One of the most common methods for calculating the production oil rate in a gas lift well is nodal analysis.This manner is an accurate one,but unfortunately it is very time consuming and slow.In some modern studies in...One of the most common methods for calculating the production oil rate in a gas lift well is nodal analysis.This manner is an accurate one,but unfortunately it is very time consuming and slow.In some modern studies in petroleum engineering such as close loop control of the wells this slowness makes it impossible to have an online optimization.In fact,before the end of the optimization the input parameters have changed.Thus having a faster model is necessary specially in some of the new studies.One of the sources of slowness of the nodal analysis is the temperature profile estimation of the wells.There are two general approaches for temperature profile estimation,some like heat balance are accurate but slow.Others,similar to linear profile assumption are fast but inaccurate and usually are not used commonly.Here,as a new approach,a combination model of heat balance and linear temperature profile estimation has represented which makes the nodal analysis three times faster and it is as accurate as heat balance calculations.To create this,two points(gas injection point and end of tubing)are selected,then using heat balance equations the temperature of those two points are calculated.In normal nodal analysis the temperature of each wanted point in the well is estimated by heat balance and it is the source of slowness but here just two points are calculated using those complex equations.It seems that between these points assuming a linear temperature profile is reasonable because the parameters of the well and production such as physical tubing,and casing shape and properties and gas oil ratio are constants.But of course,it still has some deviation from the complete method of heat balance which using regression and assigning a coefficient to the model even this much of the deviation could be overcame.Finally,the model was tested in various wells and it was compared with the normal nodal analysis with complete heat balance models.Results showed that the new model is as accurate as normal heat balance but three times faster.展开更多
There are various types of oils in distinct situations,and it is essential to discover a model for estimating their oil formation volume factors which are necessary for studying and simulating the reservoirs.There are...There are various types of oils in distinct situations,and it is essential to discover a model for estimating their oil formation volume factors which are necessary for studying and simulating the reservoirs.There are different correlations for estimating this,but most of them have large errors(at least in some points)and cannot be tuned for a specific oil.In this paper,using a wide range of experimental data points,an artificial neural network model(ANN)has been created.In which its internal parameters(number of hidden layers,number of neurons of each layer and forward or backward propagation)are optimized by a genetic algorithm to improve the accuracy of the model.In addition,four genetic programming(GP)-based models have been represented to predict the oil formation volume factor In these models,the accuracy and the simplicity of each equation are surveyed.As well as,the effect of modifying of the internal parameters of the genetic programming(by using some other values for its nodes or changing the tree depth)on the created model.Finally,the ANN and GP models are compared with fifteen other models of the most common previously introduced ones.Results show that the optimized artificial neural network is the most accurate and genetic programming is the most flexible model,which lets the user set its accuracy and simplicity.Results also recommend not adding another operator to the basic operators of the genetic programming.展开更多
The necessity of oil formation volume factor(Bo)determination does not need to be greatly emphasized.Different types of reservoir oil have specific conditions which impart the hydrocarbon's major properties,among ...The necessity of oil formation volume factor(Bo)determination does not need to be greatly emphasized.Different types of reservoir oil have specific conditions which impart the hydrocarbon's major properties,among which is the oil formation volume factor.Therefore,it seems imperative to construct a model capable of estimating the value of oil formation volume factor.Previous studies have resulted in a number of correlations for oil formation volume factor estimation;however,a large portion of them do not provide an acceptable accuracy(at least in some range of data)and cause a huge error at these points.Some others are not flexible enough to be tuned for a specific type of reservoir oil and a comprehensive piece of work does not exist as well in order to compare the applicability of the new models for estimating the oil formation volume factor.In this research,a model based on simulated annealing(SA)has been built in terms of temperature,solution gas-oil ratio,and gravity of oil and gas to predict the oil formation volume factor.This model is compared with the models proposed in the most recent studies,which shows the greater performance of the new method.In addition,in this paper the models of the recent years were compared with each other and their applicability were discussed.Aiming to compare the models,420 data points were selected and the estimated values of each model for oil formation volume factor were compared with their experimental ones.展开更多
文摘One of the most common methods for calculating the production oil rate in a gas lift well is nodal analysis.This manner is an accurate one,but unfortunately it is very time consuming and slow.In some modern studies in petroleum engineering such as close loop control of the wells this slowness makes it impossible to have an online optimization.In fact,before the end of the optimization the input parameters have changed.Thus having a faster model is necessary specially in some of the new studies.One of the sources of slowness of the nodal analysis is the temperature profile estimation of the wells.There are two general approaches for temperature profile estimation,some like heat balance are accurate but slow.Others,similar to linear profile assumption are fast but inaccurate and usually are not used commonly.Here,as a new approach,a combination model of heat balance and linear temperature profile estimation has represented which makes the nodal analysis three times faster and it is as accurate as heat balance calculations.To create this,two points(gas injection point and end of tubing)are selected,then using heat balance equations the temperature of those two points are calculated.In normal nodal analysis the temperature of each wanted point in the well is estimated by heat balance and it is the source of slowness but here just two points are calculated using those complex equations.It seems that between these points assuming a linear temperature profile is reasonable because the parameters of the well and production such as physical tubing,and casing shape and properties and gas oil ratio are constants.But of course,it still has some deviation from the complete method of heat balance which using regression and assigning a coefficient to the model even this much of the deviation could be overcame.Finally,the model was tested in various wells and it was compared with the normal nodal analysis with complete heat balance models.Results showed that the new model is as accurate as normal heat balance but three times faster.
文摘There are various types of oils in distinct situations,and it is essential to discover a model for estimating their oil formation volume factors which are necessary for studying and simulating the reservoirs.There are different correlations for estimating this,but most of them have large errors(at least in some points)and cannot be tuned for a specific oil.In this paper,using a wide range of experimental data points,an artificial neural network model(ANN)has been created.In which its internal parameters(number of hidden layers,number of neurons of each layer and forward or backward propagation)are optimized by a genetic algorithm to improve the accuracy of the model.In addition,four genetic programming(GP)-based models have been represented to predict the oil formation volume factor In these models,the accuracy and the simplicity of each equation are surveyed.As well as,the effect of modifying of the internal parameters of the genetic programming(by using some other values for its nodes or changing the tree depth)on the created model.Finally,the ANN and GP models are compared with fifteen other models of the most common previously introduced ones.Results show that the optimized artificial neural network is the most accurate and genetic programming is the most flexible model,which lets the user set its accuracy and simplicity.Results also recommend not adding another operator to the basic operators of the genetic programming.
文摘The necessity of oil formation volume factor(Bo)determination does not need to be greatly emphasized.Different types of reservoir oil have specific conditions which impart the hydrocarbon's major properties,among which is the oil formation volume factor.Therefore,it seems imperative to construct a model capable of estimating the value of oil formation volume factor.Previous studies have resulted in a number of correlations for oil formation volume factor estimation;however,a large portion of them do not provide an acceptable accuracy(at least in some range of data)and cause a huge error at these points.Some others are not flexible enough to be tuned for a specific type of reservoir oil and a comprehensive piece of work does not exist as well in order to compare the applicability of the new models for estimating the oil formation volume factor.In this research,a model based on simulated annealing(SA)has been built in terms of temperature,solution gas-oil ratio,and gravity of oil and gas to predict the oil formation volume factor.This model is compared with the models proposed in the most recent studies,which shows the greater performance of the new method.In addition,in this paper the models of the recent years were compared with each other and their applicability were discussed.Aiming to compare the models,420 data points were selected and the estimated values of each model for oil formation volume factor were compared with their experimental ones.
