Fault Detection and Diagnosis of Pneumatic Control Valve Based on a Hybrid Deep Learning Model

As the growing requirements for the stability and safety of process industries,the fault detection and diagnosis of pneumatic control valves have crucial practical significance.Many of the approaches were presented in the literature to diagnose faults through the comparison of residual sequences with thresholds.In this study,a novel hybrid neural network model has been developed to address the issue of pneumatic control valve fault diagnosis.First,the feature extractor automatically extracts in-depth features of the signals through multi-scale convolutional neural networks with different kernel sizes,which not only adequately explores the local distinguishable features,but also takes into account the global features.The extracted features are then fused by the feature fusion layer to reduce redundant features.Finally,the long short-term memory for fault identification and the dense layer for fault classification.Experimental results demonstrate that the average test accuracy is above 94%and 16 out of the 19 conditions can be successfully detected in the simulated actual industrial environment.The effectiveness and practicability of the proposed method have been verified through a comparative analysis with existing intelligent fault diagnosis methods,and the results suggest that the developed model has better robustness.

Numerical study on cavitation in a globe control valve with different numbers of anti-cavitation trims

Cavitation is a destructive phenomenon in control valves.In order to delay cavitation,a multi-series of perforated cylindrical plates,called trims,are used.Previously,the effects of orifice diameter and different types of trims have been investigated.In this study,by numerical analysis,a globe control valve was investigated by employing four different cases(without trim,with one trim,with two and three trims)and the impact of the number of these trims on the intensity,formation region and the initiation point of cavitation was analyzed.It was found that the addition of one stage or two stages of trims reduces the intensity and delays the onset of cavitation,relative to the valve without trim.However,no significant differences in terms of intensity and initiation point of cavitation were observed in the cases where two or three trims were used.Therefore,due to the high cost of producing the trims,and the severe drop in flow coefficient,it is not economically and technically justified to increase the number of trims to more than three.

Effect of Cone Angle on the Hydraulic Characteristics of Globe Control Valve

Globe control valve is widely used in chemical, petroleum and hydraulic industries, and its throttling feature is achieved by the adopting of valve plug. However, very limited information is available in literature regarding the influence of valve plug on the internal and external features in globe control valves. Thus the effect of valve plug is studied by CFD and experiment in this paper. It is obtained from external features that the pressure drop between upstream and downstream pressure-sampling position increases exponentially with flow rate. And for small valve opening, the increment of pressure drop decreases with the increase of cone angle（β）. However, with the increase of valve opening, the effect of cone angle diminishes significantly. It is also found that the cone angle has little effect on flow coefficient（Cv） when the valve opening is larger than 70%. But for the cases less than 70%, Cv curve varies from an arc to a straight line. The variation of valve performance is caused by the change of internal flow. The results of internal flow show that cone angle has negligible effect on flow properties for the cases of valve opening larger than 70%. However, when valve opening is smaller than 70%, the pressure drop of orifice decreases with the increase of β, making the reduction in value and scope of the high speed zone around the conical surface of valve plug, and then results in a decreasing intensity of adjacent downstream vortex. Meanwhile, it is concluded from the results that the increase of cone angle will be beneficial for the anti-cavitation and anti-erosion of globe control valve. This paper focuses on the internal and external features of globe control valve that caused by the variation of cone angle, arriving at some results beneficial for the design and usage of globe control valve.

STUDY ON FLUID THICKNESS BETWEEN POPPET AND VALVE GUIDE IN CONTROL VALVE OF INJECTOR

The physical model of -20 diesel oil and force model of injector controlvalve of common rail system is built. The changes of the fluid thickness are investigated on thebase of the results of CFD and experiments for control valve of injector. The results indicate thata fluid thickness of 0.02-0.03 mm between the poppet and valve guide is sufficient to dampen anyexcessive control valve poppet bouncing.

