|
|||||
|
|
| 模糊识别和随机森林算法在柴油机振动信号状态识别中的应用 | |
| 引用本文： | 曹玉坤,何嘉武,冯辅周,饶国强,范结绪. 模糊识别和随机森林算法在柴油机振动信号状态识别中的应用[J]. 装甲兵工程学院学报, 2008, 22(4) |
| 作者姓名： | 曹玉坤 何嘉武 冯辅周 饶国强 范结绪 |
| 作者单位： | 1. 装甲兵工程学院,科研部,北京,100072 2. 装甲兵工程学院,机械工程系,北京,100072 3. 北京军区坦克乘员训练大队,长治,046021 |
| 摘 要： | 针对模糊识别算法中,样本特征向量中各参量(分量)对状态分类的贡献权重难以确定的问题,提出了利用随机森林算法对特征参量的重要度评估结果作为特征权重的方法。通过对柴油机台架试验振动信号的跟踪分析,获得了柴油机在磨合期、100摩托小时、200摩托小时、300摩托小时及400摩托小时5种不同使用期(典型状态)的75个振动信号样本,然后计算出各类样本在幅域、时域和频域的特征参量,利用随机森林算法进行特征选择,确定4个重要特征参量及其权重,用统计方法得出其隶属度函数,最后根据评价向量对样本进行识别,识别准确率达到94%以上。 |
| 关 键 词： | 随机森林 隶属度 评价向量 模糊识别 状态识别系统 |
Application of Fuzzy Diagnosis and Random Forest Algorithm to Vibration Signal Status Recognition of Diesel Engine |
|
| CAO Yu-kun,HE Jia-wu,FENG Fu-zhou,RAO Guo-qiang,FAN Jie-xu. Application of Fuzzy Diagnosis and Random Forest Algorithm to Vibration Signal Status Recognition of Diesel Engine[J]. Journal of Armored Force Engineering Institute, 2008, 22(4) | |
| Authors: | CAO Yu-kun HE Jia-wu FENG Fu-zhou RAO Guo-qiang FAN Jie-xu |
| Affiliation: | 1.Department of Science Research; Academy of Armored Force Engineering; Beijing 100072; China; 2.Department of Mechanical Engineering; 3.Training Team for Tank Crew of Beijing Military Area; Changzhi 046021; China); |
| Abstract: | In view of the problem that the parameter weights are difficult determined in fuzzy diagnosis,random forest algorithm(RFA) based on weight determination method of feature parameters is put forward in this paper.The importance of feature parameters evaluated by RFA is used as a feature weight in Fuzzy diagnosis.By collecting and selecting vibration signals acquired from the diesel engine bench test,a sample sets including 75 vibration samples representing 5 typical conditions are considered in this paper.The... |
| Keywords: | random forest degree of membership evaluation vector fuzzy diagnosis condition recognition system |
| 本文献已被 维普 万方数据 等数据库收录！ | |