PortiK: A computer vision based solution for real-time automatic solid waste characterization - Application to an aluminium stream.

In Material Recovery Facilities (MRFs), recyclable municipal solid waste is turned into a precious commodity. However, effective recycling relies on effective waste sorting, which is still a challenge to sustainable development of our society. To help the operations improve and optimise their process, this paper describes PortiK, a solution for automatic waste analysis. Based on image analysis and object recognition, it allows for continuous, real-time, non-intrusive measurements of mass composition of waste streams. The end-to-end solution is detailed with all the steps necessary for the system to operate, from hardware specifications and data collection to supervisory information obtained by deep learning and statistical analysis. The overall system was tested and validated in an operational environment in a material recovery facility. PortiK monitored an aluminium can stream to estimate its purity. Aluminium cans were detected with 91.2% precision and 90.3% recall, respectively, resulting in an underestimation of the number of cans by less than 1%. Regarding contaminants (i.e. other types of waste), precision and recall were 80.2% and 78.4%, respectively, giving an 2.2% underestimation. Based on five sample analyses where pieces of waste were counted and weighed per batch, the detection results were used to estimate purity and its confidence level. The estimation error was calculated to be within ±7% after 5 minutes of monitoring and ±5% after 8 hours. These results have demonstrated the feasibility and the relevance of the proposed solution for online quality control of aluminium can stream.

Better understanding of water quality evolution in water distribution networks using data clustering.

The complexity of water distribution networks raises challenges in managing, monitoring and understanding their behavior. This article proposes a novel methodology applying data clustering to the results of hydraulic simulation to define quality zones, i.e. zones with the same dynamic water origin. The methodology is presented on an existing Water Distribution Network; a large dataset of conductivity measurements measured by 32 probes validates the definition of the quality zones. The results show how quality zones help better understanding the network operation and how they can be used to analyze water quality events. Moreover, a statistical comparison with 158,230 conductivity measurements validates the definition of the quality zones.