关键备品配件是复杂装备的核心部件，关键备件的使用量预测对复杂装备的运行维护工作具有重要意义。提出一种基于模糊神经网络和粒子群算法的两段式的复杂装备关键备品使用量的预测方法，作为设备密集型企业备品配件管理工作提供科学的决策支撑。以某企业的实际备品配件相关数据作为实验数据集，以双重指数平滑、移动平均、传统模糊神经网络和该方法作为比较算法，验证了该方法的有效性。%Key spare parts are the core components of the complex equipment,forecasting the demanded amount of key spare parts has great significance to the operation and maintenance of the complex equipments.We propose a two-stage forecasting method for the demanded amount of complex equipments,which is based on fuzzy neural network (FNN)and particle swarm optimisation and is used as the scientific decision-making support provided for the equipment intensive enterprises in their spare parts and components management work.Taking the correlated data of practical spare parts and components in a certain enterprise as the experimental dataset,we verify the effectiveness of the proposed method by using double exponential smoothing (DES),moving average (MA),traditional FNN and this method as the comparison algorithms.
展开▼
