Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Mehmet Mercangöz"'
Publikováno v:
IFAC-PapersOnLine. 53:11614-11619
We demonstrate the application of automated machine learning to the problem of identifying dynamic process models using recurrent neural networks (RNNs). The general concept relies on continuous monitoring of input-output data from a plant and the pr
Publikováno v:
Computers & Chemical Engineering. 170:108104
Autor:
Yilin Zhuang, Yixuan Liu, Akhil Ahmed, Zhengang Zhong, Ehecatl A. del Rio Chanona, Colin P. Hale, Mehmet Mercangöz
Publikováno v:
Computers in Industry. 143:103747
Autor:
Tor Olav Stava, Andrea Cortinovis, Sture Van de moortel, Mehmet Mercangöz, Arne-Marius Ditlefsen, Erling Lunde, Thomas Besselmann
Publikováno v:
Journal of Process Control. 74:76-87
This article is concerned with the impact of voltage or power dips on large electric driven gas compressors (EDC) in typical oil and gas applications. EDCs are sensitive to voltage dips affecting the operation of the gas compression process through t
Autor:
Andrea Cortinovis, Arne-Marius Ditlefsen, Sture Van de moortel, Thomas Besselmann, Erling Lunde, Terje Knutsen, Pieder Jorg, Mehmet Mercangöz, Harald Fretheim, Tor Olav Stava
Publikováno v:
IEEE Transactions on Industry Applications. 54:1460-1468
Grid voltage disturbances pose serious problems to gas compression stations powered by drives such as load commutated inverters (LCI). Until recently, drive control systems used in industrial practice were not capable of handling reduced grid voltage
Autor:
Andrea Cortinovis, Nicolas Lanzetti, Luis Dominguez, Colin N. Jones, Mehmet Mercangöz, Yingzhao Lian
Publikováno v:
ECC
Autonomous operation of industrial plants requires a cheap and efficient way of creating dynamic process models, which can then be used to either be part of the autonomous systems or to serve as simulators for reinforcement learning. The trends of di
Autor:
Andrea Cortinovis, Antonio De Marco, Mehmet Mercangöz, Matteo Zovadelli, Diego Pareschi, Sergio Bittanti
Publikováno v:
Computers & Chemical Engineering. 88:145-156
Compressor stations on natural gas pipelines are typically composed of multiple parallel compressors for operational flexibility. The aim of load sharing optimization is to operate the compressor units of a gas compression station in an energy effici
Publikováno v:
IFAC-PapersOnLine. 49:949-954
This paper investigates the influence of voltage dips on large electric driven gas compressors (EDC) considering a typical application in the oil and gas industry. Voltage or power dips are electric disturbances encountered in EDC which are mainly ca
Autor:
Alejandro Marchetti, Andrea Cortinovis, Dominique Bonvin, Predrag Milosavljevic, Mehmet Mercangöz, Timm Faulwasser
Publikováno v:
Applied Energy. 272:114883
This paper investigates the problem of load-sharing optimization of gas compressors in the presence of uncertainty. The objective is to operate a set of compressor units in an energy-efficient way, while at the same time meeting a varying load demand
Autor:
Andrea Cortinovis, Mehmet Mercangöz, Timm Faulwasser, Dominique Bonvin, René Schneider, Predrag Milosavljevic
Publikováno v:
ECC
This paper investigates the optimal load-sharing problem of serial gas compressors in the presence of plant- model mismatch. The problem is formulated as a static real- time optimization task that is solved via modifier adaptation for interconnected