Machine Learning Techniques and Big Data Tools in Design and Manufacturing

Abstract

Smart manufacturing attempts to combine big data, sophisticated analytics, and high-performance computing into outdated systems and processes in order to develop highly configurable, higher-quality products at lower prices. A smart factory, as opposed to a typical factory, monitors equipment conditions using interoperable information and communications technologies, intelligent automation systems, and sensor networks. In this chapter, we will look at the role of big data in enabling smart manufacturing, from data collection to enhancing existing data analytic tools for analyzing manufacturing data. Both descriptive and predictive analysis will be provided by the analytic approaches. In this study, a new feature selection with big data classification model is developed in the MapReduce environment. The data is categorized and analyzed using Naive Bayes, Logistic Regression, and XGBoost classifier models. Data-driven qualification assistance minimizes the high degree of arbitrariness generated by professional skills and experiences by incorporating business analytics in the form of machine learning into lead and opportunity management. By improving the predictive accuracy, we used FireFly Algorithm feature section scheme. We train and test the supervised algorithms to assess and compare the prediction performances of the induced classifiers. These proposed approaches might considerably enhance the forecast of lead and opportunity buy likelihood. A wide range of simulation analyses take place on the benchmark dataset and the results are inspected under various aspects. The experimental outcome highlighted the betterment of the proposed model over the recent methods in terms of different measures.

Topics & Concepts