"Synthetic Green Sand Process Dataset: Sand Temperature, Water Addition, Compactibility, and Mould Breakage"
- 1. Bharati Vidyapeeth's College of Engineering,Kolhapur
Description
This dataset is a synthetic green sand process dataset created for research, teaching, and modeling in foundry engineering. It simulates 1,500 foundry sand mixer batches with key process variables such as sand temperature, ambient humidity, return sand moisture, water addition, clay and additive percentages, and transfer points. Control outputs include compactibility, permeability, green compression strength, and mold hardness. Quality outcomes are represented through mould breakage events, breakage reasons, and indicative casting defect counts (burn-on and rat tails).
The dataset reflects realistic industrial behavior of green sand systems, including the relationships between water addition, compactibility, and sand temperature, modeled from standard foundry practice. Since it is synthetic, it can be freely used for statistical process control, Six Sigma studies, machine learning applications, or teaching of foundry process optimization without confidentiality concerns.
Files
Files
(150.4 kB)
| Name | Size | |
|---|---|---|
|
md5:45019c15bf4d483312f21a40e65d3b06
|
150.4 kB | Download |
Additional details
Dates
- Created
-
2025-09-02This dataset is a synthetic green sand process dataset developed for research, teaching, and modeling in foundry engineering. It contains 1,500 simulated foundry sand mixer batches with key process parameters such as sand temperature, ambient humidity, return sand moisture, water addition, clay and additive percentages, and transfer points. Output variables include compactibility, permeability, green compression strength, and mold hardness. Quality outcomes are represented through mould breakage events, reasons for breakage, and casting defect indicators such as burn-on and rat tails. The dataset is designed to reflect realistic industrial behavior of green sand systems, including the interdependence between water addition, compactibility, and sand temperature, based on standard foundry practices. Since it is synthetic, it avoids confidentiality issues and can be freely applied for statistical process control, Six Sigma projects, machine learning applications, or educational purposes in foundry process optimization.
References
- Beeley, P. (2001). Foundry Technology (2nd ed.). Butterworth-Heinemann. Jain, P. L. (2003). Principles of Foundry Technology (4th ed.). Tata McGraw-Hill. American Foundry Society (AFS). (2016). AFS Mold & Core Test Handbook. Des Plaines, Illinois, USA. Campbell, J. (2015). Complete Casting Handbook: Metal Casting Processes, Metallurgy, Techniques and Design (2nd ed.). Butterworth-Heinemann. Nayak, G., & Suman, S. (2020). "Prediction of green sand mould properties using machine learning techniques." International Journal of Cast Metals Research, 33(5), 252–262. Orlowicz, A. W., Mróz, M., & Tupaj, M. (2019). "Effect of Moisture Content on Properties of Green Moulding Sands." Archives of Foundry Engineering, 19(4), 49–54.