No abstract

Defect‐assisted recombination often restricts the performance of photovoltaic devices, and in order to mass‐produce reliable solar cells, low‐cost express methods are in demand, which could monitor contamination during the process of manufacture. In our work, we applied the deep learning‐based approach for estimating iron concentration in silicon solar cells by using ideality factor. The simulation of solar cells with the back surface field design for generating labeled training and test datasets was performed using SCAPS‐1D software. Our results demonstrate that deep neural networks can predict iron concentration using the ideality factor, temperature, base‐thickness, and doping level of solar cells. Our simulation showed smaller prediction errors at high doping level, low temperature, and the two values of ideality factor: the first one for structures containing only iron interstitial atoms and the second for structures where Fei and iron–boron pairs coexist. The proposed method was tested on real silicon structures.

The original automated method of measurement of electrical noise in the return electric-traction network is proposed. It is realized on the base of car-laboratory “Automatics, telemechanics and communication”. The mathematic model of return electric-traction network is developed to scientific bases of automated measurement. It allows us obtaining the mathematic expressions for change of voltage and current harmonics in the rail net and taking into account the inhomogeneity of lines for the following analytic determination of a source of electric noise.

A mathematical model describing distribution of an electromagnetic field around a rail with account of skineffect in rail steel is developed and experimental measurements of a magnetic intensity are carried out.

The construction and operation principle of track circuit protection system from electromagnetic hindrances have been considered in the article. The cost efficiency of introducing the system has been estimated.