Browse Prior Art Database

Method and system for guided repair of a vehicle

IP.com Disclosure Number: IPCOM000238434D
Publication Date: 2014-Aug-26
Document File: 8 page(s) / 47K

Publishing Venue

The IP.com Prior Art Database

Abstract

Figure 1 illustrates a computer system 1 for troubleshooting a vehicle 100. The computer system 1 comprises a user interface (UE) configured for registering observations from a mechanic; a communication interface 2 configured to receiving input from a electronic control system 200 of the vehicle 100; a diagnoser 10 connected to a database with a diagnostic model (DM); and a planner 20 configured to create an action plan, which action plan is used to recommend actions to the mechanic. The planner 20 is configured to create an action plan consisting of a series of recommended actions (RA1, RA2, …, RAs), by means of the probability distributions (Pi) from the diagnoser 10 and an action model (AM) from a database with action models, in which an action model (AM) includes the cost of an action ($i), the effect of an action (Ei), and the constraints (Bi) necessary for performing each action (Ai) are modelled. The planner 20 creates a sequential sub-plan for solving the necessary constraints (Bi) of each action (Ai). The planner 20 is configured to create the action plan by selecting the sequence of recommended actions (RA1, RA2, …, RAs) on the bases of an estimated lowest expected cost for correcting the faults. The planner 20 is configured to use an A* algorithm for providing the sub-plans for solving the necessary constraints (Bi) of each action (Ai).

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 28% of the total text.

Page 01 of 8

Method and system for guided repair of a vehicle

ABSTRACT

Figure 1 illustrates a computer system 1 for troubleshooting a vehicle 100. The computer system 1 comprises a user interface

plan is used to recommend actions to the mechanic.

The planner 20 is configured to create an action plan consisting of a series of recommended actions (RA1, RA2, …, RAs), by means of the probability distributions (Pi) from the diagnoser 10

necessary constraints (Bi) of each action (Ai). The planner 20 is configured to create the action plan by selecting the sequence of recommended actions (RA1, RA2, …, RAs) on the bases of an estimated lowest expected cost for correcting the faults. The planner 20 is configured to use an A* algorithm for providing the

5
(UE) configured for registering observations from a mechanic; a communication interface 2 configured to receiving input from a electronic control system 200 of the vehicle 100; a diagnoser 10 connected to a database with a diagnostic model (DM); and a planner 20 configured to create an action plan, which action

10

15

and an action model (AM) from a database with action models, in which an action model (AM) includes the cost of an action ($i), the effect of an action (Ei), and the constraints (Bi) necessary for performing each action (Ai) are modelled. The planner 20 creates a sequential sub-plan for solving the

20

25

sub-plans for solving the necessary constraints (Bi) of each action (Ai).


Page 02 of 8

2

Method and system for guided repair of a vehicle

BACKGROUND OF THE INVENTION AND PRIOR ART
The invention relates to troubleshooting vehicles, in particular

land motor vehicles such as trucks, buses and cars.

Document D1: "Warnquist, Håkan. "Computer-Assisted Troubleshooting for Efficient Off-board Diagnosis". (Licentiate dissertation). Linköping:

Linköping University Electronic Press, (2011)" describes computer based troubleshooting of parts of a truck. In more detail, D1 describes computer-assisted troubleshooting of complex products such as
heavy trucks. The troubleshooting task is to find and repair all faulty components in a malfunctioning system. The troubleshooting is done by

performing actions to gather more information regarding which
faults there can be or to repair components that are suspected to be faulty. The expected cost of the performed actions should be as low as possible.

D1 describes a troubleshooting method providing a good trade-off between computation time and solution quality. D1 descibes a computer system having a framework for troubleshooting, wherein an investigated system, such as a hydraulic braking system of a truck, is diagnosed using non-stationary dynamic Bayesian networks and the decisions of

search heuristics for solving the troubleshooting problem by searching. The methods presented in D1 are evaluated in a case study of an auxiliary hydraulic braking system of a modern truck.

5

10

15

20

25

which actions to perform are made using a planning algorithm for Stochast...