Intelligent water flow valve control method integrating mechanism and neural network

Abstract

The invention provides a water flow valve intelligent control method fusing a mechanism and a neural network, and relates to the technical field of industrial automation control. The method comprises the steps that flow and inlet pressure of a flow valve at different opening degrees in different system states are collected; based on the collected data, constructing and training a saturation opening degree prediction model, a saturation flow prediction model and an opening degree prediction model based on mixing of a mechanism and a neural network; when monitoring that the target flow is changed, judging whether the target flow is greater than saturated flow or not by using a saturated flow prediction model; if not, predicting a target opening degree by using an opening degree prediction model based on mixing of a mechanism and a neural network, and setting the opening degree of the flow valve as the predicted target opening degree; after the flow is stable, if the difference between the current flow and the target flow is smaller than or equal to a set threshold value, the PID control mode is directly used for fine adjustment so as to reach the target flow. In this way, rapid and high-precision control over the cooling water flow in the continuous casting process can be achieved.

Description

Technical Field

[0001] This invention relates to the field of industrial automation control technology, and in particular to an intelligent control method for water flow valves that integrates mechanisms and neural networks. Background Technology

[0002] Continuous casting (CV) is a crucial process in metal forming and processing. During CV, molten metal flows continuously into the mold and solidifies under the action of cooling water. The precision and efficiency of cooling water flow control directly affect the quality of the CV product and are also key to achieving real-time control. Especially during process changes or high-throughput experiments, the cooling water flow control target often needs significant adjustments, requiring a rapid response from the process.

[0003] Currently, flow control mostly employs proportional-integral-derivative (PID) controllers. For example, Chinese patent CN117884590A proposes a water flow control device and method for an aluminum casting system. It maintains stable water supply by monitoring cooling water pressure and flow rate, and using PID control. It performs well in scenarios with small flow fluctuations. However, PID parameter setting relies on experience, and when facing systems with large flow variations, nonlinearity, and delayed feedback, it suffers from slow response, large overshoot, and oscillations, failing to meet the process control requirements of large-amplitude, fast, and high-precision responses.

[0004] In recent years, data-driven models, represented by artificial neural networks (ANNs), have been proposed. For example, Chinese patent CN111456840B proposes an intelligent control method for cooling water flow in internal combustion engines based on RBF neural networks. This method uses collected data to train the neural network to predict water temperature and adjusts the water flow based on the temperature difference. While artificial neural networks have strong nonlinear fitting capabilities, their generalization ability is poor under operating conditions outside the coverage of the training data, making it difficult to guarantee reliability in industrial scenarios.

[0005] To solve the above problems, there is an urgent need to implement a flow control method that is highly accurate, fast-responding, physically meaningful, and stable. Summary of the Invention

[0006] This invention provides an intelligent control method for water flow valves that integrates mechanisms and neural networks, enabling rapid control of cooling water flow to a target value, thereby achieving fast and high-precision control of cooling water flow in the continuous casting process. The technical solution is as follows:

[0007] On the one hand, a method for intelligent control of water flow valves that integrates mechanisms and neural networks is provided. This method is implemented by an intelligent control device for water flow valves and includes: S1. Collect the flow rate and inlet pressure of the flow valve at different opening degrees under different system conditions; where the flow rate refers to the cooling water flow rate. S2. Based on the collected flow valve opening and the corresponding flow rate and inlet pressure, construct and train the saturation opening prediction model and the saturation flow prediction model. S3. Based on the opening degree of the flow valve and the corresponding flow rate and inlet pressure, construct and train an opening degree prediction model based on a hybrid mechanism and neural network. S4. When a change in the target flow rate is detected, the saturated flow rate prediction model is used to determine whether the target flow rate is greater than the saturated flow rate. If it is greater, the system will report: "Unable to reach the flow rate" and set the flow valve opening to the saturated opening. If it is less than or equal to the target flow rate, the system will use a mechanism-based and neural network-based opening prediction model to predict the target opening and set the flow valve opening to the predicted target opening. S5. Once the flow rate stabilizes, detect the difference between the current flow rate and the target flow rate. If the difference is greater than the set threshold, use the opening prediction model based on a hybrid mechanism and neural network to predict the target opening again, and set the flow valve opening to the target opening. Once the flow rate stabilizes, use PID control for fine-tuning. If the difference is less than or equal to the set threshold, use PID control directly for fine-tuning to achieve the target flow rate.

