Research Papers

Foundry Data Analytics to Identify Critical Parameters Affecting Quality of Investment Castings

[+] Author and Article Information
Amit Sata

Mechanical Engineering Department,
Faculty of Engineering,
Marwadi Education Foundation
Group of Institutes,
Rajkot 360003, Gujarat, India

B. Ravi

Institute Chair Professor
Mechanical Engineering Department,
Indian Institute of Technology Bombay,
Mumbai 400076, Maharashtra, India

Manuscript received March 20, 2018; final manuscript received August 22, 2018; published online November 19, 2018. Assoc. Editor: Siu-Kui Au.

ASME J. Risk Uncertainty Part B 5(1), 011010 (Nov 19, 2018) (7 pages) Paper No: RISK-18-1014; doi: 10.1115/1.4041296 History: Received March 20, 2018; Revised August 22, 2018

Investment castings are used in industrial sectors including automobile, aerospace, chemical, biomedical, and other critical applications; they are required to be of significant quality (free of defects and possess the desired range of mechanical properties). In practice, this is a big challenge, since there are large number of parameters related to process and alloy composition are involved in process. Also, their values change for every casting, and their effect on quality is not very well understood. It is, however, difficult to identify the most critical parameters and their specific values influencing the quality of investment castings. This is achieved in the present work by employing foundry data analytics based on Bayesian inference to compute the values of posterior probability for each input parameter. Computation of posterior probability for each parameter in turn involves computation of local probability (LP), prior odd, conditional probability (CP), joint probability (JP), prior odd, likelihood ratio (LR) as well as posterior odd. Computed value of posterior probability helps (parameters are considered to be critical if the value of posterior probability is high) in identifying critical parameter and their specific range of values affecting quality of investment castings. This is demonstrated on real-life data collected from an industrial foundry. Controlling the identified parameters within the specific range of values resulted in improved quality. Unlike computer simulation, artificial neural networks (ANNs), and statistical methods explored by earlier researchers, the proposed approach is easy to implement in industry for controlling and optimizing the parameters to achieve castings that are defect free as well as in desired range of mechanical properties. The current work also shows the way forward for building similar systems for other casting and manufacturing processes.

Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.


