上海工程技术大学学报

2025, 39(3): 1-2.

Abstract:

[Abstract](26) [FullText HTML] (16) [PDF 367KB](2)

Research on lightweight rail fastener inspection model based on YOLOv5

XIE Xing, WANG Yue, LI Liming, ZHENG Shubin, PENG Lele, ZHU Ting

2025, 39(3): 257-265. doi: 10.12299/jsues.24-0050

Abstract:
Aiming at the issues of model parameter size, detection accuracy, and efficiency in rail fastener detection algorithms, a lightweight network model named YOLO-FBS based on YOLOv5n was proposed. The model embeds the Faster Block module to achieve a reduction in network parameters, introduces the SimAM parameter-free feature selection module and the CAFARE lightweight upsampling module to improve detection accuracy, and finally employs LAMP score-based pruning to remove channels with lower weights. The resulting YOLO-FBS model has only 0.28×10⁶ parameters, achieves a detection accuracy of 89.2%, and reaches a detection speed of 190.2 frames/s. This network model offers the advantages of low parameter count and high detection speed while maintaining high detection accuracy.

[Abstract](28) [FullText HTML] (15) [PDF 2655KB](3)

Development of adaptive front-light system based on rapid control prototype

MAO Zheng, ZHOU Jianpeng, GONG Yuanming

2025, 39(3): 266-273. doi: 10.12299/jsues.24-0119

Abstract:
Traditional vehicle lighting control system are characterized by low development efficiency, long iteration cycles, high costs of real-vehicle simulation, and an inability to meet the intelligent demands of modern automobiles. To address these issues, a calculation formula for the deflection of the headlamp's illumination angle was proposed based on the adaptive control logic of the headlamps, and a model of the adaptive front-lighting system (AFS) was constructed. Then, the AFS model was rapidly transformed intoan executable real-time system by utilizing the dSPACE-based rapid control prototyping (RCP) technology. Various complex driving scenarios were simulated to verify the accuracy and validity of the AFS control logic and the deflection of the illumination angle. The application results indicate that this development method shortens the system development cycle and improve development efficiency, and that the proposed AFS significantly enhances driving safety and comfort.

[Abstract](31) [FullText HTML] (16) [PDF 1895KB](3)

Optimization of preventive maintenance for airbag type cylinders of electric locomotives based on reliability

MAO Yongwen, LI Yong, SONG Ning

2025, 39(3): 274-279. doi: 10.12299/jsues.24-0116

Abstract:
To address the problem of under-maintenance and over-maintenance in the preventive maintenance of electric locomotive pantograph airbag cylinder, a method for optimizing inspection and maintenance parameters using failure data of the airbag cylinders was proposed. Firstly, based on the traditional preventive maintenance strategy, the graph parameter method was used to analyze whether the failure data of the airbag cylinders followed an exponential distribution. Subsequently, the Bartlett test was employed to verify the validity of this distribution assumption. Secondly, based on the characteristic constant failure rate of the airbag cylinders, a reliability model was established. Key reliability indicators, such as the instantaneous availability and steady-state availability, then derived, providing a basis for formulating the optimal preventive maintenance strategy. Thirdly, a minimum cost model for the preventive maintenance and replacement of the airbag cylinder was established, and the optimal preventive maintenance interval and maintenance cost were obtained. The optimized inspection and maintenance parameters for the airbag cylinders can provide scientific basis for maintenance personnel to improve quality and reduce maintenance costs.

[Abstract](24) [FullText HTML] (13) [PDF 728KB](1)

Analysis of competition and cooperation between airlines and OTA platforms based on evolutionary game theory

YANG Chenkai, HUANG Jianwei, WANG Zihan

2025, 39(3): 280-285, 291. doi: 10.12299/jsues.24-0046

Abstract:
To investigate the strategy choice between airlines and online travel agency (OTA) platforms within a competitive-cooperative context, an evolutionary game model was constructed. The replication dynamic equation and Jacobian matrix applied to explore the evolutionary trajectory of their strategies. Taking China Eastern Airlines and the OTA platform Ctrip as a case study, the impact of varying parameters on the strategies of both sides was examined through Matlab based evolutionary game simulation method. Research shows that the stable equilibrium result of evolutionary game is that China Eastern Airlines will adopt the strategy of "increasing direct sales and reducing agency sales", while the OTA platform will adopt the strategy of "retreating to the hotel and leasing industry".

