Management system for engineering and decoration waste: An exploratory study in Shenzhen.

Rapid urban development and renewal have caused large amounts of engineering and decoration waste to be produced. These wastes pose serious risks to the environment. Disposal and management of this waste have become problematic. A mean of 11.4 × 106 m3 of engineering and decoration waste will be produced each year in Shenzhen between 2018 and 2035. Engineering and decoration waste are currently mainly sent to landfill, but this requires large amounts of land and can cause serious environmental pollution. There are problems including irregular emissions, a disorderly transportation market, and inadequate disposal facilities, so policies for managing engineering and decoration waste need to be established. In this study, a hybrid approach was used to develop a system for managing the whole engineering and decoration waste system (generation, collection & transportation, and disposal). The system was developed after determining waste emission and disposal requirements through site visits, clarifying problems involved in waste collection and transportation through interviews, identifying suitable management practices in an expert seminar, and developing a management system through desktop surveys. It was found that new buildings produce 0.02-0.04 (m3 waste)/(m2 building) and 0.11-0.13 (m3 decoration waste)/(m2 building) and that emission limits are required. Construction enterprises employ private trucks to transport waste, and illegal dumping occurs. Directed collection and transportation is required. Public welfare requires a mechanism for managing engineering and decoration waste with clear responsibilities. Government-authorized construction and operation should be explored and implemented. A propagable engineering and decoration waste management system is proposed with three management modules, generation, collection & transportation, and disposal, to act as a strategy for improving engineering and decoration waste.

An intelligent identification and classification system of decoration waste based on deep learning model.

Efficient sorting and recycling of decoration waste are crucial for the industry's transformation, upgrading, and high-quality development. However, decoration waste can contain toxic materials and has greatly varying compositions. The traditional method of manual sorting for decoration waste is inefficient and poses health risks to sorting workers. It is therefore imperative to develop an accurate and efficient intelligent classification method to address these issues. To meet the demand for intelligent identification and classification of decoration waste, this paper applied the deep learning method You Only Look Once X (YOLOX) to the task and proposed an identification and classification framework of decoration waste (YOLOX-DW framework). The proposed framework was validated and compared using a multi-label image dataset of decoration waste, and a robot automatic sorting system was constructed for practical sorting experiments. The research results show that the proposed framework achieved a mean average precision (mAP) of 99.16 % for different components of decoration waste, with a detection speed of 39.23 FPS. Its classification efficiency on the robot sorting experimental platform reached 95.06 %, indicating a high potential for application and promotion. This provides a strategy for the intelligent detection, identification, and classification of decoration waste.