A cyclone separator control method, system and device adapted to flow variations

Abstract

The application discloses a cyclone separator control method, system and equipment suitable for flow change, relates to the technical field of cyclone separators, and comprises the following steps: a cyclone separator performance prediction model is constructed based on a machine learning method; a gas flow rate at a cyclone separator inlet is input into the cyclone separator performance prediction model to predict a separation efficiency of the cyclone separator; a flow control signal is determined according to a difference between the predicted separation efficiency of the cyclone separator and an optimal separation efficiency of the cyclone separator; and a fan controller controls motor frequency based on the flow control signal, so as to control jet flow into the cyclone separator, and make the cyclone separator be in a flow mode with optimal separation efficiency. The application can make the cyclone separator always be in a flow mode with optimal separation efficiency, and avoid the problem of low separation efficiency of the cyclone separator caused by flow parameter change in a process.

Description

Technical Field

[0001] This invention relates to the field of cyclone separator technology, and in particular to a cyclone separator control method, system and equipment that adapts to changes in flow rate. Background Technology

[0002] Cyclone separators are hailed as masterpieces of process equipment. With their simple structure and lack of moving parts, they achieve gas-solid phase separation solely through centrifugal force difference. Compared to methods such as filtration, washing, and electrostatic precipitators, cyclone separation offers advantages such as wider applicability, lower operating costs, and greater tolerance to high-temperature and high-pressure conditions. It is widely used in gas purification and particle recovery in numerous industrial processes, including energy, chemical, and petroleum industries. The separation efficiency of a cyclone separator is closely related to its inlet velocity, typically operating within an optimal range. Below this range, the centrifugal force on the particles is insufficient, leading to decreased separation efficiency; excessively high inlet velocities result in significant energy loss. However, in actual industrial processes, periodic fluctuations in the process often cause the separator's inlet gas velocity to deviate from its design range, reducing separation efficiency and resulting in substandard exhaust emissions or severe particle loss.

[0003] To address the issue of reduced separation efficiency caused by fluctuations in separator inlet flow rate, existing technologies aim to adjust the inlet gas velocity by changing the separator inlet area. However, when the inlet flow rate deviates from the design range, even if the inlet gas velocity is adjusted to reach the design range, the gas flow pattern in the separator is still not optimal, making it difficult to achieve good separation efficiency.

[0004] Existing methods for enhancing gas-solid separation based on flow control cannot adapt to fluctuations in the separator inlet flow rate and are difficult to achieve excellent separation results. Summary of the Invention

[0005] The purpose of this invention is to provide a cyclone separator control method, system, and equipment that adapts to flow rate changes, in order to solve the problem of low cyclone separation efficiency caused by flow rate fluctuations in the gas-solid two-phase system in process industries.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A cyclone separator control method adapting to flow rate changes includes:

[0008] A performance prediction model for cyclone separators was constructed based on machine learning methods.

[0009] The gas flow rate at the inlet of the cyclone separator is input into the cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator;

[0010] The flow control signal is determined based on the difference between the predicted separation efficiency of the cyclone separator and the optimal separation efficiency of the cyclone separator.

[0011] Based on the flow control signal, the fan controller controls the motor frequency, thereby controlling the jet flow rate entering the cyclone separator, so that the cyclone separator is in the flow mode with optimal separation efficiency.

[0012] Optionally, a cyclone separator performance prediction model is constructed based on machine learning methods, specifically including:

[0013] Separation performance data are obtained using experimental measurements or computational fluid dynamics methods, and a dataset is created; the separation performance data includes the inlet velocity of different gases and the separation efficiency of the cyclone separator corresponding to the inlet velocity of different gases;

[0014] The dataset is divided into a training dataset and a validation dataset;

[0015] A loss function is constructed using the governing equations and boundary conditions to establish a machine learning model based on a physical information neural network; the governing equations include the Navier-Stokes equations and the continuity equation.

[0016] The machine learning model is trained and validated using the training dataset and the validation dataset to obtain a cyclone separator performance prediction model.

[0017] Optionally, the physical information neural network includes an input layer, a hidden layer, and an output layer; the nonlinear function of the physical information neural network is the Sigmoid function.

