成果筛选
院系部门
共找到429结果
筛选条件 : 机械工程学院
Luo, Jiangnan; Cai, Jinyu; Li, Jianping; Zhang, Deyi; Gao, Jiuhua; Li, Yuze
Applied Intelligence, 2025 55 (2) - EI SCIE

摘要 : Drilling for gas extraction, a common method in coal mine gas control, involves tedious loading and uploading of drill pipes. This study aims to design a method for detecting and measuring pose drill pipes using point cloud data. We present an experimental platform for acquiring drill pipe point cloud data under various lights. Additionally, we propose a GA-PointNet + + model, enhanced with an adversarial generation network. The pose of the drill pipe was calculated from the segmented pipe and pin point clouds. Results indicate that the intersection-over-union (IoU) values for pipe and pin, based on GA-PointNet + +, are 0.824 and 0.472, respectively. Evaluating the model's performance in recognizing the pin using the ROC curve yielded an AUC of 0.87. The combination of GA-Pointnet + + and RGB-D camera was used to pose drill pipes, achieving an average accuracy of 82.5% under different lighting conditions. Under lighting conditions of 25–35 lx with an added diffuser film and 10–15 lx, the accuracy reaches 90%, with average distance errors of 1.4 cm and 2.5 cm, and average angle errors of 3.5° and 3.7°, respectively. This has significant implications for the use of LED lights in underground environments. Therefore, the proposed drill pipe pose measurement method is of great significance for the intelligentization of coal mine drilling operations.

Chen, Zhihao; Liu, Jiahao; Min, Shuqiang; Zhan, Tonghuan; Huang, Yange; Wu, Xianchang
Microfluidics and Nanofluidics, 2025 29 (1) - EI SCIE

摘要 : Inexpensive, autonomous, easy to fabricate and portable self-powered microfluidic pumps are urgently required especially in rapid point-of-care testing (POCT). Here, we propose a "Plug-n-Play" permeable brick-based (PB) micropump for autonomous and continuous liquid flow without any external power sources. The key advantage of this pump is that its operation only requires the user to place the PB pump on the outlet of microfluidic devices. The PB pumps are fabricated by simply slicing permeable bricks into predetermined shapes. The microcosmic morphology investigations unveil that their unique porous structures and uneven surface provide outstanding capillary force. For instance, a typical cuboid PB pump (2 × 2 × 2 cm3) can produce an average flow rate of more than 100 μL min− 1, a working time of 10 min and a maximum liquid absorption volume of ~ 1200 μL. Also, the flow rate and absorption volume can be programmed by using the PB pumps with different shapes. Moreover, we apply hydrophobic reagents (Glaco) treatment on the PB pumps to achieve the control over the liquid flow rates. Finally, through applying the PB pumps, we can perform blood type detection in POC cases. Based on its advantages of low cost, long service life, and adjustable flow rates, brick pump can be easily integrated into microfluidic systems and has great potential for microfluidic applications, especially in developing regions or in resource-limited settings.

Zhihao Chen; Shuqiang Min; Tonghuan Zhan; Xianchang Wu; Jiahao Liu; He Wang
Colloids and Surfaces A, 2025 708 - EI SCIE

摘要 : Breakthrough pressure represents a pivotal criterion that directly influences the unidirectional liquid transport of a Janus membrane. However, most studies focus on reducing positive breakthrough pressure (a low positive one is beneficial for the positive transport of liquids), neglecting how to increase reverse breakthrough pressure (a high reverse one can effectively prevent the reverse permeation of liquids). Herein, a Janus membrane with inverted conical pores (JM-ICP)(the hydrophobic layer with small openings, the hydrophilic layer with large openings) was proposed to address the above issue. Compared to Janus membranes with positive conical pores (large openings on the hydrophobic side, small openings on the hydrophilic side) and straight pores, our JM-ICP can achieve larger reverse breakthrough pressure (up to ∼145 mm H 2 O), while keeping the positive one extremely low (∼2 mm H 2 O). Furthermore, the fluid simulations were utilized to unveil inverted conical micropores enhancement mechanism. Finally, as a proof-of-concept demonstration, the JM-ICP with high reverse breakthrough pressure renders it suitable for water level detection. This article aims to demonstrate that the inverted conical pores are beneficial for increasing reverse breakthrough pressure, and propose a new mechanism of the Janus membrane in improving its breakthrough pressures.

