Fault detection and diagnosis of pneumatic valve using Adaptive Neuro-Fuzzy Inference System approach

Subbaraj, P.; Kannapiran, B.

doi:10.1016/j.asoc.2014.02.008

Cited by 41 publications

(33 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Industrial data sets from a power plant were used to test the methods' efficiency. Recently, Subbaraj and Kannapiran [108] proposed an Adaptive Neuro-Fuzzy Inference System to detect and diagnose the occurrence of various faults in a smart pneumatic valve of a cooler water spray system in cement industry. The training and testing data required for model development were generated at normal and faulty conditions in a laboratory setup.…”

Section: Smart Diagnosismentioning

confidence: 99%

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

Capaci

Scali

2015

Processes

View full text Add to dashboard Cite

Abstract:Valve stiction is indicated as one of the main problems affecting control loop performance and then product quality. Therefore, it is important to detect this phenomenon as early as possible, distinguish it from other causes, and suggest the correct action to the operator in order to fix it. It is also very desirable to give an estimate of stiction amount, in order to be able to follow its evolution in time to allow the scheduling of valve maintenance or different operations, if necessary. This paper, in two parts, is a review of the state of the art about the phenomenon of stiction from its basic characterization to smart diagnosis, including modeling, detection techniques, quantification, compensation and a description of commercial software packages. In particular, Part I of the study analyzes the most significant works appearing in the recent literature, pointing out analogies and differences among various techniques, showing more appealing features and possible points of weakness. The review also includes an illustration of the main features of performance monitoring systems proposed by major software houses. Finally, the paper gives indications on future research trends and potential advantages for loop diagnosis when additional measurements are available, as in newly designed plants with valve positioners and smart instrumentation. In Part II, performance of some well-established methods for stiction quantification are compared by applications to different industrial datasets. OPEN ACCESSProcesses 2015, 3 423

show abstract

Section: Smart Diagnosismentioning

confidence: 99%

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

Capaci

Scali

2015

Processes

View full text Add to dashboard Cite

show abstract

“…An image of subsystems is processed to detect the faults in [18]. In [19], faults in the pneumatic valve are detected and diagnosed using neuro-fuzzy methods. Reference [20] reported a signature analysis technique based on the hysteresis property of an actuator for fault isolation in pneumatic actuators used for aviation applications.…”

Section: Introductionmentioning

confidence: 99%

Fault Detection of a Flow Control Valve Using Vibration Analysis and Support Vector Machine

Venkata

Rao

2019

Electronics

View full text Add to dashboard Cite

A control valve plays a very significant role in the stable and efficient working of a control loop for any process. In a fluid flow process, the probability of failure of a control valve may increase for many reasons pertaining to a flow process such as high pressures at the inlet, different properties of the liquid flowing through the pipe, mechanical issue related to a control valve, ageing, etc. A method to detect faults in the valve can lead to better stability of the control loop. In the proposed work, a technique is developed to determine the fault in a pneumatic control valve by analyzing the vibration data at the outlet of the valve. The fault diagnosis of the valve is carried out by analyzing the change in vibration of the pipe due to the change in flow pattern induced by the control valve. The faults being considered are inflow and insufficient supply pressure faults. Vibration data obtained is processed using a signal processing technique like amplification, Fourier transform, etc. The support vector machine (SVM) algorithm is used to classify the vibration data into two classes, one normal and the other faulty. The designed algorithm is trained to identify faults and subjected to test with a practical setup; test results show an accuracy of 97%.

show abstract

“…Many feature extraction methods are known for various types of vibration signals, and the methods include statistical and spectral approaches, wavelets [5,6], psychoacoustic features [7], the Wigner-Vile distribution [8], empirical mode decomposition [9], chaotic vibration [10], and others. Classification methods include various statistical methods, neural and fuzzy logic based methods [11,12], and other modern machine learning methods, such as support vector machines [13,14] and, recently, deep learning approaches [15]. A broad overview of the numerous methods under the general title of natural computing, including neural networks, fuzzy logic, support vector machines, and other methods applicable to mechanical systems research, is provided in [16].…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised vibration-based classification and condition monitoring of compressors

Potočnik

Govekar

2017

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Semi-supervised vibration-based classification and condition monitoring of the reciprocating compressors installed in refrigeration appliances is proposed in this paper. The method addresses the problem of industrial condition monitoring where prior class definitions are often not available or difficult to obtain from local experts. The proposed method combines feature extraction, principal component analysis, and statistical analysis for the extraction of initial class representatives, and compares the capability of various classification methods, including discriminant analysis (DA), neural networks (NN), support vector machines (SVM), and extreme learning machines (ELM). The use of the method is demonstrated on a case study which was based on industrially acquired vibration measurements of reciprocating compressors during the production of refrigeration appliances. The paper presents a comparative qualitative analysis of the applied classifiers, confirming the good performance of several nonlinear classifiers. If the model parameters are properly selected, then very good classification performance can be obtained from NN trained by Bayesian regularization, SVM and ELM classifiers. The method can be effectively applied for the industrial condition monitoring of compressors.

show abstract

Fault detection and diagnosis of pneumatic valve using Adaptive Neuro-Fuzzy Inference System approach

Cited by 41 publications

References 20 publications

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

RETRACTED: Review on Valve Stiction. Part I: From Modeling to Smart Diagnosis

Fault Detection of a Flow Control Valve Using Vibration Analysis and Support Vector Machine

Semi-supervised vibration-based classification and condition monitoring of compressors

Contact Info

Product

Resources

About