Most Download

  • Published in last 1 year
  • In last 2 years
  • In last 3 years
  • All

Please wait a minute...
  • Select all
    |
  • ZHAO Sheng-qian, CONG Zhuo-hong, YOU Qing-long, LI Yuan
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2437-2464. https://doi.org/10.13229/j.cnki.jdxbgxb.20221433
    Abstract (102) PDF (18) HTML (71)   Knowledge map   Save

    In view of the adhesion performance between asphalt-aggregate, the research results on the adhesion and raveling mechanism, evaluation methods, influencing factors and improvement measures in domestic and overseas are summarized. Formation and failure of adhesion are complex processes involving physics, chemistry, thermodynamics, and micromechanics. The characteristics of the interface between asphalt and aggregate are influenced by the properties of asphalt and aggregate, the void and asphalt film thickness of the mixture, and the external environment. The different test systems are dedicated to the development of methods that that can not only simulate the process of damage occurrence in the field but also provide an assessment method through which the suitability of mixtures would be estimated in designing steps and would be guaranteed during the pavements service life. Combined with the existing research contents,the future research directions of asphalt-aggregate adhesion performance and asphalt mixture moisture sensitivity are prospected.

  • WANG Jia-yi, LIU Xin-hui, WANG Zhan, CHEN Jin-shi, HAN Ya-fang, WANG Yu-qi
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2499-2507. https://doi.org/10.13229/j.cnki.jdxbgxb.20211265
    Abstract (49) PDF (7) HTML (28)   Knowledge map   Save

    To study the constant flow mechanism of the constant flow control valve, the influence of flow area and gradient on the characteristics of constant flow control valve are analyzed based on the actual structure of a certain type of valve. Firstly, the mathematical model, the control theoretical model and the transfer function block diagram of the dynamic system are established to quantitatively analyze the influence of these factors. Then the AMESim simulation model is established, and the influence mechanism of these factors on the steady-state and dynamic characteristics of the valve is analyzed. The reliability of the simulation model is verified by the experiment. The results show that there exists negative feedback between stages in the constant flow control valve, which compensates the pressure difference between the two sides of throttle and reduces the flow adjustment deviation. Adjusting the flow area of the pressure compensator can improve the steady-state characteristics of the constant flow control valve. Adjusting the flow area gradient of the pressure compensator can significantly improve the static and dynamic characteristics of the constant flow control valve.

  • J Jilin Univ Eng Tech Ed. 2024, 54(07): 1913-1922. https://doi.org/10.13229/j.cnki.jdxbgxb.20221236
    本文构建GWR(Geographically weighted regression)模型拟合建成环境变量与地铁客流的关系,并分析建成环境显著变量对地铁客流的异质性影响。采用西安市地铁1、2、3号线63个站点共5个工作日的客流数据,利用ArcGIS软件将客流数据与交通小区匹配,在传统最小二乘法的基础上构建GWR模型,考虑人均GDP、土地利用混合度、停车场密度、交叉口密度、地铁出入口密度等对交通小区地铁客流的影响,得到如下结论:GWR模型能有效刻画交通小区地铁通勤客流与建成环境变量互动关系的空间非平稳性及影响尺度,其结果优于传统最小二乘法;同时,分析发现人均GDP、土地利用混合度、交叉口密度、地铁出入口密度4个变量对交通小区地铁客流的影响显著;土地利用混合度对地铁通勤客流的吸引远远大于地铁出入口密度,且在土地利用开发程度和均衡度较低的交通小区表现更明显。
  • AN Ran, WANG You-zhi
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2554-2562. https://doi.org/10.13229/j.cnki.jdxbgxb.20211243
    Abstract (37) PDF (6) HTML (20)   Knowledge map   Save

    In order to understand the mechanical properties of shear stud connectors under combined tension and shear loading, five groups of model tests were tested, including uniaxial pull-out tests, uniaxial push-out tests, and combined tension and shear loading tests. Combined with finite element models, influence of concrete strength and stud size on shear capacity were analyzed, and the load-slip relationship, the ultimate shear capacity formula of shear stud connectors under tension and shear loading were proposed. The results show that as the applied tensile force ratio increase to 0.6, the shear stiffness reduces 69%; and the ratio of ultimate elastic capacity to ultimate shear capacity reduces from 0.55 to 0.24, and the ultimate shear capacity reduces 31%. The effects of concrete strength and tensile force ratio on the shear capacity of shear stud connectors are correlated. The proposed load-slip relationship and ultimate shear capacity formula under tension and shear loading can be applied to engineering design and calculation.