[0008] Furthermore, the collection of flow rate and inlet pressure at different opening degrees of the flow valve under different system conditions includes: By changing the opening degree of the flow valve under different system conditions, the flow rate and inlet pressure at different opening degrees are recorded to obtain a dataset consisting of the flow valve opening degree, flow rate, and inlet pressure.

[0009] Furthermore, the construction and training of the saturation opening prediction model and the saturation flow prediction model based on the collected flow valve opening and the corresponding flow rate and inlet pressure includes: Use the residual flow gain to determine the saturation flow rate and saturation opening of the flow valve at different opening degrees; Using the opening degree, flow rate, and inlet pressure of the flow valve at different opening degrees as inputs and the saturated flow rate as output, a first artificial neural network is trained to obtain a saturated flow rate prediction model; the trained saturated flow rate prediction model is used to output the saturated flow rate. Using the opening degree, flow rate, and inlet pressure of the flow valve at different opening degrees as inputs and the saturation opening degree as output, a second artificial neural network is trained to obtain a saturation opening degree prediction model; the trained saturation opening degree prediction model is used to output the saturation opening degree.

[0010] Furthermore, the remaining flow gain Defined as: ; in, This is the flow rate when the flow valve is at its maximum opening. and During the process of gradually adjusting the opening of the flow valve, the first... The values ​​of the valve opening and flow rate after the flow rate is adjusted; It is 100% open.

[0011] Furthermore, saturation opening H and saturation flow for: H ; ; ; in, As an intermediate variable, For gain threshold, subscript To meet time .

[0012] Furthermore, the aperture prediction model based on a hybrid mechanism and neural network is implemented by correcting the parameters of the physical formula using a neural network. The physical formula is a neural network-corrected flow formula based on the Bernoulli equation. ; in, For the predicted target opening, For target traffic, The flow rate at maximum opening. The pressure drop at maximum opening. For effective pressure differential, , The optimization terms are given for the coefficient correction network and the pressure correction network, respectively. It is a function fitted by a neural network.

[0013] Furthermore, both the coefficient correction network and the pressure correction network adopt a feedforward neural network architecture, which includes an input layer, multiple hidden layers, and an output layer.

[0014] Furthermore, the prediction of the target opening degree using a hybrid mechanism-and-neural network-based opening degree prediction model includes: Using the current opening degree, current flow rate, current inlet pressure, and target flow rate as inputs, and the target opening degree as output, an opening degree prediction model based on a hybrid mechanism and neural network is used to predict the target opening degree.

[0015] On the other hand, a smart control device for a water flow valve is provided, the smart control device for a water flow valve comprising: a processor; and a memory, the memory storing computer-readable instructions, which, when executed by the processor, implement any one of the above-described smart control methods for a water flow valve based on the fusion mechanism and neural network.

[0016] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described intelligent control methods for water flow valves based on the fusion mechanism and neural network.

[0017] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. The control speed and accuracy are significantly improved. The target opening is directly calculated by using a hybrid mechanism and neural network-based opening prediction model, achieving a millisecond-level fast response. The adjustment time is only related to the action speed of the actuator, realizing fast and high-precision control of cooling water flow in the continuous casting process.

[0018] 2. There is no overshoot or oscillation phenomenon. The target opening degree is given directly, eliminating the overshoot and oscillation phenomenon that is common in traditional feedback control, especially when the flow rate changes significantly, and shortening the process changeover time.

