Application of Neural Network and Dual-Energy Radiation-Based Detection Techniques to Measure Scale Layer Thickness in Oil Pipelines Containing a Stratified Regime of Three-Phase Flow

Figure 2. Cont.
(b)Figure 2. Recorded counts under Photopeaks of (a) ²⁴¹Am and (b) ¹³³Ba radioisotope in the second detector for different combed oil, gas and water volume fractions at thickness scale of 0 cm.

(a)

(b)
Figure 3. Recorded counts under Photopeaks of (a) ²⁴¹Am and (b) ¹³³Ba radioisotope in the second detector for different combined oil, gas and water volume fractions at thickness scale of 1.5 cm.

Registered count in detector (per source particle)
Figure 4. Extracted characteristics in terms of scale thickness in constant volume percentage (10% gas, 40% oil, and 50% water).
“Processing-structure-property-performance” is the key mantra in Materials Science and Engineering (MSE)1. The length and time scales of material structures and phenomena vary significantly among these four elements, adding further complexity2. For instance, structural information can range from detailed knowledge of atomic coordinates of elements to the microscale spatial distribution of phases (microstructure), to fragment connectivity (mesoscale), to images and spectra. Establishing linkages between the above components is a challenging task.

Direct property prediction from atomistic configurations

DL methods can be used to establish a structure-property relationship between atomic structure and their properties with high accuracy. Models such as SchNet, crystal graph convolutional neural network (CGCNN), improved crystal graph convolutional neural network (iCGCNN), directional message passing neural network (DimeNet), atomistic line graph neural network (ALIGNN) and materials graph neural network (MEGNet) shown in Table 1 have been used to predict up to 50 properties of crystalline and molecular materials. These property datasets are usually obtained from ab-initio calculations. A schematic of such models shown in Fig. 2. While SchNet, CGCNN, MEGNet are primarily based on atomic distances, iCGCNN, DimeNet, and ALIGNN models capture many-body interactions using GCNN.