A Multi-Level Genetic Assembly Planner

2000 ◽  
Author(s):  
Shiang-Fong Chen ◽  
Yong-Jin Liu
Keyword(s):  
Assembly Sequence Planning ◽  
Geometric Constraints ◽  
Control Parameters ◽  
Assembly Sequence ◽  
Low Level ◽  
Sequence Planning ◽  
Assembly Sequences ◽  
Multi Level ◽  
High Level ◽  
Optimal Assembly

Abstract Assembly sequence planning (ASP) is a combinatorial optimization problem with highly non-linear geometric constraints. Most proposed methodologies are based on graph theory and involve complex geometric and physical analysis. As a result, even for a simple structure, it is difficult or impossible to take all important criteria into consideration. In order to bring assembly sequence planning closer to real-world application, this paper proposes a genetic planner for efficiently finding global-optimal assembly sequences. To optimize our genetic-algorithm-based approach, we propose a hierarchical genetic structure and an evaluation mechanism for dynamically adapting control parameters in our hierarchical structure. Unlike conventional genetic algorithms, which use static genetic operator probability settings (GOPS), our hierarchical genetic planner searches for optimal assembly sequences in a low-level GA and manipulates low-level GOPS using a high level GA. Conventional “GA within GA” approaches perform, for every high-level generation, a full low-level GA run, whereas our multi-level GA uses a high-level GA to isochronously update low-level GA control parameters during each low-level GA run. Experimental results show that our multi-level genetic assembly sequence planner solves combinatorial ASP problems quickly, reliably, and accurately.

Assembly Sequence Planning Based on Connector Structure and Ant Colony Algorithm

2013 ◽  
Vol 712-715 ◽  
pp. 2482-2486 ◽  
Author(s):  
Ying Ying Su ◽  
Hai Dong ◽  
Di Liang
Keyword(s):  
Ant Colony Algorithm ◽  
Assembly Sequence Planning ◽  
Precedence Constraint ◽  
Ant Colony ◽  
Ant Algorithm ◽  
Assembly Sequence ◽  
Sequence Planning ◽  
Assembly Sequences ◽  
Assembly Unit ◽  
Optimal Assembly

For the purpose of effectively reducing the degree of complexity and improving the efficiency, the method of assembly sequence planning based on connector structure and ant algorithm was proposed. The concept of connector structure was presented, which was regarded as basic assembly unit to cover features of assembly parts. Then, a model of assembly sequence planning was built, which represented the precedence constraint relationship among connector structures. Additionally, the combination of the connector structure concept and characteristics of ant colony algorithm was developed for generating optimal assembly sequences under the guidance of precedence relations in the model. Finally, an example was studied to illustrate the effectiveness of the strategy.

scholarly journals Assembly Sequence Planning Using Artificial Neural Networks for Mechanical Parts Based on Selected Criteria

2021 ◽  
Vol 11 (21) ◽  
pp. 10414
Author(s):  
Marcin Suszyński ◽  
Katarzyna Peta
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Clustering Algorithm ◽  
Assembly Sequence Planning ◽  
Planning System ◽  
Assembly Sequence ◽  
Mechanical Parts ◽  
Sequence Planning ◽  
Assembly Sequences ◽  
Artificial Neural

The proposed model of the neural network describes the task of planning the assembly sequence on the basis of predicting the optimal assembly time of mechanical parts. In the proposed neural approach, the k-means clustering algorithm is used. In order to find the most effective network, 10,000 network models were made using various training methods, including the steepest descent method, the conjugate gradients method, and Broyden–Fletcher–Goldfarb–Shanno algorithm. Changes to network parameters also included the following activation functions: linear, logistic, tanh, exponential, and sine. The simulation results suggest that the neural predictor would be used as a predictor for the assembly sequence planning system. This paper discusses a new modeling scheme known as artificial neural networks, taking into account selected criteria for the evaluation of assembly sequences based on data that can be automatically downloaded from CAx systems.

