Intelligent Automation for Sustainable End-of- Life Management

Automation and robotics have been widely applied in manufacturing processes, to increase production efficiency, improve the cost-effectiveness and overcome challenges in extreme working environments. However, to achieve product lifecycle sustainability, the endof- life stage should also be taken into consideration. Due to the large variety of product types, uncertainties and complexities in product conditions, currently, the majority of the recycling activities (e.g. soring, disassembly) are undertaken manually [1]. Reducing the level of human interaction and increasing the level of machine intelligence play a significant role for achieving sustainability of waste management, in ecological, economic and social aspects. Apart from robotics used in remanufacturing and recycling, technological advances have demonstrated paced progression that supports the development of recycling sector [2]. Therefore, there is a need to understand and investigate the benefits of industrial automation and intelligence applied in waste management.

Emerging technologies has greatly enabled the development of recycling, such as Internet of Things (IoT), cyber physical systems (CPS), Augmented Reality (AR), Virtual Reality (VR), cloud computing, collaboration robot (Cobot), Industry 4.0 and machine learning, etc. For example, the IoT concept was integrated with image processing and local cell technologies in an automated system to measure the real-time waste generation in food industry [3] or used for collecting and soring obsolete products effectively [4]. The information carrier, i.e. RFID or QR codes were capable of storing product information for tracking, production scheduling, remanufacturing and recycling [5]. The integration of IoT, Geographic Information Systems (GIS), and graph theory-based optimisation techniques were used to track and initiate the trash cleaning process [2]. The AR technology can be used to convey disassembly sequence information to the operator [6], or working with a Leap Motion Controller device, seethrough glasses to evaluate and generate optimal disassembly strategy [7]. Furthermore, machine learning and artificial intelligence methods were used in sorting the waste materials in a highly feasible and time efficient way, including genetic algorithms and convolutional neural network classifier [2,8,9]. Based on data mining technique and observation record a repository was develop to characterise the disassembly time of joining elements, which was valuable for the evaluation of disassemblability [10]. It is noted that the knowledge derived from information technology and intelligent algorithms helped enhance the adaptability and robustness of the recycling system.

The concept of disassembly automation was first introduced with the set-up of a semi-automated disassembly cells for waste electronic products recycling [11]. It was designed to mitigate human interference, increase operation quality and efficiency and reduce cost. During the following decades, as research on robotic disassembly continues, an increasing number of studies developed automated systems for various products. For instance, printed circuit boards from the waste electronic components were extracted automatically through image processing, robotic handling and laser processing modules [12]. The concepts for semi-automated dismantling for LCD TVs was presented for higher productivity and flexibility [13]. After that, an evaluation and decision-making tool using matrix analysis algorism was used to identify the optimal disassembly sequence for LCD TVs [14]. With regards to the end-oflife electric vehicles (EV) management, a robotic disassembly cell was designed to extract valuable electronic components for value recovery [15]. For EV batteries, a disassembly workstation was developed where a robot and an operator can work collaboratively [16]. While the robot was assigned to perform simple and repetitive tasks, the operator was responsible for complex tasks. In order to further increase the feasibility of disassembly automation, research has focused on robotics, disassembly tooling and intelligent system design. Based on robotic disassembly cells, sensors were installed to monitor the process, cloud-based recycling process was developed for EV batteries recycling [17]. A multi-head tool was also developed for robotic disassembly of LCD screens, which was capable of sawing, grinding and removing screws [18]. Furthermore, advances in industrial automation technique enabled that multiple robots could work simultaneously in a disassembly line [19].

To cope with the challenging of large amount of waste, intelligent and automated techniques have been used in end-oflife management systems, closing the gap between the need for smarter recycling and technological capabilities required to achieve it. However, it is noted that the degree of automation in recycling and disassembly is not as high as it is applied in manufacturing processes (i.e. assembly, packaging and logistics, etc.), only a number of pilot or laboratory-scale projects are presented [20]. Based on the findings, current recycling activities still face the challenging caused by unpredictable conditions and significant variation in designs and materials used. Future recycling would require innovative techniques to disclose or reveal information of product design, share knowledge between manufacturers and waste management companies [21]. In addition, there is high potential to investigate and enhance the capability of humanrobot collaboration [22], communication between robots and recycling tools, achieve higher productivity and efficiency by means of advanced algorithms [23], and evaluate the sustainability of recycling approaches comprehensively from three dimensions - economic, social and environmental [24].

This work was supported by the Shanghai Sailing Program (19YF1401600) and the Fundamental Research Funds for the Central Universities (No. 2232019D3-32).

