OPEN ACCESS
A methodology for goal-oriented active learning with local model networks (LMNs) is proposed. It is applied for the generation of training data for a computational fluid dynamics (CFD) metamodel. The used metamodel is an LMN trained with data originating from CFD simulations. This metamodel describes the total-to-static efficiency for a given design point, defined by the pressure rise at a specific volume flow rate, depending on geometrical parameters of an impeller of centrifugal fans. The goal- oriented nature originates from three main targets that are addressed simultaneously during the active learning procedure. (I) The concentration on possibly optimal geometries and (II) the focus on areas in the input space where the metamodel’s performance is considered to be worst. Additionally, (III) new measurements should differ from already simulated geometries as much as possible. With these goals three important issues in modeling are addressed simultaneously: (I) optimality, (II) model bias, (III) model variance/uniformly space-filling property. In order to fulfill all goals, special properties of LMNs are utilized (embedded approach). Through the structure of LMNs, it is possible to assign local model errors to specific areas in the input space. New measurements are preferably placed in such high-error regions, while concentrating on presumably optimal geometries that differ most from the ones already available in the training data. In the field of fluid machinery, the range of achievable design points is usually identified by the Cordier diagram. While the design points obtained in the passive learning phase fairly agree with the standard Cordier diagram, an extension of achievable design points was observed due to the proposed goal-oriented learning strategy. In addition, the total-to-static efficiency could be improved in some areas of the Cordier diagram.
active learning, aerodynamic optimization, design of experiments, experimental modeling, impeller of centrifugal fans, metamodeling
[1] Fedorov, V.V., Theory of Optimal Experiments, Elsevier, 1972. https://doi.org/10.2307/2334826
[2] Atkinson, A., The usefulness of optimum experimental designs. Journal of the Royal Statistical Society Series B (Methodological), pp. 59–76, 1996. https://doi.org/10.2307/2344398
[3] Fedorov, V.V. & Hackl, R., Model-Oriented Design of Experiments, Volume 125 of Lecture Notes in Statistics, Springer Science & Business Media, 2012. https://doi.org/10.1007/978-1-4612-0703-0
[4] Jin, R., Chen, W. & Sudjianto, A., On sequential sampling for global metamodeling in engineering design. ASME 2002 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, American Society of Mechanical Engineers, pp. 539–548, 2002. https://doi.org/10.1115/DETC2002/DAC-34092
[5] Wang, G.G. & Shan, S., Review of metamodeling techniques in support of engineering design optimization. Journal of Mechanical Design, 129(4), pp. 370–380, 2007. https://doi.org/10.1115/1.2429697
[6] Cohn, D.A., Minimizing statistical bias with queries. Technical report, DTIC Document, 1995.
[7] Cohn, D.A., Neural network exploration using optimal experiment design. Neural Networks, 9(6), pp. 1071–1083, 1996.https://doi.org/10.1016/0893-6080(95)00137-9
[8] Cohn, D.A., Ghahramani, Z. & Jordan, M.I., Active learning with statistical models.Journal of Artificial Intelligence Research, 4, pp. 129–145, 1996.
[9] MacKay, D.J., Information-based objective functions for active data selection. Neural Computation, 4(4), pp. 590–604, 1992.https://doi.org/10.1162/neco.1992.4.4.590
[10] Settles, B., Active learning literature survey. University of Wisconsin, Madison, 52, pp. 55–66, 2010.
[11] Hartmann, B. & Nelles, O., Adaptive test planning for the calibration of combustion engines - methodology. Design of Experiments (DoE) in Engine Development, pp. 1–16, 2013.
[12] Nelles, O., Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models, Springer, 2001.
[13] Hartmann, B., Lokale Modellnetze zur Identifikation und Versuchsplanung nichtlin- earer Systeme. Ph.D. thesis, Universitat Siegen, 2014.
[14] Murray-Smith, R. & Johansen, T., Local learning in local model networks. Artificial Neural Networks, 1995, Fourth International Conference on, IET, pp. 40–46, 1995. https://doi.org/10.1049/cp:19950526
[15] Nelles, O., Axes-oblique partitioning strategies for local model networks. IEEE Inter- national Symposium on Intelligent Control, Munich, Germany, pp. 2378–2383, 2006.
[16] Akaike, H., A new look at the statistical model identification. Automatic Control, IEEE Transactions on, 19(6), pp. 716–723, 1974. https://doi.org/10.1109/TAC.1974.1100705
[17] Bamberger, K., Aerodynamic Optimization of Low-Pressure Axial Fans. Ph.D. thesis, University of Siegen, 2015.
[18] Ebert, T., Fischer, T., Belz, J., Heinz, T., Kampmann, G. & Nelles, O., Extended deterministic local search algorithm for maximin latin hypercube designs. IEEE Symposium on Computational Intelligence in Control and Automation (CICA), Cape Town, South Africa, pp. 375–382, 2015.https://doi.org/10.1109/SSCI.2015.63
[19] Cordier,O.,AhnlichkeitsbedingungenfurStromungsmaschinen.Brennstoff-Warme-Kraft (BWK), 5(10), pp. 337–340, 1953.
[20] Willinger, R., Das CORDIER-Diagramm fur Stromungsarbeitsmaschinen: Eine theo- retische Begriindung mittels Stufenkennlinien. VDI-Berichte, 2112, pp. 17–28, 2010.
[21] Willinger, R., Theoretical interpretation of the CORDIER-lines for squirrel-cage and cross-flow fans. Proceeding ASME TurboExpo, Copenhagen, Denmark, pp. 675–684, 2012.https://doi.org/10.1115/GT2012-68186
[22] Willinger, R. & Kohler, M., Influence of Blade Loading Criteria and Design Limits on the Cordier-Line for Axial Flow Fans. Proceeding ASME TurboExpo, Dusseldorf, Germany, 2014.https://doi.org/10.1115/GT2014-25140
[23] Bommes, L., Fricke, J. & Grundmann, R., Ventilatoren. Vulkan Verlag, Essen, 2003.
[24] Bamberger, K., Belz, J., Carolus, T. & Nelles, O., Aerodynamic optimization of centrifugal fans using CFD-trained meta-models. 16th International Symposium on Transport Phenomena and Dynamics of Rotating Machinery (ISROMAC), Hawaii, USA, 2016.
[25] Hartmann, B., Ebert, T. & Nelles, O., Model-based design of experiments based on local model networks for nonlinear processes with low noise levels. American Control Conference (ACC), IEEE, pp. 5306–5311, 2011.