Aiming at the problems of inefficient detection caused by traditional manual inspection and unclear features in metal surface defect detection, an improved metal surface defect detection technology based on the You Only Look Once (YOLO) model is presented. The shallow features of the 11th layer in the Darknet-53 are combined with the deep features of the neural network to generate a new scale feature layer using the basis of the network structure of YOLOv3. Its goal is to extract more features of small defects. Furthermore, then, K-Means++ is used to reduce the sensitivity to the initial cluster center when analyzing the size information of the anchor box. The optimal anchor box is selected to make the positioning more accurate. The performance of the modified metal surface defect detection technology is compared with other detection methods on the Tianchi dataset. The results show that the average detection accuracy of the modified YOLO model is 75.1%, which ia higher than that of YOLOv3. Furthermore, it also has a great detection speed advantage, compared with faster region-based convolutional neural network (Faster R-CNN) and other detection algorithms. The improved YOLO model can make the highly accurate location information of the small defect target and has strong real-time performance.

The reliability of power packs is very important for the performance of electronic equipment and ensuring the reliability of power electronic circuits is especially vital for equipment security. An alteration in the converter component parameter can lead to the decline of the power supply quality. In order to effectively prevent failure and estimate the remaining useful life (RUL) of superbuck converters, a circuit failure prognostics framework is proposed in this paper. We employ the average value and ripple value of circuit output voltage as a feature set to calculate the Mahalanobis distance (MD) in order to reflect the health status of the circuit. Time varying MD sets form the circuit state time series. According to the working condition time series that have been obtained, we can predict the later situation with support vector regression (SVR). SVR has been improved by a modified grey wolf optimizer (MGWO) algorithm before estimating the RUL. This is the first attempt to apply the modified version of the grey wolf optimizer (GWO) to circuit prognostics and system health management (PHM). Subsequently, benchmark functions have been used to validate the performance of the MGWO. Finally, the simulation results of comparative experiments demonstrate that MGWO-SVR can predict the RUL of circuits with smaller error and higher prediction precision.

The auxiliary converter is the power source of the vehicular electronic system, the failure of which may cause inestimable economic loss. As the most age-affected component in the converter, the online health monitoring for output aluminum electrolytic capacitor (AEC) is of great significance. Throughout the full-life period of AEC, the capacitance ( $C$ ) will fall and the equivalent series resistance (ESR) will rise. This article proposes an online proactive health monitoring method for output capacitors of a 1-kW vehicular auxiliary converter. The operating mechanism of the two-level Boost-LLC converter is analyzed and the ESR calculation model is derived in detail. A novel ripple measurement approach and a peak current calculation method are proposed. Both ripple measurement and current approximation are confirmed to be practical and applicable. Finally, the online health monitoring platform is built. The experimental results can show the effectiveness of this method. The monitored ESR can indicate the healthy degree for the output capacitors in the auxiliary converter. The influences of switching frequency and ambient temperature are verified to express the superiority of the online monitoring scheme.

How to extract the fault feature and how to design the classification algorithm are the two most critical problems in power electronic circuits (PECs) fault diagnosis. Based on a kernel entropy component analysis theory, combining an extreme learning machine classification algorithm, this paper explores the feasibility of applying an ensemble approach, called KECA-ELM, to deal with the hard fault and soft fault diagnosis in a superbuck converter circuit (SCC). This approach can reduce the influence of the complex correlation between the data on the accuracy of fault classification. Furthermore, it can compress the feature dimension of the data while maintaining the feature discriminating power and reduce the computation in the classification stage. We record the signal from the output of the circuit, analyze their static and dynamic electrical performance, and then select the representative feature parameters. These feature parameters are combined into feature vectors which can reflect the health status of the PECs. Finally, simulation and physical experiment are presented in the SCC to demonstrate the fault classification ability of the proposed approach.

This paper presents an enhanced YOLOv8 model designed to address multi-target detection challenges in complex traffic scenarios. The model integrates the Squeeze-and-Excitation attention mechanism, the deformable convolution C2f module, and the smooth IoU loss function, achieving significant improvements in detection accuracy and robustness in various complex environments. Experimental results show that the enhanced YOLOv8 model outperforms existing YOLO solutions across multiple metrics, particularly in precision and recall. Specifically, the enhanced model achieves 83.8% precision and 82.7% recall, improving 1.05 times in precision and 1.1 times in recall compared to the average precision (79.7%) and recall (75.4%) of other YOLO series models. In terms of mAP_0.5, the enhanced model achieves 89%, representing a 1.05-fold improvement over the average mAP_0.5 (84.4%) of YOLO series models. For mAP_0.5:0.95, the enhanced model reaches 76.5%, which is a 1.1-fold improvement over the average mAP_0.5:0.95 (69.7%) of YOLO series models. These improvements demonstrate the superior performance of the proposed model in multi-scale and complex scenarios, providing strong support for intelligent transportation systems and autonomous driving.

Hybrid cascaded multilevel inverters have been proved to be an important alternative in the medium-voltage applications for their high-quality output. To reduce the use of dc sources, the single dc source cascaded H-bridge (SDS-CHB) inverter with the low-voltage dc source replaced by a capacitor is employed and investigated in this article. To address the challenge of the input capacitor voltage regulation, the charge/discharge modes with carrier-based pulsewidth modulation at different operation conditions are analyzed in detail and generally for all the combinations of load current magnitude and power factor from −1 to 1. The stability conditions for capacitor voltage control are analytically derived. Based on the analysis, a simple but effective capacitor voltage regulation strategy and an operation parameter optimization method are proposed. Within the identified stable operation regions, the proposed control strategy can keep the input capacitor voltage at the desired voltage level, i.e., half of the high-voltage cell dc source meanwhile can ensure the inverter high-quality output. The proposed operation parameter optimization method can minimize the output filter capacitor with good output. The capacitor voltage regulation strategy and operation parameter optimization method have been successfully substantiated by the simulation and experimental results of a seven-level hybrid cascaded inverter.