Networked embedded systems are composed of a large number of distributed nodes that interact with the physical world via a set of sensors and actuators, have their own computational capabilities, and communicate with each other via a wired or wireless network. Diagnostic systems for such applications must address new challenges caused by the distribution of resources, the networking environment, and the tight coupling between the computational and the physical worlds. Our approach is to move from centralized, discrete or continuous techniques toward a distributed, hybrid diagnosis architecture. This paper demonstrates distributed, discrete diagnosis algorithms that leverage the topology of the physical plant to limit inter-diagnoser communication and compute diagnoses in an anytime and any information manner, making them robust to communication and processor failures. It also presents a particle filtering based estimation algorithm that addresses the challenge of the interaction between continuous and discrete dynamics in hybrid systems. The distributed qualitative diagnosis and hybrid estimation techniques are demonstrated using a rocket propulsion system.
We present a paradigmatic example of a feedbackcontrolled system: an electric motor with sensor and controller. Diagnosis of this system is performed based on a qualitative model that reflects deviations of parameters and behavior from a fixed reference state. The hypothesis that has been examined in this case study is that detection of behavior discrepancies does not necessarily require simulation of behavior, but can be done by checking (qualitative) states only. The qualitative models and the state-based diagnosis algorithm proved to establish a basis sufficient for fault detection and fault identification in the motor example. Some of the general preconditions for this are discussed.
Storing and Reusing Intermediate Results PRET reuses previously derived knowledge in two ways. First, knowledge about the physical system is global, whereas knowledge about a candidate model is local to that model. Therefore, PRET reuses knowledge that is independent of the current candidate model. Second, knowledge is reused within the process of reasoning about one particular model. Every time the reasoning proceeds to a less abstract level, PRET needs all information that has already been derived at the more abstract level. To avoid duplication of effort, PRET stores this information rather than rederiving it. The user declares a number of predicates as relevant (Beckstein & Tobermann 1992) which causes all succeeding subgoals with this predicate to be stored for later reuse.
We present a conflict-based approach to diagnosing Discrete Event Systems (DES) which generalises Reiter's Diagnose algorithm to a much broader class of problems. This approach obviates the need to explicitly reconstruct the system's behaviors that are consistent with the observation, as is typical of existing DES diagnosis algorithms. Instead, our algorithm explores the space of diagnosis hypotheses, testing hypotheses for consistency, and generating conflicts which rule out successors and other portions of the search space. Under relatively mild assumptions, our algorithm correctly computes the set of preferred diagnosis candidates. We investigate efficient symbolic representations of the hypotheses space and provide a SAT-based implementation of this framework which is used to address a real-world problem in processing alarms for a power transmission system.
The automotive industry was the first to promote the development of applications of model-based systems technology on a broad scale and, as a result, has produced some of the most advanced prototypes and products. In this article, we illustrate the features and benefits of model-based systems and qualitative modeling by prototypes and application systems that were developed in the automotive industry to support on-board diagnosis, design for diagnosability, and failure modes and effects analysis. Car manufacturers and their suppliers face increasingly serious challenges particularly related to fault analysis and diagnosis during the life cycle of their products. On the one hand, the complexity and sophistication of vehicles is growing, so it is becoming harder to predict interactions between vehicle systems, especially when failures occur. On the other hand, legal regulations and the demand for safety impose strong requirements on the detection and identification of faults and the prevention of their effects on the environment or dangerous situations for passengers and other people.