Even though, an innovative inorganic family of geopolymer concretes are eye-catching potential building materials, it is quite essential to comprehend the fire and thermal resistance of these structural materials at a very high temperature and also when experiencing fire with a view to make certain not only the safety and security of lives and properties but also to establish them as more sustainable edifice materials for future. The experimental and field observations of degree of cracking, spalling and loss of strength within the geopolymer concretes subsequent to exposure at elevated temperature and incidences of occurrences of disastrous fires extend an indication of their resistance against such severely catastrophic conditions. The impact of heat and fire on mechanical attributes viz., mechanical-compressive strength, flexural behavior, elastic modulus; durability—thermal shrinkage; chemical stability; the impact of thermal creep on compressive strength; and microstructure properties—XRD, FTIR, NMR, SEM as well as physico-chemical modifications of geopolymer composites subsequent to their exposures at elevated temperatures is reviewed in depth. The present scientific state-of-the-art review manuscript aimed to assess the fire and thermal resistance of geopolymer concrete along with its thermo-chemistry at a towering temperature in order to introduce this novel, most modern, user and eco-benign construction materials as potentially promising, sustainable, durable, thermal and fire-resistant building materials promoting their optimal and apposite applications for construction and infrastructure industries.
Central to the development of a successful waste sorting robot lies an accurate and fast object detection system. This study assesses the performance of the most representative deep-learning models for the real-time localisation and classification of Construction and Demolition Waste (CDW). For the investigation, both single-stage (SSD, YOLO) and two-stage (Faster-RCNN) detector architectures coupled with various backbone feature extractors (ResNet, MobileNetV2, efficientDet) were considered. A total of 18 models of variable depth were trained and tested on the first openly accessible CDW dataset developed by the authors of this study. This dataset consists of images of 6600 samples of CDW belonging to three object categories: brick, concrete, and tile. For an in-depth examination of the performance of the developed models under working conditions, two testing datasets containing normally and heavily stacked and adhered samples of CDW were developed. A comprehensive comparison between the different models yields that the latest version of the YOLO series (YoloV7) attains the best accuracy (mAP50:95 ≈ 70%) at the highest inference speed (<30 ms), while also exhibiting enough precision to deal with severely stacked and adhered samples of CDW. Additionally, it was observed that despite the rising popularity of single-stage detectors, apart from YoloV7, Faster-RCNN models remain the most robust in terms of exhibiting the least mAP fluctuations over the testing datasets considered.
1 September 2019 in Construction and Building Materials