A new approach for CMS RPC current monitoring using Machine Learning techniques

• Published in: Journal of instrumentation Vol. 15; no. 10; p. C10009
• Main Authors: Samalan, A., Tytgat, M., Zaganidis, N., Alves, G.A., Marujo, F., Araujo, F. Torres Da Silva De, Costa, E.M. Da, Damiao, D. De Jesus, Nogima, H., Santoro, A., Souza, S. Fonseca De, Aleksandrov, A., Hadjiiska, R., Iaydjiev, P., Rodozov, M., Shopova, M., Sultanov, G., Bonchev, M., Dimitrov, A., Litov, L., Pavlov, B., Petkov, P., Petrov, A., Qian, S.J., Bernal, C., Cabrera, A., Fraga, J., Sarkar, A., Elsayed, S., Assran, Y., Sawy, M. El, Mahmoud, M.A., Mohammed, Y., Combaret, C., Gouzevitch, M., Grenier, G., Laktineh, I., Mirabito, L., Shchablo, K., Bagaturia, I., Lomidze, D., Lomidze, I., Bhatnagar, V., Gupta, R., Kumari, P., Singh, J., Amoozegar, V., Boghrati, B., Ebraimi, M., Ghasemi, R., Najafabadi, M. Mohammadi, Zareian, E., Abbrescia, M., Aly, R., Elmetenawee, W., Filippis, N., Gelmi, A., Iaselli, G., Leszki, S., Loddo, F., Margjeka, I., Pugliese, G., Ramos, D., Benussi, L., Bianco, S., Piccolo, D., Buontempo, S., Crescenzo, A. Di, Fienga, F., Lellis, G. De, Lista, L., Meola, S., Paolucci, P., Braghieri, A., Salvini, P., Montagna, P., Riccardi, C., Vitulo, P., Francois, B., Kim, T.J., Park, J., Choi, S.Y., Lee, K.S., Goh, J., Lee, H., Eysermans, J., Estrada, C. Uribe, Pedraza, I., Castilla-Valdez, H., Sanchez-Hernandez, A., Herrera, C.A. Mondragon, Navarro, D.A. Perez, Sanchez, G.A. Ayala, Carrillo, S., Vazquez, E., Radi, A., Ahmad, A., Hoorani, H., Shah, M.A., Crotty, I.
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.10.2020
• Subjects: Luminosity; Machine learning; Monitoring; Parameters; Sensors
• ISSN: 1748-0221; 1748-0221
• DOI: 10.1088/1748-0221/15/10/C10009

The CMS experiment has 1054 RPCs in its muon system. Monitoring their currents is the first essential step towards maintaining the stability of the CMS RPC detector performance. The current depends on several parameters such as applied voltage, luminosity, environmental conditions, etc. Knowing the influence of these parameters on the RPC current is essential for the correct interpretation of its instabilities as they can be caused either by changes in external conditions or by malfunctioning of the detector in the ideal case. We propose a Machine Learning(ML) based approach to be used for monitoring the CMS RPC currents. The approach is crucial for the development of an automated monitoring system capable of warning for possible hardware problems at a very early stage, which will contribute further to the stable operation of the CMS RPC detector.