# Brake Disc Deformation Detection Using Intuitive Feature Extraction and Machine Learning

^{1}

^{2}

^{3}

^{4}

^{*}

^{†}

## Abstract

**:**

## 1. Introduction

## 2. Measurement Setup

#### 2.1. Brake Disc Deformations

#### 2.2. Measurement Scenario

- Two measurements: factory used brake disc (15,034 km) with 2 bar wheel pressure;
- Two measurements: aftermarket, intentionally damaged brake disc (ABE type, ground) with 2 bar wheel pressure.

## 3. Signal Description and Preprocessing

## 4. Deformation Detection Methods

## 5. Experiments

#### 5.1. Data-Driven Models

#### 5.2. Results and Discussion

## 6. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Conflicts of Interest

## References

- Van Schoor, O.; Van Niekerk, J.L.; Grobbelaar, B. Mechanical failures as a contributing cause to motor vehicle accidents—South Africa. Accid. Anal. Prev.
**2001**, 33, 713–721. [Google Scholar] [CrossRef] [PubMed] - Haq, M.T.; Ampadu, V.M.K.; Ksaibati, K. An investigation of brake failure related crashes and injury severity on mountainous roadways in Wyoming. J. Saf. Res.
**2023**, 84, 7–17. [Google Scholar] [CrossRef] [PubMed] - Isermann, R. Fault-Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2006. [Google Scholar]
- Hou, Z.; Lee, C.; Lv, Y.; Keung, K. Fault detection and diagnosis of air brake system: A systematic review. J. Manuf. Syst.
**2023**, 71, 34–58. [Google Scholar] [CrossRef] - Jegadeeshwaran, R.; Sugumaran, V. Method and apparatus for fault diagnosis of automobile brake system using vibration signals. Recent Patents Signal Process. (Discontin.)
**2013**, 3, 2–11. [Google Scholar] [CrossRef] - Jegadeeshwaran, R.; Sugumaran, V. Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines. Mech. Syst. Signal Process.
**2015**, 52, 436–446. [Google Scholar] [CrossRef] - Yin, Y.; Xiao, X.; Bao, J.; Li, Z.; Lu, Y. Feature extraction and pattern recognition on the frictional faults of disc brake. J. Balk. Tribol. Assoc.
**2016**, 22, 1208. [Google Scholar] - Zhang, X.; Zhang, M.; Xiang, Z.; Mo, J. Research on diagnosis algorithm of mechanical equipment brake friction fault based on MCNN-SVM. Measurement
**2021**, 186, 110065. [Google Scholar] [CrossRef] - Li, J.; Jiang, S.; Li, M.; Xie, J. A fault diagnosis method of mine hoist disc brake system based on machine learning. Appl. Sci.
**2020**, 10, 1768. [Google Scholar] [CrossRef] - Xu, G.; Song, D.; Zhang, D.; Zhang, X.; Sha, S. A novel mechanical design of disc brakes for fault diagnosis and monitoring positive braking pressure in mine hoist. Adv. Mech. Eng.
**2019**, 11, 1687814019842494. [Google Scholar] [CrossRef] - Jordan, M.I.; Mitchell, T.M. Machine learning: Trends, perspectives, and prospects. Science
**2015**, 349, 255–260. [Google Scholar] [CrossRef] - Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
- Montavon, G.; Samek, W.; Müller, K.R. Methods for interpreting and understanding deep neural networks. Digit. Signal Process.
