Under raising pressure of global energy and environmental issues in recent years, electric vehicles (EVs) have been an alternative solution of the automobile industry owing to its high energy efficiency, low noise, and zero emission. However, the short driving range is an urgent problem to be solved for EVs. Energy recovery is an important technology to improve energy efficiency and extend driving range of EVs. In this paper, an improved braking energy recovery strategy based on ideal braking force distribution (curve I) was proposed for the regenerative braking system (RBS) of a small four-wheel drive (FWD) EV. Compared with previous study, the improved braking energy recovery strategy gives more consideration to braking stability and covers broader braking situations of the vehicle. The braking energy recovery strategy is extensively validated through numerical simulations of a previously built vehicle system model under different fixed braking strength and continuously varying braking strength. The simulation results show that the proposed braking energy recovery strategy is able to effectively achieve the regenerative braking function under different braking conditions while ensuring braking efficiency and braking stability.

Coasting in gear is a common driving mode for the conventional vehicle equipped with the internal combustion engine (ICE), and the assistant braking function of ICE is utilized to decelerate the vehicle in this mode. However, the electric vehicle (EV) does not have this feature in the coasting mode due to the relatively small inertia of the driving motor, so it will cause the driver cannot obtain the similar driving feeling to that of the conventional vehicle, and even a traffic accident may occur if the driver cannot immediately adapt to the changes. In this paper, the coasting control for EV is researched based on the driving feeling. A conventional vehicle equipped with continuously variable transmission (CVT) is taken as the reference vehicle, and the combined simulation model of EV is established based on AVL CRUISE and MATLAB/Simulink. The torque characteristic of the CVT output shaft is measured in coasting mode, and the data are smoothed and fitted to a polynomial curve. For the EV in coasting mode, if the state of charge (SOC) of the battery is below 95%, the polynomial curve is used as the control target for the torque characteristic of the driving motor, otherwise, the required torque is replaced by hydraulic braking torque to keep the same deceleration. The co-simulation of Matlab/Simulink/Stateflow and AVL CRUISE, as well as the hardware-in-loop experiment combined with dSPACE are carried out to verify the effectiveness and the real-time performance of the control algorithm. The results show that the EV with coasting braking control system has similar driving feeling to that of the reference vehicle, meanwhile, the battery SOC can be increased by 0.036% and 0.021% in the initial speed of 100 km/h and 50 km/h, respectively. The proposed control algorithm for EV is beneficial to improve the driving feeling in coasting mode, and it also makes the EV has the assistant braking function.

Addressing the urgent need for real-time detection of cracked eggs on production lines, this study proposes a high-precision real-time detection algorithm based on an improved YOLOv8 framework. This study innovatively introduced a dual-detection method, incorporating a "crack region" classification to assist in distinguishing between intact eggs and cracked eggs. This method identifies cracked eggs by recognizing either local or overall crack characteristics, effectively reducing both false negatives and false positives. At the architectural level, the model innovatively integrates Weighted Bidirectional Feature Pyramid (BiFPN) to optimize multi-scale feature fusion, Deformable Convolutional Network v2 (DCNv2) to enhance perception of irregular geometric deformations in cracks, Weighted Intersection over Union v2 (WIoUv2) loss function to improve detection accuracy for occluded samples, and adds a small object detection layer to strengthen recognition of minute defects. Experiments demonstrate that the improved model achieves a mean average precision (mAP) of 92.9% on the test set, representing a 5.2% improvement over the original model and outperforming current mainstream detection models. In real-world production deployment testing, the system achieved a real-time detection speed of 45 FPS, with a false negative rate of only 0.46% and a false positive rate of 2.18% for intact eggs, while keeping the false positive rate for broken eggs below 2%. This performance far surpasses that of the original model and fully meets the requirements for industrial-grade real-time online quality inspection. This study provides an efficient solution for egg quality inspection with significant engineering application value.