Pattern recognition techniques for horizontal and vertically upward multiphase flow measurement

Performance of modern automated pattern recognition (PR) systems is heavily influenced by accuracy of their feature extraction algorithm. Many papers have demonstrated uses of deep learning techniques in PR, but there is little evidence on using them as feature extractors. Our goal is to contribute to this field and perform a comparative study between classical used methods in feature extraction and deep learning techniques. For that, a biometric recognition system, which is a PR application, is developed and evaluated using a proposed evaluation metric called expected risk probability. In our study, two deeply learned features, based on PCANet and DCTNet deep learning techniques, are used with two biometric modalities that are palmprint and palm-vein. Subsequently, the efficiency of these techniques is compared with various classical feature extraction methods. From the obtained results, we drew our conclusions on a very positive impact of deep learning techniques on overall recognition rate, and thus these techniques significantly outperform the classical techniques.

Accurate metering of flow rates and prediction of water breakthrough are important issues in offshore oil production. The multiphase flow rates can be found for instance from frequent well testing, from multiphase flow meters, or from software simulations. Multiphase flow meters are very expensive and so are single-well tests, especially in cases with long tiebacks. On the contrary, software simulations are cheap, they can be made accurate, and simulations can usually be based on existing sensors. Also, software is easy to install, operate, and maintain compared to hardware multiphase meters. In this article we describe the main components needed in a flexible software system for flow metering that can handle sparsely instrumented production facilities. Several sources of implicit information are pointed out, and a tuning strategy that avoids single-well tests is described. We also present examples that show the power of advanced simulations in situations that are not well handled by multiphase flow meters and standard software because of very low flow rates. What makes the situation in the examples even harder is that: There is no available information about the choke, the bottom hole sensors fail, and the temperature measurements are influenced by the seawater temperature. Despite this, good results are obtained. Introduction The offshore oil industry is facing a market where the number of brown fields is growing, and where more and more of the green fields are marginal fields. In addition, many of the new findings are on deep water. These facts all point in the direction of more production networks with long tiebacks, a stronger need for limiting the number of expensive well tests, and a push towards minimizing OPEX in general. The need for reliable monitoring of the production from each well in a production network is therefore continuously increasing. Furthermore, reservoirs may have more than one owner, whereas the various owners may share the same infrastructure and production facilities. In such cases reliable production monitoring is of course highly demanded. A software system for flow rate estimation may satisfy the above needs. Software is relatively cheap, and both installation and usage can be made very easy. Furthermore, software is easily maintained and supervised from remote, whereas hardware, such as a multiphase flow meter, usually needs to be maintained on the site. This is an important issue since many larger green fields are far away from where many of the oil companies' expertise traditionally is situated. Remote access can easily be obtained using standard web browsers and internet technology. However, if the instrumentation is sparse or inaccurate most software systems will not give reliable rate estimates. In this article we will look at how to deal with such problems. We will present the main building blocks for a flexible software system that can handle almost any production network configuration. We also show how inaccurate measurements and what may look like useless information may contribute to good rate estimates.

Representative reservoir fluid sampling and characterization has become increasingly important over the years. With exploration, appraisal and development activities moving into marginal fields and more challenging environments, accurate fluid characterization becomes more critical. This can be said for the formation tester, DST and multiphase sampling and fluid characterization environments with the most challenging area in recent years arguably being the multiphase environment. Multiphase flow meters have been accepted for several years now by the industry. Their use in permanent or well testing applications has been growing rapidly. In many cases, multiphase flow meters have replaced the separator for flow rate evaluation, but some fundamental needs from the client were not addressed properly, such as the ability to collect representative samples for phase-behavior characterization. Moreover, metering accuracies has been questionable in many cases (at very high GVF or in wet gas conditions, high pressure or /and high temperature).This paper focus on the Multiphase Active Sampling Device Service (MASS), a fluid sampling and analysis service that can be provided with the Vx multiphase metering technology with the objective of collecting representative samples, isolating and analyzing each fluid phase, and providing data from the analysis to input to the Vx acquisition software data to obtain more accurate flow rates. The collection of phase representative samples also opens the opportunity for a full recombination PVT study to be performed using the improved recombination ratio at line conditions from the multiphase flow meter. This dedicated multiphase fluid sampling and analysis system, combined with Vx technology provides flow rate better and fluid property than to a conventional test separator system.

