
浏览全部资源
扫码关注微信
1.湖南科技大学 机电工程学院,湘潭 411201
2.中国航发中传机械有限公司,长沙 410200
3.湖南大学 机械与运载工程学院,长沙 410082
李佳宾,男,2000年生,山西朔州人,硕士研究生;主要研究方向为齿轮高效精密制造;jiabin_li0@163.com。
陈海锋(通信作者),男,1986年生,湖南湘潭人,博士,副教授;主要研究方向为齿轮高效精密制造;chenhf1986@126.com。
收稿:2024-12-26,
网络首发:2026-04-30,
移动端阅览
李佳宾,陈海锋,刘国亮,等.基于机器学习的弧齿锥齿轮齿面粗糙度预测方法[J].机械传动,XXXX,XX(XX):1-9.
LI Jiabin,CHEN Haifeng,LIU Guoliang,et al.Prediction method for spiral bevel gear tooth surface roughness based on machine learning[J].Journal of Mechanical Transmission,XXXX,XX(XX):1-9.
目的
2
为解决弧齿锥齿轮齿面粗糙度参数优化与预测精度不足的问题,进而克服传统方法难以有效处理复杂的非线性关系和多变量影响的局限,采用机器学习模型对弧齿锥齿轮齿面粗糙度进行预测。
方法
2
首先,基于弧齿锥齿轮磨削试验数据集,分别应用机器学习方法中的决策树(Decision Tree
DT)、支持向量机(Support Vector Regression
SVR)和人工神经网络(Artificial Neural Network
ANN)方法构建弧齿锥齿轮凸面和凹面的粗糙度预测模型,对比3种机器学习模型的预测结果;其次,以此为基础,采用多元线性回归方法推导了考虑弧齿锥齿轮加工参数的齿面粗糙度预测公式;最后,通过机器学习模型解释工具(SHapley Additive exPlanations
SHAP)分析了各输入特征对所预测齿面粗糙度的贡献,为机器学习服务于高性能齿轮制造提供理论支持。
结果
2
结果表明,DT、SVR分别表现出欠拟合和过拟合的状态,预测效果不佳;ANN可以完美地拟合数据并精确预测齿面粗糙度,但计算效率相对较低,其预测弧齿锥齿轮凸面和凹面粗糙度的平均相对误差分别为3.5%和6.09%;各输入加工参数对所预测齿面粗糙度的影响程度依次为磨削速度、磨削深度、展成速度。
Objective
2
To address the issues of parameter optimization and prediction accuracy of the surface roughness of spiral bevel gears
and to overcome the limitations of traditional methods in effectively handling complex nonlinear relationships and the influence of multiple variables
machine learning model is used to predict the surface roughness of the spiral bevel gears.
Methods
2
Firstly
based on the spiral bevel gear grinding test dataset
decision tree (DT)
support vector machine (SVR)
and artificial neural network (ANN) methods are applied to construct roughness prediction models for the convex and concave surfaces of spiral bevel gears
and the prediction results of the three machine learning models are compared. Secondly
based on this
a multiple linear regression method is used to derive a tooth surface roughness prediction formula that considers the processing parameters of spiral bevel gears. Finally
the contribution of each input feature to the predicted tooth surface roughness is analyzed using the machine learning model explanation tool (SHAP)
providing theoretical support for the application of machine learning in high-performance gear manufacturing.
Results
2
The results show that the DT and SVR exhibit underfitting and overfitting
respectively
leading to poor prediction performance. The ANN accurately fits the data and predicts tooth surface roughness with high precision
but its computational efficiency is relatively low. The average relative errors in predicting the roughness of the convex and concave surfaces of the spiral bevel gear are 3.5% and 6.09%
respectively. The influence of the input processing parameters on the predicted tooth surface roughness follows the order of grinding speed
grinding depth
and generating speed.
钱露露 , 刘海鸥 , 高鉴 , 等 . 航空弧齿锥齿轮接触印痕主动设计与试验验证 [J]. 机械传动 , 2024 , 48 ( 5 ): 122 - 130 .
QIAN Lulu , LIU Haiou , GAO Jian , et al . Active design of contact pattern and experimental verification of the aero spiral bevel gear [J]. Journal of Mechanical Transmission , 2024 , 48 ( 5 ): 122 - 130 .
张旭阳 , 王三民 , 李林林 , 等 . 航空弧齿锥齿轮副风阻功率损失分析与优化 [J]. 航空动力学报 , 2023 , 38 ( 4 ): 976 - 985 .
ZHANG Xuyang , WANG Sanmin , LI Linlin , et al . Analysis and optimization of windage power loss for aeronautical spiral bevel gear pair [J]. Journal of Aerospace Power , 2023 , 38 ( 4 ): 976 - 985 .
WEI J , PAN Z , LIN X , et al . Copula-function-based analysis model and dynamic reliability of a gear transmission system considering failure correlations [J]. Fatigue & Fracture of Engineering Materials & Structures , 2019 , 42 ( 1 ): 114 - 128 .
