Intercooling tower temperature prediction system and method based on physical information neural network

Abstract

The invention discloses an indirect cooling tower temperature prediction system and method based on a physical information neural network. The method comprises the following steps: acquiring environmental parameters of an indirect cooling tower; the environment parameters of the indirect cooling tower are input into the trained physical information neural network, the temperature of the indirect cooling tower is obtained through prediction, the system and method can accurately predict the temperature of the indirect cooling tower, and meanwhile efficiency is high.

Description

Technical Field

[0001] The invention belongs to the field of computer science and thermal power generation technology, and relates to a method and system for predicting the temperature of an intercooler tower based on a physical information neural network. Background Art

[0002] Intercoolers are commonly used cooling equipment in industrial production, used to dissipate heat and keep equipment temperature within a safe range. However, due to environmental changes, equipment failures, and improper operation, intercoolers may face problems such as abnormal temperature and pressure, resulting in unstable operation and reduced efficiency. Traditional monitoring methods often rely on manual inspections and offline data analysis, which are inefficient and prone to missing problems. There is an urgent need for a technology that can preset the temperature of cooling towers, but no similar disclosure is given in the prior art. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a system and method for predicting the temperature of an intercooler based on a physical information neural network. The system and method can accurately predict the temperature of the intercooler with high efficiency.

[0004] In order to achieve the above object, the present invention adopts the following technical scheme:

[0005] In one aspect of the present invention, the method for predicting the temperature of an intercooling tower based on a physical information neural network of the present invention comprises:

[0006] Obtain the environmental parameters of the intercooler;

[0007] The environmental parameters of the intercooling tower are input into the trained physical information neural network to predict the temperature of the intercooling tower.

[0008] The further improvement of the indirect cooling tower temperature prediction method based on physical information neural network described in the present invention is:

[0009] Furthermore, the environmental parameters of the intercooling tower include PM10, humidity information, temperature information, wind speed information, wind direction information and atmospheric pressure information of the environment around the intercooling tower.

[0010] Furthermore, before inputting the environmental parameters of the intercooling tower into the trained physical information neural network, the method further includes:

[0011] Obtain historical environmental parameters of the intercooler and historical temperature data of the intercooler;

[0012] Constructing a data set according to the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower;

[0013] Dividing the data set into a training set and a test set;

[0014] Construct physical information neural network;

[0015] The physical information neural network is trained and tested based on the training set and the test set to obtain a trained physical information neural network.

[0016] Furthermore, the loss function of the physical information neural network during training is:

[0017] Loss_MSE=(1 / N)*Σ(T_true^i-T_pred^i)^2

[0018] Where T_pred^i represents the predicted intercooler temperature, represents the time derivative of the predicted temperature, T is the intercooler temperature, t is the time, α is the thermal diffusion coefficient, The Laplacian of temperature.

[0019] Furthermore, it also includes:

[0020] Sending the predicted temperature of the intercooler to the DCS system;

[0021] When it is predicted that the temperature of the intercooler is abnormal, an alarm is issued.

[0022] In a second aspect of the present invention, the temperature prediction system of an intercooling tower based on a physical information neural network of the present invention comprises:

[0023] The first acquisition module is used to obtain the environmental parameters of the intercooler;

[0024] The prediction module is used to input the environmental parameters of the intercooling tower into the trained physical information neural network to predict the temperature of the intercooling tower.

[0025] The further improvement of the intercooling tower temperature prediction system based on physical information neural network described in the present invention is:

[0026] It is characterized in that the environmental parameters of the intercooling tower include PM10, humidity information, temperature information, wind speed information, wind direction information and atmospheric pressure information of the environment around the intercooling tower.

[0027] Furthermore, it also includes:

[0028] The second acquisition module is used to obtain the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower;

[0029] A first construction module is used to construct a data set according to the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower;

[0030] A partitioning module, used for partitioning the data set into a training set and a test set;

[0031] The second building block is used to construct a physical information neural network;

[0032] A training module is used to train and test the physical information neural network based on the training set and the test set to obtain a trained physical information neural network.

[0033] Furthermore, the loss function of the physical information neural network during training is:

[0034] Loss_MSE=(1 / N)*Σ(T_true^i-T_pred^i)^2

[0035] Where T_pred^i represents the predicted intercooler temperature, represents the time derivative of the predicted temperature, T is the intercooler temperature, t is the time, α is the thermal diffusion coefficient, The Laplacian of temperature.

[0036] Furthermore, it also includes:

[0037] A sending module, used for sending the predicted temperature of the intercooling tower to a DCS system;

[0038] The early warning module is used to issue an alarm when it is predicted that the temperature of the intercooler is abnormal.

