A uniform initialization Gaussian mixture model–based guided wave–hidden Markov model with stable damage evaluation performance

Structural Health Monitoring - Tập 18 Số 3 - Trang 853-868 - 2019
Shenfang Yuan1, Jinjin Zhang1, Jian Chen1, Lei Qiu1, Weibo Yang1
1Research Center of Structural Health Monitoring and Prognosis, State Key Lab of Mechanics and Control of Mechanical Structures, Nanjing University of Aeronautics and Astronautics, Nanjing, China

Tóm tắt

During practical applications, the time-varying service conditions usually lead to difficulties in properly interpreting structural health monitoring signals. The guided wave–hidden Markov model–based damage evaluation method is a promising approach to address the uncertainties caused by the time-varying service condition. However, researches that have been performed to date are not comprehensive. Most of these research studies did not introduce serious time-varying factors, such as those that exist in reality, and hidden Markov model was applied directly without deep consideration of the performance improvement of hidden Markov model itself. In this article, the training stability problem when constructing the guided wave–hidden Markov model initialized by usually adopted k-means clustering method and its influence to damage evaluation were researched first by applying it to fatigue crack propagation evaluation of an attachment lug. After illustrating the problem of stability induced by k-means clustering, a novel uniform initialization Gaussian mixture model–based guided wave–hidden Markov model was proposed that provides steady and reliable construction of the guided wave–hidden Markov model. The advantage of the proposed method is demonstrated by lug fatigue crack propagation evaluation experiments.

Từ khóa


Tài liệu tham khảo

10.1098/rsta.2006.1935

10.1177/1475921711414232

10.1177/1475921714522846

10.1016/j.jsv.2009.01.052

10.1177/1045389X12460433

10.1016/j.ymssp.2015.01.020

10.1016/j.ultras.2014.12.005

10.1177/1475921713517288

10.1177/1475921708090561

10.1016/j.ymssp.2011.09.023

10.1177/1475921713506767

10.1016/j.jsv.2007.06.058

10.1016/j.compstruct.2015.03.014

10.3390/ma10060648

10.1088/0964-1726/23/12/125001

10.1109/JPROC.2013.2251852

10.1016/j.ymssp.2015.10.003

Rammohan R, IEEE international conference on systems, man and cybernetics, 1524

10.1109/JSEN.2009.2019330

10.1177/1045389X08099968

10.1088/0964-1726/25/2/025021

10.1109/MASSP.1986.1165342

10.1016/j.ijfatigue.2013.03.016

10.1088/1361-665X/aa7168

10.1348/000711005X48266

10.1016/j.sna.2009.02.032

10.1093/bioinformatics/btq498

Thông tin
Thông tin xuất bản

Structural Health Monitoring

Tập 18 Số 3

853-868

Thông tin tác giả