scholarly journals A Deep Feature Learning Method for Drill Bits Monitoring Using the Spectral Analysis of the Acoustic Signals

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2634 ◽  
Author(s):  
Caleb Vununu ◽  
Kwang-Seok Moon ◽  
Suk-Hwan Lee ◽  
Ki-Ryong Kwon
Keyword(s):  
Power Spectrum ◽  
Feature Learning ◽  
Final Diagnosis ◽  
Extraction Process ◽  
Drill Bits ◽  
High Discrimination ◽  
Convolutional Autoencoder ◽  
Spectrum Density ◽  
High Level ◽  
Nonlinear Classifier

Machine fault diagnosis (MFD) has gained an important enthusiasm since the unfolding of the pattern recognition techniques in the last three decades. It refers to all of the studies that aim to automatically detect the faults on the machines using various kinds of signals that they can generate. The present work proposes a MFD system for the drilling machines that is based on the sounds they produce. The first key contribution of this paper is to present a system specifically designed for the drills, by attempting not only to detect the faulty drills but also to detect whether the sounds were generated during the active or the idling stage of the whole machinery system, in order to provide a complete remote control. The second key contribution of the work is to represent the power spectrum of the sounds as images and apply some transformations on them in order to reveal, expose, and emphasize the health patterns that are hidden inside them. The created images, the so-called power spectrum density (PSD)-images, are then given to a deep convolutional autoencoder (DCAE) for a high-level feature extraction process. The final step of the scheme consists of adopting the proposed PSD-images + DCAE features as the final representation of the original sounds and utilize them as the inputs of a nonlinear classifier whose outputs will represent the final diagnosis decision. The results of the experiments demonstrate the high discrimination potential afforded by the proposed PSD-images + DCAE features. They were also tested on a noisy dataset and the results show their robustness against noises.

scholarly journals A New Insight to Vibration Characteristics of Spans under Random Moving Load: Case Study of 38 Bridges in Ho Chi Minh City, Vietnam

2020 ◽  
Vol 2020 ◽  
pp. 1-20
Author(s):  
Thanh Q. Nguyen ◽  
Thao D. Nguyen ◽  
Lam Q. Tran ◽  
Nhi K. Ngo
Keyword(s):  
Power Spectrum ◽  
Moving Load ◽  
Power Spectrum Density ◽  
Bending Vibration ◽  
Operational Process ◽  
Torsion Vibration ◽  
Spectrum Density ◽  
Vibration Tests ◽  
High Level

We propose a novel representative power spectrum density as a specific characteristic for showing responses of spans during a long operational period. The idea behind this method is to use the representative power spectrum density as a powerful tool to evaluate the stiffness decline of spans during their operation period. In addition, a new measurement method has been introduced to replace the traditional method of monitoring the health conditions of bridges through a periodic measurement technique. This helps to reduce costs when carrying out testing bridges. Besides, the proposed approach can be widely applied not only in Vietnam but also in many other underprivileged countries around the world. Obtained results show that, during the operational process of spans, there is not only a pure vibration evaluation such as bending vibration and torsion vibration tests but also a combination of various vibration types including bending-torsion vibration or high-level vibrations like first-mode bending and first-mode torsion. Depending on each type of structure and material properties, different types of vibrations will appear more or less during the operational process of spans under a random moving load. Furthermore, the representative power spectrum density is also suitable for evaluating and determining many different fundamental vibrations through the same measurement time as well as various measurement times.

Orientation holes positioning of printed board based on LS-Power spectrum density algorithm

2018 ◽  
Vol 35 (3-4) ◽  
pp. 277-288
Author(s):  
Xiaxia ZENG ◽  
Zhenhua SONG ◽  
Wenzhong LIN ◽  
Haibo LUO
Keyword(s):  
Power Spectrum ◽  
Power Spectrum Density ◽  
Spectrum Density

Clinical and epidemiological characteristics of chickenpox in the adult population at the present stage

2020 ◽  
pp. 17-24
Author(s):  
Ekaterina Peredelskaya ◽  
Tatyana Safyanova ◽  
Mikhail Druchanov
Keyword(s):  
Health Care ◽  
Adult Population ◽  
Final Diagnosis ◽  
Health Care Institution ◽  
Federal State ◽  
Economic Damage ◽  
Clinical Hospital ◽  
Care Institution ◽  
High Level ◽  
Epidemiological Characteristics

