The invention discloses an aircraft environmental control system air cooling equipment robust fault diagnosis method based on a random forest. The method comprises the following specific steps of 1, time series data acquisition and normalization processing; 2, constructing a random forest model and a training sample subset; 3, training each decision tree and finally completing training of the random forest model; and 4, performing robust fault diagnosis on the air cooling equipment of an aircraft environmental control system. The method is advantaged in that the random forest model is adoptedto replace a threshold constructed based on expert knowledge, the logic association relationship with the thermal fault of the air cooling equipment is extracted from the operating parameters of the aircraft environmental control system, and high-robustness diagnosis of the thermal fault of the air cooling equipment is realized by means of joint detection of multiple decision-making trees in the random forest model; the detection risk caused by a single sensor and a single threshold value is avoided by mining the incidence relation between the environment control system parameters and the aircooling equipment fault signals, and the fault detection rate is improved by avoiding the limitation of a single classifier on the fitting degree, therefore, the method has high engineering application value.
本发明公开了一种基于随机森林的飞机环控系统气冷设备鲁棒故障诊断方法,具体步骤如下:步骤一:时序数据获取与归一化处理;步骤二:构建随机森林模型与训练样本子集;步骤三:对每个决策树进行训练并最终完成随机森林模型的训练;步骤四:飞机环控系统气冷设备鲁棒故障诊断。本发明方法采用随机森林模型代替基于专家知识构建的阈值,从飞机环控系统运行参数中提取与气冷设备热故障的逻辑关联关系,并借助随机森林模型中多决策树共同检测,实现高鲁棒性的气冷设备热故障诊断。本方法通过挖掘环控系统参数与气冷设备故障信号间的关联关系,避免了单一传感器、单一阈值带来的检测风险,通过规避单一分类器在拟合程度上的局限性,提高了故障检测率。因此该方法具有较高的工程应用价值。
Aircraft environment control system air cooling equipment robust fault diagnosis method based on random forest
一种基于随机森林的飞机环控系统气冷设备鲁棒故障诊断方法
2020-08-25
Patent
Electronic Resource
Chinese
Satellite attitude control system fault diagnosis and early warning method based on random forest
European Patent Office | 2020
|Aircraft brake system fault diagnosis method and electronic equipment thereof
European Patent Office | 2022
|Fault Diagnosis of MVB Based on Random Forest and Ensemble Pruning
British Library Conference Proceedings | 2020
|