Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox
This paper studies the relevance of CWT (continuous wavelet transform) processing of vibration signals for improving the performance of CNN-based models that detect certain types of helical gearbox faults. Gear tooth damages, such as incipient and localized pitting and localized wear on helical pini...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/950 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589226349166592 |
|---|---|
| author | Iulian Lupea Mihaiela Lupea |
| author_facet | Iulian Lupea Mihaiela Lupea |
| author_sort | Iulian Lupea |
| collection | DOAJ |
| description | This paper studies the relevance of CWT (continuous wavelet transform) processing of vibration signals for improving the performance of CNN-based models that detect certain types of helical gearbox faults. Gear tooth damages, such as incipient and localized pitting and localized wear on helical pinion tooth flanks, combined with improper lubrication, are the faults under observation. Vibrations at the housing level for three rotating velocities of the AC motor and three load levels (for each velocity) are acquired with a triaxial accelerometer. Through CWT, the vibration signal is decomposed into 2D time-frequency grayscale images, with a filter bank of ten voices per octave in the frequency band of interest. Three 2D-CNN-based models trained on the CWT-based representation of the vibration signals measured on individual accelerometer axes (<i>X</i>, <i>Y</i>, and <i>Z</i>) are proposed to detect the four health states (one normal and three faulty) of the helical gearbox, regardless of the selected load level or speed on the test rig. These models achieve an accuracy higher than 99%. By fusing the CWT-based representations of the signals on individual axes for use as input to a 2D-CNN, the best-performing model for the proposed defect detection task is generated, reaching an accuracy of 99.91%. |
| format | Article |
| id | doaj-art-eb669ab65637464da7e02b8b19aac776 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-eb669ab65637464da7e02b8b19aac7762025-01-24T13:21:27ZengMDPI AGApplied Sciences2076-34172025-01-0115295010.3390/app15020950Continuous Wavelet Transform and CNN for Fault Detection in a Helical GearboxIulian Lupea0Mihaiela Lupea1Faculty of Industrial Engineering, Robotics and Production Management, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, RomaniaFaculty of Mathematics and Computer Science, Babes-Bolyai University, 400084 Cluj-Napoca, RomaniaThis paper studies the relevance of CWT (continuous wavelet transform) processing of vibration signals for improving the performance of CNN-based models that detect certain types of helical gearbox faults. Gear tooth damages, such as incipient and localized pitting and localized wear on helical pinion tooth flanks, combined with improper lubrication, are the faults under observation. Vibrations at the housing level for three rotating velocities of the AC motor and three load levels (for each velocity) are acquired with a triaxial accelerometer. Through CWT, the vibration signal is decomposed into 2D time-frequency grayscale images, with a filter bank of ten voices per octave in the frequency band of interest. Three 2D-CNN-based models trained on the CWT-based representation of the vibration signals measured on individual accelerometer axes (<i>X</i>, <i>Y</i>, and <i>Z</i>) are proposed to detect the four health states (one normal and three faulty) of the helical gearbox, regardless of the selected load level or speed on the test rig. These models achieve an accuracy higher than 99%. By fusing the CWT-based representations of the signals on individual axes for use as input to a 2D-CNN, the best-performing model for the proposed defect detection task is generated, reaching an accuracy of 99.91%.https://www.mdpi.com/2076-3417/15/2/950helical gearboxcontinuous wavelet transformtriaxial accelerometer sensorvibration signalfault detectionconvolutional neural network |
| spellingShingle | Iulian Lupea Mihaiela Lupea Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox Applied Sciences helical gearbox continuous wavelet transform triaxial accelerometer sensor vibration signal fault detection convolutional neural network |
| title | Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox |
| title_full | Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox |
| title_fullStr | Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox |
| title_full_unstemmed | Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox |
| title_short | Continuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox |
| title_sort | continuous wavelet transform and cnn for fault detection in a helical gearbox |
| topic | helical gearbox continuous wavelet transform triaxial accelerometer sensor vibration signal fault detection convolutional neural network |
| url | https://www.mdpi.com/2076-3417/15/2/950 |
| work_keys_str_mv | AT iulianlupea continuouswavelettransformandcnnforfaultdetectioninahelicalgearbox AT mihaielalupea continuouswavelettransformandcnnforfaultdetectioninahelicalgearbox |