MODELING, VALIDATION AND OPTIMAL DESIGN OF THE CLAMPING FORCE CONTROL VALVE USED IN CONTINUOUSLY VARIABLE TRANSMISSION

Associated dynamic performance of the clamping force control valve used in continuously variable transmission （CVT） is optimized. Firstly, the structure and working principle of the valve are analyzed, and then a dynamic model is set up by means of mechanism analysis. For the purpose of checking the validity of the modeling method, a prototype workpiece of the valve is manufactured for comparison test, and its simulation result follows the experimental result quite well. An associated performance index is founded considering the response time, overshoot and saving energy, and five structural parameters are selected to adjust for deriving the optimal associated performance index. The optimization problem is solved by the genetic algorithm （GA） with necessary constraints. Finally, the properties of the optimized valve are compared with those of the prototype workpiece, and the results prove that the dynamic performance indexes of the optimized valve are much better than those of the prototype workpiece.

Positioning-control Based on Trapezoidal Velocity Curve for High-precision Basis Weight Control Valve

Traditionally, basis weight control valve is driven by a constant frequency pulse signal. Therefore, it is difficult for the valve to match the control precision of basis weight. Dynamic simulation research using Matlab/Simulink indicates that there is much more overshoot and fluctuating during the valve-positioning process. In order to improve the valve-positioning precision, the control method of trapezoidal velocity curve was studied. The simulation result showed that the positioning steady-state error was less than 0.0056%, whereas the peak error was less than 0.016% by using trapezoidal velocity curve at 10 positioning steps. A valve-positioning precision experimental device for the stepper motor of basis weight control valve was developed. The experiment results showed that the error ratio of 1/10000 positioning steps was 4% by using trapezoidal velocity curve. Furthermore, the error ratio of 10/10000 positioning steps was 0.5%. It proved that the valve-positioning precision of trapezoidal velocity curve was much higher than that of the constant frequency pulse signal control strategy. The new control method of trapezoidal velocity curve can satisfy the precision requirement of 10000 steps.

Challenges Associated with the Bypass Valves of Control Valves in a Seawater Service

Modern processing plants use a variety of control loop networks to deliver a finished product to the market.Such control loops,like control valves,are designed to keep process variables such as pressure,temperature,speed,flow,etc.within the appropriate operating range and to ensure a quality product is produced.All control valves have a bypass so that production can proceed if maintenance is needed for the control valve as part of the control loop.The important point is that in both operation and maintenance situations,the bypass valve and the control valve should have approximately the same flow capacity to provide nearly the same amount of pressure.This paper presents a case study in seawater service on the selection of manual bypass valves for a 16″control valve in class 150 and titanium material.A 16″butterfly valve of class 150 was chosen for the control valve bypass,which provided a much higher flow capacity than the control valve.In this paper,four solutions are recommended to achieve the same coefficient value(Cv)for the control and bypass valve.Using the reduced size butterfly valve could be the cheapest and best solution.On the other hand,selecting the same control valve for bypass line is the most expensive but maybe the most reliable solution.Using a flow orifice for throttling could be ranked as the second expensive option and the second reliable one.Selection of butterfly valve for throttling is the second cheapest option,but it has the least reliability.Different parameters such as space and weight saving,cost as well as reliability have been considered in evaluation of different solutions.

An experimental study on flowrate and stability for 600MW supercritical steam-turbine control valve

An experimental study on flowrate and stability of a type of control valve of 600MW supercritical steam-turbine was presented by measuring instruments of static, dynamic pressure and vibration in self-designed test rig. The investigation shows that flow coefficient is 30% up more than that of the control valve of GX-1 type used widely in domestic power plants now, as small-medium lifts. If the relative lift (h/D) is less than 20%, the valve can always work steadily in all the pressure ratios. When the h/D is between 20% to 24%, big vibration of valve stem occurs if the pressure ratio is between 0.7 to 0.8. When h/D is more than 25%, relatively great vibration happens in a wide range of pressure ratios of 0.4 to 0.85.

