An Online Genetic Algorithm for Automated Disassembly Sequence Generation

In this study, we propose an intelligent automated disassembly cell for online (real time) selective disassembly. The cell is composed of an industrial robotic manipulator, a camera, range-sensing and component segmentation visual algorithms. The cell prototype allows for robotic sensory-driven disassembly under uncertainty. An online genetic algorithm model for selective disassembly is also proposed for optimal and near/optimal disassembly sequencing. INTRODUCTION Advanced technology products are regularly rendered technically obsolete within a few years of commercialization due to the rapid pace of technological developments. Thus, electronic products are frequently discarded before their materials degrade. These complex End-of-Life (EOL) products contain a broad spectrum of materials including precious metals such as silver, and valuable materials such as copper. Therefore, efficient recovery of materials in the electronic EOL products is essential for economic reasons. Furthermore, the conceptual lifetime of an electronic product depends primarily on the pace of superseding technological change that makes obsolete the otherwise fully-functioning product. Hence, the discarded product is likely to contain one or more usable components. The economically and environmentally sustainable option is to reuse these components in technically valid products. EOL processing options, e.g., reuse, recycle, and remanufacturing, are effective ways to regain the materials and the components in electronic EOL products. Regardless of the motivation, most EOL processing options necessitate a certain level of disassembly. Disassembly operations are very complex, time-consuming, and expensive. Therefore, limiting the disassembly operations to recyclable materials and reusable components in the EOL product is crucial in order to render electronic waste recovery operations economically viable. Responding to this need, generating disassembly algorithms for selective disassembly [1-2] is the first major research topic presented in this paper. Electronic waste recovery, EOL processing options, and disassembly of electronic products are well documented [316]. However, related literature falls short in providing realistic methods for product recovery. Despite the ever growing research on disassembly of electronic products, the proposed methods generally assume that the part locations are known in the product structure. Furthermore, the majority of these algorithms function under the assumption of a known hierarchical disassembly path, i.e., for a personal computer (PC) disassembly, the front or side cover must be removed to Proceedings of the ASME 2011 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference