# Method for Detecting Disorder of a Nonlinear Dynamic Plant

## TL;DR

This paper introduces a new method called CCF-AE for detecting disorders in nonlinear dynamic systems using input-output data and neural networks.

## Contribution

The novel CCF-AE method detects disorders without needing a reference model, using cross-correlation and autoencoders.

## Key findings

- CCF-AE outperforms CUSUM and EWMV in true detection rates and false alarm rates.
- CCF-AE is more effective for detecting disorders in complex nonlinear processes.
- The method was successfully tested on a nonlinear pH neutralization reaction process.

## Abstract

This paper proposes a new disorder detection method CCF-AE for a scalar dynamic plant based only on its input–output relation using a cross-correlation function and neural network autoencoder. The CCF-AE method does not use the reference model of the dynamic object, but only considers real-time behavior changes, given by input and output time series. The proposed method was used to detect disorder in the process of a nonlinear pH neutralization reaction, and was compared with the cumulative sum control chart (CUSUM) and the exponentially weighted moving variance control chart (EWMV). The CCF-AE method demonstrates a better true detection rate and lower false alarm rate than CUSUM and EWMV. Also, CCF-AE has more advantages in detecting disorder of complex nonlinear processes.