Fault detection of fluid carrying pipes using artificial intelligence - دانشکده فنی و مهندسی
Fault detection of fluid carrying pipes using artificial intelligence
نوع: Type: Thesis
مقطع: Segment: masters
عنوان: Title: Fault detection of fluid carrying pipes using artificial intelligence
ارائه دهنده: Provider: Behnaz Rezaei
اساتید راهنما: Supervisors: Dr.Yones Solgi, Dr.Abbas Ramezani
اساتید مشاور: Advisory Professors: Dr.Majid Ghanei Zarch, Dr.Alireza Kokabi
اساتید ممتحن یا داور: Examining professors or referees: Dr. Ali Kalantar nia, Dr.Razieh Torkamani
زمان و تاریخ ارائه: Time and date of presentation: 2025
مکان ارائه: Place of presentation: 33
چکیده: Abstract: Today, in the steel industry, the discussion of clogging and cracking of fluid carrying pipes is one of the most challenging topics. Failure to recognize this defect in the steel industry will lead to unfortunate and irreparable consequences such as explosions , leaks, etc. In the pipeline transmission system, defects will occur in the system due to atmospheric conditions over time, corrosion of pipes due to the passage of time, the presence of natural environmental phenomena such as floods and earthquakes, and other environmental damages, and some of these frequent defects include pipe clogging, pipe leakage, etc. This important matter, by helping preventive corrective measures, reduces losses, makes proper use of time, and also saves money. In the absence of a suitable method of fault diagnosis, the stated challenges will lead to unfortunate consequences such as pipeline explosion, threats of personal injury, reduction of productivity and transmission, etc. Now, the aim of this thesis is to present a smart and efficient fault diagnosis method that can preform the best in the shortest time. The proposed method in this thesis is to design an intelligent method based on machine learning methods. The proposed method has many advantages, some of these advantages include not needing a model and dynamic relationships of the system, being intelligent, having fast diagnosis, being resistant to disturbing factors in the system such as parameter uncertainties, external disturbances of the system, etc., low error of the diagnosis system, real time, adaptability, high reliability, high security of the diagnosis system and high availability ability.