scholarly journals A New Transfer Learning Ensemble Model with New Training Methods for Gear Wear Particle Recognition

2022 ◽  
Vol 2022 ◽  
pp. 1-10
Author(s):  
Chunhua Zhao ◽  
zhangwen Lin ◽  
Jinling Tan ◽  
Hengxing Hu ◽  
Qian Li
Keyword(s):  
Transfer Learning ◽  
Wear Particle ◽  
Experimental Results ◽  
The Other ◽  
Particle Identification ◽  
Lubricating Oil ◽  
Support Vector ◽  
Training Methods ◽  
Wear Particles ◽  
Feature Expression

Aiming at solving the acquisition problems of wear particle data of large-modulus gear teeth and few training datasets, an integrated model of LCNNE based on transfer learning is proposed in this paper. Firstly, the wear particles are diagnosed and classified by connecting a new joint loss function and two pretrained models VGG19 and GoogLeNet. Subsequently, the wear particles in gearbox lubricating oil are chosen as the experimental object to make a comparison. Compared with the other four models’ experimental results, the model superiority in wear particle identification and classification is verified. Taking five models as feature extractors and support vector machines as classifiers, the experimental results and comparative analysis reveal that the LCNNE model is better than the other four models because its feature expression ability is stronger than that of the other four models.

scholarly journals Quantitative Measuring Analysis Method and Mechanism of Wear Particle Settlement

2021 ◽  
Vol 252 ◽  
pp. 03037
Author(s):  
Kaituo Zhang ◽  
Zhiyong Lv
Keyword(s):  
Specific Gravity ◽  
Magnetic Induction ◽  
Wear Particle ◽  
Lubricating Oil ◽  
Precipitation Process ◽  
Wear Particles ◽  
Analysis Method ◽  
Abrasive Particles ◽  
Initial Stage ◽  
Precipitation Analysis

The size and distribution of wear particle in lubricating oil, as important numerical information available in ferrography, is one of the key indexes in wear diagnosis. In this paper, a new method for measuring the size and distribution of abrasive particles is proposed. First, all the abrasive fluid is left standing until all the abrasive particles are precipitated to the bottom. Then, the measuring container is inverted and the whole precipitation process of abrasive particles is recorded by magnetic induction instrument. And according to the precipitation analysis of the wear particle, the following results were obtained:1) At the initial stage of the particle settlement, the gravity, the buoyancy and the drag force of the oil achieve balance quickly, the time and distance of the wear particle moving at a constant velocity can be neglected. 2) The settling velocity is related to the diameter and specific gravity of the wear particle as well as the specific gravity and viscosity of the oil, the distribution of the wear particle is proportional to the square of the diameter of the particle, using the magnetic induction technology, the distribution of particle can be measured by settling time for different sizes of wear particles. 3) Measure the wear particle oil directly, there are different sizes of particles settlement in the bottom at the same time, which causes the difficulty in identifying the size of the particle settlement. The particle should be settled first, and then inverted, settling the particle in accordance with the order from large to small, which facilitates the measurement of different sizes of the particles, different times correspond to different sizes of the particles. 4) The bigger the particle is, the more accurate the measurement and counting is, the smaller the particle is, the bigger the error is.

scholarly journals A Partial Hierarchical Model for Online Low-Resolution Wear Particle Images Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xuxu Guo ◽  
Rui Tan ◽  
Mingyang Yang ◽  
Xinrong He ◽  
Jia Guo ◽  
...  
Keyword(s):  
Neural Network ◽  
Sliding Wear ◽  
Super Resolution ◽  
Wear Particle ◽  
Support Vector ◽  
Wear Particles ◽  
The Third ◽  
Online Recognition ◽  
New Feature ◽  
Particle Images

Wear particle image analysis is an effective method to detect wear condition of mechanical devices. However, the recognition accuracy and recognition efficiency for online wear particle automatic recognition are always mutual restricted because the online wear particle images have almost no texture information and lack clarity. Especially for confusing fatigue wear particles and sliding wear particles, the online recognition is a challenging task. Based on this requirement, a super-resolution reconstruct technique and partial hierarchical convolutional neural network, SR-PHnet, is proposed to classify wear particles in one step. The structure of this network is composed by three modules, one is super-resolution layer module, the second is convolutional neural network classifier module, and the third is support vector machine (SVM) classifier module. The classification result of the second module is partial input to the third module for precision classification of fatigue and sliding particles. In addition, a new feature of radial edge factor (REF) is put forward to target fatigue and sliding wear particles. The test result shows that the new feature has the capability to distinguish fatigue and sliding particles well and time saving. The comparison experiments of the convolution neural network (CNN) method, support vector machine method (SVM) with and without REF feature, and integrated model of back-propagation (BP) and CNN are produced. The comparison results show that the online recognition speed and online recognition rate of the proposed SR-PHnet model in this paper are both improved markedly, especially for fatigue and sliding wear particles.

