基于Plant Simulation复杂系统GOMS研究

Research on Complex System GOMS Based on Plant Simulation

随着工业化的不断深入,生产线的产能逐渐提升,而生产线中设备的故障类型也不断增多。基于此,本文以设备多种故障模式为前提,建立了多种维修方式并存预防性维修策略优化模型。模型的维修方式包括小修、周期性预防性维修和更换,并且,在周期性预防性维修时可对预防性维修时间相邻的故障模式进行成组维修。基于Plant Simulation工业仿真软件对所建立的维修模型进行仿真。由于故障发生时间存在不确定性,为消除不确定性的影响,需大量调用仿真模型,而降低了计算效率,本文利用人工神经网络训练代理模型以提升维修模型计算效率。以总利润最高为目标函数,采用遗传算法优化预防性维修周期和失效阈值。最后,通过算例验证了预防性维修策略优化模型的有效性。

With the continuous deepening of industrialization,the production capacity of the production line is gradually improved,and the types of equipment failure in the production line are also increasing.Based on this,this paper establishes an optimization model of preventive maintenance strategy based on multiple failure modes of equip-ment.The maintenance modes of the model include minor repair,periodic preventive maintenance and replacement.In addition,during periodic preventive maintenance,group maintenance can be carried out for the failure modes with ad-jacent preventive maintenance time.Plant Simulation software was used to simulate the maintenance model.Due to the uncertainty of fault occurrence time,in order to eliminate the influence of uncertainty,a large number of simulation models need to be called,which reduces the computational efficiency.In this paper,artificial neural network is used to train the agent model to improve the computational efficiency of the maintenance model.Taking the maximum total profit as the objective function,genetic algorithm was used to optimize the preventive maintenance cycle and failure threshold.Finally,the effectiveness of the preventive maintenance strategy optimization model is verified by an exam-ple.