首页|Studies from Marche Polytechnic University Further Understanding of Machine Lear ning (A Cost Modelling Methodology Based On Machine Learning for Engineered-to-o rder Products)
Studies from Marche Polytechnic University Further Understanding of Machine Lear ning (A Cost Modelling Methodology Based On Machine Learning for Engineered-to-o rder Products)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting from Ancona, Italy, by News Rx journalists, research stated, "Recent scientific studies are targeted at appl ying and assessing the effectiveness of Machine Learning (ML) approaches for cos t estimation during the preliminary design phases. To train ML prediction models,comprehensive and structured datasets of historical data are required." The news correspondents obtained a quote from the research from Marche Polytechn ic University, "This solution is inapplicable when such information is unavailab le or sparse due to the lack of structured datasets. For engineered-to-order pro ducts, the number of historical records is often limited and strongly influenced by different purchasing or manufacturing strategies, thus requiring complex nor malisation of such data. This method overcomes the above limitations by presenti ng an ML-based cost modelling methodology for the conceptual design that is appl icable even when historical data are insufficient to train the prediction algori thms. The training dataset is generated through an analytical and automatic soft ware tool for manufacturing cost estimation. Such a tool, starting from a 3D mod el of a product, can quickly and autonomously assess the related cost in differe nt scenarios. An extensive and structured training dataset can be easily generat ed. The proposed methodology was based on CRISP-DM (Cross Industry Standard Proc ess for Data Mining). Cost engineers of an Oil & Gas company used the method to develop parametric cost models for discs and spacers of an axial c ompressor. The solution guarantees lower error (7% vs 9% ) and significant time-saving (minutes instead of hours) than estimations based on other approaches."
AnconaItalyEuropeCyborgsEmerging TechnologiesEngineeringMachine LearningMarche Polytechnic University
NETL
NSTL
