References of "Camponogara, Eduardo"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailNonlinear Model Predictive Control of an Oil Well with Echo State Networks
Jordanou, Jean Panaioti; Camponogara, Eduardo; Antonelo, Eric Aislan UL et al

in IFAC-PapersOnLine (2018), 51

In oil production platforms, processes are nonlinear and prone to modeling errors, as the flowregime and components are not entirely known and can bring about structural uncertainties,making designing ... [more ▼]

In oil production platforms, processes are nonlinear and prone to modeling errors, as the flowregime and components are not entirely known and can bring about structural uncertainties,making designing predictive control algorithms for this type of system a challenge. In thiswork, an efficient data-driven framework for Model Predictive Control (MPC) using Echo StateNetworks (ESN) as prediction model is proposed. Differently from previous work, the ESN model for MPC is only linearized partially: while the free response of the system is kept fullynonlinear, only the forced response is linearized. This MPC framework is known in the literatureas the Practical Nonlinear Model Predictive Controller (PNMPC). In this work, by using theanalytically computed gradient from the ESN model, no finite difference method to compute derivatives is needed as in PNMPC. The proposed method, called PNMPC-ESN, is applied tocontrol a simplified model of a gas lifted oil well, managing to successfully control the plant,obeying the established constraints while maintaining setpoint tracking. [less ▲]

Detailed reference viewed: 115 (6 UL)
Full Text
Peer Reviewed
See detailRecurrent Neural Network based control of an Oil Well
Jordanou, Jean Panaioti; Antonelo, Eric Aislan UL; Camponogara, Eduardo et al

in Brazilian Symposium on Intelligent Automation, Porto Alegre 1-4 October 2017 (2017, October)

Echo State Networks (ESN) are dynamical learning models composed of two parts: a recurrent network (reservoir) with fixed weights and a linear adaptive readout output layer. The output layer’s weights are ... [more ▼]

Echo State Networks (ESN) are dynamical learning models composed of two parts: a recurrent network (reservoir) with fixed weights and a linear adaptive readout output layer. The output layer’s weights are learned for the ESN to reproduce temporal patterns usually by solving a least-squares problem. Such recurrent networks have shown promising results in previous applications to dynamic system identification and closed-loop control. This work applies an echo state network to control the bottom hole pressure of an oil well, whereby the opening of the production choke is manipulated. The controller utilizes a network to learn the plant inverse model, whose model input is the plant output and the vice-versa, and another network to compute the control action that induces a desired plant behavior. Despite the nonlinearities of the well model, the ESN effectively learned the inverse model and achieved near global setpoint tracking and disturbance rejection, with little setpoint deviation in the latter case. These results show that echo state networks are a viable tool for the control of complex dynamic systems by means of online inverse-model learning. [less ▲]

Detailed reference viewed: 57 (4 UL)
Full Text
Peer Reviewed
See detailEcho State Networks for Data-driven Downhole Pressure Estimation in Gas-lift Oil Wells
Antonelo, Eric Aislan UL; Camponogara, Eduardo; Foss, Bjarne

in Neural Networks (2017), 85

Detailed reference viewed: 103 (9 UL)
Full Text
Peer Reviewed
See detailAn Echo State Network-based Soft Sensor of Downhole Pressure for a Gas-lift Oil Well
Antonelo, Eric Aislan UL; Camponogara, Eduardo

in Iliadis, Lazaros; Jayne, Chrisina (Eds.) Engineering Applications of Neural Networks (2015)

Soft sensor technology has been increasingly used in indus- try. Its importance is magnified when the process variable to be estimated is key to control and monitoring processes and the respective sensor ... [more ▼]

Soft sensor technology has been increasingly used in indus- try. Its importance is magnified when the process variable to be estimated is key to control and monitoring processes and the respective sensor ei- ther has a high probability of failure or is unreliable due to harsh environ- ment conditions. This is the case for permanent downhole gauge (PDG) sensors in the oil and gas industry, which measure pressure and tempera- ture in deepwater oil wells. In this paper, historical data obtained from an actual offshore oil well is used to build a black box model that estimates the PDG downhole pressure from platform variables, using Echo State Networks (ESNs), which are a class of recurrent networks with power- ful modeling capabilities. These networks, differently from other neural networks models used by most soft sensors in literature, can model the nonlinear dynamical properties present in the noisy real-world data by using a two-layer structure with efficient training: a recurrent nonlinear layer with fixed randomly generated weights and a linear adaptive read- out output layer. Experimental results show that ESNs are a promising technique to model soft sensors in an industrial setting. [less ▲]

Detailed reference viewed: 71 (1 UL)
Full Text
Peer Reviewed
See detailSystem Identification of a Vertical Riser Model with Echo State Networks
Antonelo, Eric Aislan UL; Camponogara, Eduardo; Plucenio, Agustinho

in IFAC-PapersOnLine (2015), 48(6), 304-310

System identification of highly nonlinear dynamical systems, important for reducing time complexity in long simulations, is not trivial using more traditional methods such as recurrent neural networks ... [more ▼]

System identification of highly nonlinear dynamical systems, important for reducing time complexity in long simulations, is not trivial using more traditional methods such as recurrent neural networks (RNNs) trained with back-propagation through time. The recently introduced Reservoir Computing (RC)∗∗The term reservoir used here is not related to reservoirs in oil and gas industry. approach to training RNNs is a viable and powerful alternative which renders fast training and high performance. In this work, a single Echo State Network (ESN), a flavor of RC, is employed for system identification of a vertical riser model which has stationary and oscillatory signal behaviors depending of the production choke opening input variable. It is shown experimentally that these different behaviors are learned by constraining the high-dimensional reservoir states to attractor subspaces in which the specific behavior is represented. Further experiments show the stability of the identified system. [less ▲]

Detailed reference viewed: 33 (7 UL)