[0018] Optionally, the loss function consists of the loss of the control equation and the loss of the target variable; the loss of the control equation is obtained by mass conservation and momentum equation; the loss of the target variable is the mean square error between the dataset and the output data of the physical information neural network.

[0019] The present invention also provides a cyclone separator control system that adapts to changes in flow rate, comprising:

[0020] Cyclone separator performance prediction model building module, used to build cyclone separator performance prediction models based on machine learning methods;

[0021] The separation efficiency prediction module for the cyclone separator is used to input the gas flow rate at the inlet of the cyclone separator into the cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator;

[0022] The flow control signal determination module is used to determine the flow control signal based on the difference between the predicted separation efficiency of the cyclone separator and the optimal separation efficiency of the cyclone separator.

[0023] The control module is used to control the motor frequency of the fan controller based on the flow control signal, thereby controlling the jet flow rate entering the cyclone separator, so that the cyclone separator is in the flow mode with optimal separation efficiency.

[0024] Optionally, the cyclone separator performance prediction model building module specifically includes:

[0025] The dataset creation unit is used to obtain separation performance data using experimental measurements or computational fluid dynamics methods and create a dataset; the separation performance data includes the inlet velocity of different gases and the separation efficiency of the cyclone separator corresponding to the inlet velocity of different gases;

[0026] A partitioning unit is used to divide the dataset into a training dataset and a validation dataset;

[0027] The machine learning model building unit is used to construct a loss function based on the control equations and boundary conditions to establish a machine learning model based on a physical information neural network; the control equations include the Navier-Stokes equations and the continuity equation.

[0028] The training and validation unit is used to train and validate the machine learning model using the training dataset and the validation dataset to obtain a cyclone separator performance prediction model.

[0029] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the above-described cyclone separator control method adapted to flow changes.

[0030] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the cyclone separator control method adapted to flow rate changes as described above.

[0031] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] This invention utilizes a constructed cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator in real time. The difference between the optimal separation efficiency and the predicted separation efficiency is used as a control signal to adjust the motor frequency, ensuring the separator always operates in the optimal flow mode for separation efficiency. This avoids the problem of low cyclone separator separation efficiency caused by changes in flow parameters during the process. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0034] Figure 1 A flowchart of a cyclone separator control method adapting to flow rate changes provided in Embodiment 1 of the present invention;

[0035] Figure 2 Flowchart for establishing a performance prediction model for cyclone separators;

[0036] Figure 3 A schematic diagram of the cyclone separator performance prediction model;

[0037] Figure 4 This is a distribution diagram of the inlet velocity of a specific cyclone separator over time.

[0038] Figure 5 This is a distribution diagram of the separation efficiency over time after simulation of a specific cyclone separator provided in Embodiment 2 of the present invention.

[0039] Figure 6 This is a graph showing the distribution of separation efficiency over time after adjustment using the cyclone separator control method adapted to flow rate changes provided by the present invention in Example 2.

[0040] Figure 7 This is a distribution diagram of the separation efficiency over time after experimental measurement of a specific cyclone separator provided in Embodiment 3 of the present invention.

[0041] Figure 8 This is a graph showing the distribution of separation efficiency over time after adjustment using the cyclone separator control method adapted to flow rate changes provided by the invention in Example 3. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] The purpose of this invention is to provide a cyclone separator control method, system, and device that adapts to changes in flow rate, so that the separator is always in the flow mode with optimal separation efficiency by adjusting the frequency of the motor.

[0044] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0045] Example 1

[0046] like Figure 1 As shown, the cyclone separator control method adapting to flow rate changes provided in this embodiment includes the following steps:

[0047] S1: Construct a cyclone separator performance prediction model based on machine learning methods.

[0048] S2: Input the gas flow rate at the inlet of the cyclone separator into the cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator.

[0049] S3: Determine the flow control signal based on the difference between the predicted separation efficiency of the cyclone separator and the optimal separation efficiency of the cyclone separator.

[0050] Separation efficiency curves are obtained using experimental measurements or computational fluid dynamics methods, and the optimal value is determined to be the best separation efficiency for the cyclone separator.

