Integrated, Multiple-Component Proxy Model for Optimizing Production

This paper addresses integrated asset optimization models that are enabled by multiple-component, multi-layer neural network proxy models. The proxy models are used to represent non-linear production behavior for real-time production optimization. <br><br>The paper introduces a methodology for training neural networks that are robust proxy models for nonlinear physics-based simulators. The neural network architecture, the training, and model combinations will be presented. The training of a proxy initiates with a design of experiments. If multiple simulators, e.g. reservoir, well nodal analysis, and gathering network process analysis represent different components of the physical system, then each can be executed individually. Each results in a trained proxy which are then combined mathematically into a single proxy for the integrated system. Two example applications are presented.<br><br>The first example develops a nodal analysis model, which is critical for real-time management in fields with hundreds or even thousands of wells. The model represents the system analysis for the Inflow Performance Relationship (IPR) of the reservoir and the Vertical Lift Performance (VLP) for the tubing. The example goes through a multi-dimension table generation for training the neural network models. An optimization solver is used to find the oil rate where the bottom-hole pressures equal tubing-head pressures for a range of conditions. The complete IPR/VLP “nodal” solution is represented by the proxy. We expand this to include not just a single IPR/VLP pair of equations but a series of subsystems. <br><br>Another example builds a proxy from flow simulation of a reservoir operating with water injection and wells with downhole control valves. A multi-component proxy is used both to optimize the valve settings pro-actively in response to reservoir performance and to quickly update the reservoir model history match. <br><br>Significant contributions:<br>1. Demonstrate that a properly trained multi-layer neural network can be a robust proxy for complex, nonlinear multiple physics-based simulations of surface, reservoir, and well performance.<br>2. Demonstrate use of gradient optimization of a proxy model, for pro-active optimization of field and well operations in response to high-frequency data input. <br>3. Show how multiple neural network proxies that represent different physical components of a field operating system can be combined mathematically rather easily to form a fully integrated model.<br>