浏览全部资源
扫码关注微信
1.太原科技大学 机械工程学院,太原 030024
2.中联重科股份有限公司,长沙 410013
3.起重机械关键技术全国重点实验室,长沙 410000
DONG Qing, E-mail: 2017013@tyust.edu.cn
Received:16 May 2024,
Revised:04 September 2024,
Published Online:28 April 2025,
移动端阅览
董青,苏友成,徐格宁等.基于集成学习模型的泵车臂架结构疲劳寿命快速预测方法[J].机械强度,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001.
DONG Qing,SU Youcheng,XU Gening,et al.Fast prediction method for fatigue life of pump truck boom structure based on ensemble learning model[J].Journal of Mechanical Strength,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001.
董青,苏友成,徐格宁等.基于集成学习模型的泵车臂架结构疲劳寿命快速预测方法[J].机械强度,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001. DOI:
DONG Qing,SU Youcheng,XU Gening,et al.Fast prediction method for fatigue life of pump truck boom structure based on ensemble learning model[J].Journal of Mechanical Strength,DOI:10.16579/j.issn.1001.9669.XXXX.XX.001. DOI:
目的
2
为快速准确判断在役混凝土泵车臂架结构的疲劳寿命,以监测数据为基础,利用机器学习技术,提出基于集成学习模型的泵车臂架结构疲劳寿命预测方法。
方法
2
首先,利用混凝土泵车信息采集系统,获取泵车服役过程中的功能特征和性能特征,通过数据预处理和转换,得到典型工况下的应力变程样本数据集
O
;并从优势互补的角度出发,以梯度提升决策树(Gradient Boosting Decision Tree
GBDT)、随机森林(Random Forest
RF)、极致随机树(Extra Trees
ET)、自适应提升(Adaptive Boosting
Adaboost)和序贯模型(Sequential)为学习器,构建了一种用于应力变程预测的Stacking模型。其次,利用核密度估计抽样(Kernel Density Estimation Sampling
KDES)法,抽取特定服役周期内泵车运行的功能特征,并将其输入至构建好的Stacking模型,预测得到臂架结构的应力变程数据集。再次,以Matlab软件为计算平台,结合断裂力学理论,实现臂架结构疲劳寿命的快速预测,并通过可靠性分析获得了相应疲劳寿命的可靠度,提高了预测结果的可信度。最后,以某公司的某型混凝土泵车为例,通过与单一机器学习模型对比,验证所提方法的可行性。
结果
2
所提方法可从疲劳寿命入手为泵车检修周期指定与报废决策提供理论依据。
Objective
2
To rapidly and accurately assess the fatigue life of in-service concrete pump truck boom structures
a fatigue life prediction method based on an ensemble learning model is proposed
utilizing monitoring data and machine learning techniques.
Methods
2
Firstly
a concrete pump truck information acquisition system was employed to obtain functional and performance characteristics during the operational phase of the pump truck. Through data preprocessing and transformation
a sample dataset of stress range under typical working conditions
denoted as
O
was generated. From the perspective of complementary advantages
a Stacking model for stress range prediction was constructed using gradient boosting decision tree (GBDT)
random forest (RF)
extra trees (ET)
adaptive boosting (Adaboost)
and sequential learners. Subsequently
kernel density estimation sampling (KDES)was utilized to extract functional characteristics of the pump truck's operation within specific service cycles
which were then input into the established Stacking model to predict the stress range dataset for the boom structure. Furthermore
using Matlab as the computational platform and integrating fracture mechanics theory
rapid predictions of fatigue life for the boom structure were achieved. Reliability analysis was conducted to ascertain the reliability of the corresponding fatigue life predictions
thereby enha
ncing the credibility of the results. Finally
taking a 56X-6RZ model concrete pump truck from a certain company as an example
the feasibility of the proposed method was validated through comparisons with single machine learning models.
Results
2
The proposed method provides a theoretical basis for determining maintenance cycles and retirement decisions for pump trucks based on fatigue life assessments.
李鹏 , 王一棠 , 王佳茜 , 等 . 数据驱动的混凝土泵车臂架疲劳载荷谱编制 [J]. 中国机械工程 , 2024 , 35 ( 10 ): 1881 - 1889 .
