Processing Regimes Research Articles

Fractional Criticality Theory and Its Application in Seismology

To understand how the temporal non-locality («memory») properties of a process affect its critical regimes, the power-law compound and time-fractional Poisson process is presented as a universal hereditary model of criticality. Seismicity is considered as an application of the theory of criticality. On the basis of the proposed hereditarian criticality model, the critical regimes of seismicity are investigated. It is shown that the seismic process has the property of «memory» (non-locality over time) and statistical time-dependence of events. With a decrease in the fractional exponent of the Poisson process, the relaxation slows down, which can be associated with the hardening of the medium and the accumulation of elastic energy. Delayed relaxation is accompanied by an abnormal increase in fluctuations, which is caused by the non-local correlations of random events over time. According to the found criticality indices, the seismic process is in subcritical regimes for the zero and first moments and in supercritical regimes for the second statistical moment of events’ reoccurrence frequencies distribution. The supercritical regimes indicate the instability of the deformation changes that can go into a non-stationary regime of a seismic process.

The Public Interest Requirement in the Secondary Use of Health Data in Scientific Research: The Examples of Estonia and Finland

The General Data Protection Regulation (GDPR) foresees a flexible data processing regime for conducting scientific research with health data. This regime also enables extensive limitations on data subjects' rights to privacy and self-determination. Concern has been expressed that the notion of 'scientific research' may encompass conducting also profit-oriented commercial research that might not justify such limitations to data subjects' rights. Some authors have suggested a restriction on benefiting from the flexible scientific research regime: public interest should be set as a prerequisite for any scientific research employing health data without the data subject's consent. While the GDPR does not explicitly require that scientific research be in the public interest, it allows Member States to choose their policies. In light of this, the article examines the examples of Estonia and Finland to analyse whether national law should require the processing of health data in scientific research in the absence of the data subject's consent to be in the public interest. The article demonstrates on the basis of the two countries’ examples that it is possible to set a public interest standard without explicitly requiring the existence of a public interest via national legislation. Considering the future, the article also shows that, under the proposed European Health Data Space regulation, Member States may retain the public interest standard through the ethics-review requirement in their national law.

Numerical investigation of the combustion regime in pilot-ignited high-pressure direct-injection low reactivity fuel combustion with the injection system of eccentric configuration

The pilot-ignited high-pressure direct-injection (HPDI) combustion with the eccentric configuration is a practical approach to achieve high thermal efficiency and clean combustion. However, the combustion process and combustion regime still remain unclear. In this study, the effects of two key parameters “offset” (distance between concentric and eccentric injectors) and “dwell” (interval between concentric and eccentric injection timing) on the combustion process, combustion regime, and the corresponding performance are numerically investigated systematically. Results show that the interaction between the flame kernels of pilot fuel and the plumes of main fuel determines the combustion mode of each main fuel plume, and thereby different combustion regimes in the pilot-ignited HPDI engine can be generated by controlling the offset and dwell. Specifically, under the concentric configuration or the eccentric configuration with very small offset and dwell, all the main fuel plumes are in the non-premixed mode, exhibiting a diffusion combustion (DC) regime. Under the eccentric configuration with medium offset and dwell, some of the main fuel plumes are in the non-premixed and the others in the partially premixed mode, exhibiting a special combustion regime, which is named the multi-mode co-existing combustion (MMCC) in this study. Under the eccentric configuration with large offset and dwell, all the main fuel plumes are in the partially premixed mode, exhibiting a partially premixed combustion (PPC) regime. Among the three combustion regimes, the diffusion combustion regime exhibits the lowest ISFC and unburned HC emission but high NOx and soot emissions. The ISFC of the partially premixed combustion regime is almost double that of the other two regimes which is far from being acceptable. The MMCC regime shows a better comprehensive performance: achieving much lower ringing intensity and soot emission with almost the same ISFC compared to the diffusion combustion regime. In summary, the pilot-ignited HPDI combustion with the eccentric configuration can potentially achieve high fuel economy with low emissions, under the premise of the ratio of non-premixed and partially premixed combustion modes in the MMCC regime is well controlled.

