Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals
The Directed Energy Deposition process is used in a wide range of applications including the repair, coating or modification of existing structures and the additive manufacturing of individual parts. As the process is frequently applied in the aerospace industry, the requirements for quality assuran...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/8/3955 |
| _version_ | 1797437009377099776 |
|---|---|
| author | Angelina Marko Stefan Bähring Julius Raute Max Biegler Michael Rethmeier |
| author_facet | Angelina Marko Stefan Bähring Julius Raute Max Biegler Michael Rethmeier |
| author_sort | Angelina Marko |
| collection | DOAJ |
| description | The Directed Energy Deposition process is used in a wide range of applications including the repair, coating or modification of existing structures and the additive manufacturing of individual parts. As the process is frequently applied in the aerospace industry, the requirements for quality assurance are extremely high. Therefore, more and more sensor systems are being implemented for process monitoring. To evaluate the generated data, suitable methods must be developed. A solution, in this context, was the application of artificial neural networks (ANNs). This article demonstrates how measurement data can be used as input data for ANNs. The measurement data were generated using a pyrometer, an emission spectrometer, a camera (Charge-Coupled Device) and a laser scanner. First, a concept for the extraction of relevant features from dynamic measurement data series was presented. The developed method was then applied to generate a data set for the quality prediction of various geometries, including weld beads, coatings and cubes. The results were compared to ANNs trained with process parameters such as laser power, scan speed and powder mass flow. It was shown that the use of measurement data provides additional value. Neural networks trained with measurement data achieve significantly higher prediction accuracy, especially for more complex geometries. |
| first_indexed | 2024-03-09T11:11:48Z |
| format | Article |
| id | doaj.art-319647027ce14ba39442c7b90db0e789 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T11:11:48Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-319647027ce14ba39442c7b90db0e7892023-12-01T00:42:20ZengMDPI AGApplied Sciences2076-34172022-04-01128395510.3390/app12083955Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process SignalsAngelina Marko0Stefan Bähring1Julius Raute2Max Biegler3Michael Rethmeier4Institute of Machine Tools and Factory Management, Technical University Berlin, Straße des 17. Juni 135, 10623 Berlin, GermanyFraunhofer Institute of Production Systems and Design Engineering (IPK), Pascalstraße 8-9, 10587 Berlin, GermanyFraunhofer Institute of Production Systems and Design Engineering (IPK), Pascalstraße 8-9, 10587 Berlin, GermanyFraunhofer Institute of Production Systems and Design Engineering (IPK), Pascalstraße 8-9, 10587 Berlin, GermanyInstitute of Machine Tools and Factory Management, Technical University Berlin, Straße des 17. Juni 135, 10623 Berlin, GermanyThe Directed Energy Deposition process is used in a wide range of applications including the repair, coating or modification of existing structures and the additive manufacturing of individual parts. As the process is frequently applied in the aerospace industry, the requirements for quality assurance are extremely high. Therefore, more and more sensor systems are being implemented for process monitoring. To evaluate the generated data, suitable methods must be developed. A solution, in this context, was the application of artificial neural networks (ANNs). This article demonstrates how measurement data can be used as input data for ANNs. The measurement data were generated using a pyrometer, an emission spectrometer, a camera (Charge-Coupled Device) and a laser scanner. First, a concept for the extraction of relevant features from dynamic measurement data series was presented. The developed method was then applied to generate a data set for the quality prediction of various geometries, including weld beads, coatings and cubes. The results were compared to ANNs trained with process parameters such as laser power, scan speed and powder mass flow. It was shown that the use of measurement data provides additional value. Neural networks trained with measurement data achieve significantly higher prediction accuracy, especially for more complex geometries.https://www.mdpi.com/2076-3417/12/8/3955DEDartificial neural networkdata preparationquality assuranceprocess monitoring |
| spellingShingle | Angelina Marko Stefan Bähring Julius Raute Max Biegler Michael Rethmeier Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals Applied Sciences DED artificial neural network data preparation quality assurance process monitoring |
| title | Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals |
| title_full | Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals |
| title_fullStr | Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals |
| title_full_unstemmed | Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals |
| title_short | Quality Prediction in Directed Energy Deposition Using Artificial Neural Networks Based on Process Signals |
| title_sort | quality prediction in directed energy deposition using artificial neural networks based on process signals |
| topic | DED artificial neural network data preparation quality assurance process monitoring |
| url | https://www.mdpi.com/2076-3417/12/8/3955 |
| work_keys_str_mv | AT angelinamarko qualitypredictionindirectedenergydepositionusingartificialneuralnetworksbasedonprocesssignals AT stefanbahring qualitypredictionindirectedenergydepositionusingartificialneuralnetworksbasedonprocesssignals AT juliusraute qualitypredictionindirectedenergydepositionusingartificialneuralnetworksbasedonprocesssignals AT maxbiegler qualitypredictionindirectedenergydepositionusingartificialneuralnetworksbasedonprocesssignals AT michaelrethmeier qualitypredictionindirectedenergydepositionusingartificialneuralnetworksbasedonprocesssignals |