The phenomenon of oil-gas-water multiphase flow is common in oil Wells in the middle and late stage of oil field development. The accurate measurement of its flow is of great significance to the control of oil production process and the efficient development of oil fields. In the analysis and research on the existing problems of multiphase flow measurement technology at home and abroad and based on the proposed a flow measurement system based on conductance measurement technique design and the implementation plan, to achieve a kind of can expand production logging in multiphase flow of oil and gas flow measurement range, and with continuous measurement, no radioactive, low cost advantages, such as oil and gas water related method of flow measurement model of multiphase flow electromagnetic research, optimization of oilfield production and realization of intelligent well completion, and promote the development of new type multiphase flow instrument, with major production guiding significance and value.

The classical practice in quantitative production log interpretation involves the use of the tandem flow and density measurements. The usual companion logs such as temperature and pressure are traditionally only exploited qualitatively and for the determination of insitu fluid properties. This paper presents a scheme and its associated algorithms that handles all available measurements. It is flexible enough to accommodate non traditional and upcoming sensors. Such capabilities are needed in light of the complexities associated to multiphase fluid flow in deviated wells. The method is based in a process which seeks to reconstruct all available measurements. It uses an iterative procedure which at each step assumes the solution, i.e., the individual phase flow rates. The algorithm uses a minimization technique aimed at obtaining a minimum difference between the theoretical sensor responses and the measured log responses. The resulting output is a flow profile versus depth of the individual liquid and gas phases. This method has been successfully applied worldwide and in particular in the Middle East. To illustrate the capabilities of the method, four Middle East examples are presented in this paper. The first example shows how the temperature sensor can compensate the hampered spinner measurement due to the high deviation of the well. The second one demonstrate the integration of standard production logging sensors in a three-phasic case. The third example shows the use of a non-traditional measurement, Water Flow Log (WFL*), in a three phase flow situation. The last one, also a triphasic case, includes a tracer ejector and a capacitance meter in addition to the standard string. Introduction Production logging is intended primarily for measuring the performance of producing and injecting wells. It provides diagnostic information, pinpoints where fluids such as water, oil and gas are entering a well, and gives an indication of the efficiency of perforations. In vertical wells, where there are relatively high flow rates and one or two fluid phases, traditional production logging analysis produces reliable results. However, if spinner readings are unavailable or suspect, the logging analysis can be severely hampered. In such cases, the fluid flows from various intervals cannot be quantified. This could happen in low-flowing or highly deviated wells. Figure 1 shows a typical production log where the spinner measurements have been severely affected by three adverse conditions -low flow rate, highly viscous fluid and high deviation. P. 465^

A Physics-Informed Neural Network (PINN) was developed to solve the complex Navier-Stokes (N-S) equations for multiphase flow measurement including flowrates of individual phases in the multiphase mixture, and phase ratios. The results were compared against a mathematical based multiphase flow measurement approach and validated through a controlled loop test using oil, water, and gas. The PINN embeds fundamental fluid dynamics principles into its learning process, ensuring that the neural network adheres to the governing physical laws of motion, continuity, and conservation. Unlike traditional neural networks that rely solely on data-driven learning, PINNs incorporate fluid dynamics driven differential equations, to enhance model accuracy and reliability. This study evaluates the accuracy, efficiency, and repeatability of PINNs by comparing their results against traditional mathematical-based multiphase flow measurement (MPFM) technology and controlled test cases. The developed PINN successfully solved the Navier- Stokes (N-S) equations in their closest approximation to the original form, with minimal assumptions and simplifications, to estimate multiphase flow rates, integrating fundamental fluid dynamics principles into its learning process. The results demonstrated that the PINN-based approach achieved accuracy comparable to traditional mathematical multiphase flow measurement (MPFM) technologies, while significantly improving computational efficiency. During controlled loop tests with oil, water, and gas, the PINN model consistently captured flow dynamics with high precision, validating its effectiveness under real-world conditions. Moreover, the PINN method exhibited strong generalization capabilities, adapting to various flow regimes without the need for extensive empirical calibration. Compared to conventional MPFM technologies, PINN reduced reliance on predefined correlations and offered greater adaptability to changing fluid properties. The repeatability of results confirmed the model's reliability, positioning PINNs as a promising alternative for complex multiphase flow measurement applications. These findings highlight the potential of PINNs as an innovative, physics-guided, and data-efficient solution, effectively bridging the gap between traditional physics-based methods and modern machine learning techniques. This paper presents an innovative application of Physics-Informed Neural Networks (PINNs) for multiphase flow measurement, offering a data-driven yet physics-guided alternative to traditional mathematical MPFM technologies. By embedding fundamental physical laws into the neural network training process, the proposed approach enhances accuracy, computational efficiency, and adaptability, while minimizing reliance on extensive empirical calibration. This advancement significantly improves real-time flow monitoring, equipping practicing engineers with a more reliable, data-efficient, and scalable solution for complex multiphase flow measurement in industrial applications.

