Dissertation > Excellent graduate degree dissertation topics show

Missing Data Imputation in Bridge Health Monitoring System Base on Hybrid Model of SARIMA and Neural Network

Author: PingChunLei
Tutor: ZuoZuoWu
School: Chongqing University
Course: Instrument Science and Technology
Keywords: Missing Data Fill Bridge Health Monitoring System Neural Networks SARIMA model Hybrid model
CLC: TP183
Type: Master's thesis
Year: 2011
Downloads: 53
Quote: 0
Read: Download Dissertation

Abstract


Missing data widely exists in the survey and engineering fields. The lack of data will cause incomplete information, and thus bring a very negative impact on subsequent analysis and processing. Bridge Health Monitoring System can install the structural information in the the bridge key parts of the sensor feedback to determine the health status of the bridge, and bridges for bridge owners and users to determine whether to provide an important basis for security. However, the long-term work in the field in the harsh environment of the monitoring system is often due to the sensors and monitoring equipment wear and tear, aging, or even damage and seasonal electricity deletion reason a large number of missing data, which greatly affect the evaluation of the health status of a bridge. Bridge health monitoring system, the lack of data for the study, the accurate evaluation of bridge health status under lower error method of missing data to fill a small sample, so this work has practical significance. This paper analyzes the reasons for the lack of systematic data bridge health monitoring system, introduced several common bridge type of lack of monitoring data, and the Chongqing Yangtze River Bridge Dafosi health monitoring system data, for example, analysis of the bridge monitoring parameters temperature and The correlation between the deflection characteristics of the parameters and variables and variable; summarizes the processing method of the existing lack of data in other areas, combined with the advantages and disadvantages of these methods based on the characteristics of the actual monitoring data of the largest Buddhist temple Bridge, using a hybrid model of neural network ANN (Artificial Neural Network) missing data based on time series season summation autoregressive moving average SARIMA (Seasonal Auto Regressive Integrated Moving Average) and fill method. In order to contrast the advantages of this method using time series SARIMA method and linear regression method, respectively SARIMA and hybrid neural network-based model with the proposed deletion of several common bridge health monitoring system data processed, the results show that: based on the SARIMA and hybrid neural network model to fill method accuracy and lower error better fill; the SARIMA model the fill effect, followed by. Actual missing data to fill the results show that the proposed method based on the SARIMA neural network hybrid model is able to quickly fill a to reach the lower residuals missing small sample data.

Related Dissertations

  1. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  2. Multiple ANN/HMM Hybrid Used in Speech Recognition,TN912.34
  3. Rock-fill Concrete Experiments on Comprehensive Properties and Studies on Thermal Stress,TU528
  4. Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
  5. Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
  6. The Statistical Inference for Count Data with Zero-inflation and Over-dispersion,C81
  7. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  8. Image Restoration Method Research and Its Application Based on Probability PCA,TP391.41
  9. Multi- license plate location method based on CNN's Intelligent Transportation Systems Research,TP391.41
  10. Research on Inventory Control and Optimization of ATO System in GR Elevator Company,F426.6;F224
  11. Research on the Models of GPS Height Fitting Based on BP Neural Network and Their Applications,P228.4
  12. Experimental Research on Process Parameter Optimization for Selective Wave Soldering,TG425.1
  13. Research of QoS Optimization Based on Neural Network Prediction for Ethernet Passive Optical Network,TN929.1
  14. Sensitivity Study and Application of Complex Variabal Weight Function Neural Network,TP183
  15. Researches on the Application of the Neuron-MOS in the Neural Network,TP183
  16. A Reduction Method for Artificial Neural Network Inputs Based on An Improved Genetic Algorithm,TP18
  17. On-line Monitoring of Tool Wear for Mass Production,TG71
  18. Modeling of Photovoltaic Cells and Its Application in Energy Prediction,TM914.4
  19. Research on Evaluating the Feature Fatigue’s Effect on Customer Equip,F224
  20. Delay Neutral System Stability Analysis of Neural Networks,O175.13
  21. One kind of structure in the depth of learning prototype classification method,TP18

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