Physical Activity Classification with Wearable Sensor Data in an eCoach Recommendation System (Preprint)

2021 ◽  
Author(s):  
Ayan Chatterjee
Keyword(s):  
Physical Activity ◽  
Transfer Learning ◽  
Sedentary Lifestyle ◽  
The Other ◽  
Sensor Data ◽  
Support Vector ◽  
Accuracy Score ◽  
Classification Models ◽  
Linear Kernel ◽  
Single Feature

UNSTRUCTURED Leading a sedentary lifestyle may cause numerous health problems. Therefore, sedentary lifestyle changes should be given priority to avoid severe damage. Research in eHealth can provide methods to enrich personal healthcare with Information and Communication Technologies (ICTs). An eCoach system may allow people to manage a healthy lifestyle with health state monitoring and personalized recommendations. Using machine learning (ML) techniques, this study investigated the possibility of classifying daily physical activity for adults into the following classes - sedentary, low active, active, active, highly active, and rigorous active. The daily total step count, total daily minutes of sedentary time, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) served as input for the classification models. We first used publicly available Fitbit data to build the classification models. Second, using the transfer learning approach, we re-used the top five best-performing models on a real dataset as collected from the MOX2-5 wearable medical-grade activity sensor. We found that ensemble ExtraTreesClassifier with an estimator value of 150 outperformed other classifiers with a mean accuracy score of 99.72% for single feature and support vector classifier (SVC) with “linear” kernel outpaced other classifiers with a mean accuracy score of 99.14% for five features, for the public Fitbit datasets. To demonstrate the practical usefulness of the classifiers, we conceptualized how the classifier model can be used in an eCoach prototype system to attain personalized activity goals (e.g., stay active for the entire week). After transfer learning, K-Nearest-Neighbor (KNN) outpaced the other four classifiers for a single feature, and SVC with a “linear” kernel outdid the other four classifiers for multiple features.

scholarly journals A Lubricating Oil Condition Monitoring System Based on Wear Particle Kinematic Analysis in Microfluid for Intelligent Aeroengine

Micromachines ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 748
Author(s):  
Zhenzhen Liu ◽  
Yan Liu ◽  
Hongfu Zuo ◽  
Han Wang ◽  
Hang Fei
Keyword(s):  
Condition Monitoring ◽  
Kinematic Analysis ◽  
Oil Quality ◽  
Particle Diameter ◽  
Wear Particle ◽  
Lubricating Oil ◽  
Wear Particles ◽  
Oil Viscosity ◽  
Monitoring Technology ◽  
Oil Monitoring

Lubricating oil monitoring technology is a commonly used method in aeroengine condition monitoring, which includes particle counting technology, as well as spectral and ferrography technology in offline monitoring. However, these technologies only analyze the characteristics of wear particles and rely on physical and chemical analysis techniques to monitor the oil quality. In order to further advance offline monitoring technology, this paper explores the potential role of differences in wear particle kinematic characteristics in recognizing changes in wear particle diameter and oil viscosity. Firstly, a kinematic force analysis of the wear particles in the microfluid was carried out. Accordingly, a microfluidic channel conducive to observing the movement characteristics of particles was designed. Then, the wear particle kinematic analysis system (WKAS) was designed and fabricated. Secondly, a real-time tracking velocity measurement algorithm was developed by using the Gaussian mixture model (GMM) and the blob-tracking algorithm. Lastly, the WKAS was applied to a pin–disc tester, and the experimental results show that there is a corresponding relationship between the velocity of the particles and their diameter and the oil viscosity. Therefore, WKAS provides a new research idea for intelligent aeroengine lubricating oil monitoring technology. Future work is needed to establish a quantitative relationship between wear particle velocity and particle diameter, density, and oil viscosity.

scholarly journals Monolingual Transfer Learning via Bilingual Translators for Style-Sensitive Paraphrase Generation

