The invention provides an analog simulation anomaly detection method and an analog simulation anomaly detection device for air traffic control based on the Hopfield neural network. The method comprises the steps of S1, acquiring sample parameters inputted by a controller through a radar control simulator, and determining a level discrete type classification standard; S2, carrying out level discrete type classification on each sample parameter according to the classification standard, encoding classification results, and acquiring a sample comprehensive index corresponding to each sample parameter; S3, training based on the sample parameters and the sample comprehensive indexes of level discrete type classification so as to acquire the Hopfield neural network, and calculating factors of the Hopfield neural network; S4, acquiring real-time simulation parameters inputted by the controller through the radar control simulator; S5, carrying out level discrete type classification on the real-time simulation parameters, and calculating a corresponding comprehensive index according to the Hopfield neural network; and S6, giving out an anomaly warning if the comprehensive index acquired in the step S4 belongs to an anomaly category. Therefore, detection can be carried out on the simulation parameters which are inputted by the controller in real time in the air traffic control analog simulation anomaly detection process, classification and abnormal operation prompts corresponding to the input parameters are detected timely and accurately.
Analog simulation anomaly detection method and analog simulation anomaly detection device for air traffic control based on Hopfield neural network
20.01.2016
Patent
Elektronische Ressource
Englisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2020
|Europäisches Patentamt | 2022
|