Statistical tolerance allocation design considering form errors based on rigid assembly simulation and deep Q-network
- PDF / 5,608,411 Bytes
- 17 Pages / 595.224 x 790.955 pts Page_size
- 77 Downloads / 170 Views
ORIGINAL ARTICLE
Statistical tolerance allocation design considering form errors based on rigid assembly simulation and deep Q-network Ci He1 · Shuyou Zhang1 · Lemiao Qiu1
· Zili Wang1 · Yang Wang1 · Xiaojian Liu2
Received: 29 May 2020 / Accepted: 19 October 2020 / Published online: 6 November 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Consideration of form errors involves real machining features in tolerance modeling but increases uncertainties in functional requirement estimation, when tackling the trade-off between the cost and precision performance. In this paper, a statistical tolerance allocation method is presented to solve this problem. First of all, a top-down stepwise designing procedure is designed for complex products, and a combination of Jacobian matrix and Skin Model Shapes is applied in modeling the mechanical joints. Then, rigid assembly simulations of point-based surfaces are further advanced to provide an accurate estimation of the assembly state, through considering physical constraints and termination conditions. A mini-batch gradient descent method and a backtracking strategy are also proposed to promote computational efficiency. Finally, a deep Qnetwork is implemented in optimal computation after characterizing the systematic state, action domain, and reward function. The general tolerance scheme is then achieved using the trained Q-network. The results of 6 experiments each with 200 samples show the proposed method is capable of assessing tolerance schemes with 35.2% and 47.2% lower manufacturing costs and 16.7% and 28.3% higher precision maintenance on average than conventional particle swarm optimization and Monte Carlo method respectively. Keywords Tolerance allocation · Tolerance modeling · Rigid assembly simulation · Computer aided tolerancing · Product design
1 Introduction As a vital link between designing, manufacturing, and assembling phases, tolerance has been an important tool for specifying and controlling divergence from the nominal features in mechanical products. Generally, design scheme with narrow tolerances tends to show great functional performance and better precision retention, but results in a higher cost in manufacture [1]. Tolerance allocation (also named tolerance synthesis) acts as a trade-off between precision and cost in the design stage of industrial production [2]. However, because of the natural statistical and stochastic property of form errors [3, 4], it is difficult to formulate a certain and explicit functional relation from Lemiao Qiu
[email protected] 1
State Key Laboratory of Fluid Power, Mechatronic Systems, Zhejiang University, Hangzhou, China
2
Ningbo Research Institute, Zhejiang University, Ningbo, China
tolerances to performance, which in return brings trouble finding the optimal design scheme. Fundamental researches have focused on computeraided tolerance representation. The taxonomy and major methods are reviewed in some representative literature [5– 7]. The most significant tolerance models are basically ca
Data Loading...
