• Corpus ID: 113984509

Neural Network Predictive R2R Control to CMP Process

@inproceedings{Wang2011NeuralNP,
  title={Neural Network Predictive R2R Control to CMP Process},
  author={L. Wang and Jt Hu},
  year={2011}
}

• L. Wang, J. Hu
• Published 2011
• Computer Science

For chemical mechanical polishing(CMP)process characteristics of nonlinear, time-varying and not being in-situ measured, this paper proposes a CMP process neural network predictive run-to-run(R2R) controller named NNPR2R. RBF neural network predictive model about CMP is constructed by subtractive clustering algorithm and least squares method, thus it solves difficult problem of constructing accurate mathematical model of complicated CMP process and improves the prediction accuracy. Control law of model predictive control is obtained by feedback correction and PSO rolling optimization, therefore it solves the problem that derivative-based optimization technology is easy to fall into local optimum and improves control precision. Simulation results illustrate that performance of NNPR2R controller is better than EWMA, process drifts and shifts is suppressed significantly, product quality variation between different runs is reduced, and root mean squared error for material removal rate(MRR) is brought down substantially.