[Abstract](19) [FullText HTML] (12) [PDF 1613KB](0)

Research on emergency response alertness and operational performance of subway drivers under shift system

WANG Xianchao, ZHU Lin, LIU Zhigang, CHEN Yixin

2025, 39(3): 286-291. doi: 10.12299/jsues.24-0114

Abstract:
The impact of shift system on the emergency response performance and alertness of subway drivers was investigated through simulation experiments. Emergency response performance was measured by the average response time and accuracy rate, while electroencephalogram (EEG) indicators included an alertness index calculated from SMR waves and the average EEG power ratio. Given the special nature of emergency response scenarios, partial gamma (γ) rhythms were incorporated into the calculation of both the alertness index and the average power ratio. The findings indicate that incorporating gamma-band rhythms can enhance the evaluation of changes in subway drivers' alertness levels. Drivers on the day shift exhibited higher alertness and better emergency response performance than those on the night shift. As task complexity increased, emergency response performance declined. Meanwhile alertness showed an trend, initially rising before subsequently falling.

[Abstract](20) [FullText HTML] (13) [PDF 1397KB](0)

Optimization of evaporator structure in a direct expansion solar heat pump

ZHOU Beiyan, HUANG Xinghua, HOU Xiaohan

2025, 39(3): 292-299. doi: 10.12299/jsues.24-0158

Abstract:
The optimization of the collector/evaporator structure in a direct-expansion solar heat pump system was investigated. A distributed parameter numerical model for a roll-bond collector/evaporator was developed and validated against experimental data. The effects of the path tube number arrangement and tube spacing on the collector/evaporator collector efficiency and the coefficient of performance (COP) of the heat pump system were simulated and analyzed. The results indicate that, for a given total number of tubes, a larger tube number ratio between the first and second paths can lead to a lower total refrigerant pressure drop and a higher evaporation temperature. The optimal heat collection efficiency and COP are achieved when the tube number ratio is 1∶1. Furthermore, as the tube spacing increases, both the heat collection efficiency and COP first increase and then decrease, reaching their maximum values at a tube spacing of 0.04 m.

[Abstract](25) [FullText HTML] (16) [PDF 1576KB](1)

Analysis of auxiliary gas flow field for laser cutting of medium-thick plates

WANG Xinyu, YE Xiao

2025, 39(3): 300-306. doi: 10.12299/jsues.24-0129

Abstract:
A three-dimensional mathematical model of the auxiliary gas flow field in laser cutting of medium-thickness plates was developed based on the Gaussian heat source equation, heat transfer equation, Reynolds-averaged N-S equation and SST k-ω turbulence model. The validity of the simulation model was verified by experiments. Based on the established model, the distribution of pressure, temperature, velocity and shear stress in the auxiliary gas flow field were analyzed, and the effect of nozzle inlet pressure on the dynamic performance of the flow field was investigated. The results show that a reasonable nozzle inlet pressure can improve the dynamic characteristics of the auxiliary gas and cutting quality.

[Abstract](22) [FullText HTML] (16) [PDF 1510KB](2)

Research on transmission backlash characteristics of end-effector in minimally invasive surgical robots

YU Yongchun, JIN Xiaoyi, QIAN Yawei, NIU Yibo, MENG Panpan

2025, 39(3): 307-313. doi: 10.12299/jsues.24-0093

Abstract:
Focusing on the end-effector of minimally invasive surgical robots, proposing a novel rotation mechanism and conducting numerical simulation and experimental research on its transmission backlash characteristics. A computational model for transmission backlash was established through theoretical derivation, with analysis of transfer deviation's impact on output torque under different influencing factors. Numerical results indicate that when output torque ranges from 0 to 0.3 N·m, the transfer deviation stays within 0° to 0.04°. Transmission backlash shows significant sensitivity to preload force and steel wire cross-sectional area, while being less affected by free wire segment length. A physical prototype and experimental platform were constructed to perform tracking experiments, measuring the end-effector's rotation angle threshold at ±74.29°. Data and error analyses of transmission backlash characteristics were conducted through simulations mimicking frequent surgical direction changes during operations.

[Abstract](22) [FullText HTML] (16) [PDF 1773KB](0)

Aperture compensation method based on projection error

LIU Fangji, ZHOU Yufeng

2025, 39(3): 314-319. doi: 10.12299/jsues.24-0165

Abstract:
To address the errors caused by the non-coincidence of the hole surface with the calibration plane in machine vision-based aperture measurement, as well as the edge degradation encountered during edge extraction, an aperture diameter compensation method based on perspective projection error was proposed. Edge detection was performed using an adaptive median filtering algorithm, and the aperture diameter was determined by employing quadratic curve invariant. Perspective projection error was then introduced to obtain the corrected hole diameter. A visual inspection experimental platform was constructed, and the test results demonstrate that the proposed compensation method achieves a measurement error within ± 0.002 mm, and a measurement accuracy of 0.001 mm. The method demonstrates a better compensation effect and can meet the enterprise's accuracy requirements.

