A simple model-free butterfly shape-based detection (BSD) method integrated with deep learning CNN for valve stiction detection and quantification

Kamaruddin, Bashariah; Zabiri, Haslinda; Amiruddin, Ahmad Azharuddin Azhari Mohd; Teh, Weng Kean; Ramasamy, M.; Jeremiah, Sean Suraj

doi:10.1016/j.jprocont.2020.01.001

Cited by 23 publications

(22 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rossi and Scali, 2005;Srinivasan et al, 2005a). In recent years, a number of stiction detection methods based on neural network/machine learning have been presented in the literature (Amiruddin et al, 2019;Kamaruddin, 2020;Napoli et al, 2019;Venceslau et al, 2012). So, it is required to add one more category of stiction detection method to the above classification, i.e.…”

Section: Detection Methods For Stictionmentioning

confidence: 99%

“…The time-series data segments are classified as increasing, decreasing or steady. Then, a stiction index is Horch and Isaksson (2001) Histogram All type Kano et al (2004) Limit cycle pattern All type Yamashita (2006a) Limit cycle pattern Only FC Scali and Ghelardoni (2008) Limit cycle pattern Only FC Daneshwar and Noh (2015) Limit cycle pattern Only FC Bra ´sio et al (2015) Limit cycle pattern Only LC Yamashita (2006b) Limit cycle pattern + Statistics Only LC Rengaswamy et al (2001) Waveform shape + ANN All type Rossi and Scali (2005) Waveform shape All type Srinivasan et al (2005a) Waveform shape All type Singhal and Salsbury (2005) Waveform shape All type except LC He et al (2007) Waveform shape All type Zabiri and Ramasamy (2009) Waveform shape + Nonlinearity detection All type Teh et al (2018) Waveform shape + Nonlinearity detection All type Ahmed et al (2009) Waveform shape All type Stockmann et al (2009) Waveform shape All type except LC Ha ¨gglund (2011) Waveform shape All type Farenzena and Trierweiler (2012b) Waveform shape Only LC Dambros et al (2016) Waveform shape All type Thornhill (2005) Nonlinearity detection All type Choudhury et al (2006) Nonlinearity detection All type Aftab et al (2016Aftab et al ( , 2017 Nonlinearity detection All type Farenzena and Trierweiler (2009) Machine learning (ANN) All type Venceslau et al (2012) Machine learning (ANN) All type Sharma et al (2017) Machine learning (ANN) Only FC Amiruddin et al (2019) Machine learning (ANN) All type Dambros et al (2019) Machine learning (ANN) All type Napoli et al (2019) Machine learning (CNN) Only FC Kamaruddin et al (2020) Machine learning (CNN) All type Henry et al (2020) Machine learning (CNN) All type Choudhury et al (2007) Controller gain change method All type…”

Section: Limit Cycle Pattern-based Methodsmentioning

confidence: 99%

“…Romano and Garcia, 2011;Wang and Wang, 2009), neural network-based (e.g. Farenzena and Trierweiler, 2009;Kamaruddin et al, 2020;Venceslau et al, 2012).…”

Section: Quantification Methods For Stictionmentioning

confidence: 99%

“…Very recently, Kamaruddin et al (2020) developed a stiction estimation method based on the CNN methodology. They used three convolutional layers and three pooling layers in the CNN model.…”

Section: Neural Network-based Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Comparison of current state of control valve stiction detection and quantification techniques

Akavalappil

Radhakrishnan

2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

The process control and automation system is one of the significant features in any process plant. The control valve is considered a fundamental part of the process control system. It regulates the fluid flow by changing the size of the flow passage as directed by the controller. If properly maintained, the control valves can help to reduce process variability and improve product quality, which in turn increases the overall efficiency of the plant. But control valve stiction is an enduring concern within process industries which eventually affects the efficiency of plant operation. Hence, it is extremely essential to detect and quantify stiction at the earliest opportunity, to determine the correct maintenance measures. Numerous methods related to stiction detection and estimation have been carried out so far by researchers. A literature study of the latest publications in stiction detection and quantification discloses that research in the conventional methods of stiction detection and quantification such as limit cycle pattern-based, waveform shape-based, nonlinearity-based, and model-based methods is gradually declining. At the same time, most stiction detection/quantification methods reported in the recent literature are based on artificial neural network and convolutional neural network. This implies that future stiction detection and quantification research will be focused towards machine learning (ML) algorithms. Taking this into consideration, this paper aims to provide a literature review of stiction detection and quantification methods by focusing on the latest research ideas and innovative approaches. This review also aims to compare recent techniques based on ML algorithms with conventional methods by pointing out the relationship among different methods, differences, and possible points of weakness.