[0019] 3. Strong generalization ability: Since the core of the opening prediction model based on the combination of mechanism and neural network is to correct physical parameters, rather than just fitting the sampled data, the model can still maintain good adjustment ability when the training data is sparse or the working conditions change beyond the training set, thus overcoming the shortcomings of pure data-driven models in terms of poor generalization ability outside the training set. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a smart control method for water flow valve that integrates mechanism and neural network according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the opening degree prediction model based on a hybrid mechanism and neural network provided in an embodiment of the present invention; Figure 3 This is a schematic diagram comparing the effects of intelligent water flow valve control based on the fusion mechanism and neural network provided in this embodiment of the invention with traditional PID control; Figure 4This is a schematic diagram of the structure of an intelligent control device for a water flow valve provided in an embodiment of the present invention. Detailed Implementation

[0022] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0023] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0024] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0025] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0026] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0027] This invention provides an intelligent control method for water flow valves that integrates mechanisms and neural networks. This method can be implemented by an intelligent control device for the water flow valve, which can be a terminal or a server. Figure 1 The flowchart shown illustrates the intelligent control method for water flow valves based on the fusion mechanism and neural network. The processing flow of this method may include the following steps:

[0028] S1. Collect the flow rate and inlet pressure of the flow valve at different opening degrees under different system conditions; where the flow rate refers to the cooling water flow rate. In this embodiment, when collecting flow rate and inlet pressure under different system states (different system states mainly refer to different maximum flow rates), it is necessary to change the opening of the flow valve multiple times and record the flow rate and inlet pressure at different openings of the flow valve to obtain a dataset composed of the flow valve opening, flow rate and inlet pressure. This dataset is then divided into a training set and a test set so that the collected dataset contains different initial system states.

[0029] S2. Based on the collected flow valve opening and corresponding flow rate and inlet pressure, construct and train a saturation opening prediction model and a saturation flow rate prediction model; specifically, this may include the following steps: S21. Use the residual flow gain to determine the saturation flow rate and saturation opening of the flow valve at different opening degrees, thereby obtaining a continuous high-precision saturation label; wherein, the residual flow gain Defined as: ; in, This is the flow rate when the flow valve is at its maximum opening, i.e., 100% opening. and During the process of gradually adjusting the opening of the flow valve, the first... The values ​​of the valve opening and flow rate after the flow rate is adjusted; 100% opening; In this embodiment, a gain threshold is set. ,exist Make Define saturation opening H and saturation flow for: H ; ; ; in, As an intermediate variable, For gain threshold, subscript To meet time .

[0030] S22. Using the opening degree, flow rate, and inlet pressure of the flow valve at different opening degrees as inputs and the saturated flow rate as output, train the first artificial neural network to obtain the saturated flow rate prediction model; wherein, the trained saturated flow rate prediction model is used to output the saturated flow rate. S23. Using the opening degree, flow rate, and inlet pressure of the flow valve at different opening degrees as inputs and the saturation opening degree as output, train a second artificial neural network to obtain a saturation opening degree prediction model; wherein, the trained saturation opening degree prediction model is used to output the saturation opening degree.

[0031] S3. Based on the valve opening degree and the corresponding flow rate and inlet pressure, construct and train an opening degree prediction model based on a hybrid mechanism and neural network, such as... Figure 2 As shown, the model uses the current opening degree at the time the data is collected. Current traffic Current entry pressure and target traffic The input is the target opening, and the output is the target opening. In this embodiment, the aperture prediction model based on a hybrid mechanism and neural network is implemented by correcting the parameters of the physical formula using a neural network. The physical formula is a flow formula based on Bernoulli's equation, corrected by the neural network. ; in, For the predicted target opening, For target traffic, The flow rate at maximum opening. The pressure drop at maximum opening. For effective pressure differential, , These are coefficient correction networks ( ) and pressure correction network ( The optimization terms given are: It is a function fitted by a neural network, in this embodiment. Neural networks It employs a feedforward neural network with four hidden layers, each containing 128 neurons.

[0032] In this embodiment, both the coefficient correction network and the pressure correction network adopt a feedforward neural network architecture, which includes an input layer, multiple hidden layers (e.g., 3 hidden layers, each with 128 neurons) and an output layer.

[0033] In this embodiment, a neural network is used to apply the fixed parameters in the mechanism formula. and simplified parameters The learning function is defined as a function of opening, flow rate, inlet pressure, and target flow rate.