  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1175-1187. https://doi.org/10.13229/j.cnki.jdxbgxb.20221061
    为减小侧向运动对整车质量与道路坡度估计精度的影响,提出了一种考虑侧向运动的估计算法,利用加速度修正车辆动力学模型,采用遗忘因子提高新数据适应车辆系统时变特性的最小二乘算法估计整车质量,并将质量估计结果实时输入道路坡度估计中;建立车辆运动学和动力学两个坡度估计模型,并在模型中添加加速度修正项,设计强跟踪滤波算法分别针对2种模型进行道路坡度估计,时变交互多模型融合算法根据两个坡度估计模型的权重系数和模型间的转移概率得到道路坡道估计值。本文算法在中国第一汽车股份有限公司技术中心农安汽车试验场进行了实车试验和评估,与未考虑侧向的融合估计算法相比,提高了车辆横向运动时的道路坡度估计精度。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1188-1195. https://doi.org/10.13229/j.cnki.jdxbgxb.20220728
    提出了一种具有动态交互感知池化层的多长短期记忆神经网络(DIP-LSTM)模型结构,使得场景中相邻的车辆通过池化(Pooling)共享各自LSTM网络隐藏态,获取历史轨迹特征,进而实现自车与周围多车的时间空间关系的交互性建模,并输出车辆未来的预测轨迹。使用美国的NGSIM和德国的High-D自然驾驶车辆轨迹数据集对模型进行训练与测试,并对模型的精度、鲁棒性和迁移性(普适性)进行验证。研究结果表明:与传统模型的预测方法相比,考虑多车交互信息的DIP-LSTM网络的预测方法在预测精度与长时域预测上具有优势,且模型具有良好的迁移性和鲁棒性,显著提高了车辆轨迹预测模型的实用性和普适性。
  • J Jilin Univ Eng Tech Ed. 2024, 54(03): 641-649. https://doi.org/10.13229/j.cnki.jdxbgxb.20220563
    采用电加热喷雾冷却减阻试验台,系统研究了喷雾流量、喷雾倾角、气流温度、气流速度影响发动机排气系统减阻性能的规律;采用基于离散相模型(DPM)的数值模拟,阐释了喷雾冷却大幅降低排气阻力的原因。研究结果表明:喷雾流量为12~24 mL/s时,减阻率随喷雾流量的增加而增大;喷雾倾角由45°增加至90°时,减阻率先保持不变后减小,45°和60°喷雾倾角时的减阻效果均为最佳;气流温度为200~300℃时,随着气流温度的升高,减阻率呈增大趋势;气流速度由20 m/s增大至30 m/s时,减阻率逐渐下降。排气系统喷雾后阻力大幅度减小的原因是喷雾后气流速度降低,湍流强度降低,局部阻力和摩擦阻力显著减小。
  • SHI Rui-jie, DAI Fei, ZHAO Wu-yun, YANG Fa-rong, ZHANG Feng-wei, ZHAO Yi-ming, QU Hao, WANG Tian-fu, GUO Jun-hai
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2686-2694. https://doi.org/10.13229/j.cnki.jdxbgxb.20211199
    Abstract (51) PDF (5) HTML (26)   Knowledge map   Save

    To improve the mechanization harvesting level of quinoa and solve the problems of a significant loss rate, high impurity rate, and poor feeding during harvesting of ordinary rice-wheat combine harvester, according to the characteristics of quinoa plants during the harvesting period, a sizeable self-propelled quinoa combine harvester was designed. The machine used flaring type small row spacing chain teeth feeding into the header, combined longitudinal axial flow threshing cylinder, unique woven screen concave, double reciprocating vibrating screen and other devices, cooperation wide bridge, threshing cylinder CVT regulation, and excellent space design to realize the smooth quinoa feeding and efficient threshing separation. Critical components for the design were analyzed, and a field experiment was carried out. The results of the field experiment showed that when the water content of quinoa grain was 14.42%, the threshing rate was 96.83%, the impurity rate was 4.41%, the damage rate was 0.2%, the header loss rate was 1.14%, the entrainment loss rate was 1.73%, the cleaning loss rate was 1.09%, the splash loss rate was 0.16%, the total loss rate was 4.13%. During the experiment, the machine runs smoothly and meets the mechanical harvesting of quinoa. This paper can provide some reference for the design and test of quinoa combine harvester.

  • ZHENG Zhi, YUAN Pei, JIN Xuan-hui, WEI Si-si, GENG Bo
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2581-2590. https://doi.org/10.13229/j.cnki.jdxbgxb.20211227
    Abstract (20) PDF (4) HTML (18)   Knowledge map   Save

    Aiming at the problem that the existing protective structure can not achieve multi-objective ship-type flexible protection,a flexible fender which can protect small and medium-sized ships is proposed.The fender can be used with the existing protective structure.To determine the optimal form,the quasi-static compression tests of three different flexible fenders are carried out.And the protective performance of the optimal structural fender is analyzed through full scale impact test and numerical simulation.The results indicate that the failure modes of different specimens are similar under compression test.The outer plate shear failure, matrix cracking and fiber fracture occurred in all specimens.At the end of compression, the springback rate of each specimen was as high as 85%.Specimen 3 with energy dissipation core material is the optimal structure.For the drop weight impact test, the reduction rate of impact force reaches 97%.Fender deformation recovers completely after impact, and fender dissipates energy in the form of elastic energy dissipation.Under barge impact, the fender absorbs 63% of the collision energy and greatly reduces ship damage.In this condition, the fender mainly absorbs the collision energy with the collapse of the energy dissipating core material.

