NOTE: This item is not available outside the Texas A&M University network. Texas A&M affiliated users who are off campus can access the item through NetID and password authentication or by using TAMU VPN. Non-affiliated individuals should request a copy through their local library's interlibrary loan service.
Real-time implementation of a neural networks-based motor speed filter using a digital signal processor
dc.creator | Harihara, Parasuram Padmanabhan | |
dc.date.accessioned | 2012-06-07T23:14:27Z | |
dc.date.available | 2012-06-07T23:14:27Z | |
dc.date.created | 2002 | |
dc.date.issued | 2002 | |
dc.identifier.uri | https://hdl.handle.net/1969.1/ETD-TAMU-2002-THESIS-H368 | |
dc.description | Due to the character of the original source materials and the nature of batch digitization, quality control issues may be present in this document. Please report any quality issues you encounter to digital@library.tamu.edu, referencing the URI of the item. | en |
dc.description | Includes bibliographical references (leaves 71-73). | en |
dc.description | Issued also on microfiche from Lange Micrographics. | en |
dc.description.abstract | Induction motors play a vital industrial role. In many industrial applications, it is desirable to eliminate the use of motor speed sensors, which increase the size and cost while reducing the mechanical robustness of the drive system. Therefore, an effective sensorless dynamic speed estimation technique is required to avoid the above-mentioned drawbacks. Some of the applications of speed estimation techniques include on-line motor condition monitoring and sensorless motor speed control. Although numerous speed estimation methods have been reported in the literature for the control of an induction motor drive, it is the accuracy of the speed estimate and the response time of the filter that are the important parameters describing the speed filter performance. Furthermore, the speed filter must be portable to a wide range of motors irrespective of the machine parameters. The accuracy of the speed estimate must be acceptable also for motors with incipient faults. In this work a previously developed neural network speed filter is implemented on a Digital Signal Processor (DSP) for real-time motor speed estimation. The speed filter is constructed using a combination of three neural networks. The filter uses the line voltage, the line current, the RMS of the current and the fundamental frequency as inputs to estimate the motor speed. The filter is implemented on Spectrum Digital's EVM320F243 evaluation module, which houses the Texas Instruments (TI) TMS320F243 DSP chip. This research demonstrates the feasibility of using neural networks-based speed filters for real-time motor speed estimation using only motor current and voltage measurements. The filter accuracy is quite acceptable for a range of desirable motor applications. The filter can be used along with a control law for sensorless speed control of induction motors. While not requiring real-time performance, the filter can also be used in sensorless motor condition assessment. | en |
dc.format.medium | electronic | en |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.publisher | Texas A&M University | |
dc.rights | This thesis was part of a retrospective digitization project authorized by the Texas A&M University Libraries in 2008. Copyright remains vested with the author(s). It is the user's responsibility to secure permission from the copyright holder(s) for re-use of the work beyond the provision of Fair Use. | en |
dc.subject | mechanical engineering. | en |
dc.subject | Major mechanical engineering. | en |
dc.title | Real-time implementation of a neural networks-based motor speed filter using a digital signal processor | en |
dc.type | Thesis | en |
thesis.degree.discipline | mechanical engineering | en |
thesis.degree.name | M.S. | en |
thesis.degree.level | Masters | en |
dc.type.genre | thesis | en |
dc.type.material | text | en |
dc.format.digitalOrigin | reformatted digital | en |
Files in this item
This item appears in the following Collection(s)
-
Digitized Theses and Dissertations (1922–2004)
Texas A&M University Theses and Dissertations (1922–2004)
Request Open Access
This item and its contents are restricted. If this is your thesis or dissertation, you can make it open-access. This will allow all visitors to view the contents of the thesis.