scholarly journals Time series predictive models of piezoelectric active-sensing for SHM applications

2010 ◽  
Author(s):  
Gyuhae Park ◽  
Eloi Figueiredo ◽  
Kevin M. Farinholt ◽  
Charles R. Farrar
Keyword(s):  
Time Series ◽  
Predictive Models ◽  
Active Sensing

scholarly journals Comparative Study on Performance Analysis of Time Series Predictive Models

2017 ◽  
Vol 10 (8) ◽  
pp. 37-48 ◽  
Author(s):  
Syed Muzamil Basha ◽  
Yang Zhenning ◽  
Dharmendra Singh Rajput ◽  
Ronnie D. Caytiles ◽  
N. Ch. S.N Iyengar
Keyword(s):  
Time Series ◽  
Performance Analysis ◽  
Comparative Study ◽  
Predictive Models ◽  
Analysis Of Time Series

Use of Time-Series Predictive Models for Piezoelectric Active-Sensing in Structural Health Monitoring Applications

2012 ◽  
Vol 134 (4) ◽  
Author(s):  
Eloi Figueiredo ◽  
Gyuhae Park ◽  
Kevin M. Farinholt ◽  
Charles R. Farrar ◽  
Jung-Ryul Lee
Keyword(s):  
Time Series ◽  
Structural Health Monitoring ◽  
Frequency Response ◽  
Frequency Domain ◽  
Health Monitoring ◽  
Active Sensing ◽  
Response Functions ◽  
Active Sensors ◽  
Frequency Response Functions ◽  
Structural Health

In this paper, time domain data from piezoelectric active-sensing techniques is utilized for structural health monitoring (SHM) applications. Piezoelectric transducers have been increasingly used in SHM because of their proven advantages. Especially, their ability to provide known repeatable inputs for active-sensing approaches to SHM makes the development of SHM signal processing algorithms more efficient and less susceptible to operational and environmental variability. However, to date, most of these techniques have been based on frequency domain analysis, such as impedance-based or high-frequency response functions-based SHM techniques. Even with Lamb wave propagations, most researchers adopt frequency domain or other analysis for damage-sensitive feature extraction. Therefore, this study investigates the use of a time-series predictive model which utilizes the data obtained from piezoelectric active-sensors. In particular, time series autoregressive models with exogenous inputs are implemented in order to extract damage-sensitive features from the measurements made by piezoelectric active-sensors. The test structure considered in this study is a composite plate, where several damage conditions were artificially imposed. The performance of this approach is compared to that of analysis based on frequency response functions and its capability for SHM is demonstrated.

scholarly journals Prediction of Demand for Supply Chain using Time Series Predictive Models

2020 ◽  
Vol 175 (22) ◽  
pp. 33-39
Author(s):  
Aturika Bhatnagar ◽  
Rajeev Gupta ◽  
G.D. Thakar
Keyword(s):  
Time Series ◽  
Supply Chain ◽  
Predictive Models

scholarly journals Modeling and Prediction of COVID-19 Outbreak in India

2020 ◽  
Author(s):  
Saurabh Kumar ◽  
Varun Agiwal ◽  
Ashok Kumar ◽  
Jitendra Kumar
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Predictive Models ◽  
Predictive Value ◽  
Arima Models ◽  
Epidemiological Modeling ◽  
Modeling And Prediction ◽  
Propagation Rule ◽  
Administrative Strategies ◽  
Indian Data

As the outbreak of coronavirus disease 2019 (COVID-19) is continuously increasing in India, so epidemiological modeling of COVID-19 data is urgently required for administrative strategies. Time series and is capable to predict future observations by modeling the data based on past and present data. Here, we have modeled the epidemiological COVID-19 Indian data using various models. Based on the collected COVID-19 outbreak data, we try to find the propagation rule of this outbreak disease and predict the outbreak situations in India. For India data, the time series model gives the best results in the form of predication as compared to other models for all variables of COVID-19. For new cases, new deaths, total cases and total deaths, the best fitted ARIMA models are as follows: ARIMA(0,2,3), ARIMA(0,1,1), ARIMA(0,2,0) and ARIMA(0,2,1). Based on time series analysis, we predict all variables for next month and conclude that the predictive value of Indian COVID-19 data of total cases is more than 20 lakhs with more than 43 thousand total deaths. The present chapter recommended that a comparison between various predictive models provide the accurate and better forecast value of the COVID-19 outbreak for all study variables.

scholarly journals Machine Learning Models for Sales Time Series Forecasting

2018 ◽  
Author(s):  
Bohdan M. Pavlyshenko
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Predictive Models ◽  
Time Series Forecasting ◽  
Learning Models ◽  
Learning Generalization ◽  
Machine Learning Models

In this paper, we study the usage of machine learning models for sales time series forecasting. The effect of machine learning generalization has been considered. A stacking approach for building regression ensemble of single models has been studied. The results show that using stacking technics, we can improve the performance of predictive models for sales time series forecasting.

Sign in / Sign up

Export Citation Format

Share Document