S. Ameri

Design and development of an artificial neural network for estimation of formation permeability

Permeability is one of the most important characteristics of hydrocarbon-bearing formations and one of the most important pieces of information in the design and management of enhanced recovery operations. With accurate knowledge of permeability, petroleum engineers can manage the production process of a field efficiently. Although formation permeability is often measured in the laboratory from cores or evaluated from well-test data, core analysis and well-test data are only available from a few wells in a field, while the majority of wells are logged. In this study, the authors have designed an artificial neural network that can accurately predict the permeability of the formations by use of the data provided by geophysical well logs. Artificial neural network, a biologically inspired computing method which has an ability to learn, self-adjust, and be trained, provides a powerful tool in solving pattern recognition problems.

State-Of-The-Art in Permeability Determination From Well Log Data: Part 1- A Comparative Study, Model Development

This study discusses and compares, from a practical point of view, three different approaches for permeability determination from logs. These are empirical, statistical, and the recently introduced virtual measurement methods. They respectively make use of empirically determined models, multiple variable regression, and artificial neural networks. All three methods are applied to well log data from a heterogeneous formation and the results are compared with core permeability, which is considered to be the standard. In this first part of the paper we present only the model development phase in which we are testing the capability of each method to match the presented data. Based on this, the best two methods are to be analyzed in terms of prediction performance in the second part of this paper.

A Methodological Approach for Reservoir Heterogeneity Characterization Using Artificial Neural Networks

This paper was selected for presentation by an SPE Program Committee following review o information contained in an abstract submitted by the author(s). Contents of the paper have not been reviewed by the Society of Petroleum Engineers and are subject to correction by th e author(s). The material, as presented, does not necessarily reflect any position of the Society of Petroleum Engineers, its officers, or members. Papers presented at SPE meetings are subject to publication review by Editorial Committees of the Society of Petroleum Engineers. Permission to copy is restricted to an abstract of not more than 300 words. Illustrations may not be copied. The abstract should contain conspicuous acknowledgment of where and by whom the paper is presented. Write Librarian, SPE, P.O. Box 833836, Richardson, TX 75083-3836, U.S.A. Telex, 163245 SPEUT. logging tools became available. These calculations assume a linear

A Hybrid, Neuro-Genetic Approach to Hydraulic Fracture Treatment Design and Optimization

This paper summarizes the efforts conducted toward the development of a new and novel methodology for optimal design of hydraulic fracture treatments in a gas storage field. What makes this methodology unique is its capability to provide engineers with a near optimum design of a frac job despite very little (almost none) reservoir data availability. Lack of engineering data for hydraulic fracture design and evaluation had made use of 2D or 3D hydraulic fracture simulators impractical. As a result, prior designs of hydraulic frac jobs had been reduced to guess works and in some cases dependent on engineers with many years of experience on this particular field, who had developed an intuition about this formation and its possible response to different treatments. This was the main cause of several frac job failures every year. On the other hand, in case of relocation of engineers with experience on this particular field the risk of even more frac job failures was imminent.

A New Approach for the Prediction of Rate of Penetration (ROP) Values

Today applications of drilling require proper identification of operations where a cost reduction is possible. Many indicators are present when one tries to optimize the drilling operations such as casing size and mud properties. On the other hand the selection of the optimum bit requires information from a variety of sources. The parameters affecting the bit performance are complex and their relationship is not easily recognized. The general trend is to evaluate the performance of the bit from an offset well. A new methodology was developed to model the rate of penetration and bit wear under various formation types and operating parameters. This method introduces a new approach with improved bit wear prediction. A simulator was used to generate drilling data to eliminate errors coherent to field measurements. The data generated was used to establish the relationship between the complex patterns such as weight on bit, rotary speed, pump rates, formation hardness, and bit type. The method was tested using data from runs conducted with a rig floor simulator. The validity of the proposed method was also demonstrated with data from an existing field.

