國立虎尾科技大學 |

Stepper Motor Load Estimation Using a Neural Network

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Stepper Motor Load Estimation Using a Neural Network/ Soham S Kulkarni.
作者:	Kulkarni, Soham S.,
面頁冊數:	1 electronic resource (61 pages)
附註:	Source: Masters Abstracts International, Volume: 87-04.
Contained By:	Masters Abstracts International87-04.
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32237964
ISBN:	9798297648883

Stepper Motor Load Estimation Using a Neural Network
Kulkarni, Soham S.,

Stepper Motor Load Estimation Using a Neural Network [eletronic resource] /Soham S Kulkarni. - 1 electronic resource (61 pages)

Source: Masters Abstracts International, Volume: 87-04.

Bipolar stepper motors are common in scenarios that require low-cost precision including 3d printers. The ability to estimate stepper motor load provides an opportunity for health monitoring. For example, excessive load estimates may indicate a future problem in the driven system such as bearing wear. Stepper motor drivers often have built-in stall detection strategies that exploit the driver's precise knowledge of the high-frequency voltage pulses being sent to the motor. The goal of this work was to develop a retrofit approach to stepper motor load estimation using externally measured voltage, current, and speed. A stepper motor dynamometer was created to generate motor responses for repeatable applied loads using a d.c. motor. A classification neural network was successfully trained to estimate four different loads at two speeds using images of the sensed current versus voltage Lissajous plot. The measurement system was implemented using dSPACE, however, its signal processing and sensing suite was not exotic and could be implemented on an embedded processor of opportunity. The neural network was implemented on an analysis computer that received batch samples of current, voltage and speed at 1 Hz. The main contribution of this work was to illustrate the feasibility of a retrofit solution for load estimation. Extension to continuous load estimation is left for future work.

English

ISBN: 9798297648883Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Bipolar stepper

Stepper Motor Load Estimation Using a Neural Network
LDR:02900nam a22004453i 4500 001 1172943
005 20260622113227.5
006 m o d
007 cr|nu||||||||
008 260803s2025 miu||||||m |||||||eng d
020 $a 9798297648883
035 $a (MiAaPQD)AAI32237964
035 $a AAI32237964
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Kulkarni, Soham S., $e author. $0 (orcid)0009-0005-4836-7471 $3 1503590
245 1 0 $a Stepper Motor Load Estimation Using a Neural Network $c Soham S Kulkarni. $h [eletronic resource] /
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (61 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 87-04.
500 $a Advisors: Parker, Gordon; Blough, Jason Committee members: Walber, Chad; Zou, Shangyan.
502 $b M.S. $c Michigan Technological University $d 2025.
520 # $a Bipolar stepper motors are common in scenarios that require low-cost precision including 3d printers. The ability to estimate stepper motor load provides an opportunity for health monitoring. For example, excessive load estimates may indicate a future problem in the driven system such as bearing wear. Stepper motor drivers often have built-in stall detection strategies that exploit the driver's precise knowledge of the high-frequency voltage pulses being sent to the motor. The goal of this work was to develop a retrofit approach to stepper motor load estimation using externally measured voltage, current, and speed. A stepper motor dynamometer was created to generate motor responses for repeatable applied loads using a d.c. motor. A classification neural network was successfully trained to estimate four different loads at two speeds using images of the sensed current versus voltage Lissajous plot. The measurement system was implemented using dSPACE, however, its signal processing and sensing suite was not exotic and could be implemented on an embedded processor of opportunity. The neural network was implemented on an analysis computer that received batch samples of current, voltage and speed at 1 Hz. The main contribution of this work was to illustrate the feasibility of a retrofit solution for load estimation. Extension to continuous load estimation is left for future work.
546 $a English
590 $a School code: 0129
650 # 4 $a Electrical engineering. $3 596380
650 # 4 $a Medical imaging. $3 1180167
650 # 4 $a Mechanical engineering. $3 557493
653 # # $a Bipolar stepper
653 # # $a Health monitoring
653 # # $a High-frequency voltage
653 # # $a Neural network
653 # # $a Dynamometer
690 $a 0548
690 $a 0544
690 $a 0574
710 2 # $a Michigan Technological University. $b Mechanical and Aerospace Engineering. $e degree granting institution. $3 1503591
720 1 $a Parker, Gordon $e degree supervisor.
720 1 $a Blough, Jason $e degree supervisor.
773 0 # $t Masters Abstracts International $g 87-04.
790 $a 0129
791 $a M.S.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32237964