الفهرس 
INTRODUCTIONOnly 14 pages are availabe for public view
 |  | from | 133 |  |  |
| | | from | 133 | | |
Abstract
Machine fault problems are broad sources of high maintenance cost and unwanted downtime across the industries. So that, accurate fault diagnosis of modern machinery is becoming of paramount importance concern in their reliability, availability, and safety. Numerous condition monitoring and diagnostics methodologies are utilized to identify the machine faults based on vibration signature analysis, lubricant signature analysis, noise signature analysis, and temperature monitoring employing the appropriate sensors and instruments. Vibration signature analysis techniques for machine fault identification are the most popular technique. As the machine is operating properly, the vibration is little and constant, but when faults develop and some of the dynamic process in the machine changes, there will be changes in vibration spectrum observed.
In the present work, artificial intelligence (AI) techniques are used and expert diagnostics system is developed for identifying various rotating machinery faults employing artificial neural network (ANN), and fuzzy logic (FL). Fuzzy inference system (FIS) is used for induction motor electrical faults identification, and ANN is applied for some mechanical faults using vibration signals. Artificial intelligence techniques showed that they can provide an effective method for fault diagnosis in rotating machinery in terms of reliability. A real world application was applied using the two techniques individually and collectively. Both proved to give high accurate results for diagnosing faults. Thus, these systems can be called self-fault finding tools and not need, in this case, the interference of maintenance personnel. They will only be responsible for inputting the appropriate data to the system.