Assessment of end user expectations by enhancing quality standards in Indian ports: Volume 1

This paper presents an Internet of Things powered predictive maintenance system as part of its pioneering research. Its aim is to improve India's port infrastructure operating efficiency. A Bayesian-tuned Long Short-Term Memory defect predictive network and Fuzzy Analytic Hierarchy Process (Fuzzy AHP) decision model for efficient maintenance planning are incorporated in the proposed system. The system outperforms traditional models by recording a 99.47% success rate in predicting equipment failure through the application of real-time data from sensors. The optimization framework also enhances decision-making by cutting maintenance costs by 41.57%, lowering delays by 86.36%, and enhancing the accuracy of maintenance schedules by 99.28%, all of which are Fuzzy AHP-based. Effective cargo management and smooth port operations are assured through the interfacing of deep learning models adapted to changing contexts, real-time tracking, and multi-criterion decision-making. This smart predictive maintenance system represents a paradigmatic shift in efficient use of resources and prudent administration of ports in that it is less expensive, more adaptable, and more extensible than such more traditional modes of port governance.