[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120955-en":3,"doc-seo-120955-105":30,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120955,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","FLUID VISCOSITY AND DENSITY DETERMINATION WITH MACHINE LEARNING-ENHANCED CORIOLIS MASS FLOW SENSORS","Statistical machine learning methods are used to estimate liquid density and dynamic viscosity from a Coriolis-based sensor chip. Conventional calibration is limited by non-ideal sensor effects that make results dependent on fluid state, including mass flow, pressure, and temperature. The chip is exposed to controlled temperature, flow, and pressure combinations for ethanol, water, and isopropanol. Using raw sampled sensing signals, Gaussian Process Regression achieves high accuracy with mean absolute percentage errors under 0.01% for density and under 1% for viscosity.","2024 IEEE 37th International Conference on Micro Electro Mechanical Systems (MEMS) | 979-8-3503-5792-9/24/$31.00 ©2024 IEEE | DOI: 10. 1 109/MEMS58180.2024. 10439597  \nFLUID VISCOSITY AND DENSITY DETERMINATION WITH MACHINE LEARNING-ENHANCED CORIOLIS MASS FLOW SENSORS  \nRomas Zubavicius 1, Dennis Alveringh1, Mannes Poel1 , Jarno Groenesteijn1,2, Remco G.P. Sanders1,  \nRemco J. Wiegerink1, and Joost C. Lötters1,2  \n1 University of Twente, Enschede, The Netherlands and  \n2 Bronkhorst High-Tech BV, Ruurlo, The Netherlands  \nABSTRACT  \nWe report on statistical machine learning methods applied to a Coriolis-based sensor chip to accurately estimate liquid density and dynamic viscosity for trained liquids. This estimation is challenging with conventional methods due to non-ideal sensor effects. The chip (1 .2 cm2 ) has been exposed to different combinations of temperatures, flows, and pressures for three different liquids: ethanol, water and isopropanol. The statistical machine learning methods have been applied to the raw sampled signals of the sensing structures. The results have been obtained for different temperatures and shown to be less dependent on the liquid state (i.e., pressure and flow). The best-performing method was the Gaussian Process Regression (GPR) method, which results in a mean absolute percentage error of \u003C 0:01 % and \u003C 1 % for density and viscosity respectively, which is a factor of > 4 better compared to conventional methods.  \nKEYWORDS  \nMicrofluidics, Coriolis, mass flow sensors, machine learning, regression, viscosity, density, estimation  \nINTRODUCTION  \nResearch in microfluidic flow sensors focuses on measuring very low flows accurately in the order of a few micro or nano liters per minute [1] . This enables low-flow measurements and control for applications in pharmaceutical, biomedical and many other fields [2, 3] . Coriolis mass flow sensors (CMFS) have also been miniaturized for this purpose. These sensors can, in contrast to other flow sensing methods, measure the true mass flow by detecting the inertial effects caused by a fluid flowing through a vibrating channel as illustrated in Figure 1 . The resonance frequency of the actuation mode is dependent on the density of the fluid, enabling density measurements with the CMFS. Additionally, recent research has shown a microfabricated CMFS with integrated pressure sensors (upstream and downstream) to estimate viscosity via the Hagen-Poiseuille equation [4] . Although these direct approaches enable the estimation of density and viscosity, non-ideal sensor effects increase the dependence on the fluid state (i.e., mass flow, pressure and temperature) and therefore may cause errors of up to 4 % and 0.2 % for viscosity and density respectively for state-of-the-art devices [5] . Statistical machine learning methods, like the Gaussian Process Regression (GPR) approach, have been used previously to predict specific heat capacity and viscosity for nanofluids [6, 7] . Fluid classification has been performed before using ML techniques and  \nFigure 1: Illustration of the twist component (a), and the swing component induced by the Coriolis force due to amass flow 􀀞 m (b).  \nCMFS [8] . However, so far, ML has never been directly applied to the raw signals from microfabricated CMFS to accurately estimate liquid density and dynamic viscosity.  \nTHEORY  \nThe fabrication of the CMFS is based on [9] and is used in this research.  \nCoriolis mass flow sensor  \nAs mentioned previously, Coriolis forces are directly proportional to the mass flow. J. Haneveld et al. [10] expressed this in equation  \n®Fc = 􀀀2Ly ¹!®am 􀀂 ®􀀞mº; (1)  \nwhere Ly is the width of the tube, !®am the angular velocity and ®􀀞m mass flow. The Coriolis force introduces an extra mechanical mode of the tube. When measured using the two capacitive read-out signals, the actuated movement is 180 degrees out of phase, the Coriolis movement is measured asan extra phase shift (􀀁') between the two capacitive readout signals [10]. The additional phase","cbCaig46pBKkKcDO","https://ap.wps.com/l/cbCaig46pBKkKcDO","pdf",2339799,1,4,"English","en",105,"# Abstract\n# Introduction\n## Microfluidic flow sensing and Coriolis principles\n## Challenge of non-ideal sensor effects\n# Theory\n## Coriolis mass flow sensor fundamentals\n## Machine learning regression models\n### Linear regression\n### Support vector regression\n### Gaussian process regression","[{\"question\":\"Why is estimating viscosity and density challenging with conventional Coriolis mass flow sensor methods?\",\"answer\":\"Non-ideal sensor effects increase dependence on the fluid state, such as mass flow, pressure, and temperature, which can introduce significant estimation errors.\"},{\"question\":\"Which liquids and operating conditions are used for the sensor measurements?\",\"answer\":\"The sensor chip is tested with ethanol, water, and isopropanol across different combinations of temperatures, flows, and pressures.\"},{\"question\":\"What machine learning approach performs best and what accuracy is reported?\",\"answer\":\"Gaussian Process Regression provides the best results, achieving mean absolute percentage error below 0.01% for density and below 1% for viscosity, reported as more than a fourfold improvement over conventional methods.\"}]","FLUID VISCOSITY AND DENSITY DETERMINATION WITH MACHINE LEARNING-ENHANCED CORIOLIS MASS FLOW SENSORS | PDF",1785733046,10,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"fluid-viscosity-and-density-determination-with-machine-learning-enhanced-coriolis-mass-flow-sensors","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":21},"https://docshare.wps.com/document/fluid-viscosity-and-density-determination-with-machine-learning-enhanced-coriolis-mass-flow-sensors/120955/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is estimating viscosity and density challenging with conventional Coriolis mass flow sensor methods?","Question",{"text":74,"@type":75},"Non-ideal sensor effects increase dependence on the fluid state, such as mass flow, pressure, and temperature, which can introduce significant estimation errors.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which liquids and operating conditions are used for the sensor measurements?",{"text":79,"@type":75},"The sensor chip is tested with ethanol, water, and isopropanol across different combinations of temperatures, flows, and pressures.",{"name":81,"@type":72,"acceptedAnswer":82},"What machine learning approach performs best and what accuracy is reported?",{"text":83,"@type":75},"Gaussian Process Regression provides the best results, achieving mean absolute percentage error below 0.01% for density and below 1% for viscosity, reported as more than a fourfold improvement over conventional methods.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]