采用神经网络的断路器传动机构磨损预测

摘要: 针对某大型断路器机构系统磨损试验成本高的特点，通过建立磨损预测模型，对其传动机构危险关节的磨损量进行了预测分析。基于2种典型的预测模型建立方法，采用销盘磨损实验数据，分别建立磨损预测模型。对比分析表明Elman网络模型的预测精度较高，可准确的反映磨损率与接触压力、相对滑动速度和材料硬度之间的规律。考虑运动副间隙的存在，基于非线性弹簧阻尼模型，利用ADAMS软件仿真获得传动机构危险关节的动力学参数。基于Hertz接触理论对动力学参数进行变换，并将其作为预测模型的输入信息，对关节的磨损进行预测计算。通过迭代分析，发现随着断路器开断次数的增加，轴套表面一些特定位置的磨损越来越严重。对比采用固定系数下的Archard模型，表明预测模型计算的结果对磨损失效判定更具参考价值。
- 断路器机构 /
- 磨损预测 /
- 神经网络 /
- Archard模型
Abstract: Considering the feature that the wear experiment cost for the circuit breaker mechanism system is very high, the wear prediction model is established for the dangerous joint. Based on the pin-on-disc experiments data, two kinds of typical models are established for the wear prediction. The comparative study shows that the model based on the Elman neural network can accurately reflect the inherent wear law between wear rate and contact pressure, sliding velocity and material hardness with a high prediction precision. Considering the clearance in revolute joint, the kinematic parameters are obtained by using ADAMS software based on the elastic-damping contact force model. Then, the trained Elman model is employed to predict the wear of dangerous joint, using the parameters transformed by Hertz contact model. It can be seen from iterative analysis that wear occurs seriously in some special areas on bushing surface. The comparison result indicates that the wear calculation from prediction model is more useful for wear failure criteria than the Archard model which uses constant coefficient.
- circuit breaker mechanism /
- wear prediction /
- neural network /
- archard model

HTML全文

参考文献(16)

[1]	温诗铸.材料磨损研究的进展与思考[J].摩擦学学报,2008,28(1):1-5 Wen S Z. Research progress on wear of materials[J]. Tribology, 2008,28(1):1-5 (in Chinese)
[2]	李文丽,原大宁,刘宏昭,等.小子样下机构系统磨损仿真可靠性研究[J].机械工程学报,2015,51(13):235-243 Li W L, Yuan D N, Liu H Z, et al. Reliability research on the mechanism system wear simulation under the case of the small-scale sample[J]. Journal of Mechanical Engineering, 2015,51(13):235-243 (in Chinese)
[3]	国志刚,冯蕴雯,冯元生.铰链磨损可靠性分析及计算方法[J].西北工业大学学报,2006,24(5):644-648 Guo Z G, Feng Y W, Feng Y S. Wear reliability of linkage under periodic loading[J]. Journal of Northwestern Polytechnical University, 2006,24(5):644-648 (in Chinese)
[4]	王国庆,刘宏昭,孙百俊.考虑边界润滑的间隙机构运动副接触磨损[J].长安大学学报(自然科学版),2002,22(6):85-88 Wang G Q, Liu H Z, Song B J. Contact wear of four-bar planar linkage with clearance joint under boundary lubrication[J]. Journal of Chang'an University (Natural Science Edition), 2002,22(6):85-88 (in Chinese)
[5]	Bai Z F, Zhao Y, Chen J. Dynamics analysis of planar mechanical system considering revolute clearance joint wear[J]. Tribology International, 2013,64:85-95
[6]	Flores P. Modeling and simulation of wear in revolute clearance joints in multibody systems[J]. Mechanism and Machine Theory, 2009,44(6):1211-1222
[7]	Mukras S, Kim N H, Mauntler N A, et al. Analysis of planar multibody systems with revolute joint wear[J]. Wear, 2010,268(5-6):643-652
[8]	赵波,戴旭东,张执南,等.柔性多体系统中间隙铰接副的磨损预测[J].摩擦学学报,2013,33(6):638-644 Zhao B, Dai X D, Zhang Z N, et al. Prediction of wear in revolute clearance joints in flexible multibody systems[J]. Tribology, 2013,33(6):638-644 (in Chinese)
[9]	邱明,张永振,朱均.铝基复合材料高速干摩擦行为的遗传神经网络预测模型[J].摩擦学学报,2005,25(6):545-549 Qiu M, Zhang Y Z, Zhu J. Prediction modeling of friction behavior of aluminum matrix composites using neural network and genetic algorithms under high velocity and dry sliding condition[J]. Tribology, 2005,25(6):545-549 (in Chinese)
[10]	徐流杰,魏世忠,王强,等.基于BP神经网络的V9-Cr4-Mo3高速钢冷轧辊磨损模型[J].摩擦学学报,2006,26(6):541-545 Xu L J, Wei S Z, Wang Q, et al. Modeling of wear process of V9-Cr4-Mo3 high speed steel cooling roll via BP neural network[J]. Tribology, 2006,26(6):541-545 (in Chinese)
[11]	Kolodziejczyk T, Toscano R, Fouvry S, et al. Artificial intelligence as efficient technique for ball bearing fretting wear damage prediction[J]. Wear, 2010,268(1-2):309-315
[12]	刘玉兵,张宗扬,吴国军.基于径向基函数神经网络的发动机磨损预测分析[J].润滑与密封,2009,34(1):71-72,83 Liu Y B, Zhang Z Y, Wu G J. Analysis of engine wearing prediction based on radial basis function neural network[J]. Lubrication Engineering, 2009,34(1):71-72,83 (in Chinese)
[13]	白争锋.考虑铰间间隙的机构动力学特性研究[D].哈尔滨:争哈尔滨工业大学,2011 Bai Z F. Research on dynamic characteristics of mechanism with joint clearance[D]. Harbin:Harbin Institute of Technology, 2011 (in Chinese)
[14]	时兵,金烨.面向虚拟样机的机构间隙旋转铰建模与动力学仿真[J].机械工程学报,2009,45(4):299-303 Shi B, Jin Y. Dynamic simulation and modeling of revolute clearance joint for virtual prototyping[J]. Journal of Mechanical Engineering, 2009,45(4):299-303 (in Chinese)
[15]	薛继斌,吕亚非,齐士成,等.基于人工神经网络的摩擦材料性能评价和预测[J].润滑与密封,2014,39(11):14-18,54 Xue J B, Lv Y F, Qi S C, et al. Evaluation and prediction on tribological performances of brake friction materials based on artificial neural networks[J]. Lubrication Engineering, 2014,39(11):14-18,54 (in Chinese)
[16]	宋江腾,曾攀,赵加清,等.基于RBF神经网络模型的司太立合金磨损量预测[J].润滑与密封,2011,36(3):30-32,64 Song J T, Zeng P, Zhao J Q, et al. Analysis of stellite alloys wearing prediction based on radial basis function neural network[J]. Lubrication Engineering, 2011,36(3):30-32,64 (in Chinese)