Image-Based Deep Learning for Rheology Determination of Bingham Fluids

Abstract

Abstract. In this work, a method to predict the rheological properties of ultrasonic gel, as a reference substance of cement paste, is presented. For this purpose, images are taken with a stereo camera system which show a mixing paddle moving through the ultrasonic gels of different consistency, thus setting them in motion. A digital elevation model (DEM) and a corresponding orthophoto are created from the image pairs using classical image matching and orthoprojection methods. These are used as inputs into a Convolutional Neural Network (CNN), which predicts the support points of a flow curve which classically have to be determined in a rheometer in the laboratory. A simple network architecture consisting of a small number of convolution layers is compared with a pre-trained ResNet-18, which is fine-tuned using gel images. In a second series of experiments, rheological parameters, which alternatively need to be deduced from the flow curve in a separate step, are determined directly from the images. In the third series of experiments, the influence of different factors is tested, such as the position of the cameras relative to the direction of paddle movement and the importance of the DEMs and orthophotos in the training. It is shown in this paper that it is possible to predict the rheological properties of the ultrasonic gels with a suitable setup with a satisfying accuracy.

Image-based Deep Learning for the time-dependent prediction of fresh concrete properties

“…As the problem is less complex than usual classification and segmentation tasks and we only have a relatively small amount of training data, we limit the number of unknowns by using comparatively few layers. The results in Ponick et al (2022) support this approach. A high-level overview of the architecture is shown in Fig.…”

“…Yang et al (2021) and Guo et al (2022) employ another combination of CNN and LSTM with image sequences to predict the slump value and slump flow value respectively the plastic viscosity, while (Gao and Yan, 2023) use semantic segmentation in combination with a residual neural network for single images for the prediction of the slump class. In Ponick et al (2022), a stereo camera set up is used to observe the mixing process of ultra sonic gel, a often employed surrogate for concrete. The stereo camera observations are used as input for a CNN.…”

“…We make use of a CNN for the prediction of the state vector C, consisting of seven convolutional layers which are followed by three fully connected layers (FC layers). The architecture of the CNN is based on the CNN presented in Ponick et al (2022). As the problem is less complex than usual classification and segmentation tasks and we only have a relatively small amount of training data, we limit the number of unknowns by using comparatively few layers.…”

Concrete 4.0 ‐ Sustainable concrete construction with digital quality control

“…The regression performed in the CNN finally produces values for viscosity and yield stress of the fresh concrete. For methodological and mathematical details on the described approach, we refer the reader to [32].…”

Image‐based analysis of fresh concrete flow ‐ determining the correlation between flow behavior and rheological properties

“…In [13] a camera based characterization method for fresh concrete in the flow table test was developed. In [14] the flow behavior of ultrasound gel was studied in experimental investigations, predicting rheological properties of the material out of the flow behavior using a CNN based evaluation method of recorded stereo image frames. Beyond that, studies were carried out evaluating images of fresh concrete from the mixing process by extracting the shape of the concrete inside the mixer, for determining the slump flow and V-funnel flow time [15].…”