Wooden Pole Inspection with a Neural Network Approach

Thumbnail Image

Files

Wu_umbc_0434M_11579.pdf (3.38 MB)

Links to Files

Permanent Link

http://hdl.handle.net/11603/15720

Collections

UMBC Theses and Dissertations

Author/Creator

Author/Creator ORCID

Date

2016-01-01

Type of Work

theses
Text

Department

Mechanical Engineering

Program

Engineering, Mechanical

Citation of Original Publication

Rights

This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
Distribution Rights granted to UMBC by the author.

Subjects

Wooden Pole

Abstract

Wooden poles are one of the most commonly used utility carriers in North America. Even though they are under different protection treatments, after decades of weatherworn, wooden poles might have defection because of four main factors: Oxygen, Moisture, Temperature, and PH level, which are suitable for worm growth. Since maintenance and replacement of wooden poles are mainly based on their damage inspection results, an accurate and effective damaging inspection method for wooden poles is essential. However, accuracy of the damage inspection method used by the Baltimore Gas and Electric Company is highly dependent on technicians' experience and inspections always cause extra damage to wooden poles. In this work, an accurate and effective vibration-based wooden pole inspection method is developed in conjunction with a neural network approach. Since the current inspection method is vibration-based, it would not cause any damage to wooden poles during inspection. Lab testing is first conducted using wood samples to verify feasibility of the current inspection method, and two vibration-measurement approaches, which use a microphone and accelerometers, are used to obtain data for neural network analysis. Results from the neural network show that the current method can accurately and effectively identify healthy and damaged wood samples. Field testing is then conducted for real wooden poles. Due to complex environment background noise, data from the microphone are no longer effective for neural network analysis and only those from accelerometers are obtained and analyzed using the neural network approach. One hundred wooden poles are tested and final results show that the current vibration-based wooden pole inspection method with the neural network is accurate and effective.