Investigation of the feasibility of using microphone arrays in monitoring machining conditions

Shaffer, Derek; Ragai, Ihab; Danesh-Yazdi, Amir H.; Loker, David

doi:10.1016/j.mfglet.2017.12.008

Cited by 14 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Accordingly, the AE signal processing methods can be classified into three categories: (i) signal processing, (ii) feature extraction, and (iii) pattern recognition. The most important and widely used (Qin et al, 2018) × (Karakus & Perez, 2014) × × × × (Bastari et al, 2011) × (Parsian et al, 2017) × × × (Marinescu & Axinte, 2009) × × (Xiao, Hurich et al, 2018) × (Li et al, 2018) × × (Buj-Corral et al,, 2018) × (Shaffer et al,, 2018) × × × (Wang et al, 2017) × × (Rivero et al, 2008) × (Flegner et al, 2014) × (Feng & Yi, 2017) × (Yari et al, 2017) × (Yari & Bagherpour, 2018 (a&b)) × (Shreedharan et al, 2014) × (Kostur & Futo, 2007) × ( Kawamura et al, 2017) × (Pedrayes et al, 2018) × × (Gradl et al, 2012) × × × (Vardhan et al, 2009) × × × (Beheshtizadeh et al, 2017) × (Miklusova et al, 2006) × × × × (Goyal & Pabla, 2016) × (Liew & Wang, 1998) × × (Kong et al, 2015) × (Jain et al, 2001) The Mining-Geology-Petroleum Engineering Bulletin and the authors ©, 2019, pp. 19-32, DOI: 10.17794/rgn.2019.4.3 methods of the first category (signal processing) include: time series statistical models, Short Time Fourier Transform (STFT), Fast Fourier Transform (FFT), Wavelet Packet Decomposition (WPD), Hilbert-Huang transform (HHT), Wigner-Ville distribution, signal spectrum analysis, Adaptive Line Enhancer (ALE), wavelet transform, and the Peak-Hold-Down-Sample (PHDS) algorithm.…”

Section: Acoustic Signal Processing Feature Extraction and Pattern Rmentioning

confidence: 99%

Application of Acoustic Emission (Ae) in Mining and Earth Sciences: A Review

Khoshouei

Bagherpour

2019

MGPB

View full text Add to dashboard Cite

One of the most important products of the majority of tools, processes and, phenomena in mining engineering and earth sciences are high-frequency elastic waves, often referred to as acoustic waves. These acoustic waves can be a useful tool for prediction and measurement, monitoring and diagnosis. Due to the importance of engineering activities that should be specific, measurable, available, reliable and time-based (SMART), Acoustic Emission (AE) techniques can be integrated into engineering operations such as excavation to give exact estimations or simplify some aspects of investigations. Hence, these techniques are expected to play an increasing role in the detection, monitoring, and measurement in engineering applications. With the development of acoustic signal processing methods in earth sciences and the growing need for accurate, fast, and cost-effective prediction, monitoring and measurement methods, AE tools and techniques are expected to turn into powerful alternatives to current methods. The purpose of this paper is to review the application of the acoustic methods as a tool in various projects. For this purpose, the application of AE methods has been reviewed in different fields related to earth sciences including mining engineering, drilling engineering, geology, petroleum engineering, and other related fields. According to the purpose of using these methods, the application of AE is divided into three groups: prediction and estimation, monitoring and performance assessment, and detection. The use of AE methods, among other laboratory or in-situ methods, is very fast and accurate, and by only installing specific sensors with data logging equipment, it has been able to process and analyse data online and remotely. Finally, the possibility of using AE techniques in design and calculating in various projects and as a tool for decision making was evaluated.

show abstract

Section: Acoustic Signal Processing Feature Extraction and Pattern Rmentioning

confidence: 99%

Application of Acoustic Emission (Ae) in Mining and Earth Sciences: A Review

Khoshouei

Bagherpour

2019

MGPB

View full text Add to dashboard Cite

show abstract

“…В работе Shaffer D. и др. акустические сигналы были исследованы как способ контроля работы технологического оборудования [10]. Экспериментальным путем с различными режимами резания были статистически определены математические модели, показывающие изменение акустического сигнала для концевого фрезерования с одной режущей кромкой.…”