Identifying Best Practices in Hydraulic Fracturing Using Virtual Intelligence Techniques

Hydraulic fracturing is an economic way of increasing gas well productivity. Hydraulic fracturing is routinely performed on many gas wells in fields that contain hundreds of wells. Companies have developed databases that include information such as methods and materials used during the fracturing process of their wells. These databases usually include general information such as date of the job, name of the service company performing the job, fluid type and fluid amount, proppant type and proppant amount, and pumped rate. Sometimes more detail information may be available such as breakers, amount of nitrogen, and ISIP, to name a few. These data usually is of little use if some of the complex 3-D hydraulic fracture simulators are used to analyze them. But valuable information can be deduced from such data using virtual intelligence tools. The process covered in this paper takes the available data and couples it with general information from each well (things like latitude, longitude and elevation), any information available from log analysis and production data and uses a data mining and knowledge discovery process to identify a set of best practices for the particular field. The technique is capable of patching the data in places that certain information is missing. Complex virtual intelligence routines are used to insure that the information content of the database is not compromised during the data patching process. The conclusion of analysis is a set of best practices that has been implemented in a particular field on a well or on a group of wells basis. Since the entire process is mostly data driven we let the data “speak for itself” and “tell us” what has “worked” and what “has not worked” in that particular field and how the process can be enhanced on a single well basis. In this paper the results of applying this process to Medina formation in New York State will be presented. This data set was furnished by Belden & Blake during a GRI / NYSERDA sponsored projects. This process provides an important step toward achieving a comprehensive set of tools and processes for data mining, knowledge discovery, and data-knowledge fusion from data sets in oil and gas industry.

A New Approach to Predict Bit Life Based on Tooth or Bearing Failures

This paper presents a new methodology to predict the wear for three-cone bits under varying operating conditions. In this approach, six variables (weight on bit, rotary speed, pump rate, formation hardness, bit type, and torque) were studied over a range of values. A simulator was used to generate drlling data to eliminate arrors coherent to field measurements. The data generated was used to establish the relationship between complex patterns. A three-layer artificial neural network was designed and trained with measured data. This method incorporates computational intelligence to define the relationship between the variables. Further, it can be used to estimate the rate of penetration and formation characteristics. The new model was successful in predicting the condition of the bit. In this study, the value of 0.997 was obtained by the model as the correlation coefficient between the predicted and measured bearing wear and tooth wear values. The validity of the model was demonstrated with data from an existing field. Introduction There are numerous technological advances made in the design and manufacture of drilling bits. The demand to drill faster and physically for a longer period is the driving force behind these developments. Consequently, the trip times and the time spent to drill a well are reduced. This in turn yields a cost effective drilling operation. The need to understand the bit behavior has been long recognizedl-3. Several investigators conducted research to estimate the bit condition based on operational parameters and measured data from offset wells4-9.The models developed are based on assumptions that limit their applicability. Neural Networks. Recently, neural networks successfully applied in different areas of petroleum engineeringlO. The capability to ident.@ complex relationships is well suited to solve problems inherent to oil and natural gas operations. When sufllcient data exists, the use of neural networks are demonstrated in several areas such as multi-phase pipe flow’“12, reservoir characterization13”4, production15’16, and drilling17’18. Especially the drilling operation provides a unique challenge due to..the number of_vmjables involved. These parameters range from unknown formation characteristics and down hole conditions to surface operating conditions. A neural network to predict the rate of penetration values at a well based on recorded data was presented earlier18. In this study, a new neural network was designed and used to predict successfully the bit wear and life. Approach Anew methodolo~ is introduced to predict the bit tooth and bit bearing wear while drilling. In this study, a neural network model was selected to investigate a complex drilling problem. The study consists of simulated and field measured data sets. Approximately 8000 set of measurements were recorded using the rig floor simulator available in the departmental facilities. The use of simulated data provided additional information such as bit tooth and bearing wear that were not recorded in the field during the drilling operation. The bit condition in the field is determined only after it is pulled. The data recorded using the rig floor simulator consisted of bit tooth and bearing wear values as a function of time. The range of data used in this study are given in Table 1 where the formation drillability varied between 30 and 75 with smaller values representing harder formations. Similarly, the formation abrasiveness values represent an increasing abrasiveness from one to eight. The wellbore con.tlgurat.ionsand other operational parameters were kept constant during rig floor simulator runs. Several neural networks were developed to predict the bit tooth and bearing wear values. All networks used a typical three-layer feed-forward back propagation similar to Figure 1. The neural network models used in this study were consisted of 80 hidden neurons, nine or ten input parameters, and one or two output parameters. First and second neural networks were designed to predict bit tooth wear and bit bearing wear, respec-