1. Chang MM, Ong SK, Nee AY (2017) Approaches and challenges in product disassembly planning for sustainability. Procedia CIRP 60: 506-511.
2. Gupta PK, Shree V, Hiremath L, Rajendran S (2019) The use of modern technology in smart waste management and recycling: Artificial intelligence and machine learning. In: Kumar R, Wiil U (Eds) Recent advances in computational intelligence Studies in Computational Intelligence. Springer, Berlin, Germany.
3. Jagtap S, Bhatt C, Thik J, Rahimifard S (2019) Monitoring potato waste in food manufacturing using image processing and internet of things approach. Sustainability 11(11): 1-12.
4. Folianto F, Low YS, Yeow WL (2015) Smartbin: Smart waste management system. Proceedings of the IEEE 10^th international conference on intelligent sensors, Sensor Networks and Information Processing, Singapore.
5. Kerin M, Pham DT (2019) A review of emerging industry 4.0 technologies in remanufacturing. J Cleaner Product 237(10): 117805.
6. Chang MM, Ong SK, Nee AY (2017) AR-guided product disassembly for maintenance and remanufacturing. Procedia CIRP 61: 299-304.
7. Osti F, Ceruti A, Liverani A, Caligiana G (2017) Semi-automatic design for disassembly strategy planning: An augmented reality approach. Procedia Manufacturing 11: 1481-1488.
8. Senthilselvi A, Sellam V, Alahmari SA, Rajeyyagari S (2020) Accuracy enhancement in mobile phone recycling process using machine learning technique and MEPH process. Environmental Technology & Innovation 20: 101137.
9. Zhu B, Sarigecili MI, Roy U (2013) Disassembly information model incorporating dynamic capabilities for disassembly sequence generation. Robotics and Computer-Integrated Manufacturing 29(5): 396-409.
10. Favi C, Marconi M, Mandolini M, Germani M (2020) Big data analysis for the estimation of disassembly time and de-manufacturing activity. Procedia CIRP 90: 617-622.
11. Kepacek B, Kopacek P (1999) Intelligent disassembly of electronic equipment. Annual Reviews in Control 23: 165-170.
12. Noll R, Ambrosch R, Bergmann K, Britten S, Brumm H, et al. (2017) Next generation urban mining - automated disassembly, separation and recovery of valuable materials from electronic equipment: Overview of R&D approaches and first results of the European project ADIR. Next generation urban mining - European project ADIR.
13. Elo K, Sundin E (2014) Process concepts for semi-automatic dismantling of LCD televisions. Procedia CIRP 23: 270-275.
14. Jin G, Li WD, Wang S, Gao SM (2015) A systematic selective disassembly approach for waste electrical and electronic equipment with case study on liquid crystal display televisions. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture 231(13).
15. Li J, Barwood M, Rahimifard S (2017) Robotic disassembly for increased recovery of strategically important materials from electrical vehicles. Robotics and Computer-Integrated Manufacturing 50: 203-212.
16. Wegener K, Chen WH, Dietrich F, Droder K, Kara S (2015) robot assisted disassembly for the recycling of electric vehicle batteries. Procedia CIRP 29: 716-721.
17. Singh M, Janardhan RK (2019) Cloud based disassembly of electric vehicle battery. Procedia Manufacturing 30: 136-142.
18. Wei HC, Gwendolyn F, Sami K, Maurice P (2020) Application of a multi-head tool for robotic disassembly. Procedia CIRP 90: 630-635.
19. Ming H, Liu Q, Pham DT (2019) Multi-robotic disassembly line balancing with uncertain processing time. Procedia CIRP 83: 71-76.
20. Kopacek B (2016) Intelligent disassembly of components from printed circuit boards to enable re-use and more efficient recovery of critical metals. IFAC-Papers Online 49(29): 190-195.
21. Schwarz TE, Rübenbauer W, Rutrecht B, Pomberger R (2018) Forecasting real disassembly time of industrial batteries based on virtual MTM-UAS data. Procedia CIRP 69: 927-931.
22. Ding Y, Xu W, Liu Z, Zhou Z, Pham DT (2019) Robotic task-oriented knowledge graph for human-robot collaboration in disassembly. Procedia CIRP 83: 105-110.
23. Zil ZB, Mete S, Serin F (2019) Robotic disassembly line balancing problem: A mathematical model and ant colony optimization approach. Applied Mathematical Modelling 86: 335-348.
24. Ramirez FJ, Aledo JA, Gamez JA, Pham DT (2020) Economic modelling of robotic disassembly in end-of-life product recovery for remanufacturing. Computers & Industrial Engineering 142: 106339.

© 2020 Li J. This is an open access article distributed under the terms of the Creative Commons Attribution License , which permits unrestricted use, distribution, and build upon your work non-commercially.