• Title/Summary/Keyword: identification of obstacle shape

Search Result 4, Processing Time 0.021 seconds

Obstacle Identification by Parabolic Curve Fitting using Ultrasonic Sensors Arranged on Ring Frame (링 프레임형 초음파 센서의 포물선 피팅에 의한 장애물 식별)

  • Jang, Jin-Su;Park, Tai-Jin;Lim, Zhong-Soo;Joo, Moon-G.
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.18 no.10
    • /
    • pp.934-939
    • /
    • 2012
  • This paper proposes a new algorithm for ultrasonic sensors arranged on ring frame to identify obstacles surrounding itself by TOFs (time of flight). The ring frame has multiple channels consisting of a transmitter and a receiver. When the transmitter of a selected channel transmits ultrasonic signal, the TOFs of reflected signals from obstacles are acquired by the receiver of the channel. The process continues for all channels consecutively. Then, by using parabolic curve fitting of TOFs of all channel, the proposed algorithm not only calculates distances from multiple obstacles, but also identifies if the shape of obstacles are point or plane by the coefficients of the curve. By the experiment using 16 ultrasonic transceivers on the ring frame in the environment of two poles and two planes, we show the feasibility of the proposed scheme.

Extraction of bridge information based on the double-pass double-vehicle technique

  • Zhan, Y.;Au, F.T.K.;Yang, D.
    • Smart Structures and Systems
    • /
    • v.25 no.6
    • /
    • pp.679-691
    • /
    • 2020
  • To identify the bridge information from the response of test vehicles passing on it (also known as the indirect approach) has aroused the interest of many researchers thanks to its economy, easy implementation and less disruption to traffic. The surface roughness of bridge remains an obstacle for such method as it contaminates the vehicle response severely and thereby renders many vehicle-response-based bridge identification methods ineffective. This study aims to eliminate such effect with the responses of two different test vehicles. The proposed method can estimate the surface profile of a bridge based on the acceleration data of the vehicles running on the bridge successively, and obtain the normalized contact point response, which proves to be relatively immune to surface roughness. The frequencies and mode shapes of bridge can be further extracted from the normalized contact point acceleration with spectral analysis and Hilbert transform. The effectiveness of the proposed method is verified numerically with a three-span continuous bridge. The influence of measurement noise is also examined.

Hybrid machine learning with mode shape assessment for damage identification of plates

  • Pei Yi Siow;Zhi Chao Ong;Shin Yee Khoo;Kok-Sing Lim;Bee Teng Chew
    • Smart Structures and Systems
    • /
    • v.31 no.5
    • /
    • pp.485-500
    • /
    • 2023
  • Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

A Study on the Development of the Collision Prevention System for Aids to Navigation by Early Identification of the Tug Boat (예인선 조기 식별을 통한 항로표지시설 추돌 방지 시스템 개발 연구)

  • Han, Ju-Seop;Yu, Yong-Su;Park, Tae-Keun;Kim, Hwa-Young
    • Journal of Navigation and Port Research
    • /
    • v.43 no.6
    • /
    • pp.437-443
    • /
    • 2019
  • Aid to navigation is a navigational aid facility that informs a sailing vessel of its location and direction as well as a location of a specific obstacle by means of a light, shape, color, sound, radio wave, etc. It can be valuable in improving the safety of day and night vessel navigation at sea. For the safety of the tug boat, the minimum equipment requirements for each type of tug boat are arranged. Despite these preparations, the collision accidents between tug boats, barges, and light buoys can occur when the tug boat turns due to the length of the tow-line, tidal current, and the barge's momentum etc. The purpose of this study was to propose the basic system that analyzes the physical relationship between two vessels regarding the tug boat-barge-light buoy dynamics and propagate the corresponding data through the aid to navigation management & operation systems in use at each regional oceans and fisheries.