An adaptive Elman neural network with C-PSO learning algorithm based pitch angle controller for DFIG based WECS

2016 ◽  
Vol 23 (5) ◽  
pp. 716-730 ◽  
Author(s):  
R Sitharthan ◽  
M Geethanjali
Keyword(s):  
Neural Network ◽  
Output Power ◽  
Pitch Angle ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Pso Algorithm ◽  
Power Fluctuation ◽  
Elman Neural Network ◽  
Learning Capability ◽  
Wind Energy Conversion

Frequent variation in the wind flow affects the Wind Turbine (WT) to generate fluctuating output power and this can negatively impact the entire power network. This paper aims at modelling an Enhanced-Elman Neural Network (EENN) based pitch angle controller to mitigate the output power fluctuation in a grid connected Wind Energy Conversion System. The outstanding aspect of the proposed controller is that, they can smoothen the output power fluctuation, when the wind speed is above or below rated speed of the WT. The proposed EENN pitch controller is trained online using Gradient Descent (GD) algorithm and the network learning is carried out using Customized-Particle swarm optimization (C-PSO) algorithm. The C-PSO is adopted, in order to increase the learning capability of the training process by adjusting the networks learning rate. Further, the node connecting weights of the EENN is updated by means of GD algorithm using back-propagation methodology. The performance of the proposed controller is analysed using the simulation studies carried out in MATLAB /Simulink environment.

Hydraulic System Fault Diagnosis Based on EMD and Improved PSO-Elman ANN

2013 ◽  
Vol 284-287 ◽  
pp. 2936-2940
Author(s):  
Zeng Shou Dong ◽  
Xiao Yu Zhang ◽  
Jian Chao Zeng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convergence Rate ◽  
Hydraulic System ◽  
Learning Algorithm ◽  
Threshold Value ◽  
Pso Algorithm ◽  
Elman Neural Network ◽  
Neural Network Learning ◽  
Network Convergence

The element parameters of engineering machinery hydraulic system are detected, the fault eigenvector is extracted, and the information is applied to neural network fault diagnosis. Experience mode decomposition (EMD) is used to extract fault characteristic vectors in this paper, combined with the pressure, temperature and flow rate of dominant signal as neural network's inputs. In addition, the paper improves the Elman neural network learning algorithm by PSO algorithm. It can effectively increase network convergence rate and computing power. The particle swarm is used to optimize Elman neural network weights and the threshold value and then applied in the fault diagnosis system by training the network. The results show that the method increases the neural network convergence rate and reduces diagnoses error.

HYDRAULIC SYSTEM FAULT DIAGNOSIS BASED ON EMD AND IMPROVED PSO-ELMAN ANN

2013 ◽  
Vol 37 (4) ◽  
pp. 1189-1197 ◽  
Author(s):  
Zengshou Dong ◽  
Xiaoyu Zhang ◽  
Jianchao Zeng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convergence Rate ◽  
Hydraulic System ◽  
Learning Algorithm ◽  
Threshold Value ◽  
Pso Algorithm ◽  
Elman Neural Network ◽  
Neural Network Learning ◽  
Network Convergence

The element parameters of engineering machinery hydraulic system are detected, the fault eigenvector is extracted, and the information is applied to neural network fault diagnosis. Experience mode decomposition (EMD) is used to extract fault characteristic vectors in this paper, combined with the pressure, temperature and flow rate of dominant signal as neural network’s inputs. In addition, the paper improves the Elman neural network learning algorithm by the PSO algorithm. It can effectively increase network convergence rate and computing power. The particle swarm is used to optimize Elman neural network weights and the threshold value and then applied in the fault diagnosis system by training the network. The results show that the method increases the neural network convergence rate and reduces diagnoses error.

scholarly journals Position Control of Ultrasonic Motor Using IMC-PID Combined with Tribes Type NN Algorithm

2011 ◽  
Vol 2-3 ◽  
pp. 12-17
Author(s):  
Sheng Lin Mu ◽  
Kanya Tanaka
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Pid Control ◽  
Position Control ◽  
Back Propagation ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Ultrasonic Motor ◽  
Swarm Optimization

