Classification of Textile Polymer Composites: Recent Trends and Challenges

Area of Science:

• Materials Science
• Engineering
• Computer Science

Background:

• Polymer-based textile composites are increasingly vital in industries like automotive, construction, and aerospace.
• Natural fibers enhance carbon fiber reinforced composites, improving economic viability and material properties.
• Classifying textile products and composites is complex due to quality, price, and consumer satisfaction factors.

Purpose of the Study:

• To classify challenges in textile manufacturing and fiber-reinforced polymer composites.
• To evaluate the effectiveness of artificial neural networks, genetic algorithms, and fuzzy logic for classification.
• To propose and discuss novel sequential classification methods.

Main Methods:

• Artificial Neural Networks (ANNs)
• Genetic Algorithms (GAs)
• Fuzzy Logic (FL)
• Sequential classification methods

Main Results:

• The study details the application of ANNs, GAs, and FL in classifying textile and composite issues.
• Limitations of current state-of-the-art classification processes are identified.
• New sequential classification approaches are proposed and analyzed.

Conclusions:

• Advanced computational methods like ANNs, GAs, and FL can effectively classify complex problems in textile and composite materials.
• The research highlights areas for improvement in existing classification techniques.
• The proposed sequential methods offer potential advancements for future composite material development and quality control.