Authors

1. Mr. Manoj Tiwari
2. Mr. Malkaus Chaudhary

Affiliation

• Associate Professor, Department of Fashion Technology, NIFT, Jodhpur
• Student, Department of Fashion Technology, NIFT, Jodhpur

Abstract

Global apparel manufacturing is becoming more competitive with each day. Effective and efficient
utilization of resources has become vital for to survival. Cost optimization is the key to remain
competitive and profitable in this scenario. Machine and equipment maintenance is one of the major
factor contributing in the success or failure of any manufacturing organization. The issue of machine
breakdown is very critical in apparel manufacturing which leads to delay in manufacturing and
eventually results in various types of losses.
This research aims at reducing the downtime of the plant machinery by implementing a planned
preventive maintenance program through the application of the Reliability Centred Maintenance
using Artificial Intelligence. The traditional approach of planned preventive maintenance is based on
the calendar which doesn't take due consideration of machine behaviour and failure patterns, hence
it lacks reliability. Therefore, this research proposes a system which can learn the nature and
frequency of defects on the bases of the machine types. Subsequently, a Reliability Centred
Maintenance programme is devised ensuring improved availability of the machines, and resulting
into reduced machine breakdown and failure.
The approach discussed in this research paper is based on the deep learning model to learn the
defects and its analysis with help of a database created as per specific requirements of an apparel
manufacturing environment. Initial data grasping of the machine breakdowns on floor was done to
understand the nature of the problems. To understand the problem more accurately the nature of
frequent machine breakdown as well as frequency of the breakdowns were recorded from thirteen
sewing lines from three sewing floors. The machine breakdown data was collected for each of the
sewing machines of different types from the selected lines of a sewing floor. The data was
categorized as per the type of machine and number of machines. Month wise data related to machine
breakdown occurrence, machine breakdown time and major defects frequency was collected before
and after system implementation. A significant improvement was observed in all the aspects studied
as approximately 29% reduction in machine breakdown, 35% reduction in defects occurrence and
15% reduction in the machine breakdown time was observed after system implementation. This
approach also resulted in creating an environment of learning organisation which learns about itself
as the system grows with the organization.

Keywords

Apparel manufacturing, Planned Preventive Maintenance (PPM), Reliability Centered Maintenance (RCM), Artificial Intelligence (AI), Machine learning, Failure pattern, Defect Analysis

References

1. Fore, S., & Msipha, A. (2010). Preventive Maintenance using Reliability Centred Maintenance (RCM): A case study of a Ferrochrome Manufacturing Company. South African Journal of Industrial Engineering, 21(1), 207-235.
2. Jana, P., & Tiwari, M. (2018). Industrial Engineering in Apparel Manufacturing - A Practitioners Handbook. New Delhi, India: Apparel Resources Pvt. ltd.
3. Correia, P. I. (2016). Maintenance in tough economic times: The importance of maintenance management. www. manwinwin.com: https://manwinwin.com/wp-content/uploads/2016/12/ Maint_Economic_Times.pdf, retrieved on December 2018, 11.
4. Gross, J. M. (2002). Fundamentals of Preventive Maintenance. (C. D. 224, Ed.) AMACOM Division of American Management Association International.
5. Moubray, J. (1997). Reliability-Centered Maintenance II. Industrial Press Inc.
6. Smith, A. (1993). Reliability Centred Maintenance. New York: McGraw Hill Inc.
7. Campbell, J. (1999). The Reliability Handbook – Plant engineering and maintenance (Vol. 23). Clifford/ Elliot Publications.