Dissertation > Excellent graduate degree dissertation topics show

Exploration on Neural Networks for Water Quality Assessment and Prediction

Author: DuWei
Tutor: SunBaoSheng
School: Tianjin University
Course: Environmental Engineering
Keywords: Artificial Neural Networks Fuzzy Neural Network RBF neural network Water quality assessment Water quality prediction
CLC: X824
Type: Master's thesis
Year: 2007
Downloads: 434
Quote: 2
Read: Download Dissertation

Abstract


Artificial Neural Network (ANN) is a complex nonlinear science and artificial intelligence science frontier in the field of water pollution control is still in its infancy in China and abroad . Research Review of a comprehensive analysis of the water quality assessment and prediction of water quality analyzes the basic principle of artificial neural network algorithms and fuzzy mathematics theory after the Fuzzy Neural Network (FNN) and radial basis function neural network (RBFNN) the introduction of water the field of pollution control , mainly in water quality assessment and prediction of water quality exploratory research , has made ??efforts to improve water quality assessment and prediction of water quality , intelligent level . This paper describes the principles, algorithms and modes characteristic of FNN . The FNN is no longer a black box, of all nodes with parameters having physical significance, and to overcome the ANN structure selection disadvantage of the lack of adequate theoretical analysis . The FNN model of both direct expression of the people 's usual logical meaning and and both ANN adaptive learning function and non purely expressive power advantages . FNN applied to water quality assessment is the Preliminary proof of case studies , learning to grade 5 standards FNN to properly evaluate the water quality sample has better objectivity , reliability and interpretability . Adequately studied RBFNN mechanism based on RBFNN is applied to the prediction of water quality in Shenzhen River online monitoring data for the training sample , build a the RBFNN water quality forecast model . Application of the model to predict November 19 2006 to 2006 29 , 2010 10 days of the Shenzhen River water quality and the accuracy of the forecast results verified real monitoring data for the period , the validation results show that the model predicted the results of the error smaller, the good fit . RBFNN and of BPNN prediction performance ( back-propagation neural network) , this article also to the same monitoring data to establish a the BPNN water quality forecast model , the predicted results RBFNN water quality prediction model predicted results compared , the comparison shows that , RBFNN the prediction results are significantly better than the BPNN. Two modeling process , RBFNN in terms of convergence rate , or the stability of the output results are better than BP neural network . This study shows that : FNN and RBFNN water quality assessment and prediction of water quality is feasible in theory , in practice the value of further research and development , has a good prospect .

Related Dissertations

  1. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  2. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  3. Research on the Early-warning Technical System for the Water Environment of the River Network,X853
  4. Study on Risk Identification and Evaluation of Manufacturing Green Products R & D,F205;F224
  5. Study on the Technique of Information Fusionapplied to Enbedded Driver Fatigue Detection,TP368.12
  6. Improved Mathematical Model of Spatial Information Processing Based on Fuzzy Technology,O159
  7. Study on Application of Solar Energy Street Lamp Intelligent Controller,TM923.5
  8. Researches on the Application of the Neuron-MOS in the Neural Network,TP183
  9. The Research and Design of Pressure Cooker System Based on Fuzzy Neural Network,TM925.5
  10. The EMG Pattern Recognition System Based on Generalized Dynamic Fuzzy Neural Network,TP183
  11. Research on Evaluating the Feature Fatigue’s Effect on Customer Equip,F224
  12. AC Drive Sliding Control Algorithm,TP273
  13. One kind of structure in the depth of learning prototype classification method,TP18
  14. University Human Resources Information Management System Design and Implementation,TP311.52
  15. The Design of Identification System for Power Marketing Services,TP391.41
  16. Slurry pipeline transportation system, process monitoring and fault diagnosis,F426.1
  17. Consider short-term load forecasting PV,TM715
  18. Based on RBF artificial neural network in the application of PCB drilling process,TN405
  19. Networked Control System Fault Diagnosis and Fault Tolerant Control,TP273
  20. Linear guide system Elevator single electromagnetic levitation RBF neural network sliding mode control,TP273
  21. Optimization algorithm based on artificial intelligence Melt Index Prediction Modeling Optimization,TQ325.14

CLC: > Environmental science, safety science > Environmental Quality Assessment and Environmental Monitoring > Analysis and Evaluation of Environmental Quality > Water Quality Assessment
© 2012 www.DissertationTopic.Net  Mobile