In order to solve the problem of low accuracy of traditional artificial neural networks in approximating functional, a coupling-loop nonlinear autoregressive with exogenous inputs neural network estimation model is pr...
详细信息
In order to solve the problem of low accuracy of traditional artificial neural networks in approximating functional, a coupling-loop nonlinear autoregressive with exogenous inputs neural network estimation model is proposed and applied to the state of health forecasting of lithium-ion batteries. Firstly, eight health indicators related to the state of health of lithium-ion batteries are mined. In order to eliminate the harm of weakly correlated independent variables and redundant independent variables to the estimation results, principal component feature extraction is applied to the feature extraction of the eight health indicators. bayesian regularization algorithm is used to learn the weights of the neural network, which solves the problems of slow convergence speed and easy to fall into local extremum of back propagation learning algorithm, and improves the generalization ability of the neural network. In order to verify the rationality of the proposed model and algorithm, the coupling-loop nonlinear autoregressive with exogenous inputs neural network model is used to estimate the state of health of lithium battery under the condition of complete charge discharge test, and the estimation results are compared with other neural network models. The simulation results show that the coupling-loop nonlinear autoregressive with exogenous inputs estimation model using feature extraction method and bayesian network weight algorithm can approach the functional with higher accuracy, and the absolute error and relative error of lithium-ion battery's state of health estimation can be reduced by more than 50% on average, while the mean square error can be reduced by more than 80%. (c) 2021 Elsevier Ltd. All rights reserved.
The production of biofuel from waste has become an important topic for waste management and reducing its environmental hazard. Tea factory waste is a strong candidate due to its availability and sourceability. This st...
详细信息
The production of biofuel from waste has become an important topic for waste management and reducing its environmental hazard. Tea factory waste is a strong candidate due to its availability and sourceability. This study aimed to reveal the biochemical methane potential (BMP) of tea factory waste (TFW) and spent tea waste (STW). Additionally, the results revealed that both substrates had high biodegradability due to high VS removal. The BMP tests took 49 days under mesophilic conditions with a batch reactor and the cumulative methane yields were 249 +/- 3, and 261 +/- 8 mL CH4/g VS for TFW and STW, respectively. According to prediction data with the selected ANN model, which was 50 hidden layer sizes, trained with bayesian regularization algorithm, the maximum cumulative specific methane yield of the co-digestion was simulated as 468.43 mL CH4/g VS when the ratio of 65 and 35% (w/w by VS) of TFW and STW, respectively. The predicted methane yield for co-substrates was 183% higher than mono substrates. This result revealed that TFW can be a good candidate for biogas production as biofuel for not only its availability and sourceability but also the synergistic effect possible for codigestion.
As the conventional prediction methods for production of waterflooding reservoirs have some drawbacks, a production forecasting model based on artificial neural network was proposed, the simulation process by this met...
详细信息
As the conventional prediction methods for production of waterflooding reservoirs have some drawbacks, a production forecasting model based on artificial neural network was proposed, the simulation process by this method was presented, and some examples were illustrated. A workflow that involves a physics-based extraction of features was proposed for fluid production forecasting to improve the prediction effect. The bayesian regularization algorithm was selected as the training algorithm of the model. This algorithm, although taking longer time, can better generalize oil, gas and water production data sets. The model was evaluated by calculating mean square error and determination coefficient, drawing error distribution histogram and the cross-plot between simulation data and verification data etc. The model structure was trained, validated and tested with 90% of the historical data, and blindly evaluated using the remaining. The predictive model consumes minimal information and computational cost and is capable of predicting fluid production rate with a coefficient of determination of more than 0.9, which has the simulation results consistent with the practical data.
The accurate cooling load prediction of an air conditioning system is the basis for energy saving optimization. To solve the problems of low accuracy of prediction, and most load predictions focusing on short-time pre...
详细信息
The accurate cooling load prediction of an air conditioning system is the basis for energy saving optimization. To solve the problems of low accuracy of prediction, and most load predictions focusing on short-time prediction that causes reducing the practical significance, the application of improved BP neural networks prediction model is presented in this paper. Training and testing data for prediction model have been generated from DeST (Designer's Simulation Toolkits) with climate data of Beijing. The generalization ability of the model has been strongest based on bayesian regularization algorithm to train data. A case study shows that high accuracy is achieved by using the BPNN prediction model based on bayesianregularization method with the prediction error of 1.18% in predicting the building load for longer time.
Forecasting of groundwater levels is very useful for planning integrated management of groundwater and surface water resources in a basin. In the present study, artificial neural network models have been developed for...
详细信息
Forecasting of groundwater levels is very useful for planning integrated management of groundwater and surface water resources in a basin. In the present study, artificial neural network models have been developed for groundwater level forecasting in a river island of tropical humid region, eastern India. ANN modeling was carried out to predict groundwater levels 1 week ahead at 18 sites over the study area. The inputs to the ANN models consisted of weekly rainfall, pan evaporation, river stage, water level in the drain, pumping rate and groundwater level in the previous week, which led to 40 input nodes and 18 output nodes. Three different ANN training algorithms, viz., gradient descent with momentum and adaptive learning rate backpropagation (GDX) algorithm, Levenberg-Marquardt (LM) algorithm and bayesianregularization (BR) algorithm were employed and their performance was evaluated. As the neural network became very large with 40 input nodes and 18 output nodes, the LM and BR algorithms took too much time to complete a single iteration. Consequently, the study area was divided into three clusters and the performance evaluation of the three ANN training algorithms was done separately for all the clusters. The performance of all the three ANN training algorithms in predicting groundwater levels over the study area was found to be almost equally good. However, the performance of the BR algorithm was found slightly superior to that of the GDX and LM algorithms. The ANN model trained with BR algorithm was further used for predicting groundwater levels 2, 3 and 4 weeks ahead in the tubewells of one cluster using the same inputs. It was found that though the accuracy of predicted groundwater levels generally decreases with an increase in the lead time, the predicted groundwater levels are reasonable for the larger lead times as well.
Microwave filter is the kind of device which can separate different signals within a certain band of microwave frequency, widely used in microwave communication system. Periodic defected ground structures (PDGS) with ...
详细信息
ISBN:
(纸本)9781424437092
Microwave filter is the kind of device which can separate different signals within a certain band of microwave frequency, widely used in microwave communication system. Periodic defected ground structures (PDGS) with defected rectangles have excellent filter properties when periodic unit amounts and structure sizes meet appropriate conditions. In this paper, intelligent model of PDGS with defected rectangles is developed for the first time on the basis of FDTD analysis. Periodic unit amounts, the structure sizes of PDGS with defected rectangles and the frequency are defined as the input samples of artificial neural network (ANN), transmission coefficient (S21) are defined as the output samples. Transmission coefficient of PDGS at any arbitrary periodic unit amounts, any arbitrary structure sizes and any arbitrary frequency within training values range can be obtained quickly from intelligent model after the ANN has been successfully trained with the bayesian regularization algorithm. Finally, intelligent model has been approved by FDTD results. It is also showed that intelligent model is very effective, which will provide powerful approach for the precise analysis and quick design of microwave filter using PDGS with defected rectangles.
暂无评论