Quantum‐behaved RS‐PSO‐LSSVM method for quality prediction in parts production processes

Summary Quality control in the production process is the core of the enterprise to ensure product quality, and quality prediction is the key link of quality control and quality management. Aiming at the quality prediction of parts in the production process, a product quality prediction model is esta...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Concurrency and computation Jg. 34; H. 7
Hauptverfasser: Yingying, Su, Lianjuan, Han, Jianan, Wang, Huimin, Wang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Hoboken Wiley Subscription Services, Inc 25.03.2022
Schlagworte:
Algorithms
Microprocessors
Particle swarm optimization
Prediction models
Product quality
Quality control
Quality management
quality prediction
rough set theory
RS‐PSO‐LSSVM synthesis algorithm
Support vector machines
ISSN:1532-0626, 1532-0634
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Summary Quality control in the production process is the core of the enterprise to ensure product quality, and quality prediction is the key link of quality control and quality management. Aiming at the quality prediction of parts in the production process, a product quality prediction model is established. In this model, Rough Set (RS), Particle Swarm Optimization (PSO), and Least Square Support Vector Machine (LSSVM) are applied to solve the problem of product quality prediction and a RS‐PSO‐LSSVM synthesis algorithm is established. First, the 5M1E analysis of production process for parts is carried out, and the index system of influencing factors is established. Based on this index system, the condition attributes and decision attributes of RS are determined, in which RS is used to the reduction to extract rules and the optimal condition attribute value is obtained, which is used as the pre‐processing of LSSVM input data. Second, in order to improve the learning and generalization ability of LSSVM, PSO is used to optimize the relevant parameters and find the optimal solution. Finally, an example is given to verify the feasibility and effectiveness of the product quality prediction model and the RS‐PSO‐LSSVM comprehensive algorithm established above, and the prediction accuracy is higher than that of the RS‐LSSVM algorithm.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1532-0626
1532-0634
DOI:10.1002/cpe.5522