同步轴系统是升船机驱动机构的主要组成部分，其通过机械硬连接保证驱动机构行程协调，维持升船机承船厢的水平姿态。同步轴系统的主要部件锥齿轮、滚动轴承和空心轴容易发生各种机械故障，为实现同步轴系统故障诊断智能识别，对同步轴系统进行故障诊断方法研究。

本文以某升船机同步轴系统为对象，进行振动信号故障诊断方法研究，创建同步轴系统的动力学模型并验证，仿真获得同步轴系统正常与故障状态的振动信号。对同步轴系统振动信号进行SVD降噪预处理，采用遗传算法优化VMD方法的预设参数，得到GA-VMD方法对振动信号进行分解，提取同步轴系统振动分解信号时域和频域的特征参数，利用PCA方法降维得到状态特征空间，采用网格搜索优化Xgboost算法的预设参数，得到优化后的Xgboost算法，对同步轴系统状态特征空间进行识别，实现同步轴系统的故障诊断。主要研究成果如下：

（1）建立同步轴系统动力学模型，仿真获得振动信号。分析同步轴系统的主要部件常见故障的原因以及动力学特征用于后续验证与分析，创建同步轴系统Adams刚柔耦合动力学模型，其仿真结果表明：动力学仿真参数与理论值相对误差较小、仿真扭矩与实际扭矩值接近，验证了同步轴系统动力学模型的正确性，分析同步轴系统仿真振动信号，其时域周期特征不明显，包络谱特征频率幅值较低，表明原始振动信号的特征区分度不高。

（2）采用信号分解方法处理同步轴系统振动信号，得到明显的时域周期特征和突出的包络谱特征频率幅值。使用VMD方法所得的分解信号，频段能量重叠占比和能量偏差指标较小，表明该方法分解效果较好，但模态个数和惩罚因子取值会影响分解信号的频率带宽和中心频率，采用GA-VMD方法所得的分解信号，融合特征参数较大、包络谱特征频率幅值较高，表明该改进方法分解效果较好，可以突显振动信号特征。采用SVD降噪方法与GA-VMD方法处理同步轴系统振动信号，获得降噪预处理后的振动分解信号，其时域周期特征明显，包络谱特征频率幅值突出，表明同步轴系统的振动信号经过信号分解后，能增强信号的特征信息。

（3）采用特征提取与降维方法，构建状态特征空间，选用机器学习方法对同步轴系统进行故障诊断，得到适用于同步轴系统的故障诊断方法。利用统计方法提取振动分解信号的特征参数，采用PCA方法对特征参数降维，得到同步轴系统状态特征空间，选用网格搜索优化的Xgboost算法，对同步轴系统状态特征空间进行识别，发现GA-VMD方法分解信号状态特征空间识别效果较好；选用不同的分类算法，对该状态特征空间进行识别，发现网格搜索优化Xgboost算法识别效果较好，表明GA-VMD方法与网格搜索优化的Xgboost算法结合，可实现对同步轴系统振动信号的分类识别，适用于升船机同步轴系统故障诊断。

[1] 杨林江, 路卫兵. 三峡升船机概述[J]. 水电与新能源, 2017(1): 7-14.

[2] Akkermann J, Runte T, Krebs D. Ship lift at Three Gorges Dam, China design of steel structures[J]. Steel Construction, 2009, 2(2): 61-71.

[3] 严新平, 李晨, 刘佳仑, 等. 新一代航运系统体系架构与关键技术研究[J]. 交通运输系统工程与信息, 2021, 21(5): 22-29.

[4] 钮新强, 覃利明, 于庆奎. 三峡工程齿轮齿条爬升式升船机设计[J]. 中国工程科学, 2011, 13(7): 96-103.

[5] Krebs D, Runte T, Strack G. Planung für das schiffshebewerk am drei schluchten staudamm in China[J]. Bautechnik, 2006, 83(2): 73-84.

[6] 赵锡锦. 三峡升船机工程建设综述[J]. 中国工程科学, 2013, 15(9): 9-14.

[7] 陈涛. 三峡升船机传动系统虚拟样机设计[D]. 大连: 大连理工大学, 2006.

[8] 黄俊男. 基于实验平台的船舶轴系动力学仿真与分析[D]. 武汉: 武汉理工大学, 2013.

[9] 陈伟. 邮政旋转设备系统故障诊断方法研究[D]. 北京: 北京邮电大学, 2016.

[10] 刘雅雯. 基于Adams的火车滚动轴承仿真分析方法研究[D]. 北京: 北京邮电大学, 2015.

[11] Li Y, Guo Y, Guo J, et al. Gear fault identification by envelope order analysis based on ADAMS simulation[C]. Applied Mechanics and Materials. Trans Tech Publications Ltd, 2013, 333: 628-631.

[12] 王丹凤, 郭瑜. 含行星架裂纹故障的行星齿轮箱振动仿真[J]. 航空动力学报, 2022, 37(7): 1447-1455.

[13] 丁志伟. 基于ADAMS的行星齿轮箱故障诊断研究[D]. 太原: 中北大学, 2019.

