Health Assessment of Concrete Dams by Overall Inverse Analyses and Neural Networks

Abstract

In several existing dams alcali-silica reaction (ASR) during several decades of service life, or diffused micro-cracking (due to concrete ageing and/or past extreme loads, such as earthquakes) give rise to deterioration of concrete stiffness and to correlated reduction of its strength. An inverse methodology is presented herein apt to identify damage in concrete dams on the basis of hydrostatic loading, measurements by traditional monitoring instruments, such as pendulums and collimators, and artificial neural networks trained by means of finite-element simulations. The arch-gravity dam referred to in this study is sub-divided into homogeneous zones, to which a constant Young modulus is attributed as unknown parameter which quantifies possible damage. These elastic moduli are estimated on the basis of pseudo-experimental data and identification procedures. After a suitable 'training' process, artificial neural networks (ANNs) are employed for numerical solutions of the inverse problem, and their potentialities and limitations are examined to the present purposes. In particular, they turn out to be robust and practically useful in the presence of information which are scarce quantitatively (few available measurements) and/or qualitatively (large noise-to-signal ratio).

Concrete dam deformation prediction model for health monitoring based on extreme learning machine

“…Integrity evaluation of concrete dams is an important engineering task, because many existing concrete dams, most of which were built several decades ago, are deteriorated by physical–chemical processes and/or past extreme loadings, and their failure might cause huge losses of personal and property safety of residents living in the downstream of concrete dams . The foundation of accurate integrity evaluation is based on the whole continuous historical data gained by use of effective measurement instruments.…”

Interpretation of concrete dam behaviour with artificial neural network and multiple linear regression models

“…Some works related to this subject can be mentioned such as Perner et al [4], Gomes and Awruch [5], Fedele et al [6], Feng and Zhou [7], Bakhary et al [8], Wang and He [9], Wen et al [10], Liu et al [11], Joghataie and Dizaji [12] and Yi et al [13].…”

Diagnosis of concrete dams by flat-jack tests and inverse analyses based on proper orthogonal decomposition

“…accelerometers [Loh and Wu 2000]; (d) statical overall inverse analyses under loading due to ad hoc changes of water level in the reservoir, with measurements of consequent displacements by means of pendulums, collimators and/or interferometric radar [Fedele et al 2006]; (e) same as (d), but with loading provided by seasonal, in-service variation of reservoir level (such alternative is much more economical than (d), however it requires more complex inverse analyses taking into account thermal effects as well [Ardito et al 2008]). Diagnostic procedures (c), (d) and (e) lead to the assessment of Young modulus only.…”