Modelling of oil and gas networks

Abstract

An oil and gas network comprises multiple branched flow paths, such as in multi-zonal wells and/or multibranched wells and/or networks including multiple wells, and multiple control points at different branches, wherein the multiple control points may include multiple valves and/or pumps for controlling the flow rate through respective flow paths of the multiple branched flow network. The network is modelled to model the variation of one or more flow parameter(s) in one or more flow path(s) of the network. A method for this modelling includes: generating a long-term model using a first set of data relating to measurements of the flow parameter(s) and the status of the control points over a first period of time, wherein the long-term model describes the relationship between flow rates, the status of control points, and measured flow parameters including pressure and/or temperature; generating a short-term model using a second set of data relating to measurements of the flow parameter(s) and the status of the control points over at least one second period of time, wherein the at least one second period of time is shorter than the first period of time, and wherein the short-term model describes the relationship between the status of control points flow parameters including pressure and/or temperature; and combining the short-term model with the long-term model by: using the short-term model to determine pressure and/or temperature values that will result from the status of one or more control points or from proposed changes to those control points; using the determined pressure and/or temperature values from the short-term model along with the status of, or the proposed changes to, the control points as inputs to the long-term model and then using the long-term model to determine flow rate values that will result from those inputs; and thereby obtaining a combined model allowing for estimation of flow rates in real time as well as prediction of the effects of changes in the status of one or more of the control points. A method for training a model of this oil and gas network includes: modelling one or more flow parameter(s) in one or more flow path(s) of the network, the modelling including: generating a model using data relating to measurements of the flow parameter(s) and the status of the control points over a period of time; wherein the model describes the relationship between flow rates, the status of control points, and measured flow parameters including pressure and/or temperature; and wherein generating the model includes training the model under constraints requiring: (i) that the sum of the modelled flow rates from each branch of the flow network that contribute to a combined flow after branched flow paths join at one or more nodes must be equivalent to the respective measured combined flow rate, where a measurement of the combined flow is available, and (ii) that training of the model is suspended or modified for certain flow paths when the status of the control points is such that those flow paths will have zero flow, and/or that a flow rate for an individual flow path or branch must be or is encouraged to zero when an associated valve is closed and/or if a pump required for non-zero flow rate is inactive.