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

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.

Control valve stiction detection by use of AlexNet and transfer learning

Control valve stiction is a common problem faced by the process industries, which can have a strong adverse effect on the profitable operation of plants. Although various stiction detection methods based on neural networks have been proposed, few of these studies have considered the performance of stiction detection based on the use of 2D representations of the process signals. In this paper, such an approach is proposed, based on the use of a pretrained convolutional neural network, AlexNet. The proposed convolutional neural network stiction detection (CNN-SD) method showed highly satisfactory performance, which can be further applied on real industrial data.

Is Fault Detection and Diagnosis in Pneumatic Actuator A Topic of Concern?

The present civilization highly depends on industrial products and hence there is an increased demand for the same. Therefore, each industry is trying to increase its production output without hindering the quality. Maintenance of plant health is essential to improve the production rate without any loss. Industrial processes require monitoring of every element as their consistent behavior is a fundamental concern. Any deviation in the working of these components may alter the quality of the end product, causing a huge loss for the industry. Therefore, monitoring and finding the root cause for irregular behavior of industrial processes is a requisite for avoiding any future loss. In this paper, an attempt is made to present types of faults, types of pneumatic actuator faults, and different techniques used for the detection and isolation of faults. Simulation work is carried out to generate stiction behavior in the control valve using the Choudhury stiction model. Valve stiction behavior for different values of stick band and jump values are discussed in this paper. A comparison of several techniques used for the detection of faults based on two performance indices namely true detection rate and false alarm rate has been given at the end of this paper. From these techniques, it is observed that these indices are interdependent, such that an increase in the detection rate increases the false detection rate and increases detection time.