Inverting Prediction Models in Micro Production for Process Design
Databased prediction models are used to estimate a possible outcome for previously unknown production parameters. These forward models enable to test new production designs and parameters virtually before applying them in the real world. Cause-effect networks are one way to generate such a predictio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2018-01-01
|
| Series: | MATEC Web of Conferences |
| Subjects: | |
| Online Access: | https://doi.org/10.1051/matecconf/201819015007 |
| _version_ | 1818446019968368640 |
|---|---|
| author | Gralla Phil Piotrowska-Kurczewski Iwona Rippel Daniel Lütjen Michael Maaß Peter |
| author_facet | Gralla Phil Piotrowska-Kurczewski Iwona Rippel Daniel Lütjen Michael Maaß Peter |
| author_sort | Gralla Phil |
| collection | DOAJ |
| description | Databased prediction models are used to estimate a possible outcome for previously unknown production parameters. These forward models enable to test new production designs and parameters virtually before applying them in the real world. Cause-effect networks are one way to generate such a prediction model. Multiple inputs and stages are being connected to one large prediction model. The functional behaviour and correlation of inputs as well as outputs is obtained through data based learning. In general, these models are non-linear and not invertible, especially for micro cold forming processes. While already being useful in process design, such models have their highest impact if inverted to find process parameters for a given output. Combining methods from the mathematical field of inverse problems as well as machine learning, a generalized inverse can be approximated. This allows finding process parameters for a given output without inverting the model directly but still using inherit information of the forward model. In this work, Tikhonov functionals are used to perform a parameter identification. The classical approach is altered by changing the discrepancy term to incorporate tolerances. Thereby, small deviations of a certain pattern are being neglected and the parameter finding process is being stabilized. In addition, different types of regularization are taken into consideration. Besides theoretical aspects of this method, examples are provided to demonstrate advantages and boundaries of an application for the process design in micro cold forming processes. |
| first_indexed | 2024-12-14T19:41:04Z |
| format | Article |
| id | doaj.art-d4ddc81dc3364c75833cd9295e03582b |
| institution | Directory Open Access Journal |
| issn | 2261-236X |
| language | English |
| last_indexed | 2024-12-14T19:41:04Z |
| publishDate | 2018-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | MATEC Web of Conferences |
| spelling | doaj.art-d4ddc81dc3364c75833cd9295e03582b2022-12-21T22:49:43ZengEDP SciencesMATEC Web of Conferences2261-236X2018-01-011901500710.1051/matecconf/201819015007matecconf_icnft2018_15007Inverting Prediction Models in Micro Production for Process DesignGralla PhilPiotrowska-Kurczewski IwonaRippel DanielLütjen MichaelMaaß PeterDatabased prediction models are used to estimate a possible outcome for previously unknown production parameters. These forward models enable to test new production designs and parameters virtually before applying them in the real world. Cause-effect networks are one way to generate such a prediction model. Multiple inputs and stages are being connected to one large prediction model. The functional behaviour and correlation of inputs as well as outputs is obtained through data based learning. In general, these models are non-linear and not invertible, especially for micro cold forming processes. While already being useful in process design, such models have their highest impact if inverted to find process parameters for a given output. Combining methods from the mathematical field of inverse problems as well as machine learning, a generalized inverse can be approximated. This allows finding process parameters for a given output without inverting the model directly but still using inherit information of the forward model. In this work, Tikhonov functionals are used to perform a parameter identification. The classical approach is altered by changing the discrepancy term to incorporate tolerances. Thereby, small deviations of a certain pattern are being neglected and the parameter finding process is being stabilized. In addition, different types of regularization are taken into consideration. Besides theoretical aspects of this method, examples are provided to demonstrate advantages and boundaries of an application for the process design in micro cold forming processes.https://doi.org/10.1051/matecconf/201819015007Predictive ModelOptimizationProcess Control |
| spellingShingle | Gralla Phil Piotrowska-Kurczewski Iwona Rippel Daniel Lütjen Michael Maaß Peter Inverting Prediction Models in Micro Production for Process Design MATEC Web of Conferences Predictive Model Optimization Process Control |
| title | Inverting Prediction Models in Micro Production for Process Design |
| title_full | Inverting Prediction Models in Micro Production for Process Design |
| title_fullStr | Inverting Prediction Models in Micro Production for Process Design |
| title_full_unstemmed | Inverting Prediction Models in Micro Production for Process Design |
| title_short | Inverting Prediction Models in Micro Production for Process Design |
| title_sort | inverting prediction models in micro production for process design |
| topic | Predictive Model Optimization Process Control |
| url | https://doi.org/10.1051/matecconf/201819015007 |
| work_keys_str_mv | AT grallaphil invertingpredictionmodelsinmicroproductionforprocessdesign AT piotrowskakurczewskiiwona invertingpredictionmodelsinmicroproductionforprocessdesign AT rippeldaniel invertingpredictionmodelsinmicroproductionforprocessdesign AT lutjenmichael invertingpredictionmodelsinmicroproductionforprocessdesign AT maaßpeter invertingpredictionmodelsinmicroproductionforprocessdesign |