Deep learning based liquid level extraction from video observations of gas–liquid flows

Olbrich, Marc; Riazy, Leili; Kretz, T.; Leonard, Terri; Putten, Dennis S. van; Bär, Markus; Oberleithner, Kilian; Schmelter, Sonja

doi:10.1016/j.ijmultiphaseflow.2022.104247

Cited by 5 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies have indicated that the waterline is determined by the horizontal projection of grayscale images and edge images, which effectively overcomes the shortcomings of poor light, glare, shadow, and artificial night lighting in complex scenes, and its accuracy reaches 1 cm [33][34].…”

Section: Review Of Related Workmentioning

confidence: 99%

Contactless Water Level Detection System for Pickling Barrels Using Image Recognition Technology

Hung,

FanJiang,

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Water level monitoring has long been an important task for farmers. Because weather conditions can change quickly, farmers have often checked that the water levels of their crops were ideal for good growing conditions. Farmers would benefit from the development of a simple device to determine the water level of crops at any time. This research designs a noncontact water level detection system, including a data acquisition system, a data management monitoring system, and an instant messenger. In the data acquisition system, a digital water gauge is designed, mainly using image recognition technology to identify the water level in a barrel. Our research shows that using a black dot with a diameter of 1 cm as the water gauge scale can achieve 100% recognition results at a distance of 110 cm. Considering that the application of a contactless water level detection system (CWLDS) in agriculture is a fixed measurement method and an external light source is supported, 100% identification can be obtained, and the operation cost of a CWLDS can be reduced without an additional machine learning technique. To effectively reduce the transmission cost, the reading part of the digital water gauge is divided into single-barrel and multi-barrel parts. The water level information is sent to a management center through a narrowband Internet of Things (NB-IoT) transmission module. This system provides a well-structured and systematic approach to the problem of measuring water levels in pickling barrels. Through the data management monitoring system, the collected water level of each object is matched with a database in the host to determine whether the water level is abnormal. The system can provide immediate alerts to relevant personnel by using popular instant messaging software that transmits abnormal water level information to farmers.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

Contactless Water Level Detection System for Pickling Barrels Using Image Recognition Technology

Hung,

FanJiang,

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Regression-based prediction of flow-induced dominant vibrational frequencies in two-phase flow regimes

Sohail,

Pao,

Othman

et al. 2024

Ocean Engineering

View full text Add to dashboard Cite

Hydraulic modeling of slag cover surface in top-blown molten bath smelting processes assisted by machine learning

Yang,

Yu,

Pan

et al. 2024

Physics of Fluids

View full text Add to dashboard Cite

Variation of the slag cover surface (SCS) in the oxygen-enriched top-blown molten bath smelting process is critical for the smelting efficiency of a complex Cu–S concentrate. However, capturing these variation characteristics is difficult because of the high temperature inside the molten bath and the dynamic complexity of the smelting process. In this work, machine learning (i.e., U-net algorithm and support vector machine) is combined with a skillful hydraulic model (i.e., gas–liquid two-phase top-blown agitated vessel) and an experimental measurement strategy to quantitatively explore the variation characteristics of the SCS in an oxygen-enriched top-blown molten bath smelting process. Results showed that a minimum of 30 images, with the smallest size being 900 × 600 pixels, was sufficient for the training process. The data accuracy of the training procedure ranged from 93.20% to 96.23% for identifying the SCS at the laboratory scale. The highest average height of 2.23 cm for the SCS occurred under the operational condition, with a flow rate of 160 L/h, a liquid temperature of 60 °C, and a liquid depth of 0.4 m. The chaotic systems of SCS in industry were deterministic. It was found that the proposed strategy could be used to accurately identify the variation characteristics of the SCS in the gas–liquid two-phase top-blown agitated vessel. The variation of the SCS in the industrial process could be roughly grasped by magnifying the height of the SCS obtained from the experimental data in the laboratory. Quantification of the variation characteristics of the SCS is useful to increase the smelting efficiency of the oxygen-enriched top-blown molten bath smelting process. This also provides insights for multiphase measurements in other studies related to efficient utilization of complex Cu–S concentrates.

show abstract

Deep learning based liquid level extraction from video observations of gas–liquid flows

Cited by 5 publications

References 51 publications

Contactless Water Level Detection System for Pickling Barrels Using Image Recognition Technology

Contactless Water Level Detection System for Pickling Barrels Using Image Recognition Technology

Regression-based prediction of flow-induced dominant vibrational frequencies in two-phase flow regimes

Hydraulic modeling of slag cover surface in top-blown molten bath smelting processes assisted by machine learning

Contact Info

Product

Resources

About