4.5 Article

A systematic selective disassembly approach for Waste Electrical and Electronic Equipment with case study on liquid crystal display televisions

Publisher

SAGE PUBLICATIONS LTD
DOI: 10.1177/0954405415575476

Keywords

Selective disassembly; the Waste Electrical and Electronic Equipment Directive; the Restriction of Hazardous Substances Directive; liquid crystal display televisions

Funding

  1. Marie Curie International Research Staff Exchange Scheme Fellowship within the 7th European Community Framework Programme [294931]

Ask authors/readers for more resources

Waste Electrical and Electronic Equipment is one of the major waste streams in terms of quantity and toxicity, and a critical step in Waste Electrical and Electronic Equipment end-of-life processing is through disassembly. Compared with full disassembly, which is a sub-optimal solution due to its high operational cost, selective disassembly is more economic and practical as only selected parts with recycling potential are considered. In this article, a systematic selective disassembly approach for handling Waste Electrical and Electronic Equipment with a maximum disassembly profit in accordance to the Waste Electrical and Electronic Equipment and Restriction of Hazardous Substances Directives has been developed. First, a space interference matrix is generated based on the interference relationship between individual components in the three-dimensional computer-aided design model of Waste Electrical and Electronic Equipment. A matrix analysis algorithm is then applied to obtain all the feasible disassembly sequences through the obtained space interference matrix in a three-dimensional environment. Second, an evaluation and decision-making method is developed to find out an optimal selective disassembly sequence from the obtained feasible disassembly sequences. The evaluation takes into account the disassembly profit and requirements of the Waste Electrical and Electronic Equipment and Restriction of Hazardous Substances Directives, which regulate on recycling rates of different types of products and removal requirements of (1) hazardous, (2) heavy and (3) high-value components. Thus, an optimal solution is a selective disassembly sequence that can achieve the maximum disassembly profit, while complying with the Waste Electrical and Electronic Equipment and Restriction of Hazardous Substances restrictions based on a brute-force search method. Finally, an industrial case on Changhong liquid crystal display televisions of the type LC24F4 is used to demonstrate the effectiveness of the developed approach.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Computer Science, Interdisciplinary Applications

A multi-granularity NC program optimization approach for energy efficient machining

X. X. Li, W. D. Li, F. Z. He

ADVANCES IN ENGINEERING SOFTWARE (2018)

Article Green & Sustainable Science & Technology

Big Data enabled Intelligent Immune System for energy efficient manufacturing management

S. Wang, Y. C. Liang, W. D. Li, X. T. Cai

JOURNAL OF CLEANER PRODUCTION (2018)

Article Green & Sustainable Science & Technology

Cyber Physical System and Big Data enabled energy efficient machining optimisation

Y. C. Liang, X. Lu, W. D. Li, S. Wang

JOURNAL OF CLEANER PRODUCTION (2018)

Article Computer Science, Artificial Intelligence

A cloud-terminal-based cyber-physical system architecture for energy efficient machining process optimization

X. X. Li, F. Z. He, W. D. Li

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING (2019)

Article Computer Science, Interdisciplinary Applications

Supervision controller for real-time surface quality assurance in CNC machining using artificial intelligence

L. C. Moreira, W. D. Li, X. Lu, M. E. Fitzpatrick

COMPUTERS & INDUSTRIAL ENGINEERING (2019)

Article Engineering, Industrial

Fog computing and convolutional neural network enabled prognosis for machining process optimization

Y. C. Liang, W. D. Li, X. Lu, S. Wang

JOURNAL OF MANUFACTURING SYSTEMS (2019)

Article Computer Science, Interdisciplinary Applications

Energy-Efficient machining process analysis and optimisation based on BS EN24T alloy steel as case studies

L. C. Moreira, W. D. Li, X. Lu, M. E. Fitzpatrick

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2019)

Article Computer Science, Artificial Intelligence

An improved approach of task-parameterized learning from demonstrations for cobots in dynamic manufacturing

Shirine El Zaatari, Yuqi Wang, Yudie Hu, Weidong Li

Summary: The improved TP-LfD approach presented in this paper enhances the performance of collaborative robots in industrial applications by autonomously choosing frames from demonstrations, utilizing statistical and reinforcement learning algorithms to optimize critical task parameters, and integrating a B-Spline cut-in algorithm to improve path reproducing in dynamic manufacturing situations. This approach enables teaching a cobot to behave in a more intuitive and intelligent means for dynamic manufacturing applications.

