Dissolved gases analysis is the essence to diagnose and forecast power transformer fault. This paper utilized an auto regression model to predict contents of gases dissolved in power transformer oil, and adopted Akaik...
详细信息
ISBN:
(纸本)9783037852163
Dissolved gases analysis is the essence to diagnose and forecast power transformer fault. This paper utilized an auto regression model to predict contents of gases dissolved in power transformer oil, and adopted Akaike's Information Criterion to determine model order. Then, the prediction results of AR model are compared with results of Gray model. Finally, gray artificial immune algorithm diagnosed power transformer fault types through gases contents predicted by auto regression model. Experiments demonstrates that auto regression model has a higher accuracy than Gray model, and the fault prediction results of the proposed algorithm are in accord with the results using real gases contents, thus, the power transformer fault prediction algorithm present in the paper is effective and reliable.
Artificial neural networks represent a growing new technology as indicated by a wide range of proposed applications. At a substation, when the transformer's windings get too hot, either load has to be reduced as a...
详细信息
Artificial neural networks represent a growing new technology as indicated by a wide range of proposed applications. At a substation, when the transformer's windings get too hot, either load has to be reduced as a short-term solution, or another transformer bay has to be installed as a long-term plan. To decide on whether to deploy either of these two strategies, one should be able to predict the transformer temperature accurately, This paper explores the possibility of using artificial neural networks for predicting top-oil temperature of transformers. Static neural networks, temporal processing networks and recurrent networks are explored for predicting the top-oil temperature of transformers. The results using different networks will be compared with the autoregression linear model.
The wavelet analysis technique was combined in this study with the projection pursuit autoregression (PPAR) model, and a new mid- and long-term runoff forecasting model, the wavelet analysis-based PPAR (PPAR-WA) is pr...
详细信息
The wavelet analysis technique was combined in this study with the projection pursuit autoregression (PPAR) model, and a new mid- and long-term runoff forecasting model, the wavelet analysis-based PPAR (PPAR-WA) is proposed, which realizes runoff forecasting from the perspective of the internal mechanism of a sequence. The runoff forecasting of the leading hydropower station in the Li Xianjiang cascade reservoirs in China was carried out to test the performance of the proposed model, and the accuracy and stability of the forecasting results were evaluated and analysed. The results show that the average relative error of the forecasting period can reach 9.6%, and the best relative error is less than 5% in some years. In addition, compared with PPAR, a back-propagation neural network and autoregression moving average model through three evaluation indexes, the results of PPAR-WA have higher accuracy and stronger stability. So, it has a certain value of popularization and application.
Earth Rotation Parameter (ERP) is one of the most important parameters in the area of positioning and navigation, autonomous orbit determination and Earth reference framework. However, due to the restriction of timeli...
详细信息
ISBN:
(纸本)9789811377594;9789811377587
Earth Rotation Parameter (ERP) is one of the most important parameters in the area of positioning and navigation, autonomous orbit determination and Earth reference framework. However, due to the restriction of timeliness of data processing, the predicted ERPs are taken into the relevant applications to meet the requirements of real-time or near real-time users. Therefore, given the disadvantages of short-term prediction models for ERPs, such as model mismatch, over parametrization and divergence with time, this study proposed a method for improving the short-term prediction model for ERP based on long-term observations. Firstly, the optimal length of observations was analyzed for the Least Square (LS) prediction model based on the Akaike Information Criterion (AIC). It is found that one year of ERP observations is the optimal data sets to establish the prediction model. Then, two constraints models based on LS, called (Constraint LS) CLS and (Enhanced CLS) ECLS, were discussed to decrease the errors in prediction models, which takes the correlation factors and residuals of prediction model into consideration. The results indicated that the prediction errors of ERP can be significantly decreased for short-term prediction, which improved the accuracy of ERP prediction with 50% for polar motions (PM), and 20% for UT1-UTC. Moreover, considering the divergence of predicted ERP along with the increasing of time and separate prediction of each parameters in ERP of auto Regressive model (AR), a Multi-variable regressionmodel (MAR) was introduced to correct the residuals of predicted ERP, which combined the PM, and UT1-UTC with LOD into prediction models. And the accuracy of predicted ERP can be improved at least 20% compared with AR model. Finally, according to data experiments, the improved short-term prediction model was analyzed based on different observations. It is suggested that our method can improve the short-term prediction in cases that long-term ERP observation
An evolutionary regressionmodeling approach for software cumulative failure prediction based on auto-regression order 4, 7 and 10 models are proposed. A real coded genetic algorithm is used to optimize the mean squar...
详细信息
ISBN:
(纸本)9781424437566
An evolutionary regressionmodeling approach for software cumulative failure prediction based on auto-regression order 4, 7 and 10 models are proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training the auto-regressionmodel. In this paper, we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train the auto-regressionmodel. To evaluate the predictive capability of the developed model data sets, various projects were used. A comparison between auto-regression order 4 model trained using least square estimation [1] and real coded genetic algorithm training is provided, also a comparison between the auto-regression order 7 and 10 models trained using the genetic algorithm is presented. Experimental results show that the training of different auto-regressionmodel by the real coded genetic algorithm has a good predictive capability.
Earth Rotation Parameter(ERP) is one of the most important parameters in the area of positioning and navigation, autonomous orbit determination and Earth reference framework. However, due to the restriction of timelin...
详细信息
Earth Rotation Parameter(ERP) is one of the most important parameters in the area of positioning and navigation, autonomous orbit determination and Earth reference framework. However, due to the restriction of timeliness of data processing, the predicted ERPs are taken into the relevant applications to meet the requirements of real-time or near real-time users. Therefore, given the disadvantages of short-term prediction models for ERPs, such as model mismatch, overparametrization and divergence with time, this study proposed a method for improving the short-term prediction model for ERP based on long-term observations. Firstly, the optimal length of observations was analyzed for the Least Square(LS) prediction model based on the Akaike Information Criterion(AIC). It is found that one year of ERP observations is the optimal data sets to establish the prediction model. Then, two constraints models based on LS, called(Constraint LS) CLS and(Enhanced CLS) ECLS, were discussed to decrease the errors in prediction models, which takes the correlation factors and residuals of prediction model into consideration. The results indicated that the prediction errors of ERP can be significantly decreased for short-term prediction, which improved the accuracy of ERP prediction with 50% for polar motions(PM), and 20% for UT1-UTC. Moreover, considering the divergence of predicted ERP along with the increasing of time and separate prediction of each parameters in ERP of auto Regressive model(AR), a Multivariable regressionmodel(MAR) was introduced to correct the residuals of predicted ERP, which combined the PM, and UT1-UTC with LOD into prediction models. And the accuracy of predicted ERP can be improved at least 20% compared with AR model. Finally, according to data experiments, the improved short-term prediction model was analyzed based on different observations. It is suggested that our method can improve the short-term prediction in cases that long-term ERP observations are avai
暂无评论