%0 Journal Article
%T Stochastic scheduling for multiple mould and die manufacturing projects based on MPICH2 and parallel Q-learning<br>基于MPICH2和并行Q学习的模具制造项目群随机调度*
%A ZHANG Sha-qing
%A CHEN Xin-du
%A CHEN Qing-xin
%A CHEN Xin
%A <br>张沙清
%A 陈新度
%A 陈庆新
%A 陈新
%J 计算机应用研究
%D 2010
%I 
%X Through the analysis of uncertainties of the durations, costs and rewards as well as the characteristic of frequent repairing in the mould and die manufacturing project, this paper proposed a stochastic evolution model of multiple mould and die manufacturing projects, which was on the basis of a discrete time Markov chain. With aim to overcome the curse of dimensionality, an algorithm based on MPICH2 and parallel Q-learning was put for ward to solve the above stochastic dynamic programming model. Finally, the algorithm was realized in a multi-core environment by using Visual C++ 6 and was explained with a sample example. The results show that the model is applicable and the algorithm is reliable and effective as well. And the results show that this algorithm can effectively solve stochastic scheduling problems for multiple mould and die manufacturing projects.
%K multiple mould and die manufacturing projects
%K MPICH2
%K multi-core
%K parallel Q-learning
%K Metropolis criterion<br>模具制造项目群
%K MPICH2
%K 多核
%K 并行Q学习
%K Metropolis准则
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=1B39DEC07CC9334509D6589F1C168578&yid=140ECF96957D60B2&vid=DB817633AA4F79B9&iid=9CF7A0430CBB2DFD&sid=B4AB68B7931ADA45&eid=5418BFAA49702DF9&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=11