Stender Merten, Adams Christian, Wedler Mathies, Grebel Antje, Hoffmann Nobert
Dynamics Group, Mechanical Engineering, Hamburg University of Technology, Am Schwarzenberg-Campus, Hamburg 21073, Germany.
Mechanical Engineering Department, System Reliability, Adaptive Structures, and Machine Acoustics, Technical University of Darmstadt, Otto-Berndt-Straße, Darmstadt 64287, Germany.
J Acoust Soc Am. 2021 Mar;149(3):1932. doi: 10.1121/10.0003755.
Measurements of acoustic properties of sound absorbing materials in impedance tubes show poor reproducibility, which was demonstrated in round robin tests. The impedance tube measurements are standardized but lack precise definitions of the actual measurement setup, specimen preparation, and other factors that introduce uncertainty in practice. In this paper, machine learning models identify those factors that mostly affect the sound absorption coefficient from a large data set of more than 3000 absorption spectra measured in one impedance tube. The specimens are manufactured from one polyurethane foam, and different cutting technologies, different operators, different specimen diameters, different specimen thicknesses, and two different approaches to mount the specimens in the impedance tube are considered. Explainable machine learning techniques allow the identification and quantification of the most influential factors and, furthermore, the frequency ranges that are the most affected by the choice of these setup factors. The results indicate that besides the specimen thickness, also the operator affects the absorption coefficient by a directional and non-random relationship. Hence, it needs to be controlled carefully. The method proves to be a promising pathway for knowledge discovery from acoustic measurement data using explainability approaches for machine learning models.
在驻波管中对吸声材料声学特性的测量显示出较差的可重复性，这在循环测试中得到了证明。驻波管测量是标准化的，但缺乏对实际测量设置、样品制备以及其他在实际中引入不确定性的因素的精确定义。在本文中，机器学习模型从在一个驻波管中测量的3000多个吸收光谱的大数据集中识别出那些对吸声系数影响最大的因素。样品由一种聚氨酯泡沫制成，并考虑了不同的切割技术、不同的操作人员、不同的样品直径、不同的样品厚度以及将样品安装在驻波管中的两种不同方法。可解释的机器学习技术能够识别和量化最有影响的因素，此外，还能确定受这些设置因素选择影响最大的频率范围。结果表明，除了样品厚度外，操作人员也通过一种定向且非随机的关系影响吸声系数。因此，需要仔细控制。该方法被证明是一种利用机器学习模型的可解释性方法从声学测量数据中发现知识的有前景的途径。