[Abstract](22) [FullText HTML] (13) [PDF 1919KB](1)

Industrial equipment identification based on multimodal adaptive fusion

SHI Yicong, ZHAO Xiaoli, CHEN Mingxuan, ZHANG Yuyue

2025, 39(3): 320-325. doi: 10.12299/jsues.24-0133

Abstract:
Multimodal machine learning, which combines image and text data, is able to improve the accuracy of industrial equipment identification. To address the limitation that existing industrial equipment identification algorithms rely solely on image data and fail to leverage the widely available textual data in industrial settings, a multimodal industrial equipment identification model based on image and text was proposed. This model consists of a novel image-text dataset and a multimodal identification algorithm. The dataset images were collected from real scenarios, and the text was automatically annotated by a multimodal large model. The identification algorithm can adaptively adjust the weight of the modalities, integrate the information of the two modalities, and assist the model in decision-making. Experimental results show that the proposed algorithm can achieve an improvement of 17.62% in identification accuracy compared to single-modal image data, and outperforms other multimodal recognition algorithms by 5.3%, demonstrating its effectiveness.

[Abstract](26) [FullText HTML] (13) [PDF 1185KB](2)

Advances in synthesis and pharmacological effects of Bardoxolone and its derivatives

ZOU Yu, ZHUANG Chunlin, ZHAO Linjing

2025, 39(3): 326-332. doi: 10.12299/jsues.24-0199

Abstract:
Bardoxolone, also known as 2−cyano−3,12−dioxolanoleana−1,9(11)−dien−28−oic' acid (CDDO), is a pentacyclic triterpenoid synthesized from natural oleanolic acid through a series of chemical modifications. CDDO and its derivatives exhibit a broad pharmacological activities and have shown great potential in studies. In this review, recent advancements in the synthesis of CDDO and its derivatives were summarized. Their pharmacological effects and underlying mechanisms, including antitumor activity, anti-inflammatory properties, neuroprotection, kidney protection, antiviral activity, among others, were also dicussed. This review was conducted to provide valuable insights for the future development and application of these compounds.

[Abstract](23) [FullText HTML] (16) [PDF 768KB](0)

Performance research of MnO_x/Co₃O₄ composites within nanosheets for catalytic soot combustion

ZHANG Nianchen, WANG Chen, HAN Mengyu, QIU Jianqiang, WANG Jinguo

2025, 39(3): 333-340. doi: 10.12299/jsues.24-0127

Abstract:
Catalytic combustion is presently considered as one of the most effective methods to control soot particles from diesel exhaust, while its key issue is how to construct efficient catalysts. Herein, a series of MnO_x/Co₃O₄ composites within nanosheets were prepared using the hydrothermal integrating with wet-impregnation approach, chiefly aiming to catalyze soot purification. Experimental results indicate that, 20MnCo nanosheet composites with Mn/Co molar ratio of 20% show the optimal soot purification performance with T_m of 354 ℃ and 100% CO₂ selectivity, mainly attributing to the three aspects: 1) porous nanosheets with high surface area and rich pores not merely improved the contact area of composites and soot, but also benefited the decreased mass transfer resistance of gas reactants; 2) loading MnO_x led to the increased ratio of Mn³⁺ and Co³⁺ on composite’s surface, which favored the activating the adsorbed oxygen species on composite’s surface to generate more reactive oxygen species; 3) loading MnO_x resulted in the improved redox ability that facilitated NO oxidation to produce NO₂. Meanwhile, 20MnCo nanosheet composites demonstrated the good recycling stability, showing a good application prospect.

[Abstract](21) [FullText HTML] (14) [PDF 2688KB](0)

Optimization of virtual fabric draping effect based on VStitcher

MA Wanqing, KE Baozhu

2025, 39(3): 341-346. doi: 10.12299/jsues.24-0098

Abstract:
To optimize the virtual fabric drape effect in VStitcher, drape experiments on 38 selected fabric samples were conducted. A comparative analysis was performed by measuring 8 drape indicators for both virtual and physical fabrics to quantify their discrepancies. Subsequently, the physical properties of the virtual fabrics were systematically adjusted to align their drape behavior with that of their real-world counterparts. Using the least squares, a fitting analysis was conducted on the physical properties before and after adjustment, leading to the establishment of an optimization model for virtual fabric physical properties. To validate the model, three additional fabric samples were randomly selected for testing. The results demonstrate that the relative error between the drape indicators of the optimized virtual fabrics and the physical fabrics is within 5%. This confirms the effectiveness and accuracy of the proposed model in enhancing the realism of virtual fabric drape simulation.

