摘要
提出利用神经网络和模拟退火技术来求解有约束的FMS资源调度问题的一种新方法。有约束的FMS资源调度被分解为一系列时间间隔的调度，这些时间间隔的调度由事件驱动，随着这些时间间隔的调度的完成，整个调度过程结束。仿真结果表明，这种方法能以较快的求解速度得到全局最优解。
In this paper, an approach for resource constrained FMS scheduling is described,which integrates Hopfield neural network and simulated annealing algorithm. The resource constrained FMS scheduling problem is decomposed firstly into a series of interval scheduling which is activated by accidents. The whole scheduling is completed when a series of interval scheduling is fulfilled. The simulated results show that the approach can dislodge a state from a local minimum and guide it to the global minimum.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
1998年第3期23-24,共2页
China Mechanical Engineering
基金
航空科学基金!94G52001
关键词
模拟退火
神经网络
FMS
资源调度
simulated annealing
neural network
FMS
resource scheduling
