inproceedings by karim salahshoor
articles by karim salahshoor
Papers by karim salahshoor
Engineering Applications of Artificial Intelligence, 2019
Waterflooding optimization in closed-loop management of the oil reservoirs is always considered a... more Waterflooding optimization in closed-loop management of the oil reservoirs is always considered as a challenging issue due to the complicated and unpredicted dynamics of the process. The main goal in waterflooding is to adjust the manipulated variables such that the total oil production or a defined objective function, which has a strong correlation with the gained financial profit, is maximized. Fortunately, due to the recent progresses in the computational tools and also expansion of the calculating facilities, utilization of non-conventional optimization methods is feasible to achieve the desired goals. In this paper, waterflooding optimization problem has been defined and formulated in the framework of Reinforcement Learning (RL) methodology, which is known as a derivative-free and also model-free optimization approach. This technique prevents from the challenges corresponding with the complex gradient calculations for handling the objective functions. So, availability of explicit dynamic models of the reservoir for gradient computations is not mandatory to apply the proposed method. The developed algorithm provides the facility to achieve the desired operational targets, by appropriately defining the learning problem and the necessary variables. The fundamental learning elements such as actions, states, and rewards have been delineated both in discrete and continuous domain. The proposed methodology has been implemented and assessed on the Egg-model which is a popular and well-known reservoir case study. Different configurations for active injection and production wells have been taken into account to simulate Single-Input-Multi-Output (SIMO) as well as Multi-Input-Multi-Output (MIMO) optimization scenarios. The results demonstrate that the ''agent'' is able to gradually, but successfully learn the most appropriate sequence of actions tailored for each practical scenario. Consequently, the manipulated variables (actions) are set optimally to satisfy the defined production objectives which are generally dictated by the management level or even contractual obligations. Moreover, it has been shown that by properly adjustment of the rewarding policies in the learning process, diverse forms of multi-objective optimization problems can be formulated, analyzed and solved.
ABSTRACT This paper demonstrates the practical design and implementation of two common network-ba... more ABSTRACT This paper demonstrates the practical design and implementation of two common network-based control approaches using Foundation Fieldbus and Industrial Ethernet as two emerging alternatives for the conventional methods. The presented approaches utilize a Smar Foundation Fieldbus controller (DFI-302) for function block implementation and a remote Siemens programmable logic controller (S7-315-2DP) for networked cascade control system implementation. A proper network platform has been designed to link these two controllers to a real pilot plant via Industrial Ethernet and Foundation Fieldbus. This paper investigates the effect of network data transmission delay on the resulting control performances. The obtained observations illustrate the control performance degradation due to large transmission delay in the implemented cascade control configuration.
This paper proposes an adaptive generalized predictive control (GPC) scheme for control of non-li... more This paper proposes an adaptive generalized predictive control (GPC) scheme for control of non-linear time- varying processes. An online identification approach based on an adaptive neural network with growing and pruning radial basis function (GAP-RBF) structure is presented to model the process dynamics in real-time. A single-input, single-output (SISO) adaptive GPC controller is designed based on dynamic linearization of the
Computers & Chemical Engineering, Nov 1, 2020
Abstract Waterflooding is one of the most popular techniques which are generally used to increase... more Abstract Waterflooding is one of the most popular techniques which are generally used to increase oil recovery factor in mature reservoirs. A challenging issue in conducting the waterflooding process is how to handle the effects of exiting reservoir uncertainties. To this aim, in this paper an optimization algorithm based on Mixed H∞/passivity controller design is introduced. The presented approach is capable to systematically take into account the unpredicted influences of inherent geological uncertainties on the production regime, while guaranteeing the stability and disturbance attenuation in the closed-loop system. In addition, this technique expresses energy transition between system states and disturbances, which are representatives of the uncertainty effects. In this study, the optimization problem has been formulated such that the gained profit (here, the net present value: npv) is maximized, while dealing with the operational constraints and also the uncertainty impacts. The defined performance index is able to simultaneously achieve the H∞ performance and the passivity property, in the presence of inherent uncertainties. The optimization problem has been solved by Linear Matrix Inequality (LMI) approach. The developed algorithm has been simulated on 10th SPE-model#2 as a well-known case study, by generating hypothetical uncertainty in the permeability grids. The obtained results have shown that the designed controller can appropriately adjust the water injection profile, known as the manipulated variable, to achieve the maximum feasible npv in the presence of uncertainty and operational constraints. Finally, further analysis has been provided to compare the introduced methodology with conventional robust optimization approach.
Engineering Applications of Artificial Intelligence, Sep 1, 2013
Producing oil from gas-lift wells are often faced with severe producing oscillatory flow regimes.... more Producing oil from gas-lift wells are often faced with severe producing oscillatory flow regimes. A major source of the oscillations is recognized as casing-heading instability which is caused by dynamic interaction between injection gas and multiphase fluid. This phenomenon poses strict productionrelated challenges in terms of lower average production and strain on downstream equipment. In this paper, an effective solution is proposed based on integration of an online interpretation dynamic model and a nonlinear model predictive control (NMPC) scheme. The paper uses adaptive growing and pruning radial basis function (GAP-RBF) neural networks (NNs) to recursively capture the essential dynamics of casing-heading instability in a nonlinear model structure. Extended Kalman filter (EKF) and unscented Kalman filter (UKF) are comparatively investigated to adaptively train modified GAP-RBF NNs. NMPC methodology is developed on the basis of the identified nonlinear NN model for real-time stabilization of casing-heading instability in an oil reservoir equipped with a gas-lift production well. A set of test studies has been conducted to explore the superior performance of the proposed adaptive NMPC controller under different scenarios for an oil reservoir simulated in ECLIPSE and linked to a complementary gas-lifted oil well simulated in programming environment.