In this paper, we propose a novel scheme of IMC-PID control combined with a tribes type neural network (NN) for the position control of ultrasonic motor (USM). In this method, the NN controller is employed for tuning the parameter in IMC-PID control. The weights of NN are designed to be updated by the tribes-particle swarm optimization (PSO) algorithm. This method makes it possible to compensate for the characteristic changes and nonlinearity of USM. The parameter-free tribes-PSO requires no information about the USM beforehand; hence its application overcomes the problem of Jacobian estimation in the conventional back propagation (BP) method of NN. The effectiveness of the proposed method is confirmed by experiments.

scholarly journals Stock Market Prediction Using Artificial Neural Networks

2012 ◽  
Vol 6-7 ◽  
pp. 1055-1060 ◽  
Author(s):  
Yang Bing ◽  
Jian Kun Hao ◽  
Si Chang Zhang
Keyword(s):  
Neural Network ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Stock Exchange ◽  
Back Propagation ◽  
Composite Index ◽  
Network Models ◽  
Back Propagation Neural Network ◽  
Neural Network Models ◽  
The Neural Network

In this study we apply back propagation Neural Network models to predict the daily Shanghai Stock Exchange Composite Index. The learning algorithm and gradient search technique are constructed in the models. We evaluate the prediction models and conclude that the Shanghai Stock Exchange Composite Index is predictable in the short term. Empirical study shows that the Neural Network models is successfully applied to predict the daily highest, lowest, and closing value of the Shanghai Stock Exchange Composite Index, but it can not predict the return rate of the Shanghai Stock Exchange Composite Index in short terms.

The use of artificial neural networks for modelling rumen fill

2020 ◽  
Author(s):  
Rasheed Adekunle Adebayo ◽  
Mehluli Moyo ◽  
Evariste Bosco Gueguim-Kana ◽  
Ignatius Verla Nsahlai
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Random Forest Model ◽  
Ann Model ◽  
Forest Model ◽  
Artificial Neural ◽  
Cattle And Sheep

Artificial Neural Network (ANN) and Random Forest models for predicting rumen fill of cattle and sheep were developed. Data on rumen fill were collected from studies that reported body weights, measured rumen fill and stated diets fed to animals. Animal and feed factors that affected rumen fill were identified from each study and used to create a dataset. These factors were used as input variables for predicting the weight of rumen fill. For ANN modelling, a three-layer Levenberg-Marquardt Back Propagation Neural Network was adopted and achieved 96% accuracy in prediction of the weight of rumen fill. The precision of the ANN model’s prediction of rumen fill was higher for cattle (80%) than sheep (56%). On validation, the ANN model achieved 95% accuracy in prediction of the weight of rumen fill. A Random Forest model was trained using a binary tree-based machine-learning algorithm and achieved 87% accuracy in prediction of rumen fill. The Random Forest model achieved 16% (cattle) and 57% (sheep) accuracy in validation of the prediction of rumen fill. In conclusion, the ANN model gave better predictions of rumen fill compared to the Random Forest model and should be used in predicting rumen fill of cattle and sheep.

Continuous Learning Framework for Freeway Incident Detection

1998 ◽  
Vol 1644 (1) ◽  
pp. 124-131 ◽  
Author(s):  
Srinivas Peeta ◽  
Debjit Das
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Superior Performance ◽  
Incident Detection ◽  
Neural Net ◽  
Continuous Learning ◽  
Back Propagation Algorithm ◽  
Learning Capability ◽  
Detection Algorithms ◽  
On Line

Existing freeway incident detection algorithms predominantly require extensive off-line training and calibration precluding transferability to new sites. Also, they are insensitive to demand and supply changes in the current site without recalibration. We propose two neural network-based approaches that incorporate an on-line learning capability, thereby ensuring transferability, and adaptability to changes at the current site. The least-squares technique and the error back propagation algorithm are used to develop on-line neural network-trained versions of the popular California algorithm and the more recent McMaster algorithm. Simulated data from the integrated traffic simulation model is used to analyze performance of the neural network-based versions of the California and McMaster algorithms over a broad spectrum of operational scenarios. The results illustrate the superior performance of the neural net implementations in terms of detection rate, false alarm rate, and time to detection. Of implications to current practice, they suggest that just introducing a continuous learning capability to commonly used detection algorithms in practice such as the California algorithm enhances their performance with time in service, allows transferability, and ensures adaptability to changes at the current site. An added advantage of this strategy is that existing traffic measures used (such as volume, occupancy, and so forth.) in those algorithms are sufficient, circumventing the need for new traffic measures, new threshold parameters, and variables that require subjective decisions.

