Dissertation > Excellent graduate degree dissertation topics show

Bionics Intelligence Model Based on RBF Neural Network and Its Application in Propylene Polymerization Process

Author: LouWei
Tutor: LiuXingGao
School: Zhejiang University
Course: Systems Engineering
Keywords: The intelligent bionic optimization and statistical modeling Melt Index Prediction Radial basis function neural network Principal Component Analysis Chaos optimization Genetic Algorithms
CLC: TP183
Type: Master's thesis
Year: 2008
Downloads: 142
Quote: 3
Read: Download Dissertation


Melt Index (Melt Index, MI) is an important part of the polymerization of propylene production process quality control, which determines the quality of the products of different grades and different grades of products. Especially difficulties due to the lack of online analytical instruments, melt index measurement by manual sampling, the offline laboratory analysis, interval and delay makes it difficult to control production quality, allowing MI forecast to become the olefin polymer production control research frontier and hot. Strong correlation with the production process for propylene polymerization, strongly nonlinear production process characteristics, as well as statistical modeling parameters facing the choice of the randomness and different modeling human factors issues , the intelligent bionic optimization method with principal component analysis, combined neural network and other statistical methods to work, to the production of polypropylene melt index of optimal soft measurement model to improve the prediction accuracy of the model, eliminating the statistical modeling of human factors such as random impact. The full text of the main work and contributions are as follows: 1. Introduced the of polymerization industry and polypropylene production background knowledge and statistical modeling methods and intelligent bionic method Melt Index Prediction Research and propylene polymerization process, a review of the research. Production process for propylene polymerization strongly nonlinear, strong correlation was established based on RBF neural network method and Principal Component Analysis PCA-RBF melt index which combines the prediction model, and a petrochemical enterprise polypropylene production process actual industrial production data as an example, the results show that the conventional PCA-RBF model can not meet the requirements of industrial production. PCA-RBF forecasting model based on the optimization method based on chaotic Logistic mapping function PCR (PCA-Chaos-RBF) the optimal melt index forecast model for automatic optimization of key parameters, industrial the results of the actual data show that the effectiveness of the the optimal the MI forecasting model proposed. 4 on the basis of the above research, taking into account the limitations of chaos optimization method, and further introduction of genetic algorithm, the production of polypropylene melt index forecast PCGR (PCA-Chaos-GA-RBF) global optimal model, which Chaos optimization to optimize several key parameters, the results of industrial case studies that establish the validity of the prediction model; further establish the process of PGR (PCA-GA-RBF) global optimal model with PCGR model detailed comparative study, industrial case study results show that they have almost the same forecast accuracy that in the the MI prediction of genetic algorithm has good ability of global optimization, will have a good prospect. 5 In this paper, the above findings with domestic and international public reported results of a detailed comparative study, the results show that the proposed PCGR model and PGR model promotion test in the industrial actual production data on the root mean square error of the forecast results up to 1.19%, 1.25%, reported the best results with the international community so far 1.51% (Han Professor in the Journal of Applied Polymer Science Open results) compared, respectively, the prediction error is reduced by 21.2% and 17.2%.

Related Dissertations

  1. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  2. Development of the on-line Training and Examination System of Army,TP311.52
  3. Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
  4. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  5. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  6. Macaca mulatta palm morphological study of pattern ridge count,Q954
  7. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  8. Based on Genetic Algorithm Pishihang irrigation canal water allocation marshalling model of,S274
  9. Genetic Algorithm in logistics and warehousing Optimization Research,F259.2
  10. Mining resources based on genetic algorithm optimization model of,O224
  11. Research on Cultural Industrial Competitiveness of Chong Qing,F224
  12. The Research and Application of Modified Algorithms About Fuzzy Predictive Functional Control,TP273
  13. Optimal Control of Emulsion System in Cold Rolling,TP273
  14. Research on the Marshalling-scheduling Model and Algorithms of Freight Trains Based on Game Theory,O225
  15. The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
  16. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  17. Multi-directional Mutation Genetic Algorithm and Research on Neural Network Optimization,TP18
  18. The Application of Using Genetic Algorithms on Universities Course-arranging System,TP18
  19. Research on Mobile Robot Path Planning and Simulation Realization,TP242
  20. Research on Routing Algorithmin Sensor Networks Based on Cluster with Mobile Sink,TP212.9
  21. Research and Implement of the Theme Crawler for Automotive Industry,TP391.3

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile