Membrane deoxidizing rate and temperature cooperative control method and system

Abstract

The invention discloses a cooperative control method and system for a membrane deoxidization rate and temperature, and belongs to the technical field of membrane deoxidization control. The method comprises the steps that the real-time liquid flow and the real-time oxygen content in the deoxidizing film, the liquid temperature of the front surface of the deoxidizing film and the liquid temperature of the rear surface of the deoxidizing film are obtained; according to the real-time liquid flow and the real-time oxygen content in the deoxygenization membrane, the real-time deoxygenization rate in the deoxygenization membrane is obtained based on a pre-constructed rate and flow relation model; calculating the temperature in the deoxidizing film according to the liquid temperature of the front surface of the deoxidizing film and the liquid temperature of the rear surface of the deoxidizing film; wherein the real-time liquid flow in the deoxidizing film, the liquid temperature of the front surface of the deoxidizing film and the liquid temperature of the rear surface of the deoxidizing film are controlled through a control algorithm; parameters of the control algorithm are parameters of a BP neural network based on particle swarm optimization learning. An automatic control algorithm is adopted for controlling the deoxidizing rate and the deoxidizing film temperature, and the detection precision of the deoxidizing rate and the deoxidizing film temperature can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of membrane oxygen removal control, in particular to a membrane oxygen removal rate and temperature cooperative control method and system. BACKGROUND

[0002] With the development of various industries, the technical indicators of liquid aeration and degassing are becoming more and more demanding. The membrane system can reduce the dissolved oxygen in the liquid to below 1 ppb, and through extension and modification, it can easily meet the requirements of various technical indicators.

[0003] The existing control method suitable for the membrane oxygen removal system generally has low reliability, and the internal temperature of the oxygen removal membrane cannot be detected, which is not conducive to the efficient and long-term operation of the oxygen removal membrane. In order to improve the accuracy of oxygen removal membrane temperature detection, although the application of multi-layer and multi-point detection methods has appeared, the multi-point temperature detection data has not been effectively fused, and the detection accuracy has not been substantially improved. In the existing membrane oxygen removal control device or system, the oxygen removal rate and the oxygen removal membrane temperature control mostly adopt logic control or conventional PID control, and the control parameters involved need to be manually set. SUMMARY

[0004] The purpose of the present application is to overcome the shortcomings of the prior art and provide a membrane oxygen removal rate and temperature cooperative control method and system. The oxygen removal rate and oxygen removal membrane temperature control adopt an automatic control algorithm, which can improve the detection accuracy and reliability of the oxygen removal rate and degassing membrane temperature.

[0005] To achieve the above purpose, the present application adopts the following technical solutions:

[0006] On the one hand, the present application provides a membrane oxygen removal rate and temperature cooperative control method, comprising:

[0007] obtaining the real-time liquid flow, real-time oxygen content, liquid temperature of the front surface of the oxygen removal membrane, and liquid temperature of the back surface of the oxygen removal membrane in the oxygen removal membrane;

[0008] According to the real-time liquid flow and real-time oxygen content in the oxygen removal membrane, the real-time oxygen removal rate in the oxygen removal membrane is obtained based on a pre-constructed rate flow relationship model;

[0009] According to the liquid temperature of the front surface of the oxygen removal membrane and the liquid temperature of the back surface of the oxygen removal membrane, the temperature in the oxygen removal membrane is calculated;

[0010] The real-time liquid flow in the oxygen removal membrane, the liquid temperature of the front surface of the oxygen removal membrane, and the liquid temperature of the back surface of the oxygen removal membrane are controlled by a control algorithm. The parameters of the control algorithm are the parameters of the BP neural network based on particle swarm optimization learning.

[0011] Optionally, the training of the rate flow relationship model comprises:

[0012] updating the parameters of the rate-flow relationship model by using recursive least square method to obtain a trained rate-flow relationship model.

[0013] Optionally, the parameter updating of the rate-flow relationship model comprises:

[0014] ;

[0015] ;

[0016] ;

[0017] wherein, respectively represent the parameters of the rate-flow relationship model at the t+1 time and the t time; represents an intermediate variable or a parameter prediction value in the iterative calculation; represents an intermediate variable or a parameter prediction value in the iterative calculation; represents a gain matrix at the t time; represents an oxygen removal rate at the t time; represents an input data vector at the t time; represents a matrix transpose; respectively represent the covariance matrices at the t+1 time and the t time; represents a forgetting factor.

