Intelligent regulation and control valve and regulation and control method thereof

Abstract

The invention discloses an intelligent regulation and control valve and a regulation and control method thereof, and relates to the technical field of valves.The intelligent regulation and control valve comprises an obtaining module used for obtaining the flow change value of target flow, and the change value of the target flow refers to the difference value between the target flow value at the current moment and the target flow value at the last moment; and the regulation and control module is used for executing a pressure feedback regulation and control strategy when the flow change value of the target flow is greater than a first set value. According to the method, the flow change value of the target flow is obtained, the pressure feedback regulation and control strategy is executed when the flow change value is larger than the first set value, and the influence of the change of the target flow on the valve performance is fully considered. Meanwhile, by obtaining parameters such as the front-back pressure difference of the valve, the sound signal and the real-time pressure value, the comprehensive influence of factors such as the front-back pressure difference of the valve, the cavitation characteristic and the gap characteristic on the performance of the valve is comprehensively considered, accurate correction and control over the opening degree of the valve are achieved, and the precision and stability of flow control are improved.

Description

Technical Field

[0001] The present invention relates to the field of valve technology, and in particular to an intelligent control valve and a control method thereof. Background Art

[0002] In the field of industrial automation control, valves are key components of fluid control systems, and their performance directly affects the stability and efficiency of the entire system. Traditional valve control systems mainly rely on manual settings and empirical judgments, making it difficult to achieve precise flow control, and unable to provide real-time feedback on valve status, resulting in slow response speed and low control accuracy. With the continuous development of sensor technology, communication technology, and control algorithms, intelligent control valves have emerged. They can achieve precise control of valve openings and improve the accuracy and stability of flow control by integrating a variety of advanced technologies, such as building flow characteristic curves, pressure characteristic curves, or prediction models to achieve intelligent control.

[0003] However, existing intelligent control valves still have many defects in the process of flow control. On the one hand, existing technologies often ignore the impact of changes in target flow on valve performance, and only control based on the deviation between real-time flow and target flow, resulting in poor control effect when flow changes drastically. On the other hand, existing technologies fail to fully consider the comprehensive impact of factors such as pressure difference before and after the valve, cavitation characteristics, and clearance characteristics on valve performance, resulting in control accuracy and stability that still need to be improved.

[0004] Specifically, the change in the pressure difference before and after the valve will directly affect the flow state of the fluid and the opening characteristics of the valve, while the cavitation phenomenon may cause noise and vibration inside the valve, which in turn affects the stability and life of the valve. In addition, the clearance characteristics of the valve will also change with the change of the opening, further affecting the flow of the fluid and the control performance of the valve. Therefore, in the design of intelligent control valves, these factors need to be comprehensively considered to achieve more accurate and adaptive control. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides an intelligent control valve and a control method thereof.

[0006] In one aspect, an embodiment of the present invention provides an intelligent control valve, comprising:

[0007] An acquisition module, used to acquire a flow change value of a target flow, wherein the change value of the target flow refers to a difference between the target flow value at a current moment and the target flow value at a previous moment;

[0008] A control module, when the flow change value of the target flow is greater than a first set value, executes a pressure feedback control strategy;

[0009] Wherein, the pressure feedback control strategy includes:

[0010] Obtaining a pressure difference before and after the valve, and determining a clearance characteristic influence coefficient according to the pressure difference before and after the valve;

[0011] Acquiring a sound signal, extracting a sound feature from the sound change signal, inputting the sound feature into a cavitation degree assessment model to determine the cavitation degree, and determining a cavitation characteristic influence coefficient according to the cavitation degree;

[0012] The real-time pressure value and the target pressure change value corresponding to the target flow are obtained, and the valve opening control value is determined according to the real-time pressure value and the target pressure change value corresponding to the target flow. The valve opening control value is corrected according to the clearance characteristic influence coefficient and the cavitation characteristic influence coefficient to obtain the target control value.

[0013] Preferably, determining the clearance characteristic influence coefficient according to the pressure difference before and after the valve includes:

[0014] Establishing a valve geometry model, changing the opening in the valve geometry model to simulate the gap change under different openings, and obtaining an opening gap model;

[0015] Determine the gap area corresponding to the valve opening at the current moment according to the opening gap model;

[0016] The gap characteristic influence coefficient is determined according to the valve opening at the current moment and the gap area.

[0017] Preferably, the calculation formula for determining the gap characteristic influence coefficient according to the valve opening at the current moment and the gap area is:

[0018]

[0019] In the formula, σ represents the gap characteristic influence coefficient, C d represents the set valve flow area at the current moment, D is a constant, ρ represents the density of the fluid, Δp represents the pressure difference before and after the valve, and D is a constant; f(x) is a piecewise function used to describe the change of the clearance characteristic influence coefficient with the valve opening:

[0020]

[0021] Preferably, the sound features include a feature sequence vector and a GAF feature map, wherein the feature sequence vector includes a wavelet feature sequence vector and a Mel energy vector.

