Artificial neural network approach for flow regime classification in gas–liquid–fiber flows based on frequency domain analysis of pressure signals
Introduction
Objective flow regime identification in multi-phase flow process systems using minimally intrusive sensors is of great interest to various branches of industry. In paper making and recycling, in particular, opaque gas–liquid–pulp fiber three-phase mixtures are encountered in large delignification, bleaching, and deinking devices. An objective and minimally intrusive regime classification technique can help the development of online diagnostic or control methods for such systems. Hydrodynamic characteristics of gas–liquid–pulp fiber slurry flows have been investigated in the past (Duffy and Titchener, 1975; Duffy et al., 1976; Bennington et al., 1995; etc), and more recently their flow regimes and gas holdup characteristics have been studied (Lindsay et al., 1995; Reese et al., 1996; Heindel, 1999; Heindel and Garner, 1999; Xie 2003a, Xie 2003b). Brief reviews of the recent studies can be found in Xie 2003a, Xie 2003b).
Attempts at the characterization of two-phase flow patterns based on a combination of subjective judgments and objective methods have also been made in the past (Hubbard and Dukler, 1966; Mandhane et al., 1974; Jones and Zuber, 1975; Merilo et al., 1977; Weisman et al., 1979; Taitel et al., 1980; Mishima and Ishii, 1983; Matsumi, 1984; Lin and Hanratty, 1986; Fang et al., 1986; Franca et al., 1991; Drahos et al., 1991; Spedding and Spence, 1993; Lindsay et al., 1995; Cai et al., 1996; Zhang et al., 1997; Heindel and Monefeldt, 1997; Shim and Jo, 2000). Pressure fluctuations that result from the passage of gas and liquid pockets, and their statistical characteristics, are particularly attractive for objective characterization of flow regimes because the required sensors are robust, inexpensive and relatively well-developed, and therefore more likely to be applied in the industrial systems (Drahos et al., 1991). Power spectral density (PSD) and probability density function (PDF) of pressure drop fluctuations recorded by two pressure transducers were studied by Franca et al. (1991), and more recently by Shim and Jo (2000), for regime identification in gas–liquid two-phase flows. Based on the analysis of experimental data in a horizontal tube, Franca et al. (1991) noted that, although PSD and PDF could not easily be used for regime identification, objective discrimination between separated and intermittent regimes might be possible by fractal techniques. Based on PSD and PDF analyses, Shim and Jo could characterize bubbly, churn, and slug flow patterns in low-flow experiments in a vertical tube. At high flow rates, however, their technique could only distinguish the bubbly flow regime.
To avoid subjective judgment, artificial neural network (ANN) modeling and frequency estimation methods have been employed to implement non-linear mappings from measurable physical parameters to flow regimes (Cai et al., 1994; Mi et al., 1998; Mi et al., 2001). Artificial neural networks are analytical tools that imitate the neural aspect of the human brain, whereby learning is based on experience and repetition rather than the application of rule-based principles and formulas. An ANN (in its most typical form, so-called feed-forward network) consists of a layered network of neurons (nodes), with each neuron connected to a large number of others. The input signal to the network is passed among the neurons, with each neuron calculating its own output using weighting associated with connections. Learning is achieved by the adjustment of the weights associated with inter-neuron connections. ANNs provide capabilities such as learning, self-organization, generalization (response to new problems using incomplete information), and training; and are excellent for pattern recognition and trend prediction for processes that are non-linear, poorly-understood, and/or too complex for accurate first-principle mathematical modeling. They seem ideal for applications to multiphase flow systems, and when properly designed and trained, can potentially improve on-line monitoring and diagnostics.
ANNs have recently been applied for the prediction of complex thermal systems rather extensively. Although the application of neural networks to multiphase flow problems has started only recently, the published studies have clearly demonstrated their enormous potential. Mi 1998, Mi 2001 applied a neural network for two-phase flow regime identification in a vertical channel using signals from electric capacitance probes with excellent results. Gupta et al. (1999) successfully applied a hybrid method based on four neural networks along with simple first-principle models (the latter intended to render the model independent of specific device geometry), for prediction of the attachment rate constant in flotation columns.
