Hard-point detection of catenary based on Hidden Markov Model

2020 ◽  
Vol 64 (1-4) ◽  
pp. 701-709
Author(s):  
Shuxia Tian ◽  
Penghui Zhang ◽  
Liping Huang ◽  
Xueqian Song ◽  
Zhenmao Chen ◽  
...  
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Three Dimensional ◽  
Coupling Model ◽  
Vertical Acceleration ◽  
Element Analysis ◽  
Acceleration Signal ◽  
Three Dimensional Modeling ◽  
Point Detection

Hard-point detection is an important content of catenary detection. In this paper, the pantograph-catenary coupling model was established firstly. Then the vertical acceleration of pantograph during operation was calculated by using three-dimensional modeling software and finite element analysis software. The acceleration signal mixed with white noise was filtered by global default threshold, and the hard-point detection feature signal was obtained. Finally, the Hidden Markov Model corresponding to each state of the hard-point was obtained by using the characteristic signal, which verified the feasibility of the Hidden Markov Model for hard-point detection.

Prediction of Cutting Chatter Based on Hidden Markov Model

2007 ◽  
Vol 353-358 ◽  
pp. 2712-2715 ◽  
Author(s):  
Zhe He Yao ◽  
Xin Li ◽  
Zi Chen Chen
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Feature Matching ◽  
Hidden Markov ◽  
Cutting Process ◽  
Vibration Acceleration ◽  
State Recognition ◽  
Acceleration Signal ◽  
Cutting Chatter ◽  
Model Training

Self-chatter is a serious problem in cutting process. This paper aims to solve the problem by establishing time series model of vibration acceleration signal in cutting process based on Hidden Markov Model (HMM) technology and achieve the purpose of chatter recognition and prediction. Features which can indicate cutting state are extracted from the acceleration signal. HMM parameters are obtained by model training, and the reference models database is built. Then cutting state recognition is performed according to the feature matching level. Simulations and experiments are conducted, and the results show that the proposed method is feasible and it could get high recognition

scholarly journals Hidden Markov Model-Based Video Recognition for Sports

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Zhiyuan Wang ◽  
Chongyuan Bi ◽  
Songhui You ◽  
Junjie Yao
Keyword(s):  
Neural Network ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Gesture Recognition ◽  
Hidden Markov ◽  
Age Groups ◽  
Three Dimensional ◽  
Video Data ◽  
Convolutional Network ◽  
Video Recognition

In this paper, we conduct an in-depth study and analysis of sports video recognition by improved hidden Markov model. The feature module is a complex gesture recognition module based on hidden Markov model gesture features, which applies the hidden Markov model features to gesture recognition and performs the recognition of complex gestures made by combining simple gestures based on simple gesture recognition. The combination of the two modules forms the overall technology of this paper, which can be applied to many scenarios, including some special scenarios with high-security levels that require real-time feedback and some public indoor scenarios, which can achieve different prevention and services for different age groups. With the increase of the depth of the feature extraction network, the experimental effect is enhanced; however, the two-dimensional convolutional neural network loses temporal information when extracting features, so the three-dimensional convolutional network is used in this paper to extract features from the video in time and space. Multiple binary classifications of the extracted features are performed to achieve the goal of multilabel classification. A multistream residual neural network is used to extract features from video data of three modalities, and the extracted feature vectors are fed into the attention mechanism network, then, the more critical information for video recognition is selected from a large amount of spatiotemporal information, further learning the temporal dependencies existing between consecutive video frames, and finally fusing the multistream network outputs to obtain the final prediction category. By training and optimizing the model in an end-to-end manner, recognition accuracies of 92.7% and 64.4% are achieved on the dataset, respectively.

Sign in / Sign up

Export Citation Format

Share Document