  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1221-1226. https://doi.org/10.13229/j.cnki.jdxbgxb.20221578
    为解决汽车减震器因流动惯量导致径向动力发生偏差的问题,提出基于动力学分析的汽车减震器示功图故障检测算法。计算减震液在左、右2个封闭区域的流动惯量,将压缩行程中的径向动力和回弹行程中的径向动力代入能量与动量方程中,建立汽车减震器动力学方程,再绘制实测示功图,并将其作为样本输入支持向量机中进行分类,再设定判定阈值进行阈值判定,完成示功图故障检测。试验结果表明:本文方法在供液不足、双凡尔漏失、活塞被卡、砂阻时获取的汽车减震器示功图与实测示功图基本吻合,说明本文方法的故障检测准确性高。
  • J Jilin Univ Eng Tech Ed. 2024, 54(01): 22-43. https://doi.org/10.13229/j.cnki.jdxbgxb.20230651
    综述了国内外对胶粉改性沥青老化机理、表征及评价的研究现状。胶粉改性沥青的老化过程伴随着胶粉的溶胀、降解反应以及沥青与胶粉之间的物质交互作用;胶粉改性沥青老化行为的表征主要从化学组分、分子结构、分子量、表面形貌入手,并解释其对宏观性能的影响;胶粉改性沥青老化性能评价主要采用黏度、复数模量、低温蠕变劲度、疲劳寿命等流变学指标,且通常与微观表征及化学方法相结合。然而,当前国内外对胶粉改性沥青老化过程中填料迁移行为关注较少,特别是炭黑、白炭黑等填料的作用机理有待进一步挖掘;缺乏胶粉改性沥青多组分老化特征同步表征方法;缺乏统一的老化评价指标,且大多研究在混合料老化性能验证方面存在不足。最后,提出了胶粉改性沥青老化机理及表征评价研究的发展趋势与展望。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1258-1266. https://doi.org/10.13229/j.cnki.jdxbgxb.20221156
    本文采用离散元法(DEM)研究非均质水稳碎石(CSM)材料的细观开裂行为,基于Weibull材料随机场,建立了不同均质度水平的CSM细观断裂模型,通过虚拟半圆弯曲(SCB)试验模拟细观开裂过程,分析砂浆基体均质度的影响。结果表明:CSM裂纹沿着砂浆薄弱点和界面共同扩展,砂浆基体的断裂占主导地位。峰值强度和破坏形变随均质度的提高而增大,砂浆中少量的性能薄弱点有益于改善结构形变特性而提升其整体强度,适当均质度水平有助于CSM材料抗裂性能的发挥。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1205-1213. https://doi.org/10.13229/j.cnki.jdxbgxb.20231081
    汽车涂装过程中产生的漆面缺陷影响着整车外观质量,针对人工检测存在漏检、低效以及传统检测方案的高实施成本等问题,提出了一种基于改进YOLOv7算法的汽车漆面缺陷检测系统。构建了汽车漆面缺陷数据集,共有4023张图像,其中包含5种常见汽车漆面缺陷;针对YOLOv7算法在微小缺陷上检测精度不足的问题,在原网络中引入了GAM注意力机制和SPPFCSPC模块,用于提高算法对微小缺陷特征的提取能力,同时采用改进的ELAN模块对网络结构进行改进,减少网络过深造成的小目标信息丢失问题,保证在减轻网络模型的同时提高网络对微小特征的识别精度;实验结果表明:本文方法大幅提升了对微小漆面缺陷的检测性能,缺陷的平均检测精度达到了88.9%,与多种算法相比检测精度最高。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1285-1292. https://doi.org/10.13229/j.cnki.jdxbgxb.20220770
    为研究智能网联车(CAV)对交通流的影响,基于智能驾驶人模型(IDM),考虑后车和多前车速度差的影响,构建CAV智能驾驶跟驰模型,推导了CAV跟驰模型的临界稳定性条件。然后以考虑1辆后车和5辆前车速度差的CAV跟驰模型设计数值仿真实验。结果表明:交通流稳定性随考虑后车影响的权重比例变化而变化,即只有当后视权重比例在恰当范围内时才可提高交通流稳定性;考虑后车影响和多前车速度差还可削弱由时延导致的交通流不稳定性。同时,新模型控制下的车辆加速度变化更平稳,更有助于提高交通流稳定性和交通流安全性。
  • J Jilin Univ Eng Tech Ed. 2024, 54(04): 1045-1057. https://doi.org/10.13229/j.cnki.jdxbgxb.20220699
    为揭示级配碎石基层与沥青混合料面层的温度收缩协调变形规律,本文采用动静态应变采集系统实时获取沥青混合料层的温缩应变,基于PFC6.0 Suite和FLAC3D构建了组合结构连续-离散耦合模型,探究了级配碎石层与沥青混合料层温缩协调变形宏观和细观响应规律。研究结果表明:连续-离散耦合模型与室内试验的吻合度相比连续介质模型高,温缩系数相对误差最大为8.1%;沥青混合料及其组合试件温缩应变-时间关系曲线均呈先快后慢的非线性变化规律,沥青混合料类型及降温温差对级配碎石的约束作用基本无影响;组合试件温缩变形主要发生在前1 h内,沥青混合料层整体由“翘起”状逐渐过渡到“平缓”状;级配碎石层通过颗粒向内挤压运动,使两端松散膨胀及颗粒接触重组来实现与沥青混合料层的协调变形。本文从宏观应变响应与空隙率、配位数及三维组构细观响应揭示温缩协调变形机制,研究结果可为级配碎石基层沥青路面低温抗裂研究提供理论参考。
  • J Jilin Univ Eng Tech Ed. 2024, 54(11): 3192-3198. https://doi.org/10.13229/j.cnki.jdxbgxb.20230631
