Somnath Deb

A generalized S-D assignment algorithm for multisensor-multitarget state estimation

We develop a new algorithm to associate measurements from multiple sensors to identify the real targets in a surveillance region, and to estimate their states at any given time. The central problem in a multisensor-multitarget state estimation problem is that of data association-the problem of determining from which target, if any, a particular measurement originated. The data association problem is formulated as a generalized S-dimensional (S-D) assignment problem, which is NP-hard for S/spl ges/3 sensor scans (i.e., measurement lists). We present an efficient and recursive generalized S-D assignment algorithm (S/spl ges/3) employing a successive Lagrangian relaxation technique, with application to the localization of an unknown number of emitters using multiple high frequency direction finder sensors (S=3, 5, and 7).

A new relaxation algorithm and passive sensor data association

The static problem of associating measurements at a given time from three angle-only sensors in the presence of clutter, missed detections, and an unknown number of targets is addressed. The measurement-target association problem is formulated as one of maximizing the joint likelihood function of the measurement partition. Mathematically, this formulation leads to a generalization of the 3-D assignment (matching) problem, which is known to be NP hard. The solution to the optimization problem developed is a Lagrangian relaxation technique that successively solves a series of generalized two-dimensional (2-D) assignment problems. The algorithm is illustrated by several application examples. >

Multi-signal flow graphs: a novel approach for system testability analysis and fault diagnosis

In this paper, we present a comprehensive methodology for a formal, but intuitive, cause-effect dependency modeling using multi-signal directed graphs that correspond closely to hierarchical system schematics and develop diagnostic strategies to isolate faults in the shortest possible time without making the unrealistic single fault assumption. A key feature of our methodology is that our models lend naturally to real-world necessities, such as system integration and hierarchical troubleshooting. >

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).

A multisensor-multitarget data association algorithm for heterogeneous sensors

The problem of associating data from three spatially distributed heterogeneous sensors with three simultaneous detections for all three is discussed. The sensors can be active or passive. The source of a detection can be either a real target, in which case the measurement is the true observation variable of the target plus measurement noise, or a spurious one, i.e. a false alarm. The sensors may have nonunity detection probabilities. The problem is to associate the measurements from sensors to identify the real targets, and to obtain their position estimates. Mathematically this leads to a generalized 3D assignment problem, which is known to be NP-hard. An algorithm suited for estimating the positions of a large number of targets in a dense cluster, using a fast, but nearly optimal, 3D assignment algorithm, is presented. Performance results for several representative test cases with 64 targets are presented. >

QSI's integrated diagnostics toolset

The QSI integrated tool set, consisting of TEAMS, TEAMS-RT, TEAMATE and HARVESTER, offers a comprehensive solution to integrated diagnosis of systems with many components (modules, boards, replaceable units, etc.) that are subject to failure. The software tool set automates the DFT, FMECA, on-line monitoring, off-line diagnosis, and maintenance data management tasks. Integration is achieved via a common model-based approach wherein a consistent model is used across different tools at various stages of a systems life-cycle. In this paper, we present an overview of the Integrated Toolset, with examples of its real-world applications in model-based TPS development, real-time process monitoring, and PIMA.

Design of process parameters using robust design techniques and multiple criteria optimization

This paper presents a methodology for the design of products/processes that makes use of the concepts of robust design and the techniques of multiple criteria optimization for simultaneously optimizing many quality characteristics. First, a systematic approach to the selection of an efficient matrix experiment for a design problem is presented. Appropriate performance measures are obtained so that their joint optimization results in the minimum variation of product characteristics. The use of transformations is highlighted as a useful technique to statistically validate the design process. A discrete multiple criteria optimization algorithm that incorporates the methods of dominated approximations and reference points is developed to obtain nondominated solutions for the design problem. The methodology is illustrated using a case study gleaned from the literature. >

Decentralized real-time monitoring and diagnosis

Real time monitoring of complex systems requires a smart and efficient inference engine. TEAMS-RT is capable of monitoring up to 1000 tests in real-time. Even so, for larger systems, a centralized solution will be computationally infeasible. Here, we present a lattice architecture of multiple collaborative TEAMS-RTs that can be embedded in the different subsystems of an interconnected system. A signal processing toolkit has been developed to facilitate data acquisition, filtering, feature extraction and test decisions.

START: System Testability Analysis and Research Tool

START, a software package for automatic test sequencing and testability analysis of complex, hierarchically described modular systems, is described, and its use in modeling systems is examined. START uses algorithms based on information theory, heuristic search, and graph theory to solve various faces of the test sequencing and testability analysis problems. A system is modeled in the failure space as a hierarchical directed graph with nodes denoting modules and testpoints and with AND nodes denoting redundancy. Interconnections among the nodes denote their immediate functional dependencies. START supports hierarchical testing in accordance with the maintenance strategy; a failure source may be isolated to a component or a module at any level. Other practical features include options to integrate diagnosis with repair (after partial diagnosis) in order to optimize test time, test cost, or test and repair cost. An interactive menu-mouse graphical interface serves as a high-level front end to these algorithms and enables the user to graphically enter and modify hierarchical functional models of systems. START presents the gist of the outputs of the testability analysis algorithms as a concise testability report consisting of important figures of merit.<<ETX>>

Multisignal modeling for diagnosis, FMECA, and reliability

Multisignal modeling methodology is a simple and efficient knowledge representation scheme that captures the basic attributes of a system (structure, specifications, etc.) that are obtainable from design data and product specifications. QSIs TEAMS toolset employs multisignal modeling for testability analysis, test program set development, onboard monitoring and ground support systems. We outline the modeling methodology, its use in related areas of reliability analysis and failure modes, effects and criticality analysis (FMECA), and our efforts in building a reusable test and model library.