Deterministically generated negative selection algorithm for damage detection in civil engineering systems

Abstract In the framework of Structural Health Monitoring, vibration-based methods are commonly used to assess the condition of a structural system, being the dynamic properties sensitive to damage-induced changes. Within this context, negative selection, a bio-inspired classification algorithm, can be exploited to distinguish anomalous from normal behaviours by comparing the monitored system features with a set of detectors appropriately trained to spot any possible anomaly inside the unitary feature space. Such method results particularly convenient due to its easy implementation, low computational cost and capability to carry out the classification based on a training set of data belonging only to a healthy-state condition. This circumstance is extremely common in real civil engineering applications where no knowledge might exist about different structural conditions over time. In this paper, a negative-selection algorithm with a non-random strategy for detector generation is developed and tested on a numerical case study, namely a model simulating the I-40 Bridge over the Rio Grande in Albuquerque, New Mexico (USA). The work carried out proves that the algorithm is suitable for the purpose of damage detection (a binary classification problem) and, by introducing the anomaly score as a qualitative measure of the level of damage, provides a sound analysis of the method multiclass classification skills, aiming at the quantification of the damage.

[1]  Keith Worden,et al.  An introduction to structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[2]  Charles R. Farrar,et al.  Finite element analysis of the I-40 bridge over the Rio Grande , 1996 .

[3]  Mihály Csaba Markót.  Robust Designs for Circle Coverings of a Square , 2015 .

[4]  Akira Mita,et al.  Hybrid Methodology for Structural Health Monitoring Based on Immune Algorithms and Symbolic Time Series Analysis , 2013 .

[5]  Dong Li,et al.  A method of anomaly detection and fault diagnosis with online adaptive learning under small training samples , 2017, Pattern Recognit..

[6]  Miao Li,et al.  Negative Selection Algorithm Using Natural Frequency for Novelty Detection under Temperature Variations , 2010 .

[7]  Cecilia Surace,et al.  A Negative Selection Approach to detect damage in aeronautical structures with changing Operating Conditions , 2008 .

[8]  D. Dasgupta,et al.  Combining negative selection and classification techniques for anomaly detection , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[9]  Ricardo Perera,et al.  Power mode shapes for early damage detection in linear structures , 2009 .

[10]  Fábio Roberto Chavarette,et al.  A Comparison of Methodologies for Intelligent Computing Used to Integrity Analysis of a Structure Aeronautic , 2014 .

[11]  Dong Li,et al.  Negative selection algorithm with constant detectors for anomaly detection , 2015, Appl. Soft Comput..

[12]  Zhou Ji,et al.  Applicability issues of the real-valued negative selection algorithms , 2006, GECCO.

[13]  Fábio Roberto Chavarette,et al.  Artificial Immune Systems with Negative Selection Applied to Health Monitoring of Aeronautical Structures , 2013 .

[14]  Fernando Niño,et al.  Recent Advances in Artificial Immune Systems: Models and Applications , 2011, Appl. Soft Comput..

[15]  Charles R. Farrar,et al.  Dynamic characterization and damage detection in the I-40 bridge over the Rio Grande , 1994 .

[16]  Fabio A. González,et al.  Anomaly Detection Using Real-Valued Negative Selection , 2003, Genetic Programming and Evolvable Machines.

[17]  Fábio Roberto Chavarette,et al.  Artificial Immune Systems Applied to the Analysis of Structural Integrity of a Building , 2014 .

[18]  Reha Uzsoy,et al.  Experimental Evaluation of Heuristic Optimization Algorithms: A Tutorial , 2001, J. Heuristics.

[19]  Simon M. Garrett,et al.  How Do We Evaluate Artificial Immune Systems? , 2005, Evolutionary Computation.

[20]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[21]  Akira Mita,et al.  Abnormal state detection of building structures based on symbolic time series analysis and negative selection , 2014 .

[22]  Mauricio G. C. Resende,et al.  Designing and reporting on computational experiments with heuristic methods , 1995, J. Heuristics.

[23]  Claudia Eckert,et al.  Is negative selection appropriate for anomaly detection? , 2005, GECCO '05.

[24]  Zhou Ji,et al.  Revisiting Negative Selection Algorithms , 2007, Evolutionary Computation.

[25]  A. Heppes,et al.  Covering a Rectangle With Equal Circles , 1997 .

[26]  Henri Pierreval,et al.  Fault detection, diagnosis and recovery using Artificial Immune Systems: A review , 2015, Eng. Appl. Artif. Intell..

[27]  Cecilia Surace,et al.  A negative selection approach to novelty detection in a changing environment , 2006 .

[28]  Dong Li,et al.  A negative selection algorithm with online adaptive learning under small samples for anomaly detection , 2015, Neurocomputing.

[29]  Alan S. Perelson,et al.  Self-nonself discrimination in a computer , 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy.