Smart Design of Cz-Ge Crystal Growth Furnace and Process

Abstract

The aim of this study was to evaluate the potential of the machine learning technique of decision trees to understand the relationships among furnace design, process parameters, crystal quality, and yield in the case of the Czochralski growth of germanium. The ultimate goal was to provide the range of optimal values of 13 input parameters and the ranking of their importance in relation to their impact on three output parameters relevant to process economy and crystal quality. Training data were provided by CFD modelling. The variety of data was ensured by the Design of Experiments method. The results showed that the process parameters, particularly the pulling rate, had a substantially greater impact on the crystal quality and yield than the design parameters of the furnace hot zone. Of the latter, only the crucible size, the axial position of the side heater, and the material properties of the radiation shield were relevant.

Data‐Driven Cz–Si Scale‐Up under Conditions of Partial Similarity

“…Visual inspection of the results reveals a significant influence of the pulling velocity, as confirmed by experimental investigations and our previous findings for Cz–Ge. [ 42 ] Logically, a higher pulling velocity corresponds to a higher v / G value. Conversely, as the crystal length increases (measured as the percentage crystallized), the v / G value decreases.…”

Decision Tree-Supported Analysis of Gallium Arsenide Growth Using the LEC Method

“…Specifically, artificial neural networks (ANNs) have found application in the optimization of crystal growth, e.g., as documented in references [27][28][29][30][31]. Additionally, decision trees (DTs) and random forests have been employed for the analysis of multi-parameter crystal growth [32][33][34]. It is worth noting that while artificial neural networks exhibit excellent fitting capabilities, their effectiveness is contingent upon the availability of substantial training data.…”