Machine learning techniques have been widely applied to production processes with the aim of improving product quality, supporting decision-making, or implementing process diagnostics. These techniques proved particularly useful in the investment casting manufacturing industry, where huge variety of heterogeneous data, related to different production processes, can be gathered and recorded but where traditional models fail due to the complexity of the production process. In this study, we apply Support Vector Representation Machine to production data from a manufacturing plant producing turbine blades through investment casting. We obtain an instance ranking that may be used to infer proper values of process parameter set-points.
We account for the problem of optimal control of ceramic mould manufacturing in lost wax cast processes with the aid of a mixed linear algebraic-statistical approach based on the employment of Singular Value Decomposition (SVD) and Neural Networks (NN).We consider the peculiar aspect of minimizing ceramic inclusions occurrence in equiaxed superalloy turbine components which are manufactured resorting to gravitational pouring. The optimization consists in finding optimal extrema of scalar and/or vectorial functions of the type Rk->Rmi.e. Key Process Variable domain (KPV) vs. Target Variable domain (TV) over a large set of experimental data affected by acquisition noise leading to a typical sparse multiblock array.The goal of the work consists in the assessment of possible significant statistical multivariate correlations amongst the KPV and TV when the dimension of domain space, k, has an order of magnitude of tens, in the presence of quasi-rank deficient input matrix.
he reduction of the scraps is fundamental to achieve goals of competitiveness. Some key parameters have a direct influence on any process and they need to be predicted and taken under control. This paper present an approach ) is to develop a robust monitoring solution of the ceramic shell manufacture that will be able to determine a significant reduction of the inclusion scraps (due the ceramic shell) of the superalloy components. The control will be obtained by processing data coming both from sensors and laboratory measured values. The sensor data come from the new equipment of the Europea Microfusioni Aerospaziali SpA (EMA) and have been tested and used to develop the EMA demonstrator within the EC FP7 Project on "Intelligent Fault Correction and self-Optimizing Manufacturing systems-IFaCOM". The sensor data will merge the data measured in the EMA laboratories and both the values will concur to create the sensor fusion pattern vector, which will be used to feed an automatic system for the prediction of the process parameters. The automatic system will be implemented using cognitive paradigms, in particular Artificial Neural Networks, that will combine both data. The first testing phase will predict the number of blades with inclusions. It will provide a first idea of the correlation between the input, as a matrix composed by the sensor fusion pattern vectors per each worked blade, and the outputs, as a vector of rejected blades on the total. Moreover, this work will be the basis to implement a predictive system to estimate which is the reference range of each working parameter
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.