Arun T. Vemuri

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.

Learning methodology for failure detection and accommodation

A major goal of intelligent control systems is to achieve high performance with increased reliability, availability, and automation of maintenance procedures. In order to achieve fault tolerance in dynamical systems many algorithms have been developed during the past two decades. Fault diagnosis and accommodation methods have traditionally been based on linear modeling techniques, which restricts the type of practical failure situations that can be modeled. This article presents a learning methodology for failure detection and accommodation. The main idea behind this approach is to monitor the physical system for any off-nominal behavior in its dynamics using nonlinear modeling techniques. The principal design tool used is a generic function approximator with adjustable parameters, referred to as online approximator. Examples of such structures include traditional approximation models such as polynomials and splines as well as neural networks topologies such as sigmoidal multilayer networks and radial basis function networks. Stable learning methods are developed for monitoring the dynamical system. The nonlinear modeling nature and learning capability of the estimator allow the output of the online approximator to be used not only for detection but also for identification and accommodation of system failures. Simulation studies are used to illustrate the learning methodology and to gain intuition into the effect of modeling uncertainties on the performance of the fault diagnosis scheme. >

Neural network based fault detection in robotic manipulators

Fault detection, diagnosis, and accommodation play a key role in the operation of autonomous and intelligent robotic systems. System faults, which typically result in changes in critical system parameters or even system dynamics, may lead to degradation in performance and unsafe operating: conditions. This paper investigates the problem of fault diagnosis in rigid-link robotic manipulators. A learning architecture, with neural networks as online approximators of the off-nominal system behaviour, is used for monitoring the robotic system for faults. The approximation (by the neural network) of the off-nominal behaviour provides a model of the fault characteristics which can be used for detection and isolation of faults. The stability and performance properties of the proposed fault detection scheme in the presence of system failure are rigorously established, simulation examples are presented to illustrate the ability of the neural network based fault diagnosis methodology described in this paper to detect and accommodate faults in a simple two-link robotic system.

Sensor bias fault diagnosis in a class of nonlinear systems

This note describes a robust sensor bias fault diagnosis architecture for dynamic systems represented by a class of nonlinear discrete-time models. The nonlinearity in the system nominal model is assumed to be a function of inputs and outputs only. Specifically, this note uses adaptive techniques to estimate an unknown sensor bias in the presence of modeling uncertainties. A simulation example is presented to illustrate the methodology. The robustness, sensitivity and stability properties of the bias fault diagnosis architecture are rigorously analyzed.

Fault diagnosis of differential-algebraic systems

A large class of engineering systems are modeled by coupled differential and algebraic equations (DAE). Due to the singular nature of the algebraic equations, DAE systems do not satisfy the standard state-space description and require special techniques. So far, the literature has concentrated mostly on the numerical analysis and control of DAE systems. This paper investigates the problem of health monitoring and robust fault diagnosis of DAE systems. The main contributions are the design and analysis of a numerically feasible learning scheme for robust and stable fault diagnosis of DAE systems. The proposed fault diagnosis architecture monitors the physical system for any off-nominal behavior using nonlinear modeling techniques and learning algorithms. Online approximators, in the form of neural networks, are utilized in the detection of faults and in the derivation of models for the fault function, which can be used for fault isolation, fault identification, and fault accommodation. The stability and robustness properties of the fault diagnosis scheme are investigated. A simulation example illustrating the ability of the proposed fault diagnosis architecture to detect faults in a chemical reactive flash is presented.

A methodology for fault diagnosis in robotic systems using neural networks

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 off-nominal behavior due to faults. The robustness, sensitivity, missed detection 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.

On the use of on-line approximators for sensor fault diagnosis

This paper describes a sensor fault diagnosis algorithm for a class of nonlinear dynamic systems. The main idea behind this approach is to monitor the closed-loop system for any off-nominal system behavior due to sensor faults utilizing a nonlinear online approximator with adjustable parameters. A nonlinear estimation model and learning algorithm are described so that the online approximator provides an estimate of the sensor fault. The robustness, stability and learning performance properties of the nonlinear sensor fault diagnosis scheme are established.

On-line Approximation Methods for Robust Fault Detection

Abstract Fault diagnosis plays an important role in the operation of modern engineering plants. The design and analysis of fault diagnosis architectures using the model-based analytical redundancy approach has received considerable attention during the last two decades. One of the key issues in the design of such fault detection architectures is the effect of modeling uncertainties on their performance. In this paper, we propose a methodology to detect and diagnose faults in nonlinear dynamic systems with modeling uncertainties. The main idea behind this approach is to monitor the plant for any off-nominal system behavior due to faults utilizing a nonlinear on-line approximator with adjustable parameters. Learning algorithms based on Lyapunovs method are described and analyzed for robustness, sensitivity and stability.

Diagnosis of sensor bias faults

Describes a robust sensor fault diagnosis algorithm for a class of nonlinear dynamic systems. Specifically, the paper uses adaptive techniques to estimate the unknown constant sensor bias in the presence of system modeling uncertainties and sensor noise. The robustness, sensitivity and stability of the adaptive fault diagnosis architecture are rigorously established. A simulation example to illustrate the use of the proposed fault diagnosis architecture to diagnose bias in an automotive Universal Exhaust Gas Oxygen sensor is presented.

Short-term forecasting of traffic delays in highway construction zones using on-line approximators

Highway construction zones are often the cause of traffic delays. This is a natural consequence of the high congestion and nonuniform traffic flow conditions in construction zones. Most of the current algorithms for computing traffic delays are accurate for low density traffic conditions, and address the estimation of current travel time only. This paper presents a method for short-term forecasting of traffic delays in highway construction zones using data from presence detectors. The method is based on a modular approach wherein data from adjacent detectors is processed for estimating the travel time between the two detectors. The travel time estimates are then considered as time-series data, and the problem of short-term forecasting of traffic delay is formulated as a time-series evolution problem. A generic structure referred to as an on-line approximator is used for the prediction of travel time based on current and past travel time estimates. Simulation examples are used to illustrate the traffic delay forecasting algorithm.