数据清洗、特征选择和预测模型建立是基于数据采集与监视控制系统(supervisory control and data acquisition,SCADA)数据,实现风电机组异常状态预警不可缺少的重要环节。先结合孤立森林(isolation forest,iForest)和基于密度的空间聚类...数据清洗、特征选择和预测模型建立是基于数据采集与监视控制系统(supervisory control and data acquisition,SCADA)数据,实现风电机组异常状态预警不可缺少的重要环节。先结合孤立森林(isolation forest,iForest)和基于密度的空间聚类(density-based spatial clustering of applications with noise,DBSCAN)算法对SCADA数据异常点进行有效清洗,并采用随机森林算法(random forests,RF)与Person相关系数法优选模型输入参数;再进而基于Optuna优化的类别提升树(categorical boosting,CATBoost)算法,建立风电机组正常工况齿轮箱油池温度的预测模型;然后采用滑动窗方法,构建状态评价指标,并使用区间估计理论确定油温异常状态判别的临界阈值;实现油温异常预警;最后,采用某风电机组SCADA系统油温异常的真实历史故障数据进行检验,验证了该方法的有效性。展开更多
空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory...空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory)与自编码器(AE,autoencoder)模型的无监督异常检测方法,用以识别民机空调系统异常运行状态。首先,基于民机空调系统原始传感器参数构建表征空调热交换器性能的特征监测参数;其次,构建LSTM-AE模型进行数据特征重构并计算重构误差;最后,使用孤立森林(iForest, isolation forest)进行无监督异常监测。将本文构建的无监督异常检测方法与传统方法对比,并建立模型评估指标,验证结果表明,所构建的模型方法可以对民机空调热交换器性能异常状态进行有效检测。展开更多
Detection of unknown attacks like a zero-day attack is a research field that has long been studied.Recently,advances in Machine Learning(ML)and Artificial Intelligence(AI)have led to the emergence of many kinds of att...Detection of unknown attacks like a zero-day attack is a research field that has long been studied.Recently,advances in Machine Learning(ML)and Artificial Intelligence(AI)have led to the emergence of many kinds of attack-generation tools developed using these technologies to evade detection skillfully.Anomaly detection and misuse detection are the most commonly used techniques for detecting intrusion by unknown attacks.Although anomaly detection is adequate for detecting unknown attacks,its disadvantage is the possibility of high false alarms.Misuse detection has low false alarms;its limitation is that it can detect only known attacks.To overcome such limitations,many researchers have proposed a hybrid intrusion detection that integrates these two detection techniques.This method can overcome the limitations of conventional methods and works better in detecting unknown attacks.However,this method does not accurately classify attacks like similar to normal or known attacks.Therefore,we proposed a hybrid intrusion detection to detect unknown attacks similar to normal and known attacks.In anomaly detection,the model was designed to perform normal detection using Fuzzy c-means(FCM)and identify attacks hidden in normal predicted data using relabeling.In misuse detection,the model was designed to detect previously known attacks using Classification and Regression Trees(CART)and apply Isolation Forest(iForest)to classify unknown attacks hidden in known attacks.As an experiment result,the application of relabeling improved attack detection accuracy in anomaly detection by approximately 11%and enhanced the performance of unknown attack detection in misuse detection by approximately 10%.展开更多
文摘数据清洗、特征选择和预测模型建立是基于数据采集与监视控制系统(supervisory control and data acquisition,SCADA)数据,实现风电机组异常状态预警不可缺少的重要环节。先结合孤立森林(isolation forest,iForest)和基于密度的空间聚类(density-based spatial clustering of applications with noise,DBSCAN)算法对SCADA数据异常点进行有效清洗,并采用随机森林算法(random forests,RF)与Person相关系数法优选模型输入参数;再进而基于Optuna优化的类别提升树(categorical boosting,CATBoost)算法,建立风电机组正常工况齿轮箱油池温度的预测模型;然后采用滑动窗方法,构建状态评价指标,并使用区间估计理论确定油温异常状态判别的临界阈值;实现油温异常预警;最后,采用某风电机组SCADA系统油温异常的真实历史故障数据进行检验,验证了该方法的有效性。
文摘空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory)与自编码器(AE,autoencoder)模型的无监督异常检测方法,用以识别民机空调系统异常运行状态。首先,基于民机空调系统原始传感器参数构建表征空调热交换器性能的特征监测参数;其次,构建LSTM-AE模型进行数据特征重构并计算重构误差;最后,使用孤立森林(iForest, isolation forest)进行无监督异常监测。将本文构建的无监督异常检测方法与传统方法对比,并建立模型评估指标,验证结果表明,所构建的模型方法可以对民机空调热交换器性能异常状态进行有效检测。
基金This work was supported by the Research Program through the National Research Foundation of Korea,NRF-2018R1D1A1B07050864,and was supported by another the Agency for Defense Development,UD200020ED.
文摘Detection of unknown attacks like a zero-day attack is a research field that has long been studied.Recently,advances in Machine Learning(ML)and Artificial Intelligence(AI)have led to the emergence of many kinds of attack-generation tools developed using these technologies to evade detection skillfully.Anomaly detection and misuse detection are the most commonly used techniques for detecting intrusion by unknown attacks.Although anomaly detection is adequate for detecting unknown attacks,its disadvantage is the possibility of high false alarms.Misuse detection has low false alarms;its limitation is that it can detect only known attacks.To overcome such limitations,many researchers have proposed a hybrid intrusion detection that integrates these two detection techniques.This method can overcome the limitations of conventional methods and works better in detecting unknown attacks.However,this method does not accurately classify attacks like similar to normal or known attacks.Therefore,we proposed a hybrid intrusion detection to detect unknown attacks similar to normal and known attacks.In anomaly detection,the model was designed to perform normal detection using Fuzzy c-means(FCM)and identify attacks hidden in normal predicted data using relabeling.In misuse detection,the model was designed to detect previously known attacks using Classification and Regression Trees(CART)and apply Isolation Forest(iForest)to classify unknown attacks hidden in known attacks.As an experiment result,the application of relabeling improved attack detection accuracy in anomaly detection by approximately 11%and enhanced the performance of unknown attack detection in misuse detection by approximately 10%.
