Intelligent Decision Support System (iDSS) for Manufacturing Data Corpus

People in industries like manufacturing require, use, and produce knowledge on a daily basis. Tremendous quantity of data with difference in formats, structures and linkages need to be cautiously explored. However, the most valuable knowledge is not easy to identify or share because it is deep within the minds of experts. In manufacturing, it is very common to see dashboards on business performance, however, very few literatures available on technical knowledge management. Technical knowledge of an expert can be effectively managed and transferred by having an interface or dashboard that provides adequate information for the learners. Hence, this project aims to establish intelligent Decision Support System (iDSS) that can strategically manage, transfer, and share valuable knowledge of experts within the manufacturing organization based on machine learning and deep learning models. This study used English text data that is properly phrased to build a deep learning model in Natural Language Processing (NLP) for maintenance factory reports. As a result, interactive visualizations are presented to aid decision-makers in making knowledgeable decisions that includes the display of failure diagnostic and Named Entity Recognition (NER). These findings may provide troubleshooting insights as an assistance to new employees and deliver a precise management of decisions in looking back in history and preparing ahead. The investigation of this study will be further explored for complex numeric parameters from sensors data, integration of predictive maintenance in the dashboard, and utilizing a more sophisticated training model for better predictions.