    由于沥青混凝土内部结构极其复杂,会在不同疲劳阶段呈现出不同的变化特征,为了解沥青混凝土的疲劳损伤演化过程,在CT三维重构技术的基础上对其展开研究。对沥青混凝土展开疲劳实验,得到不同疲劳阶段的CT扫描图像和三维重构图像;利用差分盒维数法计算CT三维重构图像分形维数,得到疲劳损伤次数与分形维之数间的关系;利用Miner线性疲劳损伤模型重新定义沥青混凝土的损伤变量,得到疲劳损伤演化过程呈线性变化的结论。通过构造环氧沥青混凝土试件展开实验测试,结果表明:本文方法能准确计算出沥青混凝土压缩位移和裂缝体积与疲劳损伤之间的关系,推理得到沥青混凝土的疲劳损伤演化过程。
  • J Jilin Univ Eng Tech Ed. 2024, 54(12): 3601-3613. https://doi.org/10.13229/j.cnki.jdxbgxb.20230164
    针对大规模深度神经网络模型并行面临的内存消耗大、设备利用率低、训练时间长、模型难以收敛的问题,提出了一种面向深度神经网络模型并行的计算任务自适应调度方法。通过建立模型并行计算任务的多迭代异步并行管理机制,控制微批量单元具体调度过程,实现模型合理分区和计算资源合理分配,解决异步迭代时产生的梯度延迟更新问题;基于拓扑感知设计计算资源的分配机制,实现模型训练任务和计算资源的合理匹配;设计计算资源和模型任务的运行时调度策略,实现深度学习模型训练过程中计算与通信重叠的最大化,提高计算资源利用率。实验结果表明:与已有的模型并行方法相比,本文方法可以充分利用各GPU计算资源,在保证模型训练精度的同时,可以将大规模深度神经网络模型训练速度平均提高2.8倍。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1246-1257. https://doi.org/10.13229/j.cnki.jdxbgxb.20221519
    将车路协同系统中车辆的位置估计问题转化为时空图模型构建与优化问题,提出一种时空图优化协同定位(STGO-CL)方法。其中,感知区域中不同时刻的车辆位置构成图模型中的节点;车端与路端通过融合高精地图计算出来的车辆绝对位置与相对位置构成图模型的边,并加入时延补偿约束。在求解过程中采用Levenberg-Marquardt (LM)法求解目标函数实现对感知区域中的车辆位置最优状态估计,实现车-路-图协同定位。利用CARLA建立直道和弯道仿真实验场景以验证算法,结果表明:时空图优化协同定位方法平均定位误差为0.29 m,定位性能较GPS或路侧单元(Road side unit, RSU)单独定位分别提高了97.1%和55.4%,较不融合高精地图的时空图优化协同定位方法提高了42.0%。在时延补偿上,可将200 ms时延下的定位性能提高67.0%。本文利用时空图模型实现车-路-图协同定位可有效提升车路协同系统的环境感知性能。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1227-1236. https://doi.org/10.13229/j.cnki.jdxbgxb.20220814
    针对现有电铲自主装卸功能在料堆重构、环境感知、目标识别等领域存在技术难度的现状,从降低自主装卸作业任务难度的角度出发,本文提出了一种以载荷均衡分布为目标的矿用自卸车斗型优化方法。首先,构建了一种基于差分迭代的装卸后自卸车斗内料堆的轮廓重构方法,并对料堆质心位置进行计算;其次,建立并验证了模拟电铲装卸过程的离散元仿真方法;再次,利用离散元仿真实验,研究了不同斗型结构参数对斗内料堆质心位置的影响;最后,以横向载荷均布为目标,以纵向载荷分布、行驶安全性、斗容变化为约束对斗型进行优化。结果表明:优化后的斗型与原斗型相比,在保持装载能力和行驶安全性的前提下,极端装卸位置时的载荷分布均匀性显著提升,并具有更大的合理装卸面积和更高的作业效率。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1196-1204. https://doi.org/10.13229/j.cnki.jdxbgxb.20220757
    针对现有电伺服作动器在负载回落阶段负载势能被浪费的问题,提出了基于能量回收的新型电伺服作动器的实现方案。该方案通过与传动系统并联的蓄能器来回收负载回落时耗散的势能,在负载举升时将其用于提供辅助推力。结合功率键合图理论引入了一种复杂能域下的机械系统动态能耗分析方法,建立了新型电伺服作动器的动态能耗模型,并进行了对比仿真实验。结果表明,所设计的电伺服作动器使得系统响应时间缩短了约36.9%,所需的电机启动转矩降低了约43.3%;在举升负载时的能耗降低了约31%,在负载回落时能够回收36%的势能;在工作过程中滚珠螺旋副的承载大大降低,有助于减少摩擦热、延长丝杠的使用寿命。
  • J Jilin Univ Eng Tech Ed. 2024, 54(11): 3244-3254. https://doi.org/10.13229/j.cnki.jdxbgxb.20230073
    为定量表征矿粉对沥青胶浆的性能影响,采用改进的多应力蠕变恢复(MSCR)试验,评价沥青胶浆的高温流变性能,基于沥青胶浆的不可恢复柔量Jnr指标提出矿粉强化效应指标ΔJnr,并诠释矿粉强化规律。结果表明:矿粉强化效应与沥青种类有关,其中SBS改性沥青胶浆矿粉强化作用呈两阶段趋势,即先随矿粉掺量的增加而线性增强,随后不再受矿粉掺量的影响。两阶段临界值可作为沥青胶浆的推荐矿粉掺量,计算得到3.5%和4.0%SBS改性剂掺量的改性沥青胶浆的推荐矿粉掺量分别为120%和100%。构建了矿粉强化效应的多元线性回归模型,进一步阐明了应力等级、改性剂掺量和矿粉掺量对矿粉强化效应的影响。
  • SONG Shi-jun, FAN Min
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2659-2665. https://doi.org/10.13229/j.cnki.jdxbgxb.20220598
    Abstract (12) PDF (2) HTML (15)   Knowledge map   Save

