Neural-network-based robust fault diagnosis in robotic systems

Fault diagnosis plays an important role in the operation of modern robotic systems. A number of researchers have proposed fault diagnosis architectures for robotic manipulators using the model-based analytical redundancy approach. One of the key issues in the design of such fault diagnosis schemes is the effect of modeling uncertainties on their performance. This paper investigates the problem of fault diagnosis in rigid-link robotic manipulators with modeling uncertainties. A learning architecture with sigmoidal neural networks is used to monitor the robotic system for any off-nominal behavior due to faults. The robustness and stability properties of the fault diagnosis scheme are rigorously established. Simulation examples are presented to illustrate the ability of the neural-network-based robust fault diagnosis scheme to detect and accommodate faults in a two-link robotic manipulator.     

Tolerating Permanent State Transition Faults in Asynchronous Sequential Machines

Corrective control theory lays a novel foundation for the fault-tolerant control of asynchronous sequential machines. In this paper, we present a corrective control scheme for tolerating permanent state transition faults in the dynamics of asynchronous sequential machines. By a fault occurrence, the asynchronous machine may be stuck at a faulty state, not responding to the external input. We analyze the detectability of the considered faults and present the necessary and sufficient condition for the existence of a controller that overcomes any permanent transition faults. Fault tolerance is realized by using potential reachability and asynchronous mechanisms in the machine. A case study on an asynchronous counter is provided to illustrate the proposed fault detection and tolerance scheme.     

基于故障配置的故障树生成

故障树分析是提高系统安全性和可靠性的有效方法。传统的人工故障树生成方式难以解决当前系统的庞大规模与复杂性的问题,且容易出错。为此,提出基于故障配置的故障树生成方法,引入软件产品线的可变性管理,用于系统故障建模与形式化分析。首先,定义故障特征图模型用于刻画系统故障间的约束关系,基于Kripke结构定义故障标记迁移系统来描述系统的行为;然后,基于模型的语义建立通过模型检测生成故障树的过程;最后,通过时序逻辑描述系统安全属性,利用模型检测工具SNIP验证安全属性进而生成故障树。案例研究验证了该方法的有效性。     

Scan BIST with biased scan test signals

The conventional test-per-scan built-in self-test （BIST） scheme needs a number of shift cycles followed by one capture cycle. Fault effects received by the scan flipflops are shifted out while shifting in the next test vector like scan testing. Unlike deterministic testing, it is unnecessary to apply a complete test vector to the scan chains. A new scan-based BIST scheme is proposed by properly controlling the test signals of the scan chains. Different biased random values are assigned to the test signals of scan flip-flops in separate scan chains. Capture cycles can be inserted at any clock cycle if necessary. A new testability estimation procedure according to the proposed testing scheme is presented. A greedy procedure is proposed to select a weight for each scan chain. Experimental results show that the proposed method can improve test effectiveness of scan-based BIST greatly, and most circuits can obtain complete fault coverage or very close to complete fault coverage.     

Decentralized fault tolerant control of a class of nonlinear interconnected systems

In this paper, a novel decentralized fault tolerant controller (DFTC) is proposed for interconnected nonlinear continuous-time systems by using local subsystem state vector alone in contrast with traditional distributed fault tolerant controllers or fault accommodation schemes where the measured or the estimated state vector of the overall system is needed. The proposed decentralized controller uses local state and input vectors and minimizes the fault effects on all the subsystems. The DFTC in each subsystem includes a traditional controller term and a neural network based online approximator term which is used to deal with the unknown parts of the system dynamics, such as fault and interconnection terms. The stability of the overall system with the proposed DFTC is investigated by using Lyapunov approach and the boundedness of all signals is guaranteed in the presence of a fault. Therefore, the proposed controller enables the system to continue its normal operation after the occurrence of a fault, as long as it does not cause failure or break down of a component. Although the decentralized fault tolerant controller is designed mainly for large-scale systems where continuous transmissions between subsystems is not possible, it can also be applied to small-scale systems where sensor measurements are available for use in all subsystems. Finally the proposed methods are verified and compared in simulation environment.     

Nonlinear aircraft sensor fault reconstruction in the presence of disturbances validated by real flight data

This paper proposes an approach for Inertial Measurement Unit sensor fault reconstruction by exploiting a ground speed-based kinematic model of the aircraft flying in a rotating earth reference system. Two strategies for the validation of sensor fault reconstruction are presented: closed-loop validation and open-loop validation. Both strategies use the same kinematic model and a newly-developed Adaptive Two-Stage Extended Kalman Filter to estimate the states and faults of the aircraft. Simulation results demonstrate the effectiveness of the proposed approach compared to an approach using an airspeed-based kinematic model. Furthermore, the major contribution is that the proposed approach is validated using real flight test data including the presence of external disturbances such as turbulence. Three flight scenarios are selected to test the performance of the proposed approach. It is shown that the proposed approach is robust to model uncertainties, unmodeled dynamics and disturbances such as time-varying wind and turbulence. Therefore, the proposed approach can be incorporated into aircraft Fault Detection and Isolation systems to enhance the performance of the aircraft.     