Section: Introductionunclassified

Experimental study of the dynamics of the machining process by ball-end mills

Gimadeev¹,

Li²,

Berkun³

et al. 2023

Metal Working and Material Science

View full text Add to dashboard Cite

Introduction. Due to a significant number of factors affecting the change in the properties of a dynamic system, excessively conservative processing conditions are chosen to ensure the high quality of the resulting product. This limits the efficiency of the process and leads to an increase in the cost of production. Accordingly, modern approaches are needed that will allow diagnosing the current state of processing and making timely decisions to replace the tool, correct or change the control program. The significance of the ongoing research is to propose a real-time monitoring approach to milling control to identify emerging processing errors, predict potential problems and improve uptime. Subject. The paper discusses the features of the real-time monitoring system during mechanical processing with a single- and double-edge cutting tool, taking into account acoustic wave filtering, minimizing surface roughness. The purpose of the work is to determine the effect of the inclination orientation of the ball-end tool on the surface roughness value using real-time monitoring during milling on CNC process equipment. Methods. The study provides methods of correlation and regression analysis. The calculated data were obtained by means of vibroacoustic diagnostics and measured in the range of values of the variable angle of inclination of the surface for single- and double-edge cutting tool based on the provisions of the theory of oscillations and vibroacoustic diagnostics, cutting theory, digital processing and digital filtering of signals. Results and discussions. Experimental data obtained during machining made it possible to determine that an increase in the angle of inclination of a single-edge cutting tool has practically no effect on the change in the amplitude parameters of roughness. The values of vibroacoustic diagnostics and roughness, when using a double-edge ball-end tool, show a consistent picture with the effects created by the angles of inclination and advance. The obtained solutions to the problems of monitoring and analyzing the roughness parameters can significantly reduce the amount of experimental research and clarify the idea of the practical implementation of the method of acoustic monitoring of the cutting process.

show abstract

“…Ambient sounds from other machinery and humans can be mixed to the recorded sounds, making it difficult to find the acoustic location. Placing a spherical array of 32 microphones isolated sounds of milling operation from nearby machines (Shaffer et al, 2018). However, if a sensor is attached to the sound source to catch the internal dynamics, less sensors would be used for acoustic location and ambient noise reduction.…”

Section: Introductionmentioning

confidence: 99%

Autoencoder-based anomaly detection of industrial robot arm using stethoscope based internal sound sensor

et al. 2021

View full text Add to dashboard Cite

Sound and vibration analysis are prominent tools for machine health diagnosis. Especially, neural network (NN) strategies have focused on finding complex and nonlinear relationships between the sensor signal and the machine status to detect machine faults. However, it is difficult to collect enough amount of fault data as much as normal status data for training general NN models. To resolve the issue, this paper proposes the autoencoder-based anomaly detection framework for industrial robot arms using an internal sound sensor. The autoencoder uses signals in the normal state of the robots for training the model. It reconstructs the input signals as output, and anomalous states are found from high reconstruction error. Two stethoscopes were attached to the surface of the robot joint as sensors, and the sounds were recorded by USB microphone attached to the outlet of the stethoscopes. Features were extracted from STFT spectrogram images of the gathered sound, then used to train and test an autoencoder model. The reconstruction errors of the autoencoder were compared to distinguish the abnormal status from normal one. The experimental results suggest that the stethoscopes prevent the interference of noise, and the collected sound signals can be utilized for detecting machine anomalies.

show abstract

Investigation of the feasibility of using microphone arrays in monitoring machining conditions

Cited by 14 publications

References 4 publications

Application of Acoustic Emission (Ae) in Mining and Earth Sciences: A Review

Application of Acoustic Emission (Ae) in Mining and Earth Sciences: A Review

Experimental study of the dynamics of the machining process by ball-end mills

Autoencoder-based anomaly detection of industrial robot arm using stethoscope based internal sound sensor

Contact Info

Product

Resources

About