Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning
The interfacial adhesion, friction, and resulting tool-part interaction during composites manufacturing contribute to the formation of residual stresses and process-induced deformations (PIDs). Tool-part interaction and PIDs are highly sensitive to processing variabilities, one of which is the aging...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Journal of Manufacturing and Materials Processing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4494/7/3/81 |
| _version_ | 1797594025414361088 |
|---|---|
| author | Caleb Schoenholz Shuangshan Li Kyle Bainbridge Vy Huynh Alex Gray Navid Zobeiry |
| author_facet | Caleb Schoenholz Shuangshan Li Kyle Bainbridge Vy Huynh Alex Gray Navid Zobeiry |
| author_sort | Caleb Schoenholz |
| collection | DOAJ |
| description | The interfacial adhesion, friction, and resulting tool-part interaction during composites manufacturing contribute to the formation of residual stresses and process-induced deformations (PIDs). Tool-part interaction and PIDs are highly sensitive to processing variabilities, one of which is the aging of the release coating and the surface condition of production tools. Unfortunately, due to a lack of available tool inspection methods, manufacturers often attempt to mitigate the aging of release coating based on know-how, leading to cost-deficient tool preparation schedules, lower end-part quality, and in some cases, higher levels of PIDs. This paper presents an in-situ inspection method to evaluate the physicochemical properties of release coating and the surface condition of large production tools by utilizing global mapping, sparse sensing, and machine learning (ML). ML methods are used in conjunction with multiple automated measurement techniques to quickly identify the condition of release coating or contamination on production tool surfaces in manufacturing environments. Results in this paper demonstrate that during autoclave processing, aerospace-grade release coatings undergo significant chemical changes, but may remain highly abhesive for more than twenty autoclave processing cycles. Using the proposed novel inspection technology, dry ice blasting (DIB) is also demonstrated to be an effective method for non-abrasively removing cured resin contamination and release coating from a tool surface. Overall, this paper demonstrates how the proposed inspection method can be integrated into a manufacturing process for automatic surface inspection of large tools to improve production efficiency and potentially mitigate PIDs in composites manufacturing. |
| first_indexed | 2024-03-11T02:17:46Z |
| format | Article |
| id | doaj.art-d22ecc1a1f694599ba119087f562ed2d |
| institution | Directory Open Access Journal |
| issn | 2504-4494 |
| language | English |
| last_indexed | 2024-03-11T02:17:46Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Manufacturing and Materials Processing |
| spelling | doaj.art-d22ecc1a1f694599ba119087f562ed2d2023-11-18T11:05:15ZengMDPI AGJournal of Manufacturing and Materials Processing2504-44942023-04-01738110.3390/jmmp7030081Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine LearningCaleb Schoenholz0Shuangshan Li1Kyle Bainbridge2Vy Huynh3Alex Gray4Navid Zobeiry5Materials Science & Engineering Department, University of Washington, Seattle, WA 98195, USAMaterials Science & Engineering Department, University of Washington, Seattle, WA 98195, USAMaterials Science & Engineering Department, University of Washington, Seattle, WA 98195, USAMaterials Science & Engineering Department, University of Washington, Seattle, WA 98195, USAMaterials Science & Engineering Department, University of Washington, Seattle, WA 98195, USAMaterials Science & Engineering Department, University of Washington, Seattle, WA 98195, USAThe interfacial adhesion, friction, and resulting tool-part interaction during composites manufacturing contribute to the formation of residual stresses and process-induced deformations (PIDs). Tool-part interaction and PIDs are highly sensitive to processing variabilities, one of which is the aging of the release coating and the surface condition of production tools. Unfortunately, due to a lack of available tool inspection methods, manufacturers often attempt to mitigate the aging of release coating based on know-how, leading to cost-deficient tool preparation schedules, lower end-part quality, and in some cases, higher levels of PIDs. This paper presents an in-situ inspection method to evaluate the physicochemical properties of release coating and the surface condition of large production tools by utilizing global mapping, sparse sensing, and machine learning (ML). ML methods are used in conjunction with multiple automated measurement techniques to quickly identify the condition of release coating or contamination on production tool surfaces in manufacturing environments. Results in this paper demonstrate that during autoclave processing, aerospace-grade release coatings undergo significant chemical changes, but may remain highly abhesive for more than twenty autoclave processing cycles. Using the proposed novel inspection technology, dry ice blasting (DIB) is also demonstrated to be an effective method for non-abrasively removing cured resin contamination and release coating from a tool surface. Overall, this paper demonstrates how the proposed inspection method can be integrated into a manufacturing process for automatic surface inspection of large tools to improve production efficiency and potentially mitigate PIDs in composites manufacturing.https://www.mdpi.com/2504-4494/7/3/81composites manufacturingnon-destructive inspectionrelease coatingtool preparationmachine learning |
| spellingShingle | Caleb Schoenholz Shuangshan Li Kyle Bainbridge Vy Huynh Alex Gray Navid Zobeiry Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning Journal of Manufacturing and Materials Processing composites manufacturing non-destructive inspection release coating tool preparation machine learning |
| title | Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning |
| title_full | Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning |
| title_fullStr | Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning |
| title_full_unstemmed | Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning |
| title_short | Accelerated In Situ Inspection of Release Coating and Tool Surface Condition in Composites Manufacturing Using Global Mapping, Sparse Sensing, and Machine Learning |
| title_sort | accelerated in situ inspection of release coating and tool surface condition in composites manufacturing using global mapping sparse sensing and machine learning |
| topic | composites manufacturing non-destructive inspection release coating tool preparation machine learning |
| url | https://www.mdpi.com/2504-4494/7/3/81 |
| work_keys_str_mv | AT calebschoenholz acceleratedinsituinspectionofreleasecoatingandtoolsurfaceconditionincompositesmanufacturingusingglobalmappingsparsesensingandmachinelearning AT shuangshanli acceleratedinsituinspectionofreleasecoatingandtoolsurfaceconditionincompositesmanufacturingusingglobalmappingsparsesensingandmachinelearning AT kylebainbridge acceleratedinsituinspectionofreleasecoatingandtoolsurfaceconditionincompositesmanufacturingusingglobalmappingsparsesensingandmachinelearning AT vyhuynh acceleratedinsituinspectionofreleasecoatingandtoolsurfaceconditionincompositesmanufacturingusingglobalmappingsparsesensingandmachinelearning AT alexgray acceleratedinsituinspectionofreleasecoatingandtoolsurfaceconditionincompositesmanufacturingusingglobalmappingsparsesensingandmachinelearning AT navidzobeiry acceleratedinsituinspectionofreleasecoatingandtoolsurfaceconditionincompositesmanufacturingusingglobalmappingsparsesensingandmachinelearning |