Computers & Chemical Engineering, Nov 1, 2017
ï‚· An adaptive algorithm is introduced for waterflooding management in oil reservoirs using proxy ... more ï‚· An adaptive algorithm is introduced for waterflooding management in oil reservoirs using proxy models. ï‚· Time-varying nature and the inherent nonlinearity of the complex process is successfully handled. ï‚· Variations in market prices or operational costs are compensated such that a desired feasible profit is ensured. ï‚· Using data fusion technique, the real-time profitability/productivity status of the reservoir is monitored. ï‚· Fairly profit-sharing in different field development contracts can be achieved by applying the proposed method.
This paper investigates the application of data fusion technique to enhance the sensor fault dete... more This paper investigates the application of data fusion technique to enhance the sensor fault detection and diagnosis. The extended Kalman filter (EKF) is used to fuse the process measurement sensor data. The usual approach in the classical EKF implementation, however, is based on the constant diagonal matrices for the process and measurement covariance. This inflexible constant covariance set-up which employs
... and for the nonlinear case [7]-[9], among others. In the time delays context, a common approa... more ... and for the nonlinear case [7]-[9], among others. In the time delays context, a common approach is the PDE (partial differential equation) see Kwakernaak [10], Richard [11], Zhang, Zhang, and Xie [12]-[13] and references therein. ...
Abstract— Aim of this study is to propose fault detection and diagnosis (FDD) algorithm based on ... more Abstract— Aim of this study is to propose fault detection and diagnosis (FDD) algorithm based on input and output residuals that consider both sensor and actuator faults separately. The existing methods which have capability of fault diagnosis and its magnitude estimation suffer from ...
Page 1. Abstract—Fault diagnostic monitoring in nonlinear hybrid processes requires dedicated tec... more Page 1. Abstract—Fault diagnostic monitoring in nonlinear hybrid processes requires dedicated techniques being capable of dealing with both nonlinearity and hybrid dynamic characteristics. This paper introduces a modified ...
ABSTRACT In this paper, an advanced monitoring method is proposed to predict the time instants th... more ABSTRACT In this paper, an advanced monitoring method is proposed to predict the time instants that process variables will exceed specific abnormal limits. Presented method estimates unknown disturbances that enter the process and predicts process variables based on extended Kalman filter (EKF). Suggested strategy predicts future variables without linearization, so the results are more precise and reliable. Disturbance outset is computed based on residuals analysis. Using this method, control system (or operator) will have additional time before the abnormal or emergency situation occurs, thus more effective decisions can be made. To ensure the method efficiency, a nonlinear continuous stirred tank reactor (CSTR) is simulated and results are presented.
... is the estimation of the non-linear function . ... c) If both (27) and (28) are satisfied go ... more ... is the estimation of the non-linear function . ... c) If both (27) and (28) are satisfied go to k. d) If (27) is not satisfied, go to f. e) , 2 ; 2; ; . Go to b. f) determine β as the extreme of the second order ... Otherwise, set , ; μ and μ and go to f. k) Accept step size and return to the main algorithm. ...
ABSTRACT Some chemical plants such as distillation column have highly nonlinear behavior. These p... more ABSTRACT Some chemical plants such as distillation column have highly nonlinear behavior. These processes demand a powerful identification method such as linear and nonlinear models. In this paper, a distillation column is simulated in a rather realistic environment by HYSYS and the obtained data is in connection with MATLAB for identification and control purpose. In this case, the identified model is characterized by two structures, Linear model structure based on ARX (Autoregressive with external input) and nonlinear model structure based on neural network. For control goals, two linear and nonlinear model predictive controllers are applied. General predict control (GPC) and nonlinear predict control (NPC) are compared based adaptive identification of model. Since, practical systems change with time and the parameters of system are time varying, using real-time identification based recursive parameter estimation is necessary, although, desired control strategy is reached with a good parameter estimation. The algorithm has been tested on an distillation column. The resulting performances show the successful and promising capabilities of the proposed algorithm.
Journal of Applied Sciences, Sep 1, 2009
Arabian journal for science and engineering, Jul 22, 2014
ABSTRACT This paper presents a novel fault-tolerant control system for a class of nonlinear syste... more ABSTRACT This paper presents a novel fault-tolerant control system for a class of nonlinear systems with input constraints. A fault detection and diagnosis (FDD) is designed based on multiple model method. The bank of extended Kalman filters is used to detect the predefined actuator fault and estimate the unknown parameters of actuator position. On the other hand, until the fault detection instance, because of the mismatch between the process and the model, the system states may exit the stability region. Therefore, delay on FDD decision may lead to performance degradation or even instability for some systems. The timely proposed FDD approach could preserve system stability. When the fault is detected, the proposed FDD information is used to correct the model of faulty system recursively and reconfigure the controller. On the other hand, because of many important factors of MPC such as consideration of input and state constraints in optimization problem, it can be used as a powerful controller in the event of fault occurrence. So, the reconfigurable controller is designed based on the Lyapunov-based model predictive control approach that provides an explicit characterization of the stability region. Finally, a practical chemical process example, is presented to illustrate the effectiveness of this idea. It is shown that this scheme can provide the system stability when a fault occurs.
Uploads
inproceedings by karim salahshoor
articles by karim salahshoor
Papers by karim salahshoor