Artificial intelligence based health management of host system

Patent metadata

Field	Value
Publication number	US-2016350194-A1
Application number	US-201615074549-A
Country	US
Kind code	A1
Filing date	Mar 18, 2016
Priority date	May 27, 2015
Publication date	Dec 1, 2016
Grant date	—

Abstract

This disclosure relates generally to health management, and more particularly to a method and system for artificial intelligence based diagnostic and prognostic health management of host systems. In an embodiment, the system includes a memory to store instructions, and a neural network controller coupled to the memory. The neural network controller is configured by the instructions to monitor a plurality of unique patterns generated in real-time. The plurality of system parameters is indicative of a system-level performance of the host system. The neural network controller is configured by the instructions to compare the plurality of unique patterns with a plurality of predetermined patterns corresponding to the plurality of system parameters to detect potential anomalies in the host system and one or more subsystems of the plurality of subsystems, where the one or more subsystems are responsible for contributing to the potential anomalies in the host system.

First claim

What is claimed is:

1 . A health management system for diagnosis and prognosis of a host system, the host system having a plurality of subsystems, the health management system comprising:
a memory to store instructions and a plurality of predetermined patterns; and a neural network controller coupled to the memory, wherein the neural network controller is configured by the instructions to:
monitor a plurality of unique patterns generated in real-time, the plurality of unique patterns comprising responses associated with a set of system parameters of the host system, the set of system parameters indicative of the system-level performance of the host system in real-time;
compare the plurality of unique patterns with the plurality of predetermined patterns corresponding to the set of system parameters; and
detect one or more potential anomalies in the host system and at least one faulty subsystem of the plurality of subsystems based on the comparison, the at least one faulty subsystem is responsible for contributing to the one or more potential anomalies in the host system.

2 . The health management system of claim 1 , wherein the plurality of predetermined patterns are indicative of system-level performance of the host system, under a normal working condition of the plurality of subsystems and a plurality of abnormal working conditions of one or more subsystems of the plurality of subsystems.

3 . The health management system of claim 2 , wherein the neural network controller is further configured by the instructions to preconfigure the plurality of predetermined pat-terns, and wherein to preconfigure the plurality of predetermined patterns, the neural net-work controller is configured by the instructions to:
acquire training data comprising the system-level performance of the host system under the normal working condition of the plurality of subsystems and under the plurality of abnormal working conditions of the one or more subsystems of the plurality of subsystems; and extract a plurality of feature vectors from the training data, the plurality of feature vectors exhibiting the plurality of predetermined patterns indicative of the one or more potential anomalies in the host system.

4 . The health management system of claim 3 , wherein the neural network controller is further configured by the instructions to train a neural network model based on the plurality of feature vectors to classify the one or more potential anomalies with the at least one faulty subsystem responsible for contributing to the one or more potential anomalies.

5 . The health management system of claim 3 , wherein to acquire the training data, the neural network controller is further configured by the instructions to:
simulate the normal working condition and the plurality of abnormal working conditions of the plurality of subsystems; and generate the system-level performance under the normal and the plurality of abnormal working conditions.

6 . The health management system of claim 5 , wherein to simulate the normal and the plurality of abnormal working conditions, the neural network controller is further con-figured by the instructions to:
capture the system-level performance from a reference model and a fault introduced model continuously in a specified window of time scale, wherein the reference model comprises modeling of the normal working condition and the fault introduced model comprises modeling of the plurality of abnormal working conditions of the plurality of subsystems; and preprocess the system-level responses to remove trends in training data.

7 . The health management system of claim 1 , wherein the host system comprises one of an aircraft system, an automotive system, a turbine system and an engine system.

8 . A processor-implemented method for health management of a host system by a health management system, the host system having a plurality of subsystems, the method comprising:
provisioning the health management system comprising:
a memory to store instructions and a plurality of predetermined patterns, and
a neural network controller coupled to the memory;
monitoring, by the neural network controller, a plurality of unique patterns generated in real-time, the plurality of unique patterns comprising responses associated with a set of system parameters of the host system, the set of system parameters indicative of the system-level performance of the host system in real-time; comparing, by the neural network controller, the plurality of unique patterns with the plurality of predetermined patterns corresponding to the set of system parameters; and detecting, by the neural network controller, one or more potential anomalies in the host system and at least one faulty subsystem of the plurality of subsystems based on the comparison, the at least one faulty subsystem responsible for contributing to the one or more potential anomalies in the host system.

9 . The method of claim 8 , wherein the plurality of predetermined patterns are indicative of system-level performance of the host system, under a normal working condition of the plurality of subsystems and a plurality of abnormal working conditions of one or more subsystems of the plurality of subsystem.

10 . The method of claim 9 , further comprising preconfiguring the plurality of predetermined patterns, and wherein preconfiguring the plurality of predetermined patterns comprises:
acquiring training data comprising the system-level performance of the host system under the normal working condition of the plurality of subsystems and under the plurality of abnormal working conditions of the one or more subsystems of the plurality of subsystems; and extracting a plurality of feature vectors from the training data, the plurality of feature vectors exhibiting the plurality of predetermined patterns indicative of the one or more potential anomalies in the host system.

11 . The method of claim 10 , further comprising training a neural network model based on the plurality of feature vectors to classify the one or more potential anomalies with the at least one faulty subsystem responsible for contributing to the one or more potential anomalies.

12 . The method of claim 10 , wherein acquiring the training data comprises:
simulating the normal working condition and the plurality of abnormal working conditions of the plurality of subsystems; and generating the system-level performance under the normal and the plurality of abnormal working conditions.

13 . The method of claim 12 , wherein simulating the normal working condition of the plurality of sub-systems and the plurality of abnormal working conditions of the one or more subsystems comprises:
capturing the system-level performance from a reference model and a fault introduced model continuously in a specified window of time scale, wherein the reference model comprises modeling of the normal working condition and the fault introduced model comprises modeling of the plurality of abnormal working conditions of the plurality of subsystems; and preprocessing the system-level responses to remove trends in training data.

14 . The method of claim 8 , wherein the host system comprises one of an aircraft system, an automotive system, a turbine system and an engine system.

15 . A non-transitory computer-readable medium having embodied thereon a computer program for executing a method for health management of a host system by a health management system, the host system having a plurality of subsystems, and the health management system comprising a memory to store instructions and a plurality of predete

Assignees

• Tata Consultancy Services Ltd

Inventors

• Mohan Sreeram
• Rao Pallanti Srinivasa
• Chindam Venkateshwar

Classifications

• G06N3/088

  Non-supervised learning, e.g. competitive learning · CPC title

• G06N99/005

  Physics · mapped topic

• G06F11/2257 Primary

  using expert systems · CPC title

• G05B23/0254 Primary

  based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title

• G06N20/00

  Machine learning · CPC title