John W. Sheppard

A Formal Analysis of Fault Diagnosis with D-matrices

As new approaches and algorithms are developed for system diagnosis, it is important to reflect on existing approaches to determine their strengths and weaknesses. Of concern is identifying potential reasons for false pulls during maintenance. Within the aerospace community, one approach to system diagnosis—based on the D-matrix derived from test dependency modeling—is used widely, yet little has been done to perform any theoretical assessment of the merits of the approach. Past assessments have been limited, largely, to empirical analysis and case studies. In this paper, we provide a theoretical assessment of the representation power of the D-matrix and suggest algorithms and model types for which the D-matrix is appropriate. We also prove a surprising result relative to the difficulty of generating optimal diagnostic strategies from D-matrices. Finally, we relate the processing of the D-matrix with several diagnostic approaches and suggest how to extend the power of the D-matrix to take advantage of the power of those approaches.

A mathematical model for integrated diagnostics

The authors expand on the form of the information flow model they introduced previously, (see ibid., vol.8, no.3, p.16-30 (1991)). Compiling the model requires three algorithms for determining higher-order relationships. One of these, the algorithm for computing logical closure, helps to simplify the modeling task. The authors also introduce a hypothetical antitank missile launcher to illustrate concepts and computations presented previously.<<ETX>>

A Bayesian approach to diagnosis and prognosis using built-in test

Accounting for the effects of test uncertainty is a significant problem in test and diagnosis, especially within the context of built-in test. Of interest here, how does one assess the level of uncertainty and then utilize that assessment to improve diagnostics? One approach, based on measurement science, is to treat the probability of a false indication [e.g., built-in-test (BIT) false alarm or missed detection] as the measure of uncertainty. Given the ability to determine such probabilities, a Bayesian approach to diagnosis, and by extension, prognosis suggests itself. In the following, we present a mathematical derivation for false indication and apply it to the specification of Bayesian diagnosis. We draw from measurement science, reliability theory, signal detection theory, and Bayesian decision theory to provide an end-to-end probabilistic treatment of the fault diagnosis and prognosis problem.

Novel Classifier Fusion Approaches for Fault Diagnosis in Automotive Systems

Faulty automotive systems significantly degrade the performance and efficiency of vehicles, and oftentimes are the major contributors of vehicle breakdown; they result in large expenditures for repair and maintenance. Therefore, intelligent vehicle health-monitoring schemes are needed for effective fault diagnosis in automotive systems. Previously, we developed a data-driven approach using a data reduction technique, coupled with a variety of classifiers, for fault diagnosis in automotive systems. In this paper, we consider the problem of fusing classifier decisions to reduce diagnostic errors. Specifically, we develop three novel classifier fusion approaches: class-specific Bayesian fusion, joint optimization of fusion center and of individual classifiers, and dynamic fusion. We evaluate the efficacies of these fusion approaches on an automotive engine data. The results demonstrate that dynamic fusion and joint optimization, and class-specific Bayesian fusion outperform traditional fusion approaches. We also show that learning the parameters of individual classifiers as part of the fusion architecture can provide better classification performance.

System complexity and integrated diagnostics

An overview of a complete approach to integrated diagnostics is given. The approach is centered around an information-flow model and incorporates techniques from information fusion and artificial intelligence to guide analyses. The concept of integrated diagnosis is explained, and the model is examined. The authors show how to analyze testability, evaluate fault diagnosis, and create maintenance aids.<<ETX>>

IEEE standards for prognostics and health management

Recently operators of complex systems such as aircraft, power plants, and networks have been emphasizing the need for on-line health monitoring for purposes of maximizing operational availability and safety. The discipline of prognostics and health management (PHM) is being formalized to address the information management and prediction requirements for addressing these needs. Herein, we will explore how standards currently under development within the IEEE can be used to support PHM applications. Particular emphasis will be placed on the role of PHM and PHM-related standards with Department of Defense (DOD) automatic test systems-related research.

A Teaching Strategy for Memory-Based Control

Combining different machine learning algorithms in the same system can produce benefits above and beyond what either method could achieve alone. This paper demonstrates that genetic algorithms can be used in conjunction with lazy learning to solve examples of a difficult class of delayed reinforcement learning problems better than either method alone. This class, the class of differential games, includes numerous important control problems that arise in robotics, planning, game playing, and other areas, and solutions for differential games suggest solution strategies for the general class of planning and control problems. We conducted a series of experiments applying three learning approaches – lazy Q-learning, k-nearest neighbor (k-NN), and a genetic algorithm – to a particular differential game called a pursuit game. Our experiments demonstrate that k-NN had great difficulty solving the problem, while a lazy version of Q-learning performed moderately well and the genetic algorithm performed even better. These results motivated the next step in the experiments, where we hypothesized k-NN was having difficulty because it did not have good examples – a common source of difficulty for lazy learning. Therefore, we used the genetic algorithm as a bootstrapping method for k-NN to create a system to provide these examples. Our experiments demonstrate that the resulting joint system learned to solve the pursuit games with a high degree of accuracy – outperforming either method alone – and with relatively small memory requirements.

Improving the accuracy of diagnostics provided by fault dictionaries

Using nearest neighbor classification with fault dictionaries to resolve inexact signature matches in digital circuit diagnosis is inadequate. Nearest neighbor focuses on the possible diagnoses rather than on the tests. Our alternative-the information flow model-focuses on test information in the fault dictionary to provide more accurate diagnostics.

Fault isolation in an integrated diagnostic environment

The use of information flow models to conduct efficient fault isolation strategies is described. Of particular concern is optimizing diagnosis to minimize some objective cost function. A technique that can include multiple cost criteria such as test time, skill level, and failure frequency, as well as information value, is discussed.<<ETX>>

Overlapping particle swarms for energy-efficient routing in sensor networks

Sensor networks are traditionally built using battery-powered, collaborative devices. These sensor nodes do not rely on dedicated infrastructure services (e.g., routers) to relay data. Rather, a communal effort is employed where the sensor nodes both generate data as well as forward data for other nodes. A routing protocol is needed in order for the sensors to determine viable paths through the network, but routing protocols designed for wired networks and even ad hoc networks are not sufficient given the energy overhead needed to operate them. We propose an energy-aware routing protocol, based on overlapping swarms of particles, that offers reliable path selection while reducing the energy consumption for the route selection process. Our particle-based routing with overlapping swarms for energy-efficiency algorithm shows promise in extending the life of battery-powered networks while still providing robust routing functionality to maintain network reliability.