Development of Underwater Quality and Natural Gas Leak Detection System using Fuzzy Neuro Approach Image Processing By: Edgar Caburatan Carrillo II Thesis Proposal for the degree of Master of Science in Mechanical Engineering De La Salle University Manila, Philippines
57
Embed
Development of underwater quality and natural gas leak detection system using fuzzy neuro approach image processing
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Development of Underwater Quality and Natural Gas Leak Detection
System using Fuzzy Neuro Approach Image Processing
By: Edgar Caburatan Carrillo II
Thesis Proposal for the degree of
Master of Science in Mechanical Engineering
De La Salle University Manila, Philippines
Natural Gas Pipeline System
1. Introduction
1.1. Background of the Study
Worldwide Natural Gas Production Natural Gas in the Philippines Problem with Natural Gas leaking Existing Technologies of Natural Gas Proposed Solution
1. Introduction
1.1. Background of the Study Worldwide Natural Gas Production¾ of World Energy consumption from Natural gas,liquid and coal by 2040 (USEIA, 2013) Natural Gas in the PhilippinesProjects of Philippine government to transport natural through underground and underwater piping networks include: BATMAN 1, SU-MA (Sucat-Malaya), BATMAN 2, ET LOOP and BATCAVE (DOE, 2014) Problem with Natural Gas leaking economic and environmental risks (TRB, 2004)
Existing Technologies of Natural Gas Existing technology need to be improve either by having a leak detection technology that is cheap and accurate (Murvay & Silea, 2012).
As analyzed by Albert Einstein in 1905, this experimental evidence for kinetic theory is generally seen as having confirmed the existence of atoms and molecules.
Fuzzification- Process of transforming crisp values into grades of membership for linguistic terms of fuzzy sets.
Structure of Fuzzy Image Processing
Fuzzification process (coding of images)
History of Fuzzy Logic
1.2. Statement of the Problem
Existing technology
either expensive (Meng, Yuxing, Wuchang, & Juntao, 2011)
less accurate (Doorhy, 2011)
Proposed solution
A natural gas leak detection system that is cheap and accurate by using Fuzzy Neuro Approach.
Reasons behind:
Fuzzy neuro approach was used by many researchers in detection of water leaks and the like.
1.3. Objective of the Study
The main purpose of this study is to develop a water quality and natural
underwater gas leak detection system using fuzzy-neuro image processing. This study specifically aims:
1.To develop an aquarium prototype for an underwater water quality and gas leak detection experimental set-up,
2. To determine the quality of water using fuzzy logic algorithm,
3. To develop an image processing algorithm to detect water bubbles on both clean and average environment,
4. To develop a neural network algorithm to detect gas leaks in the underwater pipeline system using bubble formation,
5. To verify the accuracy, reliability and robustness of the proposed algorithm in determining gas leaks underwater.
1.4. Significance of the Study
The creation of study will trigger awareness in the stakeholders in the area and create a worldwide impact. These stakeholders include the companies, people occupying in the area, government, investors, and experts. .
1.5. Scope of the StudyScope: Natural Gas Lab scale PC based model Contaminant addition
2.Review of Related Literature
2.1. Properties of Natural Gas
2.Review of Related Literature
2.2. Leak Detection Method known by Science(Murvay & Silea, 2012)
Detection of Bubbles1. Classification2. Feature Extraction 3. Pattern Recognition
Techniques can be used in image processing:1. Pixelation2. Neural Networks3.Linear Filtering4. Principal Component Analysis5. Hidden Markov Models6. Anisotropic Diffusion7. Partial Diffential Equations8. Self-organizing Maps9. Wavelets
Object RecognitionAppearance-based method1. Edge Matching2. Divide and Conquer Search3. Greyscale Matching4. Gradient Matching5. Histogram of receptive field responses6. Large model bases
Motion detection is the process of detecting a change in position of an object relative to its surroundings or the change in the surroundings relative to an object.
Motion can be detected by:
1. Infrared (Passive and active sensors)2. Optics (video and camera systems)3. Radio Frequency Energy (radar, microwave and tomographic motion detection)4. Sound (microphones and acoustic sensors)5. Vibration (triboelectric, seismic, and inertia-switch sensors)6. Magnetism (magnetic sensors and magnetometers)
http://en.wikipedia.org/wiki/Motion_detection
Optical Flow
Optical flow or optic flow is the pattern of apparent motion of objects, surfaces, and edges in a visual scene caused by the relative motion between an observer (an eye or a camera) and the scene
Neural Network Structure
4. Methodology
5. Summary Answering Specific Objectives1. To develop an aquarium prototype for an underwater water quality and gas leak detection experimental set-up,
2. To determine the quality of water using fuzzy logic algorithm,
3. To develop an image processing algorithm to detect water bubbles on both clean and average environment,
4. To develop a neural network algorithm to detect gas leaks in the underwater pipeline system using bubble formation,
5. To verify the accuracy, reliability and robustness of the proposed algorithm in determining gas leaks underwater.
1. To develop an aquarium prototype for an underwater water quality and gas leak detection experimental set-up
2. To determine the quality of water using fuzzy logic algorithm
Quality of Water Expected recognition rate Actual recognition rate
Clean 80% More than 80%
Dirty 80% More than 80%
3. To develop an image processing algorithm to detect water bubbles on both clean and average environment
Quality of Water Previous recognition rate Actual recognition rate
Clean 80% More than 80%
Dirty 80% More than 80%
4. To develop a neural network algorithm to detect gas leaks in the underwater pipeline system using bubble formation
Quality of Water Previous recognition rate Actual recognition rate
Clean 90% More than 90%
Dirty 90% More than 90%
5. To verify the accuracy, reliability and robustness of the proposed algorithm in determining gas leaks underwater.
Proposed Algorithm Actual recognition rate
Fuzzy Logic Water Detector More than 80%
Neural Network gas leak detector
More than 90%
Image Detector Created More than 90%
5. Appendix A: Gantt Chart
5. Appendix B: Costing
Thank You For Listening!The Researcher is now ready to