A neural flow estimator

Ivan Harald Holger Jørgensen; Gudmundur Bogason; Erik Bruun

doi:10.1109/IMTC.1995.515299

A neural flow estimator

Ivan Harald Holger Jørgensen
, Gudmundur Bogason
, Erik Bruun

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

397 Downloads (Orbit)

Abstract

This paper proposes a new way to estimate the flow in a micromechanical flow channel. A neural network is used to estimate the delay of random temperature fluctuations induced in a fluid. The design and implementation of a hardware efficient neural flow estimator is described. The system is implemented using switched-current technique and is capable of estimating flow in the μl/s range. The neural estimator is built around a multiplierless neural network, containing 96 synaptic weights which are updated using the LMS1-algorithm. An experimental chip has been designed that operates at 5 V with a total current consumption of 2 mA, resulting in a power consumption of 10 mW. The dimensions of the clip core are 3 mm×4.5 mm

Original language	English
Title of host publication	Proceedings of the IEEE Instrumentation and Measurement Technology Conference : Integrating Intelligent Instrumentation and Control
Publisher	IEEE
Publication date	1995
Pages	385-385
ISBN (Print)	07-80-32615-6
DOIs	https://doi.org/10.1109/IMTC.1995.515299
Publication status	Published - 1995
Event	1995 IEEE Instrumentation and Measurement Technology Conference - Waltham, United States Duration: 23 Apr 1995 → 26 Apr 1995 http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3896

Conference

Conference	1995 IEEE Instrumentation and Measurement Technology Conference
Country/Territory	United States
City	Waltham
Period	23/04/1995 → 26/04/1995
Internet address	http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3896

Bibliographical note

Copyright: 1995 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Access to Document

10.1109/IMTC.1995.515299

J rgensenFinal published version, 398 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{582a26929d8149fdb5da0b40e762f6bf,

title = "A neural flow estimator",

abstract = "This paper proposes a new way to estimate the flow in a micromechanical flow channel. A neural network is used to estimate the delay of random temperature fluctuations induced in a fluid. The design and implementation of a hardware efficient neural flow estimator is described. The system is implemented using switched-current technique and is capable of estimating flow in the μl/s range. The neural estimator is built around a multiplierless neural network, containing 96 synaptic weights which are updated using the LMS1-algorithm. An experimental chip has been designed that operates at 5 V with a total current consumption of 2 mA, resulting in a power consumption of 10 mW. The dimensions of the clip core are 3 mm×4.5 mm",

author = "J{\o}rgensen, \{Ivan Harald Holger\} and Gudmundur Bogason and Erik Bruun",

note = "Copyright: 1995 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE; 1995 IEEE Instrumentation and Measurement Technology Conference, IMTC'95 ; Conference date: 23-04-1995 Through 26-04-1995",

year = "1995",

doi = "10.1109/IMTC.1995.515299",

language = "English",

isbn = "07-80-32615-6",

pages = "385--385",

booktitle = "Proceedings of the IEEE Instrumentation and Measurement Technology Conference",

publisher = "IEEE",

address = "United States",

url = "http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3896",

}

Jørgensen, IHH, Bogason, G & Bruun, E 1995, A neural flow estimator. in Proceedings of the IEEE Instrumentation and Measurement Technology Conference: Integrating Intelligent Instrumentation and Control. IEEE, pp. 385-385, 1995 IEEE Instrumentation and Measurement Technology Conference, Waltham, Massachusetts, United States, 23/04/1995. https://doi.org/10.1109/IMTC.1995.515299

TY - GEN

T1 - A neural flow estimator

AU - Jørgensen, Ivan Harald Holger

AU - Bogason, Gudmundur

AU - Bruun, Erik

N1 - Copyright: 1995 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

PY - 1995

Y1 - 1995

N2 - This paper proposes a new way to estimate the flow in a micromechanical flow channel. A neural network is used to estimate the delay of random temperature fluctuations induced in a fluid. The design and implementation of a hardware efficient neural flow estimator is described. The system is implemented using switched-current technique and is capable of estimating flow in the μl/s range. The neural estimator is built around a multiplierless neural network, containing 96 synaptic weights which are updated using the LMS1-algorithm. An experimental chip has been designed that operates at 5 V with a total current consumption of 2 mA, resulting in a power consumption of 10 mW. The dimensions of the clip core are 3 mm×4.5 mm

AB - This paper proposes a new way to estimate the flow in a micromechanical flow channel. A neural network is used to estimate the delay of random temperature fluctuations induced in a fluid. The design and implementation of a hardware efficient neural flow estimator is described. The system is implemented using switched-current technique and is capable of estimating flow in the μl/s range. The neural estimator is built around a multiplierless neural network, containing 96 synaptic weights which are updated using the LMS1-algorithm. An experimental chip has been designed that operates at 5 V with a total current consumption of 2 mA, resulting in a power consumption of 10 mW. The dimensions of the clip core are 3 mm×4.5 mm

U2 - 10.1109/IMTC.1995.515299

DO - 10.1109/IMTC.1995.515299

M3 - Article in proceedings

SN - 07-80-32615-6

SP - 385

EP - 385

BT - Proceedings of the IEEE Instrumentation and Measurement Technology Conference

PB - IEEE

T2 - 1995 IEEE Instrumentation and Measurement Technology Conference

Y2 - 23 April 1995 through 26 April 1995

ER -

A neural flow estimator

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this