2020 ◽  
Vol 34 (05) ◽  
pp. 8042-8049
Author(s):  
Tomoyuki Kajiwara ◽  
Biwa Miura ◽  
Yuki Arase
Keyword(s):  
Machine Translation ◽  
Transfer Learning ◽  
State Of The Art ◽  
Experimental Results ◽  
Fine Tuning ◽  
Training Methods ◽  
High Quality ◽  
Style Transfer ◽  
Parallel Corpus ◽  
Paraphrase Generation

We tackle the low-resource problem in style transfer by employing transfer learning that utilizes abundantly available raw corpora. Our method consists of two steps: pre-training learns to generate a semantically equivalent sentence with an input assured grammaticality, and fine-tuning learns to add a desired style. Pre-training has two options, auto-encoding and machine translation based methods. Pre-training based on AutoEncoder is a simple way to learn these from a raw corpus. If machine translators are available, the model can learn more diverse paraphrasing via roundtrip translation. After these, fine-tuning achieves high-quality paraphrase generation even in situations where only 1k sentence pairs of the parallel corpus for style transfer is available. Experimental results of formality style transfer indicated the effectiveness of both pre-training methods and the method based on roundtrip translation achieves state-of-the-art performance.

scholarly journals Rice-Field Mapping with Sentinel-1A SAR Time-Series Data

2020 ◽  
Vol 13 (1) ◽  
pp. 103
Author(s):  
Lena Chang ◽  
Yi-Ting Chen ◽  
Jung-Hua Wang ◽  
Yang-Lang Chang
Keyword(s):  
Time Series ◽  
Detection Efficiency ◽  
Experimental Results ◽  
The Other ◽  
Series Data ◽  
Support Vector ◽  
Time Interval ◽  
Detection Accuracy ◽  
Data Set ◽  
Decision Method

This study proposed a feature-based decision method for the mapping of rice cultivation by using the time-series C-band synthetic aperture radar (SAR) data provided by Sentinel-1A. In this study, a model related to crop growth was first established. The model was developed based on a cubic polynomial function which was fitted by the complete time-series SAR backscatters during the rice growing season. From the developed model, five rice growth-related features were introduced, including backscatter difference (BD), time interval (TI) between vegetative growth and maturity stages, backscatter variation rate (BVR), average normalized backscatter (ANB) and maximum backscatter (MB). Then, a decision method based on the combination of the five extracted features was proposed to improve the rice detection accuracy. In order to verify the detection performance of the proposed method, the test data set of this study consisted of 50,000 rice and non-rice fields which were randomly sampled from a research area in Taiwan for simulation verification. From the experimental results, the proposed method can improve overall accuracy in rice detection by 6% compared with the method using feature BD. Furthermore, the rice detection efficiency of the proposed method was compared with other four classifiers, including decision tree (DT), support vector machine (SVM), K-nearest neighbor (KNN) and quadratic discriminant analysis (QDA). The experimental results show that the proposed method has better rice detection accuracy than the other four classifiers, with an overall accuracy of 91.9%. This accuracy is 3% higher than fine SVM, which performs best among the other four classifiers. In addition, the consistency and effectiveness of the proposed method in rice detection have been verified for different years and studied regions.

New Support Vector Algorithms

2000 ◽  
Vol 12 (5) ◽  
pp. 1207-1245 ◽  
Author(s):  
Bernhard Schölkopf ◽  
Alex J. Smola ◽  
Robert C. Williamson ◽  
Peter L. Bartlett
Keyword(s):  
Additional Benefit ◽  
Experimental Results ◽  
The Other ◽  
Support Vector ◽  
New Class ◽  
Support Vectors ◽  
Accuracy Parameter ◽  
Vector Algorithms ◽  
Free Parameters ◽  
Theoretical Results

We propose a new class of support vector algorithms for regression and classification. In these algorithms, a parameter ν lets one effectively control the number of support vectors. While this can be useful in its own right, the parameterization has the additional benefit of enabling us to eliminate one of the other free parameters of the algorithm: the accuracy parameter ε in the regression case, and the regularization constant C in the classification case. We describe the algorithms, give some theoretical results concerning the meaning and the choice of ν, and report experimental results.

