Model-Predictive-Control (MPC) of Steam Trap Subcool in Steam-Assisted Gravity Drainage (SAGD)

Purkayastha, Sagar N.; Gates, Ian D.; Trifkovic, Milana

doi:10.1016/j.ifacol.2015.09.023

Cited by 10 publications

(10 citation statements)

References 17 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Cross‐sectional view of a developing steam chamber in SAGD: The heat from the steam is delivered through conduction at the edges of the steam chamber and the oil drains along the steam‐oil interface. [Color figure can be viewed at http://wileyonlinelibrary.com]…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, steam trap control has been identified as a possible avenue to enhance the efficiency of SAGD operations . The idea behind steam trap control is to maintain a liquid pool above the producer well at a temperature 10°C to 40°C below the temperature at which the steam is injected (also called the subcool temperature difference) so that the oil–water emulsion from the liquid pool is produced through the producer well without live steam . Moreover, this subcool temperature difference is the key to maintaining the height of the liquid pool at a certain desired level .…”

Section: Introductionmentioning

confidence: 99%

“…The idea behind steam trap control is to maintain a liquid pool above the producer well at a temperature 10°C to 40°C below the temperature at which the steam is injected (also called the subcool temperature difference) so that the oil–water emulsion from the liquid pool is produced through the producer well without live steam . Moreover, this subcool temperature difference is the key to maintaining the height of the liquid pool at a certain desired level . Research on steam trap or subcool control via proportional integral derivative (PID) control, and more advanced methods like model predictive control (MPC), have proven to be an improvement over open loop methods of steam injection for oil recovery.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, this subcool temperature difference is the key to maintaining the height of the liquid pool at a certain desired level . Research on steam trap or subcool control via proportional integral derivative (PID) control, and more advanced methods like model predictive control (MPC), have proven to be an improvement over open loop methods of steam injection for oil recovery. However, PID controllers are incapable of handling constraints, calculating optimal control gains for the manipulated variable (MV), and are incapable of Multi‐input multioutput (MIMO) control.…”

Section: Introductionmentioning

confidence: 99%

“…The other major drawback of steam trap control for both PID and MPC control is the absence of a set procedure to determine the optimal subcool or liquid pool temperature ( T P ) setpoint for a given formation. Also, assuming an average temperature for the liquid pool may not be suitable since different points along the well are at different temperatures and production of live steam may not be captured. Another challenge arises from the changing system boundary as the steam chamber grows and the absence of a technique to produce the liquid accumulating in the liquid pool.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Real‐time multivariable model predictive control for steam‐assisted gravity drainage

2018

Self Cite

View full text Add to dashboard Cite

Thermal recovery techniques, such as steam-assisted gravity drainage (SAGD), are used to recover the majority of the crude bitumen, in Western Canada. However, suboptimal production techniques have led to a large carbon footprint and a subsequent search for more efficient extraction techniques, than open loop manual control. This article summarizes research on the comparison of performance of a novel multi-input multioutput (MIMO) model predictive controller (MPC) with steam trap and oil rate controls with a multi-input single output (MISO) MPC with only steam trap control. An appropriate system identification technique was also used for periodic model update in compliance with changing system behavior. The real-time control study was made possible by establishing a bidirectional communication between computer modeling group STARS TM (virtual reservoir) and MATLAB (onsite controller) software. The results show a 171% improvement in oil recovery for the novel MIMO MPC over the MISO MPC. V C 2018 American Institute of Chemical Engineers AIChE J, 00: 000-000, 2018

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real‐time multivariable model predictive control for steam‐assisted gravity drainage

