Intelligent planning of product assembly sequences based on spatio-temporal semantic knowledge

Abstract

Purpose The implied assembly constraints of a computer-aided design (CAD) model (e.g. hierarchical constraints, geometric constraints and topological constraints) represent an important basis for product assembly sequence intelligent planning. Assembly prior knowledge contains factual assembly knowledge and experience assembly knowledge, which are important factors for assembly sequence intelligent planning. This paper aims to improve monotonous assembly sequence planning for a rigid product, intelligent planning of product assembly sequences based on spatio-temporal semantic knowledge is proposed. Design/methodology/approach A spatio-temporal semantic assembly information model is established. The internal data of the CAD model are accessed to extract spatio-temporal semantic assembly information. The knowledge system for assembly sequence intelligent planning is built using an ontology model. The assembly sequence for the sub-assembly and assembly is generated via attribute retrieval and rule reasoning of spatio-temporal semantic knowledge. The optimal assembly sequence is achieved via a fuzzy comprehensive evaluation. Findings The proposed spatio-temporal semantic information model and knowledge system can simultaneously express CAD model knowledge and prior knowledge for intelligent planning of product assembly sequences. Attribute retrieval and rule reasoning of spatio-temporal semantic knowledge can be used to generate product assembly sequences. Practical implications The assembly sequence intelligent planning example of linear motor highlights the validity of intelligent planning of product assembly sequences based on spatio-temporal semantic knowledge. Originality/value The spatio-temporal semantic information model and knowledge system are built to simultaneously express CAD model knowledge and assembly prior knowledge. The generation algorithm via attribute retrieval and rule reasoning of spatio-temporal semantic knowledge is given for intelligent planning of product assembly sequences in this paper. The proposed method is efficient because of the small search space.

Predicting Assembly Geometric Errors Based on Transformer Neural Networks

“…The probability of the uniform distribution is as p(k i |q i ) = 1/L k . So, the Kullback-Leibler (KL) divergence for measuring the probability distribution between can be expressed as Equation (10).…”

“…Utilizing traditional data-driven methods involves processing and predicting collected data, thereby establishing a mapping between the physical world and the digital world, known as a digital twin. Although these traditional data-driven methods exhibit strong operability (such as utilizing genetic algorithms to analyze assembly or disassembly sequences, among others) and can effectively improve overall assembly geometric errors, their accuracy and robustness are compromised when predicting errors in the assembly process of increasingly complex products [8][9][10][11]. To overcome the limitations of traditional data-driven methods, machine learning techniques have emerged as the mainstay in this field.…”

A Review and Prospects of Manufacturing Process Knowledge Acquisition, Representation, and Application

“…Qian et al [83] fused knowledge bases with optimization techniques to streamline assembly scheduling. Yang et al [84] utilized CAD data to inform ontology models for intelligent assembly planning. Ye et al [85] advanced CNC process planning through a cloud-based knowledge system with proven effectiveness.…”

Optimization Method for Assembly Sequence Evaluation Based on Assembly Cost and Ontology of Aviation Reducers

“…In order to realize the automatic planning of complex assembly product sequences and improve assembly efficiency, Zhao, M.H. proposed an assembly sequence planning system for workpieces (ASPW) based on deep reinforcement learning; the proposed ASPW-DQN unites curriculum learning and parameter transfer, which can avoid the explosive growth of assembly relations and improve system efficiency [13,14]. Aiming to solve the problem of insufficient individual intelligence in the evolutionary algorithm of assembly sequence planning, according to the disadvantage of the particle swarm optimization algorithm easily falling into local optimization, a various population strategy was adopted to shorten the evolution stagnation time, improve the evolution efficiency of the particle swarm optimization algorithm, and enhance the optimization ability of the algorithm [15].…”