Elman Neural Network–Based Dynamic Scheduling of Wafer Photolithography Process

2011 ◽  
Vol 186 ◽  
pp. 36-40 ◽  
Author(s):  
Bing Hai Zhou
Keyword(s):  
Neural Network ◽  
Manufacturing System ◽  
Dynamic Scheduling ◽  
Learning Algorithm ◽  
Semiconductor Wafer ◽  
Simulation Experiments ◽  
Elman Neural Network ◽  
Scheduling Method ◽  
Photolithography Process ◽  
Wafer Manufacturing

Photolithography area is usually a bottleneck area in a semiconductor wafer manufacturing system (SWMS). It is difficult to schedule photolithography area on real-time optimally. Here, an Elman neural network (ENN)-based dynamic scheduling method is proposed. An ENN-based sample learning algorithm is proposed for selecting best combination of scheduling rules. To illustrate the feasibility and practicality of the presented method, the simulation experiment is developed. A numerical example is use to evaluate the proposed method. Results of simulation experiments show that the proposed method is effective to schedule a complex wafer photolithography process.

A NEURAL NETWORK MODEL FOR CREDIT RISK EVALUATION

2009 ◽  
Vol 19 (04) ◽  
pp. 285-294 ◽  
Author(s):  
ADNAN KHASHMAN
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Credit Risk ◽  
Network Model ◽  
Neural Network Model ◽  
Risk Evaluation ◽  
Evaluation System ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Learning Schemes

Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications.

scholarly journals Passivity-Based Control for Rocket Launcher Position Servo System Based on ADRC Optimized by IPSO-BP Algorithm

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Rong-lin Wang ◽  
Bao-chun Lu ◽  
Yuan-long Hou ◽  
Qiang Gao
Keyword(s):  
Dynamic Performance ◽  
Permanent Magnet Synchronous Motor ◽  
Back Propagation ◽  
Servo System ◽  
Pso Algorithm ◽  
Bp Algorithm ◽  
Learning Capability ◽  
Prototype Test ◽  
Passivity Based Control ◽  
Position Servo

In order to achieve better motion accuracy and higher robustness of the shipborne rocket launcher position servo system driven by a permanent magnet synchronous motor (PMSM), a passivity-based controller based on active disturbance rejection control (ADRC) optimized by improved particle swarm optimization-back propagation (IPSO-BP) algorithm is proposed in this paper. The convenient method of interconnection and damping assignment and passivity-based control (IDA-PBC) is adopted to establish the port controlled Hamiltonian system with dissipation (PCHD) model of PMSM. To further enhance the robustness and adaptability of traditional ADRC, an BP algorithm is introduced to on-line update the proportional, integral, and derivative gains of ADRC. Furthermore, to improve the learning capability, the improved PSO algorithm is adopted to optimize the learning rates of the back propagation neural networks. The results of numerical simulation and prototype test indicate that the proposed IPSO-BP-ADRC-PBC controller has better static and dynamic performance than the ADRC-PBC and BP-ADRC-PBC controller with fixed learning rate.

Application of Artificial Neural Network for Prediction of Heat Treated Sintered Steels Properties

2008 ◽  
Vol 273-276 ◽  
pp. 323-328 ◽  
Author(s):  
H. Khorsand ◽  
M. Arjomandi ◽  
H. Abdoos ◽  
S.H. Sadati
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Heat Treatment ◽  
Artificial Neural Network ◽  
Learning Algorithm ◽  
Initial Density ◽  
Back Propagation ◽  
Heat Treated ◽  
Algorithm Comparison ◽  
Artificial Neural

Heat treatment is an important method for improving the mechanical properties of industrial parts that are made through the powder metallurgy. Most PM steels are subjected to hardening and tempering, and it is due to this treatment that tempered martensite is formed. After heat treatment, these steel’s mechanical properties are affected by the heat treatment parameters and the initial density. In this paper, in order to make an evaluation of the effect of the above parameters, FN-0205 PM steel with various densities is heat treated in different austenite conditions and tempering time. Their mechanical properties are then evaluated and recorded. Afterwards, this data obtained by experimental procedure are predicted for various conditions. The method employed here is the well-known feedforward Artificial Neural Network (ANN) with the Back Propagation (BP) learning algorithm. Comparison between predicted values and experimental data, in the present study, indicate that the predicted results from this model are in good agreement with the experimental values.

Sign in / Sign up

Export Citation Format

Share Document