A valve detection system and detection method thereof

Abstract

The present application provides a valve detection system and detection method thereof, including a valve data module, an associated valve module, a first prediction module, an associated verification module, and a second prediction module; the valve data module includes the associated features and fault types of the valves in the system; the associated valve module can obtain associated valves that have fault propagation correlation with the valve to be inspected based on the associated features of the valves; the first prediction module can determine whether the valve has a risk of failure based on the deviation between the actual detection data and the theoretical data of the valve; when the judgment is yes, the associated verification module can verify the judgment result of the first prediction module using the obtained detection data of the associated valve; when the verification result shows that the first prediction module has made a misjudgment, the valve failure risk is re-judged through the second prediction module. The present application improves detection accuracy and reduces false alarms.

Description

Technical Field

[0001] The present application relates to the field of valve safety detection, and in particular to a valve detection system and a detection method thereof. Background Art

[0002] Valves are control components in fluid conveying systems, performing functions such as shutting off and clearing fluids, regulating flow, directing flow, preventing reverse flow, stabilizing pressure, dispersing fluids, and providing overflow and pressure relief. Valves come in a wide variety of types and specifications, ranging from simple globe valves and ball valves to complex valves suitable for use in automated control systems. With the expansion of production demands and advancements in industrial automation technology, efficient and automated valve inspection methods are gaining increasing attention to ensure smooth and accident-free production, particularly in the aerospace, nuclear power, thermal power, and high-temperature and high-pressure sectors. To ensure the proper operation of pressure pipelines, valves in these pipelines require regular inspection to promptly identify any problems. Current valve detection methods include using instruments to detect changes in pressure and other parameters in pressure pipes, and using photographic instruments or infrared, laser and other instruments to regularly collect data on the overall working status of the valve, obtain its appearance data and working status data, and use qualitative judgment models to achieve fault warning by collecting these detection data. However, the use of such methods is often rigid in design and can only provide warnings after a fault occurs, but cannot effectively prevent the fault. There is also a lack of means to verify the fault, so the judgment results are either already formed faults or a large number of false alarms, resulting in the detection system being unable to make accurate judgments. Summary of the Invention

[0003] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are for illustrative purposes only, and those skilled in the art will readily appreciate other obvious variations. The basic principles of the present invention defined in the following description may be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the present invention.

[0004] In order to solve the technical problem, the present application provides a valve detection system, comprising a valve data module, an associated valve module, a first prediction module, an associated verification module, and a second prediction module; the valve data module includes associated features and fault types of valves in the system; the associated valve module can obtain associated valves that have a fault propagation correlation with the valve to be inspected based on the associated features of the valves;

[0005] The first prediction module can detect the valve and judge whether the valve has the risk of failure through the deviation between the actual detection data of the valve and the theoretical data; when the judgment is yes, the associated verification module can detect the associated valves of the valve to be detected and verify the judgment result of the first prediction module through the obtained detection data of the associated valves; when the verification result shows that the first prediction module has made a misjudgment, the second prediction module is used to re-judge the failure risk of the valve.

[0006] Among them, preferably, the associated features include valve position, material, function, medium, flow, pressure, vibration frequency and operation sequence.

[0007] Among them, preferably, the fault types include sticking, clogging, adhesion, leakage and valve body breakage.

[0008] Preferably, during detection, the first prediction module and the second prediction module determine the risk of the fault by obtaining deviations of several detection indicators corresponding to the fault type.

[0009] Preferably, the judgment result of the first prediction module is verified by obtaining the deviation of the risk-related indicators with risks in the detection indicators.

[0010] The present application also provides a valve detection method using the valve detection system as described above, comprising the following steps:

[0011] S1, the system provides detection of n valves FM, FM = [FM1, FM2, FM3, ..., FM n ], where the i-th valve is FM i ; Set valve FM i m types of faults IQ can occur, IQ = [IQ1, IQ2, IQ3, ..., IQ m ], where the jth type of fault is IQ j ;

[0012] For valve FM i Perform the first prediction step:

[0013] Set the fault type IQ j The judgment needs to obtain k detection indicators JB of the valve, JB= [JB1, JB2, JB3, ..., JB k ], where the zth detection index is JB z ;

[0014] Set the detection index JB to be obtained at the first detection time IT1 z The actual detection value is Zs, according to the set detection index JB zThe judgment threshold Zc can be used to obtain the detection index JB z The indicator deviation θ in this test z =Zs-Zc;