    Aiming at the problem that Big data anomaly detection process is easily interfered by edge data, which leads to poor accuracy of Big data anomaly detection, a big data anomaly detection model based on Random forest algorithm was proposed. Firstly, the improved k-means algorithm was used to cluster the big data, and the principal component analysis method was used to extract the features of the big data. Then a big data anomaly detection model based on random forest classifier was built, the extracted features was inputted into the model, a decision tree was built, and the classification accuracy of the classifier was improved by dynamically updating the weight value of the decision tree. Finally, the classification results are output to complete the anomaly detection of big data. The experimental results show that the detection time of the proposed model is about 25 s, the average big data anomaly detection accuracy is 91%, and the false alarm rate is 4.5%.

  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1332-1346. https://doi.org/10.13229/j.cnki.jdxbgxb.20220830
    为解决智能网联环境下匝道合流过程中车辆通行的效率和安全问题,提出了一种基于博弈论的智能车辆协同控制方法。该方法构建了以匝道外侧车道车辆为主体的三方博弈对局,并从换道、安全和行驶效率收益方面综合建立车辆收益函数;以博弈对局整体收益最大为控制目标,依据夏普利值进行收益分配,得到三方博弈对局中车辆最优控制策略。实验选取重庆市玉马路与重庆内环快速路包头方向合流区为路网原型,对合流区的车辆运行场景采用SUMO/TraCI和Python进行联合仿真分析。结果表明:本文所提出的合作博弈控制方法与演化博弈控制方法相比,总体平均行程时间缩短3.22%,平均延误时间缩短14.47%;车辆严重冲突降低54.04%,碰撞时间小于3 s的比例总体降低了26.56%;有效降低了交通冲突时间,改善了合流区交通运行效率。
  • CAI Zhi-dan, FANG Ming, LI Zhe, XU Jia-lu
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2649-2658. https://doi.org/10.13229/j.cnki.jdxbgxb.20230140
    Abstract (26) PDF (2) HTML (15)   Knowledge map   Save

    To tackle the motion blur in the process of acquiring remote sensing images, an algorithm for blind deblurring of remote sensing images is designed. The algorithm is based on the geometric property of image surfaces and the algebraic property of image pixels, and it utilizes Gaussian curvature and reweighted graph total variation. First, the reweighted graph total variational prior and Gaussian curvature prior were combined to obtain the skeleton image which not only retains the gradient and sharp edge information, but also removes the harmful structural information in the latent clean image. Then, the skeleton image is used to estimate the fuzzy kernel, and then the non-blind deblurring algorithm is used to obtain the clear image. Finally, simulation validation was conducted on 8 fuzzy remote sensing images in different scenarios, and the results showed that, compared with other advanced image deblurring algorithms, the peak signal-to-noise ratio of the recovery effect of the deblurring algorithm proposed is higher than that of the comparison algorithm by 2.76, 1.84, 3.11, 2.79, 3.35, 2.76 dB, respectively. The structure similarity is higher than that of the comparison algorithm by 0.0792、0.0604、0.0873、0.0801、0.0997、0.0906, respectively. The remote sensing images recovered by our proposed algorithm have clear edge contours and local details while improving the clarity of remote sensing images.

