To study the influence of geometric characteristic parameters and forming process parameters of automobile stamping die on the sharp-edged wear and realize the accurate prediction of the die sharp-edged wear, a prediction method of the die sharp-edged wear based on improved SVR algorithm was proposed in this paper. By using the improved Latin hypercube sampling (ILHS) method, the experimental samples of finite element calculation of die sharp-edged wear were obtained, and the input parameter set of the prediction model was then constructed. The chaos theory and dynamic weights were introduced into the grasshopper optimization algorithm (GOA), and the improved grasshopper optimization algorithm (IGOA) was used to improve key parameters of the SVR algorithm. Based on the IGOA-SVR algorithm, the prediction model of die sharp-edged wear was constructed, which was combined with the particle swarm optimization (PSO) algorithm to establish a multi-objective optimization model so as to realize the high-precision prediction as well as the optimization of geometric characteristic parameters and forming process parameters. Compared with five existing conventional prediction models, the prediction errors of the prediction model based on IGOA-SVR at the sampling point were 8.546%, 8.497%, and 8.473%, respectively, which were 25.9%, 26.2%, and 26.4% higher than the GOA-SVR prediction model, respectively, and the prediction accuracy was also improved to varying degrees compared with other prediction models. The results show that the improved IGOA-SVR has higher accuracy.
针对汽车覆盖件模具磨损计算以及模具寿命预测问题,目前国内外学者大多采用有限元法(Finite Element Method,FEM)对汽车覆盖件成形过程进行模拟,采用Archard理论对模具磨损进行数值计算[3],进而实现对模具的寿命预测.1953年,英国 Archard提出磨损计算理论,此后国外学者以该理论为基础开展大量的模具磨损研究;Burwell[4]研究磨损产生的机理,并将磨损分为粘着磨损、磨粒磨损、腐蚀磨损、冲蚀磨损、疲劳磨损和微动磨损等类型,构建磨损研究的基础;Lee等人[5]采用有限元法研究普通钢材模具的摩擦系数、模具温度对磨损量的影响;Altan等人[6]基于模具成形中磨损、应力、应变的关系,得出磨损易发生在应力集中处的结论;Kim等人[7]结合仿真和实验研究温度和成形速度对模具磨损的影响;陈晓航[8]通过有限元分析研究了工艺参数对模具磨损的影响,并采用Pro-M法和磨损累积法预测模具的疲劳寿命.谢晖等人[9]基于有限元法建立了超高强钢板冲压模具磨损预测模型,并研究了成形工艺参数对模具磨损程度的影响规律.上述学者采用有限元数值模拟的方法对模具磨损进行计算,研究了成形工艺参数对模具磨损的影响.
NIEX, NINGM Q, QIAOX Y .Research on stamping die wear life based on dynamic model[J].China Journal of Highway and Transport,2018,31(3):133-141.(in Chinese)
[5]
DYCKT, OBER-WÖRDERP, BUNDA .Calculation of the wear surface and the coefficient of friction for various coated contact geometries[J].Wear,2016,368/369:390-399.
[6]
BURWELLJ T Jr .Survey of possible wear mechanisms[J].Wear,1957, 1(2): 119-141.
[7]
LEER S, JOUJ L .Application of numerical simulation for wear analysis of warm forging die[J].Journal of Materials Processing Technology,2003,140(1/3):43-48.
[8]
ALTANT, KNOERRM. Application of the 2D finite element method to simulation of cold-forging processes[J]. Journal of Materials Processing Technology,1992,35(3/4):275-302.
[9]
KIMD H, LEEH C, KIMB M,et al .Estimation of die service life against plastic deformation and wear during hot forging processes[J].Journal of Materials Processing Technology, 2005,166(3): 372-380.
CHENX H. Life prediction and failure analysis of the punching die for small holes on thick plate based on numerical simulation [D]. Chongqing: Chongqing University of Technology,2013. (in Chinese)
XIEH, LIJ M, WANGS E,et al .Research and application of die wear CAE analysis of ultra high strength steel stamping[J].Journal of Hunan University (Natural Sciences), 2015, 42(8): 15-21.(in Chinese)
CHENR P, DAIT, ZHANGP,et al .Prediction method of tunneling-induced ground settlement using machine learning algorithms[J].Journal of Hunan University (Natural Sciences),2021, 48(7): 111-118.(in Chinese)
DUANL, SONGC Y, LIUC,et al .State recognition in bearing temperature of high-speed train based on machine learning algorithms[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(1): 53-62.(in Chinese)
NIEX, TANT, SHEND F .Research on stamping springback of automobile beam parts based on deep learning[J]. China Mechanical Engineering,2023,34(7):838-846.(in Chinese)
[20]
HAMBLIR, GUERINF .Application of a neural network for optimum clearance prediction in sheet metal blanking processes[J].Finite Elements in Analysis and Design,2003,39(11):1039-1052.
WUF, NONGH Y, MAC H .Tool wear prediction method based on particle swarm optimization long and short time memory model[J].Journal of Jilin University (Engineering and Technology Edition),2023,53(4):989-997.(in Chinese)
LIUM, SUNC Z, WANGX S. Stress prediction method of automobile structural part based on deep learning[C]//China Society of Automotive Engineers. Beijing: China Machine Press, 2021.
HUANGY, SUNX P, WANGL G, et al .Wear prediction of extrusion die based on BP neutral networks[J]. Journal of Plasticity Engineering,2006,13(2):64-66.(in Chinese)
[27]
ERIKSENM .The influence of die geometry on tool wear in deep drawing[J].Wear,1997,207(1/2):10-15.
JIANGL, JIAQ R, XIEH,et al. Forming process optimization of double-sharp-edged aluminum alloy fender based on SVR model[J].Manufacturing Technology & Machine Tool,2022(12): 113-120.(in Chinese)
[30]
DRUCKERH, BURGESC J C, KAUFMANL, et al .Support vector regression machines[C]//Proceedings of the 9th International Conference on Neural Information Processing Systems.Denver,Colorado: ACM, 1996: 155-161.
[31]
GAMPAS R, JASTHIK, GOLIP,et al .Grasshopper optimization algorithm based two stage fuzzy multiobjective approach for optimum sizing and placement of distributed generations,shunt capacitors and electric vehicle charging stations[J].Journal of Energy Storage,2020,27:101117.
[32]
HESHMATIM, NOROOZIANR, JALILZADEHS, et al .Optimal design of CDM controller to frequency control of a realistic power system equipped with storage devices using grasshopper optimization algorithm[J].ISA Transactions,2020,97:202-215.