An Integrated Approach for Process Control Valves Diagnosis Using Fuzzy Logic

Control valves are widely used in industry to control fluid flow in several applications. In nuclear power systems they are crucial for the safe operation of plants. Therefore, the necessity of improvements in monitoring and diagnosis methods started to be of extreme relevance, establishing as main goal of the reliability and readiness of the system components. The main focus of this work is to study the development of a model of non-intrusive monitoring and diagnosis applied to process control valves using artificial intelligence by fuzzy logic technique, contributing to the development of predictive methodologies identifying faults in incipient state. Specially in nuclear power plants, the predictive maintenance contributes to the security factor in order to diagnose in advance the occurrence of a possible failure, preventing severs situations. The control valve analyzed belongs to a steam plant which simulates the secondary circuit of a PWR—Pressurized Water Reactor. The maintenance programs are being implemented based on the ability to diagnose modes of degradation and to take measures to prevent incipient failures, improving plant reliability and reducing maintenance costs. The approach described in this paper represents an alternative departure from the conventional qualitative techniques of system analysis. The methodology used in this project is based on signatures analysis, considering the pressure (psi) in the actuator and the stem displacement (mm) of the valve. Once the measurements baseline of the control valve is taken, it is possible to detect long-term deviations during valve lifetime, detecting in advance valve failures. This study makes use of MATLAB language through the “fuzzy logic toolbox” which uses the method of inference “Mamdani”, acting by fuzzy conjunction, through Triangular Norms (t-norm) and Triangular Conorms (t-conorm). The main goal is to obtain more detailed information contained in the measured data, correlating them to failure situations in the incipient stage.

Improving the Performance of an Electro-Hydraulic Load-Sensing Proportional Control Valve

The paper deals with the simulation and the experimental verification of the hydraulic behavior of an electro-hydraulic load-sensing proportional control valve. An innovative CAE （computer aided engineering） methodology, developed combining CFD （computational fluid dynamics） simulations with lumped and distributed numerical modeling, is firstly introduced and tailored by comparing the numerical results with measurements coming from an experimental campaign performed for a wide range of pressure loads and metered flow rates. Then, both the reliability and the limits of the numerical approach are highlighted through a detailed numerical vs. experimental comparison, involving the pressure of the main hydraulic lines, the flow rate through the first section and the local compensator displacement. Finally, the CAE methodology has been applied for assessing the internal ducts hydraulic permeability and the local compensator spring pre-load influence on the control valve metering curves. At the end of this analysis, an optimized design configuration, featuring a maximum controlled volumetric flow rate increased of more than 25%, has been proposed.

Computational Cavitation Flows at Inception and Light Stages on an Axial-Flow Pump Blade and in a Cage-Guided Control Valve

Cavitation flows induced around an axial-flow pump blade and inside a high pressure cage-type valve are simulated by a two-dimensional unsteady Navier-Stokes analysis with the simplest treatment of bubble dynamics. The fluid is assumed as a continuum of homogeneous dispersed mixture of water and vapor nuclei. The analysis is aimed to capture transient stages with high amplitude pressure change during the birth and collapse of the bubble especially at the stage of cavitation inception. By the pump blade analysis, in which the field pressure is moderate, cavitation number of the inception and locations of developed cavitation are found to agree with experimental results in a wide flow range between high incidence and negative incidence. In the valve flow analysis, in which the water pressure of 5MPa is reduced to 2MPa, pressure change responding to the bubble collapse between the vapor pressure lower than 1 KPa and the extreme pressure of higher than 104 KPa is captured through a stable computation. Location of the inception bubble and pressure force to the valve plug is found agree well with the respective experimental features.

