基于CNN的泄漏电缆入侵检测定位算法

Leakage Cable Intrusion Detection and Location Algorithms Based on CNN

泄漏电缆入侵检测系统所处的外部环境较为复杂,为降低环境因素对泄露电缆入侵检测的影响,提出了基于卷积神经网络的入侵检测算法。通过卷积神经网络处理大量的样本数据,并从数据中自动提取内在特性,实现泄漏电缆电磁入侵检测系统更低的误报率、漏报率和更高的定位精度的目标,搭建了卷积神经网络入侵检测模型,并用样本数据对模型进行训练和测试。模型测试结果表示其具有低漏报率和误报率,定位精度可达到1 m。

Leakage cable intrusion detection system usually faces complex external environments.Therefore,in order to reduce the impact of environmental factors,an intrusion detection algorithm based on the convolutional neural network(CNN)is proposed.The CNN is used to process a large amount of sample data,and the intrinsic characteristics are automatically extracted from the data to realize the goal of lower false alarm rate,missing alarm rate and higher positioning accuracy in the leakage cable intrusion detection system.A CNN-based intrusion detection model is established to train and test the sample data,and the model test results show that it has low missing alarm rate and false alarm rate,and its positioning accuracy can reach 1 m.