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

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.

Fault Detection and Diagnosis Based on Unsupervised Machine Learning Methods: A Kaplan Turbine Case Study

“…On the other hand, in addition to the method applied in this work (MWPCA-BN), the methods analyzed and compared were: the Non-Linear Auto-Regressive Neural Network Model with Exogenous Inputs (NARX) [27]; the Naïve Bayes Classifier combined with BN and Event Tree Analysis (NBC-BN-ETA) [28]; the Multivariate Exponentially Weighted Moving Average Principal Component Analysis combined with BN (MEWMAPCA-BN) [29]; the PCA, BN, and Multiple Likelihood Evidence combination (PCA-T2-BN with MLE) [30]; the Ensemble Empirical Mode Decomposition combined with PCA and Cumulative Sum (EEMD-PCA-CUSUM) [31]; the Residual PCA combined with BN (PCA-R-BN) [32]; the PCA combined with fuzzy theory, data fusion, and BN (PCA-Fuzzy-BN) [33]; the traditional PCA combined with BN (PCA-BN) [34]; the ICA combined with BN (ICA-BN) [35]; Control Charts combined with BN (CC with BN) [36]; and the model-based approach with the Simulation Abnormal Event Management (SimAEM) [37].…”

Non-Singleton Type-3 Fuzzy Approach for Flowmeter Fault Detection: Experimental Study in a Gas Industry

“…These approaches have also been employed for FD problems in a few studies. For example, in [21], a neural network (NN) is used for modeling the signal dynamics and prediction, and based on the NN model, an FD scheme is developed for pneumatic valves. In [22], the genetic algorithm is suggested for online optimization of an NN and designing an FD system.…”

Sensor Fusion with NARX Neural Network to Predict the Mass Flow in a Sugarcane Harvester

“…NARX has the advantage of not requiring many different input variables, and the integration of multiple variable inputs and autoregressive inputs benefits the modeling process to provide more accurate estimates [ 22 ]. NARX was used to predict and compensate the inertial navigation system position errors when global positioning system (GPS) is unavailable [ 23 , 24 ], diagnose faults for pneumatic control valves [ 25 ], predict marine engine performance parameters [ 26 ], underwater passive target state estimation [ 27 ], undergo multiple data fusion for rainfall estimation [ 28 , 29 ], and perform long-term machine state forecasting [ 21 ].…”

“…Thus, this study makes the first approach to investigate the use of the NARX on harvested sugarcane. The NARX can incorporate the dynamics of signals from sensors [ 25 ], such as those installed in sugarcane harvesters that monitor the harvester’s operational processes. In this way, the use of the data generated by the sensors already installed in the harvester and harvester instrumentation to measure sugarcane parameters during harvest would be an essential advancement in harvester automation and agricultural operations [ 30 ].…”