Detecting cells rotations for increasing the robustness of cell sizing by impedance measurements, with or without machine learning

A series of novel metal organic frameworks with lanthanide double-layer-based inorganic subnetworks (KGF-3) was synthesized assisted by machine learning. Pure KGF-3 was difficult to isolate in the initial screening experiments. The synthetic conditions were successfully optimized by extracting the dominant factors for KGF-3 synthesis using two machine-learning techniques. Cluster analysis was used to classify the obtained PXRD patterns of the products and to decide automatically whether the experiments were successful or had failed. Decision tree analysis was used to visualize the experimental results, with the factors that mainly affected the synthetic reproducibility being extracted. The water adsorption isotherm revealed that KGF-3 possesses unique hydrophilic pores, and impedance measurements demonstrated good proton conductivities (σ = 5.2 × 10−4 S cm−1 for KGF-3(Y)) at a high temperature (363 K) and high relative humidity (95%).

Download Full-text

Failure-Experiment-Supported Optimization of Poorly-Reproducible Synthetic Conditions for Novel Lanthanide Metal-Organic Frameworks

10.26434/chemrxiv.13490925.v2 ◽

2021 ◽

Author(s):

Yu Kitamura ◽

Emi Terado ◽

Zechen Zhang ◽

Hirofumi Yoshikawa ◽

Tomoko Inose ◽

...

Keyword(s):

Machine Learning ◽

Water Adsorption ◽

Metal Organic Frameworks ◽

Machine Learning Techniques ◽

Initial Screening ◽

Impedance Measurements ◽

Screening Experiments ◽

Learning Techniques ◽

Metal Organic ◽

Lanthanide Metal

A series of novel metal organic frameworks with lanthanide double-layer-based inorganic subnetworks (KGF-3) was synthesized assisted by machine learning. Pure KGF-3 was difficult to isolate in the initial screening experiments. The synthetic conditions were successfully optimized by extracting the dominant factors for KGF-3 synthesis using two machine-learning techniques. Cluster analysis was used to classify the obtained PXRD patterns of the products and to decide automatically whether the experiments were successful or had failed. Decision tree analysis was used to visualize the experimental results, with the factors that mainly affected the synthetic reproducibility being extracted. The water adsorption isotherm revealed that KGF-3 possesses unique hydrophilic pores, and impedance measurements demonstrated good proton conductivities (σ = 5.2 × 10−4 S cm−1 for KGF-3(Y)) at a high temperature (363 K) and high relative humidity (95%).

Download Full-text

Modern Solution for Oil Well Multiphase Flows Water Cut Metering

10.2118/206475-ms ◽

2021 ◽

Author(s):

Aliaksei Sottsau ◽

Ramir Akbashev ◽

Alexandr Peratsiahin ◽

Vadim Garnaev

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Multiphase Flow ◽

High Speed ◽

Impedance Measurements ◽

Flow Rates ◽

Machine Learning Methods ◽

Preliminary Separation ◽

The Russian Federation ◽

Water Cut

Abstract An innovative technology for determining the water cut in well products (without preliminary separation into liquid and gas fractions) uses the results of electrical impedance measurements and its dependence on the alternating current frequency. Water cut meter's sensor includes measuring and current electrodes, between which there is a well's multiphase flow. Imaginary and real components of the impedance quantitatively describe the component composition of the studied oil and gas-water mixtures. In this process, machine learning methods and developed algorithms for features extraction are used. Depending on the type of emulsion, two independent sensors are used in the oil pipeline, one of which measures in a direct emulsion, the other in an inverse emulsion. Tests of the described water cut meter on flow loops in the Russian Federation and in the Netherlands, as well as studies of well flows in oil production facilities in the Russian Federation and the Kingdom of Saudi Arabia, have shown high measurement accuracy in the full range of water cut, with high gas content, as well as at high salinity and in a wide range of flow rates. To do so, modern methods of data classification based on neural networks and regression modeling implemented using machine learning are employed. It was found that the flow rates of liquid and gas do not affect the results of measuring the water cut due to the high frequency of the impedance measurements - up to 100 thousand measurements per second. Use of in-line multiphase water cut meter makes it possible to apply intelligent methods of processing field information and accumulate statistical data for each well, as a big data element for predicting and modeling in-situ processes. It will also allow to introduce promising production processes aimed at increasing oil production and monitoring the baseline indicators of the well. Novelty of the presented technology: Solution of the problem of high-speed determination of water cut in a multiphase flow without preliminary separation using impedance metering. Creation of mathematical models of multiphase flow and methods for determining the type of flow and the type of emulsion. Machine learning methods and neural networks employment for high-speed analysis of flow changes. Development, successful testing and implementation of an affordable multiphase water cut meter of our own design, which has no analogs in industrial applications.

Download Full-text

Failure-Experiment-Supported Optimization of Poorly-Reproducible Synthetic Conditions for Novel Lanthanide Metal-Organic Frameworks

10.26434/chemrxiv.13490925 ◽

2020 ◽

Author(s):

Yu Kitamura ◽

Emi Terado ◽

Zechen Zhang ◽

Hirofumi Yoshikawa ◽

Tomoko Inose ◽

...

Keyword(s):

Machine Learning ◽

Water Adsorption ◽

Metal Organic Frameworks ◽

Machine Learning Techniques ◽

Initial Screening ◽

Impedance Measurements ◽

Screening Experiments ◽

Learning Techniques ◽

Metal Organic ◽

Lanthanide Metal

A series of novel metal organic frameworks with lanthanide double-layer-based inorganic subnetworks (KGF-3) was synthesized assisted by machine learning. Pure KGF-3 was difficult to isolate in the initial screening experiments. The synthetic conditions were successfully optimized by extracting the dominant factors for KGF-3 synthesis using two machine-learning techniques. Cluster analysis was used to classify the obtained PXRD patterns of the products and to decide automatically whether the experiments were successful or had failed. Decision tree analysis was used to visualize the experimental results, with the factors that mainly affected the synthetic reproducibility being extracted. The water adsorption isotherm revealed that KGF-3 possesses unique hydrophilic pores, and impedance measurements demonstrated good proton conductivities (σ = 5.2 × 10−4 S cm−1 for KGF-3(Y)) at a high temperature (363 K) and high relative humidity (95%).

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text