scholarly journals Towards a Diagnostic Tool for Diagnosing Joint Pathologies: Supervised Learning of Acoustic Emission Signals

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8091
Author(s):  
Khadijat A. Olorunlambe ◽  
Zhe Hua ◽  
Duncan E. T. Shepherd ◽  
Karl D. Dearn
Keyword(s):  
Acoustic Emission ◽  
Supervised Learning ◽  
Diagnostic Tool ◽  
Back Propagation ◽  
Principal Component ◽  
Bp Network ◽  
Nearest Neighbours ◽  
Human Joints ◽  
Exciting Development ◽  
Ae Signals

Acoustic emission (AE) testing detects the onset and progression of mechanical flaws. AE as a diagnostic tool is gaining traction for providing a tribological assessment of human joints and orthopaedic implants. There is potential for using AE as a tool for diagnosing joint pathologies such as osteoarthritis and implant failure, but the signal analysis must differentiate between wear mechanisms—a challenging problem! In this study, we use supervised learning to classify AE signals from adhesive and abrasive wear under controlled joint conditions. Uncorrelated AE features were derived using principal component analysis and classified using three methods, logistic regression, k-nearest neighbours (KNN), and back propagation (BP) neural network. The BP network performed best, with a classification accuracy of 98%, representing an exciting development for the clustering and supervised classification of AE signals as a bio-tribological diagnostic tool.

scholarly journals A Principal Component Analysis of Acoustic Emission Signals from a Landing Gear Component

2008 ◽  
Vol 13-14 ◽  
pp. 41-47 ◽  
Author(s):  
Rhys Pullin ◽  
Mark J. Eaton ◽  
James J. Hensman ◽  
Karen M. Holford ◽  
Keith Worden ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Acoustic Emission ◽  
Background Noise ◽  
Principal Component ◽  
Component Analysis ◽  
Landing Gear ◽  
Fracture Detection ◽  
Artificial Fracture ◽  
High Level ◽  
Ae Signals

This work forms part of a larger investigation into fracture detection using acoustic emission (AE) during landing gear airworthiness testing. It focuses on the use of principal component analysis (PCA) to differentiate between fracture signals and high levels of background noise. An artificial acoustic emission (AE) fracture source was developed and additionally five sources were used to generate differing AE signals. Signals were recorded from all six artificial sources in a real landing gear component subject to no load. Further to this, artificial fracture signals were recorded in the same component under airworthiness test load conditions. Principal component analysis (PCA) was used to automatically differentiate between AE signals from different source types. Furthermore, successful separation of artificial fracture signals from a very high level of background noise was achieved. The presence of a load was observed to affect the ultrasonic propagation of AE signals.

scholarly journals Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors

Metals ◽  
2018 ◽  
Vol 8 (8) ◽  
pp. 593 ◽  
Author(s):  
Qiangjian Gao ◽  
Yingyi Zhang ◽  
Xin Jiang ◽  
Haiyan Zheng ◽  
Fengman Shen
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Influence Factors ◽  
Principal Component ◽  
Bp Network ◽  
Input Variables ◽  
Artificial Neural Network Ann

The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process.

Sensing Analysis of Aluminum Alloy Materials Based on Chemical Acoustic Emission Signals

2010 ◽  
Vol 139-141 ◽  
pp. 176-179
Author(s):  
Zhong Cao ◽  
Ju Lan Zeng ◽  
Yi Min Dai ◽  
Xun Li ◽  
Dong Mei Luo
Keyword(s):  
Acoustic Emission ◽  
Ph Value ◽  
Power Spectra ◽  
Principal Component ◽  
Al Alloy ◽  
Buffer Solution ◽  
Acid Reaction ◽  
Metal Materials ◽  
Reaction Processes ◽  
Ae Signals

