Control Valve Stiction Research Articles

Enhancing Industrial Valve Diagnostics: Comparison of Two Preprocessing Methods on the Performance of a Stiction Detection Method Using an Artificial Neural Network

The detection and mitigation of stiction are crucial for maintaining control system performance. This paper proposes the comparison of two preprocessing methods for detecting stiction in control valves via pattern recognition via an artificial neural network (ANN). This method utilizes process variables (PVs) and controller outputs (OPs) to accurately identify stiction within control loops. The ANN was comprehensively trained using data from a data-driven model after processing them. Validation and testing were conducted with real industrial data from the International Stiction Database (ISDB), ensuring a practical assessment framework. This study evaluated the impact of two preprocessing methods on fault detection accuracy, namely, the D-value and principal component analysis (PCA) methods, where the D-value method achieved a commendable overall accuracy of 76%, with 86% precision in stiction prediction and a 66% success rate in nonstiction scenarios. This signifies that feature reduction leads to a degraded stiction detection. The data-driven model was implemented in SIMULINK, and the ANN was trained in MATLAB with the Pattern Recognition Toolbox. These promising results highlight the method’s reliability in diagnosing stiction in industrial settings. Integrating this technique into existing control systems is expected to enhance maintenance protocols, reduce operational downtime, and improve efficiency. Future research should aim to expand this method’s applicability to a wider range of control systems and operational conditions, further solidifying its industrial value.

Stiction parameter identification for pneumatic valves with a simultaneous approach

In industrial processes, stiction in control valves is a common cause of degradation in control loop performance. It is important to identify and establish reliable stiction models to enhance control loop performance. This study focuses on constructing a precise model of the pneumatic control valve using the LuGre friction model. To improve the model, a smooth function based on probability density is introduced to alleviate the LuGre friction model. The maximum error resulting from this smoothing process is also analyzed. To estimate the valve stiction parameters, the direct transcription method is utilized to convert the problem from systems of ordinary differential equations into a nonlinear programming problem. The interior point method is then used to solve this problem. Furthermore, the estimability of the parameters is analyzed based on the reduced Hessian matrix before estimation. Numerical results demonstrate that the proposed approach in this study effectively estimates the stiction parameters of pneumatic control valves.

A one-class support vector machine for detecting valve stiction

In industrial processes, control valve stiction is known to be one of the primary causes for poor control loop performance. Stiction introduces oscillatory behaviour in the process, leading to increased energy consumption, variations in product quality, shortened equipment lifespan and a reduction in overall plant profitability. Several detection algorithms using routine operating data have been developed over the last few decades. However, with the exception of a handful of recent publications, few attempts to apply classical supervised learning techniques have been published thus far. In this work, principal component analysis, linear discriminant analysis and a one-class support vector machine are trained to detect stiction using time series features as input. These features are extracted from the data using the tsfresh package for Python. The training data consists of simulated stiction examples generated using the XCH stiction model as well as other sources of oscillation. The classifier is subsequently benchmarked against closed-loop stiction data collected in an industrial setting, with performance exceeding that of existing methods.

Control valve stiction detection using Markov transition field and deep convolutional neural network

AbstractControl valve stiction is an industrial problem that often causes oscillations in process control loops. Oscillating control loops are not capable of maintaining key process variables near or at their desired values, thus yielding low‐quality products, inducing economic loss, and increasing environmental impacts. Therefore, it is of vital importance to detect stiction in industrial control valves. In this regard, the present work proposes a new method based on the Markov transition field and convolutional neural network (CNN) to identify sticky control valves in industrial control loops. The Markov transition field is employed to convert process variable (PV) and controller output (OP) into two‐dimensional images, which are then utilized by CNN to learn to distinguish stiction induced oscillations from oscillations brought out by a non‐stiction condition. A transfer learning strategy is adopted to improve the stiction detection capability of the proposed method. Its performance is evaluated via its application to benchmark control loops taken from the chemical, paper, mining, and metal industries. Results demonstrate that the proposed method obtains the correct verdict for the majority of the control loops studied.

Statistical Test-Based Practical Methods for Detection and Quantification of Stiction in Control Valves

Control valve, affected by stiction, causes closed-loop signals to experience oscillations, which ultimately leads to a decrease in product quality, reduced plant throughput, and increased environmental footprint. Therefore, it is indispensable to detect and quantify stiction in control valves. To accomplish this objective, in the present work, four noninvasive practical and simple methods are developed with the help of statistical tests such as F-test, t-test (Student’s t-test), modified Hotelling T2-test, and reverse arrangement test (RAT). The developed methods are applied to benchmark control loops espoused from chemical, paper, and mining industries. The results of the proposed methods are compared with that of existing methods found in the literature. It is found that the t-test-based method, the modified Hotelling T2-test-based method, and the RAT-based method demonstrate equally good or better performance than the existing methods, while the F-test-based method outperforms some of the existing methods. In addition to detecting stiction, the proposed methods can quantify stiction to timely notify panel operators of stiction severity and assist plant maintenance engineers to arrange plant shutdowns well ahead in time. The proposed methods are applicable to all types of control loops except level loops.