**2018**, 73, 1–15. [Google Scholar] [CrossRef] - Schmidhuber, J. Deep learning in neural networks: An overview. Neural Netw.
**2015**, 61, 85–117. [Google Scholar] [CrossRef] - Gu, J.; Wang, Z.; Kuen, J.; Ma, L.; Shahroudy, A.; Shuai, B.; Liu, T.; Wang, X.; Wang, G.; Cai, J.; et al. Recent advances in convolutional neural networks. Pattern Recognit.
**2018**, 77, 354–377. [Google Scholar] [CrossRef] - Mankins, J.C. Technology readiness levels. In White Paper, April; NASA: Washington, DC, USA, 1995; Volume 6. [Google Scholar]
- Dózsa, T.; Deuschle, F.; Cornelis, B.; Kovács, P. Variable Projection Support Vector Machines and Some Applications Using Adaptive Hermite Expansions. Int. J. Neural Syst.
**2024**, 34, 2450004. [Google Scholar] [CrossRef] [PubMed] - Dózsa, T.; Ámon, A.; Braun, F.; Simonyi, E.; Soumelidis, A.; Volk, J.; Kovács, P. Towards intelligent tire development. In Proceedings of the 13th International Conference on Transport Sciences, Győr, Hungary, 8–9 June 2023; Közlekedéstudományi Egyesület: Budapest, Hungary, 2023; pp. 145–155. [Google Scholar]
- Szalay, Z.; Hamar, Z.; Simon, P. A multi-layer autonomous vehicle and simulation validation ecosystem axis: Zalazone. In Proceedings of the Intelligent Autonomous Systems 15: Proceedings of the 15th International Conference IAS-15, Baden-Baden, Germany, 11–15 June 2018; Springer: Berlin/Heidelberg, Germany, 2019; pp. 954–963. [Google Scholar]
- Dugoff, H.; Fancher, P.S.; Segel, L. An analysis of tire traction properties and their influence on vehicle dynamic performance. SAE Trans.
**1970**, 79, 1219–1243. [Google Scholar] - Okuda, R.; Kajiwara, Y.; Terashima, K. A survey of technical trend of ADAS and autonomous driving. In Proceedings of the Technical Papers of 2014 International Symposium on VLSI Design, Automation and Test, Hsinchu, Taiwan, 28–30 April 2014; IEEE: New York, NY, USA, 2014; pp. 1–4. [Google Scholar]
- Deuschle, F.; Cornelis, B.; Gryllias, K. Robust sensor spike detection method based on dynamic time warping. In Proceedings of the 4th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI), Corfu, Greece, 19–21 October 2022; pp. 20–27. [Google Scholar]
- Gasquet, C.; Witomski, P. Fourier Analysis and Applications: Filtering, Numerical Computation, Wavelets; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2013; Volume 30. [Google Scholar]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. Commun. ACM
**2017**, 60, 84–90. [Google Scholar] [CrossRef] - Kovács, P.; Bognár, G.; Huber, C.; Huemer, M. VPNet: Variable projection networks. Int. J. Neural Syst.
**2022**, 32, 2150054. [Google Scholar] [CrossRef] - Luz, E.J.d.S.; Schwartz, W.R.; Cámara-Chávez, G.; Menotti, D. ECG-based heartbeat classification for arrhythmia detection: A survey. Comput. Methods Programs Biomed.
**2016**, 127, 144–164. [Google Scholar] [CrossRef] - Dózsa, T.; Böck, C.; Bognár, G.; Meier, J.; Kovács, P. Color classification of visually evoked potentials by means of Hermite functions. In Proceedings of the 2021 55th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 31 October–3 November 2021; IEEE: New York, NY, USA, 2021; pp. 251–255. [Google Scholar]
- Dózsa, T.; Radó, J.; Volk, J.; Kisari, Á.; Soumelidis, A.; Kovács, P. Road abnormality detection using piezoresistive force sensors and adaptive signal models. IEEE Trans. Instrum. Meas.
