针对工控系统现场网中的物理设备状态信息,提出一种利用BP神经网络模型实时分析和判断设备是否处于正常运行状态的入侵检测算法.该算法旨在能够发现来自工控系统内外部的入侵行为和合法控制指令被恶意利用的复杂攻击. Aiming at the status information of the physical equipment in the field network of industrial control system, this paper proposes an intrusion detection algorithm which uses BP neural network model to analyze and determine whether the equipment is in normal operation in real time.The algorithm aims to find intrusion detection from inside and outside of industrial control system and Complex controls that lawfully control the malicious use of instructions.