This paper follows our previous investigations (Xie 2003a, Xie 2003b). Xie et al. (2003a) reported on a detailed investigation of the flow patterns and gas holdup of gas–water–pulp three-phase flows in a vertical, upward column. The range of pulp consistency (i.e., weight fraction of dry pulp in the pulp-water mixture) in the experiments was varied in the 0.0–1.5% range, which represents the low consistency (LC) pulp suspension range. The aforementioned test facility, with some modifications, was subsequently used (Xie et al., 2003b), whereby local pressure fluctuations recorded by a single high-sensitivity pressure transducer at a particular location on the test section wall ( above the test section inlet) were measured and utilized for the development of an ANN-based method for flow regime identification. Two feed-forward back-propagation ANNs were developed, each having a single hidden layer, and they were shown to predict the flow regimes well using inputs based on the pressure signal: the standard deviation, coefficients of skewness and kurtosis, and several time shift autocorrelations of normalized signals.
Although the aforementioned studies have shown that ANNs are capable of learning to recognize flow regimes based on pressure fluctuation and some other flow-induced signals, a number of important issues need to be resolved before they can find widespread industrial applications. Practical functional transportability of trained ANNs is among these crucial issues. This transportability is defined here as the capability of a single ANN to function with several sensors in the following sense: trained with a sensor, and/or a scaled-down system, it performs acceptably with another reasonably similar sensor and/or a prototypical-scale system. The ANN must then use somewhat sensor-independent, invariant characteristics of the input signal; we will help it along by preprocessing these signals to promote such invariance in the inputs.
In this paper, using the data obtained with the aforementioned test facility (Xie et al., 2003b), the transportability of an ANN trained for regime classification, between pressure signals from three separate but in principle similar sensors, is addressed. The sensors represent different observation points in flow that is not fully developed, and their signal characteristics are therefore somewhat different in addition to differences in calibration (zero, gain, and linearity)—also minor differences in the physical installation of the sensors can affect their signals. Transportability with respect to multiple similar sensors applied to the same system scale (i.e., no scale-change difference) is considered here. This type of transportability is important since small differences among similar sensors (caused by sensor drift, for example) are often inevitable. An ANN is developed that uses the power spectral characteristics of the normalized pressure fluctuations as input, and is shown to have good transportability. An ANN-based method is furthermore developed that enhances the transportability of the aforementioned ANNs. While a redundant system with multiple sensors is an obvious target application, such robustness of algorithms that provides transportability will also contribute to performance with a single sensor, shielding against effects of calibration changes or sensor replacements.
Section snippets
Experiments
The experimental test loop has been described in detail by Xie 2003a, Xie 2003b, and will be reviewed here briefly. A schematic of the experimental facility is shown in Fig. 1. The main components of the loop include a feed tank, a receiving tank, a circulation pump (, Discflo pump), a Hydrosonic pump (also known as a Shock Pulse Generator or SPG), and the test section. The flow in the test loop was established by the circulation pump in these tests, and the Hydrosonic pump was not
Spectral analysis
Periodic phenomena pervade in engineering systems, and the hydrodynamic processes in bubble columns are no exception. Spectral analysis is commonly used to reveal the periodicity in a time-series. The power spectral density is a frequency domain characteristic of a time series and is appropriate for the detection of frequency composition in a stochastic process (Matsumoto and Suzuki, 1984). Assuming the process to be stationary and ergodic, the power spectral density function Px(f) of a
Neural network model for regime identification using the power spectral characteristics of pressure
The principles of ANNs have been described in numerous publications, and will not be repeated here, and only the major characteristics of the designed ANNs are presented. ANNs represent a class of algorithms that can be designed and trained to perform flow regime identification. To some extent, an ANN pattern recognition approach involves a trainable black box (Tsoukalas and Uhrig, 1997). An ANN can be trained to learn the correct output or classification for each of the training samples. After
