Diagnosis method for aircraft system sensor faults

• Main Author: LU FANGXIANG
• Format: Patent
• Language: Chinese; English
• Published: 13.08.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention relates to a diagnosis method for aircraft system sensor faults, which comprises the following steps of: performing sample and feature processing on acquired sensor data to serve as a training set for training a fault diagnosis model; according to the training set, using a decision tree, a random forest or a deep neural network method to train a fault diagnosis model so as to construct the fault diagnosis model; using sensor data without sample and feature processing as a test set, and verifying the constructed fault diagnosis model; and after verification of the fault diagnosis model is completed, inputting newly collected sensor data into the fault diagnosis model, and a diagnosis result is obtained. According to the method, the training set comprises data of the equipment under various performances, the trained fault diagnosis model can know what performance of the equipment has faults, and the fault point location can be completely positioned. 本发明涉及一种用于飞机系统传感器故障的诊断方法，包括以下步骤：对获取的传感器数据进行样本及特征处