Harmonizing sound and light: X-ray imaging unveils acoustic signatures of stochastic inter-regime instabilities during laser melting

Laser powder bed fusion (LPBF) is a metal additive manufacturing technique involving complex interplays between vapor, liquid, and solid phases. Despite LPBF’s advantageous capabilities compared to conventional manufacturing methods, the underlying physical phenomena can result in inter-regime instabilities followed by transitions between conduction and keyhole melting regimes — leading to defects. We investigate these issues through operando synchrotron X-ray imaging synchronized with acoustic emission recording, during the remelting processes of LPBF-produced thin walls, monitoring regime changes occurring under constant laser processing parameters. The collected data show an increment in acoustic signal amplitude when switching from conduction to keyhole regime, which we correlate to changes in laser absorptivity. Moreover, a full correlation between X-ray imaging and the acoustic signals permits the design of a simple filtering algorithm to predict the melting regimes. As a result, conduction, stable keyhole, and unstable keyhole regimes are identified with a time resolution of 100 µs, even under rapid transitions, providing a straightforward method to accurately detect undesired processing regimes without the use of artificial intelligence.

Optimization of solid wood workability parameters in the planing process

It is known from theory and practice that the workability of wood depends on structural parameters that are closely related to the physical, mechanical and chemical properties of the type of wood itself, and disturbance parameters that refer to the technological and geometric parameters determined by the specific processing regime. That machinability, in addition to the mechanical output sizes, is often expressed by the quality, that is, the roughness of the processed surface. By defining a mathematical model in the process of planing solid wood in which the input sizes are processing parameters: wood density (ρ), feed rate (m/min) and number of cutting spirals (z), and the spilled sizes are praamters of roughness of the treated surface (Ra and Rz), and by applying optimization methods, optimal solutions for the process of planing solid wood on planer machines will be determined, so that the obtained Yoptim model will aim to improve the workability of solid wood, specifically its roughness of the processed surface.

Rhythmic modulation of prediction errors: A top-down gating role for the beta-range in speech processing.

Natural speech perception requires processing the ongoing acoustic input while keeping in mind the preceding one and predicting the next. This complex computational problem could be handled by a dynamic multi-timescale hierarchical inferential process that coordinates the information flow up and down the language network hierarchy. Using a predictive coding computational model (Precoss-β) that identifies online individual syllables from continuous speech, we address the advantage of a rhythmic modulation of up and down information flows, and whether beta oscillations could be optimal for this. In the model, and consistent with experimental data, theta and low-gamma neural frequency scales ensure syllable-tracking and phoneme-level speech encoding, respectively, while the beta rhythm is associated with inferential processes. We show that a rhythmic alternation of bottom-up and top-down processing regimes improves syllable recognition, and that optimal efficacy is reached when the alternation of bottom-up and top-down regimes, via oscillating prediction error precisions, is in the beta range (around 20-30 Hz). These results not only demonstrate the advantage of a rhythmic alternation of up- and down-going information, but also that the low-beta range is optimal given sensory analysis at theta and low-gamma scales. While specific to speech processing, the notion of alternating bottom-up and top-down processes with frequency multiplexing might generalize to other cognitive architectures.

Self-Supervised Bayesian representation learning of acoustic emissions from laser powder bed Fusion process for in-situ monitoring

This study presents a self-supervised Bayesian Neural Network (BNN) framework using air-borne Acoustic Emission (AE) to identify different Laser Powder Bed Fusion (LPBF) process regimes such as Lack of Fusion, conduction mode, and keyhole without ground-truth information. The proposed framework addresses the challenge of labelling datasets with semantic complexities into discrete process dynamics. This novel AE-based in-situ monitoring approach provides a promising alternative to quantify part density in LPBF process. The study demonstrates the effectiveness of a Bayesian encoder backbone for learning the manifold representations of LPBF regimes, which were visually separable in a lower-dimensional representation using t-distributed stochastic neighbour embedding. The generalized representations learned by the Bayesian backbone allowed traditional classifiers trained on smaller datasets to exhibit high classification accuracy. The feature map computed using pre-trained Bayesian encoder on other datasets was also effective in anomaly detection, achieving 92% accuracy with one-class Support Vector Machine. Additionally, the representation learned by the BNN facilitates transfer learning, where it can be fine-tuned for classification tasks on different process maps, which is also demonstrated in this work. Our proposed framework improves the generalization and robustness of the LPBF monitoring, particularly in the face of varying data distribution across multiple process parameter spaces.