Jolly, M. , 2002, “ How Well Do Reality and Virtual Casting Match? State of Art Review,” Int. J. Cast Met. Res., 56(5), pp. 303–313. [CrossRef]
Ravi, B. , and Joshi, D. , 2007, “ Feedability Analysis and Optimization Driven by Casting Simulation,” Indian Foundry J., 53(6), pp. 71–78. https://www.indianfoundry.org/archived-articles.php
Buhner, J. F. , 2007, “ Advances in the Prevention of Investment Casting Defects Assisted by Computer Simulation,” Santa Fe Symposium on Jewellary Manufacturing Technology, pp. 149–172.
Cleary, P. W. , 2010, “ Extension of SPH to Predict Feeding, Freezing and Defect Creation in Low Pressure Die Casting,” Appl. Math. Modell., 34(11), pp. 3189–3201. [CrossRef]
Roy, R. K. , 2001, Design of Experiments Using the Taguchi Approach: 16 Steps to Product and Process Improvement, 1st ed., Wiley, New York.
Seifeddine, S. , Wessen, M. , and Svensson, I. , 2006, “ Use of Simulation to Predict Microstructure and Mechanical Properties in An as Cast Aluminum Cylinder Head—Comparison With Experiments,” Metall. Sci. Technol., 24(2), pp. 26–32. http://www.gruppofrattura.it/ors/index.php/MST/article/view/1121
Schneider, M. , Schaefer, W. , Sjölander, E. , Seiffeddine, S. , and Svensson, I L. , 2012, “ Simulation of Microstructure and Mechanical Properties of Aluminum Components During Casting and Heat Treatment,” Mater. Sci. Eng., 33, pp. 1–8.
Guo, J. , and Sammonds, M. T. , 2007, “ Microstructure and Mechanical Properties Prediction for Ti-Based Alloys,” J. Manuf. Eng. Perform., 16(6), pp. 680–684. [CrossRef]
Perzyk, M. , and Kochanski, A. , 2003, “ Detection of Causes of Casting Defects Assisted by Artificial Neural Network,” Proc. Inst. Eng.: Part B, 217(9), pp. 1279–1284. [CrossRef]
Zheng, J. , Wang, Q. , Zhao, P. , and Wu, C. , 2009, “ Optimization of High-Pressure Die-Casting Process Parameters Using Artificial Neural Network,” Int. J. Adv. Manuf. Technol., 44(7–8), pp. 667–674. [CrossRef]
Sata, A. , 2014, “ Investment Casting Defect Prediction Using Neural Network and Multivariate Regression Along With Principal Component Analysis,” Int. J. Manuf. Res., 11(4), pp. 356–373. [CrossRef]
Perzyk, M. , and Kochanski, A. , 2001, “ Prediction of Ductile Iron Quality by Artificial Neural Networks,” J. Process. Technol., 109(3), pp. 305–307. [CrossRef]
Dobrzanski, L. A. , and Krol, M. , 2010, “ Neural Network Application for Prediction Mechanical Properties of Mg-Al-Zn Alloys,” Arch. Comput. Mater. Sci. Surf. Eng., 2(4), pp. 181–188. http://www.archicmsse.org/index.php?id=76
Krupinski, M. , and Tanski, T. , 2012, “ Prediction of Mechanical Properties of Cast Mg-Al-Zn Alloys,” Arch. Mater. Sci. Eng., 56(2), pp. 30–36.
Sata, A. , and Ravi, B. , 2014, “ Comparison of Some Neural Network and Multivariate Regression for Predicting Mechanical Properties of Investment Casting,” Int. J. Mater. Eng. Perform., 23(8), pp. 2953–2964. [CrossRef]
Perzyk, M. , Kochanski, A. , Kozlowski, J. , Soroczynski, A. , and Biernacki, R. , 2014, “ Comparison of Data Mining Tools for Significance Analysis of Process Parameters in Applications to Process Fault Diagnosis,” Inf. Sci., 259, pp. 380–392. [CrossRef]
Perzyk, M. , Biernacki, R. , and Kozlowski, J. , 2008, “ Data Mining in Manufacturing: Significance Analysis of Process Parameters,” Proc. Inst. Mech. Eng., Part B, 222(11), pp. 1503–1516. [CrossRef]
Kershaw, J. , and Ardekani, B. , 1999, “ Application of Bayesian Inference to fMRI Data Analysis,” IEEE Trans. Med. Imaging, 18(12), pp. 1138–1153. [CrossRef] [PubMed]
Ransing, R. S. , Srinivasan, M. N. , and Lewis, R. W. , 1995, “ ICADA: Intelligent Computer Aided Defect Analysis for Castings,” J. Intell. Manuf., 6(1), pp. 29–40. [CrossRef]
Ole, J. , Darwiche, A. , and Uckun, S. , 2008, “ Sensor Validation Using Bayesian Networks,” Ninth International Symposium on Artificial Intelligence Robotics, and Automation in Space, Los Angeles, CA, Feb. 25–29, p. 8.
Kalinowski, M. , Mendes, E. , Card, D. N. , and Travassos, G. H. , 2010, Applying DPPI: A Defect Causal Analysis Approach Using Bayesian Networks, Vol 6156, In: Ali Babar M., Vierimaa M., Oivo M., eds., Lecture Notes in Computer Science, Springer, Berlin/Heidelberg.
Alaeddini, A. , and Dogan, I. , 2011, “ Using Bayesian Networks for Root Cause Analysis in Statistical Process Control,” Expert Syst. Appl., 38(9), pp. 11230–11243. [CrossRef]
Li, B. , Ting, H. , and Fuyong, K. , 2013, “ Fault Diagnosis Expert System of Semi-Conductor Manufacturing Equipment Using Bayesian Network,” Int. J. Comput. Integr. Manuf., 26(12), pp. 1161–1171. [CrossRef]
Sata, A. , and Ravi, B. , 2017, “ Bayesian Inference-Based Investment Casting Defect Analysis for Industrial Application,” Int. J. Adv. Manuf. Technol., 90(9–12), pp. 3301–3315. [CrossRef]


Grahic Jump Location
Fig. 2

Industrial casting and sample test bar as per ASTM A370 guidelines

Grahic Jump Location
Fig. 3

Computation of posterior probability



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Articles from Part A: Civil Engineering

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In