LI Peng , WANG Yitang , WANG Jiaqian , et al . Data-driven fatigue load spectrum compiling of concrete pump truck booms [J]. China Mechanical Engineering , 2024 , 35 ( 10 ): 1881 - 1889 . (In Chinese)
SUN X J , YE H , FEI S M . A closed-loop detection and open-loop control strategy for booms of truck-mounted concrete pump [J]. Automation in Construction , 2013 , 31 : 265 - 273 .
唐涛 , 张飞庆 , 佘玲娟 . 基于名义应力法的高强钢泵车臂架疲劳寿命研究 [J]. 工程机械 , 2016 , 47 ( 3 ): 12 - 17 .
TANG Tao , ZHANG Feiqing , SHE Lingjuan . A study on fatigue life of high strength steel used in pump truck boom frames as based on nominal stress process [J]. Construction Machinery and Equipment , 2016 , 47 ( 3 ): 12 - 17 . (In Chinese)
ZHU Q Y , LU P M , XIANG Q Y . Fatigue life evaluation of web butt welding structure on boom of excavator by hot spot stress approach [J]. Engineering Failure Analysis , 2020 , 113 : 104547 .
渠晓刚 , 张晓康 , 焦松岩 , 等 . 基于断裂力学的桥式起重机剩余寿命数值仿真 [J]. 安全与环境学报 , 2022 , 22 ( 3 ): 1284 - 1290 .
QU Xiaogang , ZHANG Xiaokang , JIAO Songyan , et al . Numerical simulation research on residual life of bridge crane based on fracture mechanics [J]. Journal of Safety and Environment , 2022 , 22 ( 3 ): 1284 - 1290 . (In Chinese)
杨海宾 , 朱涛 , 肖守讷 , 等 . 基于结构应力法的车体结构疲劳裂纹扩展与剩余寿命评估 [J]. 铁道机车车辆 , 2019 , 39 ( 1 ): 15 - 20 .
YANG Haibin , ZHU Tao , XIAO Shoune , et al . Fatigue crack propagation and residual life evaluation method of vehicle body structure based on structural stress method [J]. Railway Locomotive & Car , 2019 , 39 ( 1 ): 15 - 20 . (In Chinese)
TIAN B J , XIONG J J , LIU J Z . A new approach for evaluating fatigue lives of multi-fastener mechanical joints based on a nominal stress concept and minimal datasets [J]. International Journal of Fatigue , 2015 , 80 : 257 - 265 .
OSHOGBUNU E O , WANG Y C , STALLARD T . Reliability and applications of a new design method for calculating hot-spot stress in CHS double K-joints under arbitrary combined loading [J]. Structures , 2021 , 29 : 1610 - 1626 .
FUNARI M F , LONETTI P , SPADEA S . A crack growth strategy based on moving mesh method and fracture mechanics [J]. Theoretical and Applied Fracture Mechanics , 2019 , 102 : 103 - 115 .
YANG L , YANG B , YANG G W , et al . Fatigue evaluation method based on equivalent structural stress approach for bolted connections [J]. International Journal of Fatigue , 2023 , 174 : 107738 .
JIANG S Q , ZHANG W , CHEN X D , et al . CFD-DEM simulation research on optimization of spatial attitude of concrete pumping boom based on evaluation of minimum pressure loss [J]. Powder Technology , 2022 , 403 : 117365 .
CAZZULANI G , GHIELMETTI C , GIBERTI H , et al . A test rig and numerical model for investigating truck mounted concrete pumps [J]. Automation in Construction , 2011 , 20 ( 8 ): 1133 - 1142 .
XIANG S , QIN Y , LUO J , et al . A concise self-adapting deep learning network for machine remaining useful life prediction [J]. Mechanical Systems and Signal Processing , 2023 , 191 : 110187 .
戚其松 , 李成刚 , 董青 , 等 . 起重机生命周期载荷谱预测及基于疲劳寿命的结构优化设计 [J]. 工程设计学报 , 2023 , 30 ( 3 ): 380 - 389 .
