Mr Rinta-aho received his M.Sc. degree in Physics at University Helsinki in 2016. At the moment, he is working as Research Scientist at VTT Technical Research Centre of Finland Ltd. His scientific interest includes quantitative NDE, ultrasound physics and artificial intelligence.
Machine learning and multimethod-NDE for estimating neutron-induced embrittlement
In this study, 157 irradiated and non-irradiated Charpy specimens  manufactured from six different steel alloys used in the reactor pressure vessels (18MND5-W, 22NiMoCr37, A508-B, 15Kh2NMFA, HSST03 and A508-Cl2) were measured. The measurements included determining several non-destructively measurable electric, magnetic and elastic parameters. The applied non-destructive methods were Direct Current-Reversal Potential Drop (resistivity) , 3MA (eddy current impedance loop shape) , TEP (Seebeck Coefficient) , MIRBE (Barkhausen noise) , MAT (magnetic hysteresis loop shape)  and sound velocity. After the non-destructive measurements, the ductile-brittle transition temperature (DBTT) was determined destructively using the ISO-standard method .
Several different regression algorithms, including neural network regression and support vector regression, were applied to the data. The algorithms were implemented with TensorFlow and scikit-learn using Python 3.7. With these algorithms, it was possible to estimate the DBTT with the mean absolute error smaller than 20 °C. Based on the results, the method can be seen as a potential candidate for estimating neutron-induced embrittlement non-destructively.
 ISO-148.  J. Rinta-aho et. al. Baltica XI (2019).  G. Dobmann et. al. Electromagnetic Nondestructive Evaluation (2008).  M. Niffenegger and H. J. Leber J. Nuclear Mat. 389(1), 62-67, (2009).  I. Tomáš et. al. Nuclear Engineering and Design 265, 201-209, (2013).
Ultrasound as a non-destructive tool to estimate polymer embrittlement
There is approximately 1500 km of electric cables in a single NPP. During operation, some of these cables are exposed to high level gamma irradiation. Gamma radiation is known to brittle polymers such as polyethylene used as insulator in these cables. Since the planned lifetime for a single NPP is 60 to 80 years, a low-cost method to estimate the embittlement level non-destructively is required.
While polyethylene ages, Elongation at Break (EaB) decreases and Young’s modulus increases. Since sound velocity for longitudinal wave mode in homogenous and isotropic media is a function of Young’s modulus, Poisson’s ratio and density (Eq. 1), it can be used as a non-destructive indicator for embrittlement.
While polyethylene ages, Elongation at Break (EaB) decreases and Young’s modulus increases. Since sound velocity for longitudinal wave mode in homogenous and isotropic media is a function of Young’s modulus, Poisson’s ratio and density (Eq. 1), it can be used as a non-destructive indicator for embrittlement. In our study, 10 specimens of commercially available coaxial cable were exposed to gamma irradiation using two different dose rates and five different total doses. Then, the sound velocities were measured using traditional pulse-echo approach with an integrated transducer-micrometer setup developed by VTT. EaB values were measured via tensile testing by ÚJV.
The results clearly show, that sound velocity increases and EaB decreases when polyethylene is exposed to gamma irradiation. The correlation between sound velocity and EaB is linear. Based on the results, it is possible to use sound velocity as a low-cost non-destructive indicator for gamma-irradiation induced degradation of polyethylene