2018

Self Cite

View full text Add to dashboard Cite

show abstract

Real‐time feedback control of SAGD wells using model predictive control to optimize steam chamber development under uncertainty

et al. 2018

View full text Add to dashboard Cite

The efficiency of steam assisted gravity drainage (SAGD) operation depends on developing a uniform steam chamber by maintaining an optimal subcool temperature along the length of the well pair. Implementing operational parameters obtained from model‐based optimization directly in the field may not lead to the desired subcool temperature. Based on the real‐time measurements from surface and downhole sensors, along with other well and surface constraint information, a real‐time feedback control of SAGD well pairs can be implemented to optimize subcool and steam chamber development. Model predictive control (MPC), which is a multivariable constrained controller, provides a framework for such control. To evaluate the use of MPC for real‐time control of SAGD wells, a case study is performed using a 3D heterogeneous reservoir model. Porosity and permeability realizations are created and ranked based on net present value (NPV). One of the realizations is considered as the ‘true’ reservoir, and two other realizations are selected to represent different cases of uncertain reservoir models. For each model, a reservoir simulator is used to find the optimum rates and subcool temperature, which become the set‐points for MPC to operate the wells. We compare the steam chamber growth and NPV calculated using MPC with the base case where no MPC is used and discuss the implementation advantages. Since MPC led to expedited and accurate tracking of optimized operating targets obtained using reservoir models, ∼18 % improvement in NPV is achieved compared to manual open‐loop application of optimum rates, a practice used commonly in the field.

show abstract

Actor-critic reinforcement learning leads decision-making in energy systems optimization—steam injection optimization

Abdalla¹,

Hollstein²,

Carvajal³

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

Steam injection is a popular technique to enhance oil recovery in mature oil fields. However, the conventional approach of using a constant steam rate over an extended period can lead to sub-optimal performance due to the complex nature of the problem and reservoir heterogeneity. To address this issue, the Markov decision process can be employed to formulate the problem for reinforcement learning (RL) applications. The RL agent is trained to optimize the steam injection rate by interacting with a reservoir simulation model and receives rewards for each action. The agent’s policy and value functions are updated through continuous interaction with the environment until convergence is achieved, leading to a more efficient steam injection strategy for enhancing oil recovery. In this study, an actor-critic RL architecture was employed to train the agent to find the optimal strategy (i.e., policy). The environment was represented by a reservoir simulation model, and the agent’s actions were based on the observed state. The policy function gave a probability distribution of the actions that the agent could take, while the value function determined the expected yield for an agent starting from a given state. The agent interacted with the environment for several episodes until convergence was achieved. The improvement in net present value (NPV) achieved by the agent was a significant indication of the effectiveness of the RL-based approach. The NPV reflects the economic benefits of the optimized steam injection strategy. The agent was able to achieve this improvement by finding the optimal policies. One of the key advantages of the optimal policy was the decrease in total field heat losses. This is a critical factor in the efficiency of the steam injection process. Heat loss can reduce the efficiency of the process and lead to lower oil recovery rates. By minimizing heat loss, the agent was able to optimize the steam injection process and increase oil recovery rates. The optimal policy had four regions characterized by slight changes in a stable injection rate to increase the average reservoir pressure, increasing the injection rate to a maximum value, steeply decreasing the injection rate, and slightly changing the injection rate to maintain the average reservoir temperature. These regions reflect the different phases of the steam injection process and demonstrate the complexity of the problem. Overall, the results of this study demonstrate the effectiveness of RL in optimizing steam injection in mature oil fields. The use of RL can help address the complexity of the problem and improve the efficiency of the oil recovery process. This study provides a framework for future research in this area and highlights the potential of RL for addressing other complex problems in the energy industry.

show abstract

Model-Predictive-Control (MPC) of Steam Trap Subcool in Steam-Assisted Gravity Drainage (SAGD)

Cited by 10 publications

References 17 publications

Real‐time multivariable model predictive control for steam‐assisted gravity drainage

Real‐time multivariable model predictive control for steam‐assisted gravity drainage

Real‐time feedback control of SAGD wells using model predictive control to optimize steam chamber development under uncertainty

Actor-critic reinforcement learning leads decision-making in energy systems optimization—steam injection optimization

Contact Info

Product

Resources

About