Authors:
J. Sturek
;
S. Ramakrishnan
;
P. Nagula
and
K. Srihari
Affiliation:
Binghamton University, United States
Keyword(s):
Robotic Dispensing System, Failure Mode Effects and Analysis (FMEA), Reliability Prediction.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence and Decision Support Systems
;
Enterprise Information Systems
;
Strategic Decision Support Systems
Abstract:
Decision Support Systems (DSS) are information systems designed to support individual and collective
decision-making. This research presents the development of a DSS to facilitate the prediction of the reliability of a Robotic Dispensing System (RDS). While it is extremely critical for design teams to identify the potential defects in the product before releasing them to the customers, predicting reliability is extremely difficult due to the absence of actual failure data. Design teams often adopt tools such as Failure Mode Effects and Analysis (FMEA) to analyze the various failure modes in the product. There are commercial softwares that facilitate predicting reliability and conducting FMEA. However, there are limited approaches that combine these two critical aspects of product design. The objective of this research is to develop a DSS that would help design teams track the overall system reliability, while concurrently using the data from the alpha testing phase to perform the F
MEA. Hence, this DSS is capable of calculating the age-specific reliability value for a Robotic Dispensing System (RDS), in addition to storing the defect information, for the FMEA process. The Risk Priority Number (RPN) calculated using the data gathered serves as the basis for the design team to identify the modifications to the product design. The tool, developed in Microsoft Access®, would be subsequently utilized to track on-field performance of the RDS. This would facilitate continuous monitoring of the RDS from the customer site, especially during its “infant mortality” period.
(More)