[0039] The present invention has the following beneficial effects:

[0040] In the specific operation of the intercooling tower temperature prediction system and method based on physical information neural network described in the present invention, the environmental parameters of the intercooling tower are input into the trained physical information neural network to predict the temperature of the intercooling tower. The temperature of the intercooling tower is predicted using the physical information neural network, and the prediction has high accuracy. At the same time, online prediction can be achieved, and the practicability is strong. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 It is the principle diagram of the method of the present invention;

[0043] Figure 2 This is a distribution diagram of data collection in the present invention. DETAILED DESCRIPTION

[0044] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0045] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.

[0046] Embodiment 1

[0047] refer to Figure 1 The method for predicting the temperature of an intercooler tower based on a physical information neural network of the present invention comprises the following steps:

[0048] 1) Build a dataset;

[0049] refer to Figure 2 By placing environmental temperature monitoring devices in the southwest and northeast directions of the intercooling tower, the environmental information around the intercooling tower is monitored in real time, including PM10, temperature, humidity, wind speed, wind direction and atmospheric pressure. The intercooling tower unit adopts two units and one tower, with a total of 210 cooling triangles, of which 208 cooling triangles are 33m high, and 2 cooling triangles on the upper side of the tower door are 21.8m high. The 210 cooling triangles are divided into 14 sectors, each sector is arranged with 15 cooling triangles, and the 7 cooling sectors of Unit 1 and the 7 cooling sectors of Unit 2 are arranged at intervals from each other.

[0050] In the present invention, monitoring devices are placed in the southwest and northeast directions of the intercooler tower to collect particulate matter and meteorological data in real time. These data are collected once an hour and uploaded to the DCS system in real time, and the historical operation data of the power plant is obtained through the DCS system;

[0051] 2) Construct physical information neural network;

[0052] The physical neural network is trained by combining the collected data with physical constraints to predict the temperature change characteristics of the cooling tower over a period of time. The neural network selects a fully connected neural network as the basis of the prediction model and adds the physical equation to the training loss function. The specific physical equation is the Clausius-Clapeyron equation. The Clausius-Clapeyron equation is a basic equation in thermodynamics, which relates the vapor pressure of a substance to its temperature and vaporization enthalpy to describe the phase change behavior between a liquid and its vapor.

[0053] The Clausius-Clapeyron equation can be expressed as:

[0054]

[0055] Where T is the temperature of the intercooler, t is the time, α is the thermal diffusion coefficient, The Laplacian of temperature.

[0056] In order to add the physical equation as a constraint to the loss function, the comprehensive loss function is set as:

[0057] Loss_MSE=(1 / N)*Σ(T_true^i-T_pred^i)^2

[0058] Where N represents the number of samples, T_true^i represents the true intercooler tower temperature of the i-th sample, and T_pred^i represents the predicted intercooler tower temperature.

[0059] Set physical equation constraints to measure whether the predicted value satisfies the Clausius-Clapeyron equation:

[0060]

[0061] in, Represents the time derivative of the predicted temperature. Through optimization algorithms such as gradient descent, the comprehensive loss function is minimized and the network parameters are updated so that the predicted value gradually approaches the true value and satisfies the constraints of the Clausius-Clapeyron equation.

[0062] During the training process, 80% of the training data and 20% of the test data are set, and the trained physical information neural network is added to the engineer station terminal computer for use. By embedding this equation into the loss function, it can be ensured that the prediction model satisfies the physical laws during the learning process. Such physical constraints can improve the reliability of the prediction model and ensure that the model prediction results are reasonable in practical applications; adding it to the loss function can also provide prior knowledge guidance for the physical information neural network. In this way, the physical information neural network can better utilize these physical laws during the learning process and more accurately predict the temperature of the intercooler tower.

[0063] 3) obtaining environmental parameters of the intercooling tower; inputting the environmental parameters of the intercooling tower into the trained physical information neural network to predict the temperature of the intercooling tower;

[0064] 4) The predicted temperature of the intercooler is sent to the DCS system, and when the predicted temperature of the intercooler is abnormal, an alarm is issued.

[0065] Embodiment 2

[0066] The indirect cooling tower temperature prediction system based on physical information neural network of the present invention comprises:

[0067] The first acquisition module is used to obtain the environmental parameters of the intercooler;

[0068] The prediction module is used to input the environmental parameters of the intercooling tower into the trained physical information neural network to predict the temperature of the intercooling tower.

[0069] In this embodiment, the environmental parameters of the intercooling tower include PM10, humidity information, temperature information, wind speed information, wind direction information and atmospheric pressure information of the environment around the intercooling tower.