Purpose:This study aims to compare the accuracy of the ADNEX MR scoring system and pattern recognition system to evaluate adnexal lesions indeterminate on the US exam. Methods:In this cross-sectional retrospective study, pelvic DCE-MRI of 245 patients with 340 adnexal masses was studied based on the ADNEX MR scoring system and pattern recognition system. Results:ADNEX MR scoring system with a sensitivity of 96.6% and specificity of 91% has an accuracy of 92.9%. The pattern recognition system’s sensitivity, specificity, and accuracy are 95.8%, 93.3%, and 94.7%, respectively. PPV and NPV for the ADNEX MR scoring system were 85.1 and 98.1, respectively. PPV and NPV for the pattern recognition system were 89.7% and 97.7%, respectively. The area under the ROC curve for the ADNEX MR scoring system and pattern recognition system is 0.938 (95% CI, 0.909-0.967) and 0.950 (95% CI, 0.922-0.977). Pairwise comparison of these AUCs showed no significant difference (p = 0.052). Conclusion:The pattern recognition system is less sensitive than the ADNEX MR scoring system, yet more specific.

The authors demonstrate how a pattern-recognition system can be applied to the interpretation of capacitance-voltage (C-V) curves on an MOS test structure. By intelligently sequencing additional measurements it is possible to accurately extract the maximum amount of information available from C-V and conductance-voltage (G-V) measurements. The expert system described, (CV-EXPERT), is completely integrated with the measurement, instrumentation, and control software and is thus able to call up a sequence of individually tailored tests for the MOS test structure under investigation. The prototype system is able to correctly identify a number of process faults, including a leaky oxide, as shown. Improvements that could be gained from developing rules to coordinate G-V, capacitance-time, and doping profile measurements simply by recognizing the important factors in the initial C-V measurement are illustrated. >

The need for multiphase flow measurement in the oil and gas production and petrochemical industries has been significantly increased over the last few years.Reliable measurements of the multiphase flow parameters such as void fraction, phase concentration, phase velocity and flow pattern identification are important for accurate modelling and/or in the operation of multiphase systems.Although many multiphase flow meters were recently developed, challenges in measuring multiphase flow components remain unresolved.Therefore, extensive research efforts were spent in designing accurate multiphase flow meters and several meters are currently under development worldwide.However, due to the complexity of the multiphase flow mixture and in some cases when three or more phases co-exist, it is impossible to adopt only one technique to develop a multiphase flow meter.Consequently, the integration of multiple sensors, based on several measurement techniques, found to be the optimum solution for accurate multiphase flow metering.The main objective of this study is to evaluate existing multiphase flow measurement techniques for the potential integration in a multiphase flow metering device.

