基于IPSO-Elman神经网络的飞机客舱能耗预测

为了提高飞机客舱使用地面空调制冷时客舱能耗的预测精度，提出了一种改进的粒子群优化（IPSO）Elman神经网络的飞机客舱能耗预测模型。依据对算法中惯性权重与学习因子的收敛域分析，得出了二者合理的取值范围，将粒子到全局最优位置间距离与参数的取值范围相结合，构造了惯性权重与学习因子的动态调节函数，对其进行非线性的动态调节，并引入了变异因子，提出了一种跳出局部最优的策略，防止粒子群优化（PSO）陷入局部最优。将IPSO-Elman应用于Boeing738飞机客舱能耗预测中，与PSO-Elman、Elman算法进行性能比较，仿真结果表明基于IPSO-Elman的客舱能耗预测模型在预测精度和收敛速度方面均有一定的提升。该研究结果为飞机客舱能耗预测模型的建立提供了理论依据，对飞机地面空调的节能与机场电能合理调配提供了支持。

Prediction of aircraft cabin energy consumption based on IPSO-Elman neural network

To improve the prediction accuracy of cabin energy consumption when the aircraft cabin uses ground air conditioning for refrigeration, an aircraft cabin energy consumption prediction model based on the Improved Particle Swarm Optimization (IPSO) Elman neural network is proposed. The main procedure of the IPSO is as follows:the convergence domain analysis of the inertia weight and the learning factors is used to obtain a reasonable range of these two parameters; the range of the two parameters and the distance from the particle to the global optimal position are combined to dynamically adjust the two parameters; the dynamic adjustment function of the inertia weight and the learning factors are then constructed; a variation factor is introduced and a strategy proposed to prevent the PSO from being trapped in the local optimum. The IPSO-Elman is applied to the Boeing738 aircraft cabin energy consumption prediction and compared with PSO-Elman and Elman. The simulation results show the effectiveness of the cabin energy consumption prediction model based on IPSO-Elman in improving both the prediction accuracy and the convergence rate. The research results establish a theoretical basis for the aircraft cabin energy prediction model and provide further support for the energy saving of ground air conditioning and the reasonable allocation of airport electrical energy.