摘要： 针对汽车渗氮齿轮制造过程中的关键技术瓶颈，系统研究了渗氮钢材料体系、工艺参数优化及质量监控方法。通过对比分析Cr Mo Al系与Cr-Mo-V系渗氮钢的冶金特性，揭示了合金元素协同作用对渗氮层性能的影响机制。采用正交试验法优化了气体渗氮、液体渗氮及离子渗氮工艺参数，建立了基于硬度分布特征的渗氮质量评价模型。研究表明：采用42Cr Mo S4钢配合两段式离子渗氮工艺(520℃×20h+560℃×8h)，可使表面硬度达到785HV0.5，有效硬化层深度0.4mm；提出齿端面硬度替代检测法，实现非破坏性检验，检测成本降低67%。研究结果为汽车渗氮齿轮的工业化生产提供了理论指导和技术支撑。

关键词： 采煤机摇臂   行星传动齿轮   有限元分析   优化设计  

摘要： 针对摇臂传动系统末端行星传动齿轮经常出现严重磨损问题，运用ANSYS Workbench有限元仿真分析软件，完成了行星传动系统强度分析工作。分析结果显示，太阳轮和行星轮轮齿啮合位置存在应力集中，最大应力数值接近轮齿制备材料的屈服强度是其长时间使用过程中经常出现严重磨损问题的原因。通过对太阳轮和行星轮轮齿齿顶进行修形完成了轮齿结构的优化，降低了太阳轮和行星轮啮合位置的最大应力数值，使轮齿工作过程中的安全系数达到了1.48倍。优化之后的太阳轮和行星轮满足采煤机使用要求，摇臂运行更加平稳。

摘要： 在德意志符腾堡州的晨雾中，那个用拉丁文背诵《奥德赛》的苍白少年，像一片过早凋零的菩提树叶，悄然坠入内卡河。赫尔曼·黑塞用诗意的冷酷掀开了20世纪初的文明面纱——《在轮下》不仅是一部教育小说，更是一部关于人类精神异化的现代寓言。当我在书页间目睹汉斯·吉本拉特的生命轨迹，看到的不仅是某个小镇天才的陨落，更是每一个被困在文明齿轮下的灵魂发出的无声呐喊。

关键词： Signal modulation  

摘要： Signal processing and deep learning are often combined to achieve better diagnostic results in the field of fault diagnosis. Based on this, the symplectic geometric mode decomposition was improved and the ResNeXt neural network was optimized, and then a gearbox fault diagnosis model was proposed based on the combination of optimized symplectic geometric mode decomposition and ResNeXt neural network was improved. Firstly, the collected vibration signals were filtered and reconstructed by optimized symplectic geometric mode decomposition to obtain the effective components. Then it was sent to the improved ResNeXt neural network for fault recognition and classification. The rolling bearing variable condition data from the University of Ottawa was used to verify the feasibility of the model. The gearbox data from drivetrain dynamics simula (DDS) was used for contrast experiment and anti-noise experiment, which verified the effectiveness of changes and the generalization of the model. © 2025 Beijing Kexue Jishu yu Gongcheng Zazhishe. All rights reserved.

关键词： 煤炭含量检测   分光光度法   TCN   LSTM  

摘要： 针对矿用机电设备润滑油易受煤炭颗粒污染而导致润滑性能下降、防磨损与防锈蚀功能失效，进而引发齿轮副卡涩、设备故障等问题，提出了一种基于分光光度法的齿轮油煤炭含量检测方法。设计了一种融合时间卷积网络(TCN)与长短时记忆神经网络(LSTM)和挤压-激励(SE)注意力机制的齿轮油中煤炭含量混合预测模型，实现了齿轮油中煤炭含量的实时监测与预警。实验结果表明：分光光度法精度达到94.21%,混合预测模型的平均绝对百分比误差为1.98%,显著优于传统检测方法。

关键词： 齿轮箱   健康监测   高斯混合模型   局部分布差异   自适应阈值  

摘要： 齿轮箱的健康监测对于机械传动系统以及机械设备的健康管理极为重要。针对变工况齿轮箱在使用过程中的健康状态较难监测的情况，提出一种基于高斯混合模型(Gaussian mixture model, GMM)和局部分布差异(local distribution difference, LDD)的自适应动态阈值健康监测方法。首先，对原始振动信号进行处理，从处理信号中提取特征，并依据单调性排序；使用核主成分分析对单调性较好的特征进行降维，构建退化趋势。再使用健康数据训练高斯混合模型，确定模型参数，并计算贝叶斯推断的距离(Bayesian inference distance, BID)。最后使用LDD动态调整滑动窗口大小并结合核密度估计(kernel density estimation, KDE)建立自适应阈值，对齿轮箱的健康状态进行监测。通过实验对比分析表明：本方法的预测准确性为99%,假警率为0.05%,灵敏度为98%,相较于其他方法有较大优势。

关键词： Gear trains  

摘要： Aiming at the problem of determining the effective design range of parameters during the optimization design of planetary gear transmission system, the dynamic sensitivity of two-stage planetary gear transmission system parameters was studied. Taking the two-stage planetary gear transmission system of vehicle as the research object, the natural vibration model of the system was established by Lagrange, the vibration modal characteristics of the two-stage planetary system were summarized, the expression of the vibration energy of the planetary system was deduced, the distribution state and the law of the vibration energy transfer in the same order were studied, and the mode change mechanism of the natural frequency of the system was further explored. The vibration energy transfer essential of the system natural frequency mode transition triggered by parameter change was analyzed. The parameter sensitivity equation of the natural frequency of the system is derived, the influence law of the modal transition phenomenon on the parameter sensitivity was studied, and the dynamic change law of the natural frequency sensitivity with the change of the parameter value was revealed. The method of dividing the parameter sensitivity interval based on the modal transition phenomenon was proposed, which realizes the effective guidance for the selection of the variable value range in the optimization design stage. © 2025 Beijing Kexue Jishu yu Gongcheng Zazhishe. All rights reserved.