Innovation Owner
Mr. PURIPAT PRINGPPATTANAPONG
Student
Details
This project enhances the efficiency of the Hydrogen Manufacturing Unit (HMU-2) and PSA-3 unit by integrating Machine Learning models with AVEVA Pro/II. The approach improved prediction accuracy, resulting in an additional 7.8 tons of hydrogen production per day and 850,966.23 Baht in annual profit.
This cooperative education project aims to enhance the efficiency of Hydrogen Manufacturing Unit 2 (HMU-2) and Pressure Swing Adsorption 3 (PSA-3) by using AVEVA Pro/II process modeling and a Machine Learning model for process simulation. Key findings include:
- The AVEVA Pro/II model showed deviations exceeding the company’s 10% limit.
- A Random Forest-based Machine Learning model achieved high accuracy with R-squared values of 0.98 and 0.88.
- Hydrogen flow rate deviations were reduced to 4.75% and 1.35% for different production rates.
- Optimization via the model increased hydrogen production by 7.8 tons per day and generated an additional annual profit of 850,966.23 Baht.
Objective
The objectives are to compare the accuracy of AVEVA Pro/II against Machine Learning, develop predictive models for product quality, and optimize production parameters to maximize hydrogen output and overall benefits.
- To compare the accuracy between the AVEVA Pro/II program and Machine Learning techniques.
- To develop a predictive model using Machine Learning for advance product quality forecasting.
- To analyze and improve production efficiency by identifying parameters that yield maximum hydrogen output and overall benefits.