Fang Tu

Computationally efficient algorithms for multiple fault diagnosis in large graph-based systems

Graph-based systems are models wherein the nodes represent the components and the edges represent the fault propagation between the components. For critical systems, some components are equipped with smart sensors for on-board system health management. When an abnormal situation occurs, alarms will be triggered from these sensors. This paper considers the problem of identifying the set of potential failure sources from the set of ringing alarms in graph-based systems. However, the computational complexity of solving the optimal multiple fault diagnosis (MFD) problem is exponential. Based on Lagrangian relaxation and subgradient optimization, we present a heuristic algorithm to find approximately the most likely candidate fault set. A computationally cheaper heuristic algorithm - primal heuristic - has also been applied to the problem so that real-time MFD in systems with several thousand failure sources becomes feasible in a fraction of a second. This paper also considers systems with asymmetric and multivalued alarms (tests).

Rollout strategies for sequential fault diagnosis

Test sequencing is a binary identification problem wherein one needs to develop a minimal expected cost testing procedure to determine which one of a finite number of possible failure sources, if any, is present. The problem can be solved optimally using dynamic programming or AND/OR graph search methods (AO/sup */, CF, and HS). However, for large systems, the associated computation with dynamic programming or AND/OR graph search methods is substantial, due to the rapidly increasing number of OR nodes (denoting ambiguity states) and AND nodes (denoting tests) in the search graph. In order to overcome the computational explosion, the one-step or multistep lookahead heuristic algorithms have been developed to solve the test sequencing problem. In this paper, we propose to apply rollout strategies, which can be combined with the one-step or multistep lookahead heuristic algorithms, in a computationally more efficient manner than the optimal strategies, to obtain solutions superior to those using the one-step or multistep lookahead heuristic algorithms. The rollout strategies are illustrated and tested using a range of real-world systems. We show computational results, which suggest that the information-heuristic based rollout policies are significantly better than other rollout policies based on Huffman coding and entropy.

A dependency model-based approach for identifying and evaluating power quality problems

The purpose of this paper is to present a diagnostic system that will not only monitor sensor data streams, but also classify power conditions, and diagnose power quality problems both in real-time and off-line. Signal processing techniques are applied to extract features from monitored data for event detection and classification. A cause-effect relationship model is used to trace the power quality related events to particular equipment of a system under consideration. The methodology has been implemented in a software tool. Results obtained from the application of this tool on monitored data collected from a facility validate the utility of this approach.

Integration of a Holonic Organizational Control Architecture and Multiobjective Evolutionary Algorithm for Flexible Distributed Scheduling

Based on the concept of autonomous cooperating holons, this paper presents a holonic command and control ( C 2) organizational control architecture (OCA) that models a C 2 organization as an integration of holonic multilevel decentralized decision-making networks. The OCA consists of two levels: operational- and tactical-level controls. Authority and control are highly distributed among agents belonging to different levels of the holarchy to empower the edges, whereas the integration of decisions is ensured to achieve overall mission objectives. In order to complete a mission in real time in dynamic environments, the decision makers (DMs) at different control levels need to coordinate their actions extensively and be prepared to adapt their schedules. Based on the proposed OCA, we present a holonic multiobjective evolutionary algorithm that produces flexible distributed schedules that account for the unexpected changes in the mission environment, such as asset breakdown, appearance of new events, DM failure, etc. This approach generates multilevel Pareto optimal solutions and, as a consequence, produces a set of ranked neighboring schedules. The actual schedule is a combination of different phases from alternative neighboring schedules that adapt to environmental disturbances. Moreover, the cost of adaptability is reduced while maintaining the stability of the organization. Numerical experiment shows the advantages of the proposed OCA, viz., simplicity, efficiency, and flexibility, which enable an organization to achieve high performance under dynamic and uncertain environments.

A novel congruent organizational design methodology using group technology and a nested genetic algorithm

A key concept in congruent organizational design is the so-called strategic grouping, which involves the aggregation of task functions, positions, and assets into units. Group technology (GT) has emerged as a manufacturing philosophy for improving productivity in batch production systems, while retaining the flexibility of a job shop production. In this paper, a methodology [nested genetic algorithm (NGA)] to group tasks and assets into several clusters [decision makers (DMs), command cells] is proposed; this methodology employs concepts from GT and genetic algorithms (GAs) to minimize the weighted total workload, measured in terms of intra-DM and inter-DM coordination workloads. The numerical results show that the proposed NGA approach obtains a near-optimal layout of the organization, i.e., the assignment of platforms to tasks and the patterns of coordination achieve a nice tradeoff between inter-DM and intra-DM coordination workload.

