Karoline Raulf

Current data gaps hinder an efficient sustainability transition of the construction sector. Simultaneously, at the intersection of data science and waste management, much research is being conducted to monitor quality factors of interest for material flows in recycling processes. In the past years, we developed and implemented a prototype sensor-based quality monitoring system to analyze the particle size distribution during processing of construction and demolition waste. In this work, we assess this prototype in terms of 1) contribution to data availability and thus closing the current data gap, and 2) its preliminary social, environmental and economic implications in the context of a circular economy. We find that our system can record data robustly, provide results timely and cover a significantly larger share of material (5.3–5.6 %) compared to the current state-of-the-art (<0.01 %). Additionally, preliminary implications regarding the social, environmental and economic aspects support the potential of our system to positively contribute to the transitioning towards a circular and sustainable construction sector. Nonetheless, further research is needed to solve persisting limitations regarding fine fractions and bulk monitoring and carrying out a holistic LCSA is considered valuable.

In this work, the development and validation of an AI- and sensor-based inline quality monitoring system for the analysis of particle size distributions (PSDs) of comminuted construction and demolition waste (CDW) material flows are described. In this, a custom-developed multitask CNN (CDW-MT-CNN) was developed using manually sieve analyzed particles. This model is able to rapidly and simultaneously predict the particle class and weight, essential for the determination of the PSD. The single particle data are then aggregated per raw image, usually consisting of around 1000 particles for full-scale experiments, to acquire a per-image PSD. The inline mounted RGB line scan sensor records high-resolution images in subsecond frequencies. With an inference time of around 54 ms for a single image, this model would be able to provide a PSD every minute in a full-scale plant. For the purpose of inline monitoring of CDW material flows in a comminution process, such intervals are sufficient according to experts and solve existing gaps regarding the upscaling of laboratory-developed systems. Together with the high predictive performance of the model, especially in terms of classification (82% accuracy), it is shown that this technology has potential for monitoring in full-scale plants, for instance by offering operators new insights to improve operation efficiency. Further research should focus on increasing the precision for weight prediction, for instance by increasing the labeled data set with a larger number of unique particles and on methods to verify the performance of the model on pilot or full-scale plants during live operation.

In this work, the development and validation of an AI- and sensor-based inline quality monitoring system for the analysis of particle size distributions (PSDs) of comminuted construction and demolition waste (CDW) material flows are described. In this, a custom-developed multitask CNN (CDW-MT-CNN) was developed using manually sieve analyzed particles. This model is able to rapidly and simultaneously predict the particle class and weight, essential for the determination of the PSD. The single particle data are then aggregated per raw image, usually consisting of around 1000 particles for full-scale experiments, to acquire a per-image PSD. The inline mounted RGB line scan sensor records high-resolution images in subsecond frequencies. With an inference time of around 54 ms for a single image, this model would be able to provide a PSD every minute in a full-scale plant. For the purpose of inline monitoring of CDW material flows in a comminution process, such intervals are sufficient according to experts and solves existing gaps regarding the upscaling of laboratory-developed systems. Together with the high predictive performance of the model, especially in terms of classification, it is shown that this technology has potential for monitoring in full-scale plants, for instance by offering operators new insights to improve operation efficiency. Further research should focus on increasing the precision for weight prediction, for instance by increasing the labeled data set with a larger number of unique particles and on methods to verify the performance of the model on pilot or full-scale plants during live operation.

To effectively utilise secondary raw materials, pre-concentrates of defined quality are required. Packaging waste streams are treated in waste sorting plants, where different sorting operations are applied. Ballistic separators are frequently used to separate 2D and 3D materials during (pre)conditioning and therefore have a major influence on the overall process performance. Despite their widespread use, until now, few studies have examined how parameter settings affect the performance of ballistic separators. To assess and optimise process performance, we conducted a parameter study on packaging waste using an industrial-scale ballistic separator and near-infrared-based process monitoring. At 22.5 wt% 2D input content, we varied 2D material properties, paddle angle (15°, 17.5°, 20°), rotational speeds ( s ₁ – s ₅ ) and paddle types (45 mm, closed). All parameters showed significant effects on the process performance. In the material stream used, which contained a proportion of fine material, the 45 mm paddles demonstrated higher separation performance compared to the closed paddles. A specific rotational speed must be reached to achieve an effective separation efficiency. Beyond this, a further increase does not lead to measurable improvements. Two optimisation strategies were developed to determine process optima and enable the integration of the generated results into operational practice. Therefore, the results contribute to the optimisation and potential automation of ballistic separators and the overall improvement of packaging waste sorting plants.

Automated quality assurance is gaining popularity across application areas; however, automatization for monitoring and control of product quality in waste processing is still in its infancy. At the same time, research on this topic is scattered, limiting efficient implementation of already developed strategies and technologies across research and application areas. To this end, the current work describes a scoping review conducted to systematically map available sensor-based quality assurance technologies and research based on the PRISMA-ScR framework. Additionally, the current state of research and potential automatization strategies are described in the context of construction and demolition waste processing. The results show 31 different sensor types extracted from a collection of 364 works, which have varied popularity depending on the application. However, visual imaging and spectroscopy sensors in particular seem to be popular overall. Only five works describing quality control system implementation were found, of which three describe varying manufacturing applications. Most works found describe proof-of-concept quality prediction systems on a laboratory scale. Compared to other application areas, works regarding construction and demolition waste processing indicate that the area seems to be especially behind in terms of implementing visual imaging at higher technology readiness levels. Moreover, given the importance of reliable and detailed data on material quality to transform the construction sector into a sustainable one, future research on quality monitoring and control systems could therefore focus on the implementation on higher technology readiness levels and the inclusion of detailed descriptions on how these systems have been verified.