Asset managers constantly seek to determine how wells are performing to assess performance of long-term strategy and to achieve expected results. For this purpose, periodic production tests are performed to measure individual flow contribution to total measured platform production in addition to other measurements, including BSW, gas-oil ratio, pressure, and temperature. Daily well production is estimated by back-allocating production measured at fiscal meters to individual wells based on the well’s production potential validated during tests. This paper presents an alternative system for measuring individual well-oil production based on a neural network and online correlation logic using data from sensors, well tests, and simulations. This system permits a closer right-time monitoring of the wells by enabling readings to be taken more frequently and by minimizing the intrinsic estimation errors that normally arise when doing back-allocation of well production based on performance of other wells. This paper describes a methodology for data selection, sensor validation analysis, modeling, online implementation, and quality control of the results. The main benefit of this implementation has been to quickly identify production deviations above or below well potential and to identify and adjust the variables that affect these deviations. The combination of high volumes of measured data that automation technology enables and historical values of testing data made it possible to implement this smart solution where data is constantly transformed into information. This information allows the engineers to analyze and associate results and transform them into events of knowledge. This methodology can be applied to any asset where time and operational constraints do not permit the testing of wells on a daily basis or where it is too expensive to justify the installation of multiphase meters and where a high level of automation is available.

Companies worldwide have been investing in solutions to provide production and cost optimization. As a result, real-time operation systems have been used to help in achieving these objectives. This paper provides a description of the use of real-time operation systems and how the integration of their disciplines made it possible to optimize production and costs for oil and gas fields. Working as an integrated multi-disciplinary approach, real-time production-operation systems enable the maximization of oil and gas production of assets at lower costs, while providing a better understanding of the current scenario of oil and gas fields. To obtain these improvements, some characteristics to be considered are described below. The consolidation of the whole asset- production data into a single system provides mechanisms to monitor, analyze, and control oil and gas fields. These data are automatically uploaded to the system to minimize manual efforts, making more time available for process analyses. To avoid spurious data, an automatic validation mechanism for the data acquisition process was developed. In addition to production monitoring and the enhanced data quality, historical data, alarms, and statistic tools are used to improve the data analysis and interpretation process. The solution also enables the online well-production prediction using a neural-networks model as well as the integration with a reliable system to identify, quantify, and classify production losses. Because the information is displayed in an online system, the same data at the same time are available for access from different users. The use of real-time production-operation systems enables strategies for asset managers to make faster decisions and provide better solutions to asset operational issues. These outcomes are achieved as a result of integrated production, losses, and process-parameters information, as well as the acquisition process of validated data and the availability of tools for analysis and interpretation.

Asset managers constantly seek to determine how wells are performing to assess performance of long-term strategy and to achieve expected results. For this purpose, periodic production tests are performed to measure individual flow contribution to total measured platform production in addition to other measurements, including BSW, gas-oil ratio, pressure, and temperature. Daily well production is estimated by back-allocating production measured at fiscal meters to individual wells based on the well's production potential validated during tests. This paper presents an alternative system for measuring individual well-oil production based on a neural network and online correlation logic using data from sensors, well tests, and simulations.This system permits a closer right-time monitoring of the wells by enabling readings to be taken more frequently and by minimizing the intrinsic estimation errors that normally arise when doing back-allocation of well production based on performance of other wells. This paper describes a methodology for data selection, sensor validation analysis, modeling, online implementation, and quality control of the results. The main benefit of this implementation has been to quickly identify production deviations above or below well potential and to identify and adjust the variables that affect these deviations.The combination of high volumes of measured data that automation technology enables and historical values of testing data made it possible to implement this smart solution where data is constantly transformed into information. This information allows the engineers to analyze and associate results and transform them into events of knowledge. This methodology can be applied to any asset where time and operational constraints do not permit the testing of wells on a daily basis or where it is too expensive to justify the installation of multiphase meters and where a high level of automation is available.