In this paper, statistical experimental design is used to characterize the contact formation process for high-performance silicon solar cells. Central composite design is employed, and neural networks trained by the error back-propagation algorithm are used to model the relationships between several input factors and solar cell efficiency. Subsequently, both genetic algorithms and particle swarm optimization are used to identify the optimal process conditions to maximize cell efficiency. The results of the two approaches are compared, and the optimized efficiency found via the particle swarm method was slightly larger than the value determined via genetic algorithms. More importantly, repeated applications of particle swarm optimization yielded process conditions with smaller standard deviations, implying greater consistency in recipe generation.

This paper explores the use of neural networks for real-time, model-based feedback control of reactive ion etching (RIE). This objective is accomplished in part by constructing a predictive model for the system which can be approximately inverted to achieve the desired control. An indirect adaptive control (IAC) strategy is pursued. The IAC structure includes a controller and plant emulator, which are implemented as two separate backpropagation neural networks. These components facilitate nonlinear system identification and control, respectively. The neural network controller is applied to controlling the etch rate and DC bias while processing a GaAs/AlGaAs metal-semiconductor-metal structure in a BCl/sub 3//Cl/sub 2/ plasma using a Plasma Therm 700 SLR series RIE system. Results indicate that in the presence of disturbances and shifts in RIE performance, the IAC neural controller is able to adjust the recipe to match the etch rate and DC bias to that of the target values in less than 5 s. These results are shown to be superior to those of a more conventional LQG/LTR control scheme based on a linearized transfer function model of the RIE system.

Neural network models of semiconductor manufacturing processes offer advantages in accuracy and generalization over traditional methods. However, model development is complicated by the fact that backpropagation neural networks contain several adjustable parameters whose optimal values are initially unknown. These include learning rate, momentum, training tolerance, and the number of hidden layer neurons. This paper investigates the use of genetic algorithms (GAs) to determine the optimal neural network parameters for modeling plasma-enhanced chemical vapor deposition (PECVD) of silicon dioxide films. To find an optimal parameter set for the PECVD models, a performance matrix is defined and used in the GA objective function. This index accounts for both prediction error as well as training error, with a higher emphasis on reducing prediction error. Results of the genetic search are compared with a similar search using the simplex algorithm. The GA search performed approximately 10% better in reducing training error and 66% better in reducing prediction error.

Silicon dioxide films deposited by plasma-enhanced chemical vapor deposition (PECVD) are useful as interlayer dielectrics for metal-insulator structures. In this study, PECVD modeling using neural networks and genetic algorithms is introduced. The deposition process was characterized via a fractional factorial experiment, and data from this experiment were used to train feed-forward neural networks using the error back-propagation algorithm. The networks were optimized to minimize both learning and prediction error. The optimal neural process models were then used for recipe synthesis to generate the proper deposition conditions to obtain specific film properties. The response surfaces of the neural process models were explored using genetic algorithms, and the performance of this procedure was evaluated by comparing the deposition conditions indicated by the generic algorithms with the neural process model predictions.>