Amirkabir University of Technology Amirkabir Journal of Mechanical Engineering 2008-6032 52 3 2018 03 13 Identification of Cavitation Phenomenon in Centrifugal Pump by Artificial Immune Network Method Identification of Cavitation Phenomenon in Centrifugal Pump by Artificial Immune Network Method 717 730 2847 10.22060/mej.2018.13622.5686 FA Seyed Mostafa Matloobi PhD student/IUST Mohammad Riahi Hamed Sadeghi IUST Journal Article 2017 11 04 Reduce the cost of unscheduled shutdown and enhance the reliability of systems, is one of the important goals for various industries that could be achieved by condition monitoring. Cavitation is a common phenomenon in centrifugal pumps which causes the damage and its true identification in early stage is too important. In this paper cavitation is identified by use of artificial immune net that is modeled on the function of the human immune system. For this purpose, after data collection by a laboratory setup and extraction of various features, feature selection and dimensions reduction were done by artificial immune method and then with artificial immune net method, the system condition was identified. Finally, the results of this study were compared with the principal component analysis method and the results of nonlinear supportive vector machine, multi-layer artificial neural network, K-means and fuzzy C-means clustering. Reduce the cost of unscheduled shutdown and enhance the reliability of systems, is one of the important goals for various industries that could be achieved by condition monitoring. Cavitation is a common phenomenon in centrifugal pumps which causes the damage and its true identification in early stage is too important. In this paper cavitation is identified by use of artificial immune net that is modeled on the function of the human immune system. For this purpose, after data collection by a laboratory setup and extraction of various features, feature selection and dimensions reduction were done by artificial immune method and then with artificial immune net method, the system condition was identified. Finally, the results of this study were compared with the principal component analysis method and the results of nonlinear supportive vector machine, multi-layer artificial neural network, K-means and fuzzy C-means clustering. https://mej.aut.ac.ir/article_2847_fdf1bc5669e8ff5ba45d02fded729feb.pdf