  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1237-1245. https://doi.org/10.13229/j.cnki.jdxbgxb.20220756
    在653~713 K温度范围和0.01~10 s~(-1)应变速率下,进行了w(GNP/7075Al)=0.5%增强7075铝基复合材料的热压缩试验,建立了BP神经网络和应变补偿Arrhenius模型,同时建立了复合材料的热加工图和动态再结晶体积分数预测模型,研究了复合材料的热变形行为,并确定了复合材料的热加工工艺参数。结果表明:BP神经网络模型得到的流变应力预测值与试验结果吻合较好,其相关系数最高为99.9983%,平均相对误差绝对值最小为0.5%,表明神经网络对w(GNP/7075Al)=0.5%复合材料的热变形行为具有较高的预测精度。w(GNP/7075Al)=0.5%复合材料最佳变形温度和应变速率分别为685~705 K和0.01~0.1 s~(-1)。动态再结晶(DRX)倾向于在低应变速率和高变形温度下发生。数值模拟和热挤压试验表明,在挤压温度693 K、挤压速度1 mm/min的工艺参数下可以挤出表面质量良好的型材。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1302-1310. https://doi.org/10.13229/j.cnki.jdxbgxb.20220850
    载货汽车重心高的特点极易因操作不当引发侧翻,为此,依靠现有路侧测量设备提出一种可快速投入使用的车辆弯道侧翻预测方法。首先,提出基于改进KNN的车辆重心高度回归预测模型实现车辆重心高度路侧动态估计;然后,建立基于横向载荷转移率的车辆侧倾估计模型实现侧倾程度路侧估计;最后,提出在线ARIMA模型在线预测车辆侧倾状态。MATLAB/Simulink与TruckSim联合仿真结果表明:本文提出的侧翻预测方法在弯道全程均能准确预测车辆LTR变化趋势和其极限值,从而为路侧设施在弯道发布针对性预警提供依据。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1323-1331. https://doi.org/10.13229/j.cnki.jdxbgxb.20220744
    选取典型山区双车道公路弯道和直道为研究对象,基于无人机航拍视频提取的交通轨迹数据,通过轻度提升机算法构建了货车移动遮断下小客车跟驰风险预测模型,采用支持向量机、随机森林验证了模型有效性,分析了模型关键特征参数风险作用机制。实验结果表明:基于轻度提升机算法的风险预测模型准确率达96.9%,具有优越性,速度差、跟驰间距是模型关键特征参数,直道上单因子重要度更大;相比弯道,直道路段危险驾驶行为突出,大幅横向偏移等不稳定跟驰特征明显;由模型解释器结果可知,当速度差小于0.5 m/s、跟驰间距大于40 m时,是较为安全的跟驰状态。
  • J Jilin Univ Eng Tech Ed. 2024, 54(10): 2849-2858. https://doi.org/10.13229/j.cnki.jdxbgxb.20221538
    为论证垂直振动法(VTM)设计沥青混合料在光照环境与荷载反复作用环境下的耐久性能,本文首先对VTM法、马歇尔法(Marshall)和旋转压实法(GTM)成型的AC-16混合料力学性能进行对比,并深入分析VTM、Marshall两种设计方法的抗老化性能和耐疲劳特性,应用Weibull分布建立疲劳方程,对疲劳寿命进行对比。结果表明:VTM成型试件具有密实度高、空隙率和矿料间隙率低的特点;GTM、VTM沥青混合料力学性能较Marshall至少提高35%;GTM法、VTM法、Marshall法与现场相关性分别为94%、92%和72%;老化后两种方法设计沥青混合料低温性能相当;短期老化后VTM设计沥青混合料回收沥青性能变化比Marshall的大;长期老化后VTM设计沥青混合料回收沥青性能变化比Marshall的小;建立的Weibull模型呈现良好的线性相关性;不同失效概率下,基于VTM设计的沥青混合料耐疲劳性能优于Marshall法。
  • CAI An-jiang, LIU Chen-yang, WANG Pei-peng
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2493-2498. https://doi.org/10.13229/j.cnki.jdxbgxb.20220472
    Abstract (27) PDF (1) HTML (13)   Knowledge map   Save

    During the operation of 5-axis CNC machine tools, the angle deviation of the rotation axis greatly affects the tool path control. Therefore, a post-processing algorithm of five-axis CNC machine tool with optimized rotation angle was proposed. Firstly, the basic structure of the machine tool was analyzed, the Hausdoff distance was used to obtain the matching error between the actual machined surface and the difference surface, and the error compensation method was used to compensate the obtained error, and the rotation axis angle of the machine tool was completed according to the processing result. Based on the optimization results, the machine tool coordinate system was established, and the machine tool post-processor was developed through the coordinate transformation results and integrated into the relevant software to realize the post-processing of the machine tool. The experimental results show that the proposed method achieves better processing results when used for post processing of machine tools.

  • ZHANG Jian, LI Qing-yang, LI Dan, JIANG Xia, LEI Yan-hong, JI Ya-ping
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2508-2518. https://doi.org/10.13229/j.cnki.jdxbgxb.20220106
    Abstract (18) PDF (1) HTML (15)   Knowledge map   Save

    Exclusive lanes for connected and autonomous vehicles(CAVs) will emerge in order to ensure the safety and efficiency requirements in the process of traffic flow mixed with human-driving vehicles and CAVs. When the inner lane of the expressway is set as the exclusive lane for CAVs, it has important theoretical significance and practical value to study the strategy of guiding CAVs to merge from the ordinary lane to the exclusive lane. Firstly, the entrance area of exclusive lane was designed and vehicle control rules were proposed. Secondly, with the goal of making more CAVs change lanes to the exclusive lane, the strategy of selecting lane-changing signal actions was proposed based on deep reinforcement learning. Finally, the numerical simulation was carried out with Python language compilation. The results show that the proposed algorithm can converge very quickly under 9 scenarios constructed by different factors, such as the CAV penetration rates and the proportion of CAVs arriving at the exclusive lane; it can effectively guide CAVs to merge into exclusive lanes and ensure traffic efficiency; congestion in the second lane can be significantly reduced compared to the unsignalized control when the penetration rate changes from 20% to 40%; the proportion of CAVs changing to the exclusive lane is significantly higher under the two exclusive lane entrances scenario than that under the one entrance scenario. It shows that the proposed strategy has good applicability and can provide reference for engineering construction.

