AGO-Based Time Series Prediction Method Using LS-SVR

Fault or health condition prediction of complex system equipments has attracted more and more attention in recent years. Complex system equipments often show complex dynamic behavior and uncertainty, it is difficult to establish precise physical model. Therefore, the time series of complex equipments are often used to implement the prediction in practice. In this paper, in order to improve the prediction accuracy, based on grey system theory, accumulated generating operation (AGO) with raw time series is made to improve the data quality and regularity, and then inverse accumulated generating operation (IAGO) is performed to get the prediction results with the sequence, which is computed by LS-SVR. The results indicate preliminarily that the proposed method is an effective prediction method for its good prediction precision.

Download Full-text

Time Series Adaptive Online Prediction Method Combined with Modified LS-SVR and AGO

Mathematical Problems in Engineering ◽

10.1155/2012/985930 ◽

2012 ◽

Vol 2012 ◽

pp. 1-12 ◽

Cited By ~ 1

Author(s):

Guo Yangming ◽

Zhang Lu ◽

Cai Xiaobin ◽

Ran Congbao ◽

Zhai Zhengjun ◽

...

Keyword(s):

Time Series ◽

Complex Systems ◽

Incremental Learning ◽

Learning Algorithm ◽

Computing Time ◽

Grey System Theory ◽

Good Prediction ◽

Grey System ◽

Online Prediction ◽

Prediction Approach

Fault or health condition prediction of the complex systems has attracted more attention in recent years. The complex systems often show complex dynamic behavior and uncertainty, which makes it difficult to establish a precise physical model. Therefore, the time series of complex system is used to implement prediction in practice. Aiming at time series online prediction, we propose a new method to improve the prediction accuracy in this paper, which is based on the grey system theory and incremental learning algorithm. In this method, the accumulated generating operation (AGO) with the raw time series is taken to improve the data quality and regularity firstly; then the prediction is conducted by a modified LS-SVR model, which simplifies the calculation process with incremental learning; finally, the inverse accumulated generating operation (IAGO) is performed to get the prediction results. The results of the prediction experiments indicate preliminarily that the proposed scheme is an effective prediction approach for its good prediction precision and less computing time. The method will be useful in actual application.

Download Full-text

A New Prediction Method for Chaotic Time Series

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.380-384.1673 ◽

2013 ◽

Vol 380-384 ◽

pp. 1673-1676

Author(s):

Juan Du

Keyword(s):

Neural Network ◽

Time Series ◽

Prediction Accuracy ◽

Time Series Prediction ◽

Prediction Method ◽

Cumulative Effect ◽

Training Data ◽

Training Algorithm ◽

Learning Speed ◽

Sunspot Data

In order to show the time cumulative effect in the process for the time series prediction, the process neural network is taken. The training algorithm of modified particle swarm is used to the model for the learning speed. The training data is sunspot data from 1700 to 2007. Simulation result shows that the prediction model and algorithm has faster training speed and prediction accuracy than the artificial neural network.

Download Full-text

Grey system theory-based models in time series prediction

Expert Systems with Applications ◽

10.1016/j.eswa.2009.07.064 ◽

2010 ◽

Vol 37 (2) ◽

pp. 1784-1789 ◽

Cited By ~ 448

Author(s):

Erdal Kayacan ◽

Baris Ulutas ◽

Okyay Kaynak

Keyword(s):

System Theory ◽

Time Series ◽

Time Series Prediction ◽

Grey System Theory ◽

Grey System

Download Full-text

Benchmarking Nonstationary Time Series Prediction

10.5753/sbbd_estendido.2021.18182 ◽

2021 ◽

Author(s):

Rebecca Pontes Salles ◽

Eduardo Ogasawara ◽

Pedro González

Keyword(s):