On a multimode test sequencing problem

Test sequencing is a binary identification problem wherein one needs to develop a minimal expected cost test procedure to determine which one of a finite number of possible failure states, if any, is present. In this paper, we consider a multimode test sequencing (MMTS) problem, in which tests are distributed among multiple modes and additional transition costs will be incurred if a test sequence involves mode changes. The multimode test sequencing problem can be solved optimally via dynamic programming or AND/OR graph search methods. However, for large systems, the associated computation with dynamic programming or AND/OR graph search methods is substantial due to the rapidly increasing number of OR nodes (denoting ambiguity states and current modes) and AND nodes (denoting next modes and tests) in the search graph. In order to overcome the computational explosion, we propose to apply three heuristic algorithms based on information gain: information gain heuristic (IG), mode capability evaluation (MC), and mode capability evaluation with limited exploration of depth and degree of mode Isolation (MCLEI). We also propose to apply rollout strategies, which are guaranteed to improve the performance of heuristics, as long as the heuristics are sequentially improving. We show computational results, which suggest that the information-heuristic based rollout policies are significantly better than traditional information gain heuristic. We also show that among the three information heuristics proposed, MCLEI achieves the best tradeoff between optimality and computational complexity.

A Probabilistic computational model for identifying organizational structures from uncertain message data

The knowledge of the principles and goals under which an adversary organization operates is required to predict its future activities. To implement successful counter-actions, additional knowledge of the specifics of the organizational structures, such as command, communication, control, and information access networks, as well as responsibility distribution among members of the organization, is required. In this paper, we employ a hidden Markov random field (HMRF) model and a graph matching algorithm to discover the attributes of and relationships among organizational members, assets, environment areas, and mission tasks. We focus on identifying the mapping between hypothesized nodes of enemy command organization and tracked individuals and resources. This also allows us to compute the posterior energy function quantifying the belief that the observed data has been generated by a particular organization. The experiment results show that our probabilistic model and the simulated annealing search algorithm can accurately identify the different organizational structures and achieve correct node mappings among organizational members.

A Lagrangian Relaxation Algorithm for Finding the MAP Configuration in QMR-DT

The quick medical reference decision-theoretic (QMR-DT) network is a large two-layer Bayesian network (BN) [consisting of 571 diseases (ldquofailure sourcesrdquo) and 4075 findings (ldquotest outcomesrdquo)] based on expert and statistical knowledge in internal medicine. The maximum a posteriori (MAP) diagnosis (configuration) based on QMR-DT constitutes an intractable inference problem for all, but a small set of, cases. Consequently, we consider near-optimal algorithms for finding the most likely set of diseases given a set of findings. A computationally efficient algorithm that can handle cases with hundreds of positive findings, i.e., the Lagrangian relaxation algorithm (LRA), is presented. By relaxing the original problem via a set of Lagrange multipliers, the LRA generates an upper bound for the objective function. The near-optimal diagnosis (configuration) is found by minimizing the duality gap via a subgradient method. Numerical experiments show that the LRA is promising in achieving highly accurate diagnosis, and that it is computationally very efficient in solving MAP configuration problems in large and dense two-layer BNs with noisy-OR (BN2O) nodes and containing undirected loops (cycles), such as the QMR-DT network.

Multiple disease (fault) diagnosis with applications to the QMR-DT problem

In this paper, we present three classes of computationally efficient algorithms that can handle cases with hundreds of positive findings in QMR-DT(Quick Medical Reference, Decision-Theoretic) Network. These include Lagrangian Relaxation Algorithm (LRA), Primal Heuristic Algorithm (PHA), and Approximate Belief Revision Algorithm (ABR). These algorithms solve the QMR-DT problem by finding the most likely set of diseases given the findings. Extensive computational experiments have shown that LRA obtains the best solutions among the three algorithms proposed within a relatively small processing time. We also show that the Variational Probabilistic Inference method is a special case of our LRA. The solutions are generic and have application to multiple fault diagnosis in complex industrial systems.

Multiple fault diagnosis in graph-based systems

Graph-based systems are models wherein the nodes represent the components and the edges represent the fault propagation between the components. For critical systems, some components are equipped with smart sensors for on-board system health management. When an abnormal situation occurs, alarms will be triggered from these sensors. This paper considers the problem of identifying the set of potential failure sources from the set of ringing alarms in graph-based systems. However, the computational complexity of solving the optimal multiple fault diagnosis problem is super-exponential. Based on Lagrangian relaxation and subgradient optimization, we present a heuristic algorithm to find the most likely candidate fault set. A computationally cheaper heuristic algorithm - primal heuristic - has also been applied to the problem so that real-time multiple fault diagnosis in systems with several thousand failure sources becomes feasible in a fraction of a second.