INTEGRATING DATA ANALYTICS AND SIMULATION METHODS TO SUPPORT MANUFACTURING DECISION MAKING.

Area of Science:

• Manufacturing Systems Engineering
• Data Science
• Operations Research

Background:

• Modern manufacturing relies on smart devices and sensors for performance monitoring and data collection.
• Complex systems generate vast, varied data, overwhelming human analysis and traditional simulation methods.
• Informed decision-making requires systematic approaches to handle large-scale, real-time operational data.

Purpose of the Study:

• To propose a methodology integrating data analytics and simulation for enhanced decision-making in smart manufacturing.
• To identify critical parameters influencing system performance from collected sensor data.
• To develop optimized simulation scenarios using extracted parameters for improved operational insights.

Main Methods:

• Data analytics techniques for parameter extraction from sensor data.
• Development of simulation input scenarios based on identified critical parameters.
• Optimization of simulation outputs for guided decision-making in manufacturing operations.
• Review of relevant standards for data collection, simulation, and system interfaces.

Main Results:

• A methodology was developed and demonstrated on a machine shop case study.
• Key parameters significantly affecting manufacturing system performance were successfully extracted.
• Optimized simulation inputs and outputs were generated, leading to informed decisions.
• Candidate standards for data, simulation, and interfaces were reviewed.

Conclusions:

• The proposed methodology effectively leverages data analytics and simulation for smart manufacturing.
• This approach addresses the challenge of large-scale data in complex operational environments.
• It provides a systematic framework for improving decision-making and system optimization.