[14] Du J, Hou H, Wang Z. Simulation analysis of gear box of wind turbine based on flexible multi-body dynamics[J]. Metalurgia International, 2013, 18(3): 116-121.

[15] Wang M, Wen B, Han Q, et al. Dynamic characteristics of a misaligned rigid rotor system with flexible supports[J]. Shock and Vibration, 2021, 43: 1-16.

[16] Nabaglo T, Kowal J, Jurkiewicz A. Construction of a parametrized tracked vehicle model and its simulation in MSC. ADAMS program[J]. Journal of Low Frequency Noise, Vibration and Active Control, 2013, 32(2): 167-173.

[17] Lu Z, Wang X, Yue K, et al. Coupling model and vibration simulations of railway vehicles and running gear bearings with multitype defects[J]. Mechanism and Machine Theory, 2021, 157: 447-455.

[18] 李婷, 付德义, 薛扬. 基于AE与STFT的变桨轴承裂纹诊断研究[J]. 振动测试与诊断, 2021, 41(2): 299-303, 412.

[19] Wang X, Song Y, Su L, et al. Recognition of abnormal car door noise based on multi-scale feature fusion[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2022: 41(1): 261-271.

[20] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London, Series A: mathematical, physical and engineering sciences, 1998, 454(19): 903-995.

[21] 杜陈艳, 张榆锋, 杨平, 等. 经验模态分解边缘效应抑制方法综述[J]. 仪器仪表学报, 2009, 30(1): 55-60.

[22] Smith J S. The local mean decomposition and its application to EEG perception data[J]. Journal of the Royal Society Interface, 2005, 2(5): 443-454.

[23] Wu Z, Huang N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 31-41.

[24] 胡璇, 叶柯华, 李春, 等. 基于集合经验模态分解和关联维数的风力机齿轮箱故障诊断[J]. 热能动力工程, 2020, 35(8): 132-141, 170.

[25] Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

[26] Yang K, Wang G, Dong Y, et al. Early chatter identification based on an optimized variational mode decomposition[J]. Mechanical Systems and Signal Processing, 2019, 115: 238-254.

[27] 蒲子玺, 殷红, 张楠, 等. 基于峭度准则VMD及平稳小波的轴承故障诊断[J]. 机械设计与研究, 2017, 33(1): 67-71.

[28] 许子非, 岳敏楠, 李春. 基于改进变分模态分解与支持向量机的风力机轴承故障诊断[J]. 热能动力工程, 2020, 35(6): 233-242.

[29] 唐刚, 朱立军, 胡雄. 基于优化VMD和深度置信网络的滚动轴承故障诊断[J]. 轴承, 2020, (10): 47-53.

[30] 李永琪, 彭珍瑞. 基于参数自适应的VMD滚动轴承故障诊断[J]. 噪声与振动控制, 2021, 41(5): 139-146.

[31] 李道军, 卢青波, 宋航帆. 基于萤火虫算法优化VMD的滚动轴承故障检测[J]. 机床与液压, 2021, 49(15): 195-199.

[32] 张晓龙. 基于优化VMD和BP神经网络的液压管路故障诊断研究[D]. 鞍山: 辽宁科技大学, 2021.

[33] Cai Z, Zhao H, Yang Z, et al. A modular spectrum sensing system based on PSO-SVM[J]. Sensors, 2012, 12(11): 15292-15307.

[34] Chen T, Guestrin C. Xgboost[M]. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016: 785-794.

[35] Lei Y, Jiang W, Jiang A, et al. Fault diagnosis method for hydraulic directional valves integrating PCA and XGBoost[J]. Processes, 2019, 7(9): 589-595.

[36] 张钰, 陈珺, 王晓峰, 等. Xgboost在滚动轴承故障诊断中的应用[J]. 噪声与振动控制, 2017, 37(4): 166-170, 179.

[37] Zhang D, Qian L, Mao B, et al. A data-driven design for fault detection of wind turbines using random forests and xgboost[J]. IEEE Access, 2018, 6: 21020-21031.

[38] Zhou D, Yao Q, Wu H, et al. Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks[J]. Energy, 2020, 200: 60-68.

[39] 靳志杰, 霍志红, 许昌, 等. 基于特征选择和XGBoost的风电机组故障诊断[J]. 可再生能源, 2021, 39(03): 353-358.

[40] 田浩. 基于HHT和XGBoost的风电机组滚动轴承故障诊断研究[D]. 乌鲁木齐: 新疆大学, 2018.

[41] 张又文, 冯斌, 陈页, 等. 基于遗传算法优化XGBoost的油浸式变压器故障诊断方法[J]. 电力自动化设备, 2021, 41(2): 200-206.

[42] Gu K, Wang J, Qian H, et al. Study on intelligent diagnosis of rotor fault causes with the PSO-XGBoost algorithm[J]. Mathematical Problems in Engineering, 2021, 198: 1-17.

[43] Zhang R, Zhang J-X, Wu Y-H, et al. Numerical simulation of water conveyance system in hydraulic floating shiplift[J]. Journal of Hydraulic Engineering, 2007, 38(5): 624-629, 36.

