Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: English
- Document No: 42841 (55)
- University: Sharif University of Technology, International Campus, Kish Island
- Department: Science and Engineering
- Advisor(s): Mortazavi, Mohammad; Ghorshi, Mohammad Ali
- Abstract:
- Structural Health Monitoring (SHM) means to give a diagnosis of the “state” of the subjects. Small leaks along the entire lengths of oil pipelines are detected and located by monitoring.Nowadays health monitoring of pipeline in water, gas, oil and chemical industry has been the focus of researchers. This is due to the fact that leak accidents may cause great economic problems to human resources as well as extreme environmental pollution. This project focuses on a visual and photographic observation system as leakage detection to monitor long range pipelines. In this system, several cameras with overlapping views are located along the entire lengths of pipelines. We are using digital cameras for external pipelines and X-ray cameras for internal pipelines. One of the most important issues related to image processing is how to store and also transmit this information to the base station. Hence, we require using small storage and yet a lossless image compression scheme to transfer data to the base station. In digital oil pipeline images, there is a correlation between neighboring pixels. Therefore, it is obvious that some information in rows or columns related to images is redundant. To remove this extra data we can use a lossless image compression with a lesser complex method such as Differential Pulse Code Modulation (DPCM). DPCM is a simple and efficient method for transforming images in a manner suitable for hardware implementation. In our proposed method, we use a predictive neural network as an adaptive lossless compression system to find out the best coefficients of DPCM. The neural network predicts the pixels from neighboring pixels of the original imagein real-time to minimize errors between an original image and its predictive image which is used for storage and transmission. This method shows a good improvement in characteristics of image compression such as entropy and Signal to Noise Ratio (SNR). Finally, in the base station, we can locate and detect small leaks of oil pipelines by comparison between images.
- Keywords:
- Neural Network ; Pipelines ; Structural Health Monitoring (SHM)Pipline ; Differential Pulse Code Modulation (DPCM)
Digital Object List
-
محتواي پايان نامه
- view
Bookmark