Development of a Methodology Using Artificial Neural Network in the Detection and Diagnosis of Faults for Pneumatic Control Valves.

Ana Andrade,Kennedy Lopes,André Maitelli,Bernardo Lima

doi:10.3390/s21030853

Abstract

To satisfy the market, competition in the industrial sector aims for productivity and safety in industrial plant control systems. The appearance of a fault can compromise the system’s proper functioning process. Therefore, Fault Detection and Diagnosis (FDD) methods contribute to avoiding any undesired events, as there are techniques and methods that study the detection, isolation, identification and, consequently, fault diagnosis. In this work, a new methodology that uses faults emulation to obtain parameters similar to the Development and Application of Methods for Diagnosis of Actuators in Industrial Control Systems (DAMADICS) benchmark model will be developed. This methodology uses previous information from tests on sensors with and without faults to detect and classify the situation of the plant and, in the presence of faults, perform the diagnosis through a process of elimination in a hierarchical manner. In this way, the definition of residue signature is used as well as the creation of a decision tree. The whole process is carried out incorporating FDD techniques, through the Non-Linear Auto-Regressive Neural Network Model With Exogenous Inputs (NARX), in the diagnosis of the behavioral prediction of the signals to generate the residual values. Then, it is applied to the construction of the decision tree based on the most significant residue of a certain signal, enabling the process of acquisition and formation of the signature matrix. With the procedures in this article, it is possible to demonstrate a practical and systematic method of how to emulate faults for control valves and the possibility of carrying out an analysis of the data to acquire signatures of the fault behavior. Finally, simulations resulting from the most sensitized variables for the production of residuals that is generated by neural networks are presented, which are used to obtain signatures and isolate the flaws. The process proves to be efficient in computational time and makes it easy to present a fault diagnosis strategy that can be reproduced in other processes.

Highlights

There is a continuous search for increasingly efficient productivity, safely and with quality, the search for improvement in processes can be threatened due to the need for the accelerated use of the equipment that make up an industrial plant, making them increasingly likely to show signs of degradation such as: wear due to incorrect operation or repetitive movement, the principle of corrosion, the appearance of erosion, the accumulation of debris, the discovery of an, among others
Faults in the process, production and power generation industries, among others, can be classified according to their type as faults of actuators, sensors and plant components or parameters. These possible failures interrupt the action in the control process and they can produce substantial measurement errors or even change the dynamic input/output properties of the system, causing an increase in operating costs and even a degradation in the performance of the industrial plant [4,5,6]
Sensors 2021, 21, 853 work proposes an adaptive multisensor fusion method based on Deep Convolutional Neural Networks (DCNN) for fault diagnosis, the results reported better diagnostic accuracy in relation to the comparative methods in the experiment [30]

Summary

Introduction

With industries presenting an increasingly competitive profile, companies in the oil, petrochemical and natural gas sector, among others, are beginning to demonstrate a need for improvement in productivity, reliability in system stabilization and safety of their industrial plants. there is a continuous search for increasingly efficient productivity, safely and with quality, the search for improvement in processes can be threatened due to the need for the accelerated use of the equipment that make up an industrial plant, making them increasingly likely to show signs of degradation such as: wear due to incorrect operation or repetitive movement, the principle of corrosion, the appearance of erosion, the accumulation of debris (sedimentation), the discovery of an (obstruction), among others.The appearance of these symptoms can be an indication of the presence of abnormalities in the system and qualify failures that can lead to a permanent interruption in the ability to perform a certain function during operation [1]. the controllers are able to meet several types of disturbances, there are some changes, during the process, that they are unable to deal with correctly. There is a continuous search for increasingly efficient productivity, safely and with quality, the search for improvement in processes can be threatened due to the need for the accelerated use of the equipment that make up an industrial plant, making them increasingly likely to show signs of degradation such as: wear due to incorrect operation or repetitive movement, the principle of corrosion, the appearance of erosion, the accumulation of debris (sedimentation), the discovery of an (obstruction), among others The appearance of these symptoms can be an indication of the presence of abnormalities in the system and qualify failures that can lead to a permanent interruption in the ability to perform a certain function during operation [1]. These possible failures interrupt the action in the control process and they can produce substantial measurement errors or even change the dynamic input/output properties of the system, causing an increase in operating costs and even a degradation in the performance of the industrial plant [4,5,6]

Methods

Results

Conclusion