Application of six sigma through deep learning in the production of fasteners

Abstract

Purpose The purpose of this study was conducted at an enterprise that produces fasteners and is one of the leading companies in the sector in terms of market share. Possible defects in the coating of bolts and nuts either lead to products being scrapped or all of the coating process being repeated from beginning to end. In both cases, the enterprise faces a waste of time and excessive costs. Through this project, the six sigma theory and its means were effectively used to improve the efficiency and quality management of the company. The selection of the six sigma project has also contributed to the creation of various documents to be used for project screening and evaluation of financial results. Design/methodology/approach Six sigma is an optimization strategy that is used to improve the profitability of businesses, avoid waste, scrap and losses, reduce costs and improve the effectiveness of all activities to meet or exceed customers’ needs and expectations. Six sigma’s process improvement model, known as Definition-Measurement-Analysis-Improvement-Control, contributes to the economic and technical achievements of businesses. The normal distribution of a process should be within ±3 sigma of the mean. This represents a scale of 99.7% certainty. However, improving the process through the utilization of the six sigma rule, which accepts normal variabilities of processes twice as strict, will result in an error rate of 3.4 per million instead of 2,700 per million for each product or service. Findings Using six sigma practices to reduce the costs associated with low quality and to increase economic added value became a cultural practice. With this, the continuation of six sigma practices throughout the Company was intended. The annual cost reduction achieved with the utilization of six sigma practices can be up to $21,780. When time savings are also considered, a loss reduction of about $30,000 each year can be achieved. The coating thickness efficiency increased from 85% to 95% after the improvements made through the six sigma project. There is a significant increase in the efficiency of coating thickness. In addition, the coating thickness efficiency is also close to the target value of 95%–97%. Originality/value The results of the study were optimized with the help of deep learning. The performance of the model created in deep learning was quite close to the actual performance. This result implicates the validity of the improvement work. The results may act as a guide for the use of deep learning in new projects.