距離限制下應用基因演算法之最佳無線感測器布置

Application of genetic algorithm in optimal sensor placement under range constraints

林子陽(Tzu-Yang Lin)

指導教授 ： 洪士林

國立交通大學/工學院/土木工程系所/碩士(2014年)

https://doi.org/10.6842/NCTU.2014.00096

摘要

任何結構上的裂縫都有可能對其結構的安全造成影響，所以結構健康監測系統 (Structural Health Monitoring system，SHM)是必需且重要的。進行SHM時，會在結構物上安裝許多的感測器(sensor)在不同的位置，並藉由接收器(gateway)得到感測器的資訊並將其傳送到系統使用者的面前，藉以判斷此結構的健康程度。不過，感測器布置在結構物上的哪個位置可以使吾輩進行測量時得到最正確、精準的資訊，因此，最佳感測器布置(Optimal Sensor Placement，OSP)便因應而生，本文中，OSP方面利用基因演算法將Fisher Information Matrix(FIM)之絕對值趨近極大做為適應度方程式，將固定數目的無線感測器布置在待測建築上之最佳位置，就不用依靠經驗或盲目地將感測器擺放在或許不是最佳的位置，造成量測的建築物資訊之準確度不佳。在將感測器布置在結構物上最佳位置後，由於無線感測器與接收器有其在資料傳輸距離上的限制以及每個接收器能收集的感測器數量也有其限制，因此接收器的位置係變得事關重要，本文接收器布置中，以此兩限制為前提，同樣利用基因演算法，讓接收器可以完全收集到所有感測器的資訊。最後並利用【Cable Bridge】及【橋上某一跨】兩例對本文中程式進行測試，並與傳統有效的方法Effect Independence Methond(EFI)比較，證明此法有效而且可行。

關鍵字

基因演算法 ； 最佳感測器布置 ； 傳輸距離限制

並列摘要

Structures may be damaged due to ageing of material or by external force. Continued monitoring of structural health monitoring (SHM) system is significant equipment. Hence, how to effectively plan and arrangement of sensors has become the key search topic in SHM. Meanwhile, how to use limited and want sensors to measure structural behavior is an optimal sensor figuration issues. The objective of the present study is based on improved GA algorithm to optimal placement of acceleration sensors for structural health monitoring system. Under a fixed number of sensors, the study will explore how to select the best sensor location emplacement. The determinant of the Fisher Information Matrix (FIM) is employed as a fitness index for GA algorithm for optimal locating sensors. Following, another enhanced GA algorithm is employed to optimal set the gateways for the optimized OSP SHM system acceleration sensors for structural health monitoring system, based on the two constraints, communication distance and number of minimum gateways. Two simulation cases, a cable bridge and a deck of one –bay bridge, are utilized to investigate the performance and possibility of the proposed optimization models. The simulated results reveal that the proposed GA models outperform Effect Independence Method (EFI).

並列關鍵字

Genetic Algorithm ； Optimal Sensor Placement ； Range Constraints

參考文獻

[4] Ting-Hua Yi, Hong-Nan Li,and Ming Gu,“Optimal Sensor Placement for Health Monitoring of High-Rise Structure Based on Gene Algorithm” Mathematical Problems in Engineering, Volume 2011 (2011), Article ID 395101, 12 pages,2010.

[1] H. Y. Guo,L. Zhang,L. L. Zhang and J X Zhou,“Optimal placement of sensorsfor structural health monitoring using improved genetic algorithms” Smart Materials and Structures, Vol. 13, No. 3 ,2004.

[2] Z.N. Li,J. Tang,Q.S. Li,“Optimal sensor locations for structural vibration measurements” Applied Acoustics

[3] 鄭穎泰 “改良式基因演算法對二維鋼構房屋結構斷面最佳化之研究”國立交通大學，碩士論文，民國101年。

[5] W.A. Maul,G. Kopasakis,L.M. Santi,T.S. Sowers and M. Chicatelli,“sensor selection and optimization for health assessment of aeropace systems”Tech. Rep. NASA/TM-2007-214822,2007