[0015] At the first detection time IT1, according to the obtained detection index JB z The indicator deviation θ z , can get valve FM i Fault Type IQ j The first prediction score ;

[0016] According to the set fault type IQ j The risk threshold IW0;

[0017] When IW1>IW0, go to the association verification step S2:

[0018] S2, obtain valve FM based on the index deviation obtained during IT1 detection time i The r risk related indicators of the valves associated with it IJB = [IJB1, IJB2, IJB3, ..., IJB r ], r≤k, where the pth risk association index is IJB p , IJB p The indicator deviation is θ p ;

[0019] Obtain the associated risk threshold GW0;

[0020] Get Valve FM i The c associated valves IG = [IG1, IG2, IG3, ..., IG c ], where the u-th associated valve is IG u , FM i With IG u The correlation coefficient is ω u Among them, IQ j The associated valve is the valve FM i Related, in valve FM i Valves that are also susceptible to fault propagation when a failure risk occurs;

[0021] At the first associated time GT1, GT1= IT1+△T1, obtain the u-th associated valve IG u Risk-related indicators IJB p The actual detection value, and then according to IJB p The judgment threshold of the associated valve IG can be obtained u Risk-related indicators IJB p The indicator deviation θ u ;

[0022] Thus IJB p The correlation index deviation ;

[0023] Get the correlation prediction scores of r risk association indicators IJB ;

[0024] When GW1≥GW0, for fault type IQ j Conduct system warnings;

[0025] When GW1<GW0, enter the second prediction step S3:

[0026] S3, at the second detection time IT2, IT2=GT1+△T2, obtain valve FM i The k detection indicators JB are obtained according to the detection indicators JB z The indicator deviation θ in this test z ', can get valve FM i Fault Type IQ j The second prediction score ;

[0027] When IW2≥IW1, it is confirmed that there is a risk. At this time, the fault type IQ j Conduct system warnings;

[0028] When IW2≤IW0, the risk is confirmed to be eliminated, this step ends, and the process goes to the first prediction step S1;

[0029] When IW0<IW2<IW1, the risk situation cannot be confirmed, and the process proceeds to the association detection step S2.

[0030] In the association detection step S2, the method for obtaining the risk association index is:

[0031] Set the detection index JB z The maximum deviation θ max ;

[0032] When the detection index JB obtained at the IT1 detection time z The indicator deviation θ z >θ max When JB z As valve FM i Risk-related indicators of the valves associated with it.

[0033] In the association detection step S2, the method for obtaining the association risk threshold is:

[0034] We get the risk association distribution λ=r / k;

[0035] Get the associated risk threshold .

[0036] In the associated detection step S2, the valve FM is obtained. i The method of the association valve is: by establishing a network neural model, taking the association features and association degrees as input and output data samples, and training the network neural model.

[0037] The beneficial effects achieved by this application are as follows:

[0038] The present application can overcome the problem of frequent false alarms in the linear judgment of the qualitative model. First, the risk judgment of the fault is obtained; then the judgment result is mapped and verified through the correlation influence relationship of the associated valves. When the double judgments both represent the occurrence of risks, the system is alarmed. In this way, the accuracy of the alarm will be greatly improved. At the same time, the threshold of the first judgment can also be lowered, so that data collection and recording reminders can be carried out before the fault occurs completely. The triggering speed is fast, the cost is low, the start-up and verification of the early warning are very fast, and the application range is wide. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can also be obtained based on these drawings.

[0040] Figure 1 This is a flow chart of the steps of the valve detection method for this application. DETAILED DESCRIPTION

[0041] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of the present application. It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way are interchangeable where appropriate so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] The system of the present application is provided with automatic detection of n valves FM, FM = [FM1, FM2, FM3, ..., FM n ], where the i-th valve is FM i . Known valve FM i m types of faults IQ can occur, IQ = [IQ1, IQ2, IQ3, ..., IQ m ], where the jth type of fault is IQ j .

[0043] For example, for stop valves and regulating valves in hydraulic pipeline applications, due to long-term contact with liquid media, the types of failures that are prone to occur generally include sticking, blockage, valve body breakage, etc.; and for boiler safety valves, since they need to bounce according to pressure, the specific types of failures include valve sticking, adhesion, leakage, etc.

