Engine Knock Detection Based on Time-Frequency Images and Support Vector Machine

2013 ◽  
Vol 694-697 ◽  
pp. 1387-1390
Author(s):  
Ning Li ◽  
Rui Zhou
Keyword(s):  
Support Vector Machine ◽  
Economic Performance ◽  
Detection Task ◽  
Support Vector ◽  
Image Generation ◽  
Time Frequency ◽  
Engine Cylinder ◽  
Engine Knock ◽  
Knock Detection ◽  
Knock Control

Knock is a major cause of pollution, parts damage and metallic noise in an engine. But slight knock can improve the power and economic performance of an engine. Therefore, existence and intensity of the knock are preconditions for the automatic knock control system to work. This paper describes an advanced approach solving the knock detection task. It is based on a time-frequency image generation solution followed by a support vector machine detection step trained in a constructive supervised way. The proposed method is applied to analyze the pressure signals measured from an engine cylinder to detect the knock based on the popular cycle-by-cycle classification. It is shown that this approach can qualify well for knock detection.

scholarly journals Mechanical Fault Diagnosis of High Voltage Circuit Breakers Based on Wavelet Time-Frequency Entropy and One-Class Support Vector Machine

Entropy ◽  
2015 ◽  
Vol 18 (1) ◽  
pp. 7 ◽  
Author(s):  
Nantian Huang ◽  
Huaijin Chen ◽  
Shuxin Zhang ◽  
Guowei Cai ◽  
Weiguo Li ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
High Voltage ◽  
Support Vector ◽  
Circuit Breakers ◽  
Time Frequency

Time-frequency feature analysis and recognition of fission neutrons signal based on support vector machine

2010 ◽  
Vol 22 (10) ◽  
pp. 2441-2447
Author(s):  
金晶 Jin Jing ◽  
魏彪 Wei Biao ◽  
冯鹏 Feng Peng ◽  
唐跃林 Tang Yuelin ◽  
周密 Zhou Mi
Keyword(s):  
Support Vector Machine ◽  
Feature Analysis ◽  
Support Vector ◽  
Time Frequency ◽  
Fission Neutrons ◽  
Frequency Feature

scholarly journals Support-vector machine and naïve bayes based diagnostic analytic of harmonic source identification

2020 ◽  
Vol 20 (1) ◽  
pp. 1
Author(s):  
Mohd Hatta Jopri ◽  
Abdul Rahim Abdullah ◽  
Jingwei Too ◽  
Tole Sutikno ◽  
Srete Nikolovski ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Naive Bayes ◽  
Current Source ◽  
Naïve Bayes ◽  
Support Vector ◽  
Time Frequency ◽  
Frequency Representation ◽  
S Transform ◽  
Harmonic Voltage ◽  
Harmonic Source

<span>A harmonic source diagnostic analytic is a vital to identify the location and type of harmonic source in the power system. This paper introduces a comparison of machine learning (ML) algorithm which are support vector machine (SVM) and Naïve Bayes (NB). Voltage and current features are used as the input for ML are extracted from time-frequency representation (TFR) of S-transform. Several unique cases of harmonic source location are considered, whereas harmonic voltage and harmonic current source type-load are used in the diagnosing process. To identify the best ML, the performance measurement of the propose method including accuracy, specificity, sensitivity, and F-measure are calculated. The adequacy of the proposed methodology is tested and verified on IEEE 4-bust test feeder and each ML algorithm is executed for 10 times due to different partitions and to prevent any overfitting result.</span>

scholarly journals A Hybrid EEG-Based Emotion Recognition Approach Using Wavelet Convolutional Neural Networks (WCNN) and Support Vector Machine

2021 ◽  
pp. 1-29
Author(s):  
Sara Bagherzadeh ◽  
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Convolutional Neural Networks ◽  
Hybrid Approach ◽  
Support Vector ◽  
Emotional States ◽  
Eeg Signals ◽  
Color Representation ◽  
Time Frequency ◽  
Average Accuracy

Nowadays, deep learning and convolutional neural networks (CNNs) have become widespread tools in many biomedical engineering studies. CNN is an end-to-end tool which makes processing procedure integrated, but in some situations, this processing tool requires to be fused with machine learning methods to be more accurate. In this paper, a hybrid approach based on deep features extracted from Wavelet CNNs (WCNNs) weighted layers and multiclass support vector machine (MSVM) is proposed to improve recognition of emotional states from electroencephalogram (EEG) signals. First, EEG signals were preprocessed and converted to time-frequency (T-F) color representation or scalogram using the continuous wavelet transform (CWT) method. Then, scalograms were fed into four popular pre-trained CNNs, AlexNet, ResNet-18, VGG-19 and Inception-v3 to fine-tune them. Then, the best feature layer from each one was used as input to the MSVM method to classify four quarters of the valence-arousal model. Finally, subject-independent Leave-One-Subject-Out criterion was used to evaluate the proposed method on DEAP and MAHNOB-HCI databases. Results show that extracting deep features from the earlier convolutional layer of ResNet-18 (Res2a) and classifying using the MSVM increases the average accuracy, precision and recall about 20% and 12% for MAHNOB-HCI and DEAP databases, respectively. Also, combining scalograms from four regions of pre-frontal, frontal, parietal and parietal-occipital and two regions of frontal and parietal achieved the higher average accuracy of 77.47% and 87.45% for MAHNOB-HCI and DEAP databases, respectively. Combining CNN and MSVM increased recognition of emotion from EEG signal and results were comparable to state-of-the-art studies.

scholarly journals A Novel Method for Mechanical Fault Diagnosis Based on Variational Mode Decomposition and Multikernel Support Vector Machine

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Zhongliang Lv ◽  
Baoping Tang ◽  
Yi Zhou ◽  
Chuande Zhou
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Optimal Parameter ◽  
Locally Linear Embedding ◽  
Support Vector ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Feature Sets ◽  
Mode Decomposition ◽  
Mechanical Faults

A novel fault diagnosis method based on variational mode decomposition (VMD) and multikernel support vector machine (MKSVM) optimized by Immune Genetic Algorithm (IGA) is proposed to accurately and adaptively diagnose mechanical faults. First, mechanical fault vibration signals are decomposed into multiple Intrinsic Mode Functions (IMFs) by VMD. Then the features in time-frequency domain are extracted from IMFs to construct the feature sets of mixed domain. Next, Semisupervised Locally Linear Embedding (SS-LLE) is adopted for fusion and dimension reduction. The feature sets with reduced dimension are inputted to the IGA optimized MKSVM for failure mode identification. Theoretical analysis demonstrates that MKSVM can approximate any multivariable function. The global optimal parameter vector of MKSVM can be rapidly identified by IGA parameter optimization. The experiments of mechanical faults show that, compared to traditional fault diagnosis models, the proposed method significantly increases the diagnosis accuracy of mechanical faults and enhances the generalization of its application.

Sign in / Sign up

Export Citation Format

Share Document