An Analysis of Manufacturing Machine Failures and Optimization Using Replacement Year Prediction

Title

An Analysis of Manufacturing Machine Failures and Optimization Using Replacement Year Prediction

Creator

Saranya R.; Sneha M.; Sridevi R.

Description

The manufacturing industry is highly susceptible to equipment failures, leading to costly downtime, production delays, and increased maintenance expenses. Effective maintenance planning and resource allocation depend on the early detection of possible faults and the precise forecasting of replacement years. The fundamental technique for assuring operational resilience, limiting disruptions, and improving preventative maintenance processes is manufacturing failure analysis. It entails the methodical analysis of failures and spans several sectors, including the automobile, aerospace, electronics, and heavy machinery. In this research, an integrated methodology for predicting replacement years in the manufacturing industry using operations research approaches and the Python-based machine learning algorithm Random Forest Classifier (RFC) is proposed. The program first calculates the total failure rate after importing manufacturing data from a dataset. The failure rate for each manufacturing line is then determined, and the lines with a high failure rate are identified. The program uses machine learning to improve the analysis by teaching a Random Forest classifier to anticipate failures. The model's performance is assessed by measuring the accuracy of a test set. To determine machine replacement years, it also incorporates replacement theory assumptions. Based on the company's founding year and the current year, it determines the replacement year considering the machine's lifespan. This program's advantages include recognizing production lines with high failure rates, employing machine learning to forecast problems, and offering suggestions on when to replace machines. Manufacturers may enhance their processes, lower failure rates, and increase overall efficiency by utilizing statistical analysis, machine learning, andoptimizationstrategies. As technology advances, the field of failure analysis will continue to evolve, enabling firms to achieve improvements. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Source

Lecture Notes in Networks and Systems, Vol-922 LNNS, pp. 311-324.

Date

2024-01-01

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Failure rate; Machine learning; Manufacturing failures; Operations research; Random forest classifier; Replacement years; Statistical analysis

Coverage

Saranya R., PSG College of Arts and Science, Coimbatore, India; Sneha M., PSG College of Arts and Science, Coimbatore, India; Sridevi R., Christ Deemed to be UniversityCentral Campus, Bangalore, 560029, India

Rights

Restricted Access

Relation

ISSN: 23673370; ISBN: 978-981970974-8

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-981-97-0975-5_28

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85197277440&doi=10.1007%2f978-981-97-0975-5_28&partnerID=40&md5=fa4c27e07b7cd3cc1ca110e6e0238922