[0044] One of the design objectives of this application is to predict and warn of possible valve failures before they cause any harm. Therefore, first, i Perform the first prediction step:

[0045] The first prediction step includes: setting the fault type IQ j The judgment needs to obtain k detection indicators JB of the valve, JB= [JB1, JB2, JB3, ..., JB k ], where the zth detection index is JB z ;

[0046] Set the detection index JB to be obtained at the first detection time IT1z The actual detection value is Zs, according to the set detection index JB z The judgment threshold Zc can be used to obtain the detection index JB z The indicator deviation θ in this test z =Zs-Zc; For example, in the implementation method, an important detection and evaluation indicator corresponding to the valve fault type "stuck" is the deviation between the actual valve opening and the command opening. Once the deviation between the valve opening and the command opening is large, it means that the risk of "stuck" is also large. In addition, the deviation of detection indicators such as valve flow and pressure difference can also be used as a basis for judging the fault type.

[0047] At the first detection time IT1, according to the obtained detection index JB z The indicator deviation θ z , can get valve FM i Fault Type IQ j The first prediction score ;

[0048] According to the set fault type IQ j The risk threshold IW0;

[0049] When IW1>IW0, it means valve FM i There is a fault type IQ j According to the design concept of this application, the purpose is to predict faults in advance, that is, to take preventive measures before a fault occurs. Therefore, during the initial setting, the value of the risk threshold IW0 should be set to a small value. However, once the value of IW0 is set to a small value, misjudgments may occur frequently. To solve the problem of misjudgment, the prediction needs to be verified again. At this time, the association verification step is entered:

[0050] Set the detection index JB z The maximum deviation θ max ;

[0051] When the detection index JB obtained at the IT1 detection time z The indicator deviation θ z >θ max When JB z As valve FM i Risk-related indicators of its associated valves;

[0052] Set IT1 detection time to obtain r risk association indicators IJB = [IJB1, IJB2, IJB3, ..., IJB r ], r≤k, where the pth risk association index is IJB p , IJB p The indicator deviation is θ p;

[0053] We get the risk association distribution λ=r / k;

[0054] Get the associated risk threshold ;

[0055] Among the remaining n-1 valves, obtain valve FM i The associated valve is the valve FM i Fault Type IQ j When the valve is in operation, it will also be affected by the related effects of the fault and may cause certain risks.

[0056] Specifically, valve FM i The valves associated with it are usually located in the same piping system, are relatively close in physical location, and control parameters such as flow, direction or pressure on the same operating platform. The more similar the valve and its associated valves are in type, function, medium and other characteristics, and the more interdependent they are in operation, the higher their correlation is.

[0057] For example, in an embodiment of a hydraulic application system, it can be found based on historical data that when the spacing L≤S The data for two valves with a flow interaction coefficient K > 0.3 (where S is the pressure wave velocity, approximately 1480 m / s for water media; Δt is the system response time threshold, typically <50 ms) indicates that a change in the opening of one valve can cause a flow change of more than 30% in the other valve. Therefore, the valves meeting these conditions are considered correlated valves, and the flow change is used as the quantitative value of their correlation.

[0058] Similar situations also occur in other implementations. For example, when a valve and its associated valves process the same medium (such as a slurry containing solid particles), the probability of simultaneous valve seat erosion increases by 3-5 times. For valves coexisting in high-vibration areas (such as compressor outlets), mechanical fatigue failures exhibit a linear correlation (the risk is significant when vibration acceleration exceeds 5g). For another example, in a steam generator system, multiple steam valves and condensate valves typically need to be opened or closed in a specific sequence, complementing or relying on each other in operation. For example, after one valve is opened, another valve will be closed to prevent reverse flow. At this time, if a valve fails, it will directly affect the operation of the other valve, and these two valves serve as highly correlated associated valves.

[0059] Therefore, the above correlation data can be quantified as the correlation degree of the correlated valves.

[0060] In addition, the valve correlation features and correlation degrees can also be used as input and output data samples (x, y) to train the network neural model.

[0061] Among them, the associated features include valve position, material, function, medium, flow, pressure, vibration frequency, and operation sequence, and the output sample is the valve's association degree.

[0062] The specific algorithm is: divide the hyperplane in the sample space , recorded as (w, b), sample point The function interval to the partition hyperplane is , the geometric interval is:

[0063] like , we can see that the function interval and the geometric interval are equal. If the hyperplane parameters w and b change proportionally, the function interval also changes proportionally, while the geometric interval remains unchanged.

