Intelligent Controller for UPQC Using Combined Neural Network

The Unified Power Quality Conditioner (UPQC) plays an important role in the constrained delivery of electrical power from the source to an isolated pool of load or from a source to the grid. The proposed system can compensate voltage sag/swell, reactive power compensation and harmonics in the linear and nonlinear loads. In this work, the off line drained data from conventional fuzzy logic controller. A novel control system with a Combined Neural Network (CNN) is used instead of the traditionally four fuzzy logic controllers. The performance of combined neural network controller compared with Proportional Integral (PI) controller and Fuzzy Logic Controller (FLC). The system performance is also verified experimentally.

Evaluation of hydraulic fracturing of horizontal wells in tight reservoirs based on the deep neural network with physical constraints

Accurate diagnosis of fracture geometry and conductivity is of great challenge due to the complex morphology of volumetric fracture network. In this study, a DNN (deep neural network) model was proposed to predict fracture parameters for the evaluation of the fracturing effects. Field experience and the law of fracture volume conservation were incorporated as physical constraints to improve the prediction accuracy due to small amount of data. A combined neural network was adopted to input both static geological and dynamic fracturing data. The structure of the DNN was optimized and the model was validated through k-fold cross-validation. Results indicate that this DNN model is capable of predicting the fracture parameters accurately with a low relative error of under 10% and good generalization ability. The adoptions of the combined neural network, physical constraints, and k-fold cross-validation improve the model performance. Specifically, the root-mean-square error (RMSE) of the model decreases by 71.9% and 56% respectively with the combined neural network as the input model and the consideration of physical constraints. The mean square error (MRE) of fracture parameters reduces by 75% because the k-fold cross-validation improves the rationality of data set dividing. The model based on the DNN with physical constraints proposed in this study provides foundations for the optimization of fracturing design and improves the efficiency of fracture diagnosis in tight oil and gas reservoirs.

Wind-speed forecasting model based on DBN-Elman combined with improved PSO-HHT

Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel prediction model for ultrashort-term wind-speed prediction in wind farms is developed by combining a deep belief network,the Elman neural network,and the Hilbert-Huang transform modified using an improved particle swarm optimization algorithm.The experimental results show that the prediction results of the proposed deep neural network is better than that of shallow neural networks.Although the complexity of the model is high,the accuracy of wind-speed prediction and stability are also high.The proposed model effectively improves the accuracy of ultrashort-term wind-speed forecasting in wind farms.

Study on the echinococcosis blood serum detection based on Raman spectroscopy combined with neural network

A Raman spectroscopy method combined with neural network is used for the invasive and rapid detection of echinococcosis. The Raman spectroscopy measurements are performed on two groups of blood serum samples,which are from 28 echinococcosis patients and 38 healthy persons,respectively. The normalized Raman reflection spectra show that the reflectivity of the echinococcosis blood serum is higher than that of the normal human blood serum in the wavelength ranges of 101—175 nm and 1 801—2 701 nm. Then the principal component analysis(PCA) and back propagation neural network(BPNN) model are used to obtain the diagnosis results. The diagnosis rates for healthy persons and echinococcosis persons are 93.333 3% and 90.909 1%,respectively,so the average final diagnosis rate is 92.121 2%. The results demonstrate that the Raman spectroscopy analysis of blood serum combined with PCA-BPNN has considerable potential for the non-invasive and rapid detection of echinococcosis.

State Estimation Approach for Combined Heat and Electric Networks

State estimation(SE)is essential for combined heat and electric networks(CHENs)to provide a global and selfconsistent solution for multi-energy flow analysis.This paper proposes an SE approach for CHEN based on steady models of electric networks(ENs)and district heating networks(DHNs).A range of coupling components are considered.The performance of the proposed estimator is evaluated using Monte Carlo simulations and case studies.Results show that a relationship between the measurements from ENs and DHNs can improve the estimation accuracy for the entire network by using the combined SE model,especially when ENs and DHNs are strongly coupled.The coupling constraints could also provide extra redundancy to detect bad data in the boundary injection measurements of both networks.An analysis of computation time shows that the proposed method is suitable for online applications.

RESEARCH ON COMBINATION AND PLANNING OF PROCESSING UNITS UNDER CIMS CONDITION

A method of the rational combinging and planning of the given processing machines into units under the condition of computer integrated manufacturing systems is presented. Here the modelling method is a kind of queuing network model with the change of productivity, which has been checked in the reality and effectivencss by a manufacturing case in China