[0022] Preferably, the method for obtaining the characteristic graph includes: fitting the sound signal into a sound response curve; and converting the sound response curve into a three-dimensional GAF characteristic graph using a GAF algorithm.

[0023] Preferably, the cavitation degree assessment model includes a convolutional neural network module, a BP neural network module, a fusion module and an output module, the convolutional neural network module is used to process the feature map to obtain a first target feature, the BP neural network module is used to process the feature sequence vector to obtain a second target feature, the fusion module is used to fuse the first target feature and the second target feature to obtain a target feature; the output module is used to output the cavitation degree based on the target feature.

[0024] Preferably, the valve opening control value is corrected according to the clearance characteristic influence coefficient and the cavitation characteristic influence coefficient, and the formula for obtaining the target control value is:

[0025] H=E·σ·μ·h;

[0026] Among them, σ represents the influence coefficient of clearance characteristics, μ represents the influence coefficient of cavitation characteristics, h represents the valve opening control value, and E is a constant.

[0027] On the other hand, a method for controlling an intelligent control valve includes:

[0028] Step 1, obtaining a flow change value of a target flow, wherein the change value of the target flow refers to a difference between a target flow value at a current moment and a target flow value at a previous moment;

[0029] Step 2, when the flow change value of the target flow is greater than the first set value, execute the pressure feedback control strategy; wherein the pressure feedback control strategy includes: obtaining the pressure difference before and after the valve, and determining the clearance characteristic influence coefficient according to the pressure difference before and after the valve; obtaining a sound signal, extracting the sound feature from the sound change signal, inputting the sound feature into the cavitation degree assessment model to determine the cavitation degree, and determining the cavitation characteristic influence coefficient according to the cavitation degree; obtaining the target pressure change value corresponding to the target flow, and adjusting the valve opening according to the clearance characteristic influence coefficient, the cavitation characteristic influence coefficient and the target pressure change value.

[0030] The beneficial effects of the present invention are as follows: the present invention provides an intelligent control valve and a control method thereof. The present invention obtains the flow change value of the target flow and executes a pressure feedback control strategy when it is greater than a first set value, thereby fully considering the influence of the change of the target flow on the valve performance. At the same time, the present invention also obtains parameters such as the pressure difference before and after the valve, the sound signal, and the real-time pressure value, comprehensively considering the comprehensive influence of factors such as the pressure difference before and after the valve, cavitation characteristics, and clearance characteristics on the valve performance, thereby achieving accurate correction and control of the valve opening and improving the accuracy and stability of flow control. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0032] Figure 1 A schematic diagram of the structure of an intelligent control valve provided by an embodiment of the present invention;

[0033] Figure 2 A flow chart of an intelligent control valve control method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0035] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0036] like Figure 1 As shown, an embodiment of the present invention provides an intelligent control valve, including: an acquisition module, used to acquire a flow change value of a target flow, wherein the change value of the target flow refers to the difference between the target flow value at the current moment and the target flow at the previous moment; and a control module, which executes a pressure feedback control strategy when the flow change value of the target flow is greater than a first set value. The pressure feedback control strategy includes: acquiring a pressure difference before and after the valve, and determining a clearance characteristic influence coefficient according to the pressure difference before and after the valve; acquiring a sound signal, extracting a sound feature from the sound change signal, inputting the sound feature into a cavitation degree assessment model to determine the cavitation degree, and determining a cavitation characteristic influence coefficient according to the cavitation degree; acquiring a real-time pressure value and a target pressure change value corresponding to the target flow, determining a valve opening control value according to the real-time pressure value and the target pressure change value corresponding to the target flow, and correcting the valve opening control value according to the clearance characteristic influence coefficient and the cavitation characteristic influence coefficient to obtain a target control value.

[0037] In this embodiment, the gap characteristic influence coefficient is determined according to the pressure difference before and after the valve, including: establishing a valve geometry model, changing the opening in the valve geometry model to simulate the gap change under different openings, and obtaining an opening gap model; determining the gap area corresponding to the valve opening at the current moment according to the opening gap model; and determining the gap characteristic influence coefficient according to the valve opening at the current moment and the gap area.