The frequency domain power spectra of acoustic emission (AE) signals from different metal-acid reaction processes such as 6111 Al-alloy-hydrochloric acid (HCl) and 7070 Al-alloy-HCl for evolving hydrogen gases were obtained by fast Fourier transform (FFT) program and used for chemical analysis of different metal materials. Averaged power spectra from these processes and their corresponding characteristics were extracted. The characteristic AE frequency signals could be used for chemical pattern recognition of different metal materials like 6111 and 7050 aluminum alloys from the metal-acid reaction processes, that the principal component analysis (PCA) with appropriate frequency selection procedure gave a satisfactory classification with a correct rate of 78.1%. The back-propagation (BP) algorithm of artificial neural network (ANN) could give better recognition of AE signals for 6111 and 7050 alloys with a correct rate of 100%. Moreover, the AE energetic parameters are linearly correlated with the pH value of the acidic buffer solution, which opens a new possibility for quantitatively analytical application of AE signals on metal materials.

scholarly journals Prediction of Mumps Incidence Trend in China Based on Differ-ence Grey Model and Artificial Neural Network Learning

2021 ◽  
Author(s):  
Jin Jia ◽  
Mingming Liu ◽  
Zhigang Xue ◽  
Zhe Wang ◽  
Yu Pan
Keyword(s):  
Dimension Reduction ◽  
Incidence Rate ◽  
Prediction Models ◽  
Back Propagation ◽  
Principal Component ◽  
Small Error ◽  
Grey Model ◽  
Bp Network ◽  
Neural Network Learning ◽  
Advantages And Disadvantages

Background: We aimed to compare the prediction efficiency of back propagation (BP) network and grey model (GM) (1.1) for mumps infectious diseases and compare the application effect of the two models. Methods: By calculating the average incidence rate of mumps in January 2014 -2016, we conducted the modeling of the BP time series, GM (1,1) grey model and the combination models of them, and predicted the incidence rate in June 2016 in comparison with the actual one. We compared the quarterly incidence rate to test the two prediction models, and compared the advantages and disadvantages of these models. Results: R value of BP model was 68.45%, for GM (1,1) was 58.49%, and for combined forecasting model was 86.95%. We used the principal component analysis clustering method to control the samples, and found that the samples were close to the population mean. We found that the GM (1.1) model was more suitable for the prediction of mumps infection mode. We carried out dimension reduction analysis on the model data, and the accuracy of the data after dimension reduction is within the range of Da. For the discrete degree of the data in the combined model, matlab pipeline was used to verify the reliability of the data and results. By calculation after manifold optimization small error probability was P=0.875 and semi mean relative error 2.43%. Conclusion: BP, GM (1,1) is a better method for modeling the epidemic trend of mumps in China, but the efficiency of prediction is not as high as the combination of them.

scholarly journals A New Feature Selection Algorithm Based on the Mean Impact Variance

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Weidong Cheng ◽  
Tianyang Wang ◽  
Weigang Wen ◽  
Jianyong Li ◽  
Robert X. Gao
Keyword(s):  
Feature Selection ◽  
Back Propagation ◽  
Feature Selection Method ◽  
Principal Component ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Bp Network ◽  
The Mean ◽  
New Feature ◽  
Artificial Neural Network Ann

The selection of fewer or more representative features from multidimensional features is important when the artificial neural network (ANN) algorithm is used as a classifier. In this paper, a new feature selection method called the mean impact variance (MIVAR) method is proposed to determine the feature that is more suitable for classification. Moreover, this method is constructed on the basis of the training process of the ANN algorithm. To verify the effectiveness of the proposed method, the MIVAR value is used to rank the multidimensional features of the bearing fault diagnosis. In detail, (1) 70-dimensional all waveform features are extracted from a rolling bearing vibration signal with four different operating states, (2) the corresponding MIVAR values of all 70-dimensional features are calculated to rank all features, (3) 14 groups of 10-dimensional features are separately generated according to the ranking results and the principal component analysis (PCA) algorithm and a back propagation (BP) network is constructed, and (4) the validity of the ranking result is proven by training this BP network with these seven groups of 10-dimensional features and by comparing the corresponding recognition rates. The results prove that the features with larger MIVAR value can lead to higher recognition rates.