Research on Aircraft Assembly Sequence Planning Technology Based on Key Characteristics

2013 ◽  
Vol 328 ◽  
pp. 9-16 ◽  
Author(s):  
Zhan Lei Sun ◽  
Peng Fei Han ◽  
Gang Zhao
Keyword(s):  
Process Design ◽  
Assembly Sequence Planning ◽  
Assembly Process ◽  
Assembly Sequence ◽  
Assembly Quality ◽  
Constraint Matrix ◽  
Aircraft Assembly ◽  
Sequence Planning ◽  
Key Characteristics ◽  
Assembly Sequences

Assembly Sequence Planning (ASP) is an essential question for aircraft assembly process design. Modern aircraft assembly contains plenty of complex shape components, which have so many assembly features to ensure, this leads to a large number of feasible assembly sequences using traditional sequence planning algorithms; and it is hard to evaluate the contribution to assembly quality for every sequence. A methodology called Key Characteristics Based ASP is proposed in this paper, which can significantly reduce unavailable sequences and ensure key features for quality in assembly process designing compared with previous methods. The methodology focuses on the final assembly quality and considers it as Assembly Key Characteristics (AKCs) in the beginning of assembly process design. With tools such as AKCs decomposition, Datum Flow Chain, precedence constraint matrix, the methodology describes the main process for ASP. To verify the technologys effectiveness, this paper presents an application of the algorithm in an aircraft component assembly by an 863 program.

Petri Net Models for Assembly Sequences Planning

2007 ◽  
Vol 10-12 ◽  
pp. 411-415 ◽  
Author(s):  
Y.L. Fu ◽  
R. Li ◽  
H.B. Feng ◽  
Y.L. Ma
Keyword(s):  
Petri Net ◽  
Assembly Sequence Planning ◽  
Assembly Model ◽  
Assembly Sequence ◽  
Assembly Operation ◽  
Knowledge Based ◽  
Assembly Sequences ◽  
Model Size ◽  
Assembly Sequences Planning ◽  
Optimal Assembly

Assembly sequences can be represented by a Petri net(PN) which characterizes dynamic system changes and provides a tool for obtaining optimal assembly sequences. In this study some assembly operation constraints are considered in order to obtain more practical sequences which are conformed to real situations. In order to enhancing the efficiency of the assembly sequence planning, knowledge-based Petri net, combining an usual Petri net with expert’s knowledge and experiences, is proposed to construct the assembly model. With the complexity of the product, the product’s assembly model size will be too large to analysis. So the basic subnets are used to reduce the large PN. And the reduced version can be used for the analysis of the original PN. To verify the validity and efficiency of the approach, a variety of assemblies including some complicated products from industry are tested, and the corresponding results are also presented.

AUTOMATIC COLLISION DETECTION FOR ASSEMBLY SEQUENCE PLANNING USING A THREE-DIMENSIONAL SOLID MODEL

2011 ◽  
Vol 10 (02) ◽  
pp. 277-291 ◽  
Author(s):  
ALFADHLANI ◽  
T. M. A. ARI SAMADHI ◽  
ANAS MA'RUF ◽  
ISA SETIASYAH TOHA
Keyword(s):  
Free Path ◽  
Collision Detection ◽  
Three Dimensional ◽  
Assembly Sequence Planning ◽  
Detection Methods ◽  
Assembly Sequence ◽  
Sequence Planning ◽  
Assembly Sequences ◽  
Geometrical Data ◽  
Selection Of

Assembly sequence planning of a product involves several steps, including generation of precedence constraints, generation of assembly sequences, and selection of assembly sequences. Generation and selection of assembly sequences should be able to guarantee the feasibility of assembly. Assembly will be feasible if there is no collision between components when assembled. Detection of collision-free path of assembly can be done in an automated way. There are a number of collision detection methods that have been developed, but the method requires a complicated process of data geometry analysis. This paper proposes a method for detecting a collision-free path of the assembly component in a more simple way. Geometrical data required, taken from the three-dimensional (3D) solid drawing in the form of stacked drawing in computer-aided design (CAD) systems. Retrieval of geometrical data of components and detection of the collision-free path of an assembly were done in an automated way, directly from the CAD system.