Dependence of Electrochemical Characteristics of a Biodegradable Fe-30Mn-5Si wt.% Alloy on Compressive Deformation in a Wide Temperature Range

Fe-30Mn-5Si alloy subjected to a compression test at various deformation temperatures ranging from 350 to 900 °C with a strain rate of 1 s−1 are studied. It was found that the Fe-30Mn-5Si alloy exhibits high resistance to the dynamic recrystallization process in a whole studied range of deformation temperatures. There are no differences in structure formation in the zone of action of tangential tensile stresses and peripheral and central zones of localized compressive stresses. The room-temperature X-ray diffraction study shows the presence of a single-phase state (FCC γ-austenite) after deformation temperature range from 350 to 700 °C and a two-phase state (FCC γ-austenite + HCP ε-martensite) after deformation test at 900 °C. The presence of a two-phase state provides a higher rate of biodegradation compared with a single-phase state. The changes in the biodegradation rate dependence on the structure change with an increase in the deformation temperature are explained. Favorable temperature regimes for subsequent thermomechanical processing are proposed based on the relationship between structure formation and biodegradation rate to obtain semi-products from the Fe-30Mn-5Si alloy.

A defect detection framework using three-dimensional convolutional neural network (3D-CNN) with in-situ monitoring data in laser powder bed fusion process

Laser powder bed fusion (L-PBF) is a promising additive manufacturing (AM) technology for manufacturing complex-shaped metallic parts with high density. Since L-PBF has been rapidly developed and applied in various industries, the quality assurance of the printed part using the process became a topic of primary importance. In this respect, in-situ monitoring techniques have received increased attention in recent years for aiding the quality control of L-PBF process and the certification of the products. This study proposes a novel defect detection framework with a three-dimensional convolutional neural network (3D-CNN) and in-situ monitoring of light intensity for detecting both the lack-of-fusion and keyhole-induced defects. The proposed 3D-CNN model works with a 3D moving window to perform the local inspection using the measured light intensities in three-dimensional space to classify the type of defect. Furthermore, the model predicts the local volume fraction to provide insights into the degree of defect. To perform the classification and regression with a single 3D-CNN, the joint classification and regression approach was adopted to train the model using the results obtained with micro-computed tomography as the ground truth. In order to build the training dataset, the samples with artificial defects were fabricated in different process regimes with energy densities ranging from 19.84J/mm3 to 110.12J/mm3. After the training process, the proposed model was evaluated with the test specimens which contain randomized defects generated due to the excessively low and high energy input. The results showed that the proposed 3D-CNN-based defect detection framework can detect pores greater than 80μm induced by both lack-of-fusion and keyhole mode melting. The sensitivity of the proposed framework was evaluated, showing the true positive rate of 75.69% and 70.47% for lack-of-fusion and keyhole defects with a void volume larger than 0.0003mm3. The prediction of local volume fraction with R2 score of 0.91 was also achieved with the proposed 3D-CNN approach.

Sedimentological and tectono-stratigraphic characterisation of a shallow-marine reservoir, ‘Dona’ field, offshore Niger Delta

The ‘Dona’ field is located in the shallow offshore Coastal Swamp depobelt, western Niger Delta. The field contains multiple, stacked shallow-marine reservoir intervals of Miocene to early Pliocene age in the Agbada Formation. The area surrounding the field is characterised by a series of synthetic, listric normal faults that strike north-northwest to south-southeast and dip southwest. These faults show stratigraphic thickening in their hangingwalls, indicating growth, and are associated with the development of rollover anticlines, which define the trap configuration of the ‘Dona’ field. Spatio-temporal variations in stratigraphic expansion indicate that growth faulting started in more landward (northeasterly) locations and migrated progressively basinward (southwestward). These variations are consistent with growth faulting due to gravity-induced shale diapirism, potentially driven by overall progradation of the Niger Delta.Core and wireline-logs from a representative reservoir interval contain a facies assemblage and stratigraphic architecture developed under a mixed-influence depositional process regime, which was dominated by wave processes but influenced by tidal processes. Wave-dominated shoreface deposits occur in a series of coarsening- and shallowing-upward parasequences that are laterally continuous over the reservoir but are locally erosionally truncated by fining-upward tidal channel-fill deposits. The mixed-influence process regime may reflect spatial variations in the dominance of wave, tide and fluvial processes, as in the modern Niger Delta, and/or temporal variations between a regressive, wave-dominated regime and a transgressive, tide-dominated regime. Sedimentological heterogeneities are present across a range of scales, and their distribution reflects the mixed-influence depositional process regime.

