In this paper, we demonstrate the application of MATLAB to develop a pandemic prediction system based on Simulink. The susceptible-exposed-asymptomatic but infectious-symptomatic and infectious (severe infected population + mild infected population)-recovered-deceased (SEAI(I ₁ + I ₂)RD) physical model for unsupervised learning and two types of supervised learning, namely, fuzzy proportional–integral–derivative (PID) and wavelet neural-network PID learning, are used to build a predictive-control system model that enables self-learning artificial intelligence (AI)-based control. After parameter setting, the data entering the model are predicted, and the value of the data set at a future moment is calculated. PID controllers are added to ensure that the system does not diverge at the beginning of iterative learning. To adapt to complex system conditions and afford excellent control, a wavelet neural-network PID control strategy is developed that can be adjusted and corrected in real time, according to the output error.

在本文中，我们展示了 MATLAB 在开发基于 Simulink 的大流行预测系统中的应用。易感-暴露-无症状但有传染性-有症状和传染性（重度感染人群+轻度感染人群）-康复-死亡（SEAI（I ₁ + I _2）)RD) 物理模型用于无监督学习和两类监督学习，即模糊比例-积分-微分 (PID) 和小波神经网络 PID 学习，用于构建预测控制系统模型，使自学习人工基于智能 (AI) 的控制。参数设置后，对进入模型的数据进行预测，计算出该数据集在未来时刻的价值。添加PID控制器以确保系统在迭代学习开始时不会发散。为了适应复杂的系统条件并提供出色的控制，开发了一种可以根据输出误差实时调整和校正的小波神经网络 PID 控制策略。