Graduate Thesis Or Dissertation

 

Learning approaches for the early detection of kickback in chainsaws Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/2227mr86m

Descriptions

Attribute NameValues
Creator
Abstract
  • Among the many safety hazards facing chainsaw operators, the phenomenon known as kickback is the most dangerous. Kickback occurs when the chain at the tip of the chainsaw is caused to stop abruptly, and transfers the energy of the cutting chain to motion of the saw. The saw will rotate backward toward the operator rapidly. The limited amount of published research on the topic of chainsaw kickback was conducted to develop standardized testing for consumer chainsaws. Modern chainsaws are equipped with safety measures such as low-kickback cutting chains and hand-guard braking mechanisms. These mechanisms have greatly improved the safety of chainsaws, but their inherent mechanical simplicity leaves room for improvement. The current work presents the research that analyzed the possible methods for detecting kickback electronically. Phase 1 of this work utilized a set of two accelerometers and a single gyroscope to determine if it is possible to distinguish a kickback event from normal cutting operations. A method for applying weighting coefficients to the three sensor readings, then summing the three signal values was optimized to obtain the greatest margin between kickback and normal cutting. The result of this study was that kickback is most easily identified by using only a gyroscope and setting a threshold. Phase 2 focused on detecting kickback as early as possible. Three methods were attempted: Signal Differentiation, a Simplified Bag of Words method, and applying a Support Vector Machine with selective undersampling and a stack of classifier vectors. Signal differentiation, while detecting the kickback events earlier, also suffered from many false positives. The Bag of Words method was unsuccessful in creating results different than the threshold method from Phase 1. The Support Vector Machine classification was able to detect kickback an average of 19.4 ms before the simple threshold method with no occurrence of either false positives or false negatives. This method is the most reliable and provides the greatest likelihood of detecting kickback early.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Submitted by Drew Arnold (arnolddr@onid.orst.edu) on 2013-01-05T03:10:50Z No. of bitstreams: 1 DArnold-Thesis-Learning Approaches for the Early Detection of Kickback in Chainsaws.pdf: 5031497 bytes, checksum: 69c170f1f6402f93cb034f4554b171b7 (MD5)
  • description.provenance : Made available in DSpace on 2013-01-10T22:41:15Z (GMT). No. of bitstreams: 1 DArnold-Thesis-Learning Approaches for the Early Detection of Kickback in Chainsaws.pdf: 5031497 bytes, checksum: 69c170f1f6402f93cb034f4554b171b7 (MD5) Previous issue date: 2012-11-27
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2013-01-10T22:41:14Z (GMT) No. of bitstreams: 1 DArnold-Thesis-Learning Approaches for the Early Detection of Kickback in Chainsaws.pdf: 5031497 bytes, checksum: 69c170f1f6402f93cb034f4554b171b7 (MD5)
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2013-01-08T20:53:37Z (GMT) No. of bitstreams: 1 DArnold-Thesis-Learning Approaches for the Early Detection of Kickback in Chainsaws.pdf: 5031497 bytes, checksum: 69c170f1f6402f93cb034f4554b171b7 (MD5)

Relationships

Parents:

This work has no parents.

In Collection:

Items