Fluvial geomorphic evolution and stream fish community trajectories in the Bayou Pierre, Mississippi, U.S.A.

Abstract Human activities have often altered sediment dynamics in rivers, leading to aquatic habitat degradation. The dominant paradigm in fish–sediment interactions focuses on excessive fine sediments as indicators of habitat and water quality degradation. In contrast, geomorphologists have provided frameworks linking altered sediment dynamics to much broader and more complex changes to channel morphology and stream habitats across spatial scales. In this paper we use an interdisciplinary approach with historical and contemporary channel morphology and fish community datasets to examine how altered sediment dynamics have affected stream fish community evolution in the Bayou Pierre, Mississippi, U.S.A. Erosional process regimes have advanced upstream consistent with models of knickpoint propagation and channel evolution, leaving most of the catchment in a state of increased sediment transport and local sediment deficits. Fish communities in modern samples have less α and β diversity and fewer habitat specialist taxa than in historical samples. Whole‐community analysis via non‐metric multidimensional scaling found a strong gradient of homogenisation towards a fauna comprised of small‐bodied taxa adapted to large rivers. Comparisons of community and geomorphic change on this gradient found that reaches that transitioned between process regimes had more community change, and that local habitat factors relating to advanced channel evolution were strongly positively related to total community change. These results demonstrate that a catchment‐scale geomorphic analysis provided a strong tool for understanding fish community change on a decadal scale. Our findings further demonstrate concordant ecological responses to a complex sequence of disturbances and suggest that a broader view of sediment dynamics offers a rich toolkit for ecological analyses.

Reevaluating the process regime in the Sego Sandstone: Sedimentological and ichnological evidence for an underemphasised fluvial signature

AbstractRocks of coastal to shallow‐marine origin are challenging to interpret owing to the complex interplay of various depositional processes. This study reevaluates the relative roles of fluvial, tidal and wave processes in the Upper Cretaceous Sego Sandstone (and subordinately in the underlying Buck Tongue) of the Book Cliffs, USA, a well‐studied ancient coastal to shallow‐marine succession. Detailed sedimentological and ichnological analyses were used to interpret a previously underemphasised riverine signature, consisting of centimetre‐ to decimetre‐thick alternations of sandstone and heterolithic beds inferred to represent flood–interflood periods of variable river discharge. Recognition of a widespread fluvial‐dominated signature across the studied units better agrees with other sedimentological and regional observations in the study area, such as high sandstone–mudstone ratios, largely unidirectional and seaward‐oriented palaeocurrents, and modelled weak tidal conditions in the basin. When considering all of the sedimentological, ichnological and stratigraphic observations together with its regional depositional context, the Sego Sandstone/Buck Tongue system is better explained using a mixed‐energy but fluvial‐dominated deltaic model. This highlights an historical over‐interpretation of tidal processes and subordinate wave processes in the Sego Sandstone and likely in similar units. The widely used approach that emphasises only certain sedimentary features in discerning the process regime from analysis of rocks of inferred coastal to shallow‐marine origin is unrefined and may therefore underrepresent the actual complexity of these systems.

Processing condition dependency of increased layer thickness on surface quality during electron beam powder bed fusion

The energy beam and powder layer interaction influences the dynamic melt behavior and determines the surface quality in electron beam powder bed fusion (PBF-EB). It is generally believed that increasing the powder layer thickness favors production efficiency but is contradictory to improving the forming quality. How variations in the powder layer thickness affect the interaction between the electron beam and the powder bed, which influences the melt behavior and resultant surface quality, has not been well understood. In this study, cylindrical specimens with increased nominal layer thicknesses from 80 to 140 μm were prepared using PBF-EB. The study verified the processing feasibility of ensuring the forming quality under a high layer thickness. Within the processing regime of this study, a relatively large powder layer thickness expanded the processing window. According to the thermophysical-property analysis of the powder bed, the emissivity and thermal conductivity exhibited upward and downward trends, respectively, with increased powder layer thickness. The increased thickness reduced the fusion efficiency, restricting the height difference within the overall sample surface caused by overheating. The numerical simulation clarified the dependence of the layer thickness-effect on the processing conditions. The proportion of incomplete melted powder in the electron beam irradiating area increased at a high scan speed. Subsequently, the hindering effect on heat absorption and transfer caused by the powder layer and its increased thickness was fully manifested. That is, the evolution trend of melt behavior and surface morphology resulting from increased layer thickness is remarkable at high scan speeds.