A Dynamic Cost Sensitive Support Vector Machine

2012 ◽  
Vol 424-425 ◽  
pp. 1342-1346 ◽  
Author(s):  
Xiao Lin Chen ◽  
Yan Jiang ◽  
Min Jie Chen ◽  
Yong Yu ◽  
Hong Ping Nie ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Experimental Results ◽  
Promising Method ◽  
The Other ◽  
Support Vector ◽  
Imbalanced Datasets ◽  
Misclassification Cost

A lot of cost-sensitive support machine vector methods are used to handle the imbalanced datasets, but the obtained results are not as perfect as expectation. A promising method is proposed in this paper, named ADC-SVM, which uses genetic algorithm to dynamically search the optimal misclassification cost to build a cost sensitive support machine. We empirically evaluate ADC-SVM with SVM and Cost-sensitive SVM over 8 realistic imbalanced bi-class datasets from UCI. The experimental results show that ADC-SVM outperforms the other two methods over all the imbalanced datasets.

The Influence of Water Regime on the Performance of Aquatic Plants

1994 ◽  
Vol 29 (4) ◽  
pp. 127-132 ◽  
Author(s):  
Naomi Rea ◽  
George G. Ganf
Keyword(s):  
Deep Water ◽  
Aquatic Plants ◽  
Water Regime ◽  
Optimal Performance ◽  
Experimental Results ◽  
The Other ◽  
Full Potential ◽  
Influence Of Water ◽  
Emergent Species

Experimental results demonstrate bow small differences in depth and water regime have a significant affect on the accumulation and allocation of nutrients and biomass. Because the performance of aquatic plants depends on these factors, an understanding of their influence is essential to ensure that systems function at their full potential. The responses differed for two emergent species, indicating that within this morphological category, optimal performance will fall at different locations across a depth or water regime gradient. The performance of one species was unaffected by growth in mixture, whereas the other performed better in deep water and worse in shallow.

A Computational Method for the Identification of Endolysins and Autolysins

2020 ◽  
Vol 27 (4) ◽  
pp. 329-336 ◽  
Author(s):  
Lei Xu ◽  
Guangmin Liang ◽  
Baowen Chen ◽  
Xu Tan ◽  
Huaikun Xiang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Cell Wall ◽  
Experimental Results ◽  
Computational Method ◽  
Lytic Enzyme ◽  
Support Vector ◽  
Lytic Enzymes ◽  
Data Set ◽  
Optimal Feature ◽  
Better Than

Background: Cell lytic enzyme is a kind of highly evolved protein, which can destroy the cell structure and kill the bacteria. Compared with antibiotics, cell lytic enzyme will not cause serious problem of drug resistance of pathogenic bacteria. Thus, the study of cell wall lytic enzymes aims at finding an efficient way for curing bacteria infectious. Compared with using antibiotics, the problem of drug resistance becomes more serious. Therefore, it is a good choice for curing bacterial infections by using cell lytic enzymes. Cell lytic enzyme includes endolysin and autolysin and the difference between them is the purpose of the break of cell wall. The identification of the type of cell lytic enzymes is meaningful for the study of cell wall enzymes. Objective: In this article, our motivation is to predict the type of cell lytic enzyme. Cell lytic enzyme is helpful for killing bacteria, so it is meaningful for study the type of cell lytic enzyme. However, it is time consuming to detect the type of cell lytic enzyme by experimental methods. Thus, an efficient computational method for the type of cell lytic enzyme prediction is proposed in our work. Method: We propose a computational method for the prediction of endolysin and autolysin. First, a data set containing 27 endolysins and 41 autolysins is built. Then the protein is represented by tripeptides composition. The features are selected with larger confidence degree. At last, the classifier is trained by the labeled vectors based on support vector machine. The learned classifier is used to predict the type of cell lytic enzyme. Results: Following the proposed method, the experimental results show that the overall accuracy can attain 97.06%, when 44 features are selected. Compared with Ding's method, our method improves the overall accuracy by nearly 4.5% ((97.06-92.9)/92.9%). The performance of our proposed method is stable, when the selected feature number is from 40 to 70. The overall accuracy of tripeptides optimal feature set is 94.12%, and the overall accuracy of Chou's amphiphilic PseAAC method is 76.2%. The experimental results also demonstrate that the overall accuracy is improved by nearly 18% when using the tripeptides optimal feature set. Conclusion: The paper proposed an efficient method for identifying endolysin and autolysin. In this paper, support vector machine is used to predict the type of cell lytic enzyme. The experimental results show that the overall accuracy of the proposed method is 94.12%, which is better than some existing methods. In conclusion, the selected 44 features can improve the overall accuracy for identification of the type of cell lytic enzyme. Support vector machine performs better than other classifiers when using the selected feature set on the benchmark data set.

Sign in / Sign up

Export Citation Format

Share Document