**2022**, 71, 1–11. [Google Scholar] [CrossRef] - Chapelle, O. Training a support vector machine in the primal. Neural Comput.
**2007**, 19, 1155–1178. [Google Scholar] [CrossRef] [PubMed] - Abdi, H.; Williams, L.J.; Valentin, D. Multiple factor analysis: Principal component analysis for multitable and multiblock data sets. Wiley Interdiscip. Rev. Comput. Stat.
**2013**, 5, 149–179. [Google Scholar] [CrossRef] - Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res.
**2011**, 12, 2825–2830. [Google Scholar] - Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the 33rd Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 8–14 December 2019; Volume 32. [Google Scholar]
- Ring, M.; Eskofier, B.M. An approximation of the Gaussian RBF kernel for efficient classification with SVMs. Pattern Recognit. Lett.
**2016**, 84, 107–113. [Google Scholar] [CrossRef] - Parmar, A.; Katariya, R.; Patel, V. A review on random forest: An ensemble classifier. In Proceedings of the International Conference on Intelligent Data Communication Technologies and Internet of things (ICICI) 2018, Coimbatore, India, 7–8 August 2018; Springer: Berlin/Heidelberg, Germany, 2019; pp. 758–763. [Google Scholar]
- Banfield, R.E.; Hall, L.O.; Bowyer, K.W.; Kegelmeyer, W.P. A comparison of decision tree ensemble creation techniques. IEEE Trans. Pattern Anal. Mach. Intell.
**2006**, 29, 173–180. [Google Scholar] [CrossRef] [PubMed] - Xu, B.; Huang, J.Z.; Williams, G.; Wang, Q.; Ye, Y. Classifying very high-dimensional data with random forests built from small subspaces. Int. J. Data Warehous. Min.
**2012**, 8, 44–63. [Google Scholar] [CrossRef] - Rish, I. An empirical study of the naive Bayes classifier. In IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence; IBM: New York, NY, USA, 2001; Volume 3, pp. 41–46. [Google Scholar]
- Li, Y.; Yuan, Y. Convergence analysis of two-layer neural networks with relu activation. In Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017; Volume 30. [Google Scholar]
- Zhang, J.; Tian, J.; Alcaide, A.M.; Leon, J.I.; Vazquez, S.; Franquelo, L.G.; Luo, H.; Yin, S. Lifetime Extension Approach Based on the Levenberg–Marquardt Neural Network and Power Routing of DC–DC Converters. IEEE Trans. Power Electron.
**2023**, 38, 10280–10291. [Google Scholar] [CrossRef] - Zhang, J.; Tian, J.; Yan, P.; Wu, S.; Luo, H.; Yin, S. Multi-hop graph pooling adversarial network for cross-domain remaining useful life prediction: A distributed federated learning perspective. Reliab. Eng. Syst. Saf.
**2024**, 244, 109950. [Google Scholar] [CrossRef] - Moré, J.J. The Levenberg-Marquardt algorithm: Implementation and theory. In Proceedings of the Numerical Analysis: Proceedings of the Biennial Conference, Dundee, UK, 28 June–1 July 1977; Springer: Berlin/Heidelberg, Germany, 2006; pp. 105–116. [Google Scholar]
- Dózsa, T.; Őri, P.; Szabari, M.; Simonyi, E.; Soumelidis, A.; Lakatos, I. Breakdiscdeformation, Software Material for Current Article. Available online: https://gitlab.com/tamasdzs/ (accessed on 31 January 2024).
- Li, T.; Zhao, Z.; Sun, C.; Cheng, L.; Chen, X.; Yan, R.; Gao, R.X. WaveletKernelNet: An interpretable deep neural network for industrial intelligent diagnosis. IEEE Trans. Syst. Man, Cybern. Syst.
**2021**, 52, 2302–2312. [Google Scholar] [CrossRef]