[0034] S4. When a change in the target flow rate is detected, the saturated flow rate prediction model is used to determine whether the target flow rate is greater than the saturated flow rate. If it is greater, the system will report: "The flow rate cannot be reached," and set the flow valve opening to the saturated opening (determined by the saturated opening prediction model in S2). If it is less than or equal to the target flow rate, the system will use a mechanism-based and neural network-based opening prediction model to predict the target opening, and set the flow valve opening to the predicted target opening. S5. Once the flow rate stabilizes, the difference between the current flow rate and the target flow rate is detected. If the difference is greater than a set threshold, the target opening is predicted again using a hybrid mechanism and neural network-based opening prediction model, and the flow valve opening is set to the target opening. After the flow rate stabilizes, PID control is used for fine-tuning. If the difference is less than or equal to the set threshold, PID control is used directly for fine-tuning to achieve the target flow rate. In this way, the cooling water flow rate can be quickly controlled to the target value, and overshoot and oscillation are less likely to occur, thus achieving rapid and high-precision control of the cooling water flow rate in the continuous casting process. Figure 3 This diagram illustrates a comparison between the intelligent control of the water flow valve based on the fusion mechanism and neural network provided in this embodiment and the traditional PID control. Compared to traditional PID control, the intelligent control provided in this embodiment has significant advantages. In fact, due to the hysteresis of the flow sensor, the intelligent control provided in this embodiment is significantly better than traditional PID control. Figure 3 The time shown is faster to reach the set target value, and its speed is only related to the action speed of the actuator.

[0035] In summary, the intelligent control method for water flow valves that integrates the fusion mechanism and neural network provided in this invention has at least the following beneficial effects: 1. The control speed and accuracy are significantly improved. The target opening is directly calculated by using a hybrid mechanism and neural network-based opening prediction model, achieving a millisecond-level fast response. The adjustment time is only related to the action speed of the actuator, realizing fast and high-precision control of cooling water flow in the continuous casting process.

[0036] 2. There is no overshoot or oscillation phenomenon. The target opening degree is given directly, eliminating the overshoot and oscillation phenomenon that is common in traditional feedback control, especially when the flow rate changes significantly, and shortening the process changeover time.

[0037] 3. Strong generalization ability: The core of the opening prediction model based on a hybrid mechanism and neural network is to correct physical parameters according to the actual state of the system (flow rate, pressure, opening). and It is not just a fit to the sampled data. Therefore, when the training data is sparse or the working conditions change beyond the training set, the model can still maintain good adjustment ability, overcoming the shortcomings of pure data-driven models in generalizing ability outside the training set.

[0038] Figure 4 This is a structural schematic diagram of a smart control device for a water flow valve provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the intelligent control device for water flow valves may include the above-mentioned Figure 3 The illustrated intelligent control device for water flow valves utilizes a fusion mechanism and neural network. Optionally, the intelligent control device 410 for water flow valves may include a first processor 2001.

[0039] Optionally, the intelligent control device 410 for the water flow valve may also include a memory 2002 and a transceiver 2003.

[0040] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0041] The following is combined Figure 4 A detailed introduction to each component of the intelligent water flow valve control device 410 is provided below: The first processor 2001 is the control center of the intelligent water flow valve control device 410. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0042] Optionally, the first processor 2001 can perform various functions of the intelligent water flow valve control device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0043] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0044] In a specific implementation, as one example, the intelligent water flow valve control device 410 may also include multiple processors, for example... Figure 4 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0045] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0046] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently, and may be connected via the interface circuit of the water flow valve intelligent control device 410. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0047] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0048] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0049] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected to the interface circuit of the water flow valve intelligent control device 410. Figure 4 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0050] It should be noted that, Figure 4 The structure of the intelligent water flow valve control device 410 shown in the figure does not constitute a limitation on the router. The actual knowledge structure identification device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0051] Furthermore, the technical effects of the intelligent water flow valve control device 410 can be referenced from the technical effects of the intelligent water flow valve control method based on the fusion mechanism and neural network described in the above method embodiments, and will not be repeated here.