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

AbstractControl 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.

An approach for stiction compensation in industrial process control valves

In the process industry, control valve stiction causes oscillations in the control loop, and this results in deterioration of control performance. Therefore, the sticking control valves are repaired during a scheduled plant shutdown maintenance. Until such permanent solutions are used, it is expected that the oscillations can be reduced with a low-cost approach; PID control parameter re-tuning is a suitable approach in this case. This study involves a method of compensating for control valve stiction. In particular, it aims to improve the control performance by tuning the parameters of normal PID controllers. We propose a method to search for the optimal PID parameter values based on control simulation using a stiction model. First, the stiction model and the process model are identified. Next, simulation is performed using a combination of the stiction model, process model and PID controller. Finally, the PID parameter values are optimized based on the assessment.

Practical Linear Regression-Based Method for Detection and Quantification of Stiction in Control Valves

Practical Linear Regression-Based Method for Detection and Quantification of Stiction in Control Valves

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.

Detection and severity identification of control valve stiction in industrial loops using integrated partially retrained CNN-PCA frameworks

The wear and tear of control valves is a common problem encountered on process plants, owing to continuous movements of the valves. Aging of control valves leads to operational problems, such as valve stiction. Detection and severity identification of valve stiction remain an extensive research area even today, since the behaviour of these values tend to be nonlinear and is not necessarily easy to detect. In this paper, an integrated framework based on the use of convolutional neural networks (CNN) and principal component analysis (PCA) is proposed for both the detection of stiction, as well as identification of the severity of stiction. More specifically, a CNN is used to extract features from time series, while PCA acts as a dimensionality reduction tool to visualize the extracted features. Both the T2 and Q-statistics of the PCA model are applied for automated and predictive monitoring of control valve stiction. The CNN is then constructed to identify the severity of stiction as ‘weak’ or ‘strong‘. The detection results on industrial benchmark loops show the ability of the proposed method to retain the generalization property and balance of false-positive and false-negative detections of the latest methods published in literature, while having the key advantage of being readily extendible to the identification of the severity of stiction. Results based on simulated data also show the promising capability of the proposed method to be used in online predictive monitoring for process plants which may be beneficial to alert the instrumentation/maintenance teams on the current and future health of their valves.

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

Control valve stiction is a long-standing problem within process industries. In most methods for shape-based stiction detection, they rely heavily on the traditional controller output (OP) and process variable (PV) plot (i.e. PV-OP plot) that tends to produce an “elliptical” shape which is the widely acknowledged pattern indication for the presence of stiction. However, many of the methods suffered from unsatisfactory generalization capability when subjected to different loop dynamics. In this paper, a “butterfly” shape derived from the manipulation of the standard PV and OP data, which is more robust towards different loop dynamics, is developed for stiction detection. This simple model-free butterfly shape-based detection (BSD) method uses Stenman's one parameter stiction model, which results in a distinctive ‘butterfly’ pattern in the presence of stiction. The proposed BSD is tested on simulated data, as well as 26 benchmark industrial case studies and has shown a relatively higher generalization capability with relatively higher successful detection rate on stiction loops and on non-stiction loops. A simple quantification algorithm based on BSD-convolutional neural network (BSD-CNN) framework is then developed to quantify the stiction severity. Based on the 15 benchmark industrial loops with stiction, the proposed BSD-CNN quantification algorithm has shown reasonable accuracy when compared to other published quantification methods in literature.

Control Valve Stiction: Experimentation, Modeling, Model Validation and Detection with Convolution Neural Network

Control Valve Stiction: Experimentation, Modeling, Model Validation and Detection with Convolution Neural Network

Performance Analysis of Stiction Detection Methods

Industrial studies stated that, nearly 30% of badly performing process control loops are produced by nonlinearities in the pneumatic control valves, one among the main cause is stiction. The influence of this stiction nonlinearity is commonly detected as the process variable oscillations. As industrial plants contain several loops that are interacting, these oscillations will be spread to the whole system. Overhauling the defective valves will be the one among the top solution to this problem, which is probable only during the period of shut down process. But, this solution of process shut down to separate the defective valve is not cost-effective solution and hence it is taken into account as the prime one. So, there is a necessity for a technique to identify the effect of the control valve stiction. Detection algorithms available in literature are numerous and these techniques create either a quantitative or a qualitative statement about the occurrence of stiction in the control valve. While using available data, a detection method is considered to be effective only when its concluding result is relatively reliable. The main drawback while detecting stiction is that the stem position (MV) of the valve is not available in most of the situations. Quantifying the actual position of the control valve stem is always not probable. Commonly, process output and controller output are taken as the available data from most of the processes. The methods which use these data sets (PV and OP) are more appreciable by the control engineers. In this work, modified bispectral analysis technique is used as control valve stiction detection method and to prove its efficiency four different existing detection techniques available in literature are considered in this study and the performance of each method is reported. Here, eleven different data sets, seven from different laboratory processes and four from process industries are used to make the comparative analysis of performance.

