An Intelligent Deep Learning Process to Predict Textile Industry Fabric Quality Evaluation using Artificial Intelligence Logic

The textile industry is highly dependent on maintaining stringent quality standards to ensure product consistency, reduce defects, and meet consumer expectations. This paper presents an intelligent deep learning process for evaluating fabric quality in the textile industry using advanced artificial intelligence (AI) techniques. The proposed hybrid model integrates EfficientNet for feature extraction, GRU (Gated Recurrent Unit) for sequential data handling, and XGBoost for robust classification. The model was trained and tested on fabric images, evaluating parameters like fabric density, texture patterns, and defects. The experimental results demonstrated that the proposed model achieved the highest accuracy of 93.45%, surpassing traditional models like CNN, LSTM, SVM, and Random Forest. Furthermore, the model also excelled in precision, recall, and F1-score, highlighting its robustness and suitability for real-time fabric quality evaluation in industrial applications. The superior performance of the model underscores the potential of AI-driven approaches in improving textile quality assurance processes.