Promoting Patient Advocacy During an Interprofessional Parkinson Simulation

Background: Parkinson's is the second-most common neurodegenerative disease after Alzheimer's disease with about 90,000 people in the United States being diagnosed each year [1]. These staggering numbers make it essential for future nurses to understand the disease process and treatment regimes. Methods: The study is a mixed method design using quantitative data from 5 post simulation questions utilizing the Likert scale and 1 open ended question. Results: The majority of students answered between a 4-5 on the Likert scale indicating they felt very comfortable/ confident to somewhat comfortable/confident on all 5 questions. The student takeaways from the simulation experience were positive indicating they learned the importance of listening to the patient and family, the importance of medication, adhering to the medication schedule, and communication with the physician. Conclusions: Using an interprofessional simulation experience that focused on the medication schedule of a patient with Parkinson’s to help student learn patient advocacy has proven effective. A well planned out simulation scenario created a space where educator could focus on soft skills, like communication, collaboration, and advocacy.

Evaluation of the efficiency of microwave heating of soils

One of the innovative directions of heat treatment of soil in the technologies of decontamination from pesticides, oil products and disinfection is heating in a microwave electromagnetic field. Numerical studies testify to the effectiveness of the microwave treatment method. This is due to the peculiarities of the interaction of the microwave field with dielectric materials. Unique effects arise, such as the possibility of local heating, volume heating of the material, unidirectionality of pressure and humidity gradients. This contributes to the intensification of transfer processes and the possibility of energy savings. However, the challenge at present is to determine the processing regimes, including load mass, specific microwave field power, electric field strength, material layer thickness, and processing time, under which the microwave method will be energy efficient. Conducting multifactorial experimental studies allows determining the conditions of energy feasibility of microwave soil treatment. Therefore, the object of research is the process of heating a dense layer of soil under the action of a microwave electromagnetic field. The results of studies on the effect of microwave treatment of soil contaminated with organophosphorus pesticides, contaminated with petroleum products, and under what conditions the qualitative effect was obtained, as well as the results of the effect of the microwave field on the pathogenic microflora of the soil used for growing plants, were considered. The high quality of implementation of soil treatment technologies is determined. Energy efficiency was determined on the basis of data on temperature and moisture content, analysis of thermograms of microwave heating of chernozem and clay soil, analysis of the influence of material layer thickness, influence of dielectric properties and power of the microwave field. According to the results of thermal calculations, the values of the efficiency of the microwave chamber and the intensity of the electric field were determined, which are recommended as the basis for scaling in order to transfer the experimental results to industrial installations. During the research, specific experimental methods of research under microwave heating conditions, analytical methods of thermal calculations, developed by the authors of the experimental research methodology were used. Experimental studies were carried out on the installation created by the authors. The results of the research are intended for the wide implementation into practice of technological calculations of microwave chambers for heat treatment of soils, intensification of disinfection processes under the conditions of energy efficiency of the transformation of the energy of the microwave field into the internal energy of the soil.

Nutritional Quality and Overall Acceptability Optimization of Ultra-Fast Air-Superchilled Golden Rainbow Trout (Oncorhynchus mykiss, Stevanovski) Using the Response Surface Methodology

Temperatures below the cryoscopic point help to partially freeze most of the water in the fish muscle tissue. This reduces water activity and makes the remaining free water hardly accessible to microorganisms. The objective of this study was to determine the best process regime of ultra-fast air-superchilling, giving us the optimal quality of golden rainbow trout. Two hundred and thirty-four live golden rainbow trout (Oncorchynchus mykiss, Stevanovski) (18 groups of 13 fish in a group) were caught and immediately stunned by an electric current (P = 42 W). The stunned fish was placed in styrofoam cans and covered with flaked ice. The sensory analysis, total nitrogen volatile bases (TVB-N), total number of microorganisms (TVC), and presence of biogenic amines were determined. According to the optimized values for TVB-N, TVC, and sensory scores, giving us a better quality of ultra-fast air-superchilled golden rainbow, the process regime has been found at the following parameters: air temperature T = −11.3 °C; airflow velocity υ = 6.5 m s−1; and packaging layer thickness D = 79.2 μ. The superchilled golden rainbow trout processed by this regime has the lowest degree of proteolytic degradation, delayed development of the microflora, and retains the best possible sensory properties and freshness.

