Fuzzy inference system used for a quantitative evaluation of the material discontinuities detected by eddy current sensors

The automatic systems for eddy current non-destructive control permit rendering evident superficial discontinuities in the electroconductive products. Their response is influenced by numerous factors and therefore it is quite difficult to quantitatively estimate the shape and severity of the detected discontinuity, based on the sensor's response. This work presents an artificial intelligence system based on fuzzy logic, dedicated to the quantitative evaluation of the severity of material discontinuities existing on wires, which dramatically reduces noise influence and enables to determine the discontinuity depth as a function of prescribed quality classes.