刘斌 , 剡昌锋 , 魏理林 , 等 . 弧齿锥齿轮复合磨粒磨削性能仿真与分析 [J]. 机械强度 , 2023 , 45 ( 3 ): 684 - 691 .
LIU Bin , YAN Changfeng , WEI Lilin , et al . Simulation and analysis of compound abrasive grinding performance of spiral bevel gears [J]. Journal of Mechanical Strength , 2023 , 45 ( 3 ): 684 - 691 .
彭先龙 , 赵朋辉 , 胡锡文 , 等 . 基于四轴数控机床面齿轮磨削方法 [J]. 航空动力学报 , 2021 , 36 ( 5 ): 1113 - 1120 .
PENG Xianlong , ZHAO Penghui , HU Xiwen , et al . Grinding method for face gear based on four-axis CNC machine tool [J]. Journal of Aerospace Power , 2021 , 36 ( 5 ): 1113 - 1120 .
MA X F , CAI Z Q , YAO B , et al . Prediction model for surface generation mechanism and roughness in face gear grinding [J]. The International Journal of Advanced Manufacturing Technology , 2022 , 120 ( 7 ): 4423 - 4442 .
CHEN H F , TANG J Y , ZHOU W . Modeling and predicting of surface roughness for generating grinding gear [J]. Journal of Materials Processing Technology , 2013 , 213 ( 5 ): 717 - 721 .
CHEN H F , TANG J Y , ZHOU W H , et al . The equal theoretical surface roughness grinding method for gear generating grinding [J]. The International Journal of Advanced Manufacturing Technology , 2017 , 90 ( 9 ): 3137 - 3146 .
WANG Y Z , CHEN Y Y , ZHOU G M , et al . Roughness model for tooth surfaces of spiral bevel gears under grinding [J]. Mechanism and Machine Theory , 2016 , 104 : 17 - 30 .
WANG Y Z , LIU Y , CHU X M , et al . Calculation model for surface roughness of face gears by disc wheel grinding [J]. International Journal of Machine Tools and Manufacture , 2017 , 123 : 76 - 88 .
WEN J , TANG J Y , ZHOU W H . Study on formation mechanism and regularity of residual stress in ultrasonic vibration grinding of high strength alloy steel [J]. Journal of Manufacturing Processes , 2021 , 66 : 608 - 622 .
陈小琦 , 唐成 , 廖祥贵 , 等 . 考虑局部磨削条件变化的齿轮成形磨削表面粗糙度建模研究 [J]. 机械传动 , 2023 , 47 ( 8 ): 9 - 15 .
CHEN Xiaoqi , TANG Cheng , LIAO Xianggui , et al . Study on tooth surface roughness modeling of form grinding considering the change of the local grinding condition [J]. Journal of Mechanical Transmission , 2023 , 47 ( 8 ): 9 - 15 .
MAHMOOD M A , VISAN A I , RISTOSCU C , et al . Artificial neural network algorithms for 3D printing [J]. Materials , 2020 , 14 ( 1 ): 163 .
UÇAR F , KATI N D . Machine learning based predictive model for surface roughness in cylindrical grinding of al based metal matrix composite [J]. European Journal of Technic , 2020 , 10 ( 2 ): 415 - 430 .
MIRIFAR S , KADIVAR M , AZARHOUSHANG B , et al . First steps through intelligent grinding using machine learning via integrated acoustic emission sensors [J]. Journal of Manufacturing and Materials Processing , 2020 , 4 ( 2 ): 35 .
FU H , JIANG L P , SONG Q H , et al . Grinding surface roughness prediction for silicon nitride ceramics:a dynamic grinding force and frequency domain approach [J]. Ceramics International , 2023 , 49 ( 22 ): 35239 - 35253 .
ABYANEH M D , NARIMANI P , HADAD M , et al . Using machine learning and optimization for controlling surface roughness in grinding of St 37 Authors [J]. Energy Equipment and Systems , 2023 , 11 ( 3 ): 321 .
LIU X , LIU T Q , FENG P . Long-term performance prediction framework based on XGBoost decision tree for pultruded FRP composites exposed to water,humidity and alkaline solution [J]. Composite Structures , 2022 , 284 : 115184 .
黄迪青 . 螺旋伞齿轮磨削表面完整性实验与仿真研究 [D]. 北京 : 北京理工大学 , 2018 : 29 - 35 .
HUANG Diqing . 螺旋伞齿轮磨削表面完整性实验与仿真研究Experimental and simulation study on grinding surface integrity of spiral bevel gear [D]. Beijing : Beijing Institute of Technology , 2018 .
SONG Y Y . Decision tree methods:applications for classification and prediction [J]. Shanghai Archives of Psychiatry , 2015 , 27 ( 2 ): 130 - 135 .
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621