Description:
OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Integrated Sensing & Cyber, Trusted AI & Autonomy
OBJECTIVE: To address supply chain shortages by providing a fast, reliable, and widely-available capability to identify, appraise, and extract valuable mechanical and electronic components from scrapped or damaged systems, for reuse in functioning systems [1-3].
DESCRIPTION: Mechanical parts recycling, and electronic waste (e-waste) reuse falls into two broad categories. The first is the recovery of valuable materials such as aluminum, steel, gold, rare earths, and lithium. This is a high-volume bulk process where the high-value manufactured components are systematically reduced to raw material [4].
The second broad category is ad-hoc recovery through junkyards and scrap-picking. In this case, experts look through the scrap and select the parts needed—a labor-intensive process that does not scale. The experts have (1) the skills to understand which parts are needed [5], (2) an encyclopedic knowledge of which systems have the needed part and where it is in the system, (3) the ability to assess whether the scrapped part appears to be functional, and (4) the expertise to safely extract the needed part [6].
Today, each of these steps requires substantial knowledge of potential donor systems. Given the plethora of donor systems (cars, trucks, phones, computers, printers) now available, and the broad understanding of available components and means of extraction, the potential utility of harvesting this vast pool of high-value resources is far above what can be done today by human experts [7].
Note: please see DARPA SBIR 23.4 - Release 4 under the DoD STTR 23.4 Annual BAA at https://www.defensesbirsttr.mil/SBIR-STTR/Opportunities/ for DARPA proposal instructions, to include duration and funding information for this topic.
PHASE I: This topic is soliciting Direct to Phase II (DP2) proposals only. In a Deuce Coupe environment, operators equipped with high-end cell phones would be given search lists and then cued to look for the sources of needed components. Based on information from service manuals, shop manuals, disassembly information, and related sources [8], Deuce Coupe-developed software would use image-feature extraction, natural language processing, and knowledge of physical dynamics to identify systems containing the necessary components [9]. When a candidate donor system is identified, the operator is then cued as to where to find the material within the system [10, 11].
Feasibility requirements firms must meet to be considered for a Phase II award:
• Ability to create the models and structures needed to identify embedded material
• Capability to capture information from sensors to feed the inventory of material
Success criteria for Phase I: Identification of the components needed. In Phase I, the identification will not require a pass/fail for the component [12].
PHASE II: During Phase II, Deuce Coupe will use the sensors on the phone to evaluate the state of the identified components or sub-assemblies [3, 13]. A highly-skilled mechanic or technician can examine the appearance, color, and shape of parts and subsystems and then rapidly assess the part’s condition and suitability for reuse [2, 14].
Phase II Milestones (Base):
• Month 4: Demonstration of an automated, functioning workflow to take an operator from parts ingestion though populating a s design system component library
• Month 7: Capability to ingest and identify junked systems (e.g. car, truck) and provide sufficient metadata to be able to access the parts database systems
• Month 10: Capability to provide information on the available parts from the junked systems based on sensor input and synthesis of the metadata on the system (e.g. shop manual)
Phase II Milestones (Option):
• Month 5: Ability to assess the utility of a part based on sensor data and evaluate its capacity for reuse
• Month 6: Capability to advise on preferential reuse of parts based on assessed utility of the part and information in available metadata
Success criteria for Phase II: the components are to be identified with a reliability indicator that is accurate 80% of the time for P(working) and 90% of the time for P(failure).
PHASE III DUAL USE APPLICATIONS: Scale up to provide efficient and local resupply, measuring the ability to keep a greater quantity of systems in the field for longer periods of time, while simultaneously increasing confidence levels for systems’ operational capabilities. Expand the range of sourcing possibilities for parts and subsystems, thus allowing otherwise-incapacitated systems to be made available for operation.
REFERENCES:
1. J. Aitken and A. Murray, "Crash repair in the UK: reusing salvaged parts in car repair centres," International Journal of Logistics: Research and Applications, vol. 13, no. 5, pp. 359-372, 2010.
2. O. Akinade et al., "Design for deconstruction using a circular economy approach: Barriers and strategies for improvement," Production Planning & Control, vol. 31, no. 10, pp. 829-840, 2020.
3. A. A. Dubey and J. Adhikari, "Design and development of smart junkyard system based on machine learning," International Research Journal of Modernization in Engineering Technology and Science, vol. 4, no. 6, 2022.
4. S. S. Sawyer-Beaulieu, J. A. Stagner, and E. K. Tam, "Sustainability issues affecting the successful management and recycling of end-of-life vehicles in Canada and the United States," in Environmental issues in automotive industry: Springer, 2014, pp. 223-245.
5. A. K. Parlikad and D. McFarlane, "Quantifying the impact of AIDC technologies for vehicle component recovery," Computers & Industrial Engineering, vol. 59, no. 2, pp. 296-307, 2010.
6. P. Thongkaow, T. Prueksasit, and W. Siriwong, "Quantification and characterization of recovered materials in the cycle of the informal household electronic waste dismantling in Buriram province, Thailand: A challenge towards sustainable management and circular economy," Waste Management & Research, vol. 40, no. 12, pp. 1766-1776, 2022.
7. T. A. Kurniawan et al., "Transformation of solid waste management in China: moving towards sustainability through digitalization-based circular economy," Sustainability, vol. 14, no. 4, p. 2374, 2022.
8. D. Page, A. Koschan, and M. Abidi, "Methodologies and techniques for reverse engineering–the potential for automation with 3-d laser scanners," in Reverse Engineering: Springer, 2008, pp. 11-32.
9. M. Ghoreishi and A. Happonen, "Key enablers for deploying artificial intelligence for circular economy embracing sustainable product design: Three case studies," in AIP conference proceedings, 2020, vol. 2233, no. 1: AIP Publishing LLC, p. 050008.
10. P. Haribabu, S. R. Kassa, J. Nagaraju, R. Karthik, N. Shirisha, and M. Anila, "Implementation of an smart waste management system using IoT," in 2017 International Conference on Intelligent Sustainable Systems (ICISS), 2017: IEEE, pp. 1155-1156.
11. S. Keivanpour, D. Ait Kadi, and C. Mascle, "End-of-life aircraft treatment in the context of sustainable development, lean management, and global business," International Journal of Sustainable Transportation, vol. 11, no. 5, pp. 357-380, 2017.
12. C. A. Zimring, "The complex environmental legacy of the automobile shredder," Technology and culture, vol. 52, no. 3, pp. 523-547, 2011.
13. E. Williams et al., "Towards the development of junkyard hacks: networked robotics applications," in 31st Florida Conference on Recent Advances in Robotics, 2018.
14. F. Elghaish, S. T. Matarneh, D. J. Edwards, F. P. Rahimian, H. El-Gohary, and O. Ejohwomu, "Applications of Industry 4.0 digital technologies towards a construction circular economy: gap analysis and conceptual framework," Construction Innovation, no. ahead-of-print, 2022.
KEYWORDS: Supply Chain, Sustainability, Resilience, Machine Reasoning, Automatic decomposition of system-of-systems, Automatic assessment of system wear, Part reuse, Machine vision, Mobile applications
