Dissertation > Excellent graduate degree dissertation topics show

Simulation and Prediction of Microstructure and Properties of Hot-rolled Steels Based on Physical Metallurgy and BP Neural Network

Author: LiJunKai
Tutor: LiuZhenYu；HuHengFa
School: Northeastern University
Course: Materials Processing Engineering
Keywords: Hot strip Organizational performance Predictive simulation Data Extraction Physical Metallurgy model BP neural network
CLC: TG335.11
Type: Master's thesis
Year: 2008
Downloads: 45
Quote: 0
Read: Download Dissertation

Abstract


The steel materials currently facing fierce competition from other material. In order to improve product quality, reduce production costs, and modeling of Materials Research, intelligent, information technology, hot-rolled steel organizational performance prediction and control has become a research focus in recent years. The development of computer technology and automatic control technology for steel organizational performance prediction and control technology in the field of application. Microstructure evolution and predict the mechanical properties of the product by the numerical simulation of hot rolling process, may lead to lower production costs, increase productivity, and promote the purpose of the development of new products and new processes. Meishan Steel 1422mm hot rolling production line, using the the Physical Metallurgy model and BP neural network model, the establishment of the microstructure evolution and organization - performance prediction system and a laboratory controlled rolling and controlled cooling. The contents of the paper mainly include the following aspects: (1) in-depth understanding of the L2-level data report based on the programmed batch extraction coil number of steel coils and hot rolling process parameters, and combined with database technology associated chemical composition of the steel coils, process parameters and mechanical properties, and provide a lot of production data for the of Physical Metallurgy model and artificial neural element model. (2) Physical Metallurgy theory, summarize previous research foundation established the Physical Metallurgy model microstructure evolution in the description of hot strip production process, including dynamic recrystallization, static recrystallization flow stress, dislocation density and phase transformation kinetics model. Through computer simulations, the calculated and measured values ​​are in good agreement. (3) based on the physical metallurgy knowledge and on-site research, screening chemical composition and hot rolling process parameters as input parameters, the use of separate modeling established BP neural network model of the yield strength, tensile strength and elongation. Empirical formula and a large number of tests, to determine the best network number of hidden units. Network to obtain high prediction accuracy. (4) of the Q235 and X52 controlled rolling and controlled cooling experiment results show that: the key is to improve the mechanical properties of the hot rolled strip unrecrystallized reduction rate in the final rolling important optimization of process parameters such as temperature and coiling temperature combination. Unrecrystallized using large reduction, while reducing the final rolling temperature, and low temperature coiling, can improve the strength of the product, and to maintain a high elongation. Provide guidance and the TMCP Production formulation designed so as to the composition of the steels.

Related Dissertations

  1. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  2. Research on Visual Servo System of Mechanical ARM,TP242.6
  3. Municipal tourism land use planning environmental impact assessment,X820.3
  4. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  5. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  6. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  7. Study on Luohe Technical Supervision Bureau of Food Safety Early Warrning System Based on Neural Network,F203
  8. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  9. Research on Automatic Reading System for Digital Meters,TP391.41
  10. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  11. The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
  12. Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
  13. The Research and Design of Converter Steelmaking Endpoint Guiding System,TF345
  14. Analysis on Water Ecological Carrying Capacity of Jiangxi Province,TV213.4
  15. Research Offingerprint of Communication Behavior,TP311.13
  16. Research of the Electrode Lifting Hydraulic System of the 60t Electric Arc Furnace,TF748.41
  17. In-furnace Temperature Information Included Combustion Optimization of a Utility Boiler,TK227.1
  18. Research on Daily Load-forecasting for Power Grid Based on ANN,TM715
  19. Study on Safety Comprehensive Assessment of Hydro-Power Construction Sites,TV513
  20. A Research on Power Coal Blending Model of Bituminous Coal Blended with Indonesian Coal,TK227.1
  21. Study on Agricultural Machinery Injury in North of China and Related Risk Factors,R139

CLC: > Industrial Technology > Metallurgy and Metal Craft > Metal pressure processing > Rolling > Rolling process > Rolling method > Hot-rolled
© 2012 www.DissertationTopic.Net  Mobile