Automated diagnostic system

• US 4,967,337 A
• Filed: 10/11/1988
• Issued: 10/30/1990
• Est. Priority Date: 10/11/1988
• Status: Expired due to Term

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: English, Roe E., Crone, Jerry A., Kilgore, Michael A.
• Primary Examiner(s): Smith, Jerry
• Assistant Examiner(s): GORDON, PAUL P
• Application Number:
  US07/256,020
• Time in Patent Office: 749 Days
• Field of Search: 364/184, 364/5, 364/188, 364/130, 364/550, 364/474.16, 364/570, 364/513, 371/15, 371/16.5, 371/20, 371/25, 371/29.1, 371/14, 371/17, 324/512
• US Class Current: 700/79
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 2219/33303 Expert system for diagnostic, monitoring use of tree and probability
• CPC Class Codes: G05B 23/0248 Causal models, e.g. fault tree; digraphs; qualitative physics
• CPC Class Codes: G06F 11/2257 using expert systems
• CPC Class Codes: Y10S 706/912 Manufacturing or machine, e.g. agricultural machinery, machine tool

Abstract

Artificial intelligence diagnostic expert system software is used to interrogate and monitor etcher machine state by directly accessing vital hardware/process sensors. Sensor values and `recipe` variables are analyzed to determine cause of failures and recommend repair strategies, realtime monitoring and analysis of these values allows the expert system to predict failures prior to occurrence and show cause of impending failure.

Claims

1. An automated diagnostic system, comprising:

a machine for performing process steps on a workpiece, wherein a plurality of process variables assume different states;

an interface coupled to said machine for sensing the state of said plurality of process variables, and for controlling said plurality of process variables;

a master controller coupled to said interface for setting values for the plurality of process variables to be controlled, and for reading the state of the plurality of process variables to be sensed, wherein said master controller generates an error signal and suspends operation of said machine when a sensed process variable moves out of a preselected range; and

a diagnostics controller coupled to said master controller for, when operation of said machine has been suspended by said master controller, sensing the state of process variables to be sensed, for querying an operator regarding other states of said machine, and for applying the sensed states and results of operator inquiries to an expert system having a set of rules and a set of facts capable of identifying possible causes for the error signal, to determine the cause of the error.

2. The automated diagnostic system of claim 1, wherein the expert system utilized by said diagnostics controller performs a search of a decision tree.

3. A method for diagnosing the cause of an error condition in a machine, responsive to an error signal generated by means including a sensor for detecting the status of a process variable, comprising the steps of:

(a) halting operation of the machine;

(b) querying an operator to determine a current status for said process variable;

(c) sensing states of process variables within the machine without operator intervention;

(d) applying the results of steps (b) and (c) to an expert system having a set of rules and a set of facts capable of identifying possible causes for the error signal, to determine the cause of the error; and

(e) repeating steps (b), (c), and (d) until the cause of the error is diagnosed.

4. The method of claim 3, wherein the expert system utilized in step (d) performs a search of a decision tree.

5. A system for diagnosing an error condition in a machine, responsive to an error signal generated by means including a sensor for detecting the state of a process variable, comprising:

a diagnostics controller coupled to the machine, wherein said diagnostics controller can determine the state of said process variable within the machine;

an interactive input/output device, coupled to said diagnostics controller, for communication with an operator, wherein enquiries are displayed to the operator and answers are received from the operator; and

a knowledge base coupled to said diagnostics controller, said knowledge base containing information regarding the cause and effect of said error condition within the machine;

wherein said diagnostics controller, when said error condition occurs within the machine, queries the operator through the input/output device, senses the state of said process variable within the machine independently of the operator, and applies the information so received and sensed to the knowledge base to determine the probable cause of said error condition.

6. The system of claim 5, wherein said knowledge base comprises a set of rules and facts.

7. The system of claim 5, wherein said knowledge base comprises a decision tree of error condition causes and effects.

8. The system of claim 5, wherein said diagnostics controller comprises an expert software system operating on a general purpose computer.

9. The system of claim 8, wherein said expert software system operates on a general purpose computer also used to control operation of the machine during normal operation.

10. The system of claim 5, further comprising a long term storage device coupled to said diagnostics controller for storing sequences of steps taken by said diagnostics controller during diagnosis of an error condition.