[0052] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0053] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0054] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0055] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0056] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0057] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0058] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0059] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0060] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0062] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0063] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for intelligent control of water flow valves that integrates mechanisms and neural networks, characterized in that, The method includes: S1. Collect the flow rate and inlet pressure of the flow valve at different opening degrees under different system conditions; where the flow rate refers to the cooling water flow rate. S2. Based on the collected flow valve opening and the corresponding flow rate and inlet pressure, construct and train the saturation opening prediction model and the saturation flow prediction model. S3. Based on the opening degree of the flow valve and the corresponding flow rate and inlet pressure, construct and train an opening degree prediction model based on a hybrid mechanism and neural network. S4. When a change in the target flow rate is detected, the saturated flow rate prediction model is used to determine whether the target flow rate is greater than the saturated flow rate. If it is greater, the system will report: "Unable to reach the flow rate" and set the flow valve opening to the saturated opening. If it is less than or equal to the target flow rate, the system will use a mechanism-based and neural network-based opening prediction model to predict the target opening and set the flow valve opening to the predicted target opening. S5. Once the flow rate stabilizes, detect the difference between the current flow rate and the target flow rate. If the difference is greater than the set threshold, use the opening prediction model based on a hybrid mechanism and neural network to predict the target opening again, and set the flow valve opening to the target opening. Once the flow rate stabilizes, use PID control for fine-tuning. If the difference is less than or equal to the set threshold, use PID control directly for fine-tuning to achieve the target flow rate.

2. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 1, characterized in that, The collection of flow rate and inlet pressure at different opening degrees of the flow valve under different system conditions includes: By changing the opening degree of the flow valve under different system conditions, the flow rate and inlet pressure at different opening degrees are recorded to obtain a dataset consisting of the flow valve opening degree, flow rate, and inlet pressure.

3. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 1, characterized in that, The construction and training of the saturation opening prediction model and the saturation flow prediction model based on the collected flow valve opening degree and the corresponding flow rate and inlet pressure includes: Use the residual flow gain to determine the saturation flow rate and saturation opening of the flow valve at different opening degrees; Using the opening degree, flow rate, and inlet pressure of the flow valve at different opening degrees as inputs and the saturated flow rate as output, a first artificial neural network is trained to obtain a saturated flow rate prediction model; the trained saturated flow rate prediction model is used to output the saturated flow rate. Using the opening degree, flow rate, and inlet pressure of the flow valve at different opening degrees as inputs and the saturation opening degree as output, a second artificial neural network is trained to obtain a saturation opening degree prediction model; the trained saturation opening degree prediction model is used to output the saturation opening degree.

4. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 3, characterized in that, The remaining flow gain Defined as: ； in, This is the flow rate when the flow valve is at its maximum opening. and During the process of gradually adjusting the opening of the flow valve, the first... The values ​​of the valve opening and flow rate after the flow rate is adjusted; It is 100% open.

5. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 4, characterized in that, Saturation opening H and saturation flow for: H ； ； ； in, As an intermediate variable, For gain threshold, subscript To meet time .

6. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 1, characterized in that, The flow rate prediction model based on a hybrid mechanism and neural network is implemented by modifying the parameters of the physical formula using a neural network. The physical formula is a flow rate formula based on Bernoulli's equation modified by the neural network. ； in, For the predicted target opening, For target traffic, The flow rate at maximum opening. The pressure drop at maximum opening. For effective pressure differential, , The optimization terms are given for the coefficient correction network and the pressure correction network, respectively. It is a function fitted by a neural network.

7. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 6, characterized in that, Both the coefficient correction network and the pressure correction network adopt a feedforward neural network architecture, which includes an input layer, multiple hidden layers, and an output layer.

8. The intelligent control method for water flow valve based on the fusion mechanism and neural network as described in claim 1, characterized in that, The method of using a hybrid mechanism-based and neural network-based opening prediction model to predict the target opening includes: Using the current opening degree, current flow rate, current inlet pressure, and target flow rate as inputs, and the target opening degree as output, an opening degree prediction model based on a hybrid mechanism and neural network is used to predict the target opening degree.

9. A smart control device for a water flow valve, characterized in that, The intelligent control device for the water flow valve includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 8.

Images