{"title":"基于选择性激光熔化声学信号的熔化状态识别和工艺性能研究","authors":"Dongju Chen, Anqing Wang, Peng Wang, Na Li","doi":"10.2351/7.0000991","DOIUrl":null,"url":null,"abstract":"An acoustic signal acquisition experiment platform was constructed to gather the acoustic signals throughout the formation of 35 single-tracks of a 120 mm length copper-tin alloy in order to monitor and precisely manage the selective laser melting (SLM) forming process and enhance overall quality. The monitoring of the SLM forming process includes the analysis of the time and frequency domains, the extraction of the SLM process features using linear prediction techniques, and the development of support vector machine (SVM) model, back-propagation (BP) neural network models, and convolutional neural network models. The results show that the over-melted state can be identified by extracting time and frequency-domain features over a given range, but the normal and unmelted states are difficult to distinguish. The convolutional neural network model had a recognition rate of 99%, the BP neural network had an effective recognition rate of 90%, and the SVM model had a combined classification rate of 83.14% for the three states after optimization. In contrast, the convolutional neural network model performs best in monitoring and offers a framework and point of reference for acoustic signal analysis and online SLM quality monitoring.","PeriodicalId":50168,"journal":{"name":"Journal of Laser Applications","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2023-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research of melting state identification and process performance based on selective laser melting acoustic signals\",\"authors\":\"Dongju Chen, Anqing Wang, Peng Wang, Na Li\",\"doi\":\"10.2351/7.0000991\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An acoustic signal acquisition experiment platform was constructed to gather the acoustic signals throughout the formation of 35 single-tracks of a 120 mm length copper-tin alloy in order to monitor and precisely manage the selective laser melting (SLM) forming process and enhance overall quality. The monitoring of the SLM forming process includes the analysis of the time and frequency domains, the extraction of the SLM process features using linear prediction techniques, and the development of support vector machine (SVM) model, back-propagation (BP) neural network models, and convolutional neural network models. The results show that the over-melted state can be identified by extracting time and frequency-domain features over a given range, but the normal and unmelted states are difficult to distinguish. The convolutional neural network model had a recognition rate of 99%, the BP neural network had an effective recognition rate of 90%, and the SVM model had a combined classification rate of 83.14% for the three states after optimization. In contrast, the convolutional neural network model performs best in monitoring and offers a framework and point of reference for acoustic signal analysis and online SLM quality monitoring.\",\"PeriodicalId\":50168,\"journal\":{\"name\":\"Journal of Laser Applications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2023-12-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Laser Applications\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.2351/7.0000991\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Laser Applications","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.2351/7.0000991","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
Research of melting state identification and process performance based on selective laser melting acoustic signals
An acoustic signal acquisition experiment platform was constructed to gather the acoustic signals throughout the formation of 35 single-tracks of a 120 mm length copper-tin alloy in order to monitor and precisely manage the selective laser melting (SLM) forming process and enhance overall quality. The monitoring of the SLM forming process includes the analysis of the time and frequency domains, the extraction of the SLM process features using linear prediction techniques, and the development of support vector machine (SVM) model, back-propagation (BP) neural network models, and convolutional neural network models. The results show that the over-melted state can be identified by extracting time and frequency-domain features over a given range, but the normal and unmelted states are difficult to distinguish. The convolutional neural network model had a recognition rate of 99%, the BP neural network had an effective recognition rate of 90%, and the SVM model had a combined classification rate of 83.14% for the three states after optimization. In contrast, the convolutional neural network model performs best in monitoring and offers a framework and point of reference for acoustic signal analysis and online SLM quality monitoring.
期刊介绍:
The Journal of Laser Applications (JLA) is the scientific platform of the Laser Institute of America (LIA) and is published in cooperation with AIP Publishing. The high-quality articles cover a broad range from fundamental and applied research and development to industrial applications. Therefore, JLA is a reflection of the state-of-R&D in photonic production, sensing and measurement as well as Laser safety.
The following international and well known first-class scientists serve as allocated Editors in 9 new categories:
High Precision Materials Processing with Ultrafast Lasers
Laser Additive Manufacturing
High Power Materials Processing with High Brightness Lasers
Emerging Applications of Laser Technologies in High-performance/Multi-function Materials and Structures
Surface Modification
Lasers in Nanomanufacturing / Nanophotonics & Thin Film Technology
Spectroscopy / Imaging / Diagnostics / Measurements
Laser Systems and Markets
Medical Applications & Safety
Thermal Transportation
Nanomaterials and Nanoprocessing
Laser applications in Microelectronics.