[0018] Optionally, the rate-flow relationship model is represented as:

[0019] ;

[0020] wherein, represents an oxygen removal rate in the oxygen removal membrane at the t time; represents a liquid flow in the oxygen removal membrane at the t time; represents the parameters of the rate-flow relationship model; represents a functional relationship between the oxygen removal rate and the liquid flow in the oxygen removal membrane at the t time.

[0021] Optionally, the temperature in the oxygen removal membrane is calculated according to the liquid temperature at the front surface of the oxygen removal membrane and the liquid temperature at the back surface of the oxygen removal membrane, comprising:

[0022] ;

[0023] ;

[0024] wherein, respectively represent the convective heat transfer coefficients between the liquid at the front surface of the oxygen removal membrane and the oxygen removal membrane and between the liquid at the back surface of the oxygen removal membrane and the oxygen removal membrane; represents These represent the temperature inside the deoxygenation membrane, the liquid temperature on the surface before the deoxygenation membrane, and the liquid temperature on the surface after the deoxygenation membrane, respectively.

[0025] Optionally, the parameter update of the BP neural network based on particle swarm optimization learning includes:

[0026] The initial position, initial velocity, initial individual optimal position, and initial global optimal position of each particle are randomly generated within a preset range.

[0027] Calculate the fitness function for each particle and update the position and velocity of each particle in each iteration;

[0028] Repeat the process until the preset number of iterations is reached or the fitness function reaches the preset threshold to obtain the updated global optimal position of the particle.

[0029] The parameters corresponding to the updated global optimal position of the particle are used as the parameters of the BP neural network.

[0030] Optionally, the position and velocity of each particle are updated in each iteration, including:

[0031] Each particle represents a set of parameters for a backpropagation (BP) neural network. ),in:

[0032] ;

[0033] ;

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] in, This represents the velocity of the particle updated in the (m+1)th iteration; This represents the velocity of the particle updated in the t-th iteration; This represents the individual optimal position of the particle after the m-th iteration update; This represents the initial global optimal position of the particle; Indicates inertia weight; Indicates the learning factor; Represents a random number; This represents the position of the particle updated in the (m+1)th iteration; This represents the position of the particle updated in the m-th iteration.

[0039] In a second aspect, the present application provides a membrane oxygen removal rate and temperature cooperative control system, comprising:

[0040] a data acquisition module configured to acquire real-time liquid flow, real-time oxygen content, liquid temperature of a front surface of the oxygen removal membrane, and liquid temperature of a back surface of the oxygen removal membrane;

[0041] a rate calculation module configured to acquire real-time oxygen removal rate of the oxygen removal membrane based on a pre-constructed rate-flow relationship model according to the real-time liquid flow and the real-time oxygen content of the oxygen removal membrane;

[0042] a temperature calculation module configured to calculate temperature of the oxygen removal membrane according to the liquid temperature of the front surface of the oxygen removal membrane and the liquid temperature of the back surface of the oxygen removal membrane;

[0043] a data control module configured to control the real-time liquid flow, the liquid temperature of the front surface of the oxygen removal membrane, and the liquid temperature of the back surface of the oxygen removal membrane through a control algorithm, wherein parameters of the control algorithm are parameters of a BP neural network based on particle swarm optimization learning.

[0044] In a third aspect, the present application provides a computer readable storage medium having computer instructions stored thereon, wherein the computer instructions are executed by a processor to implement steps of the membrane oxygen removal rate and temperature cooperative control method of the first aspect.

[0045] In a fourth aspect, the present application provides a computer device, comprising:

[0046] a memory configured to store computer instructions;

[0047] a processor configured to execute the computer instructions to implement steps of the membrane oxygen removal rate and temperature cooperative control method of the first aspect.

[0048] Compared with the prior art, the present application has the following beneficial effects:

[0049] The present application adopts a multi-layer temperature detection method, fuses multi-layer temperature detection data, effectively improves the oxygen removal membrane temperature detection precision, improves the control method of the oxygen removal rate and the oxygen removal loop temperature, and adopts an automatic control algorithm for the oxygen removal rate and the oxygen removal membrane temperature control, thereby improving the detection precision and reliability of the oxygen removal rate and the deaeration membrane temperature, and the control parameters involved do not need to be manually set, which is beneficial to efficient and long-time operation of the oxygen removal membrane. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 Fig. 1 shows a flowchart of the membrane oxygen removal rate and temperature cooperative control method in an embodiment of the present application;

[0051] Figure 2The structure of the membrane oxygen removal rate and temperature synergistic control device in an embodiment is shown. DETAILED DESCRIPTION

[0052] The technical solutions of the present application will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0053] The term "and / or", only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " generally represents that the associated objects before and after are in an "or" relationship.