Chenwei Dai; Qihui Cheng; Qing Miao; Zhen Yin; Ming Zhang; Jiajia Chen
Materials Science in Semiconductor Processing, 2025 187 - EI SCIE

摘要 : At present, because of the lack of ultrasonic composite vibration assisted grinding mechanism, neural network optimization algorithm (NNOA) is used to optimize the processing results. In NNOA, multi-layer perceptron (MLP) neural network model and non-dominated sorting genetic algorithm-II (NSGA-II) are very efficient and accurate methods. In this paper, based on the measurement and analysis of the specific ultrasonic vibration device, the CUVAG experiments on silicon carbide (SiC) ceramic were carried out to investigate the influence of processing parameters on the grinding forces, the ground surface roughness and morphology, and the subsurface damage. Then, the brittle-ductile removal behavior of hard-and-brittle materials could be revealed according to the above analysis. After that, MLP model and NSGA-II were utilized to predict and optimize the processing results in CUVAG. The results show that the grinding forces are basically constant, the surface quality deteriorates, and the subsurface damage increases with increased axial vibration amplitude and workpiece infeed speed, but all fluctuate with enlarged wheel speed, and turns at the inflection point of brittle-ductile transition with increased elliptic vibration amplitude. The fitting goodness R 2 of the established MLP neural network prediction model is between 0.94 and 0.975, and the process parameters calculated by the NSGA-II optimization algorithm are verified. With optimized processing parameters, the grinding forces are reduced by about 13 %, the surface roughness is reduced to Ra0.037 μm (by 29 %), and the depth of subsurface damage is reduced by 68 %.

Guizhong Fu; Jiaao Chen; Shikang Qian; Jing Miao; Jinbin Li; Quansheng Jiang
Measurement, 2025 243 - EI SCIE

摘要 : In the field of precision manufacturing, machine vision technology is gradually replacing traditional manual inspection methods as a key technology to improve product quality. In precision manufacturing companies, weak defects on the product surface are unacceptable. However, existing defect detection methods rarely focus on the weak surface defect detection task. To address this challenge, we acquire and build a dataset called USB-DET, which contains weak defect samples. Then, we propose an innovative lightweight deep learning model, SDIA-net, which integrates SPD-Conv, Dysample technique, and attention mechanism-iRMA, to improve the recognition and localization of weak defects effectively. On the USB-DET dataset, SDIA-net achieves 55.1% mAP, which is 3.2% higher than the existing SOTA models. The computational efficiency is 205.1 FPS, which satisfies real-time demands. SDIA-net's advantages make it well-suited for deployment in resource-limited precision manufacturing environments, providing an effective technical solution for product surface quality control with significant practical application value.

Hongzhuang Wu; Cheng Cheng; Deyi Zhang; Hongzhi Zhou
Engineering Applications of Artificial Intelligence, 2025 141 - EI SCIE

摘要 : Recently, the underground unmanned tunneling technology has received increasing attention, in which the pose estimation of the tunneling machinery occupies a prominent position. However, the autonomous positioning of the tunneling machinery presents significant challenges due to the harsh underground environments and the extremely complicated working conditions, which severely restricts the development and application of underground intelligent tunneling technology. Therefore, this paper investigates a machine vision and deep learning based pose estimation method for the underground tunneling machinery. Considering that both effective features and interference features of time-series images exhibit spatiotemporal correlations across multiple scales, we propose a multi-scale latent space sequential fusion (MSLSSF) model to integrate information from time-sequence images and further estimate the pose variables of the tunneling machine. The multi-scale variational autoencoder (MSVAE) is employed in the proposed model to obtain multi-scale latent space representations for each image in the time sequence. The proposed MSLSSF strategy consists of two steps. The first step involves fusing the latent representations of the time-series images at each scale using long short-term memory (LSTM) models, as specific correlations may exist in the representations of the sequential images across various scales. The second step employs an attention mechanism to adaptively fuse the results from the first step across all scales and timesteps. The presented information fusion methods provide a way for the model to take full advantage of the multi-scale features of time-sequence images. Experiments are conducted on our custom-made tunneling machine visual localization dataset, where the proposed MSLSSF based pose estimation method outperforms the advanced comparison methods in both accuracy and robustness, thereby validating the efficacy of the proposed approach. Additionally, the feasibility of the MSLSSF strategy is confirmed through the visualization results of the proposed model.

