journal article·2024-08-01

Addressing data scarcity using audio signal augmentation and deep learning for bolt looseness prediction

Nikesh Chelimilla, Viswanath Chinthapenta, Srikanth Korla

Smart Materials and Structures· Volume 33· Issue 8
Publisher page

Abstract

Abstract Deep learning models such as convolutional neural networks (CNNs) encounter challenges, including instability and overfitting, while predicting bolt looseness in data-scarce scenarios. In this study, we proposed a novel audio signal augmentation approach to classify bolt looseness in the event of data deficiency using CNN models. Audio signals at varied bolt torque conditions were extracted using the percussion method. Audio signal augmentation was performed using signal shifting and scaling strategies after segmenting the extracted audio signals. The unaugmented and augmented audio signals were transformed into scalograms using the continuous wavelet transform approach to train the CNN models. Upon training with augmented datasets, a promising improvement in the loss and accuracy of the CNN models in recognizing bolt looseness was noticed. One of the significant observations from the current study is that the implementation of audio signal augmentation improved the extrinsic generalization ability of the CNN models to classify bolt looseness. A maximum increase of 73.5% to identify bolt looseness in novel data was exhibited as compared to without augmentation. Overall, a maximum accuracy of 94.5% to classify bolt looseness in unseen data was demonstrated upon audio signal augmentation. In summary, the results affirm that the audio signal augmentation approach empowered the CNN models to predict bolt looseness in data-deficient scenarios accurately.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Engineering Structural Analysis Methods · Mechanical stress and fatigue analysis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (53)

