Treffer: Multi-objective optimization for CF/PPS-stainless steel induction welding with pin structure based on SSA-BP neural network.

Carbon Fiber Reinforced Thermoplastic Plastic (CFRTP) has been increasingly used in aerospace and automotive manufacturing with its excellent mechanical properties. Based on the melt-curing characteristics of thermoplastic composites, combining the full-thickness reinforced joining technology with induction welding can provide an effective way for high-strength joining. In this paper, the full factorial experimental design method is used to deeply explore the influence law of welding time, consolidation force and heating current on the tensile properties of welded joints. Combined with Sparrow Search Algorithm (SSA) and BP neural network, a welding joint tensile strength prediction model was constructed. In addition, a multi-objective model based on Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was developed. The multi-objective optimization method of TOPSIS was used to select the optimal parameter combinations with ultimate tensile strength and first debonding strength as the optimization objectives: welding time of 29.995 min, consolidation force of 638.669 N, and heating current of 443.351 A. Experimental studies have shown that the optimized welding joints have an increase in ultimate tensile strength of up to 32.4 % and an increase in first time debonding strength of up to 47.0 % with respect to the non-optimized welding joints. [ABSTRACT FROM AUTHOR]

Copyright of Advanced Composite Materials is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Volltext ist im Gastzugang nicht verfügbar. Login für vollen Zugriff.