QI Qisong , LI Chenggang , DONG Qing , et al . Prediction of load spectrum for crane life cycle and structural optimal design based on fatigue life [J]. Chinese Journal of Engineering Design , 2023 , 30 ( 3 ): 380 - 389 . (In Chinese)
蔡薇薇 , 徐彦伟 , 颉潭成 . 基于CNN-LSTM的轴承剩余使用寿命预测 [J]. 机械传动 , 2022 , 46 ( 10 ): 17 - 23 .
CAI Weiwei , XU Yanwei , XIE Tancheng . Prediction of bearing remaining service life based on CNN-LSTM [J]. Journal of Mecha-nical Transmission , 2022 , 46 ( 10 ): 17 - 23 . (In Chinese)
SHAHEEN B , KOCSIS Á , NÉMETH I . Data-driven failure prediction and RUL estimation of mechanical components using accumulative artificial neural networks [J]. Engineering Applications of Arti-ficial Intelligence , 2023 , 119 : 105749 .
FRIEDMAN J H . Greedy function approximation: a gradient boosting machine [J]. Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .
BREIMAN L . Random forests [J]. Machine Learning , 2001 , 45 ( 1 ): 5 - 32
GEYRTS P , ERNST D , WEHENKEL L . Extremely randomized tress [J]. Machine Learning , 2006 , 63 : 3 - 42 .
FREUND Y , SCHAPIRE R E . A decision-theoretic generalization of on-line learning and an application to boosting [J]. Journal of Computer and System Sciences , 1997 , 55 ( 1 ): 119 - 139 .
WOLPERT D H . Stacked generalization [J]. Neural Networks , 1992 , 5 ( 2 ): 241 - 259 .
文昌俊 , 陈哲 , 邵明颖 , 等 . 基于改进PSO-BP神经网络的干燥机可靠性预测 [J]. 机械强度 , 2023 , 45 ( 2 ): 504 - 508 .
WEN Changjun , CHEN Zhe , SHAO Mingying , et al . Reliability prediction of dryer based on improved PSO-BP neural network [J]. Journal of Mechanical Strength , 2023 , 45 ( 2 ): 504 - 508 . (In Chinese)
QIAN H M , WEI J , HUANG H Z . Structural fatigue reliability analysis based on active learning Kriging model [J]. International Journal of Fatigue , 2023 , 172 : 107639 .
常琦 , 陈乐乐 , 赵恒 , 等 . 基于数字孪生的裂纹扩展结构健康管理方法研究 [J]. 振动与冲击 , 2023 , 42 ( 9 ): 253 - 260 .
CHANG Qi , CHEN Lele , ZHAO Heng , et al . Health management method of crack propagation structures based on digital twin [J]. Journal of Vibration and Shock , 2023 , 42 ( 9 ): 253 - 260 . (In Chinese)
FARHANGI F . Investigating the role of data preprocessing,hyperparameters tuning,and type of machine learning algorithm in the improvement of drowsy EEG signal modeling [J]. Intelligent Systems with Applications , 2022 , 15 : 200100 .
KUANG Y C , LU Z P , LI L Y , et al . Robust constrained Kalman filter algorithm considering time registration for GNSS/Acoustic joint positioning [J]. Applied Ocean Research , 2021 , 107 : 102435 .
全国起重机械标准化技术委员会 . 起重机 金属结构能力验证 : GB/T 30024—2020 [S]. 北京 : 中国标准出版社 , 2020 , 1 - 72 .
National Technical Committee for Standardization of Lifting Machi-nery . Cranes—Proof of competence of steel structures : GB/T 30024—2020 [S]. Beijing : Standards Press of China , 2020 , 1 - 72. (In Chinese)
邹喜红 , 周擎 , 袁冬梅 , 等 . 主减速器台架疲劳试验等效方法研究 [J]. 机械传动 , 2024 , 48 ( 6 ): 153 - 161 .
ZOU Xihong , ZHOU Qing , YUAN Dongmei , et al . Research on equivalent method of bench fatigue tests for main reducers [J]. Journal of Mechanical Transmission , 2024 , 48 ( 6 ): 153 - 161 . (In Chinese)
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution