Return to Schedule HERE

20.01 Artificial Intelligence for Noise and Vibration Control, Part 2

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.

You must be logged in to download paper. Click here to login

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.

You must be logged in to download paper. Click here to login

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

You must be logged in to download paper. Click here to login

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.

You must be logged in to download paper. Click here to login

Deep Learning-based Health Indicator for Better Bearing RUL Prediction
Time: 6:20 am

Author: Taewan Kim

Abstract ID: 1492

The prognostic performance of data-driven approaches closely depends on the features extracted from the measurement. For a high level of prognostic performance, features must be carefully designed to represent the machine’s health state well and are generally obtained by signal processing techniques. These features are themselves used as health indicators (HI) or used to construct HIs. However, many conventional HIs are heavily relying on the type of machine components and expert domain knowledge. To solve these drawbacks, we propose a fully data-driven method, that is, the adversarial autoencoder-based health indicator (AAE-HI) for remaining useful life (RUL) prediction. Accelerated degradation tests of bearings collected from PRONOSTIA were used to validate the proposed AAE-HI method. It is shown that our proposed AAE-HI can autonomously find monotonicity and trendability of features, which will capture the degradation progression from the measurement. Therefore, the performance of AAE-HI in RUL prediction is promising compared with other conventional HIs.

You must be logged in to download paper. Click here to login

Sound field reconstruction in rooms with deep generative models
Time: 6:00 am

Author: Xenofon Karakonstantis

Abstract ID: 1864

The characterization of Room Impulse Responses (RIR) over an extended region in a room by means of measurements requires dense spatial with many microphones.  This can often become intractable and time consuming in practice. Well established reconstruction methods such as plane wave regression show that the sound field in a room can be reconstructed from sparsely distributed measurements. However, these reconstructions usually rely on assuming physical sparsity (i.e. few waves compose the sound field) or trait in the measured sound field, making the models less generalizable and problem specific. In this paper we introduce a method to reconstruct a sound field in an enclosure with the use of a Generative Adversarial Network (GAN), which s new variants of the data distributions that it is trained upon. The goal of the proposed GAN model is to estimate the underlying distribution of plane waves in any source free region, and map these distributions from a stochastic, latent representation. A GAN is trained on a large number of synthesized sound fields represented by a random wave field and then tested on both simulated and real data sets, of lightly damped and reverberant rooms.

You must be logged in to download paper. Click here to login

Partial discharge monitoring using deep neural networks with acoustic emission
Time: 6:40 am

Author: Saichand Gourishetti

Abstract ID: 2373

The occurrence of partial discharge (PD) indicates failures in electrical equipment. Depending on the equipment and operating conditions, each type of PD has its own acoustic characteristics and a wide frequency spectrum. To detect PD, electrical equipment is often monitored using various sensors, such as microphones, ultrasonic, and transient-earth voltage, whose signals are then analyzed manually by experts using signal processing techniques. This process requires significant expertise and time, both of which are costly. Advancements in machine learning, aim to address this issue by automatically learning a representation of the signal, minimizing the need for expert analysis. To this end, we propose a deep learning-based solution for the automatic detection of PD using airborne sound emission in the audible to the ultrasonic range. As input to our proposed model, we evaluate common time-frequency representations of the acoustic signal, such as short-time Fourier, continuous wavelet transform and Mel spectrograms. The extracted spectrum from the PD signal pulses is used to train and evaluate the proposed deep neural network models for the detection of different types of PD. Compared to the manual process, the automatic solution is seen as beneficial for maintenance processes and measurement technology.

You must be logged in to download paper. Click here to login

A neural network based noise suppression method for transient noise control with low-complexity computation
Time: 7:00 am

Author: Yiya Hao

Abstract ID: 11598

Over the decades, the noise-suppression (NS) methods for speech enhancement (SE) have been widely utilized, including the conventional signal processing methods and the deep neural networks (DNN) methods. Although stationary-noise can be suppressed successfully using conventional or DNN methods, it is significantly challenging while suppressing the non-stationary noise, especially the transient noise. Compared to conventional NS methods, DNN NS methods may work more effectively under non-stationary noises by learning the noises' temporal-frequency characteristics. However, most DNN methods are challenging to be implemented on mobile devices due to their heavy computation complexity. Indeed, even a few low-complexity DNN methods are proposed for real-time purposes, the robustness and the generalization degrade for different types of noise. This paper proposes a single channel DNN-based NS method for transient noise with low computation complexity. The proposed method enhanced the signal-to-noise ratio (SNR) while minimizing the speech’s distortion, resulting in a superior improvement of the speech quality over different noise types, including transient noise.

You must be logged in to download paper. Click here to login