Affiliation:
1. Shanghai Key Laboratory of Intelligent, Manufacturing and Robotics, School of Mechatronic, Engineering and Automation, Shanghai University, 99 Shangda Road, Shanghai 200444, China
Abstract
Abstract
As an important branch of machine learning, Monte Carlo learning has been successfully applied to engineering design optimization and product predictive analysis, such as design optimization of heavy machinery. However, the accuracy of the classical Monte Carlo algorithm is not high enough, and the existing improved Monte Carlo algorithm has a complex calculation process and difficult parameter control. In this paper, the Monte Carlo method based on boundary point densification is proposed to calculate workspace. This paper takes the calculation of 2000T offshore crane workspace as an example to verify the effectiveness and practicability of the algorithm. The D-H method is used to establish the workspace model of the offshore crane. The calculation method of crane workspace based on the Monte Carlo learning method with increased boundary point density is discussed in detail, and the correctness of crane workspace is verified. The steps of the algorithm include generate the basic space, extract and draw the boundary, increase the density of boundary points, and cyclic. The rationality of the method is proved by comparing the simulation results with the design experience and calculated values.
Funder
National Natural Science Foundation of China
Subject
Industrial and Manufacturing Engineering,Computer Graphics and Computer-Aided Design,Computer Science Applications,Software
Reference22 articles.
1. A Machine Learning Approach to Kinematic Synthesis of Defect-Free Planar Four-Bar Linkages;Deshpande;ASME J. Comput. Inf. Sci. Eng.,2019
2. Digital Twin-Driven Sustainable Intelligent Manufacturing: A Review;He;Adv. Manuf.,2020
3. Data-Driven Smart Manufacturing;Tao;J. Manuf. Syst.,2018
4. Model-Based Contextual Policy Search for Data-Efficient Generalization of Robot Skills;Kupcsik;Artif. Intell.,2017
5. Reinforcement Learning for Production Ramp-Up: A Q-Batch Learning Approach;Doltsinis,2012
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献