This work proposes a new methodology to identify and validate deep learning models for artificial oil lift systems that use submersible electric pumps. The proposed methodology allows for obtaining the models and evaluating the prediction's uncertainty jointly and systematically. The methodology employs a nonlinear model to generate training and validation data and the Markov Chain Monte Carlo algorithm to assess the neural network's epistemic uncertainty. The nonlinear model was used to overcome the limitations of the need for big datasets for training deep learning models. However, the developed models are validated against experimental data after training and validation with synthetic data. The validation is also performed through the models' uncertainty assessment and experimental data. From the implementation point of view, the method was coded in Python with Tensorflow and Keras libraries used to build the neural Networks and find the hyperparameters. The results show that the proposed methodology obtained models representing both the nonlinear model's dynamic behavior and the experimental data. It provides a most probable value close to the experimental data, and the uncertainty of the generated deep learning models has the same order of magnitude as that of the nonlinear model. This uncertainty assessment shows that the built models were adequately validated. The proposed deep learning models can be applied in several applications requiring a reliable and computationally lighter model. Hence, the obtained AI dynamic models can be employed for digital twin construction, control, and optimization.

This study presents practical details and results from implementing model-based predictive controllers for artificial lift systems in oil production, which utilise electrical submersible pumps (ESPs). The proposed methodology integrates the existing instrumentation architecture with new control systems and techniques. This work implements two control strategies: a standard MPC and an MPC with input targets. Both were executed in real time, encapsulated in a C++ executable, and deployed within Petrobras's supervisory and control system. The results include an analysis of the instrumentation system, a discussion of operation under unmeasured disturbances and constraints, and a comparison of the controllers. The findings are extensive and indicate that both controllers stabilise the system, ensure constraint satisfaction, and appropriately compensate disturbances.