Method and apparatus for providing on-board diagnostics

• US 8,977,529 B2
• Filed: 09/16/2010
• Issued: 03/10/2015
• Est. Priority Date: 04/09/2010
• Status: Active Grant

• Current Assignee: BAE Systems Information and Electronic Systems Integration Incorporated (BAE Systems Plc)
• Original Assignee: BAE Systems Information and Electronic Systems Integration Incorporated (BAE Systems Plc)
• Inventors: Wagner, Ronald E.
• Primary Examiner(s): ALHIJA, SAIF A
• Application Number:
  US12/807,923
• Publication Number:
  US 20140052418A1
• Time in Patent Office: 1,636 Days
• Field of Search: 703/2, 703/8
• US Class Current: 703/8
• CPC Class Codes: G05B 2219/2637 Vehicle, car, auto, wheelchair
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks

Abstract

On-board diagnostics for fleet maintenance is improved by embedding a microprocessor programmed with a prognostication algorithm on a vehicle.

Claims

1. A system for providing a computationally less intense prognostication algorithm for a monitored lightweight vehicle to provide a fault determination comprising:

a monitored lightweight vehicle, with a gross weight less than 30,000 pounds and having microprocessors configured to perform on-board diagnostics, comprising nodes, wherein the monitored lightweight vehicle performing a function in which the implementation of the function takes place at a number of physically spaced apart points that correspond to the nodes;

a microprocessor being embedded in the monitored lightweight vehicle at a point of performance for providing a fault determination, wherein the point of performance comprises at least one node,

wherein said microprocessor being programmed with a stripped down version of a prognostication algorithm, wherein the stripped down version of the prognostication algorithm is developed by;

developing the prognostication algorithm by utilizing selected input sets of said at least one node that first determines a probability of one output as having a predicted value at one input of the selected input sets, wherein only said one input and said one output that describes operation of said monitored vehicle is used to determine the probability of said one output, and

developing said stripped down version of the prognostication algorithm by utilizing result of analysis of one input and one output, comprising;

developing the stripped down version of the prognostication algorithm by utilizing modeling and simulation based on the probability of said one output having said predicted value at said one input such that said stripped down version of the prognostication algorithm operates not directly on said one output but on the probability of said one output.

2. The system of claim 1, wherein multiple inputs are utilized with a single output for determining the probability of said output.

3. The system of claim 2, wherein when the probability of a node is above a predetermined threshold, the corresponding inputs and output are used in the modeling and simulation to develop said stripped down version of the prognostication algorithm.

4. The system of claim 1, wherein said one input and said one output determine the probability at a predetermined node in the monitored vehicle.