A Domestic Trash Detection Model Based on Improved YOLOX.

Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industrial applications. This paper proposes an i-YOLOX model for domestic trash detection based on deep learning algorithms. First, a large number of real-life trash images are collected into a new trash image dataset. Second, the lightweight operator involution is incorporated into the feature extraction structure of the algorithm, which allows the feature extraction layer to establish long-distance feature relationships and adaptively extract channel features. In addition, the ability of the model to distinguish similar trash features is strengthened by adding the convolutional block attention module (CBAM) to the enhanced feature extraction network. Finally, the design of the involution residual head structure in the detection head reduces the gradient disappearance and accelerates the convergence of the model loss values allowing the model to perform better classification and regression of the acquired feature layers. In this study, YOLOX-S is chosen as the baseline for each enhancement experiment. The experimental results show that compared with the baseline algorithm, the mean average precision (mAP) of i-YOLOX is improved by 1.47%, the number of parameters is reduced by 23.3%, and the FPS is improved by 40.4%. In practical applications, this improved model achieves accurate recognition of trash in natural scenes, which further validates the generalization performance of i-YOLOX and provides a reference for future domestic trash detection research.

Synchronization of Shop-Floor Logistics and Manufacturing Under IIoT and Digital Twin-Enabled Graduation Intelligent Manufacturing System.

Logistics interfaces with manufacturing throughout the entire production process need synchronous operations. For achieving integrated organization and operations between manufacturing and logistics, this article introduces the concept of shop-floor logistics and manufacturing synchronization with four principles, including: 1) synchronization-oriented manufacturing system; 2) synchronized information sharing; 3) synchronized decision making; and 4) synchronized operations. The marriage of the principles rendered the development of an overall framework of the Industrial Internet of Things (IIoT) and digital twin-enabled graduation intelligent manufacturing system (GiMS). A mixed-integer programming-based synchronization mechanism is proposed under GiMS. To meet the requirement of fast decision making in real-life shop-floor logistics and manufacturing synchronization problems, an equivalent constraint programming model is developed and tested. The observation and analysis of the case company show the advantage of the proposed concept and approach with the best performance regarding key performance indicators. The concept of synchronization provides an insight for understanding the interaction of logistics and manufacturing at the operational level. This article potentially enables manufacturers to reevaluate and develop their manufacturing planning and control strategies in the IIoT and digital twin-based manufacturing environment.

Internet of Everything and Digital Twin enabled Service Platform for Cold Chain Logistics.

The proliferation of the e-commerce market has posed challenges to staff safety, product quality, and operational efficiency, especially for cold chain logistics (CCL). Recently, the logistics of vaccine supply under the worldwide COVID-19 pandemic rearouses public attention and calls for innovative solutions to tackle the challenges remaining in CCL. Accordingly, this study proposes a cyber-physical platform framework applying the Internet of Everything (IoE) and Digital Twin (DT) technologies to promote information integration and provide smart services for different stakeholders in the CCL. In the platform, reams of data are generated, gathered, and leveraged to interconnect and digitalize physical things, people, and processes in cyberspace, paving the way for digital servitization. Deep learning techniques are used for accident identification and indoor localization based on Bluetooth Low Energy (BLE) to actualize real-time staff safety supervision in the cold warehouse. Both algorithms are designed to take advantage of the IoE infrastructure to achieve online self-adapting in response to surrounding evolutions. Besides, with the help of mobile and desktop applications, paperless operation for shipment, remote temperature and humidity (T&H) monitoring, anomaly detection and warning, and customer interaction are enabled. Thus, information traceability and visibility are highly fortified in this way. Finally, a real-life case study is conducted in a pharmaceutical distribution center to demonstrate the feasibility and practicality of the proposed platform and methods. The dedicated hardware and software are developed and deployed on site. As a result, the effectiveness of staff safety management, operational informatization, product quality assurance, and stakeholder loyalty maintenance shows a noticeable improvement. The insights and lessons harvested in this study may spark new ideas for researchers and inspire practitioners to meet similar needs in the industry.

Building demolition waste management through smart BIM: A case study in Hong Kong.