Visualization Experiment and Numerical Analysis of Cavitation Flow Characteristics in Diesel Fuel Injector Control Valve with Different Structure Design

Increasing the injection pressure has been proven an effective method to enhance performance and reduce pollutant of diesel engine.With the increase of the injection pressure,the cavitation damage problem inside common rail fuel injector is more significant,which has direct influences on reliability of diesel engine.While the most studies so far have focused on cavitation occurred in injector nozzle and its atomization characteristics,few researchers studied the cavitation phenomenon in fuel injector control valve.But due to the complexity of flow field and difficulty of experiment,the cavitation in control valve could not be fully described by existing theories.In this paper,the two-dimensional visualization experiment and numerical simulation of control valve was implemented to acquire the image of cavitation intuitively and validate the simulation method and model.Then a new structure design of control valve named convergent model was presented for comparison.The origin model and convergent model with different valve lifts were simulated in three dimensions.The results showed that the sheet cavitation occurred at the surface of seal cone and steel ball then turned to cloud cavitation in downstream area.The intensity of cavitation increased with the increase of valve lift.Convergent model could efficiently reduce the cavitation intensity near the seal area.This research could provide references for engineering optimization design of control valve.

Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network

A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is therefore important for operation of the system.In this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing data.The multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed method.The effects of the proposed method in missing data imputation and fault diagnosis are analyzed.Compared with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.

Seat tightness of pneumatic cryogenic control valve

Pneumatic cryogenic control valves(PCCV)are designed to meet the special requirements for the large cryogenic helium refrigeration system.Polychlorotrifluoroethylene(PCTFE)is adopted as the flat seal material of the valve seat.The leakage rates and compressive strain of the PCTFE gasket with different sealing stress are tested at both room temperature(293 K)and liquid nitrogen temperature(77 K).After 300 open/close cycles,the experimental results show that the sealing properties of the PCTFE gasket are improved.The leakage rates are about 10-8(293 K)and 10-4(77 K)Pam3 s-1 respectively.Finally,the effects of working pressure on sealing characteristics are discussed.The working pressure has little effect on compressive strain but it has a great influence on leakage rate.The leakage rate is linear with the working pressure of inlet at room temperature,but at liquid nitrogen temperature the leakage rate is linear with the square of the working pressure.

Thermodynamic Characteristic Study of a High-temperature Flow-rate Control Valve for Fuel Supply of Scramjet Engines

Thermodynamic characteristics are of great importance for the performance of a high-temperature flow-rate control valve,as high-temperature environment may bring problems,such as blocking of spool and increasing of leakage,to the valve.In this paper,a high-temperature flow-rate control valve,pilot-controlled by a pneumatic servo system is developed to control the fuel supply for scramjet engines.After introducing the construction and working principle,the thermodynamic mathematical models of the valve are built based on the heat transfer methods inside the valve.By using different boundary conditions,different methods of simulations are carried out and compared.The steady-state and transient temperature field distribution inside the valve body are predicted and temperatures at five interested points are measured.By comparing the simulation and experimental results,a reasonable 3D finite element analysis method is suggested to predict the thermodynamic characteristics of the high-temperature flow-rate control valve.

Control Valve with a Constant Inner Authority Value

The aim of the article is to propose the method of designing double regulation control valves used in heating installations, allowing to obtain a constant value of the so-called inner authority and thus the constancy of the valve control characteristic, regardless of the pre-setting value set on the valve. The shape of the valve's regulation characteristics is one of the main factors determining the quality of the quantitative regulation, and thus the stability of the system's operation and overall operating costs. For this reason, the issue discussed in the article is important and can be applied in practical implementations of the valve sizing and the valve selection. The analysis was based on the relations binding the hydraulic resistances occurring inside the control valve, and the corresponding flow factors, using original author's proposal. The experimental verification was performed on a special measuring stand prepared for this purpose, measuring the values of the medium volume flow at a constant differential pressure, and then the results were converted into values of the flow factor, used in the proposed mathematical model. The results confirm the thesis put forward and the proposed mathematical model. High convergence of the results of experimental verification with the proposed mathematical model was obtained.

