Co‐evolutionary algorithm for structural damage identification using minimal physical testing

Kouchmeshky, Babak; Aquino, Wilkins; Bongard, Josh; Lipson, Hod

doi:10.1002/nme.1803

Cited by 44 publications

(29 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A second evolutionary algorithm optimizes a set of models against the current set of training data. We have applied the EEA to problems in machine learning [4], gene network identification [9], damage localization in truss structures [17], and to robotics [7]. The EEA applied to a quadrupedal robot.…”

Section: Introductionmentioning

confidence: 99%

Action-selection and crossover strategies for self-modeling machines

Bongard

2007

Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

In previous work [7] a computational framework was demonstrated that employs evolutionary algorithms to automatically model a given system. This is accomplished by alternating the evolution of models with the evolutionary search for new training data. Theory predicts [23] that the best new training data is that which induces maximum disagreement across the current model set. Here it is demonstrated that in a robot application this is not the case, and alternative fitness functions are developed that seek other, better training data. Also, it is shown that although crossover successfully reduces the mean error of the model set, it compromises the ability of the framework to find new, informative training data. This has implications for how to create adaptive, selfmodeling machines, and suggests how competitive processes in the brain underlie the generation of intelligent behavior.

show abstract

Section: Introductionmentioning

confidence: 99%

Action-selection and crossover strategies for self-modeling machines

Bongard

2007

Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…[11,13]). In [4], Bongard and Lipson present a nonlinear system identification method called estimation-exploration algorithm, which co-evolves tests and models in a way that minimizes the amount of tests (in this study performed in simulation).…”

Section: System Identification Through Coevolutionary Algorithmsmentioning

confidence: 99%

A coevolutionary approach to learn animal behavior through controlled interaction

Gauci

Groß

2013

Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

This paper proposes a method that allows a machine to infer the behavior of an animal in a fully automatic way. In principle, the machine does not need any prior information about the behavior. It is able to modify the environmental conditions and observe the animal; therefore it can learn about the animal through controlled interaction. Using a competitive coevolutionary approach, the machine concurrently evolves animats, that is, models to approximate the animal, as well as classifiers to discriminate between animal and animat. We present a proof-of-concept study conducted in computer simulation that shows the feasibility of the approach. Moreover, we show that the machine learns significantly better through interaction with the animal than through passive observation. We discuss the merits and limitations of the approach and outline potential future directions.

show abstract

“…Although dynamic testing has its merits, static testing using trucks may be a simpler alternative for some bridges. For its simplicity and practicality, many algorithms employ static testing to identify damage [3][4][5][6]22]. However, no study has been conducted yet that used multi-objective optimization combined with the static testing.…”

Section: Introductionmentioning

confidence: 99%

Robust structural damage identification based on multi‐objective optimization

Jung

Song

2009

Numerical Meth Engineering

View full text Add to dashboard Cite

SUMMARYInverse analysis for structural damage identification often involves an optimization process that minimizes the discrepancies between the computed responses and the measured responses. Conventional singleobjective optimization approach defines the objective function by combining multiple error terms into a single one, which leads to a weaker constraint in solving the identification problem. A multi-objective approach is proposed, which minimizes multiple error terms simultaneously. Its non-domination-based convergence provides a stronger constraint that enables robust identification of damages with lower falsenegative detection rate. Another merit of the proposed approach is quantified confidence in damage detection through processing Pareto-optimal solutions. Numerical examples that simulate static testing are provided to compare the proposed approach with conventional formulation based on single-objective optimization.

show abstract

Co‐evolutionary algorithm for structural damage identification using minimal physical testing

Cited by 44 publications

References 13 publications

Action-selection and crossover strategies for self-modeling machines

Action-selection and crossover strategies for self-modeling machines

A coevolutionary approach to learn animal behavior through controlled interaction

Robust structural damage identification based on multi‐objective optimization

Contact Info

Product

Resources

About