Research breakthrough possible @S-Logix pro@slogix.in

Office Address

  • 2nd Floor, #7a, High School Road, Secretariat Colony Ambattur, Chennai-600053 (Landmark: SRM School) Tamil Nadu, India
  • pro@slogix.in
  • +91- 81240 01111

Social List

Fault Detection and Diagnosis for Non-Linear Processes Empowered by Dynamic Neural Networks - 2022

Fault Detection And Diagnosis For Non-Linear Processes Empowered By Dynamic Neural Networks

Research Paper on Fault Detection And Diagnosis For Non-Linear Processes Empowered By Dynamic Neural Networks

Research Area:  Machine Learning

Abstract:

In the era of the 4th industrial revolution, a key challenge for the industries is the efficient reduction of the production cost caused by malfunctioning equipment. This paper proposes a Fault Detection and Diagnosis (FDD) framework for Non-Linear Processes utilizing Dynamic Neural Networks and feature reduction methods. We investigate both types of dynamic neural models, ie. Recurrent Neural Networks -in particular Long Short-Term Memory (LSTM) models, and Time Delay Neural Networks (TDNN). Intending to mitigate the overfitting problem, we also investigated the use of feature reduction techniques such as Non-Negative Matrix Factorization (NMF), Principal Component Analysis (PCA), and kernel PCA (kPCA), as preprocessing steps in our Machine Learning pipeline. The Tennessee Eastman Process (TEP) is used to evaluate our proposed framework on 18 different faults. Our simulations demonstrate that our method outperforms state of the art methods in the majority of those faults.

Keywords:  
Fault Detection And Diagnosis
Non-Linear Processes
Dynamic Neural Networks
Long Short-Term Memory (LSTM)
Time Delay Neural Networks (TDNN)
Principal Component Analysis
Deep Learning
Machine Learning

Author(s) Name:  Georgios Gravanis, Ioannis Dragogias, Konstantinos Papakiriakos, Chrysovalantou Ziogou, Konstantinos Diamantaras

Journal name:  Computers & Chemical Engineering

Conferrence name:  

Publisher name:  Elsevier

DOI:  10.1016/j.compchemeng.2021.107531

Volume Information:  Volume 156, January 2022, 107531