Modern challenges in reservoir management have recently faced new opportunities in production control and optimization strategies. These strategies in turn rely on the availability of monitoring equipment, which is used to obtain production rates in real-time with sufficient accuracy. In particular, a multiphase flow meter is a device for measuring the individual rates of oil, gas and water from a well in real-time without separating fluid phases. Currently, there are several technologies available on the market but multiphase flow meters generally incapable to handle all ranges of operating conditions with satisfactory accuracy in addition to being expensive to maintain. Virtual Flow Metering (VFM) is a mathematical technique for the indirect estimation of oil, gas and water flowrates produced from a well. This method uses more readily available data from conventional sensors, such as downhole pressure and temperature gauges, and calculates the multiphase rates by combining physical multiphase models, various measurement data and an optimization algorithm. In this work, a brief overview of the virtual metering methods is presented, which is followed by the application of several advanced machine-learning techniques for a specific case of multiphase production monitoring in a highly dynamic wellbore. The predictive capabilities of different types of machine learning instruments are explored using a model simulated production data. Also, the effect of measurement noise on the quality of estimates is considered. The presented results demonstrate that the data-driven methods are very capable to predict multiphase flow rates with sufficient accuracy and can be considered as a back-up solution for a conventional multiphase meter.

Accurate oil, water and gas flow rate measurements from individual wells are essential in order to properly manage both the wells and reservoirs, as well as to obtain reliable data for production performance monitoring, optimization, allocation and simulation models1, 2, 3, 4, 5. Over the past three decades, there has been great advancement in the multiphase metering technology. These advancements have resulted in a significant improvement in measurement accuracy as well as in reducing the physical size of these meters which is a crucial element in limited-space environments as in offshore platforms. The intent of this paper is to present results of a compact Multiphase Flow Meter (MPFM) " PhaseWatcher?? based on information gathered from Saudi Arabia, where more than one hundred meters have been installed so far in several fields covering wide ranges of fluid properties and operating conditions. Moreover, the paper will discuss in detail the effect of crude sourness (H2S concentration) and pressure on the meter's measurement accuracy. Multiphase Flow Meter (MPFM) Design The PhaseWatcher is designed to measure the total volumetric flow rates of oil, water and gas at line conditions. These flow rates are converted to standard onditions via a pressure-volume-temperature (PVT) package, which can be either the default Black Oil Model or a specific model derived using a client supplied PVT data. The meter comprises of five basic components, Fig. 1:A Venturi meter with pressure transducers across it to measure the differential pressure between the inlet and throat of the Venturi.A nuclear dual energy fraction meter consisting of a Smart Detector and Barium Source, measures the count range of photons transmitted from the source to the detector at two different photon energy levels (the high energy level is used to measure the density of the mixture, while the low energy level is used to calculate the water-oil ratio).Process fluid temperature transducers, which measure the fluid temperature upstream of the Venturi section and the ambient temperature.A Blind Tee Static Mixer, used to homogenize the flow stream ahead of the Venturi meter.A process flow computer used to manipulate the measured data.

Reducing the effect of wrist variation on pattern recognition of Myoelectric Hand Prostheses Control through Dynamic Time Warping

Abstract: Future subsea developments will to an ever greater extent be focused on the development of small and marginal fields. The utilization of experiences from previous development stages will be a kqy issue for these developments, as slim lining of the development concepts, strategies, the technology and the execution will have to be significant. Experience and market situation has shown that the use of new technology will be important, as will new contract strategies, new project execution models, strategic alliances, organization and fast track developments. This paper summarizes only some of the experiences of Kongsberg Offshore a.s to date and highlights areas for improvement as well as key areas with regards to technological advancement with a focus on project execution, intervention techniques and subsea multiphase metering. Introduction The situation today is that the elephants have been developed in some of the mature markets., e.g. US, North Sea, etc. and the more marginal fields remains for development. There exists an uncertainty with respect to the oil price in addition to potentially great risk and relatively small reward when developing small and marginal fields. Marginal economy is due to a variety of causes including using existing technology, existing ways of organizing developments and operational procedures. We need to be innovative in these areas in order to make the fields commercial. The smaller and less accessible fields, deep waters, high pressure, increased distance to processing plants as some of the reasons causing a marginal economy. The subsea industry has, however, developed considerably in the last decade, which show how young the industry is. We must find new and more cost effective field development solutions in order to meet the challenges of uncertain oil price and marginality of the fields. As part of this industry, Kongsberg Offshore as. (KOS) has been involved in the subsea industry as it's main area of operation from the start in 1974, and has developed products for this industry serving a busy home market. Today the company operates within two business units, Subsea systems and Metering systems. The products developed include control systems, diverless intervention technology, complete subsea systems, metering systems including multiphase flow metering etc. All of which are of importance to enable the industry to meet the challenges set by the scenario described above. Other solutions to the needs foreseen is the development of a system approach and the organization of system engineering solutions that will be needed in the economic exploitation of marginal reserves since the field developments will need to be optimized relative to the operational and specific reservoirs needs. The following sections will give examples of the technology developed and how this has been utilized and will outline experiences from some of the fieId development projects where KOS has been involved. The paper will also cover the experiences with different contract strategies and organizational forms used in the different projects.