Transportability
Transportability of a model is often defined as the capability to produce accurate predictions of data not included in the development of the prediction model, and drawn from a different but plausible related population (Justice et al., 1999). For ANNs of interest in flow regime classification, where the system scale and the characteristics of the sensor are also important, the transportability concept needs to be extended to not only address a different but plausible population, but the system
Conclusions
In this paper, the feasibility of using a transportable artificial neural network (ANN)-based technique for the identification of flow regimes in a gas/liquid/pulp fiber three-phase flow system was examined. Experimental data were obtained using an instrumented test loop that included a transparent vertical column (test section) that was long and had an inner diameter of . Flow regimes, including bubbly, plug, churn and slug, were identified visually. Measurements included pressure
Notation
f frequency (Hz) sampling frequency (Hz) k discrete time shift N finite length of a discrete time signal p pressure (Pa) normalized pressure signal power spectral density function (dB) autocorrelation function superficial gas velocity (cm/s) superficial pulp–water mixture velocity (cm/s) discrete time signal variance of spectrum fiber consistency in mixture (%) Superscripts estimated - time average
Acknowledgements
This work was partially supported by DOE grant DE-FC07-00ID13871, which is gratefully acknowledged.
References (39)
- et al.
Transportability of data between electronic nosesmathematical methods
Sensors and Actuators B
(2000) - et al.
Diagnostics of gas–liquid flow patterns in chemical engineering systems
Chemical Engineering and Processing
(1989) - et al.
Effect of operating conditions on the characteristics of pressure fluctuations in a bubble column
Chemical Engineering and Processing
(1991) - et al.
The use of fractal techniques for flow regime identification
International Journal of Multiphase Flow
(1991) - et al.
The interrelation between void fraction fluctuations and flow patterns in two-phase flow
International Journal of Multiphase Flow
(1975) - et al.
A flow pattern map for gas–liquid flow in horizontal pipes
International Journal of Multiphase Flow
(1974) - et al.
Statistical analysis of fluctuations of froth pressure on perforated plates without downcomers
International Journal of Multiphase Flow
(1984) - et al.
Vertical two-phase flow identification using advanced instrumentation and neural networks
Nuclear Engineering and Design
(1998) - et al.
Flow regime identification methodology with neural networks and two-phase flow models
Nuclear Engineering and Design
(2001) - et al.
Bubble characteristics in three-phase systems used for pulp and paper processing
Chemical Engineering Science
(1996)
Flow regimes in two-phase gas–liquid flow
International Journal of Multiphase Flow
Effect of fluid properties and pipe diameter in two-phase flow patterns in horizontal lines
International Journal of Multiphase Flow
Flow regimes and gas holdup in paper pulp–water–gas three-phase slurry flow
Chemical Engineering Science
Flow regime identification in gas–liquid flow and three-phase fluidized beds
Chemical Engineering Science
The yield-stress of medium- and high-consistency mechanical pulp fiber suspensions at high gas contents
Journal of Pulp and Paper Science
Neural network based objective flow regime identification in air–water two-phase flow
Canadian Journal of Chemical Engineering
Application of chaos theory in identification of two-phase flow patterns and transitions in a small, horizontal, rectangular channel
Journal of Fluids Engineering
The disruption shear stress of pulp networks
Svensk Papperstidn
The mechanism of flow of pulp suspensions in pipes
Appita
Cited by (99)
Prediction of drilling plug operation parameters based on incremental learning and CNN-LSTM
2024, Geoenergy Science and EngineeringCapturing intrinsic features from field data for predicting the production of natural gas
2023, Geoenergy Science and EngineeringIdentification of gas-liquid two-phase flow regime in pipelines with low liquid holdup based on ResNet1D-34
2022, Flow Measurement and InstrumentationTwo-phase flow pressure drop modelling in horizontal pipes with different diameters
2022, Nuclear Engineering and DesignTop-of-line corrosion via physics-guided machine learning: A methodology integrating field data with theoretical models
2022, Journal of Petroleum Science and Engineering