Multimodal deep learning for predicting the choice of cut parameters in the milling process
In this paper, we use multimodal deep learning to predict the choice of optimal cutting parameters (cutting speed, depth of cut, and feed rate per tooth) and the appropriate cutting tool for reproducing an existent piece of the same surface state, considering the footprints left by the cutting tool....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Intelligent Systems with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305322000503 |
| _version_ | 1811281342251401216 |
|---|---|
| author | Cheick Abdoul Kadir A Kounta Bernard Kamsu-Foguem Farid Noureddine Fana Tangara |
| author_facet | Cheick Abdoul Kadir A Kounta Bernard Kamsu-Foguem Farid Noureddine Fana Tangara |
| author_sort | Cheick Abdoul Kadir A Kounta |
| collection | DOAJ |
| description | In this paper, we use multimodal deep learning to predict the choice of optimal cutting parameters (cutting speed, depth of cut, and feed rate per tooth) and the appropriate cutting tool for reproducing an existent piece of the same surface state, considering the footprints left by the cutting tool. We use the image of the aluminum plate's surface states considering the tool's footprints, the cutting parameters, and the roughness average (Ra) obtained with a roughness meter to drive our model. We built a late multimodal fusion model with two networks, a convolutional neural network (CNN) and a recurrent neural network with long short-term memory layers (LSTM). The first network consists of the first branch with a convolutional network that receives the input images. In the second network, modeling is performed by the LSTM network to receive the digital input data. This provides a framework to integrate information from two modalities to ensure surface quality in machining processes. This approach aims to assist in selecting the appropriate cutting tool and cutting parameters to automatically reproduce a machined piece using the image and roughness of an already existing piece. It is observed that the performance of the multimodal model is better than that of the unimodal model on image data. The accuracy continues to improve on both sets (training and validation), and the multimodal model finally reaches good accuracy results. Contrary to the unimodal model, which fails to generalize the training on a validation dataset. The results estimated by the multimodal fusion model are encouraging when applied to the milling activity in industrial production processes. |
| first_indexed | 2024-04-13T01:30:38Z |
| format | Article |
| id | doaj.art-47c1da422e274e998b60d2d5f42f312b |
| institution | Directory Open Access Journal |
| issn | 2667-3053 |
| language | English |
| last_indexed | 2024-04-13T01:30:38Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Intelligent Systems with Applications |
| spelling | doaj.art-47c1da422e274e998b60d2d5f42f312b2022-12-22T03:08:30ZengElsevierIntelligent Systems with Applications2667-30532022-11-0116200112Multimodal deep learning for predicting the choice of cut parameters in the milling processCheick Abdoul Kadir A Kounta0Bernard Kamsu-Foguem1Farid Noureddine2Fana Tangara3Laboratoire Génie de Production, École Nationale d'Ingénieurs de Tarbes, 47 Avenue Azereix, B.P. 1629, F-65016 Tarbes Cedex, France; Faculté des Sciences et Techniques, Université des Sciences, des Techniques et des Technologies de Bamako (USTTB), B.P. E : 423, Bamako, Mali; Corresponding author at: Laboratoire Génie de Production, École Nationale d'Ingénieurs de Tarbes, 47 Avenue Azereix, B.P. 1629, F-65016 Tarbes Cedex, France.Laboratoire Génie de Production, École Nationale d'Ingénieurs de Tarbes, 47 Avenue Azereix, B.P. 1629, F-65016 Tarbes Cedex, FranceLaboratoire Génie de Production, École Nationale d'Ingénieurs de Tarbes, 47 Avenue Azereix, B.P. 1629, F-65016 Tarbes Cedex, FranceFaculté des Sciences et Techniques, Université des Sciences, des Techniques et des Technologies de Bamako (USTTB), B.P. E : 423, Bamako, MaliIn this paper, we use multimodal deep learning to predict the choice of optimal cutting parameters (cutting speed, depth of cut, and feed rate per tooth) and the appropriate cutting tool for reproducing an existent piece of the same surface state, considering the footprints left by the cutting tool. We use the image of the aluminum plate's surface states considering the tool's footprints, the cutting parameters, and the roughness average (Ra) obtained with a roughness meter to drive our model. We built a late multimodal fusion model with two networks, a convolutional neural network (CNN) and a recurrent neural network with long short-term memory layers (LSTM). The first network consists of the first branch with a convolutional network that receives the input images. In the second network, modeling is performed by the LSTM network to receive the digital input data. This provides a framework to integrate information from two modalities to ensure surface quality in machining processes. This approach aims to assist in selecting the appropriate cutting tool and cutting parameters to automatically reproduce a machined piece using the image and roughness of an already existing piece. It is observed that the performance of the multimodal model is better than that of the unimodal model on image data. The accuracy continues to improve on both sets (training and validation), and the multimodal model finally reaches good accuracy results. Contrary to the unimodal model, which fails to generalize the training on a validation dataset. The results estimated by the multimodal fusion model are encouraging when applied to the milling activity in industrial production processes.http://www.sciencedirect.com/science/article/pii/S2667305322000503Deep learningMultimodal data processingHeterogeneous data fusionUnstructured dataManufacturing processesRoughness |
| spellingShingle | Cheick Abdoul Kadir A Kounta Bernard Kamsu-Foguem Farid Noureddine Fana Tangara Multimodal deep learning for predicting the choice of cut parameters in the milling process Intelligent Systems with Applications Deep learning Multimodal data processing Heterogeneous data fusion Unstructured data Manufacturing processes Roughness |
| title | Multimodal deep learning for predicting the choice of cut parameters in the milling process |
| title_full | Multimodal deep learning for predicting the choice of cut parameters in the milling process |
| title_fullStr | Multimodal deep learning for predicting the choice of cut parameters in the milling process |
| title_full_unstemmed | Multimodal deep learning for predicting the choice of cut parameters in the milling process |
| title_short | Multimodal deep learning for predicting the choice of cut parameters in the milling process |
| title_sort | multimodal deep learning for predicting the choice of cut parameters in the milling process |
| topic | Deep learning Multimodal data processing Heterogeneous data fusion Unstructured data Manufacturing processes Roughness |
| url | http://www.sciencedirect.com/science/article/pii/S2667305322000503 |
| work_keys_str_mv | AT cheickabdoulkadirakounta multimodaldeeplearningforpredictingthechoiceofcutparametersinthemillingprocess AT bernardkamsufoguem multimodaldeeplearningforpredictingthechoiceofcutparametersinthemillingprocess AT faridnoureddine multimodaldeeplearningforpredictingthechoiceofcutparametersinthemillingprocess AT fanatangara multimodaldeeplearningforpredictingthechoiceofcutparametersinthemillingprocess |