Zhihui Liu; Yumeng Yang; Yi Sun; Tengda Guo; Kai Shen; Yongjun Cheng
Small, 2025 21 (1) - EI SCIE
Zihan Deng; Jinbin Lu; Hongzhe Li; Yi Wu; Xinyu Xu; Qing Miao
Diamond and Related Materials, 2025 151 - EI SCIE

摘要 : For brazed tools, diamond is an optimal abrasive to process the hard and brittle materials, and the interface reaction between it and the filler alloy determines the performance of the brazed tools. This paper uses the first-principles methods to investigate the microscopic interaction behavior and formation mechanism of the interface between the Cr/Ti-doped Cu-based solid solution and diamond. We established four types of Cu-based solid solution(100)/diamond(100) interface models and calculated the adhesive work, interface structures, electronic structures, population analysis, and density of states. The results indicate that the adhesive work of the interfaces doped with Cr and Ti can be increased by about 16.6 % and 10.5 %, respectively, and it can continue to increase by 21.9 % and 4.1 % when the doping proportion is increased. In addition, the investigation of the electronic structures, population analysis, and density of states show that Cr and Ti elements facilitate the formation of more substantial chemical bonds at the interface. Therefore, doping Cr/Ti element can improve the bonding strength between diamond and Cu-based solid solution and enhance the wettability of Cu-based filler alloy to the diamond. Notably, the effect of doping the Cr element is significantly better than that of Ti, and the calculated results are also consistent with the experimental findings.

Lu Yang; Xi Chen; Jingxiang Zhang; Haoliang Zhang; Qiuying Zhao; Haiyan He
Surfaces and Interfaces, 2025 56 - SCIE

摘要 : High-efficient and recyclable piezo-photocatalysts are garnering substantial attention in line with the advancements in environmental purification. Herein, a novel micropatterned piezo-photocatalytic composite film, wherein BaTiO 3 @TiO 2 core-shell nanoparticles are embedded within porous poly(vinylidene fluoride) matrix, is developed. The impressive synergy between photocatalytic and dual piezocatalytic effects emanating from integrated components contributes to significantly amplified piezo-photocatalysis process. Moreover, by modulating the geometric structure of nanofiller along with topographical pattern design, one can further harness the piezo-photocatalysis effect upon electrical poling. As a result, the newly-developed composite film exhibits distinguished piezophotocatalytic activity, i.e., the degradation efficiency of highly-concentrated Methyl Orange (MO) solution (C 0 = 10 mg/L, 100 mL) reaches 97.3 % within 90 min, implying its viability as high-performance piezo-photocatalysts.

Dehao Li; Dan Wang; Yunfei Gao; Jun Duan; Zhiyan Li; Hao Chen
Vibrational Spectroscopy, 2025 136 - EI SCIE

摘要 : Nitrogen dioxide (NO 2 ) is a significant atmospheric pollutant with notable impacts on the environment and human health. The measurement of NO 2 concentration is crucial for gas phase analysis in atmospheric chemistry, assessment of regional pollution levels, and improvement of data management systems. In this paper, a highly sensitive cavity ring-down spectroscopy (CRDS) technique has been used to measure the concentration of NO 2 . The CRDS system utilizes a diode laser and high reflectivity mirrors (over 99.99 %) at 405 nm, achieving a minimum detection limit of 43 ppt (1σ, 40 s) and 92 ppt (1σ, 10 s) as determined by Allan variance. In order to improve the measurement accuracy and stability, the Kalman filtering has been used to process the background ring-down time and ring-down time, and the minimum detection limit can be increased by about 2.06 times to 45 ppt (1σ, 10 s), while preserving temporal response and reducing noise. Under the condition of atmospheric NO 2 measurement, a comparative experiment was carried out in Hefei with the CEAS system. The linear fitting slope was 1.033 ± 0.017, and the correlation coefficient reached about 92 %. The CRDS device was integrated for vehicle-mounted measurements of NO 2 concentrations in suburban, urban, and industrial areas of Maanshan City. The experimental result has demonstrated that this system can achieve high-precision, high-sensitivity, and stable measurements of NO 2 .