Evaluating the Quality of Manufactured Products by Providing an Approach based on the ANFIS Neural-Fuzzy Network (Case Study: Khazar Plastic Manufacturing and Industrial Company)

Introduction and Purpose: The current need for expanding accurate and rapid quality assurance to provide high-quality and safe manufactured products is essential. Quality focuses on internal issues that control and improve internal processes, aiming to enhance performance for customer satisfaction and competitiveness. Quality in industry, government, and society emphasizes the continuous improvement of products and processes. The quality performance evaluation system heavily relies on identifying and selecting critical success factors and indicators within the quality management framework. However, the manufacturing industry faces problems such as low production efficiency, low accuracy, and lack of innovation in products. Methods: To address these issues, this study proposes introducing an artificial intelligence method for manufacturing companies to solve these problems and improve product quality and production efficiency. An adaptive neuro-fuzzy inference system (ANFIS) is presented to evaluate the accuracy of the results and compare its efficiency. The proposed method contrasts with hard calculations and aims to save time and money. As data volumes in industries increase, leading to new concepts like big data analytics, the study discusses the limitations and advantages of AI-based solutions. The focus is on stimulating creative solutions and new directions in manufacturing, commercial, and service industries to improve process efficiency, enhance the value of solutions, and design new products to find new markets. International roadmaps focused on innovation and research consistently highlight AI as a fundamental driver of future technology. Traditional quality management methods face challenges in managing high-dimensional and non-linear production data. To address these challenges, this research develops an AI-based process to improve product quality and production efficiency. An adaptive neuro-fuzzy inference model, combining the advantages of neural networks and fuzzy inference, is proposed to evaluate and extract the quality level of manufactured products and infer the relationships between production parameters and process quality in a production system. Findings: To train the proposed model, data from the quality process of a piece from Khazar Plastic Industrial Company's production line were used. The study included 550 data points related to the quality process, emphasizing influential variables such as "appearance standard, external diamete