An automatic system using mobile-agent software to model the calculation process of a chemical vapor deposition film deposition simulator.

We have developed an automatic modeling system for calculation processes of the simulator to reproduce experimental results of chemical vapor deposition (CVD), in order to decrease the calculation cost of the simulator. Replacing the simulator by the mathematical models proposed by the system will contribute towards decreasing the calculation costs for predicting the experimental results. The system consists of a mobile agent and two software resources in computer networks, that is, generalized modeling software and a simulator reproducing cross-sections of the deposited films on the substrates with the micrometer- or nanometer-sized trenches. The mobile agent autonomously creates appropriate models by moving to and then operating the software resources. The models are calculated by partial least squares regression (PLS), quadratic PLS (QPLS) and error back propagation (BP) methods using artificial neural networks (ANN) and expresses by mathematical formulas to reproduce the calculated results of the simulator. The models show good reproducibility and predictability both for uniformity and filling properties of the films calculated by the simulator. The models using the BP method yield the best performance. The filling property data are more suitable to modeling than film uniformity.

An automatic modeling system of the reaction mechanisms for chemical vapor deposition processes using real-coded genetic algorithms.

The identification of appropriate reaction models is very helpful for developing chemical vapor deposition (CVD) processes. In this study, we have developed an automatic system to model reaction mechanisms in the CVD processes by analyzing the experimental results, which are cross-sectional shapes of the deposited films on substrates with micrometer- or nanometer-sized trenches. We designed the inference engine to model the reaction mechanism in the system by the use of real-coded genetic algorithms (RCGAs). We studied the dependence of the system performance on two methods using simple genetic algorithms (SGAs) and the RCGAs; the one involves the conventional GA operators and the other involves the blend crossover operator (BLX-alpha). Although we demonstrated that the systems using both the methods could successfully model the reaction mechanisms, the RCGAs showed the better performance with respect to the accuracy and the calculation cost for identifying the models.