An Acoustic-Based Recognition Algorithm for the Unreleased Braking of Railway Wagons in Marshalling Yards

Abstract

The abnormal braking of wagons is a challenging safety problem for operators at railway marshalling yard. This paper develops an acoustic-based technology to detect the unreleased braking of wagons during the uncoupling operation. Experiments have been conducted to collect the acoustic waves of wagons abnormal braking, as well as the background sounds like train whistling and wheel vibration. Before data collection, a wayside recording system and an experimental train composed of 5 different wagons have been prepared in the marshalling yard. The recognition algorithm consists of the fast Fourier transform (FFT), feature extraction, template matching and support vector machine (SVM) classification. Based on the sample data of different acoustic waves, the FFT is firstly performed to obtain the frequency spectrum from original time-domain signals. Then the major spectrum features of different sounds are carefully extracted for SVM training through a newly-devised algorithm, where the features include the spectrum center, spectrum flux, energy peak and corresponding frequency. During the SVM training, classifiers are designed under oneagainst-one strategy to guarantee the recognition accuracy. Given a test data, at most 3 SVM classifiers will be activated according to the decision matrix of template matching. Meanwhile, rules have been made to regulate the classification result considering different activation cases. Finally, a case study of all 12 sound categories has been performed to illustrate the application of proposed algorithm. Results show that the acoustic-based recognition algorithm is indeed reliable to identify wagons unreleased braking, with the global warning accuracy over 98%.

A study of sound recognition algorithm for power plant equipment fusing MFCC and IMFCC features

“…Where, ( ) x m represents the power plant equipment sound sampling sequence, and ( ) h n represents the window function. I In the above equation, firstly, the individual values of the collected time domain waveform of the power plant equipment sound signal are squared out, and then different short-time sequences are selected in turn using a certain moving window h(n-m), and then the squared values of these individual segments are selected and summed up to obtain the final shorttime energy sequence [10][11][12] .…”

“…The maximum value of the posterior probability can be obtained by finding ( | ) i p X  , so that the recognition result of the sound of the power plant equipment can be expressed as the formula (12).…”

Detecção De Vazamentos De Fluidos De Freios a Ar Em Vagões Do Tipo Gôndola Através Do Sinal Acústico: Um Modelo De Classificação De Falhas

“…Já [Ye et al 2020], desenvolveu uma pesquisa onde os sons produzidos pela frenagem dos vagões ferroviários serviram de entrada para um modelo de detecção de freios aplicados. Um dispositivo instalado ao lado da linha férrea, a princípio isolada para o estudo, gravava em formato waveform o som emitido pelas pás de freio em contato com as rodas dos trens no momento da aplicação e liberação dos freios.…”

Powering the WSN Node for Monitoring Rail Car Parameters, Using a Piezoelectric Energy Harvester

“…In the case of ground-based systems, the energy to power them is drawn from the power grid [3] or battery [4]; in some systems, the energy is transmitted via fiber optic link [5]. However, some ground-based systems use energy harvesting to power the nodes that monitor railroad infrastructure [6].…”