Enhancing MPC formulations by identification and estimation of valve stiction

A common source of poor control performance in industrial processes is represented by stiction in control valves, which often induces offset, oscillating behavior, and even loss of stability. Recent studies have investigated the effectiveness of embedding stiction models into model predictive controller (MPC) schemes, moving from stiction unaware to different stiction aware formulations, which help to remove fluctuations and may guarantee higher set-point tracking ability. To this aim, along with the process model the controller needs to use a dynamic model of sticky valves. This paper proposes an efficient, computational approach to obtain both valve and process dynamics, under the framework of Hammerstein system identification, which is based on nonlinear, gradient-based, numerical optimization. In order to improve the computational behavior and effectiveness of the methodology, a recently proposed smoothed model of stiction is deployed. The proposed methodology is validated in several (single-input single-output, and multivariable) examples, where the effectiveness of the obtained stiction aware MPC regulator is also evaluated against a stiction unaware counterpart.

Control Valve Stiction Compensation - Part II: Performance Analysis of Different Stiction Compensation Methods

Control valves are important elements of control loops. Stiction in control valves limits the performance of control loops. It decreases the life of control valves. Minimizing the negative impact of sticky control valves can improve the performance of control loops. This is the second part of a two-part study on control valve stiction compensation. In the first part, a novel stiction compensation method has been proposed. This second part compares the performance of the proposed stiction compensator described in Part I with six other important stiction compensators that have appeared in the literature. The proposed compensator performs better than any of the other six compensators.

Control Valve Stiction Compensation - Part I: A New Method for Compensating Control Valve Stiction

Valve stiction is a hidden menace in process control loops. The presence of stiction in control valves limits the control loop performance. Compensation of its effect is beneficial before the sticky valve can be sent for maintenance. This work is the first of a two part study on control valve stiction compensation. This part proposes a novel stiction compensation method while the second part compares the performance of this proposed stiction compensation method with some of other compensation methods appeared in literature. The proposed compensator is developed based on reduction of control action and addition of an extra pulse of finite energy as required. A method for estimating an appropriate parameter for reducing controller action has been developed. The proposed stiction compensator has been extensively evaluated using MATLAB Simulink environment. The compensator has also been implemented in a pilot plant experimental set-up. It has been found to be successful in removing valve stiction induced osci...

IAM: An Intuitive ANFIS-based method for stiction detection

Stiction in control valves is an industry-wide problem which results in degradation of control performance. A new approach to detect the presence of stiction by utilising only the PV-OP data from control loops is proposed using an Adaptive Neuro-fuzzy Inferencing System (ANFIS). Intuitively, the error between the output of an FIS model developed with stiction and a process with stiction would be minimal. When benchmarked against seventeen well-known industrial control loop case studies, the Intuitive ANFIS-based Method (IAM) accurately predicts the presence or absence of stiction in 65% of loops tested.

Control valve stiction compensation by dynamic inversion: a comparative study

PurposeThe purpose of this paper is to improve the performance of control loop suffering from control valve stiction. Control valve stiction is considered as of one of the main causes of oscillation in process variables, which require performing costly unplanned maintenance and process shutdown. An adaptive solution to handle valve stiction while maintaining safety and quality until next planned maintenance is highly desirable to save considerable cost and effort.Design/methodology/approachThis paper implements a new stiction compensation method built using adaptive inverse model techniques and intelligent control theories. Finite impulse response (FIR) model, which is known to be robust, as a compensator for stiction. The parameters of FIR model are tuned in an adaptive way using differential evolution (DE) technique. The performance of proposed method is compared with other two compensation techniques.FindingsThe new method showed excellent performance of the DE–FIR compensator compared to other dynamic inversion methods in terms of minimizing process variability, energy saving and valve stem aggressiveness.Research limitations/implicationsThe compensation ability for all compensators reduces with the increase of stiction severity, thus the over shoot case always shows the worst result. In future works, other optimization techniques will be explored to find the appropriate technique that can extend the FIR model size with smallest computation time that can improve the performance of the compensator in over shoot case. In addition, the estimation of the valve residual life based on the level of stiction and effort required by the controller should be considered.Originality/valueThe presented approach represents an original contribution to the literature. It performs stiction compensation without a need for a prior knowledge on the process or the valve models and guarantees a smooth control of the stem movement with a low control effort. The proposed approach differs from previous adaptive methods as it uses stable FIR models and DE to find the appropriate parameters of the inverse model and handle nonlinear behavior of stiction.

An Improved Diagnostic Tool for Control Valve Stiction Based on Nonlinear Principle Component Analysis

Control valves suffer from wear and aging as the valves open and close. Such continuous movements result in many operational issues, and one of the widely known problems is stiction nonlinearity. Stiction results in inferior quality of the products, large rejection rates, increased energy consumption, and reduced profitability. In this paper, a simple algorithm that combines preprocessing and postprocessing as well as average crossing autocovariance (AC) together with the nonlinear principal component analysis (NLPCA) is investigated. The results obtained from the simulated and industrial case studies show that the proposed NLPCA-AC method has favorable proficiencies for control valve stiction detection.