Identifying factors affecting the quality of industrial products through data clustering analysis

Accurate identification of factors affecting product quality can lead to improved production processes, reduced waste, increased productivity, and ultimately improved customer satisfaction. This study aimed to identify factors affecting the quality of industrial products and analyze the relationships between these factors using data mining and clustering techniques. Data related to the industrial production process, including variables such as raw material purity, machine error rate, temperature, pressure, production speed, and human experience, were simulated and preprocessed. K-Means, hierarchical clustering, and DBSCAN algorithms were used to analyze the data. The results showed that raw material purity, machine error rate, and temperature are among the most important factors affecting product quality. Also, clusters with high raw material purity (>95%) and machine error rate less than 2% showed the best quality, while clusters with low purity and high production speed had poor quality. This research provides a comprehensive model for analyzing and optimizing the quality of industrial products that can be used in various industries such as automotive, pharmaceutical, and food industries