{"title":"一种植入式旋转血泵系统识别算法","authors":"D. Petukhov, D. Telyshev, M. Walter, Leonie Korn","doi":"10.1109/USBEREIT.2018.8384550","DOIUrl":null,"url":null,"abstract":"The paper presents an algorithm of system identification for implantable rotary blood pumps. The algorithm allows to build mathematical models in accordance with the quality metric introduced to assess the effectiveness of identification. The quality metric was set as an error of pump flow estimation. In the result the mathematical models were identified using experimental dataset for two different rotary blood pumps Sputnik. The identified model of Sputnik 1 characterizes by the mean error about 0.12 L on the control set, the identified model of updated pump — Sputnik 2 — mean error about 0.14 L. The identified models intended for control of pump flow during in vitro trials.","PeriodicalId":176222,"journal":{"name":"2018 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"An algorithm of system identification for implantable rotary blood pumps\",\"authors\":\"D. Petukhov, D. Telyshev, M. Walter, Leonie Korn\",\"doi\":\"10.1109/USBEREIT.2018.8384550\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper presents an algorithm of system identification for implantable rotary blood pumps. The algorithm allows to build mathematical models in accordance with the quality metric introduced to assess the effectiveness of identification. The quality metric was set as an error of pump flow estimation. In the result the mathematical models were identified using experimental dataset for two different rotary blood pumps Sputnik. The identified model of Sputnik 1 characterizes by the mean error about 0.12 L on the control set, the identified model of updated pump — Sputnik 2 — mean error about 0.14 L. The identified models intended for control of pump flow during in vitro trials.\",\"PeriodicalId\":176222,\"journal\":{\"name\":\"2018 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)\",\"volume\":\"31 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/USBEREIT.2018.8384550\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/USBEREIT.2018.8384550","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An algorithm of system identification for implantable rotary blood pumps
The paper presents an algorithm of system identification for implantable rotary blood pumps. The algorithm allows to build mathematical models in accordance with the quality metric introduced to assess the effectiveness of identification. The quality metric was set as an error of pump flow estimation. In the result the mathematical models were identified using experimental dataset for two different rotary blood pumps Sputnik. The identified model of Sputnik 1 characterizes by the mean error about 0.12 L on the control set, the identified model of updated pump — Sputnik 2 — mean error about 0.14 L. The identified models intended for control of pump flow during in vitro trials.