[0070] In this embodiment, it also includes:

[0071] The second acquisition module is used to obtain the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower;

[0072] A first construction module is used to construct a data set according to the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower;

[0073] A partitioning module, used for partitioning the data set into a training set and a test set;

[0074] The second building block is used to construct a physical information neural network;

[0075] A training module is used to train and test the physical information neural network based on the training set and the test set to obtain a trained physical information neural network.

[0076] In this embodiment, the loss function of the physical information neural network during training is:

[0077] Loss_MSE=(1 / N)*Σ(T_true^i-T_pred^i)^2

[0078] Where T_pred^i represents the predicted intercooler temperature, represents the time derivative of the predicted temperature, T is the intercooler temperature, t is the time, α is the thermal diffusion coefficient, The Laplacian of temperature.

[0079] In this embodiment, it also includes:

[0080] A sending module, used for sending the predicted temperature of the intercooling tower to a DCS system;

[0081] The early warning module is used to issue an alarm when it is predicted that the temperature of the intercooler is abnormal.

[0082] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0083] Embodiment 3

[0084] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the intercooler temperature prediction method based on physical information neural network are implemented. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, the network interface, and the memory are interconnected through an internal bus. The internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard structure bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0085] Embodiment 4

[0086] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intercooling tower temperature prediction method based on physical information neural network are implemented. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0087] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0088] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting the temperature of an intercooler tower based on a physical information neural network, characterized in that: include: Obtain the environmental parameters of the intercooler; The environmental parameters of the intercooling tower are input into the trained physical information neural network to predict the temperature of the intercooling tower.

2. The method for predicting the temperature of an intercooling tower based on a physical information neural network according to claim 1, characterized in that: The environmental parameters of the intercooling tower include PM10, humidity information, temperature information, wind speed information, wind direction information and atmospheric pressure information of the environment around the intercooling tower.

3. The method for predicting the temperature of an intercooling tower based on a physical information neural network according to claim 1, characterized in that: Before inputting the environmental parameters of the intercooling tower into the trained physical information neural network, the method further includes: Obtain historical environmental parameters of the intercooler and historical temperature data of the intercooler; Constructing a data set according to the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower; Dividing the data set into a training set and a test set; Construct physical information neural network; The physical information neural network is trained and tested based on the training set and the test set to obtain a trained physical information neural network.

4. The method for predicting the temperature of an intercooling tower based on a physical information neural network according to claim 1, characterized in that: The loss function of the physical information neural network during training is: Loss_MSE=(1 / N)*Σ(T_true^i-T_pred^i)^2 Where T_pred^i represents the predicted intercooler temperature, represents the time derivative of the predicted temperature, T is the intercooler temperature, t is the time, α is the thermal diffusion coefficient, The Laplacian of temperature.

5. The method for predicting the temperature of an intercooling tower based on a physical information neural network according to claim 1, characterized in that: Also includes: Sending the predicted temperature of the intercooler to the DCS system; When it is predicted that the temperature of the intercooler is abnormal, an alarm is issued.

6. A temperature prediction system for intercooling tower based on physical information neural network, characterized in that: include: The first acquisition module is used to obtain the environmental parameters of the intercooler; The prediction module is used to input the environmental parameters of the intercooling tower into the trained physical information neural network to predict the temperature of the intercooling tower.

7. The temperature prediction system for intercooling tower based on physical information neural network according to claim 6 is characterized in that: The environmental parameters of the intercooling tower include PM10, humidity information, temperature information, wind speed information, wind direction information and atmospheric pressure information of the environment around the intercooling tower.

8. The method for predicting the temperature of an intercooling tower based on a physical information neural network according to claim 6, characterized in that: Also includes: The second acquisition module is used to acquire the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower; A first construction module is used to construct a data set according to the historical environmental parameters of the intercooling tower and the historical temperature data of the intercooling tower; A partitioning module, used for partitioning the data set into a training set and a test set; The second building block is used to construct a physical information neural network; A training module is used to train and test the physical information neural network based on the training set and the test set to obtain a trained physical information neural network.

9. The temperature prediction system for intercooling tower based on physical information neural network according to claim 8, characterized in that: The loss function of the physical information neural network during training is: Loss_MSE=(1 / N)*Σ(T_true^i-T_pred^i)^2 Where T_pred^i represents the predicted intercooler temperature, represents the time derivative of the predicted temperature, T is the intercooler temperature, t is the time, α is the thermal diffusion coefficient, The Laplacian of temperature.

10. The temperature prediction system for intercooling tower based on physical information neural network according to claim 8, characterized in that: Also includes: A sending module, used for sending the predicted temperature of the intercooling tower to a DCS system; The early warning module is used to issue an alarm when it is predicted that the temperature of the intercooler is abnormal.

Images