[0051] S4: Based on the flow control signal, the fan controller controls the motor frequency, thereby controlling the jet flow rate entering the cyclone separator, so that the cyclone separator is in the flow mode with optimal separation efficiency.

[0052] The gas-solid two-phase flow enters the cyclone separator through a pipeline. A gas flow detection device is installed on the pipeline. The gas flow detection device transmits the detected gas flow to the cyclone separator performance prediction model. The cyclone separator performance prediction model makes a judgment and outputs a signal to the frequency converter to control the output power of the fan and the gas flow to the cyclone separator, so that the gas-solid flow in the separator is in the mode of optimal separation efficiency.

[0053] Furthermore, such as Figure 2 As shown, step S1 specifically includes:

[0054] S11: Create a dataset by obtaining separation performance data using experimental measurements or computational fluid dynamics methods; the separation performance data includes the inlet velocity of different gases and the separation efficiency of the cyclone separator corresponding to the inlet velocity of different gases.

[0055] Experimental measurement:

[0056] By measuring the particle concentration and particle size distribution at the separator inlet and outlet under different gas inlet velocities, the overall separation efficiency η at the inlet can be obtained. 总 and particle classification efficiency η i :

[0057] η总 =1-c 出口 / c 入口 (1)

[0058] η i =1-n i出口 / n i入口 (2)

[0059] In the formula, c is the particle concentration, n is the number of particles, and i represents the i-th particle size.

[0060] Computational fluid dynamics methods:

[0061] First, the gas phase flow in the separator under different inlet gas velocities is calculated using the Reynolds Stress Model (RSM). Then, the separation efficiency η of particles with different sizes is calculated using the Discrete Particle Model (DPM). i (Calculations are performed using Formula 2), thus obtaining the overall separation efficiency:

[0062] η 总 =∑η i f i (3)

[0063] Formula f i The distribution density of particles of the i-th particle size is obtained by measuring a particle size analyzer.

[0064] S12: Use the datasets in an 8:2 ratio as the training dataset and validation dataset for the machine learning model, respectively.

[0065] S13: Construct a loss function using the control equations and boundary conditions to establish a machine learning model based on a Physically Informed Neural Network (PINN); the control equations include the Navier-Stokes equations and the continuity equation.

[0066] S14: Train a machine learning model using the training dataset.

[0067] S15: Compare the validation dataset with the prediction data of the machine learning model under the same conditions. When the machine learning calculation results make the flow field satisfy the continuity equation, the cyclone separator performance prediction model is obtained. Otherwise, continue iterative calculation, using the validation dataset to correct the model, until the cyclone separator performance prediction model is obtained.

[0068] Figure 3The process of establishing the above-mentioned cyclone separator performance prediction model is illustrated. The PINN network consists of three fully connected, nonlinear network layers: a data input layer, a hidden layer, and an output layer. The spatiotemporal coordinates (t, x, y, z) of the separator flow field are input into the input layer of the neural network, and the nonlinear function in the hidden layer is the Sigmoid function. The overall loss function is composed of the loss L from the governing equation. E The loss of the target variable Lu + Lv + Lw + Lp constitutes (L = Lu + Lv + Lw + Lp + L) E ), where Lu, Lv, and Lw represent the time-averaged velocity losses u, v, and w in the x, y, and z directions, respectively, and Lp represents the pressure loss. The losses in the governing equations are induced by the mass conservation equation E4 and the momentum equations E1, E2, and E3 in the x, y, and z directions.

[0069]

[0070]

[0071]

[0072]

[0073] In the formula, u, v, w are the time-averaged velocities in the x, y, and z directions, and ν is the viscosity of the fluid.

[0074] The loss of the target variable is the mean squared error between the training dataset and the neural network output data.

[0075]

[0076] In the formula, u(t) n ,x n ,y n ,z n ), v(t) n ,x n ,y n ,z n ), w(t) n ,x n ,y n ,z n ) and p(t n ,x n ,y n ,z n To verify the dataset at the nth spatiotemporal coordinate t n ,x n ,y n ,z n The values ​​of u, v, w, and p at point u. n ,v n ,w n,p n Let be the nth value of u, v, w, p in the neural network output, and N be the total number of data points in the dataset. Automatic differentiation of the overall loss function is implemented using PyTorch. When the error of the loss function is less than a small ε, a flow field prediction model is obtained, and further, a separation performance prediction model is derived.

