The tribological behavior of silicon nitride (Si₃N₄) ceramic with textured patterns under water lubrication was investigated in this paper. Different textured patterns were fabricated using laser surface texturing (LST). Surface wettability was characterized by contact angle. The original surface and textured Si₃N₄ ceramic with triangular patterns presented as hydrophobic. However, the textured Si₃N₄ ceramic with hexagonal patterns presented as hydrophilic. Surface wettability and textured patterns were important factors affecting the friction performance of the Si₃N₄ ceramic. Our results indicated that symmetrical textured patterns were more beneficial for decreasing the coefficient of friction (COF) at lower reciprocating frequencies. In contrast, better surface wettability played a more important role in reducing the COF at higher reciprocating frequencies. The most severe damage observed on the untextured Si₃N₄ ceramic led to a higher wear rate. The symmetrical structure of hexagonal patterns was more conducive to decreasing the wear rate than triangular patterns. However, the Si₃N₄ ceramic with triangular patterns was more suitable for use at high-speed frictions due to better lubrication. The textured patterns had the function of storing lubricants and capturing and cutting debris. Thus, friction performance was improved by introducing textured patterns onto the surface of the Si₃N₄ ceramic. The friction and wear mechanisms are also discussed in this study.

Accurate and timely forest fire detection is critical for early warnings and effective wildfire containment, safeguarding both ecological systems and human lives. However, in the early stages of a fire, the flames are typically small, and the smoke often bears a close resemblance to mist or fog, which makes prompt and accurate detection difficult and frequently causing the loss of the optimal response window. To tackle this challenge, we present an enhanced single-stage object detector, that excels at identifying fires, especially in their nascent stages. First, we incorporate a contrast enhancement technique that leverages an atmospheric scattering model and entropy optimization to clarify the blurred smoke edges. Next, we integrate deformable convolutions into the original feature extraction module, enabling more effective capture of long-range dependencies and spatial relationships, thus improving multi-scale fire detection accuracy. Additionally, we introduce a novel Hybrid Spatial Pyramid Pooling (HSPP) structure, which uses parallel average and max pooling operations to enrich feature extraction, facilitating better recognition of small-scale early fires. Finally, we propose a Dynamic Channel Attention (DCA) module to adaptively optimize cross-channel interactions across multiple feature extraction layers, bolstering cross-scale feature representations. Extensive experimental results show that on the M4SFWD and FLAME public datasets, our method achieves a 1% improvement in both precision and recall compared to the SOTA methods, while reducing the number of parameters by about 40%, making it more suitable for practical application.

As the car price war has intensified in China from 2023, the continuous decline in prices of new cars for both conventional fuel vehicles and electric vehicles (EVs) has led to a sharp decline in used cars. In particular, the EV market appears more vulnerable as the prime cost of battery raw materials has decreased since January 2023. And thus, a second-hand EV price prediction system is urgent. This study compares several methods for used EVs in China. We find that the random forest method and the gradient boosting regression tree (GBRT) method have good effects on predicting used EV prices in respecting price ranges. Timed EV data capture is applied to guarantee the real-time property of our prediction system. Then, we propose the concept of circular pricing, which means that the obsolete data for the priced car will be repriced according to the latest data. In this way, such a system can guide the used car dealers to adjust the price in time.

Silicon nitride (Si₃N₄) ceramic is widely used in the production of structural components. The surface wettability is closely related to the service life of materials. Laser surface texturing is considered an effective method for controlling surface wettability by processing specific patterns. This research focused on the laser surface texturing of a Si₃N₄ ceramic, employing rectangular patterns instead of the typical dimple designs, as these had promising applications in heat transfer and hydrodynamic lubrication. The effects of scanning speed and number of scans on the change of the morphologies and dimensions of the grooves were investigated. The results indicated that the higher scanning speed and fewer number of scans resulted in less damage to the textured surface. As the scanning speed increased, the width and depth of the grooves decreased significantly first, and then fluctuated. Conversely, increasing the number of scans led to an increase in the width and depth of the grooves, eventually stabilizing. The analysis of the elemental composition of different areas on the textured surface presented a notable increase in oxygen content at the grooves, while Si and N levels decreased. It was mainly caused by the chemical reaction between Si₃N₄ ceramic and oxygen during laser surface texturing in an air environment. This study also assessed the wettability of the textured surface, finding that the contact angle of the water droplet was significantly affected by the groove dimensions. After laser surface texturing, the contact angle increased from 35.51 ± 0.33° to 57.52 ± 1.83°. Improved wettability was associated with smaller groove volume, indicating better hydrophilicity at lower scanning speed and enhanced hydrophobicity with a fewer number of scans.