[0054] Embodiment 1

[0055] As Figure 1 shown, the present embodiment introduces a membrane oxygen removal rate and temperature synergistic control method, which includes the following steps:

[0056] Step 1: Obtain the real-time liquid flow rate in the oxygen removal membrane, the real-time oxygen content, the liquid temperature on the front surface of the oxygen removal membrane, and the liquid temperature on the back surface of the oxygen removal membrane.

[0057] The real-time liquid flow rate in the oxygen removal membrane is detected by a flow sensor, the real-time oxygen content in the oxygen removal membrane is detected by a dissolved oxygen sensor, and the liquid temperature on the front surface of the oxygen removal membrane and the liquid temperature on the back surface of the oxygen removal membrane are detected by a temperature sensor.

[0058] Step 2: According to the real-time liquid flow rate and the real-time oxygen content in the oxygen removal membrane, the real-time oxygen removal rate in the oxygen removal membrane is obtained based on a pre-constructed rate-flow relationship model, which is specifically:

[0059] The oxygen removal rate is the removal amount of oxygen per unit time, and its calculation must depend on the change of oxygen content.

[0060] By collecting the data set of the historical oxygen removal rate and the liquid flow rate in the field oxygen removal membrane, the functional relationship model between the oxygen removal rate and the liquid flow rate in the oxygen removal membrane, i.e. the rate-flow relationship model, is determined, which is expressed as:

[0061] ;

[0062] Wherein, represents the oxygen removal rate in the oxygen removal membrane at the t-th moment; represents the liquid flow rate in the oxygen removal membrane at the t-th moment; Parameters representing the rate-flow relationship model, which can contain multiple parameters for describing the flow-rate relationship in different intervals; represents the functional relationship between the oxygen removal rate in the oxygen removal membrane and the liquid flow at the t th moment.

[0063] The recursive least squares method is used to update the parameters of the rate-flow relationship model, and the recursive update formula is:

[0064] ;

[0065] wherein, respectively represent the parameters of the rate-flow relationship model at the t+1 th moment and the t th moment; represents an intermediate variable or parameter prediction value in iterative calculation; represents the oxygen removal rate at the t th moment; represents the input data vector at the t th moment, which generally contains the liquid flow in the oxygen removal membrane and its nonlinear transformation, such as polynomial terms between the liquid flow in the oxygen removal membrane; represents the matrix transpose; is the prediction value of the oxygen removal rate of the rate-flow relationship model under the current liquid flow in the oxygen removal membrane; represents the gain matrix at the t th moment, and the update speed is related to the liquid flow in the oxygen removal membrane, which is represented as:

[0066] ;

[0067] wherein, represents the forgetting factor, when , the algorithm has complete memory, and all historical data are equally valued, when , the algorithm gradually "forgets" the old data, and gives higher weight to the new data; respectively represent the covariance matrices at the t+1 th moment and the t th moment, which are used to control the amplitude of parameter update, and the covariance matrix at the t+1 th moment is represented as:

[0068] .

[0069] In actual control application, the liquid flow in the oxygen removal membrane is taken as the input of the rate-flow relationship model, the oxygen removal rate in the oxygen removal membrane is obtained based on the rate-flow relationship model, and the liquid flow in the oxygen removal membrane is controlled to keep the oxygen removal rate in the oxygen removal membrane at a set value.

[0070] Step three: according to the liquid temperature on the front surface of the oxygen removal membrane and the liquid temperature on the back surface of the oxygen removal membrane, the temperature in the oxygen removal membrane is calculated, which is specifically:

[0071] According to the heat conduction law, the temperature distribution in the oxygen removal membrane satisfies the one-dimensional steady-state heat conduction equation:

[0072] ;

[0073] The temperature distribution is linear:

[0074] ;

[0075] Tfront is the liquid temperature at the front surface of the oxygen removal membrane , the convective heat transfer coefficient between the liquid at the front surface of the oxygen removal membrane and the oxygen removal membrane ; Tback is the liquid temperature at the back surface of the oxygen removal membrane , the convective heat transfer coefficient between the liquid at the back surface of the oxygen removal membrane and the oxygen removal membrane .

[0076] At steady state, the heat flow on both sides of the oxygen removal membrane should be equal. According to the Fourier heat conduction law, the heat flow can be expressed as:

[0077] ;

[0078] where, is the direct objective of solving the equation, representing the change of temperature inside the object with spatial position; is the integral constant, determined by the boundary conditions; is the thermal conductivity, a measure of the material's ability to conduct heat.

