Actuator fault diagnosis for a class of nonlinear systems and its application to a laboratory 3D crane

In this paper, an actuator fault diagnosis scheme is proposed for a class of affine nonlinear systems with both known and unknown inputs. The scheme is based on a novel input/output relation derived from the considered nonlinear systems and the use of the recently developed high-order sliding-mode robust differentiators. The main advantages of the proposed approach are that it does not require a design of nonlinear observer and applies to systems not necessarily detectable. Conditions are provided to characterize the feasibility of fault detection and isolation using the proposed scheme and the maximum number of isolatable actuator faults. The efficacy of the proposed actuator fault diagnosis approach is tested through experiments on a laboratory 3D Crane, and the experimental results show that the proposed actuator fault diagnosis approach is promising and can achieve fault detection and isolation satisfactorily.     

一种基于小波神经网络故障检测方法的仿真研究

文中提出了一种基于小波神经网络一性观测器的故障检测方法。它是一种把信号分析和模型相结合的故障检测方法,通过小波对信号的去噪和神经的神经网络的自学习功能,来获取系统输入输出的非线性动力学特性,进而实时计算出残差并进行逻辑判疡,可提高故障检测的速度和准确率。对同步交流电机的结构损伤故障进行了仿真,结果表明了该方法是可行的。     

一类基于神经网络非线性观测器的鲁棒故障检测和诊断

利用神经网络的非线性建模能力,对一类具有建模不确定项的非线性系统提出一种基于观测器的故障检测和诊断的方法。设计的观测器不仅能实现故障检测,而旦应用神经网络设计的故障估计器能在线估计系统中的故障向量。通过分析验证了该方法对系统中的建模误差和外部扰动具有良好的鲁棒性。仿真结果表明所提出的方法是有效的。     

基于深度强化学习的恶意软件混淆对抗样本生成

设计一种PE格式恶意软件混淆对抗样本生成模型。利用深度强化学习算法,实现对恶意软件的自动混淆。通过加入历史帧和LSTM神经网络结构的方法使深度强化学习模型具有记忆性。对比实验表明,该恶意软件变种在基于机器学习的检测模型上的逃逸率高于现有研究,在由918个PE格式恶意软件组成的测试集上达到39.54%的逃逸率。     

Supervisory fault tolerant control for a class of uncertain nonlinear systems

This paper focuses on the design of a unique scheme that simultaneously performs fault isolation and fault tolerant control for a class of uncertain nonlinear systems with faults ranging over a finite cover. The proposed framework relies on a supervisory switching among a family of pre-computed candidate controllers without any additional model or filter. The states are ensured to be bounded during the switching delay, which ends when the correct stabilizing controller has been selected. Simulation results about a flexible joint robotic example illustrate the efficiency of the proposed method.     

基于局部梯度平滑的解释鲁棒性对抗训练方法

深度学习可解释性在发展的同时,也面临着安全性方面的巨大挑战。模型对输入数据的解释结果存在被恶意操纵攻击的风险,此攻击严重限制了可解释性技术的应用场景并阻碍了人类对模型的探索与认知。针对此问题,提出一种使用模型梯度作为相似性约束的解释鲁棒性对抗训练方法。首先,沿解释方向采样生成对抗训练数据;其次,结合训练过程中样本的梯度信息来计算采样数据解释之间的多种相似性指标,用以对模型正则化,平滑模型的曲率;最后,为验证所提出的解释鲁棒性对抗训练方法的有效性,在多个数据集和解释方法上进行验证,实验结果表明,所提方法在防御对抗解释样本上具有显著效果。     

基于对抗网络与卷积神经网络的目标检测方法

在目标检测方法中,通过使用具有不同遮挡程度的数据集进行训练,能够提升目标检测算法对遮挡的不变性,但现实生活中的数据集往往存在长尾效应。因此提出一种基于对抗网络与卷积神经网络的目标检测方法。通过对抗网络在输入数据上进行计算得到不同遮挡程度的样本,使用Faster RCNN算法进行训练提升遮挡不变性,以此提高算法检测精度。实验结果表明,该方法与Faster RCNN相比,在VOC 2007数据集上平均精度提升了2.2个百分点,在VOC 2007和VOC 2012联合数据集上平均精度提升了1.3个百分点。     

