Dissertation > Excellent graduate degree dissertation topics show

Research on Prediction Method of Elevator Traffic Flow Based on Chaos Theory

Author: WangSheng
Tutor: WanJianRu;LuoZhiQun
School: Tianjin University
Course: Electrical Engineering
Keywords: chaos theory BP neural network time series prediction Lyapunovexponent attractor dimension neural network structure prediction accuracy reliability
CLC: TU857
Type: Master's thesis
Year: 2012
Downloads: 2
Quote: 0
Read: Download Dissertation

Abstract


Elevator traffic flow predictive is drawing more and more attention, as theelevator vertical traffic problem becomes increasingly serious. The elevator systemscheduling is the key to solve the vertical traffic problems. Essential data can beprovided to make system scheduling through elevator traffic flow prediction, thusvertical traffic problem will be greatly ameliorated.Firstly, change curve of the elevator traffic flow time series graph is analysised inthis paper,and it can be found that the elevator traffic flow time series have basicchaotic characteristics. Then, studying of the chaos theory indicates that there are twobasic characteristics of chaotic systems: Lyapunov exponent and attractor dimension.The method for getting the delay time, embedding dimension and distinguishing thetime series of chaotic characteristics are studied under the phase space reconstructiontheory. C-C method is adopted to calculating the delay time and embed dimensionthrough the and reconstructing the elevator traffic flow time series. This paper alsocomes up with the maximum Lyapunov exponent through Worf method and makesout the Poincare section. Chaotic characteristics of the elevator traffic flow time seriesare judged through qualitative method(the Poincare section method) and quantitativemethod(the maximum Lyapunov exponent method).Secondly, the BP neural network structure with a single input/single output isused for elevator traffic flow time series prediction. On this basis, proposing aimproved BP neural network prediction method with a multi-input/single outputneural network architecture. Simulation results show that the improved BP neuralnetwork prediction method can be very suitable for the elevator traffic flow timeseries prediction.Finally, an elevator traffic flow prediction method of BP neural network based onchaos theory is proposed. Simulation results show that this prediction model isreliable and the prediction accuracy is satisfied. Comparing the two methods, theprediction method of BP neural network based on chaos theory is better than theimproved BP neural network prediction method both in network structure, predictionaccuracy and model reliability.

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. Development and Preliminary Application of the Questionnaire on Emotional Labour of the Middle School Teacher,B841
  4. Municipal tourism land use planning environmental impact assessment,X820.3
  5. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  6. The Research on Reliability of Low-Voltage Power Line Communication,TM73
  7. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  8. The Research and Application of Software Reliability Test for User Right Management System,TP311.53
  9. Research on Subsea Pipeline Repair Coupling,TE973
  10. Research and Application on Reliability Technology of Mine Hidrological Monitoring System,TD742.1
  11. Mine Risk Information Integration and Intelligent Early Warning,X936
  12. Body Sensor Networks Adaptive Communication Protocol,TP212.9
  13. Periodic testing of the storage system reliability model,O213.2
  14. Research of Virus Detection Methods Based on Multiple Anti-virus Softwares Collaboration,TP309.5
  15. The Optimization Research of Feedforward Neural Network Based on Genetic Algorithms,TP183
  16. JSYJ Company Purchasing Risk Management Research,F426.92
  17. The Research on the Highway Pavement System with Neural Network and Combination Forecast,TP315
  18. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  19. Amendment of Mental Health Evaluation Scale for Chinese Nuclear Power Plant Operators,B849
  20. Degradation of Amorphous Silicon Thin Film Transistors under Gate and Drain Voltage Bias Stress,TN321.5
  21. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662

CLC: > Industrial Technology > Building Science > Housing construction equipment > Mechanical and Electrical Equipment > Elevator Engineering
© 2012 www.DissertationTopic.Net  Mobile