US 7,536,277 B2 · Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance

Abstract

Systems and methods are provided for monitoring, diagnosis and condition-based maintenance of mechanical systems. The disclosed systems and methods employ intelligent model-based diagnostic methodologies to effectuate such monitoring, diagnosis and maintenance. According to exemplary embodiments of the present disclosure, the intelligent model-based diagnostic methodologies combine or integrate quantitative (analytical) models and graph-based dependency models to enhance diagnostic performance. The disclosed systems and methods may be employed a wide variety of applications, including automotive, aircraft, power systems, manufacturing systems, chemical processes and systems, transportation systems, and industrial machines/equipment.

Claims21

Dependent claims

A diagnostic method for a system, comprising:

(a) generating a hybrid quantitative and graphical dependency model that captures at least one fault-to-error characteristic for the system,
(b) establishing at least one fault condition associated with the system;
(c) running at least one test design on the hybrid quantitative and graphical dependency model for the system;
(d) evaluating performance of the at least one test design with respect to the at least one fault condition using the hybrid quantitative and graphical dependency model to refine the hybrid quantitative and graphical dependency model for the system;
(e) establishing one or more performance limits for the system based on the performance evaluation;
and
(f) effecting at least one remedial action based on the one or more performance limits, said at least one remedial action directly impacting upon operation of the system.

4 more elements

A diagnostic system for providing diagnostics with respect to a system, comprising:

(a) a plurality of subsystem-resident local agents in communication with said system, each of the subsystem-resident local agents being adapted to (i) make diagnostic determinations with respect to said system based, at least in part, on a design matrix, and (ii) implement at least one remedial action that directly impacts upon operation of the system based on said diagnostic determinations;
(b) a system-level agent in communication with said plurality of subsystem-resident local agents, said system-level agent being adapted to combine diagnostic determinations by said plurality of subsystem-resident local agents;
wherein said design matrix is established by:
(i) generating a hybrid quantitative and graphical dependency model that captures at least one fault-to-error characteristic for the system,
(ii) establishing at least one fault condition associated with the system,
(iii) running at least one test design on the hybrid quantitative and graphical dependency model,
(iv) evaluating performance of the at least one test design with respect to the at least one fault condition using the hybrid quantitative and graphical dependency model to refine the hybrid quantitative and graphical dependency model, and
(v) establishing the design matrix based on the refined hybrid quantitative and graphical dependency model.

5 more elements

Dependencies are inferred from the claim text.

Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance

Life of this patent

Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance

Life of this patent

Abstract

Claims21