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

TL;DR

The paper addresses the challenge of predicting fresh concrete properties during the mixing process to enable in-process control. It introduces a multimodal CNN that ingests stereoscopic imagery, optical flow, and mix-design information, augmented with a time-difference input $\Delta_t$, to predict the time-dependent rheological state $C=[\delta_{\Delta_t},\tau_{0,\Delta_t},\mu_{\Delta_t}]$. Key contributions include showing time-dependent predictions are feasible, demonstrating that depth and motion information combined with mix design improves accuracy, and illustrating continuous property prediction over the fresh concrete age with potential for real-time adjustments in production. The findings have practical impact for reducing waste and emissions by enabling proactive quality-control actions during concrete production.

Abstract

Increasing the degree of digitisation and automation in the concrete production process can play a crucial role in reducing the CO$_2$ emissions that are associated with the production of concrete. In this paper, a method is presented that makes it possible to predict the properties of fresh concrete during the mixing process based on stereoscopic image sequences of the concretes flow behaviour. A Convolutional Neural Network (CNN) is used for the prediction, which receives the images supported by information on the mix design as input. In addition, the network receives temporal information in the form of the time difference between the time at which the images are taken and the time at which the reference values of the concretes are carried out. With this temporal information, the network implicitly learns the time-dependent behaviour of the concretes properties. The network predicts the slump flow diameter, the yield stress and the plastic viscosity. The time-dependent prediction potentially opens up the pathway to determine the temporal development of the fresh concrete properties already during mixing. This provides a huge advantage for the concrete industry. As a result, countermeasures can be taken in a timely manner. It is shown that an approach based on depth and optical flow images, supported by information of the mix design, achieves the best results.

Figures (3)

• Figure 1: CNN architecture of developed method.
• Figure 2: Experimental set up for generating the data set.
• Figure 3: Three examples for the prediction of the time-dependent behaviour of the slump flow diameter.