基于智能优化灰色模型的电子固废预测

Electronic Solid Waste Prediction Based on Intelligent Optimization Grey Model

针对已有电子固废产生量预测时存在的建模机理复杂、建模精度低等问题,提出一种分数阶多元灰色模型与神经网络补偿模型相混合的智能建模方法。利用粒子群算法对灰色模型的累加阶数以及背景值参数寻优,发挥灰色模型的最大性能;利用BP神经网络对灰色建模的误差进行补偿,提高固废产生量的预测精度;利用华盛顿州电子固废数据验证了所提方法的有效性。通过对电子固废产生量的精确估计,为电子固废回收的基础设施规划、回收流程优化等提供参考。

Aiming at the problems of complex modeling mechanism and low modeling accuracy in the prediction of electronic solid waste production,an intelligent modeling method combining fractional order multiple gray model and neural network compensation model is proposed.Particle swarm optimization is used to optimize the accumulative order and background parameters of the gray model to maximize the performance of the gray model.BP neural network is used to compensate the error of gray modeling and improve the prediction accuracy of solid waste production.The effectiveness of the proposed method is verified by Washington state electronic solid waste data.The accurate estimation of electronic solid waste production provides reference for infrastructure planning and process optimization of electronic solid waste recovery.