Multiphase flow meters are available from sometime, however, there still remain unresolved challenges. Dependable flow sensing is essential for reservoir management and production optimization. Most commercial water-cut and multiphase flow meters have limitations while measuring over the full range of flow conditions. Exiting meters need recurrent calibration, and have significant capital and operational overheads. In this paper an ultrasonic tomography based meter for water hold-up measurement is presented and the the experiences and challenges of testing the system in the field are shared. The designed system has the potential to resolve the shortcomings of available multiphase metering solutions.

Distinguished Author Series articles are general, descriptiverepresentations that summarize the state of the art in an area of technology bydescribing recent developments for readers who are not specialists in thetopics discussed. Written by individuals recognized as experts in the area, these articles provide key references to more definitive work and presentspecific details only to illustrate the technology. Purpose: to informthe general readership of recent advances in various areas of petroleumengineering. Summary. Multiphase flow can occur throughout the production system. Thefluids involved in multiphase flow in the petroleum industry are multicomponentmixtures with complex phase behavior. Petroleum engineers are faced with theneed to predict the relationships between flow rates, pressure drop, and piping(geometry or reservoir fluids produced during, the life of a field. This paperreviews the historical (Development of design tools used to address theseunique multiphase-flow features. State-of-the-art technology is alsopresented. Introduction Multiphase flow can occur throughout the entire production system involvedin flowing fluids from oil and gas reservoirs to processing facilities at thesurface. The production system in this context includes the reservoir: the wellcompletion: the tubulars that connect the reservoir to the surface: all surfacefacilities on land, seabed. or offshore platform and any pipelines that carryproduced fluids to other processing facilities. The multiphase flow encounteredin producing oil and gas can be any combination of a saturations phase, ahydrocarbon liquid phase, and a water phase. A vast amount of technical information on multiphase flow in pipes isavailable in the literature. Many of these sources are related to otherindustries and involve different types of- fluids. The reference list for thispaper clearly demonstrates the diversity of interest in multiphase flow inpipes. In particular, significant contributions have been made in the nuclearindustry. where a major concern is a possible loss-of--coolant accident in anuclear reactor. These studies involve the transient simulation of two-phase, single-component (water) fluid flow in piping systems. Multiphase flow in the petroleum industry has many unique features thatcreate complications not encountered by other industries. The fluids involvedare multicomponent mixtures whose phase behavior is extremely complex. Therange of pressures and temperatures encountered in production systems isextremely broad. Pressures can range from 15.000 psia [100 MPa] to nearatmospheric conditions. Temperatures can range from 400deg.F [200deg.C) to below the freezing, temperature of water. Pipe lengths can vary from a few feet to several hundredmiles for surface pipe or pipelines and from a few hundred feet to more than20,000 ft (6100) mi for wells. Piping, systems often involve significantvariations in (geometry, such as inclination angle. Diameter, pipe roughness, and even shape, such as when fluids flow in the annular space between casingand tubing in a wellbore. Although most vertical piping systems involve upflow, it is not uncommon to have multiphase downward flow in injection wells ordowncomers connecting, offshore platforms to subsea pipelines. Simulationmultiphase flow in wells also requires the ability to predict fluidtemperatures in a system that undergoes complex heat transfer phenomena betweenthe reservoir and the surface. The entire wellbore is surrounded by a huge rockvolume, much of which may even be frozen, as in the case of permafrost inarctic locations. Engineers in the petroleum industry are faced with the requirement topredict the relationships between flow rates, pressure drop, and pipinggeometry (length, diameter, angle, etc.) for the fluids produced from areservoir over the entire life of the field. The objective of this paper is toreview the historical development of design tools used to address the uniquemultiphase-flow features of the petroleum industry, including an evaluation ofthe state of the art. JPT P. 15^