The Application of ANN for Zone Identification in a Complex Reservoir

Reservoir characterization plays a critical role in appraising the economic success of reservoir management and development methods. Nearly all reservoirs show some degree of heterogeneity, which invariably impacts production. As a result, the production performance of a complex reservoir cannot be realisticall y predicted without accurate reservoir description. Characterization of a heterogeneous reservoir is a complex problem. The difficulty stems from the fact that sufficient data to accurately predict the distribution of the formation attributes are not usually available. Generally the geophysical logs are available from a considerable number of wells in the reservoir. Therefore, a methodology for reservoir description and characterization utilizing only well logs data represents a significant technical as well as economic advantage. One of the key issues in the description and characterization of heterogeneous formations is the distribution of various zones and their properties. In this study, several artificial neural networks (ANN) were successfully designed and developed for zone identification in a heterogeneous formation from geophysical well logs. Granny Creek Field in West Virginia has been selected as the study area in this paper. This field has produced oil from Big Injun Formation since the early 1900s. The water flooding operations were initiated in the 1970s and are currently still in progress. Well log data on a substantial number of wells in this reservoir were available and were collected. Core analysis results were also available from a few wells. The log data from 3 wells along with the various zone definitions were utilized to train the networks for zone recognition. The data from 2 other wells with previously determined zones, based on the core and log data, were then utilized to verify the developed networks predictions. The results indicated that ANN can be a useful tool for accurately identifying the zones in complex reservoirs.

Candidate Selection for Stimulation of Gas Storage Wells Using Available Data With Neural Networks and Genetic Algorithms

The methodology developed in this study uses several artificial neural networks and genetic algorithm routines to help engineers select restimulation candidates based on available data. The neural networks provide realistic models of the hydraulic frac jobs and chemical treatments in this field. The genetic algorithms provide design optimization and economic analysis (capital investment allocation). Historically wells in this storage field have been stimulated/restimulated by hydraulic fracturing or by being chemically treated using one, two or sometimes three different chemicals. Several neural network models were developed for different stimulation processes. The first series of genetic algorithm routines are used with each of the neural network models to provide optimum treatment design for each of the stimulation processes. A separate genetic algorithm uses several economic parameters and provides the engineer with an optimum stimulation combination of the candidate wells. A software tool based on this methodology has been developed for a gas storage field in Ohio. Upon the completion of the analysis, the software tool provides a list of the maximum number of candidate wells. This maximum number is based on the provided stimulation budget for a particular year. The list specifies the type of stimulation for each candidate well - whether it should be refraced or chemically stimulated - and recommends a list of possible parameters to be used during the implementation. Background This paper presents the continuation of the efforts that were published in two previous SPE publications. In the first paper authors showed the feasibility of using artificial neural networks to accurately model hydraulic fracturing process in a gas storage field 1 . In a second paper as a continuation of that project, genetic algorithm routines were used in an attempt to optimize the design parameters of hydraulic fracturing process 2 . The study being presented in this paper takes into account new realities that the operators are facing in the field. These realities include fundamentally different stimulation jobs such as refracs versus chemical treatments. Each of these restimulation jobs must be treated differently during the model building process. Economic considerations play an important role in restimulation projects. A new economic optimization tool has been added to the process in this study. Therefore, many challenging complexities that were not included in the previous studies have been addressed here. During a stimulation/restimulation program the engineers face several challenging questions. The hydraulic fractures cost four to five times as much as a chemical treatment, and yet some wells

Identification of Contaminanted Data in Hydraulic Fracturing Databases: Application to the Codell Formation in the DJ Basin

With the advance of computer technologies, digitized data is becoming increasingly available. Currently, many companies are in possession of oil or gas-field databases that contain large amounts of information related to hydraulic fracturing, reservoir characterization, production, drilling, etc. However, not all the records are completely accurate or reflect reality. Errors in stored data can be subjective or objective and can be the result of improper or incomplete data collection, errors in data entry, lack of proper interpretation and others. These errors can later lead to poor, erroneous, or even impossible interpretation of the data. This leads to the question: how much of the data is reliable and how can the contaminated data be identified?