Machine learning classification of flow regimes in a long pipeline-riser system with differential pressure signal

Xu, Qiang; Liu, Chenying; Wang, Xinyu; Cao, Yeqi; Yu, Haiyang; Li, Wensheng; Guo, Liejin

doi:10.1016/j.ces.2020.116402

Cited by 24 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our results, the performance was generally enhanced as the sample length increased. This is generally consistent with the results of previous studies that examined the effects of the sample length on the performance of the suggested systems [65,66]. Interestingly, sample lengths with the highest performance in walking and running were shown to be slightly different; signal lengths of 100 samples (approximately 2 s) and 150 samples (approximately 3 s) demonstrated the best F m for most classifiers in both walking and running conditions.…”

Section: Effect Of Waveform Lengthsupporting

confidence: 90%

Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices

Joo

Kim

Ryu

et al. 2022

IJERPH

View full text Add to dashboard Cite

People who exercise may benefit or be injured depending on their foot striking (FS) style. In this study, we propose an intelligent system that can recognize subtle differences in FS patterns while walking and running using measurements from a wearable smartwatch device. Although such patterns could be directly measured utilizing pressure distribution of feet while striking on the ground, we instead focused on analyzing hand movements by assuming that striking patterns consequently affect temporal movements of the whole body. The advantage of the proposed approach is that FS patterns can be estimated in a portable and less invasive manner. To this end, first, we developed a wearable system for measuring inertial movements of hands and then conducted an experiment where participants were asked to walk and run while wearing a smartwatch. Second, we trained and tested the captured multivariate time series signals in supervised learning settings. The experimental results obtained demonstrated high and robust classification performances (weighted-average F1 score > 90%) when recent deep neural network models, such as 1D-CNN and GRUs, were employed. We conclude this study with a discussion of potential future work and applications that increase benefits while walking and running properly using the proposed approach.

show abstract

Section: Effect Of Waveform Lengthsupporting

confidence: 90%

Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices

Joo

Kim

Ryu

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…Niza et al found that the bubble size acquired in acid conditions (pH = 5) was smaller than that in basic conditions (pH = 10). In addition, an effective method to predict the interface evolution behavior of gas–liquid two-phase flow by using pressure signals in the flow field has also been developed by researchers. − However, when the electrolyte pH varies over a wide range, how the bubble growth and detachment changes and its effect on the reaction rate are still unclear.…”

Section: Introductionmentioning

confidence: 99%

Effect of Electrolyte pH on Oxygen Bubble Behavior in Photoelectrochemical Water Splitting

Liang

Nie

et al. 2023

J. Phys. Chem. C

Self Cite

View full text Add to dashboard Cite

The issue of increased reaction resistance due to bubble growth has always been a major bottleneck limiting the efficiency improvement of photoelectrochemical water splitting. In this study, we developed a synchronized measurement system with a micro-high-speed camera and an electrochemical workstation to observe oxygen bubble evolution on the surface of a fixed TiO2 film electrode in situ. The intrinsic relationship between the nucleation and growth of oxygen bubbles and photocurrent at different pH values (1.0–13.0) was investigated. The results indicate that higher pH can promote bubble nucleation at lower potentials. Additionally, increasing pH from 1.0 to 13.0 at 0.1 V vs Ag/AgCl, the photocurrent in the bubble growth stage increases by about 35 times, and the average period of bubble growth decreases by about 15 times. Compared with pH = 9.0, the gas production rates of pH = 1.0 and pH = 13.0 are improved by 13 times and 22 times at 0.71 V vs RHE, respectively. Then, we developed a force balance model for oxygen bubbles at the anode surface, and the predicted bubble detachment diameters are in good agreement with the experimental results. The Marangoni force induced by the nonuniform distribution of dissolved oxygen was found to be increased with pH, which leads to the larger detachment diameter of bubbles. The results show that the strong alkali environment is an effective means to remove oxygen bubbles from the surface of the photoelectrode.

show abstract

“…Yu Guopeng et al [27] conducted a stress analysis of LNG cryogenic pipelines, and analyzed the influence of wind load, earthquake load and other factors on pipe stress. Qiang Xu et al [28,29] conducted research on two-phase flow regimes of a long-distance pipeline-riser system and found that differential pressure signals at different pipe positions can have a significant impact on the recognition rate. Se-Yun Hwang et al [30] studied pipe stresses of piping system installed on LNG carriers under various conditions using CAESAR-II software based on beam elements and conducted an evaluation of analytical results of piping arrangement of LNG.…”

Section: Introductionmentioning

confidence: 99%

Stress and Pressure Pulsation Analysis of Low Temperature Compressor Piping System in LNG Vaporizing Station

et al. 2022

View full text Add to dashboard Cite

LNG (Liquefied Natural Gas) vaporizing stations are usually built in the cities and towns, and the BOG (Boiled Off Gas) pressurizing system is a very important element. In the pressurizing system, the severe vibration of the low-temperature reciprocating compressor may lead to a failure of the pipeline system and the equipment. Therefore, this paper analyzes the stress and pressure pulsation of the BOG compressor piping system in the LNG vaporizing station. The beam model was used to establish the pipe model. The static, harmonic and modal analysis were carried out based on the plane-wave theory and the pressure-fluctuation theory, and the influence factors of support spacing, the settlement of the fulcrum foundation, pipe pressure and elbow angle were analyzed. The main conclusions are as follows: (1) the unbalanced excited force caused by pressure pulsation greatly affects the stress of the exhaust pipe and compressor outlet pipe, and has less influence on the stress of the suction pipe and compressor inlet pipe; (2) although unbalanced excited force is generated in the elbow, it also has an impact on the straight pipe stress; (3) adding an expansion joint to the pipe of the BOG compressor can effectively reduce the stress of the pipe its the displacement, and can increase the flexibility of the pipe.

show abstract

Machine learning classification of flow regimes in a long pipeline-riser system with differential pressure signal

Cited by 24 publications

References 26 publications

Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices

Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices

Effect of Electrolyte pH on Oxygen Bubble Behavior in Photoelectrochemical Water Splitting

Stress and Pressure Pulsation Analysis of Low Temperature Compressor Piping System in LNG Vaporizing Station

Contact Info

Product

Resources

About