Prediction of machine failure based on vibration trend information

Patent metadata

Field	Value
Publication number	US-11573153-B2
Application number	US-201916546385-A
Country	US
Kind code	B2
Filing date	Aug 21, 2019
Priority date	Aug 21, 2019
Publication date	Feb 7, 2023
Grant date	Feb 7, 2023

Abstract

A method for detecting defects in a rotational element of a machine based on changes in measured vibration energy includes: (a) collecting vibration data over an extended period of time using vibration sensors attached to the machine; (b) processing the vibration data to generate a time waveform comprising processed vibration values sampled during sequential sampling time intervals within the extended period of time; (c) detecting multiple time blocks within the extended period of time during which the processed vibration values exhibit sustained increases at progressively increasing rates; and (d) generating alerts based on detection of the multiple time blocks during which the processed vibration values exhibit sustained increases at progressively increasing rates. The multiple time blocks may include a first time block during which the processed vibration values increase at a first rate, and a second time block occurring after the first time block during which the processed vibration values increase at a second rate that is greater than the first rate.

First claim

What is claimed is:

1. A method for detecting defects in a rotational element of a machine based on changes in measured vibration energy over an extended period of time, comprising:
(a) collecting vibration data over the extended period of time using one or more vibration sensors attached to the machine;
(b) processing the vibration data to generate a time waveform comprising scalar vibration values that characterize the vibration data sampled during sequential sampling time intervals within the extended period of time;
(c) determining a first rate of increase of the scalar vibration values during a first time block within the extended period of time;
(d) determining a second rate of increase of the scalar vibration values during a second time block within the extended period of time, wherein the second time block occurs after the first time block;
(e) based on a comparison of the second rate of increase to the first rate of increase, determining that the second rate of increase is greater than the first rate of increase; and
(f) based on determining that the second rate of increase is greater than the first rate of increase, generating one or more alerts.

2. The method of claim 1 wherein the first rate of increase is indicative of a first stage of deterioration of the rotational element due to a defect therein, and the second rate of increase is indicative of a second stage of deterioration of the rotational element that is more severe than the first stage.

3. The method of claim 1 wherein the scalar vibration values comprise PeakVue values.

4. The method of claim 1 wherein the first and second rates of increase in the scalar vibration values are determined based on a curve fit calculated over a moving time window or a fixed interval time window, or based on an overall range calculated over a moving time window or fixed interval time window.

5. The method of claim 4 wherein the curve fit comprises a linear regression or an exponential curve fit.

6. An apparatus for detecting defects in a rotational element of a machine based on changes in measured vibration energy over an extended period of time, comprising:
one or more vibration sensors attached to the machine for collecting vibration data over the extended period of time;
a processor that receives the vibration data and executes instructions to process the vibration data to:
generate a time waveform comprising scalar vibration values that characterize the vibration data sampled during sequential sampling time intervals within the extended period of time;
determine a first rate of increase of the scalar vibration values during a first time block within the extended period of time;
determine a second rate of increase of the scalar vibration values during a second time block within the extended period of time, wherein the second time block occurs after the first time block;
based on a comparison of the second rate of increase to the first rate of increase, determine that the second rate of increase is greater than the first rate of increase; and
based on determining that the second rate of increase is greater than the first rate of increase, generate one or more alerts.

7. The apparatus of claim 6 in which the processor is a component of a portable vibration analyzer, a wired or wireless vibration transmitter, a continuous online vibration monitoring system, or a vibration analysis computer.

8. The apparatus of claim 7 wherein the first rate of increase in the scalar vibration values is indicative of a first stage of deterioration of the rotational element due to a defect therein, and the second rate of increase in the scalar vibration values is indicative of a second stage of deterioration of the rotational element that is more severe than the first stage.

9. The apparatus of claim 6 wherein the scalar vibration values comprise PeakVue values.

10. The apparatus of claim 6 wherein the processor determines rates of increase in the scalar vibration values based on a curve fit calculated over a moving time window.

11. The method of claim 10 wherein the curve fit comprises a linear regression or an exponential curve fit.

Assignees

• Computational Systems Inc

Inventors

• Turner John S
• Skeirik Robert D

Classifications

• G01M13/045 Primary

  Acoustic or vibration analysis · CPC title

• G07C3/06

  in graphical form · CPC title

• G05D19/02

  characterised by the use of electric means · CPC title

• G01M13/00

  Testing of machine parts · CPC title

• G01H1/003

  of rotating machines (G01H1/10 takes precedence) · CPC title