[44] Zhang Y, Shi D, Liao L, et al. Pitch stability analysis of high-lift wire rope hoist vertical shiplift under shallow water sloshingstructure interaction[J]. Proceedings of the Institution of Mechanical Engineers, Part K: Journal of Multi-body Dynamics, 2019, 233(4): 942-955.

[45] Zhang Y, Shi D, Xiao T, et al. Pitch stability analysis for mechanical hydraulic structural fluid coupling system of high lift hoist vertical shiplift[J]. Journal of Mechanical Engineering, 2020, 66(4): 266-275.

[46] Shen Z, Qiao B, Yang L, et al. Fault mechanism and dynamic modeling of planetary gear with gear wear[J]. Mechanism and Machine Theory, 2021, 155: 390-394.

[47] Yuan W, Wang H, Guo Q, et al. Study on wear mechanism of helical gear by three-body abrasive based on impact load[J]. Materials, 2022, 15(12): 4135-4139.

[48] Zhang H, Zhang G, Cong T, et al. Effect of non-metallic inclusions on the peeling of axle box bearing in EMUs[J]. China Railway Science, 2020, 41(6): 127-134.

[49] Liu J, Yang L, Yu B. Failure path-independent method for structural damage evolution and ultimate bearing capacity analysis[J]. Journal of Basic Science and Engineering, 2020, 28(4): 926-937.

[50] 仝瑶瑶, 张可馨. 基于粒子群改进最小二乘支持向量机的汽轮机轴振动故障诊断[J]. 自动化应用, 2021, (9): 15-19.

[51] 黄剑锋, 余涛, 陈江义. 刚体碰撞的Hertz接触力模型比较分析[J]. 机械设计与制造, 2017(8): 28-30.

[52] 常红阳, 邓松, 钱东升, 等. 基于非线性动力学模型高速球轴承摩擦力矩研究[J]. 机械工程学报, 2022, 58(17): 181-190.

[53] Li X, Chen K, HuangFu Y, et al. Vibration characteristic analysis of spur gear systems under tooth crack or fracture[J]. Journal of Low Frequency Noise Vibration and Active Control, 2021, 40(1): 135-153.

[54] Shi X, Li K, Wang Z, et al. Fault simulation and modeling of wind turbine gear based on ADAMS[C]. 2016 IEEE International Conference on Information and Automation (ICIA). IEEE, 2016: 1096-1099..

[55] 王双不, 蒋汉军, 邵毅敏. 斜齿轮齿面剥落故障动力学建模与动态特征研究[J]. 机械传动, 2014, 38(10): 26-30.

[56] 王红军, 徐小力, 万鹏. 基于轴心轨迹流形拓扑空间的转子系统故障诊断[J]. 机械工程学报, 2014, 50(5): 95-101.

[57] Yang H, Liu S, Zhang H. Adaptive estimation of VMD modes number based on cross correlation coefficient[J]. Journal of Vibroengineering, 2017, 19(2): 1185-1196.

[58] 岳应娟, 孙钢, 蔡艳平, 等. 变分模态分解在轴承故障诊断中的应用[J]. 轴承, 2016, (8): 50-54, 65.

[59] 马洪斌, 佟庆彬, 张亚男. 优化参数的变分模态分解在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2018, 29(4): 390-397.

[60] Guan Y, Lv M, Dong S. Pressure-driven background leakage models and their application for leak localization using a multi-population genetic algorithm[J]. Water Resources Management, 2023, 37(1): 359-373.

[61] 张玉兰, 张宏伟, 王新环. 基于CEEMDAN-TSMPE-PCA风力发电机齿轮箱高速轴承故障诊断技术[J]. 噪声与振动控制, 2022, 42(4): 158-164, 234.

[62] Jiang F, Zhu Z, Li W. An improved VMD with empirical mode decomposition and its application in incipient fault detection of rolling bearing[J]. IEEE Access, 2018, 6: 44483- 44493.

[63] Shen Z, Shi Z, Shen G, et al. Informative singular value decomposition and its application in fault detection of planetary gearbox[J]. Measurement Science and Technology, 2022, 33(8): 21-26.

[64] Rutledge D N. Comparison of principal components analysis, independent components analysis and common components analysis[J]. Journal of Analysis and Testing, 2018, 2(3): 235-248.

[65] 许海燕, 寇庆康, 谢迎娟, 等. 基于补偿距离估计的光纤振动信号特征提取算法[J]. 光子学报, 2022, 51(4): 57-67.

[66] Xiang, Chuan Ren, Zejun Shi, etc. Data-driven fault diagnosis for rolling bearing based on DIT-FFT and XGBoost[J]. Complexity, 2021.

[67] 张钰, 陈珺, 王晓峰, 等. Xgboost在滚动轴承故障诊断中的应用[J]. 噪声与振动控制, 2017, 37(4): 166-170, 79.

[68] Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks[J]. Information Processing and Management, 2009, 45(4): 427-437.