[0079] The convective heat transfer on both sides of the oxygen removal membrane can also be expressed as:

[0080] ;

[0081] ;

[0082] At steady state, the heat flow should be equal:

[0083] ;

[0084] Solve the temperature in the oxygen removal membrane :

[0085] .

[0086] Step four: control the real-time liquid flow in the oxygen removal membrane, the liquid temperature at the front surface of the oxygen removal membrane, and the liquid temperature at the back surface of the oxygen removal membrane through the control algorithm, specifically:

[0087] The real-time liquid flow in the oxygen removal membrane, the liquid temperature in front of the oxygen removal membrane surface and the liquid temperature behind the oxygen removal membrane surface are controlled by a control algorithm; parameters of the control algorithm are parameters of a BP neural network based on particle swarm optimization learning, and updating of the parameters of the BP neural network based on particle swarm optimization learning includes:

[0088] An initial position, an initial speed, an initial individual optimal position and an initial global optimal position of each particle are randomly generated within a preset range;

[0089] A fitness function of each particle is calculated, and the position and speed of each particle are updated at each iteration;

[0090] The process is repeated until a preset iteration number is reached or a preset threshold of the fitness function is reached, and an updated global optimal position of the particle is obtained;

[0091] The parameters corresponding to the updated global optimal position of the particle are used as parameters of the BP neural network.

[0092] In a specific embodiment, as Figure 2 The membrane oxygen removal rate and temperature cooperative control device is shown in the figure. The valve opening degree of the electric valve is adjusted to change the liquid flow in the oxygen removal membrane system, thereby realizing oxygen removal rate control. Since there is a certain functional relationship between the oxygen removal rate and the liquid flow in the oxygen removal membrane, the control of the oxygen removal rate can be converted into the control of the liquid flow in the oxygen removal membrane. According to the mechanism of the membrane oxygen removal process, the oxygen removal rate control is divided into three stages, and the time length of each stage is set. When the electric valve is in an open state, the command signal of the electric valve is calculated by using a PID control algorithm, and the PID control parameters are automatically adjusted online based on a BP neural network based on particle swarm optimization learning, so as to change the liquid flow into the membrane oxygen removal system and adjust the membrane flow rate to reach the target value. During the oxygen removal process, the running speed of the EC cooling fan is controlled by the PID control algorithm, so that the temperature in the oxygen removal membrane system is maintained at a specified temperature. The control valve and the EC fan are controlled by the PID control algorithm, and the PID control algorithms of the two are independent of each other. Taking the PID control algorithm of the control valve as an example:

[0093] Each particle is a set of BP neural network parameters );

[0094] An initial position and an initial speed of each particle are randomly generated within a preset range:

[0095] ];

[0096] ];

[0097] ];

[0098] ;

[0099] generate initial individual optimal position, initial global optimal position;

[0100] The fitness function is used to evaluate the performance of each particle, usually based on the response of the control system, such as minimizing error, overshoot, and steady-state error, etc. The fitness of a particle is expressed as:

[0101] ;

[0102] wherein, and represent the target deoxygenation rate and the current deoxygenation rate, respectively; represents a quantification function, which can use indicators such as integral absolute error, integral square error, etc.

[0103] Update the position and velocity of each particle:

[0104] ;

[0105] ;

[0106] ;

[0107] ;

[0108] ;

[0109] ;

[0110] wherein, represents the lower limit of the position of the particle; represents the upper limit of the position of the particle; represents the velocity of the particle updated in the m+1th iteration; represents the velocity of the particle updated in the tth iteration; represents the individual optimal position of the particle updated in the mth iteration; represents the initial global optimal position of the particle; represents the inertia weight, used to balance exploration and exploitation; represents the learning factor, usually taking a value between [0, 2]; represents a random number, usually taking a value between [0, 1]; represents the position of the particle updated in the m+1th iteration; represents the position of the particle updated in the mth iteration.

[0111] The repeated execution is performed until a preset iteration number is reached or a fitness function reaches a preset threshold, to obtain an updated global optimal position of the particle;

[0112] The parameter corresponding to the global optimal position of the particle is taken as a parameter of the BP neural network.

[0113] The output of the PID control algorithm is used to adjust the opening degree of the electric valve.