[Abstract](22) [FullText HTML] (11) [PDF 1036KB](0)

Forward-reverse design method for acoustic metamaterial plates based on neural networks

CHEN Weiqian, GUO Hui, FU Wei, SUN Pei, WANG Yansong

2025, 39(3): 347-353, 374. doi: 10.12299/jsues.24-0163

Abstract:
As an artificial composite structure, an acoustic metamaterial plate (AMP) can block the propagation of the elastic wave within specific frequency ranges. Due to the combined effects of multiple mechanisms in the composite structure, it is difficult to derive and express the physical properties using theoretical formulas. An AMP structure based on local resonance mechanism was proposed, and the bandgap characteristics were analyzed using finite element method, to obtain different cell structure parameters and corresponding bandgap characteristics. A sample set of the relationship between the structure parameters and corresponding bandgap characteristics was established for the AMP. A forward neural network model was designed to obtain the mapping relationship between structural parameters and bandgap range, and the forward prediction of the corresponding bandgap range by inputting structural parameters can be achieved. On this basis, a reverse neural network was proposed, and the reverse design can be carried out to obtain the structural parameters of AMP aiming the required bandgap range. The simulation results show that complex and cumbersome theoretical derivation and calculation can be avoided with the forward-reverse design method for AMP, which is helpful to promote further development of acoustic metamaterials.

[Abstract](24) [FullText HTML] (13) [PDF 1939KB](1)

Predicting drug-target interactions based on dynamic multi-grained scanning

ZHANG Qi, YIN Zhixiang, LU Lin

2025, 39(3): 354-359. doi: 10.12299/jsues.24-0143

Abstract:
To address the poor classification performance of traditional machine learning models in the drug-target prediction, a problem caused by their shallow structure and complex data features, a novel prediction model DMS-DF was proposed. The model was based on the deep forest algorithm, the model incorporated a dynamic adaptive multi-granularity scanning mechanism. Furthermore, CatBoost and XGBoost were selected as cascade forest-based classifiers. It demonstrates that that the DMS-DF model outperforms the other four models in terms of drug-target prediction on the same dataset, providing a novel approach for drug discovery.

[Abstract](23) [FullText HTML] (16) [PDF 1111KB](0)

Ensemble model and empirical analysis of breast cancer diagnosis based on Stacking

CHENG Mushuang, WANG Guoqiang

2025, 39(3): 360-365. doi: 10.12299/jsues.24-0147

Abstract:
The early diagnosis of breast cancer can significantly improve the possibility of cure. In recent years, the boom of big data and artificial intelligence technology provides technical support for early diagnosis of many diseases, including breast cancer. In order to improve the accuracy of breast cancer diagnosis, an improved Stacking integration model based on area under curve (AUC) was constructed. Firstly, an AdaBoost ensemble model based on $v$-SVM is constructed and used as a meta learner for Stacking. Secondly, the overall AUC values of each base learner were used to weight the training results of each base learner, and the weighted results were used as the training set of the meta learner for training. Finally, empirical analysis was conducted on the WDBC and WBC datasets. The experimental results show that the Stacking ensemble model based on AUC improvement can achieve high accuracy on two datasets, provide doctors with more refined and personalized diagnostic criteria, thereby achieving the goal of earlier intervention and more efficient treatment.

[Abstract](24) [FullText HTML] (15) [PDF 895KB](0)

Improved YOLO-based image segmentation method for AEC welding cup profile

ZHANG Hongpu, LIU Xiyan, ZHAO Fengzhi, YAN Xiyan, FENG Yan

2025, 39(3): 366-374. doi: 10.12299/jsues.24-0125

Abstract:
To achieve the accurate positioning of automated welding of aviation electrical connector (AEC), a method for the detection and segmentation of welding cup profiles was proposed based on machine learning. The effectiveness of feature extraction and prediction accuracy of the original network model were enhanced by incorporating a small target detection layer, the CBAM mechanism, and the GhostNet network. Concurrently, the number of parameters and space size of the improved model were reduced. The experimental results show that the improved YOLOv5s-Seg model achieves mean average precision of 84.2% and 44.6%. Compared with the original YOLOv5s model, this represents improved by 5.5% and 1.3%, respectively. The detection-segmentation method proposed effectively balances precision and speed, facilitating practical application and equipment deployment, and provides a theoretical basis for advancing the automated welding of AEC based on machine vision.

[Abstract](24) [FullText HTML] (14) [PDF 2705KB](2)

Current Issue 2025 Vol. 39, No. 3

Current Issue
2025 Vol. 39, No. 3