Prediction of frictional braking noise based on brake dynamometer test and artificial intelligent algorithms

Wang, Shuwen; Zhong, Liu; Niu, Yayun; Liu, Shuangxia; Wang, Shaofan; Li, Ké; Wang, Lijing; Barton, D.C.

doi:10.1177/09544070211062276

Cited by 4 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stender et al [17] used Convolutional Neural Networks (CNN) based on machine learning to detect vibrations combined with the RNN algorithm to predict braking noise. Wang et al [18] used the LSTM algorithm and the optimized XGBoost algorithm to predict the braking COFs and braking noise, and the prediction results were in good agreement with the experimental results. Alexsendric and Barton [19] used artificial neural networks (ANN) to predict the COFs of a disk brake system for different operating conditions taking account of the composition of the friction material.…”

Section: Introductionmentioning

confidence: 77%

See 1 more Smart Citation

Braking Friction Coefficient Prediction Using PSO–GRU Algorithm Based on Braking Dynamometer Testing

Wang,

Yu,

Liu

et al. 2024

Lubricants

Self Cite

View full text Add to dashboard Cite

The coefficients of friction (COFs) is one of the most important parameters used to evaluate the braking performance of a friction brake. Many indicators that affect the safety and comfort of automobiles are associated with brake COFs. The manufacturers of friction brakes and their components are required to spend huge amounts of time and money to carry out experimental tests to ensure the COFs of a newly developed braking system meet the required standards. In order to save time and costs for the development of new friction brake applications, the GRU (Gate Recurrent Unit) algorithm optimized by the improved PSO (particle swarm optimization) global optimization method is employed in this work to predict brake COFs based on existing experimental data obtained from friction braking dynamometer tests. Compared with the LSTM (Long Short-Term Memory) method, the GRU algorithm optimized by PSO avoids the accuracy reduction problem caused by gradient descent in the training process and hence reduces the prediction error and computational cost. The combined PSO–GRU algorithm increases the coefficient of determination (R2) of the prediction by 4.7%, reduces the MAE (mean absolute error) by 14.3%, and increases the prediction speed by 40.1% compared with the standalone GRU method. The prediction method based on machine learning proposed in this study can not only be applied to the prediction of automobile braking COFs but also for other frictional system problems, such as the prediction of braking noise and the friction of various bearing transmission components.

show abstract

Section: Introductionmentioning

confidence: 77%

“…More detailed information about the brake materials and the setup of the braking dynamometer testing can be found in Ref. [18]. Table 1 demonstrates typical experimental data obtained from just 11 out of the approximately 1000 braking dynamometer tests.…”

Section: Braking Dynamometer Testing and Typical Resultsmentioning

confidence: 99%

Braking Friction Coefficient Prediction Using PSO–GRU Algorithm Based on Braking Dynamometer Testing

Wang,

Yu,

Liu

et al. 2024

Lubricants

Self Cite

View full text Add to dashboard Cite

show abstract

“…The procedure described therein is very successful even if it seems to be unusual to use image recognition for this application. In another work [55], various parameter-based classification algorithms are used to predict the squeal behavior of a particular brake system. There, however, the time series of the recorded squeal is not used directly, instead external parameters such as brake pressure, speed, or temperature.…”

Section: Data Analysis Of Dynamometer Results Using Machine Learningmentioning

confidence: 99%

On Drum Brake Squeal—Assessment of Damping Measures by Time Series Data Analysis of Dynamometer Tests and Complex Eigenvalue Analyses

Gräbner,

Schmid,

von Wagner

2023

Machines

View full text Add to dashboard Cite

Brake squeal—an audible high-frequency noise phenomenon in the range between 1 kHz and 15 kHz resulting from self-excited vibrations—is one of the main cost drivers while developing brake systems. Increasing damping is often a crucial factor in the context of self-excited vibrations. Countermeasures applied for preventing brake squeal have been investigated particularly for disk brakes in the past. However, in recent years, drum brakes have once again become more important, partly because of the issue of particle emissions. Concerning noise problems, drum brakes have a decisive advantage compared to disk brake systems in that the outer drum surface is freely accessible for applying damping devices. This paper focuses on the fundamental proving and evaluation of passive damping measures on a simplex drum brake system. To obtain a detailed understanding of the influence of additional damping on the squealing behavior of drum brakes, extensive experimental investigations are performed on a brake with an intentionally introduced high squealing tendency in the initial configuration. This made it possible to investigate the influence of different types of damping measures on their effectiveness. Techniques from the field of big data analysis and machine learning are tested to detect squeal in measured time series data. These techniques were remarkably reliable and made it possible to detect squeal efficiently even in data that was not generated on a traditional costly NVH brake dynamometer. To investigate whether the simulation method usually used for the simulation of brake squeal is applicable to depicting the influence of additional damping in drum brakes, a complex eigenvalue analysis was performed with Abaqus, and the results were compared with those from the experiments.

show abstract

Minimal model identification of drum brake squeal via SINDy

Wulff,

Gräbner,

von Wagner

2024

Arch Appl Mech

View full text Add to dashboard Cite

The industrial standard in the design and development process of NVH(Noise Vibration Harshness) characteristic of brakes is the application of Finite Element(FE) models with a high number of degrees of freedom in the range of one or several millions. Nevertheless, parallel experimental investigations are still indispensable. On the other hand, minimal models with, due to the inclusion of the self-excitation process, at least two degrees of freedom are well known to be capable to explain qualitatively phenomena as instability of the desired non-vibrating solution or limit cycle oscillation but are in general very inaccurate in predicting the dynamics of a specific real brake. This is because the underlying physical assumptions are already too restrictive and model parameters (especially those referring to nonlinearities) are widely unknown. To overcome this problem, the data-driven modeling approach SINDy(Sparse Identification of Nonlinear Dynamics) is applied to identify appropriate nonlinear functions for a brake squeal minimal model. A problem thereby is the limited database. It turns out that the naive implementation of the method yielding the lowest possible residuum does not necessarily provide physically meaningful models and results, respectively. Instead, a constrained model that incorporates physical knowledge is used to robustly identify parameters and reproduce realistic dynamic behavior. Thereby, several appropriate models with coexisting limit cycles and stationary equilibrium are identified. In particular, it was found that the angular position of the brake drum has a significant influence on the model parameters and therefore must be taken into account in a model with long-term validity.

show abstract

Prediction of frictional braking noise based on brake dynamometer test and artificial intelligent algorithms

Cited by 4 publications

References 39 publications

Braking Friction Coefficient Prediction Using PSO–GRU Algorithm Based on Braking Dynamometer Testing

Braking Friction Coefficient Prediction Using PSO–GRU Algorithm Based on Braking Dynamometer Testing

On Drum Brake Squeal—Assessment of Damping Measures by Time Series Data Analysis of Dynamometer Tests and Complex Eigenvalue Analyses

Minimal model identification of drum brake squeal via SINDy

Contact Info

Product

Resources

About