| 摘要 |
A computer neural network regulatory process control system and method allows for the elimination of human operator from real time control of the process. The present invention operates in three modes: training, operation (prediction), and retraining. In the training mode, training input data is produced by the control adjustment made to the process by the human operator. The neural network of the pres- ent invention is trained by producing output data using input data for prediction. The output data is compared with the training input data to produce error data, which is used to adjust the weight(s) of the neural network. When the error data is less than a preselected criterion, train- ing has been completed. In the operation mode, the neural network of the present invention provides output data based upon predictions us- ing the input data. The output data is used to control a state of the pro- cess via an actuator. In the retraining mode, retraining data is supplied by monitoring the supplemental actions of the human operator. The retraining data is used by the neural network for adjusting the weight(s) of the neural network.
|