  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1377-1384. https://doi.org/10.13229/j.cnki.jdxbgxb.20230262
    进行建筑结构层间变形特征分析时未建模分析特征,导致分析效果较差,为解决上述问题,本文对地震后建筑结构层间变形分布特征展开研究。利用建筑信息模型技术建立建筑结构三维模型;引入广义层间位移谱法,构建层间位移等公式,进行建筑结构层间变形特征分布分析。研究结果表明:不同加速度下,层间位移随着加速度增加而增大;1层楼时弯矩、剪力和层间位移角分别达到237 kN·m、210 kN和1/231 rad,呈现最大的变化。分析结果与实际相符,可以有效地分析层间变形特征。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1214-1220. https://doi.org/10.13229/j.cnki.jdxbgxb.20221577
    汽车机械式自动变速系统难以同时满足低能耗、高动力的运行需求,为提升变速系统运行性能,提出基于粒子群算法的汽车机械式自动变速系统参数多目标优化。该方法首先学习并分析汽车整体动力模型以及电机效率,之后依据汽车在行驶中的最高速度、加速度性能以及爬坡性能确立目标函数,最后利用粒子群算法求解目标函数最优解,利用汽车在行驶过程中的惯性权重使全局搜索能力达到平衡状态,基于学习因子实现粒子自动寻优,实现汽车机械式自动变速系统参数多目标优化。实验结果表明:本文方法能耗低、运行效率高且拥有良好的动力性能,能有效提升汽车机械式自动变速系统的运行性能,对汽车的无延迟变速具有一定的促进作用。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1311-1322. https://doi.org/10.13229/j.cnki.jdxbgxb.20220754
    考虑车辆类型、驾驶风格及不同阶段影响车辆换道的关键目标,将车辆避障过程中的“车-车交互”机理描述为力的关系,构建协同换道避障模型(CLAM),提取并建立适用于突发事件的车辆避障微观轨迹数据集,将车辆避障转化为多约束优化控制问题,以优化算法(OA)为纽带,设计车辆协同避障控制(CLAM-OA)策略。结果表明:相较于数据驱动的长短时记忆模型,CLAM-OA策略输出的误差均显著减小、车速与位移在不同时域的输出结果也更加稳定。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1267-1276. https://doi.org/10.13229/j.cnki.jdxbgxb.20221262
    为解决机场在进行智慧化程度评价过程中由于建设内容体量庞大,业务错综复杂,无法做到业务流科学划分并有效评价的难题,本文从面向任务对象角度以及面向功能属性的角度建立了基于对象-属性双维度的机场核心业务流评价体系,并提出了90项基础指标。在此基础上,通过优劣解距法对禄口机场的双维度指标层进行了分值计算。研究结果表明:双维度评价指标体系的建立有助于厘清机场业务流种类多元且流向繁杂的问题,方便后续机场进行智慧化程度评价;从基于任务对象维度的指标层分值可以看出,旅客流的隔离区外智慧化建设程度最高为73.76分。以功能属性维度划分的各指标中,感知类的数量/重量指标评分最高为79.68分,高出平均值21.4%;预测类的时间类指标评分最高为80.26分,高出平均值9.1%;决策类的事件类指标评分最高为76.30分,高出平均值10.2%。预测类和决策类的相关指标智慧化建设程度相对均衡,而感知类指标最低分为54.36分,最高分为79.68分,各业务智慧化建设程度相差较大。
  • J Jilin Univ Eng Tech Ed. 2024, 54(01): 259-267. https://doi.org/10.13229/j.cnki.jdxbgxb.20230802
    针对现有薄壁结构存在比吸能不高、压缩力效率较低的问题,以蜂窝为原型,模拟蜂窝多级嵌套结构,进行仿生结构优化设计。为了更好地探究形状参数对吸能能力的影响,进一步以相对旋转角度及加强柱直径为设计变量,设计了共20种仿蜂窝多级薄壁结构。运用3D打印技术,制备了尼龙材质的仿蜂窝多级薄壁结构样件,并进行准静态压缩试验。最后,对比分析了数值模拟结果与试验结果,得出以下结论:本文吸能能力最强的模型为YMT20-3.6,比吸能达到了10.87 J·g-1,较初始模型YMT0-0提高了约86%;旋转角度越大,加强柱直径越大,模型截面面积分布越均匀,模型变形模式也趋于对称,其能量吸收能力也更强;较大的旋转角度拥有更优异的吸能能力,但是其压缩力效率较小。增大模型加强柱直径能够减少旋转角度对压缩力效率的影响,提高模型的压缩力效率,从而得到吸能能力强、压缩力效率高的薄壁结构。
  • J Jilin Univ Eng Tech Ed. 2024, 54(10): 2941-2951. https://doi.org/10.13229/j.cnki.jdxbgxb.20230110
    对比和分析了广东省高速公路多孔沥青路面近年抗滑、渗水及降噪性能变化状况,研究了多孔沥青路面铺设前后路段交通事故降低幅度,测试了车道不同位置的路面渗水系数,并使用新的试验方法来测试和评价多孔沥青路面的侧向排水能力。结果表明:小粒径多孔沥青路面初始抗滑性能相对较好,但工后两年抗滑性能开始下降;大粒径多孔沥青路面工后两年抗滑性能继续呈现上升趋势。小粒径多孔沥青路面渗水系数衰减速度快于大粒径多孔沥青路面。车辆轮迹带排水性能优于轮迹带中间及路肩处;大粒径多孔沥青路面厚度是小粒径多孔沥青路面的2倍,但侧向排水能力相差2.39倍。多孔沥青路面铺设后,晴天事故数减少64.3%,雨天事故数减少57.1%,总事故数减少59.5%;多孔沥青路面对改善高速公路排水困难点的交通安全具有积极作用。本文可为新建和养护排水沥青路面的工程决策提供参考。
  • SU Yu-ting, WANG Ji, ZHAO Wei, JING Pei-guang
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2601-2610. https://doi.org/10.13229/j.cnki.jdxbgxb.20211169
    Abstract (18) PDF (1) HTML (17)   Knowledge map   Save