Application of Machine Learning in Animal Disease Analysis and Prediction

2020 ◽  
Vol 15 ◽  
Author(s):  
Shuwen Zhang ◽  
Qiang Su ◽  
Qin Chen
Keyword(s):  
Machine Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Clustering Algorithm ◽  
Principal Component ◽  
Support Vector ◽  
Animal Disease ◽  
Human Beings ◽  
Animal Diseases ◽  
Disease Analysis

Abstract: Major animal diseases pose a great threat to animal husbandry and human beings. With the deepening of globalization and the abundance of data resources, the prediction and analysis of animal diseases by using big data are becoming more and more important. The focus of machine learning is to make computers learn how to learn from data and use the learned experience to analyze and predict. Firstly, this paper introduces the animal epidemic situation and machine learning. Then it briefly introduces the application of machine learning in animal disease analysis and prediction. Machine learning is mainly divided into supervised learning and unsupervised learning. Supervised learning includes support vector machines, naive bayes, decision trees, random forests, logistic regression, artificial neural networks, deep learning, and AdaBoost. Unsupervised learning has maximum expectation algorithm, principal component analysis hierarchical clustering algorithm and maxent. Through the discussion of this paper, people have a clearer concept of machine learning and understand its application prospect in animal diseases.

scholarly journals Analysis of Acoustic Emission (AE) Signals for Quality Monitoring of Laser Lap Microwelding

2021 ◽  
Vol 11 (15) ◽  
pp. 7045
Author(s):  
Ming-Chyuan Lu ◽  
Shean-Juinn Chiou ◽  
Bo-Si Kuo ◽  
Ming-Zong Chen
Keyword(s):  
Stainless Steel ◽  
Acoustic Emission ◽  
Frequency Domain ◽  
Monitoring System ◽  
Welding Quality ◽  
Steel Sheets ◽  
Signal Features ◽  
Ae Signal ◽  
Laser Microwelding ◽  
Ae Signals

In this study, the correlation between welding quality and features of acoustic emission (AE) signals collected during laser microwelding of stainless-steel sheets was analyzed. The performance of selected AE features for detecting low joint bonding strength was tested using a developed monitoring system. To obtain the AE signal for analysis and develop the monitoring system, lap welding experiments were conducted on a laser microwelding platform with an attached AE sensor. A gap between the two layers of stainless-steel sheets was simulated using clamp force, a pressing bar, and a thin piece of paper. After the collection of raw signals from the AE sensor, the correlations of welding quality with the time and frequency domain features of the AE signals were analyzed by segmenting the signals into ten 1 ms intervals. After selection of appropriate AE signal features based on a scatter index, a hidden Markov model (HMM) classifier was employed to evaluate the performance of the selected features. Three AE signal features, namely the root mean square (RMS) of the AE signal, gradient of the first 1 ms of AE signals, and 300 kHz frequency feature, were closely related to the quality variation caused by the gap between the two layers of stainless-steel sheets. Classification accuracy of 100% was obtained using the HMM classifier with the gradient of the signal from the first 1 ms interval and with the combination of the 300 kHz frequency domain signal and the RMS of the signal from the first 1 ms interval.

scholarly journals Acoustic Emission Testing and Ib-Value Analysis of Ultraviolet Light-Irradiated Fiber Composites

2021 ◽  
Vol 11 (14) ◽  
pp. 6550
Author(s):  
Doyun Jung ◽  
Wonjin Na
Keyword(s):  
Acoustic Emission ◽  
Irradiation Time ◽  
Tensile Load ◽  
Failure Behavior ◽  
Value Analysis ◽  
Emission Testing ◽  
Final Failure ◽  
Acoustic Emission Testing ◽  
Woven Glass Fiber ◽  
Ae Signals

