Knowledge extraction algorithms dedicated for identification of steel bars in reinforced concrete structures

Abstract

The purpose of this paper is to present knowledge extraction algorithms, dedicated for new electromagnetic system used to evaluate steel bars in reinforced concrete structures. All stages of the rebar identification process have been presented. At the first step, relations between parameters of the tested structure and measured waveform are extracted. For this purpose, a dedicated association rules learning algorithm is proposed. In the next stage, the collected data are filtered and smoothed. Finally, classification models are implemented, tested and evaluated. The experimental verification of the applied techniques was carried out, and the selected results are presented.

Identification of rebars in a reinforced mesh using eddy current method

“…The curse of dimensionality can be avoided by reducing number of the dimensions. Usually only a few attributes is enough to build the optimal classification model [4,5]. However, in the presented case only possibility that attributes are useless is very high correlation with the other one or very high impact of the noise, then reduction of attributes number means usually reduction of available knowledge.…”

“…[4,5]) the identification problems were solved by the simple classification algorithms, like Naive Bayes, Neural Networks, Decision Tree etc. These methods are effective when investigator want to check the correctness of his hypothesis or method.…”

“…This article proposes software solutions, which allow eliminating or reducing both of these problems. The utilized system was presented in the previous works [4,5], it consists of the E-shape differential transducer (Fig. 1a) and four subsystems: a XYZ scanner, an excitation subsystem, a data acquisition subsystem and a controlling computer.…”

Detection and Inspection of Steel Bars in Reinforced Concrete Structures Using Active Infrared Thermography with Microwave Excitation and Eddy Current Sensors

“…The eddy current method uses the phenomena of electromagnetic induction to detect inner flaws or inclusions in the examined materials. This method is a natural choice in the case of conducting materials and the possibility of using it in rebar detection has been discussed earlier [ 34 , 35 , 36 , 37 ]. Here we present the multi-frequency technique and we propose a method that may be used for the problem of identification of chosen parameters of the rebar on the basis of obtained signals.…”

“…During this investigations the assessment of distance between the ferromagnetic material and transducer was considered the simplest task ( Figure 13 ). However like with SFM, the set of most useful attributes was selected and association rules were inferred [ 35 , 36 ]. Rough set theory was used for this purpose [ 38 , 39 ].…”