This paper presents an automated tool for estimating assembly times of products based on a three step process: connectivity graph generation from assembly mate information, structural complexity metric analysis of the graph, and application of the complexity metric vector to predictive artificial neural network models. The tool has been evaluated against different training set cases, suggesting that partially defined assembly models and training product variety are critical characteristics. Moreover, the tool is shown to be robust and insensitive to different modeling engineers. The tool has been implemented in a commercial CAD system and shown to yield results of within ±25% of predicted values. Additional extensions and experiments are recommended to improve the tool.
Assembly Time Estimation: Assembly Mate Based Structural Complexity Metric Predictive Modeling
Clemson, SC 29634-0921
Contributed by the Computers and Information Division of ASME for publication in the JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINNERING. Manuscript received September 24, 2012; final manuscript received October 12, 2013; published online January 22, 2014. Editor: Bahram Ravani.
- Views Icon Views
- Share Icon Share
- Cite Icon Cite
- Search Site
Owensby, J. E., and Summers, J. D. (January 22, 2014). "Assembly Time Estimation: Assembly Mate Based Structural Complexity Metric Predictive Modeling." ASME. J. Comput. Inf. Sci. Eng. March 2014; 14(1): 011004. https://doi.org/10.1115/1.4025808
Download citation file:
- Ris (Zotero)
- Reference Manager