Real Time Automation and Ratio Control Using PLC&SCADA in Industry 4.0

Industrial Control Systems(ICS)and SCADA(Supervisory Control and Data Acquisition)systems play a critical role in the management and regulation of critical infrastructure.SCADA systems brings us closer to the real-time application world.All process and equipment control capability is typically provided by a Distributed Control System(DCS)in industries such as power stations,agricultural systems,chemical and water treatment plants.Instead of control through DCS,this paper proposes a SCADA and PLC(Programmable Logic Controller)system to control the ratio control division and the assembly line division inside the chemical plant.A specific design and implementation method for development of SCADA/PLC based real time ratio control and automated assembly line system in a chemical plant is introduced.The assembly line division is further divided into sorting stage,filling stage and the auxiliary stage,which includes the capping unit,labelling unit and then the storage.In the ratio control division,we have defined the levels inside the mixer and ratio of the raw materials through human machine interface(HMI)panel.The ratio of raw materials is kept constant on the basis of flow rates of wild stream and manipulated stream.There is a flexibility in defining new levels and the ratios of the raw materials inside the mixer.But here we taken the predefined levels(low,medium,high)and ratios(3:4,2:1,2:5).Control valves are used for regulating the flow of the compositions.In the assembly line division,the containers are sorted on the basis of size and type of material used i.e.,big sized metallic containers and small sized non-metallic containers by inductive and capacitive proximity sensors.All the processes are facilitated with laser beam type or reflective type sensors on the conveyor system.Building a highly stable and dependable PLC/SCADA system instead of Distributed Control System is required to achieve automatic management and control of chemical industry processes to reduce waste manpower and physical resources,as well as to improve worker safety.

TRANSIENT RESPONSE OF A VALVE CONTROL HYDRAULIC SYSTEM WITHLONG PIPES

The simulation model of a valve control hydraulic system with long pipe isestablished in Simulink4.0, and then the step responses of the systems with difference pipeparameters are investigated by simulation. Simulation results show that the long pipes will slowdown the step response of system and make it fluctuate periodically. The results of simulationconform to the results of experiment on the whole, which proves the mathematic model is correct.

Parameters Sensitivity Characteristics of Highly Integrated Valve-Controlled Cylinder Force Control System

Nowadays, a highly integrated valve?controlled cylinder(HIVC) is applied to drive the joints of legged robots. Although the adoption of HIVC has resulted in high?performance robot control, the hydraulic force system still has problems, such as strong nonlinearity, and time?varying parameters. This makes HIVC force control very diffcult and complex. How to improve the control performance of the HIVC force control system and find the influence rule of the system parameters on the control performance is very significant. Firstly, the mathematical model of HIVC force control system is established. Then the mathematical expression for parameter sensitivity matrix is obtained by applying matrix sensitivity analysis(PSM). Then, aimed at the sinusoidal response under(three factors and three levels) working conditions, the simulation and the experiment are conducted. While the error between the simulation and experiment can’t be avoided. Therefore, combined with the range analysis, the error in the two performance indexes of sinusoidal response under the whole working condition is analyzed. Besides, the sensitivity variation pattern for each system parameter under the whole working condition is figured out. Then the two sensitivity indexes for the three system parameters, which are supply pressure, proportional gain and initial displacement of piston, are proved experimentally. The proposed method significantly reveals the sensitivity characteristics of HIVC force control system, which can make the contribution to improve the control performance.

Adaptive H-infinity control of synchronous generators with steam valve via Hamiltonian function method

Based on Hamiltonian formulation, this paper proposes a design approach to nonlinear feedback excitation control of synchronous generators with steam valve control, disturbances and unknown parameters. It is shown that the dynamics of the synchronous generators can be expressed as a dissipative Hamiltonian system, based on which an adaptive H-infinity controller is then designed for the systems by using the structure properties of dissipative Hamiltonian systems. Simulations show that the controller obtained in this paper is very effective.