[0077] Example 2

[0078] This example uses numerical simulation data. The main characteristic dimensions of the cyclone separator are: cylinder diameter 60mm, cylinder height 90mm, cone outlet diameter 20mm, cone height 180mm, exhaust port diameter 30mm, and inlet width and height 15mm and 30mm respectively. The particle size ranges from 0.1 to 140μm, with a median particle size of 65μm. The inlet gas velocity of the cyclone separator is between 16 and 17.5m / s. Figure 4 As shown. Simulation results indicate that the separator's separation efficiency is between 84% and 92%, as... Figure 5 As shown.

[0079] The gas velocity signal at the separator inlet is input into the cyclone separator performance prediction model established in step S1. The output of the cyclone separator performance prediction model indicates that the gas flow rate input to the separator cone section is between 0 and 2.43 m³ / s. 3 / h. After flow input control, the separation efficiency of the cyclone separator is between 91.5% and 92%. Figure 6 As shown.

[0080] Example 3

[0081] This example uses laboratory measured data. The main characteristic dimensions of the cyclone separator are: cylinder diameter 60mm, cylinder height 90mm, cone outlet diameter 20mm, cone height 180mm, exhaust port diameter 30mm, and inlet width and height 15mm and 30mm respectively. The particle size ranges from 0.1 to 140μm, with a median particle size of 65μm. The inlet gas velocity of the separator is controlled between 16 and 17.5m / s by a regulating valve. Figure 4 As shown. Experimental measurements indicate that the separator's separation efficiency is between 80% and 91%, as... Figure 7 As shown.

[0082] The gas velocity signal at the separator inlet is input into the cyclone separator performance prediction model established in step 1. The output of the cyclone separator performance prediction model indicates that the gas flow rate input to the separator cone section is between 0 and 2.43 m³ / s. 3 / h. After flow input control, the separation efficiency of the cyclone separator is between 91.5% and 92%. Figure 8 As shown.

[0083] Example 4

[0084] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a cyclone separator control system that adapts to flow rate changes is provided below.

[0085] The system includes:

[0086] The Cyclone Separator Performance Prediction Model Building Module is used to build cyclone separator performance prediction models based on machine learning methods.

[0087] The separation efficiency prediction module for cyclone separators is used to input the gas flow rate at the inlet of the cyclone separator into the cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator.

[0088] The flow control signal determination module is used to determine the flow control signal based on the difference between the predicted separation efficiency of the cyclone separator and the optimal separation efficiency of the cyclone separator.

[0089] The control module is used to control the motor frequency of the fan controller based on the flow control signal, thereby controlling the jet flow rate entering the cyclone separator, so that the cyclone separator is in the flow mode with optimal separation efficiency.

[0090] Furthermore, the cyclone separator performance prediction model construction module specifically includes:

[0091] The dataset creation unit is used to obtain separation performance data using experimental measurements or computational fluid dynamics methods and create datasets; the separation performance data includes the inlet velocity of different gases and the separation efficiency of the cyclone separator corresponding to the inlet velocity of different gases.

[0092] The partitioning unit is used to divide the dataset into training and validation datasets.

[0093] The machine learning model building unit is used to construct a loss function based on the control equations and boundary conditions to establish a machine learning model based on a physical information neural network; the control equations include the Navier-Stokes equations and the continuity equations.

[0094] The training and validation unit is used to train and validate the machine learning model using the training dataset and the validation dataset to obtain the cyclone separator performance prediction model.

[0095] Example 5

[0096] This embodiment provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the cyclone separator control method adapted to flow changes provided in Embodiment 1.

[0097] In practical applications, the aforementioned electronic devices can be servers.

[0098] In practical applications, electronic devices include: at least one processor, memory, bus, and communication interface.

[0099] The processor, communication interface, and memory communicate with each other via a communication bus.

[0100] A communication interface is used to communicate with other devices.

[0101] The processor is used to execute programs, specifically the methods described in the above embodiments.

[0102] Specifically, the program may include program code, which includes computer operation instructions.

