The application of neural network soft sensor technology to an advanced control system of distillation operation

For successful monitoring and controlling chemical process, an accurate on-line measurement of important quality variables is essential. However, these variables usually are difficult to measure on-line due to the limitations such as the time delay, high cost and reliability, so they cannot be directly close-loop controlled. In view of the problem above existing in an industry distillation column, a new design methodology is proposed. At first, an adaptive soft sensor instrument based on neural network technology was constructed as an alternative for the physical sensors. Then, the soft-instrument is correctly applied to an advanced control system and run successfully on DCS equipment. The data measured online show the control system has realized the quality close-loop control very well.