The failure behavior of composites under ultraviolet (UV) irradiation was investigated by acoustic emission (AE) testing and Ib-value analysis. AE signals were acquired from woven glass fiber/epoxy specimens tested under tensile load. Cracks initiated earlier in UV-irradiated specimens, with a higher crack growth rate in comparison to the pristine specimen. In the UV-degraded specimen, a serrated fracture surface appeared due to surface hardening and damaged interfaces. All specimens displayed a linearly decreasing trend in Ib-values with an increasing irradiation time, reaching the same value at final failure even when the starting values were different.

scholarly journals Identification of Pilots’ Fatigue Status Based on Electrocardiogram Signals

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3003
Author(s):  
Ting Pan ◽  
Haibo Wang ◽  
Haiqing Si ◽  
Yao Li ◽  
Lei Shang
Keyword(s):  
Back Propagation ◽  
Principal Component ◽  
Back Propagation Neural Network ◽  
Practical Significance ◽  
Support Vector ◽  
State Identification ◽  
Feature Parameter ◽  
The Time Domain ◽  
Pilot Fatigue ◽  
Identification Model

Fatigue is an important factor affecting modern flight safety. It can easily lead to a decline in pilots’ operational ability, misjudgments, and flight illusions. Moreover, it can even trigger serious flight accidents. In this paper, a wearable wireless physiological device was used to obtain pilots’ electrocardiogram (ECG) data in a simulated flight experiment, and 1440 effective samples were determined. The Friedman test was adopted to select the characteristic indexes that reflect the fatigue state of the pilot from the time domain, frequency domain, and non-linear characteristics of the effective samples. Furthermore, the variation rules of the characteristic indexes were analyzed. Principal component analysis (PCA) was utilized to extract the features of the selected feature indexes, and the feature parameter set representing the fatigue state of the pilot was established. For the study on pilots’ fatigue state identification, the feature parameter set was used as the input of the learning vector quantization (LVQ) algorithm to train the pilots’ fatigue state identification model. Results show that the recognition accuracy of the LVQ model reached 81.94%, which is 12.84% and 9.02% higher than that of traditional back propagation neural network (BPNN) and support vector machine (SVM) model, respectively. The identification model based on the LVQ established in this paper is suitable for identifying pilots’ fatigue states. This is of great practical significance to reduce flight accidents caused by pilot fatigue, thus providing a theoretical foundation for pilot fatigue risk management and the development of intelligent aircraft autopilot systems.

Acoustic Emission Monitoring of Leaks in Pipes for Transport of Liquid and Gaseous Media: A Model Experiment

2006 ◽  
Vol 13-14 ◽  
pp. 351-356 ◽  
Author(s):  
Andreas J. Brunner ◽  
Michel Barbezat
Keyword(s):  
Acoustic Emission ◽  
Model Experiment ◽  
Structural Integrity ◽  
Fiber Composite ◽  
Leak Testing ◽  
Pipe Segment ◽  
Potential Applications ◽  
Gaseous Media ◽  
The Media ◽  
Ae Signals

In order to explore potential applications for Active Fiber Composite (AFC) elements made from piezoelectric fibers for structural integrity monitoring, a model experiment for leak testing on pipe segments has been designed. A pipe segment made of aluminum with a diameter of 60 mm has been operated with gaseous (compressed air) and liquid media (water) for a range of operating pressures (between about 5 and 8 bar). Artificial leaks of various sizes (diameter) have been introduced. In the preliminary experiments presented here, commercial Acoustic Emission (AE) sensors have been used instead of the AFC elements. AE sensors mounted on waveguides in three different locations have monitored the flow of the media with and without leaks. AE signals and AE waveforms have been recorded and analysed for media flow with pressures ranging from about 5 to about 8 bar. The experiments to date show distinct differences in the FFT spectra depending on whether a leak is present or not.

Sign in / Sign up

Export Citation Format

Share Document