[0038] It should be noted that the process of determining the clearance characteristic influence coefficient is a complex calculation process that comprehensively considers the valve geometry, opening state and fluid dynamics characteristics. The following is a detailed process of determining the clearance characteristic influence coefficient based on the pressure difference before and after the valve:

[0039] First, in order to accurately simulate the gap change of the valve at different openings, a geometric model of the valve was established. This model accurately reflects the physical structure and size of the valve, including the valve disc, valve seat and the gap between them. Then, a series of simulation experiments were carried out using this geometric model. During the simulation process, the valve opening was changed to simulate the various opening states that the valve may encounter during actual operation. Through these simulation experiments, the relationship between the valve opening and the gap area was obtained, namely the opening gap model. This model can accurately describe the change of the valve gap area at different openings. Then, based on the valve opening information obtained in real time, the gap area corresponding to the current valve opening was determined using the opening gap model. This gap area is an important parameter for calculating the gap characteristic influence coefficient. Finally, the valve opening and gap area at the current moment were comprehensively considered, and the gap characteristic influence coefficient was determined using a specific calculation formula. This coefficient reflects the joint influence of the valve opening and gap characteristics on the fluid flow state, and is an important reference for subsequent valve opening regulation.

[0040] Through this series of steps, the clearance characteristic influence coefficient can be accurately calculated, providing strong support for the precise control of the intelligent control valve.

[0041] In this embodiment, the calculation formula for determining the gap characteristic influence coefficient according to the valve opening at the current moment and the gap area is:

[0042]

[0043] In the formula, σ represents the gap characteristic influence coefficient, C d represents the set valve flow area at the current moment, D is a constant, ρ represents the density of the fluid, Δp represents the pressure difference before and after the valve, and D is a constant; f(x) is a piecewise function used to describe the change of the clearance characteristic influence coefficient with the valve opening:

[0044]

[0045] This formula can be used to calculate the clearance characteristic influence coefficient δ according to the change in valve opening, and it can be used for precise flow control. In practical applications, the specific values ​​of n and m need to be determined based on the valve characteristics and experimental data.

[0046] In this embodiment, the sound features include a feature sequence vector and a GAF feature graph, wherein the feature sequence vector includes a wavelet feature sequence vector and a Mel energy vector, wherein the method for obtaining the feature graph includes: fitting the sound signal into a sound response curve; and converting the sound response curve into a three-dimensional GAF feature graph using a GAF algorithm.

[0047] In this embodiment, the sound features include a feature sequence vector and a GAF feature graph, wherein the feature sequence vector includes a wavelet feature sequence vector and a Mel energy vector, wherein the method for obtaining the feature graph includes: fitting the sound signal into a sound response curve; and converting the sound response curve into a three-dimensional GAF feature graph using a GAF algorithm.

[0048] The GAF algorithm is an image coding technique that uses coordinate transformation and Gram matrix to convert time series (such as sound signals) into two-dimensional or three-dimensional images. This conversion method can maintain the time dependency in the time series, so that the pixels or voxels in the image can reflect the time structure and dynamic characteristics of the original signal.

[0049] In this embodiment, the cavitation degree assessment model includes a convolutional neural network module, a BP neural network module, a fusion module and an output module. The convolutional neural network module is used to process the feature map to obtain a first target feature, the BP neural network module is used to process the feature sequence vector to obtain a second target feature, the fusion module is used to fuse the first target feature and the second target feature to obtain a target feature; the output module is used to output the cavitation degree based on the target feature.

[0050] In the field of cavitation assessment, existing methods only use single modal features such as graph domain features or wavelet vectors to assess the degree of cavitation, without considering the complementarity of information between different modalities and the importance of modal fusion for cavitation assessment. Therefore, in order to analyze the impact of different domain features on the assessment of sound signals with cavitation noise, the embodiment of the present invention combines the "late" fusion (decision-level fusion) idea in the multimodal information fusion method, and uses a deep learning model to train the graph domain modality and vector modality of the sound signal respectively, and then through the "addition" combination in the multimodal joint architecture, that is, feature fusion, finally realizes the cavitation degree assessment.

[0051] In this embodiment, the valve opening control value is corrected according to the clearance characteristic influence coefficient and the cavitation characteristic influence coefficient, and the formula for obtaining the target control value is:

[0052] H=E·σ·μ·h;

[0053] Among them, σ represents the influence coefficient of clearance characteristics, μ represents the influence coefficient of cavitation characteristics, h represents the valve opening control value, and E is a constant.

[0054] Taking into account the influence coefficient of clearance characteristics and cavitation characteristics, a specific correction formula is used to correct the valve opening control value. This correction process can ensure accurate control of valve opening under different working conditions and improve the accuracy and stability of flow control.

[0055] It should be noted that when calculating the valve opening control value, a valve control value is determined according to the target flow rate, the real-time flow rate, and the pressure difference before and after the valve. Of course, in some embodiments, a correction coefficient can also be determined according to the pressure at the outlet of the fluid channel at the current moment and the pressure value at the previous moment to make a preliminary correction to the valve control value.

