Information Technology Reference
In-Depth Information
()
The control objective is to maximize the endpoint concentration of B ,
xt by ma-
nipulating the reactor temperature, T . To proceed with the proposed method, 30
batches of independent random signal with uniform distribution between [0, 1] are
used to obtain input-output data for training purpose. Applying the identification pro-
cedure in [15] results in a neuro-fuzzy model with 6 fuzzy rules.
The robustness of the proposed integrated control system is evaluated by introduc-
ing 5% Gaussian white noise to the measured batch process variables at fifth batch.
As illustrated in Fig. 1 and 2, the proposed integrated control system has reasonable
robustness to stochastic noise.
2
f
Fig. 1. 5-th batch error curves of two methods under the same disturbance
Fig. 2. 5-th batch production quality curves of two methods under the same disturbance
5
Conclusion
The proposed system integrates discrete-time (batch-axis) information and conti-
nuous-time (time-axis) information into one uniform frame. More specifically, the
Search WWH ::




Custom Search