Chickenpox is an urgent problem, as it is widely spread with a high level of morbidity and an increasing share in the structure of the General infectious pathology with significant economic damage. The aim of the study is to study the epidemiological and clinical features of chickenpox in adults hospitalized in Krai government-owned publicy funded health care institution «City clinical hospital No. 5, Barnaul» for the period 2008‑2018. Content analysis included statistical reporting forms No. 2 of Federal state statistical supervision «Data on infectious and parasitic diseases» in the city of Barnaul during the period 2008‑2018 of medical archival documents adult infectious Department Krai government-owned publicy funded health care institution «City clinical hospital №5, Barnaul» for the same period. Data processing was performed using calculation of intensive and extensive indicators, calculation of the arithmetic mean (X) and standard error of the average (m). Calculations were made using the STATISTICA-10 program. Consistently high rates were recorded, with an average of 64.32 ± 3.46 per 100,000 population. The percentage of hospitalized adults averaged 18.5% during the study period. Adults aged 18‑30 were more likely to be admitted to the hospital (90.3%); 41.6% were students. Adults with moderate severity were hospitalized more often (70.6%); 7 patients (1.3%) had complications: aphthous stomatitis (3 cases), pustulosis (2 cases), and pneumonia (2 cases). Patients with severe severity of the disease accounted for 2.4%, the premorbid background was burdened in 48% (HIV infection, tuberculosis). In 35% of patients with severe severity, the final diagnosis of Herpes zoster was made, all patients older than 40 years, stayed in the hospital for 20‑25 days.

Random Response Analysis of a Large-Size Cooling Tower Subjected to the Stationary Earthquake Motion

2013 ◽  
Vol 423-426 ◽  
pp. 1589-1593
Author(s):  
Jia Ning Zhu ◽  
Ya Zhou Xu ◽  
Guo Liang Bai ◽  
Rui Wen Li
Keyword(s):  
Power Spectrum ◽  
Random Vibration ◽  
Cooling Tower ◽  
Response Spectrum ◽  
Power Spectrum Density ◽  
Random Response ◽  
Large Size ◽  
Earthquake Motion ◽  
Spectrum Density ◽  
Random Vibration Theory

The response of a large-size cooling tower with 250m high subjected to the seismic action are investigated by both random vibration theory and response spectrum method. Shell element is taken to model the tower body, and beam element is used for the circular foundation and supporting columns. The earthquake motion input is a colored filtered white noise model and mode superposition method is adopted to analyze the random response of the large-size cooling tower. The paper presents the power spectrum density functions (PDF) and standard deviation of the displacement of the top and characteristic node, and the analysis results indicate that the results of the stationary random vibration theory and the response spectrum method are the same order of magnitude. The power spectrum density function of the bottom node stress is obviously bigger than the one at the top and the throat, and the random response of meridonal stress is dominated at the top. In addition, the peak frequency position of the power spectrum density function is different from the corresponding stress.

The Time Domain Simulation of Non-Stationary Road Roughness

2013 ◽  
Vol 423-426 ◽  
pp. 1238-1242
Author(s):  
Hao Wang ◽  
Xiao Mei Shi
Keyword(s):  
Power Spectrum ◽  
Time Domain ◽  
Ride Comfort ◽  
Time History ◽  
Random Excitation ◽  
Power Spectrum Density ◽  
The Road ◽  
Road Roughness ◽  
Spectrum Density ◽  
History Of

The input of road roughness, which affects the ride comfort and the handling stability of vehicle, is the main excitation for the running vehicle. The time history of the road roughness was researched with the random phases, based on the stationary power spectrum density of the road roughness determined by the standards. Through the inverse Fourier transform, the random phases can be used to get the road roughness in time domain, together with the amplitude. Then, the time domain simulation of the non-stationary random excitation when the vehicle ran at the changing speed, would also be studied based on the random phases. It is proved that the random road excitation for the vehicle with the changing speed is stationary modulated evolution random excitation, and its power spectrum density is the stationary modulated evolutionary power spectrum density. And the numerical results for the time history of the non-stationary random inputs were also provided. The time history of the non-stationary random road can be used to evaluate the ride comfort of the vehicle which is running at the changing speed.

scholarly journals D-dCNN: A Novel Hybrid Deep Learning-Based Tool for Vibration-Based Diagnostics

Energies ◽  
2021 ◽  
Vol 14 (17) ◽  
pp. 5286 ◽  
Author(s):  
Ugochukwu Ejike Akpudo ◽  
Jang-Wook Hur
Keyword(s):  
Neural Network ◽  
Feature Learning ◽  
Ease Of Use ◽  
Fault Detection And Isolation ◽  
Vibration Signals ◽  
One Dimensional ◽  
Real Time Applications ◽  
Equipment State ◽  
High Level

This paper develops a novel hybrid feature learner and classifier for vibration-based fault detection and isolation (FDI) of industrial apartments. The trained model extracts high-level discriminative features from vibration signals and predicts equipment state. Against the limitations of traditional machine learning (ML)-based classifiers, the convolutional neural network (CNN) and deep neural network (DNN) are not only superior for real-time applications, but they also come with other benefits including ease-of-use, automated feature learning, and higher predictive accuracies. This study proposes a hybrid DNN and one-dimensional CNN diagnostics model (D-dCNN) which automatically extracts high-level discriminative features from vibration signals for FDI. Via Softmax averaging at the output layer, the model mitigates the limitations of the standalone classifiers. A diagnostic case study demonstrates the efficiency of the model with a significant accuracy of 92% (F1 score) and extensive comparative empirical validations.

Sign in / Sign up

Export Citation Format

Share Document