False positives are common in single-station template matching

Template matching has become a cornerstone technique of observational seismology. By taking known events, and scanning them against a continuous record, new events smaller than the signal-to-noise ratio can be found, substantially improving the magnitude of completeness of earthquake catalogues. Template matching is normally used in an array setting, however as we move into the era of planetary seismology, we are likely to apply template matching for very small arrays or even single stations. Given the high impact of planetary seismology studies on our understanding of the structure and dynamics of non-Earth bodies, it is important to assess the reliability of template matching in the small-n setting. Towards this goal, we estimate a lower bound on the rate of false positives for single-station template matching by examining the behaviour of correlations of totally uncorrelated white noise. We find that, for typical processing regimes and match thresholds, false positives are likely quite common. We must therefore be exceptionally careful when considering the output of template matching in the small-n setting.

GaAs ablation with ultrashort laser pulses in ambient air and water environments

Water-assisted ultrashort laser pulse processing of semiconductor materials is a promising technique to diminish heat accumulation and improve process quality. In this study, we investigate femtosecond laser ablation of deep trenches in GaAs, an important optoelectronic material, using water and ambient air environments at different laser processing regimes. We perform a comprehensive analysis of ablated trenches, including surface morphological analysis, atomic-resolution transmission electron microscopy imaging, elemental mapping, photoluminescence, and Raman spectroscopy. The findings demonstrate that GaAs ablation efficiency is enhanced in a water environment while heat-accumulation-related damage is reduced. Raman spectroscopy reveals a decrease in the broad feature associated with amorphous GaAs surface layers during water-assisted laser processing, suggesting that a higher material quality in deep trenches can be achieved using a water environment.

Planetary roller melt granulation (PRMG) – A new continuous method for powder processing

For the continuous operation of granulation, which is a standard unit operation in powder processing to modify the particle size, the use of twin-screw machines was established as standard method for wet and melt granulation over the last decade. A main characteristic for this technology is the pronounced mechanical energy input and the coupling of this parameter to the throughput for high throughputs. This is challenging for melt granulation with respect to temperature control and the handling of temperature sensitive materials.In this respect, the use of a planetary roller granulator is a promising alternative due to the distinctive process concept. Here, planetary spindles within a roller cylinder are circulating around a motor-driven central spindle. These three main parts are interlocking due to a 45°toothing, which results in an enhanced generated surface of the processed material. In addition with the heating concept, which includes the roller cylinder and central spindle, this leads to an enhanced ratio of heated surface to process volume.For planetary roller melt granulation (PRMG), the feed rate and rotation speed as direct process parameters are suitable to adjust the mechanical and thermal energy input, while the ratio of these correlates to the product temperature. Therefore, a predictive determination of an operating point in this context is possible by the derived corresponding model. Moreover, the variation of the direct process parameters also impacts the fraction of net granulated particles during PRMG. This is an indicator for a shift in the overall process regime with respect to the fundamental process rates.

Development of an intelligent dual-beam gamma densitometer for real-time recognition of two-phase flow regime in horizontal pipe

This work includes the hardware and software development of a high sampling rate dual-beam gamma densitometer for real-time two-phase flow monitoring. The designed densitometer consists of two fast SiPM-based gamma detectors and a custom embedded system for digital signal processing and running flow regime recognition neural network. An exclusive LSTM deep neural network has been developed to classify flow regimes into six classes including stratified, annular, bubbly, wavy, slug, and plug. Therefore, the proposed design is superior to the traditional approaches by (i), unifying signal processing and flow identification units into a single cost-effective embedded system; (ii), reducing the need for time-consuming signal preprocessing steps from conventional to feed-forward neural networks, and (iii), real-time identification of the flow due to the high refresh rate of the data processing chain. The optimal neural network model has been obtained through comprehensive sensitivity analyses to have the best interpolation and generalization. The experimental evaluations showed that the optimized model recognizes the flow regime based on 6 s of gamma data sequence with an accuracy of ∼92%–97% depending on the flow regime in the pipeline. Furthermore, the real-time experiment proved the successful performance of the densitometer to trace the flow regime across the two-phase flow map.