[0103] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0104] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0105] Example 6

[0106] Based on the description of Embodiment 5, Embodiment 4 of the present invention provides a storage medium on which a computer program is stored. The computer program can be executed by a processor to implement the cyclone separator control method adapting to flow rate changes of Embodiment 1.

[0107] The cyclone separator control system adapted to flow rate changes provided in Embodiment 4 of this invention exists in various forms, including but not limited to:

[0108] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and primarily aim to provide voice and data communication. These terminals include: smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones, etc.

[0109] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access capabilities. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0110] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes: audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

[0111] (4) Other electronic devices with data interaction functions.

[0112] Specific embodiments of the subject matter have now been described. Other embodiments are within the scope of the appended claims. In some cases, the actions described in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0113] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0114] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this invention, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0119] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0120] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined in this invention, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0122] This invention can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules.

[0123] Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific transactions or implement specific abstract data types. This invention can also be practiced in distributed computing environments where transactions are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0124] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0125] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A cyclone separator control method adapting to flow rate changes, characterized in that, include: A performance prediction model for cyclone separators was constructed based on machine learning methods. Specifically, this includes: obtaining separation performance data using experimental measurements or computational fluid dynamics methods, and creating a dataset; the separation performance data includes the inlet velocities of different gases and the separation efficiency of the cyclone separator corresponding to the inlet velocities of different gases; dividing the dataset into a training dataset and a validation dataset; constructing a loss function using the governing equations and boundary conditions, and establishing a machine learning model based on a physical information neural network; the governing equations include the Navier-Stokes equations and the continuity equation; training and validating the machine learning model using the training dataset and the validation dataset to obtain a cyclone separator performance prediction model; the loss function consists of the loss of the governing equations and the loss of the target variable; the loss of the governing equations is induced by mass conservation and momentum equations; the loss of the target variable is the mean square error between the dataset and the output data of the physical information neural network; The gas flow rate at the inlet of the cyclone separator is input into the cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator; The flow control signal is determined based on the difference between the predicted separation efficiency of the cyclone separator and the optimal separation efficiency of the cyclone separator. Based on the flow control signal, the fan controller controls the motor frequency, thereby controlling the jet flow rate entering the cyclone separator, so that the cyclone separator is in the flow mode with optimal separation efficiency.

2. The cyclone separator control method adapting to flow rate changes according to claim 1, characterized in that, The physical information neural network includes an input layer, a hidden layer, and an output layer; the nonlinear function of the physical information neural network is the Sigmoid function.

3. A cyclone separator control system adaptable to changes in flow rate, characterized in that, include: A cyclone separator performance prediction model construction module is used to construct a cyclone separator performance prediction model based on machine learning methods. Specifically, it includes: a dataset creation unit, used to obtain separation performance data using experimental measurements or computational fluid dynamics methods and create a dataset; the separation performance data includes the inlet velocities of different gases and the corresponding separation efficiencies of the cyclone separators; a partitioning unit, used to partition the dataset into a training dataset and a validation dataset; a machine learning model construction unit, used to construct a loss function based on the control equations and boundary conditions to establish a machine learning model based on a physical information neural network; the control equations include the Navier-Stokes equations and the continuity equation; and a training and validation unit, used to train and validate the machine learning model using the training dataset and the validation dataset to obtain the cyclone separator performance prediction model; the loss function consists of the loss of the control equations and the loss of the target variable; the loss of the control equations is induced by mass conservation and momentum equations; and the loss of the target variable is the mean square error between the dataset and the output data of the physical information neural network. The separation efficiency prediction module for the cyclone separator is used to input the gas flow rate at the inlet of the cyclone separator into the cyclone separator performance prediction model to predict the separation efficiency of the cyclone separator; The flow control signal determination module is used to determine the flow control signal based on the difference between the predicted separation efficiency of the cyclone separator and the optimal separation efficiency of the cyclone separator. The control module is used to control the motor frequency of the fan controller based on the flow control signal, thereby controlling the jet flow rate entering the cyclone separator, so that the cyclone separator is in the flow mode with optimal separation efficiency.

4. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the cyclone separator control method adapted to flow changes as described in any one of claims 1-2.

5. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the cyclone separator control method adapting to flow rate changes as described in any one of claims 1-2.

Images