Show source-provided references
1. Coda wave interferometry-based very early stage bolt looseness monitoring using a single piezoceramic transducer10.1088/1361-665X/ac5128 ↗
2. Automatic inspection of bridge bolts using unmanned aerial vision and adaptive scale unification-based deep learning10.3390/rs15020328 ↗
3. Tribological aspects of the self-loosening of threaded fasteners
4. Invention of smart tightening tool for directly controlling the preload of bolted joints10.1088/1361-665X/acb02a ↗
5. A review of bolt tightening force measurement and loosening detection10.3390/s20113165 ↗
6. A comprehensive review of loosening detection methods for threaded fasteners10.1016/j.ymssp.2021.108652 ↗
7. Review on recent advances in structural health monitoring paradigm for looseness detection in bolted assemblies10.1177/14759217231158540 ↗
8. Analysis of transient vibrations for estimating bolted joint tightness10.1007/978-3-030-12391-8_3 ↗
9. Axial force measurement of the bolt/nut assemblies based on the bending mode shape frequency of the protruding thread part using ultrasonic modal analysis10.1016/j.measurement.2020.107914 ↗
10. Modeling and experimental studies on the dynamics of bolted joint structure: comparison of three vibration-based techniques for structural health monitoring
11. Monitoring of early looseness of multi-bolt connection: a new entropy-based active sensing method without saturation10.1088/1361-665X/ab3a08 ↗
12. Early bolt looseness monitoring using the leading waves energy in piezoelectric active sensing10.1088/1361-665X/ad3bfd ↗
13. Real time bolt preload monitoring using piezoceramic transducers and time reversal technique—a numerical study with experimental verification10.1088/0964-1726/25/8/085015 ↗
14. Piezo impedance-based monitoring of loosening of bolts: experimental and numerical study10.1177/1045389X211041166 ↗
15. Vibration acoustic modulation for bolt looseness monitoring based on frequency-swept excitation and bispectrum10.1088/1361-665X/acb579 ↗
16. Bolt-looseness detection by a new percussion-based method using multifractal analysis and gradient boosting decision tree10.1177/1475921720912780 ↗
17. Research on the influence of an adhesive layer on the monitoring signal of piezoelectric sensors10.1088/1361-665X/acf4d7 ↗
18. ResNet-integrated very early bolt looseness monitoring based on intrinsic feature extraction of percussion sounds10.1088/1361-665X/acb2a0 ↗
19. Autonomous bolt loosening detection using deep learning10.1177/1475921719837509 ↗
20. Research on double-sided detection method of bolt looseness based on machine vision10.1007/s40430-022-03996-9 ↗
21. A two-step computer vision-based framework for bolt loosening detection and its implementation on a smartphone application10.1177/14759217211049995 ↗
22. Quasi-autonomous bolt-loosening detection method using vision-based deep learning and image processing10.1016/j.autcon.2019.102844 ↗
23. Quantitative loosening detection of threaded fasteners using vision-based deep learning and geometric imaging theory10.1016/j.autcon.2021.104009 ↗
24. Vision-based detection of loosened bolts using the Hough transform and support vector machines10.1016/j.autcon.2016.06.008 ↗
25. Fully automated vision-based loosened bolt detection using the Viola–Jones algorithm10.1177/1475921718757459 ↗
26. Tapping and listening: a new approach to bolt looseness monitoring10.1088/1361-665X/aac962 ↗
27. Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network10.1088/1361-665X/ab3b39 ↗
28. Bolt loosening detection based on audio classification10.1177/1369433219852565 ↗
29. 1D-TICapsNet: an audio signal processing algorithm for bolt early looseness detection10.1177/1475921720976989 ↗
30. Research on a percussion-based bolt looseness identification method based on phase feature and convolutional neural network10.1088/1361-665X/acb4cb ↗
31. Percussion-based loosening detection method for multi-bolt structure using convolutional neural network DenseNet-CBAM10.1177/14759217231182305 ↗
32. Bolt preload monitoring based on percussion sound signal and convolutional neural network (CNN)10.1080/10589759.2022.2030735 ↗
33. Looseness detection in cup-lock scaffolds using percussion-based method10.1016/j.autcon.2020.103266 ↗
34. A novel percussion-based method for multi-bolt looseness detection using one-dimensional memory augmented convolutional long short-term memory networks10.1016/j.ymssp.2021.107955 ↗
35. 1D-TICapsNet: an audio signal processing algorithm for bolt early looseness detection10.1177/1475921720976989 ↗
36. If structure can exclaim: a novel robotic-assisted percussion method for spatial bolt-ball joint looseness detection10.1177/1475921720923147 ↗
37. An efficient robotic-assisted bolt-ball joint looseness monitoring approach using CBAM-enhanced lightweight ResNet10.1088/1361-665X/ad06e0 ↗
38. An exploratory study of underwater bolted connection looseness detection using percussion and a shallow machine learning algorithm10.1007/s10409-023-22360-x ↗
39. Underwater bolted flange looseness detection using percussion-induced sound and feature-reduced multi-ROCKET model10.1177/14759217231153991 ↗
40. Review of robot-based damage assessment for offshore wind turbines10.1016/j.rser.2022.112187 ↗
41. A study of overfitting in optimization of a manufacturing quality control procedure10.1016/j.asoc.2017.05.027 ↗
42. Empowering precision medicine: AI-driven schizophrenia diagnosis via EEG signals: a comprehensive review from 2002–202310.1007/s10489-023-05155-6 ↗
43. A method of data augmentation for classifying road damage considering influence on classification accuracy10.1016/j.procs.2019.09.315 ↗
44. A fatigue crack growth prediction method on small datasets based on optimized deep neural network and Delaunay data augmentation10.1016/j.tafmec.2023.104218 ↗
45. A diagnostic framework with a novel simulation data augmentation method for rail damages based on transfer learning10.1177/14759217221149129 ↗
46. Autonomous assessment of delamination in laminated composites using deep learning and data augmentation10.1016/j.compstruct.2022.115502 ↗
47. A deep learning-based approach for condition assessment of semi-rigid joint of steel frame10.1016/j.jobe.2020.101946 ↗
48. The impact of filter size and number of filters on classification accuracy in CNN10.1109/CSASE48920.2020.9142089 ↗
49. A CNN-integrated percussion method for detection of FRP–concrete interfacial damage with FEM reconstruction10.1177/14759217221082007 ↗
50. Percussion-based quasi real-time void detection for concrete-filled steel tubular structures using dense learned features10.1016/j.engstruct.2022.115197 ↗
51. An innovative deep neural network coordinating with percussion-based technique for automatic detection of concrete cavity defects10.1016/j.conbuildmat.2023.132700 ↗
52. Percussion-based pipeline ponding detection using a convolutional neural network10.3390/app12042127 ↗
53. The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset10.1016/j.icte.2020.04.010 ↗