Experimental force reconstruction on plates of arbitrary shape using neural networks
Time: 7:40 pm
Author: Tyler Dare
Abstract ID: 2397
Measuring the forces that excite a structure into vibration is an important tool in modeling the system and investigating ways to reduce the vibration. However, determining the forces that have been applied to a vibrating structure can be a challenging inverse problem, even when the structure is instrumented with a large number of sensors. Previously, an artificial neural network was developed to identify the location of an impulsive force on a rectangular plate. In this research, the techniques were extended to plates of arbitrary shape. The principal challenge of arbitrary shapes is that some combinations of network outputs (x- and y-coordinates) are invalid. For example, for a plate with a hole in the middle, the network should not output that the force was applied in the center of the hole. Different methods of accommodating arbitrary shapes were investigated, including output space quantization and selecting the closest valid region.
Investigating the relationship between train speed and ground vibrations using random forest machine learning models
Time: 11:40 am
Author: Frank Klein Schaarsberg
Abstract ID: 2463
In the Netherlands, concerned citizens have proposed reducing train speed as an effective measure to mitigate annoyance caused by railway-induced vibrations. In the present study the relationship between train speed and other influencing parameters (e.g. axle load, wheel roughness), and ground vibrations was investigated using measurements, at different locations, of ground vibrations caused by the passage of regular freight trains and a test train at different speeds. Measurements have been analysed using multivariate regression models and a random decision forest model. The prevailing uncertainties have also been measured using normalized mean deviation between the model predicted value and the actual value. A comparison of results demonstrates that a trained and tested random forest model has certain predictive advantages: i) mean deviation between predicted and actual value is found to be the lowest with random forest model; ii) the random forest model considers all available parameters in the dataset, thus simulating the real situation more closely. However, the model is very location-specific and must therefore be used with caution. In general it is observed that a decrease in train speed results in the reduction of measured vibration levels.
A Sound Insulation Prediction Model for Floor Structures in Wooden Buildings Using Neural Networks approach
Time: 5:20 pm
Author: Mohamad BADER EDDIN
Abstract ID: 2619
Recently, machine learning and its applications have gained a large attraction in different fields. Accurate predictions in building acoustics is vital especially in the design stage. This paper presents a sound insulation prediction model based on Artificial Neural Networks (ANNs) to estimate acoustic performance for airborne and impact sound insulation of floor structures. At an initial stage, the prediction model was developed and tested for a small amount of data, specifically 67 measurement curves in one third octave bands. The results indicate that the model can predict the weighted airborne sound insulation for various floors with an error around 1 dB, while the accuracy decreases for the impact sound especially for complex floor configurations due to large error deviations in high frequency bands between the real and estimated values. The model also shows a very good accuracy in predicting the airborne and impact sound insulation curves in the low frequencies, which are of higher interest usually in building acoustics. Keywords: building acoustics, airborne sound, impact sound, prediction model, neural networks
Scalable Machine Learning Approach to Classifying Transportation Noise at Two Urban Sites in Greater Boston, Massachusetts
Time: 12:00 pm
Author: Tiange Wang
Abstract ID: 2907
The goal of this study was to characterize transportation noise by vehicle class in two urban communities, to inform studies of transport noise and ultra-fine particulates. Data were collected from April to September 2016 (150 days) of continuous recording in each urban community using high-resolution microphones. Training data was created for airplanes, trucks/buses, and train events by manual listening and extraction of audio files. Digital signal processing using STFT and Hanning windowing was performed in MATLAB, creating audio spectrograms with varying frequency: log vs linear frequency scales, and 4K vs 20K max frequency. For each of the four spectrogram sets, a neural net model using PyTorch was trained via a compute cluster. Initial results for a multi-class model provide an accuracy of 85%. Comparison between a selection of frequency scales and expanding to longer time periods is ongoing. Validation with airport transport logs and local bus and train schedules will be presented.
Investigating the influence of microphone mismatch for acoustic traffic monitoring
Time: 11:20 am
Author: Saichand Gourishetti
Abstract ID: 2375
The development of robust acoustic traffic monitoring (ATM) algorithms based on machine learning faces several challenges. The biggest challenge is to collect and annotate large high-quality datasets for algorithm training and evaluation. Such a dataset must reflect a broad variety of vehicle sounds since their emitted acoustic noise patterns depend on a variety of factors such as engine noises at different speeds and road conditions. Additionally, the characteristics of the employed microphones have a strong influence on the data. If microphones with different directionality and frequency responses are used during the model development and the final deployment phase, a data mismatch is caused, which can have a deteriorating effect on the performance of machine learning algorithms. In this paper, the influence of mismatched recording locations and microphone characteristics on the proposed ATM system is investigated. To evaluate these effects, we implement state-of-the-art convolutional neural networks to detect passing vehicles, classify their type, and estimate their speed and direction of movement. The evaluated models perform well on low- and high-quality recordings at different locations when using the same recording device for training and testing. However, the results indicate that microphone mismatch causes several issues, which need to be carefully addressed.
Learning-based estimation of individual absorption profiles from a single room impulse response with known positions of source, sensor and surfaces
Time: 11:00 am
Author: Stéphane Dilungana
Abstract ID: 3186
In situ estimation of the individual absorption profiles of a room remains a challenging problem in building acoustics. This work is aimed at studying the feasibility of this estimation in a shoebox room of fixed and known geometry, using a room impulse response measured from a source and sensor at fixed and known positions. This problem is tackled using supervised learning. Three neural network architectures are compared. Simulated training and validation sets featuring various types of perturbations (surface diffusion, geometrical errors and additive white Gaussian noise) are generated. An extensive empirical simulated study is carried out to determine the influence of these perturbations on the performances of learned models, and to determine which components of the room impulse response are most useful for absorption coefficients prediction. Trained models are shown to yield errors significantly smaller than those of a naive mean estimator on every simulated datasets, including those featuring realistic perturbation levels. Our study outlines the benefit of using convolutional neural network layers, especially when geometrical errors exist. It also reveals that early acoustic echoes are the most salient feature of room impulse responses for absorption coefficient prediction under a fixed geometry.