    Aiming at the problem that there exists semantic gap between visual features and high-level emotional semantics and the subjectivity and ambiguity of emotional labels in image sentiment distribution learning, this paper proposes an Emotional Semantic Dynamic Graph Convolution Network (ESDGCN). In this framework, the Emotion Activation Module (EAM) is constructed to automatically locate the emotional semantic regions to effectively mine the content representation that fits the emotional semantics. In addition, the Semantic Dynamic Graph Convolution Network (SDGCN) is to adaptively capture the semantic relevance between labels. Finally, we adopt the parallel structure to jointly consider local semantic emotional information and label correlations. Experimental results on three open emotional datasets demonstrate the effectiveness of the proposed method.

  • CHEN Mian-shu, YU Lu-lu, LI Xiao-ni, ZHENG Hong-yu
    J Jilin Univ Eng Tech Ed. 2023, 53(09): 2666-2675. https://doi.org/10.13229/j.cnki.jdxbgxb.20211293
    Abstract (19) PDF (1) HTML (17)   Knowledge map   Save

    Aiming to solve the aggregation problem of traditional uniform oriented FAST and rotated BRIEF(ORB) features in visual simultaneous localization and mapping(SLAM), a uniform FAST corner extraction method is designed, which is based on grid division and laying to determinate key points. Furthermore, a corresponding loop detection method is designed based on uniform distribution of ORB features combined with brute force matching. Experiment results compared with BoW-based loop detection algorithms show that the proposed algorithm can significantly improve the accuracy of loop detection. Furthermore, a robot operating system(ROS) based loosely coupled semi-direct SLAM system is designed, which combine the uniform ORB feature loop detection module with direct sparse odometry(DSO). The experimental results show that the proposed system has high map construction performance.

  • J Jilin Univ Eng Tech Ed. 2024, 54(03): 610-619. https://doi.org/10.13229/j.cnki.jdxbgxb.20220537
    针对现有救援车辆的液压悬挂系统存在作动器非线性、参数不确定性以及对动力学模型依赖性较强等问题,提出了一种液压主动悬挂系统控制方法——基于扩张状态观测器的模型预测控制方法(ESO-MPC)。首先,通过车载惯性导航系统实时获取车辆位姿信息,并基于位姿偏差方法计算出各个液压作动器的输出位移量。其次,完成救援车辆液压悬挂系统动力学建模,通过扩张状态观测器估计系统中的非线性扰动和未知输出信号。最后,基于扩张状态观测器的模型预测控制方法,使每个液压作动器的输出在限制范围内对期望位移信号进行有效追踪。为验证该控制方法的有效性,搭建了液压悬架整车试验平台,并与被动悬架和传统PID控制方法进行了多种路面对比试验。结果表明,相比于被动悬挂和传统的PID控制方法,本文提出的基于扩张状态观测器的模型预测控制方法可以降低垂向高度均方根值35%,俯仰角度均方根值17%,侧倾角度均方根值23%,显著提升了车辆的行驶平顺性和操纵稳定性。
  • J Jilin Univ Eng Tech Ed. 2024, 54(05): 1407-1416. https://doi.org/10.13229/j.cnki.jdxbgxb.20221367
    为提升模型对合成孔径雷达(SAR)图像多尺度舰船目标的检测能力,保证检测网络的实时性,提出一个基于注意力机制改进的无锚框舰船检测模型。在YOLOX网络特征金字塔处嵌入空洞注意力模块,调节感受野与多尺度融合的关系,强化特征的表示能力。在检测头部设计中心性预测分支,对锚点的分类得分进行加权处理,调整模型的损失函数,优化检测结果。在数据集SSDD上进行的对比实验结果表明:本文提出的模型优于主流的深度网络检测模型,精度达到94.73%,且在检测精度和检测速度中取得最佳平衡。