Analytical research of artificial intelligent models for machining industry under varying environmental strategies: An industry 4.0 approach

Abstract

Since the introduction of Industry 4.0, manufacturing industries have adopted smarter automation systems enabling better interconnection amongst various aspects of the production industry. Application of industry 4.0 furnishes better performance and efficiency with improved reliability and robustness. The present research provides a novel framework which takes in consideration the complexity and flexibility of the working environment within the factory premises, previously not explored. Smart systems equipped with sensors and communicators are responsible for monitoring information and detecting malfunctions pre-hand which eventually boosts the system performance. Furthermore, the research explores the concept of predictive maintenance in industry 4.0 setup which apprehends any system failure based on atmospheric related changes. A novel algorithm is explored in this research which takes in consideration multisource diverse dataset based on varying environmental conditions and simultaneously furnishing inputs for predictive maintenance in Industry 4.0 implementation, thereby providing a transparent and effective manufacturing method. The framework for Industry 4.0 is validated and deemed feasible with quantitative comparison with previous prediction models which can further predict any future malfunctions in the industrial machines. The productivity values are validated with models developed with the help of intelligent hybrid prediction techniques such as adaptive neuro-fuzzy inference system (ANFIS) and response surface methodology (RSM). The input parameters considered are atmospheric conditions whereas the required output response is productivity of the machines. Error rates were evaluated lowest error rate for triangular membership functions for both machining models.