Franco Failli

Computer Aided Disassembly Planning: State of the Art and Perspectives

Abstract In the last two decades, the problems related to the preservation of the environment and the resources of the planet have been dramatically highlighted by different phenomena (thinning of ozone layer, greenhouse effect, decreasing of forests, air pollution, increasing difficulties in the industrial and domestic waste management, etc.). In order to face this situation, the governments have begun to apply rules to control some aspects of the industrial production and energy. Consequently, the environment has become an interesting issue also for the researchers. A key-point in these new techniques, grouped under the name of “sustainable development”, is the disassembly and recycling of the end-of-life goods, necessary to minimize the environmental impact of discarded materials and energy consumption. In this keynote paper the state of the art of the software tools developed to help the designer and the dismantler in the optimization of the disassembly-for-recycling of discarded goods is discussed. The architecture of a complete and general computer aided disassembly planning system is described and a number of system developed both in the academic institutes and in the industry are shown together a review and classification of the different adopted solutions.

Generation of Optimized Assembly Sequences Using Genetic Algorithms

Abstract This paper describes a method based on genetic algorithms for the generation and the evaluation of assembly sequences. Genetic algorithms are here used to drastically reduce the high computational time, usually necessary to evaluate the best assembly sequences, owing to ‘combinatorial explosion’ phenomena. The generation of optimized sequences is performed using an appropriate fitness function which takes into account simultaneously the geometrical constraints, the minimization of gripper changes and object orientations, and the possibility of grouping similar assembly operations (screwing, pressing, etc.). The paper also presents the chromosome structure used in the system, the genetic operators and, finally, a meaningful example of application.

A disassembly planning software system for the optimization of recycling processes

This paper describes the methods and algorithms adopted in a software system for the generation of optimized disassembly plans to be used in recycling of end-of-life goods. Three aspects of the system are particularly emphasized: the integration with CAD; the capability to automatically detect the subassemblies of the product; and the capability to auto matically generate all the feasible disassembly sequences. The selection of the best disassembly plan is made on the basis of the maximum profit achievable from the recycling of components, calculated according to the information contained in a database and concerning the market, the available tools, etc. A meaningful example of application is reported and discussed in detail, analysing the system performance in different situations, e.g. different market conditions, different deterioration of the good, application of different kinds of disassembly operations.

Optimization of Disassembly Sequences for Recycling of End-of-Life Products by Using a Colony of Ant-Like Agents

In this paper the problem of recycling of end-of-life goods is approached using a computer-aided technique named Ant Colony Optimization system. The need of disassembly for recycling and the opportunity of using computer-aided techniques, AI tools in particular, are discussed. The basic concepts of Ant Colony Optimization systems are also introduced. The main topics related to a future application of this methodology to a software system able to support the designer in choosing the best disassembly sequences of products are discussed.

An Innovative Approach to the Automated Stacking and Grasping of Leather Plies

Abstract In this paper, a complete study of automatizing the manipulation process of tanned natural leather plies is presented. The considered leather plies are partially refined and their surface is suitable for grasping by suction grippers. The particular features (non-rigid structure, irregular shape and size, etc.) of such a material make the handling and loading on the workstations very critical and difficult to be approached. To increase the reliability of grasping, the development of customized vacuum cups seems to be advisable. In the paper, an innovative vacuum cup model is proposed. Its performances are quantitatively compared with a other models by means of appropriate measuring methods. Another problem concerning the automatic manipulation of leather plies is to avoid the grasping of more than one ply at a time, due to the irregularity of the ply profile. A device able to solve this problem, using an innovative equipment for moving the entire stack from the store to the workstation and for separating the plies, is also shown and discussed.

Guidelines for Implementing Augmented Reality Procedures in Assisting Assembly Operations

The use of Augmented Reality (AR) in training or assisting operators during an assembly task can be considered an innovative and efficient method in terms of time saving, error reduction, and accuracy improvement. Nevertheless, the implementation of an AR-based application is quite difficult, requiring to take into account several factors. This paper provides a general procedure to follow for a correct implementation, starting from an assessment of the assembly task, until the practical implementation. To assess the procedure, it has been applied to the training of unskilled operators during the assembly of a planetary gearbox, with the help of a hand-held device.

Assembly planning based on genetic algorithms

A genetic algorithm that generates and evaluates assembly plans is proposed. This algorithm is able to generate near-optimal assembly plans through purposely developed crossover and mutation operators starting from a randomly initialized population of assembly sequences. The optimization criteria we used to assess the quality of feasible assembly sequences are: (i) to minimize the orientation changes of the product; (ii) to minimize the gripper changes, and (iii) to group technologically similar assembly operations together as much as possible. Experimental results that confirm the validity of our approach are also included.

Disassembly for Recycling, Maintenance and Remanufacturing: State of the Art and Perspectives

The continuous progress in manufacturing techniques and the increasing ecological consciousness have led to a constant refinement in natural resources exploitation. In particular, the advisability of a longer and more reliable life cycle of products and the reintroduction of mere materials in the production cycle have created new research fields in maintenance, remanufacturing and recycling, respectively. All these subjects have a common need: the complete or partial disassembly of the product in order to obtain more efficient and profitable results. The aim of this paper is therefore to analyse the state of the art of the research in disassembly techniques applied in these fields, emphasising the problems to be solved and the perspectives in the next years.

Planning grasps for industrial robotized applications using neural networks

Abstract The present paper proposes a computer-aided module for the detection of grasps of 3D objects by using artificial neural networks. This module considers the grasps performed by the most common classes of grippers used in industrial applications: two-jaw grippers, three-jaw grippers, magnetic grippers, vacuum grippers and expandable grippers. The neural networks are properly tailored and trained in order to evaluate and compare the different grasping alternatives according to geometrical and technological aspects of object surfaces. A case study is also discussed in order to point out the performances of this methodology.

Neural-Based Grasping for Industrial Grippers

The problem of automatic grasp planning for industrial applications involving solid bodies is approached by using Artificial Neural Networks (ANNs). Three kinds of industrial grippers are considered: two-jaw grippers, magnetic grippers and vacuum grippers. To allow the automatic solution of a wide set of cases, the ANNs are trained using different sets of practical situations where geometrical and technological features of grasped objects are considered. This paper, in particular, is mainly focused to the discussion of the results obtained in different examples of application aiming at showing the performance of the proposed approach.