Distributed Diagnosis of Dynamic Systems Using Dynamic Bayesian Networks? (original) (raw)
Related papers
Distributed diagnosis in uncertain environments using Dynamic Bayesian Networks
2010
Abstract Model-based diagnosis for industrial applications have to be efficient, and deal with modeling approximations and measurement noise. This paper presents a distributed diagnosis scheme, based on Dynamic Bayesian Networks (DBNs) that generates globally correct diagnosis results through local analysis, by only communicating a minimal number of measurements among diagnosers.
Ecient Estimation for Diagnosis Using Factored Dynamic Bayesian Networks?
2000
Robust and ecient estimation of hidden state variables of a system in the presence of measurement noise and modeling errors is crucial for online model based fault diagnosis of continuous systems. Dynamic Bayesian Networks (DBNs) provide generalized and systematic methods for reasoning under uncertainty. This paper presents an approach to improve estimation eciency by partitioning the DBN into smaller factors
Efficient Estimation for Diagnosis Using Factored Dynamic Bayesian Networks
7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, 2009
Robust and efficient estimation of hidden state variables of a system in the presence of measurement noise and modeling errors is crucial for online model based fault diagnosis of continuous systems. Dynamic Bayesian Networks (DBNs) provide generalized and systematic methods for reasoning under uncertainty. This paper presents an approach to improve estimation efficiency by partitioning the DBN into smaller factors and invoking estimation algorithms on each factor independently. The factors are generated by replacing some state variables with algebraic functions of some measurement variables, thus reducing the across-time links between these state variables. Hence, given the measurements, these state variables become conditionally independent of the state variables in other factors, and the states of each factor can be estimated separately. This paper derives an algorithm for generating these factors and presents experimental results to demonstrate the effectiveness of our factoring approach for accurate estimation of system behavior.
Bayesian fault detection and diagnosis in dynamic systems
2000
Abstract This paper addresses the problem of tracking and diagnosing complex systems with mixtures of discrete and continuous variables. This problem is a difficult one, particularly when the system dynamics are nondeterministic, not all aspects of the system are directly observed, and the sensors are subject to noise. In this paper, we propose a new approach to this task, based on the framework of hybrid dynamic Bayesian networks (DBN).
Dynamic Bayesian Network Factors from Possible Conflicts for Continuous System Diagnosis
Lecture Notes in Computer Science, 2011
This paper introduces a factoring method for Dynamic Bayesian Networks (DBNs) based on Possible Conflicts (PCs), which aim to reduce the computational burden of Particle Filter inference. Assuming single fault hypothesis and known fault modes, the method allows performing consistency based fault detection, isolation and identification of continuous dynamic systems, with the unifying formalism of DBNs. The three tank system benchmark has been used to illustrate the approach. Two fault scenarios are discussed and a comparison of the behaviors of a DBN of the complete system with the DBN factors is also included. Comparison has confirmed that DBN computation is more efficient for factors than for the complete DBN.
This paper presents some approaches on the new applications in fault estimation, detection and diagnosis emerged from three powerful concepts: theory of distributed parameter systems, applied to large and complex physical processes, artificial intelligence, with its tool adaptive-network-based fuzzy inference and the intelligent wireless ad-hoc sensor networks. Sensor networks have large and successful applications in the real world. They may be placed in the areas of distributed parameter systems, to be seen as a "distributed measuring sensor" for the physical variables. Using sensor networks multivariable estimation techniques may be applied in distributed parameter systems. Fault detection and diagnosis in distributed parameter systems become more easily and more performing using these concepts. The paper presents some applications in fault detection and diagnosis based on the adaptive-network-based fuzzy inference, allows treatment of large and complex systems with many variables by learning and extrapolation.
Distributed diagnosis in dynamic fault environments
IEEE Transactions on Parallel and Distributed Systems, 2004
The problem of distributed diagnosis in the presence of dynamic failures and repairs is considered. To address this problem, the notion of bounded correctness is defined. Bounded correctness is made up of three properties: bounded diagnostic latency, which ensures that information about state changes of nodes in the system reaches working nodes with a bounded delay, bounded start-up time, which guarantees that working nodes determine valid states for every other node in the system within bounded time after their recovery, and accuracy, which ensures that no spurious events are recorded by working nodes. It is shown that, in order to achieve bounded correctness, the rate at which nodes fail and are repaired must be limited. This requirement is quantified by defining a minimum state holding time in the system. Algorithm HeartbeatComplete is presented and it is proven that this algorithm achieves bounded correctness in fully-connected systems while simultaneously minimizing diagnostic latency, start-up time, and state holding time. A diagnosis algorithm for arbitrary topologies, known as Algorithm ForwardHeartbeat, is also presented. ForwardHeartbeat is shown to produce significantly shorter latency and state holding time than prior algorithms, which focused primarily on minimizing the number of tests at the expense of latency.
2006
Abstract: This papers aims to design a new approach in order to increase the performance of the decision making in model-based fault diagnosis when signature vectors of various faults are identical or closed. The proposed approach consists on taking into account the knowledge issued from the reliability analysis and the model-based fault diagnosis. The decision making, fonnalised as a bayesian network, is established with a priori knowledge on the dynamic component degradation through Markov chains.
Designing distributed diagnosers for complex physical systems
2005
Abstract Online diagnosis methods require large computationally expensive diagnosis tasks to be decomposed into sets of smaller tasks so that time and space complexity constraints are not violated. This paper defines the distributed diagnosis problem in the Transcend qualitative diagnosis framework, and then develops heuristic algorithms for generating a set of local diagnosers that solve the global diagnosis problem without a coordinator. Two versions of the algorithm are discussed.
A Bayesian approach to efficient diagnosis of incipient faults
2006
Abstract Safe, reliable, and efficient operation of complex dynamical systems requires the ability to detect, isolate, and identify degradation in system components. Degradations are typically modeled as incipient faults, which are slow drifts in system parameters over time. This paper presents an efficient approach for the detection, isolation, and identification of incipient faults under uncertainty using a Dynamic Bayesian Network (DBN) approach. Initially a DBN is used as an observer to track nominal system behavior.