(107b) Visualization and Visual Analysis of Batch-Continuous Process Data

The operation of batch-continuous processes is a unique case as it contains the characteristics of both batch and continuous processes. The retention of characteristics unique to each type of process while also including interactions between the sub-processes render the operation of batch-continuous process an interesting topic of study.

While the design^1,2 and scheduling^3,4 of batch-continuous processes have received some attention in the literature, the monitoring of such processes remains unstudied. We will discuss a novel geometric method for data-driven monitoring of batch-continuous processes in this presentation. Our work is an extension of the time-explicit Kiviat (radial) plot visualization and fault detection frameworks that were previously developed for both continuous processes⁵ as well as batch processes⁶. In this framework, each sample data point of the multivariate time-series collected from process operations is represented in a radial plot. These plots are stacked vertically in the order they were acquired, resulting in a time-explicit representation of the multivariate time series. The geometric properties of this setup allow for the process state at a given time to be represented as a single point, the centroid of the corresponding polygon in radial coordinates.

To extend these ideas to batch-continuous processes, we propose a parallel monitoring fault detection algorithm, whereby fault detection for the whole process is done at any given time by executing both continuous and batch fault detection algorithms in parallel. Based on the fault detection results of both algorithms we are able to identify if a fault exists in the process, and if so, which part of the process (batch or continuous) is the fault located in.

We will also introduce the use of classification techniques that will be used to split process data into batch and continuous process training data for the generation of the appropriate confidence regions. We demonstrate our methodology on a simulation case study of a batch-continuous process.

 

References

1. Knopf, F. Carl, Martin R. Okos, and Gintaras V. Reklaitis. "Optimal design of batch/semicontinuous processes." Industrial & Engineering Chemistry Process Design and Development 21.1 (1982): 79-86.
2. Yeh, N. C., and G. V. Reklaitis. "Synthesis and sizing of batch/semicontinuous processes: single product plants." Computers & chemical engineering 11.6 (1987): 639-654.
3. Ierapetritou, M. G., and C. A. Floudas. "Effective continuous-time formulation for short-term scheduling. 2. Continuous and semicontinuous processes." Industrial & engineering chemistry research 37.11 (1998): 4360-4374.
4. Karimi, Iftekhar A., and Conor M. McDonald. "Planning and scheduling of parallel semicontinuous processes. 2. Short-term scheduling." Industrial & Engineering Chemistry Research 36.7 (1997): 2701-2714.
5. Wang, R. C., Edgar, T. F., Baldea, M., Nixon, M., Wojsznis, W., & Dunia, R. (2015). Process fault detection using time‐explicit Kiviat diagrams. AIChE Journal, 61(12), 4277-4293
6. Wang, R., Baldea, M., & Edgar, T.F. (2015). Visualization and Data-Driven Monitoring of Batch Processes. 2015 AIChE Annual Meeting, 418567