**Figure 6.**The piezoelectric acceleration sensor mounted on the swingarm. Sensors were mounted symmetrically on both sides of the vehicle.

**Figure 7.**Frequency spectrum of acceleration signals at low and high vehicle speeds. (

**Left**): Power spectrum of the signals. (

**Right**): Filtered power spectrum using a moving average filter. The shown signals were recorded from a single acceleration sensor without any brake disc deformation present.

**Figure 8.**Only parts of the signals where vehicle speed was decreasing and remained between 90 and 30 km/h were considered.

**Figure 10.**TOP: Segmentation of the acceleration signals without overlap to create dataset 1. BOTTOM: Overlapping segmentation to create dataset 2.

**Figure 11.**Fully connected neural network architecture used for the proposed experiments. Each linear layer uses 10 neurons with hidden layers equipped with ReLU activation functions. The final linear layer uses sigmoid activation.

Dataset | # of Deformed Signals | # of Normal Signals | Total # of Signals |
---|---|---|---|

Non-overlapping | 12 (∼55%) | 10 (∼45%) | 22 |

Overlapping | $3279\phantom{\rule{4pt}{0ex}}(50\%)$ | $3279\phantom{\rule{4pt}{0ex}}(50\%)$ | 6558 |

Name | Abbreviation | Nonlinear Data |
---|---|---|

Support vector classifier (linear kernel) | SVM (linear) | No |

Support vector classifier (radial basis kernel) | SVM (RBF) | Yes |

Naive Bayes classifier | NB | Yes |

Random forest classifier | RF | Yes |

Fully connected neural network | FCNN | Yes |

Convolutional neural network | CNN | Yes |

Levenberg-Marquardt backpropagation network | LM-BPNN | Yes |

**Table 3.**Experimental results achieved using 5-fold cross-validation on the non-overlapping dataset.

Model | Feature Extraction | Avg. Acc. | Min. Acc. | Max. Acc. |
---|---|---|---|---|

SVM (linear) | - | $0.54$ | $0.2$ | $\mathbf{1.0}$ |

PCA | $0.67$ | $0.5$ | $0.8$ | |

std | $0.9$ | $0.75$ | $\mathbf{1.0}$ | |

SVM (RBF) | - | $0.54$ | $0.5$ | $0.6$ |

PCA | $0.71$ | $0.5$ | $\mathbf{1.0}$ | |

std | $0.92$ | $\mathbf{0.8}$ | $\mathbf{1.0}$ | |

NB | - | $0.58$ | $0.5$ | $0.8$ |

PCA | $0.68$ | $0.5$ | $0.8$ | |

std | $0.85$ | $0.75$ | $\mathbf{1.0}$ | |

RF | - | $0.54$ | $0.25$ | $0.75$ |

PCA | $0.78$ | $0.6$ | $\mathbf{1.0}$ | |

std | $\mathbf{0.95}$ | $0.75$ | $\mathbf{1.0}$ |

**Table 4.**Experimental results achieved using the larger, overlapping dataset. In this case, more sophisticated neural-network-based models were also considered.

Model | Feature Extraction | Accuracy on Test Set |
---|---|---|

SVM (linear) | - | $0.502$ |

PCA | $0.737$ | |

std | $\mathbf{1.0}$ | |

SVM (RBF) | - | $0.799$ |

PCA | $0.976$ | |

std | $\mathbf{1.0}$ | |

NB | - | $0.655$ |

PCA | $0.800$ | |

std | $0.854$ | |

RF | - | $0.837$ |

PCA | $0.804$ | |

std | $0.963$ | |

FCNN | - | $0.573$ |

PCA | $0.891$ | |

std | $\mathbf{1.0}$ | |

CNN | automatic | $\mathbf{1.0}$ |

LM-BPNN | - | $0.599$ |

PCA | $0.599$ | |

std | $\mathbf{1.0}$ |

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |

© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Dózsa, T.; Őri, P.; Szabari, M.; Simonyi, E.; Soumelidis, A.; Lakatos, I.
Brake Disc Deformation Detection Using Intuitive Feature Extraction and Machine Learning. *Machines* **2024**, *12*, 214.
https://doi.org/10.3390/machines12040214

**AMA Style**

Dózsa T, Őri P, Szabari M, Simonyi E, Soumelidis A, Lakatos I.
Brake Disc Deformation Detection Using Intuitive Feature Extraction and Machine Learning. *Machines*. 2024; 12(4):214.
https://doi.org/10.3390/machines12040214

**Chicago/Turabian Style**

Dózsa, Tamás, Péter Őri, Mátyás Szabari, Ernő Simonyi, Alexandros Soumelidis, and István Lakatos.
2024. "Brake Disc Deformation Detection Using Intuitive Feature Extraction and Machine Learning" *Machines* 12, no. 4: 214.
https://doi.org/10.3390/machines12040214