Details of Grant 

EPSRC Reference:	GR/R89912/01
Title:	Learning cause and effect relationships from example- The finite element way
Principal Investigator:	Ransing, Dr RS
Other Investigators:	Lewis, Professor RW
Researcher Co-Investigators:
Project Partners:	Rolls-Royce Plc (UK) Swansea University
Department:	Mechanical Engineering
Organisation:	Swansea University
Scheme:	Standard Research (Pre-FEC)
Starts:	17 June 2002	Ends:	16 December 2005	Value (£):	159,944
EPSRC Research Topic Classifications:	Artificial Intelligence Intelligent & Expert Systems
EPSRC Industrial Sector Classifications:	Aerospace, Defence and Marine
Related Grants:
Panel History:
Summary on Grant Application Form
SummaryDescribe the proposed research in about 200 words.Every day, foundries manufacture a large number of castings and, daily, provide a solution to manufacturing process problems, or study rejections that might have occurred. In other words, valuable information is generated within the foundry every time a casting is poured.The proposed research aims to focus on investigating computer-based techniques to use this information in learning cause and effect relationship. The cause and effect relationship is generally complex and highly interlinked for many manufacturing processes. Identification of the degree of influence of a cause on the occurrence of a defect is one of the most difficult task in a diagnostic process and the highly interlinked causal relationship further complicates the problem. An expert system approach requires the knowledge of degree of influence of each cause on the occurrence of every defect where as neural network techniques learn from examples to perform diagnosis. However, neural network techniques have some serious limitations which have constrained their use in analysing cause and effect relationships. A novel concept from the Finite Element method will be explored in this research so that the degree of influence of each cause on the occurrence of a defect or a combination of defects can be quantified based on past diagnostic examples.This is a novel and originial approach and is of direct relavance to the manufacturing industry. The research is generic and has potential application in medical diagnosis to improve patient care in NHS.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.swan.ac.uk