Hong Kong's construction industry, known for its massive building infrastructure, produces an enormous amount of waste every year, the vast majority of which is disposed for landfills. Therefore, some effective operational measures and waste management policies have been implemented. However, enormous waste remains a concern for stakeholders and exert pressure on the limited capacity of Hong Kong's landfills. Though previous research discusses Building Information Modelling (BIM) application for construction waste management enhancement, the BIM model has not been widely implemented for building demolition with waste management. Hence, as a response to the aforementioned shortcomings, this paper develops a conceptual framework that allows collecting, maintaining, and analyzing comprehensive information through Smart BIM that uses advanced technologies such as Internet of Things (IoT) and capable of reacting to user activities such as waste quantitative assessment, demolition process planning, optimal disposal route selection, and waste management strategy are executed. The advantages of the proposed framework are shown in a case study benefit-cost analysis based on three planned reuse and recycling-rate scenarios that explain on- and off-site recycling methods. The results show that the proposed framework will pave the way for generating sustainable waste disposal practices by providing technical and decision-making support functionalities to engineers and planners in the construction industry.

A supply chain disruption recovery strategy considering product change under COVID-19.

A recent global outbreak of Corona Virus Disease 2019 (COVID-19) has led to massive supply chain disruption, resulting in difficulties for manufacturers on recovering their supply chains in a short term. This paper presents a supply chain disruption recovery strategy with the motivation of changing the original product type to cope with that. In order to maximize the total profit from product changes, a mixed integer linear programming (MILP) model is developed with combining emergency procurement on the supply side and product changes by the manufacturer as well as backorder price compensation on the demand side. The model uses a heuristic algorithm based on ILOG CPLEX toolbox. Experimental results show that the proposed disruption recovery strategy can effectively reduce the profit loss of manufacturer due to late delivery and order cancellation. It is observed that the impact of supply chain disruptions is reduced. The proposed model can offer a potentially useful tool to help the manufacturers decide on the optimal recovery strategy whenever the supply chain system experiences a sudden massive disruption.

Spark Analysis Based on the CNN-GRU Model for WEDM Process.

Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in manufacturing industry, is a nontraditional machining method using discharge energy which is transformed into thermal energy to efficiently remove materials. A great amount of research has been conducted based on pulse characteristics. However, the spark image-based approach has little research reported. This paper proposes a discharge spark image-based approach. A model is introduced to predict the discharge status using spark image features through a synchronous high-speed image and waveform acquisition system. First, the relationship between the spark image features (e.g., area, energy, energy density, distribution, etc.) and discharge status is explored by a set of experiments). Traditional methods have claimed that pulse waveform of "short" status is related to the status of non-machining while through our research, it is concluded that this is not always true by conducting experiments based on the spark images. Second, a deep learning model based on Convolution neural network (CNN) and Gated recurrent unit (GRU) is proposed to predict the discharge status. A time series of spark image features extracted by CNN form a 3D feature space is used to predict the discharge status through GRU. Moreover, a quantitative labeling method of machining state is proposed to improve the stability of the model. Due the effective features and the quantitative labeling method, the proposed approach achieves better predict result comparing with the single GRU model.

Development of radio-frequency identification (RFID) sensors suitable for smart-monitoring applications in sewer systems.

Sanitary and stormwater sewers are buried assets that play important roles in the prevention of diseases and the reduction of health risks for our societies. Due to their hidden nature, these assets are not frequently assessed and maintained to optimal conditions. The lack of maintenance can cause sewer blockages and overflows that result in the release of pathogens into the environment. For cities, monitoring sewer conditions on a large-scale can be costly, time-consuming, and labor-intensive if using current low-throughput technologies, such as dye testing or closed-circuit television. Alternatively, smart sensor systems can provide low-cost, high-throughput, and automatic data-driven features for real-time monitoring applications. In this study, we developed ultrahigh-frequency radio-frequency identification (UHF RFID)-based sensors that are flushable and suitable for sanitary and stormwater pipes quick surveys. 3D printed RFID sensors were designed to float at the water-air interface and minimize the water interference to RF signal communications. The optimal detection range was also determined to support the design and installation of the reader in various utility holes. Field trials demonstrated that the UHF RFID system is a low-cost, high-throughput, and robust solution for monitoring blockage, illicit-connection, and water flow in sewer networks.