Methods for using digitized sound patterns to monitor operation of automated machinery

• US 9,945,755 B2
• Filed: 09/30/2015
• Issued: 04/17/2018
• Est. Priority Date: 09/30/2014
• Status: Active Grant

• Current Assignee: Barry-Wehmiller Papersystems, Inc.
• Original Assignee: Marquip, LLC (Barry-Wehmiller Group Incorporated)
• Inventors: Pluemer, Blake
• Primary Examiner(s): Menz, Laura
• Application Number:
  US14/870,256
• Publication Number:
  US 20160091398A1
• Time in Patent Office: 930 Days
• CPC Class Codes: G01M 7/00 Vibration-testing of structures; Shock-testing of structures G01M9/00 takes precedence
• CPC Class Codes: G05B 19/4065 Monitoring tool breakage, life or condition
• CPC Class Codes: G05B 2219/37337 Noise, acoustic emission, sound
• CPC Class Codes: G05B 2219/37433 Detected by acoustic emission, microphone
• CPC Class Codes: G05B 2219/37434 Measuring vibration of machine or workpiece or tool

Abstract

In an operating machine, one example of a method for monitoring operation of operating machinery includes converting an actual sound pattern generated by the machine into an audio signal and digitizing the audio signal to create a real-time acoustic fingerprint unique to the actual sound pattern. A reference database contains a plurality of stored acoustic fingerprints, each stored acoustic fingerprint in the plurality of stored acoustic fingerprints representing a unique sound pattern associated with a particular operating condition. A controller compares the real-time acoustic fingerprint to the stored acoustic fingerprints in the reference database and generates an output in response to detection of a match between the real-time acoustic fingerprint and one of the plurality of stored acoustic fingerprints. One example of the machine is a corruptor machine that converts paper webs into corrugated paperboard sheets.

Claims

1. In a corrugator that converts paper webs into corrugated paperboard sheets, a method for monitoring operation of corrugator machinery, the method comprising:

with a sensor, converting an actual sound pattern generated by an operating corrugator machine into an audio signal;

receiving the audio signal with a controller, and with the controller, digitizing the audio signal to create a real-time acoustic fingerprint unique to the actual sound pattern;

with the controller, accessing a reference database in a storage system, the reference database containing a plurality of stored acoustic fingerprints, each stored acoustic fingerprint in the plurality of stored acoustic fingerprints representing a unique sound pattern associated with a particular operating condition of the corrugator machine;

comparing the real-time acoustic fingerprint to the plurality of stored acoustic fingerprints in the reference database with the controller; and

in response to detecting a match between the real-time acoustic fingerprint and one of the plurality of stored acoustic fingerprints with the controller, generating an output command with the controller, which output command is associated with the particular operating condition in the storage system;

receiving and carrying out the output command at a component of the corrugator machine.

2. The method of claim 1, further comprising populating the reference database with the plurality of stored acoustic fingerprints by converting sound patterns generated by particular operating conditions of the corrugator machine into audio signals, digitizing the audio signals and storing their acoustic fingerprints, and associating each stored acoustic fingerprint with its respective particular operating condition.

3. The method of claim 2, further comprising intentionally creating the particular operating conditions and recording the resulting sound patterns.

4. The method of claim 2, further comprising associating each stored acoustic fingerprint with a respective output command in the reference database.

5. The method of claim 4, wherein the output command comprises a command to shut down the corrugator machine, and the method further comprises shutting down the corrugator machine.

6. The method of claim 4, wherein the output command comprises a command to generate an alert that identifies the particular operating condition associated with the one of the plurality of stored acoustic fingerprints to a corrugator operator, and the method further comprises displaying the alert at a user interface of the corrugator machine.

7. The method of claim 4, wherein the particular operating condition comprises a particular machine malfunction, and the output command comprises a command to take automatic corrective action to rectify the particular machine malfunction associated with the one of the plurality of stored acoustic fingerprints, and the method further comprises taking the corrective action.

8. The method of claim 7, further comprising determining if a sound pattern preceding the match between the real-time acoustic fingerprint and the one of the plurality of stored acoustic fingerprints indicates an impending machine malfunction, and if so, storing an acoustic fingerprint of the preceding sound pattern in the reference database and associating it with a pre-malfunction condition of the corrugator machine.

9. The method of claim 8, wherein the particular operating condition comprises the pre-malfunction condition, and the output command comprises a command to generate an alert that identifies the pre-malfunction condition to a corrugator operator.

10. The method of claim 1, further comprising installing sensors on the corrugator machine to collect sound.

11. The method of claim 10, further comprising installing the sensors proximate at least one of the following corrugator machine components:

an infeed nip of a singlefacer;

a head of a splicer;

an infeed nip of a doublefacer;

a gear train of a knife; and

a trim chute of a slitter/scorer.

12. The method of claim 10, wherein the output command comprises a command to turn on one of the sensors at a particular location where that sensor had previously been off.

13. The method of claim 1, further comprising continuously converting the actual sound pattern generated by the operating corrugator machine into the audio signal.

14. The method of claim 13, further comprising automatically digitizing the audio signal to create the real-time acoustic fingerprint at regular time intervals.

15. In a corrugator that converts paper webs into corrugated paperboard sheets, a method for monitoring operation of corrugator machinery, the method comprising:

(a) with a sensor, converting an actual sound pattern generated by a machine into an audio signal;

(b) receiving the audio signal with a controller, and with the controller, digitizing the audio signal to create a real-time acoustic fingerprint unique to the actual sound pattern;

(c) with the controller, accessing a reference database in a storage system of the controller, the reference database containing a plurality of stored acoustic fingerprints, each stored acoustic fingerprint in the plurality of stored acoustic fingerprints representing a unique sound pattern associated with a particular operating condition of the machine;

(d) comparing the real-time acoustic fingerprint to the plurality of stored acoustic fingerprints in the reference database with the controller;

(e) in response to detecting a match between the real-time acoustic fingerprint and one of the plurality of stored acoustic fingerprints generating a corrective output command with the controller, which corrective output command is associated with the particular operating condition in the storage system;

(f) receiving and carrying out the corrective output command at a component of the machine; and

(g) thereafter repeating steps (a) through (f) until the real-time acoustic fingerprint matches a stored acoustic fingerprint representing a unique sound pattern associated with a correct operating condition of the machine.

16. The method of claim 15, further comprising populating the reference database with the plurality of stored acoustic fingerprints by intentionally creating particular operating conditions, converting sound patterns generated by the machine during the particular operating conditions into audio signals, digitizing the audio signals and storing their acoustic fingerprints, and associating each stored acoustic fingerprint with its respective particular operating condition.

17. The method of claim 16, further comprising associating each stored acoustic fingerprint with a respective corrective output command in the reference database.

18. The method of claim 17, wherein the particular operating condition comprises a particular machine malfunction, and wherein the corrective output command comprises

a command to take automatic corrective action to rectify the particular machine malfunction associated with the one of the plurality of stored acoustic fingerprints;

and

wherein the method further comprises taking the corrective action.

19. The method of claim 15, further comprising continuously converting the actual sound pattern generated by the machine into the audio signal and automatically digitizing the audio signal to create the real-time acoustic fingerprint at regular time intervals.

20. The method of claim 15, wherein the machine is a corrugator that converts paper webs into corrugated paperboard sheets, and the method further comprises installing sensors proximate at least one of the following corrugator machine components:

an infeed nip of a singlefacer;

a head of a splicer;

an infeed nip of a doublefacer;

a gear train of a knife; and

a trim chute of a slitter/scorer.