JOURNAL OF INTELLIGENT MANUFACTURING (2022)

Article Computer Science, Artificial Intelligence

Adaptive obstacle avoidance in path planning of collaborative robots for dynamic manufacturing

Yudie Hu, Yuqi Wang, Kaixiong Hu, Weidong Li

Summary: This paper proposes an improved GMM/GMR-based approach for collaborative robot path planning in dynamic manufacturing, which achieves adaptive obstacle avoidance through adaptive parameter modification and the introduction of the fruit fly optimization algorithm. The effectiveness and efficiency of the approach are validated through case studies.

JOURNAL OF INTELLIGENT MANUFACTURING (2023)

Article Engineering, Manufacturing

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Weidong Li, Xiaoyang Zhang, Sheng Wang, Xin Lu, Zhiwen Huang

Summary: To optimize the cost of cutting tools, a novel online system based on deep learning algorithms distributed over an edge-cloud computing architecture is proposed to predict tool wear conditions and remaining useful lives accurately and efficiently. The system includes a lightweight CNN-RF model on the edge device for assessing tool wear conditions and a CNN-LSTM model on the cloud for predicting the RUL of the cutting tool. Signal compression is used to minimize the transferred signal volumes and improve signal security. Experimental results show high prediction accuracies for tool wear and RUL, as well as a significant reduction in transferred signal volume. The system demonstrates great potential for real-world cutting tool optimization.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE (2023)

Article Computer Science, Artificial Intelligence

Safe human-robot collaboration for industrial settings: a survey

Weidong Li, Yudie Hu, Yong Zhou, Duc Truong Pham

Summary: In this survey paper, the importance of human-robot collaboration (HRC) in the industry is highlighted. The paper provides an update on standards and implementation approaches for HRC safety, covering industrial robots, collaborative robots, and HRC. Various approaches to HRC safety are surveyed from the perspectives of pre-collision and post-collision, including sensing, prediction, learning, planning/replanning, and compliance control. The paper also discusses challenging issues and future prospects for HRC safety, providing recommendations for stakeholders in designing HRC-enabled industrial systems.

JOURNAL OF INTELLIGENT MANUFACTURING (2023)

Article Engineering, Industrial

Prediction of melt pool width and layer height for Laser Directed Energy Deposition enabled by physics-driven temporal convolutional network

Yanghui Wang, Kaixiong Hu, Weidong Li, Lihui Wang

Summary: Laser Directed Energy Deposition (L-DED) is a significant metal additive manufacturing technology that has been gradually adopted by high-value manufacturing industries due to its high flexibility. This research presents a novel physics-driven temporal convolutional network (TCN) approach to accurately predict the melt pool size for high-quality L-DED processes.

JOURNAL OF MANUFACTURING SYSTEMS (2023)

Article Engineering, Electrical & Electronic

Tool Wear Prediction Based on Multi-Information Fusion and Genetic Algorithm-Optimized Gaussian Process Regression in Milling

Zhiwen Huang, Jiajie Shao, Weicheng Guo, Weidong Li, Jianmin Zhu, Qichao He, Dianjun Fang

Summary: Tool wear condition monitoring is crucial in intelligent manufacturing systems. This study proposes a tool wear prediction method based on multi-information fusion and genetic algorithm optimized Gaussian process regression. Experimental results show that the proposed method can effectively lower prediction error and uncertainty of flank wear width in milling.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2023)

Article Engineering, Industrial

Thermal error prediction for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture

Y. C. Liang, W. D. Li, P. Lou, J. M. Hu

Summary: This paper presents a new system for thermal error prediction on heavy-duty CNC machines using LSTM networks and a fog-cloud architecture. By combining data-driven modeling with physics-based modeling, optimizing the number and location of thermal sensors, and reducing excessive data, the system improves prediction accuracy and computational efficiency. Practical case studies show that the system successfully reduces data transmission volume and improves machining accuracy.

JOURNAL OF MANUFACTURING SYSTEMS (2022)

No Data Available