[0114] The operation data of the membrane deoxidization system are detected by sensors, that is, the flow, dissolved oxygen and temperature of the membrane deoxidization system, and according to the values of the flow sensor, the dissolved oxygen sensor and the temperature sensor, a control signal is determined and sent to the electric valve and the EC fan; in this embodiment, the control signal is generated by the PLC.

[0115] The PLC establishes communication with the cloud server by means of a data transmission unit, that is, a 5G mobile network, realizes remote data storage of the membrane deoxidization process on the cloud server, and can also realize remote state monitoring of the on-site equipment through a smart phone, and external personnel can establish communication with the PLC through a touch screen.

[0116] According to the actual test data on site, the effective functional relationship between the deoxidization rate and the liquid flow in the membrane is identified, the multi-layer temperature detection data are fused by using an information fusion algorithm on the basis of the multi-layer temperature detection mode, the deoxidization membrane temperature detection precision is effectively improved, the deoxidization rate and the deoxidization membrane temperature control adopt an intelligent PID algorithm, and the control parameters are automatically adjusted online, without manual setting, the membrane deoxidization control system is constructed by means of the 5G mobile network and the cloud platform to realize the Internet of Things mode, the remote data storage and state monitoring of the membrane deoxidization process are realized.

[0117] Embodiment 2

[0118] The embodiment introduces a membrane deoxidization rate and temperature cooperative control system, which comprises:

[0119] The data acquisition module is configured to acquire the real-time liquid flow, the real-time oxygen content, the liquid temperature of the front surface of the deoxidization membrane and the liquid temperature of the rear surface of the deoxidization membrane.

[0120] The rate calculation module is configured to acquire the real-time deoxidization rate in the deoxidization membrane based on a pre-constructed rate-flow relationship model according to the real-time liquid flow and the real-time oxygen content in the deoxidization membrane.

[0121] The temperature calculation module is configured to calculate the temperature in the deoxidization membrane according to the liquid temperature of the front surface of the deoxidization membrane and the liquid temperature of the rear surface of the deoxidization membrane.

[0122] The data control module is configured to control the real-time liquid flow in the oxygen removal membrane, the liquid temperature on the front surface of the oxygen removal membrane, and the liquid temperature on the rear surface of the oxygen removal membrane through a control algorithm, and parameters of the control algorithm are parameters of a BP neural network based on particle swarm optimization learning.

[0123] The specific functions of the modules are described in the method of Embodiment 1, and are not repeated here.

[0124] Embodiment 3

[0125] This embodiment introduces a computer readable storage medium, which stores computer instructions, and the computer instructions are executed by a processor to implement the steps of the membrane oxygen removal rate and temperature cooperative control method described in Embodiment 1.

[0126] Embodiment 4

[0127] This embodiment introduces a computer device, which includes:

[0128] a memory configured to store computer instructions;

[0129] a processor configured to execute the computer instructions to implement the steps of the membrane oxygen removal rate and temperature cooperative control method described in Embodiment 1.

[0130] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in 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.

[0131] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 an apparatus for performing the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams. Figure 1 an apparatus for performing the functions specified in one or more flows and / or blocks in the flowcharts and / or block diagrams.

[0132] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The function specified in the flow or flows and / or blocks.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks Figure 1 The function specified in the flow or flows and / or blocks.

[0134] The embodiments of the present application described above are merely intended to illustrate the present application, but are not intended to limit the present application. The above-described embodiments are merely illustrative, and are not intended to limit the present application. Those skilled in the art can make many modifications without departing from the spirit and scope of the present application, and these modifications are also intended to be within the scope of the present application.

Claims

1. A method for synergistic control of membrane deoxygenation rate and temperature, characterized in that, include: The real-time liquid flow rate, real-time oxygen content, liquid temperature on the front surface of the deoxygenation membrane, and liquid temperature on the back surface of the deoxygenation membrane are obtained. Based on the real-time liquid flow rate and real-time oxygen content within the deoxygenation membrane, and using a pre-built rate-flow relationship model, the real-time deoxygenation rate within the deoxygenation membrane is obtained. The temperature inside the deoxygenation membrane is calculated based on the liquid temperature on the front surface of the deoxygenation membrane and the liquid temperature on the rear surface of the deoxygenation membrane. The real-time liquid flow rate within the deoxygenation membrane, the liquid temperature on the front surface of the deoxygenation membrane, and the liquid temperature on the rear surface of the deoxygenation membrane are controlled by a control algorithm; the parameters of the control algorithm are the parameters of a BP neural network based on particle swarm optimization learning.