show abstract

Section: Detection Methods For Stictionmentioning

confidence: 99%

Section: Limit Cycle Pattern-based Methodsmentioning

confidence: 99%

“…Romano and Garcia, 2011;Wang and Wang, 2009), neural network-based (e.g. Farenzena and Trierweiler, 2009;Kamaruddin et al, 2020;Venceslau et al, 2012).…”

Section: Quantification Methods For Stictionmentioning

confidence: 99%

“…Very recently, Kamaruddin et al (2020) developed a stiction estimation method based on the CNN methodology. They used three convolutional layers and three pooling layers in the CNN model.…”

Section: Neural Network-based Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of current state of control valve stiction detection and quantification techniques

Akavalappil

Radhakrishnan

2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…Some recent applications in chemical process systems can also be found for control valve stiction diagnosis as reported in Basha et al. 242 and YY Song et al. 243.…”

Section: Challenges and Opportunitiesmentioning

confidence: 99%

A Review on Data‐Driven Learning Approaches for Fault Detection and Diagnosis in Chemical Processes

et al. 2021

View full text Add to dashboard Cite

Fault detection and diagnosis for process plants has been an active area of research for many years. This review presents a concise overview on supervised and unsupervised data‐driven approaches for fault detection and diagnosis in chemical processes. Methods based on supervised and unsupervised data‐driven techniques are reviewed, and the challenges in the field of fault detection and diagnosis have also been highlighted. It is observed that most of the data‐driven approaches are application specific, in that no single method can be used to obtain a generalized solution for nearly all purposes. The methods reviewed differ significantly from one to the other, and hence it is difficult to generalize any key similarity. The majority of the works proposed in the literature focused mainly on single fault detection, and do not cover the root‐cause diagnosis of the detected faults. In cases where both detection and diagnosis are performed, the focus is mainly for a single fault. In addition, majority of the articles do not extend to the diagnosis of the root cause for multiple and simultaneous faults.

show abstract

A convolutional neural network (CNN)‐based direct method to detect stiction in control valves

2023

View full text Add to dashboard Cite

Control valves are considered important capital assets in any process industry. A properly maintained control valve can have a significant impact on how well the process is controlled as well as the overall cost of the plant. However, control valves can suffer from poor control performance due to valve non‐linearities. One of the main reasons for non‐linearity is control valve stiction. Stiction not only causes oscillations in the process variables but also shortens the life of the control valve, resulting in an economic loss for the process. In a process plant, a control engineer generally analyzes the time series plot of process value (PV), set point (SP), and controller output (OP) data and identifies stiction based on the typical shape pattern of PV/SP/OP plot. In this study, the same shape pattern methodology is adapted to identify stiction using convolutional neural network (CNN) technique. A one‐dimensional convolution neural network (Conv1D) algorithm is developed, which works directly on PV/SP/OP time series data for stiction detection. The proposed CNN algorithm is tested on both simulated and industrial control loop data. The suggested method provides promising results with a combined stiction prediction accuracy of 92% (92.2% in predicting non‐sticky and 91.53% in predicting sticky loops) for the industrial loops data studied.

show abstract

A simple model-free butterfly shape-based detection (BSD) method integrated with deep learning CNN for valve stiction detection and quantification

Cited by 23 publications

References 30 publications

Comparison of current state of control valve stiction detection and quantification techniques

Comparison of current state of control valve stiction detection and quantification techniques

A Review on Data‐Driven Learning Approaches for Fault Detection and Diagnosis in Chemical Processes

A convolutional neural network (CNN)‐based direct method to detect stiction in control valves

Contact Info

Product

Resources

About