Conference Paper

Using Artificial Intelligence to Aid Measurement Accuracy and Reliability in Coriolis Gas Flow meters

To read the full-text of this research, you can request a copy directly from the author.


Coriolis is one of the fastest growing technologies in the oil and gas flow measurement. Flow sensitivity, pressure drop, temperature changes and increased noise level affects the accuracy and reliability of these types of transmitters. However in most situations those parameters are not constant and not a mathematical model exist to include in the logic for the actual gas flow calculation. AGA Report Number 11 specifically concentrates on the measurement of natural gas and the impact of expanded compositional ranges on the flow calculation. Using Artificial intelligence enables performance characteristics that are much better than traditional metering technologies. Compressibility factors for natural gas and other Hydrocarbon gases are some of the factors that will be considered in artificial intelligence model for gas flow measurement. In this paper uncertain input parameters will be identified as fuzzy variables and will be integrated into fuzzy calculation of the gas flow measurement. It can be argued that Coriolis technology integrated with artificial intelligence greatly increases the accuracy and robustness of flow calculation. Uses of artificial intelligence in these types of Coriolis flow meters can minimize error and extend sensor life. This paper will discuss the appropriate implementation of such expert system with Coriolis flow measurement technology.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

ResearchGate has not been able to resolve any citations for this publication.
Full-text available
A new implementation of a Coriolis mass-flow meter transmitter is described. It is based on digital components, and has improved performance compared with the commercial, mostly analogue, transmitter using the same flowtube (transducer). Improvements are found in flowtube control, measurement precision, and performance with two-phase and partially-empty conditions, including batching from empty. The new transmitter is viewed as a second-generation sensor validation (SEVA) demonstrator, in which experience from validating the commercial analogue transmitter has led to a redesign using digital technology. The resulting SEVA transmitter provides improved measurement performance and reduced vulnerability to fault conditions, as well as on-line estimates of measurement quality and fault compensation (Henry and Clarke, Control Engineering practice, 1 (4) (1993) 585–610).
Purpose To provide an overview of self‐validating sensor technology for researchers and engineers which can help them understand the concept and recent developments of this research area. Design/methodology/approach The concept of self‐validating (SEVA) sensors, including definition, output parameters and requirement of SEVA sensors are introduced. The differences between SEVA sensors and traditional sensors are given from which we can see many advantages of SEVA sensors. The principium of SEVA sensors is presented by the functional architecture. The research development of SEVA sensors is introduced in two aspects: research development of sensor fault diagnosis and signal reconstruction and research development of SEVA sensor hardware. Findings Summarizes the methods for sensor fault diagnosis and signal reconstruction in the research of SEVA sensors, and the development steps of SEVA sensor hardware. Indicates the shortages and problems of current research and gives our research and ideas to solve these problems. Originality/value This paper provides a detailed description and research information of self‐validating sensor technology for those who want to know and research on this area.
A new flow measurement system for real-time flow computation of a two-phase flow in an oil field is described. The system utilizes an array of ultrasound sensors together with capacitance and conductance sensors to accurately interpret the fluid composition in the whole water-cut range. The flow rate is determined using venturi and differential pressure techniques. A dedicated hierarchical neural network algorithm that relies on the various physical properties of the fluid was implemented and tested in a laboratory-scale flow loop. Experimental results demonstrated that real-time classification within a plusmn5% relative error in volumetric flow regardless of the flow regime or the fluid composition can be achieved. This is an improvement over traditional systems, where weak accuracy is usually obtained either within the 40%-60% water-cut range or in the case of a high water cut.
Vertical two-phase flows often need to be categorized into flow regimes. In each flow regime, flow conditions share similar geometric and hydrodynamic characteristics. Previously, flow regime identification was carried out by flow visualization or instrumental indicators. In this research, to avoid any instrumentation errors and any subjective judgments involved, vertical flow regime identification was performed based on theoretical two-phase flow simulation with supervised and self-organizing neural network systems. Statistics of the two-phase flow impedance were used as input to these systems. They were trained with results from an idealized simulation that was mainly based on Mishima and Ishii's flow regime map, the drift flux model, and the newly developed model of slug flow. These trained systems were verified with impedance signals measured by an impedance void-meter. The results conclusively demonstrate that the neural network systems are appropriate classifiers of vertical flow regimes. The theoretical models and experimental databases used in the simulation are shown to be reliable.
The effect of gas entrainment in oil on the performance of a range of single-phase flowmeters has been investigated experimentally using the National Standard Multiphase Flow facilities at NEL. The flowmeters tested were 4-inch and 2-inch positive displacement, venturi, helicoidal and flat-bladed turbine meters and 2-inch U-tube and 1.5-inch straight tube Coriolis meters. The flowmeters were tested in oil flow with gas fractions up to 15% by volume. The aim of the project was to quantify the effect of second-phase fluid components on the basic uncertainty of a range of single-phase flowmeters and, as a consequence, identify which generic types of single-phase flowmeter were most suitable in applications where such components may be present. These tests have provided evidence of the suitability of particular flowmeters for two-component flow applications. Comparisons have been made between generic type and size of flowmeter. At low gas fractions, the positive displacement and venturi flowmeters were more accurate than the other meters and estimated the total flowrate to within ±2%. Over 9% gas fraction, there was an improvement to the response from some of the flowmeters with increasing gas fractions. This was considered to be indicative of improved mixing in the flow.
Coriolis mass flow meters provide accurate measurement of single-phase flows, typically to 0.2%. However gas–liquid two-phase flow regimes may cause severe operating difficulties as well as measurement errors in these flow meters. As part of the Sensor Validation (SEVA) research at Oxford University a new fully digital coriolis transmitter has been developed which can operate with highly aerated fluids. This paper describes how a neural network has been used to correct the mass flow measurement for two-phase flow effects, based entirely on internally observed parameters, keeping errors to within 2%. The correction strategy has been successfully implemented on-line in the coriolis transmitter. As required by the SEVA philosophy, the quality of the corrected measurement is indicated by the on-line uncertainty provided with each measurement value.
The development of practical and accurate methods to measure two-phase mass flow rates is of prime interest to applied nuclear reactor safety research. This article summarizes a comparison and evaluation of four commonly used mass flow rate devices. The particular systems investigated include (a) the true mass flow meter (TMFM), (b) the radionuclide technique, (c) the combination of a free field drag disk-turbine meter-transducer (DTT) and a gamma densitometer, and (d) the combination of a venturi nozzle and a full flow turbine meter. The experiments were performed under similar conditions in steady-state steam-water flow. The flow direction upstream of the instruments was horizontal except for the last method. The pressures varied between 3 and 9 MPa, and the highest values of the mass flow rate, the quality were 5 kg/s and 90 per cent respectively. The test matrix included wave-, slug- and annular flow. The measuring techniques are described briefly and a classification is proposed, which is based on the different ways of mass flow rate evaluation. The experimental results show that the accuracy of some methods is distinctively dependent on phase distribution (flow regime). Simple calibration correlations were developed to account for these effects.
Explaining how two phase flow affects mass flowmeters
  • Micro Motion
  • Paper
MICRO MOTION WHITE PAPER, " Explaining how two phase flow affects mass flowmeters ".