies the InceptionV3 base with ImageNet weights, enhanced by convolutional layers, squeeze-and-excitation (SE) blocks, residual connections, and global average pooling. The model includes two dense layers with LeakyReLU and batch normalization, ending with a Soft-Max output layer. Incorporating image segmentation into deep learning models significantly improves the precision and test accuracy of identifying issues in solar panels. The proposed model achieves exceptional performance, having a validation accuracy of 98.34%, a test accuracy of 94.35% with an F1 score of 0.94, a precision of 0.94, and a Recall of 0.94.

In recent years, significant efforts have been made to enhance the power-harnessing capacity of photovoltaic (PV) systems. Despite advancements, PV systems remain less efficient. Faults occurring in the PV system are one of the major reasons for reduced output power. Improving PV system efficiency reduces overall costs and extends the system’s operational lifespan. This research utilizes a machine learning-based non-linear Gaussian posterior distribution (GPR) algorithm for detecting, classifying, and localizing various faults in PV systems. The proposed technique uses solar cell parameters to classify the faults based on the severity levels. The experimental results validate the effectiveness of the proposed approach, emphasizing its potential to improve PV system performance and reliability. The model statistics show that training time for squared exponential GPR is shorter than exponential and rational quadratic GPR models, with squared exponential GPR taking 2771.5 s, while exponential GPR and rational quadratic GPR took 4227.6 s and 6660.5 s, respectively. Despite longer training time, rational quadratic GPR has the lowest root mean squared error (RMSE) validation, ranging from 0.016598 to 0.025616, among the three approaches. Exponential GPR, with an RMSE range of 363.59 to 397.1 across various faults, was chosen for its superior performance when compared to the other approaches.

In the wind turbine remote fault diagnosis, sensor data is susceptible to low-quality phenomena such as missing and damaged data due to communication delays, environmental noise, and sensor faults. These issues decrease the accuracy of fault diagnostic models (FDMs), necessitating a solution to enhance model robustness under non-ideal sensor data conditions. Hence, a robust fault diagnostic scheme based on adaptive noise filtering and useful feature-domain enhancement (UFDE) is proposed in this article to improve the stability of fault diagnostic performance. An interference identification branch (IIB) is designed to analyze sensor data from a high-dimensional and multilevel perspective, automatically identifying and localizing feature noise during training. Subsequently, a UFDE mechanism containing three feature mapping modes is created, using adaptive mapping and filling of fault features in the neighborhood to eliminate feature noise and enhance the useful feature domain. This process improves the representation of fault features under non-ideal sensor data conditions, such as noise interference and data defects, thereby enhancing the FDMs robustness. Finally, under non-ideal sensor data conditions, comparative experiments with advanced fault diagnostic methods demonstrate that the proposed method exhibits minimal fluctuations in diagnostic accuracy and achieves the highest correctness rate, validating its robustness.

This article deals with the measurement of the hand keypoints in a vision-based setup under different constraints. Hand keypoint detection (HKD) plays a crucial role in many gesture-based applications. However, developing a generalized detection method has remained a long-standing problem. Several factors impede accurate detection: the fingers’ distance from the camera and their nearness, self-occlusion, variations in illumination, and background clutter. To overcome these barriers, we propose a two-stage architecture. The first stage generates precise hand regions, eliminating adjoining skin regions and background clutter. The second stage incorporates a novel multiscale attention block to detect keypoint coordinates precisely. Qualitative and quantitative evaluations found that the proposed architecture outperforms state-of-the-art models, with endpoint errors as low as 2.3, 1.14, and 2.11 pixels for the three benchmark datasets. This advancement lays the groundwork for future 3-D hand pose estimation developments and their applications.

Thyroid disease has been on the rise during the past few years. Owing to its importance in metabolism, early detection of thyroid disease is a task of critical importance. Despite several existing works on thyroid disease detection, the problem of class imbalance is not investigated very well. In addition, existing studies predominantly focus on the binary-class problem. This study aims to solve these issues by the proposed approach where ten types of thyroid diseases are considered. The proposed approach uses a differential evolution (DE)-based optimization algorithm to fine-tune the parameters of machine learning models. Moreover, conditional generative adversarial networks are used for data augmentation. Several sets of experiments are carried out to analyze the performance of the proposed approach with and without model optimization. Results suggest that a 0.998 accuracy score can be obtained using AdaBoost with DE optimization which is better than existing state-of-the-art models.