To address the low efficiency of manual water immersion and the susceptibility to damage of wooden spoon blanks in the molding process, this paper presents the design of an adaptive flexible gripper for grasping wooden spoon blank bundles. An optimized experimental design was developed using finite element analysis software. A regression prediction model for the gripper's strain energy was constructed using a Random Forest (RF) method optimized by a Bayesian optimization (BO) algorithm, termed BO-RF. Furthermore, the explainable machine learning method, SHAP (SHapley Additive exPlanations), was employed to provide both global and local interpretability analysis of the model. Based on this predictive model, a genetic algorithm (GA) was utilized to perform an optimal design of the flexible gripper, with the conflicting objectives of maximizing the top surface strain energy and minimizing the overall strain energy. The multi-objective Pareto front was computed using the BO-RF model. Simulation results validate the effectiveness and feasibility of the proposed modeling and optimization methodology.
ZHAOH, ZHAIQ L, CAOW H,et al.Static and dynamic characteristics and structural optimization of wooden spoon production line[J].China Forest Products Industry,2024,61(3):52-58,64.
ZHANGZ Y, WANGY, LIL F.Analysis on the development status and trend of wood processing industry against the background of carbon peaking and carbon neutralization[J].Journal of Wildland Fire Science,2022,40(2):90-92.
LEIJ, ZHANGW F, WANGQ,et al.Design and testing of a continuous automatic forming device for bamboo spoons[J].Journal of Forestry Engineering,2023,8(5):152-159.
HUANGH, TANGW Y, SHIY.Research on current situation,problems and coping strategies of artificial intelligence technology in furniture design[J].China Forest Products Industry,2023,60(12):73-78.
ZHANGS, ZHANGJ C, HUANGH,et al.Design of Jansen linkage end linear parallel clamping robot hand for grabbing wooden fork bundles[J/OL].Forest Engineering,2025,1-11[2025-09-03].
[15]
PFAFFO, SIMEONOVS, CIROVICI,et al.Application of finray effect approach for production process automation[M]//Proceedings of the 22nd International DAAAM Symposium,DAAAM International,Vienna,Austria,2011,22(1):1247-1249.
[16]
SUDERJ, BOBOVSKÝZ, MLOTEKJ,et al.Structural optimization method of a FinRay finger for the best wrapping of object[J].Applied Sciences,2021,11(9):3858.
[17]
ELGENEIDYK, LIGHTBODYP, PEARSONS,et al.Characterising 3D-printed soft fin ray robotic fingers with layer jamming capability for delicate grasping[C]//2019 2nd IEEE International Conference on Soft Robotics (RoboSoft).April 14-18,2019.Seoul,Korea.IEEE,2019:143-148.
[18]
DENGZ F, LIM.Learning optimal fin-ray finger design for soft grasping[J].Frontiers in Robotics and AI,2021,7:590076.
[19]
KITAMURAT, MATSUSHITAK, NAKATANIN.Analysis of contact force and shape change on grasping a square object using an actual fin ray soft gripper[J].Sensors,2023,23(24):9827.
[20]
DE BARRIED, PANDYAM, PANDYAH,et al.A deep learning method for vision based force prediction of a soft fin ray gripper using simulation data[J].Frontiers in Robotics and AI,2021,8:631371.
[21]
GOHG L, HUANGX,TOH W,et al.Joint angle prediction for a cable-driven gripper with variable joint stiffness through numerical modeling and machine learning[J].International Journal of Ai for Materials and Design,2024,1(1):62-74.
HANX J, YANGW J, GAOH Y,et al.The kinematics analysis and footprint optimization of the four legged bionic robot based on linkage mechanism[J].Forest Engineering,2017,33(1):52-58.
[24]
LUNDBERGS M, LEES I.A unified approach to interpreting model predictions[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.Long Beach:AMC,2017,30:4768-4777.