[0064] The mathematical formula of support vector machine is:

[0065]

[0066] Function interval The value of does not affect the solution of the optimization problem. The function interval has no effect on the inequality of the above optimization problem and has no effect on the objective function. Therefore, , while maximizing Equivalent to minimizing , we can get the optimization problem of the support vector machine that supports linear separability;

[0067]

[0068] Apply Lagrange duality to solve the dual problem; establish Lagrange function and introduce Lagrange multiplier , define the Lagrangian function:

[0069]

[0070] According to the duality of the original problem, the duality of the original problem is a minimax problem, that is

[0071]

[0072] When finding the minimum, Taking the derivative of w and b to zero, we can get

[0073]

[0074] Bringing it into the dual problem, we can get

[0075]

[0076] Solve After that, w and b can also be obtained accordingly.

[0077]

[0078] The kkt condition of the above inequality constraint

[0079]

[0080] For any training sample There is always or ;

[0081] The dual problem is:

[0082]

[0083] Introducing kernel function

[0084] Set the original space , the new space is , define the change (mapping) from the original space to the new space:

[0085]

[0086] set up is a symmetric function, then The necessary and sufficient condition for a positive kernel function is that for any The corresponding Gram matrix (matrix composed of vector inner products):

[0087] It is a semi-positive definite matrix: all eigenvalues ​​are not less than 0

[0088] The objective function of SVM is:

[0089]

[0090] Here C represents the degree of penalty for classification errors in the case of linear inseparability; in principle, C can be selected as any number greater than 0 as needed. The larger C is, the greater the penalty for the total error in the entire optimization process. The higher the level of concern, the higher the requirement for reducing errors, even at the cost of reducing the interval.

[0091] According to the above model, we obtain c associated valves IG = [IG1, IG2, IG3, ..., IG c ], where the u-th associated valve is IG u , FM i With IG u The correlation coefficient is ω u ;

[0092] At the first associated time GT1 (GT1= IT1+△T1), obtain the u-th associated valve IG u Risk-related indicators IJB p The actual detection value, and then according to IJB p The judgment threshold of the associated valve IG can be obtained u Risk-related indicators IJB p The indicator deviation θ u ;

[0093] Thus IJB p The correlation index deviation ;

[0094] Get the correlation prediction scores of r risk association indicators IJB ;

[0095] When GW1≥GW0, it means that after the associated verification, it is confirmed that there is a risk. At this time, the fault type IQ j Conduct system warnings;

[0096] When GW1 < GW0, it means that after the associated verification, it is suspected that the risk may be a false alarm, so the valve needs to be re-tested and enter the second prediction step:

[0097] Get valve FM at the second detection time IT2 (IT2=GT1+△T2) i The k detection indicators JB are obtained according to the detection indicators JB z The indicator deviation θ in this test z ', can get valve FM i Fault Type IQ j The second prediction score ;

[0098] When IW2≥IW1, it is confirmed that there is a risk. At this time, the fault type IQ j Conduct system warnings;

[0099] When IW2≤IW0, the risk is confirmed to be eliminated, this step ends, and the process goes to the first prediction step;

[0100] When IW0<IW2<IW1, the risk situation cannot be confirmed and the process proceeds to the association detection step.

[0101] Furthermore, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein the method described in the above method embodiment is executed when the program is run.

[0102] Furthermore, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the method described in the above method embodiment through the computer program.

[0103] Furthermore, it should be understood that since the configuration of each module is merely for the purpose of illustrating the functional units of the apparatus of the present invention, the physical devices corresponding to these modules may be the processor itself, or a portion of the software in the processor, a portion of the hardware, or a combination of software and hardware. Therefore, the number of modules in the figure is merely illustrative.

[0104] It will be understood by those skilled in the art that all or part of the processes in the methods for implementing the above embodiments of the present invention may also be accomplished by instructing related hardware through a computer program, and the computer program may be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each of the above method embodiments may be implemented. The computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable storage medium may include any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal, and software distribution medium, etc., which may carry the computer program code.

[0105] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is implemented by a network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0106] Those skilled in the art will understand that the various modules in the device can be adaptively split or merged, and such splitting or merging of specific modules will not cause the technical solution to deviate from the principles of the present invention. Therefore, the technical solutions after splitting or merging will fall within the scope of protection of the present invention.

