OverviewThe aim of this research is on improving&nbsp;of&nbsp;automotive RSC in the context of sustainable development by applying AI techniques in facilitating efficient logistics and information flow of automotive RSC under uncertainty.&nbsp;The main hypothesis is that the proposed prediction model, automotive reverse logistics network (RLN)&nbsp;and information and&nbsp;service&nbsp;system&nbsp;(ISS)&nbsp;could support decision-making and recycling management for automotive industry and provide a reference for automotive&nbsp;remanufacturing industry.MotivationThe upgrading speed of automobile products is accelerating, which leads to the increase of scrapped automobiles and parts of used automobiles.&nbsp;In urban and rural areas, a large number of used automobiles are accumulated, which exceeds the carrying capacity of the environment, causing problems such as energy shortage and environmental pollution.&nbsp;Recycling end-of-life vehicles from consumers effectively could save a large quantity of renewable resources for automobile enterprise. Due to the uncertainty of recovery quantities and the lack of transparency of information, the operation efficiency of automobile RLN is low at present. Reverse logistics and information flow supported by AI can optimize the whole automative RSC, thus improving the utilization rate of enterprise resources, reducing costs and solving the problem of low operational efficiency.Intellectual MeritThis study aims to optimize automotive RSC by improving automotive logistics flow and information flow. The purpose of this research is to establish a multi-objective model of automobile RLN under uncertainty by using AI technology, which can improve the efficiency of automotive logistics flow. Also, the aim of this research is to establish an automobile RSC based on blockchain framework and simulation model, which can effectively improve the transparency and efficiency of information flow.Hence, in order to address these challenges in this research I will answer the following questions and prove the hypothesis:Primary Research Question&nbsp;- What is method that could realize efficient logistics and information flow of automotive RSC under uncertainty?Research Hypothesis&nbsp;- The efficiency of logistics and information flow in automotive RSC can be improved by using AI prediction, combined AI algorithm and blockchain technology in design&nbsp;stage.Question 1&nbsp;- What is the prediction method that facilitates prediction accuracy under uncertainty?Hypothesis 1&nbsp;- With the combined AI-based prediction model, more accurate prediction results of recovery quantity of end-of-life vehicles can be obtained with less historical data.Question 2&nbsp;- What is the method that solves multi-objective model of automotive RLN&nbsp;in a limited time?Hypothesis 2&nbsp;- I hypothesis&nbsp;that building a multi-objective model enables the automobile RLN&nbsp;to effectively save costs, reduce the environmental pollution caused by automobile waste, improve customer satisfaction and utilization rate (if possible). I hypothesis&nbsp;that developing an algorithm based on AI could solve proposed complex multi-objective model of automobile RLN&nbsp;optimization in a limited time.Question 3&nbsp;-&nbsp;What is the method that can enhance information transparency and traceability of automotive RSC?Hypothesis 3&nbsp;- I hypothesis that a blockchain-based ISS&nbsp;is constructed for automotive RSC. The&nbsp;ISS&nbsp;is&nbsp;designed by combining RFID, Digital Twin and blockchain technology to realize transparency and traceability.

Optimization of Automotive Reverse Supply Chain Based on Ai Techniques

Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2021/volume/85369

ASME 2021 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.