On-line predictive model for disassembly process planning adaptation

doi:10.1016/S0736-5845(99)00019-8

Robotics and Computer-Integrated Manufacturing

Volume 15, Issue 3, June 1999, Pages 211-220

https://doi.org/10.1016/S0736-5845(99)00019-8 Get rights and content

Abstract

This paper presents an on-line predictive model for disassembly process adaptation. The prediction enables a planner to adapt the process plan based on the condition of the product (e.g., degree of rustiness, deformation) during process execution. This model tries to correlate the product physical condition, used as an explanatory variable, with the component value and disassembly cost, the response variables. The core of the approach is based on an inference engine that used a kernel regression. A simple methodology for integrating the predictive planner in a disassembly system is presented and exemplified by a case study of the disassembly of a ratio.

References (0)

Cited by (39)

Energy evaluation method and its optimization models for process planning with stochastic characteristics: A case study in disassembly decision-making
2012, Computers and Industrial Engineering
Citation Excerpt :
Some related studies can be summarized as follows. Salomonski and Zussman (1999) present an on-line predictive model for a disassembly process. The prediction enable a planner to adapt the process plan based on the condition of the product (e.g., degree of rustiness, deformation) during process execution.
Disassembly is not only a premise of products recycling, but also an important link of products remanufacturing. However, used products suffer from the influence of a variety of uncertainties. The randomness of disassembly process is a significant feature. In this paper, a disassembly network is established, in which lengths of arc are stochastic variables with a specified power subject to specified distributions and denote removal times of parts, the energy evaluation method integrating two or more uncertain variables is proposed. According to different disassembly decision-making criteria, three types of typical stochastic programming models of a disassembly process are developed, namely the minimum expected value model, the maximum energy disassemblability degree model and D′-minimum energy model. The energy probability distributions are determined through the application of stochastic linear programming and maximum entropy principle. Synchronously, based on obtained theoretical probability distributions, the quantitative evaluation and stochastic programming of a disassembly process are realized. The simulation results show that the proposed method is feasible and effective to solve the stochastic programming issue with time-varying stochastic characteristics.
Disassembly scheduling using stochastic algorithms
2007, IFAC Proceedings Volumes (IFAC-PapersOnline)
An essential criterion for a disassembly system is the benefit it brings, that is the revenue brought by the retrieved parts and material, decreased by the cost of their retrieval. In the recycling industry the main problem is the uncertainty that occurs during the disassembly operations. A fast scheduling algorithm is proposed so as to optimize the income flow of the disassembly system taking into account alternative destructive operations. Two examples from industry are given.
A review of electronics demanufacturing processes
2006, Resources, Conservation and Recycling
Hundreds of millions of end-of-life electronics require demanufacturing for materials recovery. The challenges of significant quantities of different products converging to demanufacturing processes present research opportunities for technology, recycling process design, and controls. In this review, we summarize research to improve demanufacturing processes through disassembly, automation, bulk recycling of ferrous and nonferrous metals, and plastics identification and separation. We conclude with future research directions for electronics recycling.
Flexible robotic demanufacturing using real time tool path generation
2006, Robotics and Computer-Integrated Manufacturing
The need for new demanufacturing technologies exists due to a growing population of end of life electronic products. The demanufacturing method presented in this work is unique from disassembly because destructive methods are employed; thus, eliminating the need to account for precedence relationships. Furthermore, the new demanufacturing method employs cutting operations but differs from traditional machining operations due to the degree of flexibility required. To address this very high scale flexibility, a unique prototype flexible demanufacturing work cell has been established. Unique contributions of this flexible demanufacturing method include a new system model that utilizes a product surface model and a robot tool position model to actively generate real time tool paths. The model uses manifolds to reduce the tool path generation function to navigation of the surface manifold. Tool path generation occurs in three stages: machining operation sequencing, active tool path generation and active product avoidance. A case study of the demanufacture of mobile phones is presented to illustrate the flexible robotic demanufacturing operation. The case study shows that a new flexible robotic demanufacturing process has been achieved that requires no predetermined information on the product surface geometry.
Applying equal piles approach to disassembly line balancing problem
2005, IFAC Proceedings Volumes (IFAC-PapersOnline)
A Hybrid Approach Combining Improved Shuffled Frog-Leaping Algorithm with Dynamic Programming for Disassembly Process Planning
2021, IEEE Access

View all citing articles on Scopus

View full text