Immunotronics - novel finite-state-machine architectures withbuilt-in self-test using self-nonself differentiation

A novel approach to hardware fault tolerance is demonstrated that takes inspiration from the human immune system as a method of fault detection. The human immune system is a remarkable system of interacting cells and organs that protect the body from invasion and maintains reliable operation even in the presence of invading bacteria or viruses. This paper seeks to address the field of electronic hardware fault tolerance from an immunological perspective with the aim of showing how novel methods based upon the operation of the immune system can both complement and create new approaches to the development of fault detection mechanisms for reliable hardware systems. In particular, it is shown that by use of partial matching, as prevalent in biological systems, high fault coverage can be achieved with the added advantage of reducing memory requirements. The development of a generic finite-state-machine immunization procedure is discussed that allows any system that can be represented in such a manner to be "immunized" against the occurrence of faulty operation. This is demonstrated by the creation of an immunized decade counter that can detect the presence of faults in real time     

UIO design for singular delayed LPV systems with application to actuator fault detection and isolation

In this paper, the unknown input observer (UIO) design for singular delayed linear parameter varying (LPV) systems is considered regarding its application to actuator fault detection and isolation. The design procedure assumes that the LPV system is represented in the polytopic framework. Existence and convergence conditions for the UIO are established. The design procedure is formulated by means of linear matrix inequalities (LMIs). Actuator fault detection and isolation is based on using the UIO approach for designing a residual generator that is completely decoupled from unknown inputs and exclusively sensitive to faults. Fault isolation is addressed considering two different strategies: dedicated and generalised bank of observers’ schemes. The applicability of these two schemes for the fault isolation is discussed. An open flow canal system is considered as a case study to illustrate the performance and usefulness of the proposed fault detection and isolation method in different fault scenarios.     

全相关核偏最小二乘故障诊断方法及在抽油机上应用

针对油田抽油机生产数据存在强非线性和强耦合性, 导致故障诊断困难的问题, 本文提出一种全相关动态 核偏最小二乘(FCDKPLS)故障诊断方法. 首先, 构建抽油机生产数据自回归模型, 反映数据变量间的动态特性; 其 次, 分析了KPLS算法中输出变量与输入变量残差子空间的相关性, 为此, 在输出模型上构建一个辅助矩阵, 从而表 征输入变量与输出变量的全相关性, 建立输入变量和输出变量之间更直接的联系. 最后, 将提出的全相关动态偏最 小二乘方法应用于抽油机过程故障诊断, 实验结果表明本文提出方法的有效性.     

Generating single-stuck-fault coverage from a collapsed-fault set

Fault simulators do not simulate all the single stuck faults (SSFs), because as the simulated fault set grows, the increase in their runtime and memory requirements is greater than linear. Fault-set size is reduced, or collapsed, during circuit preprocessing by using the concepts of equivalence and dominance. It is shown that collapsed-fault (CF) coverage is not the same as SSF coverage and that this difference has a large effect on the defect level as the coverage approaches 100%. A very-low-overhead technique is presented that calculates true fault coverage while simulating with a CF set, thereby retaining the runtime and memory savings of simulating with CFs without sacrificing fault-coverage accuracy. This technique can be applied to any fault model exhibiting equivalence and dominance properties. The results are confirmed by benchmark results     

Fuzzy functions with support vector machines

A new fuzzy system modeling (FSM) approach that identifies the fuzzy functions using support vector machines (SVM) is proposed. This new approach is structurally different from the fuzzy rule base approaches and fuzzy regression methods. It is a new alternate version of the earlier FSM with fuzzy functions approaches. SVM is applied to determine the support vectors for each fuzzy cluster obtained by fuzzy c-means (FCM) clustering algorithm. Original input variables, the membership values obtained from the FCM together with their transformations form a new augmented set of input variables. The performance of the proposed system modeling approach is compared to previous fuzzy functions approaches, standard SVM, LSE methods using an artificial sparse dataset and a real-life non-sparse dataset. The results indicate that the proposed fuzzy functions with support vector machines approach is a feasible and stable method for regression problems and results in higher performances than the classical statistical methods.     

Sensor fault diagnosis of singular delayed LPV systems with inexact parameters: an uncertain system approach

In this paper, sensor fault diagnosis of a singular delayed linear parameter varying (LPV) system is considered. In the considered system, the model matrices are dependent on some parameters which are real-time measurable. The case of inexact parameter measurements is considered which is close to real situations. Fault diagnosis in this system is achieved via fault estimation. For this purpose, an augmented system is created by including sensor faults as additional system states. Then, an unknown input observer (UIO) is designed which estimates both the system states and the faults in the presence of measurement noise, disturbances and uncertainty induced by inexact measured parameters. Error dynamics and the original system constitute an uncertain system due to inconsistencies between real and measured values of the parameters. Then, the robust estimation of the system states and the faults are achieved with H_∞ performance and formulated with a set of linear matrix inequalities (LMIs). The designed UIO is also applicable for fault diagnosis of singular delayed LPV systems with unmeasurable scheduling variables. The efficiency of the proposed approach is illustrated with an example.     

基于支持向量机的径向基网络结构优化

为了解决径向基网络（RBF NN）结构设计的随机性,进一步优化RBF网络性能,提出一种基于支持向量机（SVM）的径向基网络结构优化方法。通过训练得到的SVM确定径向基网络的隐层节点个数、隐层权值和阈值;同时利用SVM对输入向量进行特征变换,进一步对输入向量进行维数约简。通过齿轮箱的故障诊断实验表明,优化后的RBF网络具有更精简、稳定的网络结构,能得到更准确的诊断结果。     

Active fault tolerant control using state-space self-tuning control approach

This paper presents a new fault tolerant control scheme for unknown multivariable stochastic systems by modifying the conventional state-space self-tuning control approach. For the detection of faults, a quantitative criterion is developed by comparing the innovation process errors occurring in the Kalman filter estimation algorithm, which, for faulty system recovery, a weighting matrix resetting technique is developed by adjusting and resetting the covariance matrices of the parameter estimate obtained in the Kalman filter estimation algorithm to improve the parameter estimation of the faulty systems. The proposed method can effectively cope with partially abrupt and/or gradual system faults and/or input failures with fault detection. The modified state-space self-tuning control scheme can be applied to the multivariable stochastic faulty system without requiring prior knowledge of system parameters and noise properties.