Time Series ◽

Prediction Accuracy ◽

Time Series Prediction ◽

Prediction Method ◽

Data Transformation ◽

Nonstationary Time Series ◽

Prediction Methods ◽

Simple Task ◽

Model Training ◽

Transformation Methods

The prediction of time series has gained increasingly more attention among researchers since it is a crucial aspect of decision-making activities. Unfortunately, most time series prediction methods assume the property of stationarity, i.e., statistical properties do not change over time. In practice, it is the exception and not the rule in most real datasets. Several transformation methods were designed to treat nonstationarity in time series. In this context, nonstationary time series prediction is challenging since it demands knowledge of both data transformation and prediction methods. Since there are no silver bullets, it leads to exploring a large number of data transformation and prediction method combinations for building prediction setups. However, selecting a prediction setup that is appropriate to a particular time series and application is not a simple task. Benchmarking of different candidate combinations helps this selection. This work contributes by providing a review and experimental analysis of transformation methods and a systematic framework (TSPred) for benchmarking and selecting prediction setups for nonstationary time series. Suitable nonstationary time series transformation methods provided improvements of more than 30% in prediction accuracy for half of the evaluated time series. They improved the prediction by more than 95% for 10% of the time series. The features provided by TSPred are also shown to be competitive regarding prediction accuracy. Furthermore, the adoption of a validation phase during model training enables the selection of suitable transformation methods.

Download Full-text

A Novel Nonlinear Time Series Prediction Method and its Application in Structural Vibration Response Prediction

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.599-601.1918 ◽

2014 ◽

Vol 599-601 ◽

pp. 1918-1921 ◽

Cited By ~ 3

Author(s):

Yi Lin ◽

Hong Sen Yan ◽

Bo Zhou

Keyword(s):

Time Series ◽

Prediction Accuracy ◽

Time Series Prediction ◽

Prediction Method ◽

Response Prediction ◽

Nonlinear Time Series ◽

Vibration Response ◽

Structural Vibration ◽

Input Output ◽

Output Data

A novel nonlinear time series prediction method is proposed in this paper. This prediction method is based on the Multi-dimensional Taylor Network. The structure of the Multi-dimensional Taylor Network is introduced firstly. The Multi-dimensional Taylor Network provides a new method to predict the nonlinear time series. The prediction model based on the Multi-dimensional Taylor Network can realize the prediction of the nonlinear time series just with input-output data without the system mechanism, and it can describe the dynamic characteristics of the system. Finally, the new prediction method is applied in the structural vibration response prediction. Results indicate the validity and the better prediction accuracy of this method.

Download Full-text

Dynamic Prediction for Accuracy Maintaining Reliability of Superprecision Rolling Bearing in Service

Shock and Vibration ◽

10.1155/2018/7396293 ◽

2018 ◽

Vol 2018 ◽

pp. 1-15 ◽

Cited By ~ 1

Author(s):

Liang Ye ◽

Xintao Xia ◽

Zhen Chang

Keyword(s):

Time Series ◽

Bootstrap Method ◽

Prediction Method ◽

Vibration Signal ◽

Rolling Bearing ◽

Grey System Theory ◽

Dynamic Monitoring ◽

Grey System ◽

Dynamic Prediction ◽

The Future

A dynamic prediction method for accuracy maintaining reliability (AMR) of superprecision rolling bearings (SPRBs) in service is proposed by effectively fusing chaos theory and grey system theory and applying stochastic processes. In this paper, the time series of a vibration signal is used to characterize the state information for SPRB, and four runtime data points can be predicted in the future, which depends on four chaotic forecasting models to preprocess the time series. Using the grey bootstrap method and sampling from the four runtime data, a large amount of generated data (GD) are gained to analyze the changes in information on bearing service accuracy. Then, using a predefined accuracy threshold to match the Poisson count for the GD, the estimated value of variation intensity is obtained. Subsequently, with the help of the Poisson process, the dynamic evolution process is forecast in real time for AMR of the SPRB for each step in the future. Finally, according to a novel concept for maintaining relative reliability in an SPRB, the failure degree of a bearing maintaining an optimum accuracy status (BMOAS) is effectively described. Experimental investigation shows that multiple chaotic forecasting methods are accurate and feasible with all relative errors below 15%; the reliability of each step in the future can truly be described, and the prediction results for AMR over the same subseries show good consistency; dynamic monitoring of the health status of SPRB can be realized by the degree to which a BMOAS fails.

Download Full-text