Dissertation > Excellent graduate degree dissertation topics show

Research on Condition Monitoring and Trend Prediction Technique of Centrifugal Compressor K5403

Author: WangQiuXiang
Tutor: YuDeJie
School: Hunan University
Course: Mechanical and Electronic Engineering
Keywords: Compressor Predictive maintenance Condition Monitoring Trend forecasting Neural Networks Object-oriented technology
CLC: TH452
Type: Master's thesis
Year: 2009
Downloads: 138
Quote: 0
Read: Download Dissertation

Abstract


K5403 centrifugal compressor is the key equipment Baling Petrochemical Co., Ltd., Once the equipment failure, not only seriously affect the production, bring significant economic losses to the enterprise, but also caused a serious accident casualties. K5403 centrifugal compressors study conducted condition monitoring and trend forecasting techniques in order to achieve the predictive maintenance of the unit. Thesis research: elaborated condition monitoring and trend forecasting technology research purpose, meaning and the course of development and trends, combined with K5403 centrifugal compressor maintenance of the status quo and the user needs to clarify the condition monitoring and trend forecasting technology applications at K5403 centrifugal compressor system necessity; according to the structural features of the K5403 centrifugal compressor unit common form of several fault (such as: imbalance, misalignment, static and dynamic RUBBING rotor support system links looseness fault rolling bearing fault and surge), failure mechanism, given the failure characteristics, several commonly used method of fault diagnosis based on the vibration signal analysis and processing; 3 with the actual needs of the enterprise development K5403 centrifugal compressor condition monitoring and trend forecasting system briefly system key technologies, including object-oriented technology, the virtual instrument technology and configuration technology, focus on UML-based system requirements analysis and object-oriented design ; 4. K5403 centrifugal compressor running state of the non-linear, non-stationary characteristics and advantages of the neural network, the proposed iterative multi-step the trend forecasting polynomial neural network prediction method. In this method, the polynomial neural network BP algorithm reflects the stronger generalization capability, faster convergence speed and more accurate training accuracy and make the training convergence to global optimal solution using a genetic algorithm, and compared with the conventional multi-step prediction method, iterative multi-step prediction method in the improvement in the medium-and long-term forecasts more obvious; according to the principles of system design, on the basis of the above techniques, from a hardware and software perspective designed to achieve K5403 centrifugal compressor condition monitoring and trend forecasting system. Taking into account the efficiency of data acquisition and transmission line noise immunity, selected PCI-6224 data acquisition card and signal conditioning modules; according to the modular design concept of the system functionality is divided into data acquisition, condition monitoring and status analysis and diagnosis of three module details the implementation of each module; Finally this article summary and outlook, the research and innovation, and analysis of the inadequacies of the work of this study, which raised the outlook on the follow-up work to carry out .

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  3. Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
  4. Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
  5. Research on Object-Oriented Integration Testing Method,TP311.53
  6. Responses of the Double-Cropping Rice Population Growth and Nitrogen Uptake to Density and Nitrogen Management and the Diagnosis Based on NDVI,S511
  7. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  8. Multi- license plate location method based on CNN's Intelligent Transportation Systems Research,TP391.41
  9. Research on the Models of GPS Height Fitting Based on BP Neural Network and Their Applications,P228.4
  10. Research of QoS Optimization Based on Neural Network Prediction for Ethernet Passive Optical Network,TN929.1
  11. Sensitivity Study and Application of Complex Variabal Weight Function Neural Network,TP183
  12. Multi-channel Real-time Online Monitoring System for Polymerizers,TP274
  13. Researches on the Application of the Neuron-MOS in the Neural Network,TP183
  14. A Reduction Method for Artificial Neural Network Inputs Based on An Improved Genetic Algorithm,TP18
  15. On-line Monitoring of Tool Wear for Mass Production,TG71
  16. Modeling of Photovoltaic Cells and Its Application in Energy Prediction,TM914.4
  17. Research on Evaluating the Feature Fatigue’s Effect on Customer Equip,F224
  18. Research and Development of a DSP Based Monitoring System,TV738
  19. Research on Patent Output of Universities in China,G306;F224
  20. Delay Neutral System Stability Analysis of Neural Networks,O175.13
  21. Band Entropy Method and Its Application to Fault Diagnosis of Rolling Bearings,TH165.3

CLC: > Industrial Technology > Machinery and Instrument Industry > Gas compression and transportation machinery > Compressors, compressor > Centrifugal
© 2012 www.DissertationTopic.Net  Mobile