[0056] Based on the same inventive concept, an embodiment of the present invention further provides an intelligent control valve control method, the method comprising:

[0057] Step 1, obtaining a flow change value of a target flow, wherein the change value of the target flow refers to a difference between a target flow value at a current moment and a target flow value at a previous moment;

[0058] Step 2, when the flow change value of the target flow is greater than the first set value, execute the pressure feedback control strategy; wherein the pressure feedback control strategy includes: obtaining the pressure difference before and after the valve, and determining the clearance characteristic influence coefficient according to the pressure difference before and after the valve; obtaining a sound signal, extracting the sound feature from the sound change signal, inputting the sound feature into the cavitation degree assessment model to determine the cavitation degree, and determining the cavitation characteristic influence coefficient according to the cavitation degree; obtaining the target pressure change value corresponding to the target flow, and adjusting the valve opening according to the clearance characteristic influence coefficient, the cavitation characteristic influence coefficient and the target pressure change value.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An intelligent control valve, characterized in that: include: An acquisition module, used to acquire a flow change value of a target flow, wherein the change value of the target flow refers to a difference between the target flow value at a current moment and the target flow value at a previous moment; A control module, when the flow change value of the target flow is greater than a first set value, executes a pressure feedback control strategy; Wherein, the pressure feedback control strategy includes: Obtaining a pressure difference before and after the valve, and determining a clearance characteristic influence coefficient according to the pressure difference before and after the valve; Acquiring a sound signal, extracting a sound feature from the sound change signal, inputting the sound feature into a cavitation degree evaluation model to determine the cavitation degree, and determining a cavitation characteristic influence coefficient according to the cavitation degree; The real-time pressure value and the target pressure change value corresponding to the target flow are obtained, and the valve opening control value is determined according to the real-time pressure value and the target pressure change value corresponding to the target flow. The valve opening control value is corrected according to the clearance characteristic influence coefficient and the cavitation characteristic influence coefficient to obtain the target control value.

2. The intelligent control valve according to claim 1, characterized in that: The clearance characteristic influence coefficient is determined according to the pressure difference before and after the valve, including: Establishing a valve geometry model, changing the opening in the valve geometry model to simulate the gap change under different openings, and obtaining an opening gap model; Determine the gap area corresponding to the valve opening at the current moment according to the opening gap model; The gap characteristic influence coefficient is determined according to the valve opening at the current moment and the gap area.

3. The intelligent control valve according to claim 2, characterized in that: The calculation formula for determining the gap characteristic influence coefficient according to the valve opening at the current moment and the gap area is: In the formula, σ represents the gap characteristic influence coefficient, C d represents the set valve flow area at the current moment, D is a constant, ρ represents the density of the fluid, Δp represents the pressure difference before and after the valve, and D is a constant; f(x) is a piecewise function used to describe the change of the clearance characteristic influence coefficient with the valve opening:

4. The intelligent control valve according to claim 1, characterized in that: The sound features include a feature sequence vector and a GAF feature map, wherein the feature sequence vector includes a wavelet feature sequence vector and a Mel energy vector.

5. The intelligent control valve according to claim 4, characterized in that: The method for obtaining a characteristic graph comprises: fitting the sound signal into a sound response curve; and converting the sound response curve into a three-dimensional GAF characteristic graph by using a GAF algorithm.

6. The intelligent control valve according to claim 5, characterized in that: The cavitation degree assessment model includes a convolutional neural network module, a BP neural network module, a fusion module and an output module, wherein the convolutional neural network module is used to process the feature map to obtain a first target feature, the BP neural network module is used to process the feature sequence vector to obtain a second target feature, and the fusion module is used to fuse the first target feature and the second target feature to obtain a target feature; The output module is used to output the cavitation degree based on the target feature.

7. The intelligent control valve according to claim 1, characterized in that: The valve opening control value is corrected according to the clearance characteristic influence coefficient and the cavitation characteristic influence coefficient, and the formula for obtaining the target control value is: H=E·σ·μ·h; Among them, σ represents the influence coefficient of clearance characteristics, μ represents the influence coefficient of cavitation characteristics, h represents the valve opening control value, and E is a constant.

8. An intelligent control valve control method, characterized in that: include: Step 1, obtaining a flow change value of a target flow, wherein the change value of the target flow refers to a difference between a target flow value at a current moment and a target flow value at a previous moment; Step 2, when the flow change value of the target flow is greater than the first set value, execute the pressure feedback control strategy; wherein the pressure feedback control strategy includes: obtaining the pressure difference before and after the valve, and determining the clearance characteristic influence coefficient according to the pressure difference before and after the valve; obtaining a sound signal, extracting the sound feature from the sound change signal, inputting the sound feature into the cavitation degree assessment model to determine the cavitation degree, and determining the cavitation characteristic influence coefficient according to the cavitation degree; obtaining the target pressure change value corresponding to the target flow, and adjusting the valve opening according to the clearance characteristic influence coefficient, the cavitation characteristic influence coefficient and the target pressure change value.

Images