2. The method for coordinated control of membrane deoxygenation rate and temperature according to claim 1, characterized in that, The training of the rate-flow relationship model includes: The parameters of the rate-flow relationship model are updated using the recursive least squares method to obtain the trained rate-flow relationship model.

3. The method for coordinated control of membrane deoxygenation rate and temperature according to claim 2, characterized in that, The parameter updates for the rate-flow relationship model include: ； ； ； in, These represent the parameters of the rate-flow relationship model at time t+1 and time t, respectively. express Predicted values ​​of intermediate variables or parameters in iterative calculations; Let represent the gain matrix at time t; This represents the deoxygenation rate at time t; This represents the input data vector at time t; Indicates matrix transpose; Let represent the covariance matrices at time t+1 and time t, respectively; This represents the forgetting factor.

4. The method for coordinated control of membrane deoxygenation rate and temperature according to claim 1, characterized in that, The rate-flow relationship model is expressed as follows: ； in, This represents the oxygen removal rate within the deoxygenation membrane at time t. This represents the liquid flow rate within the deoxygenation membrane at time t; The parameters represent the rate-flow relationship model. This represents the functional relationship between the deoxygenation rate and the liquid flow rate within the deoxygenation membrane at time t.

5. The method for coordinated control of membrane deoxygenation rate and temperature according to claim 1, characterized in that, The temperature inside the deoxygenation membrane is calculated based on the liquid temperature at the surface before and after the deoxygenation membrane, including: ； ； in, These represent the convective heat transfer coefficients between the liquid on the front surface of the deoxygenation membrane and the deoxygenation membrane, and the convective heat transfer coefficients between the liquid on the back surface of the deoxygenation membrane and the deoxygenation membrane, respectively. express; These represent the temperature inside the deoxygenation membrane, the liquid temperature on the surface before the deoxygenation membrane, and the liquid temperature on the surface after the deoxygenation membrane, respectively.

6. The method for coordinated control of membrane deoxygenation rate and temperature according to claim 1, characterized in that, The parameter update of the BP neural network based on particle swarm optimization learning includes: The initial position, initial velocity, initial individual optimal position, and initial global optimal position of each particle are randomly generated within a preset range. Calculate the fitness function for each particle and update the position and velocity of each particle in each iteration; Repeat the process until the preset number of iterations is reached or the fitness function reaches the preset threshold to obtain the updated global optimal position of the particle. The parameters corresponding to the updated global optimal position of the particle are used as the parameters of the BP neural network.

7. The method for coordinated control of membrane deoxygenation rate and temperature according to claim 6, characterized in that, The position and velocity of each particle are updated at each iteration, including: Each particle represents a set of parameters for a backpropagation (BP) neural network. ),in: ； ； ； ； ； ； in, This represents the velocity of the particle updated in the (m+1)th iteration; This represents the velocity of the particle updated in the t-th iteration; This represents the individual optimal position of the particle after the m-th iteration update; This represents the initial global optimal position of the particle; Indicates inertia weight; Indicates the learning factor; Represents a random number; This represents the position of the particle updated in the (m+1)th iteration; This represents the position of the particle updated in the m-th iteration.

8. A membrane deoxygenation rate and temperature coordinated control system, characterized in that, include: The data acquisition module is used to acquire the real-time liquid flow rate, real-time oxygen content, liquid temperature on the front surface of the deoxygenation membrane, and liquid temperature on the back surface of the deoxygenation membrane. The rate calculation module is used to: obtain the real-time deoxygenation rate in the deoxygenation membrane based on the real-time liquid flow rate and real-time oxygen content in the deoxygenation membrane, and on a pre-built rate-flow relationship model. The temperature calculation module is used to calculate the temperature inside the deoxygenation membrane based on the liquid temperature on the front surface of the deoxygenation membrane and the liquid temperature on the rear surface of the deoxygenation membrane. The data control module is used to: wherein the real-time liquid flow rate within the deoxygenation membrane, the liquid temperature on the front surface of the deoxygenation membrane, and the liquid temperature on the rear surface of the deoxygenation membrane are controlled by a control algorithm; the parameters of the control algorithm are the parameters of a BP neural network based on particle swarm optimization learning.

9. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the computer instruction is executed by the processor, it implements the steps of the membrane deoxygenation rate and temperature coordinated control method according to any one of claims 1-7.

10. A computer device, characterized in that, include: Memory, used to store computer instructions; A processor for executing the computer instructions to implement the steps of the membrane deoxygenation rate and temperature coordinated control method according to any one of claims 1-7.

Images