Claims

1. A valve detection method, characterized in that: The following steps are involved: S1, the system provides detection of n valves FM, FM = [FM1, FM2, FM3, ..., FM n ], where the i-th valve is FM i ; Set valve FM i m types of faults IQ can occur, IQ=[IQ1,IQ2,IQ3,…,IQ m ], where the jth type of fault is IQ j ; For valve FM i Perform the first prediction step: Set the fault type IQ j The judgment needs to obtain k detection indicators JB of the valve, JB=[JB1,JB2,JB3,…,JB k ], where the zth detection index is JB z ; Set the detection index JB to be obtained at the first detection time IT1 z The actual detection value is Zs, according to the set detection index JB z The judgment threshold Zc can be used to obtain the detection index JB z The indicator deviation θ in this test z =Zs-Zc; At the first detection time IT1, according to the obtained detection index JB z The indicator deviation θ z , can get valve FM i Fault Type IQ j The first prediction score According to the set fault type IQ j The risk threshold IW0; When IW1>IW0, go to the association verification step S2: S2, obtain valve FM based on the index deviation obtained during IT1 detection time i r risk-related indicators of the valves associated with it IJB=[IJB1,IJB2,IJB3,…,IJB r ], r≤k, where the pth risk association index is IJB p , IJB p The indicator deviation is θ p ; Obtain the associated risk threshold GW0; Get Valve FM i c associated valves with fault propagation IG=[IG1,IG2,IG3,…,IG c ], where the u-th associated valve is IG u , FM i With IG u The correlation coefficient is ω u ; At the first associated time GT1, GT1 = IT1 + △T1, obtain the u-th associated valve IG u Risk-related indicators IJB p The actual detection value, and then according to IJB p The judgment threshold of the associated valve IG can be obtained u Risk-related indicators IJB p The indicator deviation θ u ; Thus IJB p The correlation index deviation Get the correlation prediction scores of r risk association indicators IJB When GW1≥GW0, for fault type IQ j Conduct system warnings; When GW1<GW0, enter the second prediction step S3: S3, at the second detection time IT2, IT2 = GT1 + △T2, obtain the valve FM i The k detection indicators JB are obtained according to the detection indicators JB z The indicator deviation θ in this test z ', can get valve FM i Fault Type IQ j The second prediction score When IW2≥IW1, it is confirmed that there is a risk. At this time, the fault type IQ j Conduct system warnings; When IW2≤IW0, the risk is confirmed to be eliminated, this step ends, and the process goes to the first prediction step S1; When IW0<IW2<IW1, the risk situation cannot be confirmed, and the process proceeds to the association detection step S2.

2. The valve detection method according to claim 1, characterized in that: In the association detection step S2, the method for obtaining the risk association index is: Set the detection index JB z The maximum deviation θ max ; When the detection index JB obtained at the IT1 detection time z The indicator deviation θ z >θ max When JB z As valve FM i Risk-related indicators of the valves associated with it.

3. The valve detection method according to claim 1, characterized in that: In the association detection step S2, the method for obtaining the association risk threshold is: We obtain the risk association distribution λ = r / k; Get the associated risk threshold 4. The valve detection method according to claim 1, wherein: In the associated detection step S2, the valve FM is obtained i The method of the association valve is: by establishing a network neural model, taking the association features and association degrees as input and output data samples, and training the network neural model.

5. A valve detection system using the valve detection method according to any one of claims 1 to 4, characterized in that: It includes a valve data module, an associated valve module, a first prediction module, an associated verification module and a second prediction module; the valve data module includes the associated characteristics and fault types of the valves in the system; the associated valve module can obtain associated valves that have fault propagation correlation with the valve to be inspected based on the associated characteristics of the valves; the first prediction module can detect the valve, and judge whether the valve has a risk of failure through the deviation between the actual detection data of the valve and the theoretical data; when the judgment is yes, the associated verification module can detect the associated valves of the valve to be inspected, and verify the judgment result of the first prediction module through the obtained detection data of the associated valves; when the verification result is that the first prediction module has made a misjudgment, the failure risk of the valve is re-judged through the second prediction module.

6. The valve detection system according to claim 5, characterized in that: The associated features include valve position, material, function, medium, flow, pressure, vibration frequency and operation sequence.

7. The valve detection system according to claim 5, characterized in that: The fault types include sticking, clogging, adhesion, leakage and valve body breakage.

8. The valve detection system according to claim 5, characterized in that: During detection, the first prediction module and the second prediction module determine the risk of the fault by obtaining deviations of several detection indicators corresponding to the fault type.

9. The valve detection system according to claim 8, characterized in that: The association verification module verifies the judgment result of the first prediction module by obtaining the deviation of the risk association indicator with risks in the detection indicators.

Images