Fault diagnosis of a class of nonlinear uncertain systems with Lipschitz nonlinearities using adaptive estimation

This paper presents a fault detection and isolation (FDI) scheme for a class of Lipschitz nonlinear systems with nonlinear and unstructured modeling uncertainty. This significantly extends previous results by considering a more general class of system nonlinearities which are modeled as functions of the system input and partially measurable state variables. A new FDI method is developed using adaptive estimation techniques. The FDI architecture consists of a fault detection estimator and a bank of fault isolation estimators. The fault detectability and isolability conditions, characterizing the class of faults that are detectable and isolable by the proposed scheme, are rigorously established. The fault isolability condition is derived via the so-called fault mismatch functions, which are defined to characterize the mutual difference between pairs of possible faults. A simulation example of a single-link flexible joint robot is used to illustrate the effectiveness of the proposed scheme.     

Integrating independent component analysis and local outlier factor for plant-wide process monitoring

We propose a novel process monitoring method integrating independent component analysis (ICA) and local outlier factor (LOF). LOF is a recently developed outlier detection technique which is a density-based outlierness calculation method. In the proposed monitoring scheme, ICA transformation is performed and the control limit of LOF value is obtained based on the normal operating condition (NOC) dataset. Then, at the monitoring phase, the LOF value of current observation is computed at each monitoring time, which determines whether the current process is a fault or not. The comparison experiments are conducted with existing ICA-based monitoring schemes on widely used benchmark processes, a simple multivariate process and the Tennessee Eastman process. The proposed scheme shows the improved accuracy over existing schemes. By adopting LOF, the monitoring statistic is computed regardless of data distribution. Therefore, the proposed scheme integrating ICA and LOF is more suitable for real industry where the monitoring variables are the mixture of Gaussian and non-Gaussian variables, whereas existing ICA-based schemes assume only non-Gaussian distribution.     

High-gain observation with disturbance attenuation and application to robust fault detection

One approach to the problem of residual generation in a purpose of fault detection is to use an observer. One particular difficulty is to distinguish between faults and disturbances. Various observers have already been inspected in that direction, generally based on exact decoupling w.r.t. unknown disturbances. Here the use of high-gain observer techniques is inspected, with a purpose of attenuation of disturbances rather than exact decoupling: conditions allowing some “robust partial estimation” are first presented, and their possible use in fault detection is then discussed.     

基于特征差分选择的集成模型流量对抗样本防御架构

当前,基于深度学习的异常流量检测模型容易遭受流量对抗样本攻击。作为防御对抗攻击的有效方法,对抗训练虽然提升了模型鲁棒性,但也导致了模型检测精度下降。因此,如何有效平衡模型检测性能和鲁棒性是当前学术界研究的热点问题。针对该问题,基于集成学习思想构建多模型对抗防御框架,通过结合主动性特征差分选择和被动性对抗训练,来提升模型的对抗鲁棒性和检测性能。该框架由特征差分选择模块、检测体集成模块和投票裁决模块组成,用于解决单检测模型无法平衡检测性能与鲁棒性、防御滞后的问题。在模型训练方面,设计了基于特征差分选择的训练数据构造方法,通过有差异性地选择和组合流量特征,形成差异化流量样本数据,用于训练多个异构检测模型,以抵御单模型对抗攻击;在模型裁决方面,对多模型检测结果进行裁决输出,基于改进的启发式种群算法优化集成模型裁决策略,在提升检测精度的同时,增大了对抗样本生成的难度。实验效果显示,所提方法的性能相比单个模型对抗训练有较大提升,相较于现有的集成防御方法,其准确率和鲁棒性提升了近10%。