Denoising Autoencoders and LSTM-Based Artificial Neural Networks Data Processing for Its Application to Internal Model Control in Industrial Environments-The Wastewater Treatment Plant Control Case.

Ivan Pisa,Ramon Vilanova,Antoni Morell,Jose Lopez Vicario

doi:10.3390/s20133743

Abstract

The evolution of industry towards the Industry 4.0 paradigm has become a reality where different data-driven methods are adopted to support industrial processes. One of them corresponds to Artificial Neural Networks (ANNs), which are able to model highly complex and non-linear processes. This motivates their adoption as part of new data-driven based control strategies. The ANN-based Internal Model Controller (ANN-based IMC) is an example which takes advantage of the ANNs characteristics by modelling the direct and inverse relationships of the process under control with them. This approach has been implemented in Wastewater Treatment Plants (WWTP), where results show a significant improvement on control performance metrics with respect to (w.r.t.) the WWTP default control strategy. However, this structure is very sensible to non-desired effects in the measurements—when a real scenario showing noise-corrupted data is considered, the control performance drops. To solve this, a new ANN-based IMC approach is designed with a two-fold objective, improve the control performance and denoise the noise-corrupted measurements to reduce the performance degradation. Results show that the proposed structure improves the control metrics, (the Integrated Absolute Error (IAE) and the Integrated Squared Error (ISE)), around a 21.25% and a 54.64%, respectively.

Highlights

Nowadays, the Digital Transformation is changing the way of understanding the different processes performed in the industrial sector
MLPd and LSTMd model the direct relationships between the actuation and controlled variables
This scenario has been previously analysed in Reference [20], the Internal Model Controllers (IMC) was implemented with Multilayer Perceptron (MLP) nets and its stability was not computed

Summary

Introduction

The Digital Transformation is changing the way of understanding the different processes performed in the industrial sector. Cyber-Physical Systems have arisen as the main paradigms of this digital transformation. They drive the adoption of new technologies such as data-driven based ones to support and improve the industrial processes. One of the main tools which have arisen as one of the core concepts of the Industry 4.0 paradigm are the Artificial Neural Networks (ANNs) [2]. They are computational models characterised by their capabilities in the modelling of highly complex and non-linear processes performed in several industries such as the chemical one [3]. One of the most important points of ANNs is that they

Methods

Results

Conclusion