A Symbolic OBDD-Based Algorithm for Assembly Sequence Planning

2010 ◽  
Vol 97-101 ◽  
pp. 2444-2448
Author(s):  
Feng Ying Li ◽  
Tian Long Gu ◽  
Liang Chang
Keyword(s):  
Petri Nets ◽  
Petri Net ◽  
Assembly Sequence Planning ◽  
Decision Diagrams ◽  
Assembly Sequence ◽  
Binary Decision ◽  
Sequence Planning ◽  
Assembly Sequences ◽  
Planning Algorithm ◽  
The One

Algorithms based on timed Petri net are competitive for solving the problem of assembly sequence planning (ASP). In order to alleviate the state-space explosion problem which is caused by the Petri net-based representation of assembly sequences and to improve the efficiency of planning algorithms, an approach based on ordinary binary decision diagrams (OBDDs) is presented in this paper. On the one hand, all the timed transitions in Petri nets are substituted by some technically designed timed transition structures; on the other hand, Petri nets used in algorithms of assembly sequence planning are represented symbolically as OBDDs. As a result, a novel assembly sequence planning algorithm based on symbolic OBDDs is presented. With the help of OBDDs, both the marking vectors and the states of Petri nets are formulated more compactly; at the same time, the searching processes can be manipulated implicitly. Therefore, compared with original algorithms, both the time performance and the space performance are improved.

A Particle Swarm Algorithm for Assembly Sequence Planning

2010 ◽  
Vol 97-101 ◽  
pp. 3243-3246
Author(s):  
Yan Feng Xing ◽  
Yan Song Wang ◽  
Xiao Yu Zhao
Keyword(s):  
Particle Swarm ◽  
Tolerance Analysis ◽  
Assembly Sequence Planning ◽  
Particle Swarm Algorithm ◽  
Assembly Sequence ◽  
Sequence Generation ◽  
Assembly Sequences ◽  
Swarm Algorithm ◽  
Assembly Sequence Generation ◽  
Optimal Assembly

A particle swarm algorithm is proposed to generate optimal assembly sequences for compliant assemblies. Firstly, the liaison graph and the adjacency matrix describe the geometry of the compliant assemblies. An assembly sequence is represented by a character string, whose length is the number of all parts. The conceptual tolerance analysis is used to evaluate feasible sequences. Thereafter, the particle swarm algorithm is presented to generate assembly sequences, in which the elite ratio is applied to improve optimization results. Finally a fender assembly is used to illustrate the algorithm of assembly sequence generation and optimization.

scholarly journals Assembly Sequence Planning by Probabilistic Tree Transformation

2018 ◽  
Vol 6 (2) ◽  
pp. 354-368
Author(s):  
Takeshi Murayama ◽  
Yuichi Mine ◽  
Hiroshi Fujinaka ◽  
Toru Eguchi
Keyword(s):  
Software Tool ◽  
Assembly Sequence Planning ◽  
Assembly Sequence ◽  
Sequence Planning ◽  
Cad System ◽  
Assembly Sequences ◽  
Long Time ◽  
Cad Cam ◽  
Machine Industry ◽  
Tree Transformation

Various types of computer systems including CAD/CAM systems have been introduced in machine industry. Some of the systems can handle assembly sequence planning, however it requires long time for planning. This paper proposes a method of generating assembly sequences efficiently. This method extracts some parts and/or subassemblies whose possibilities of being removed from a product are strong, and tests whether they can be removed without any geometric interference. By performing these operations repeatedly, the method generates a disassembly sequence of the product, and obtains an assembly sequence by reversing it. The extraction of some parts and/or subassemblies is performed, based on probabilistic tree transformation. The authors present a calculation example by using a software tool integrated with a CAD system.

Sign in / Sign up

Export Citation Format

Share Document