An air-cooled condenser automatic dosing control method and related device

Abstract

The application belongs to the technical field of air-cooled condensers, and discloses an automatic dosing control method for an air-cooled condenser and related devices, which comprises the following steps: obtaining real-time flow of condensate water, real-time frequency of a dosing pump and real-time concentration of hydrogen peroxide at the outlet of a condensate pump, and inputting the three parameters into a neural network prediction model to output a required dosing amount prediction value; according to the required dosing amount prediction value and a predetermined target concentration of hydrogen peroxide, the deviation and the deviation change rate of the required dosing amount prediction value and the target concentration are calculated; the deviation and the deviation change rate of the required dosing amount prediction value and the target concentration are input into a fuzzy neural network model to output a dosing pump frequency change value; according to the dosing pump frequency change value and the real-time frequency of the dosing pump, a dosing pump frequency control value is obtained, and then a frequency control instruction is generated and sent to a frequency converter; the application can improve the dosing precision control, improve the adaptive ability and robustness of the dosing system, and ensure the stable operation of the air-cooled condenser.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of air-cooled condensers, and particularly relates to an air-cooled condenser automatic dosing control method and related device. BACKGROUND

[0002] An air-cooled condenser (Air Condenser, also known as an air-cooled island) is a condenser that cools and condenses a heat medium through natural or forced convection heat exchange. It is an important carbon steel equipment in a direct air-cooled unit. Because the relative volatility of ammonia is too large (about 22.4) under the condition of 50℃ negative pressure of the air-cooled condenser, the pH of the condensate is only 7-8. In a low-pH environment, the carbon steel body of the air-cooled condenser is prone to severe flow-accelerated corrosion in high-speed vapor-liquid two-phase flow. Therefore, hydrogen peroxide is usually added to the air-cooled condenser as an oxidizing agent to inhibit corrosion, reduce the iron content of the condensate, reduce the pollution of iron to the mixed bed resin of the polishing treatment, and prolong the operation cycle of the polishing treatment mixed bed.

[0003] At present, the traditional air-cooled condenser automatic dosing system mainly includes an online hydrogen peroxide meter, a controller, a frequency converter, and a dosing pump. The dosing point of hydrogen peroxide is arranged on the main steam discharge pipeline of the air-cooled condenser, and the sampling point of the online hydrogen peroxide meter is arranged at the outlet of the condensate pump. The dosing process usually adopts PID control, feedforward control, or compound ring feedback control. For example, during the dosing process, the amount of dosing is determined according to the content of hydrogen peroxide after sampling at the outlet of the condensate pump. Then, the frequency of the dosing pump is controlled through the control of the frequency converter, so as to control the amount of dosing. However, the existing dosing control method generally has the characteristics of time lag and nonlinearity, which leads to low dosing control precision and poor adaptability, and manual repeated adjustment is required, which seriously affects the normal operation of the air-cooled condenser. SUMMARY

[0004] In view of the technical problems in the prior art, the application provides an air-cooled condenser automatic dosing control method and related device to solve the technical problem that the existing dosing control method generally has the characteristics of time lag and nonlinearity, which leads to low dosing control precision, poor adaptability, and the need for manual repeated adjustment, which seriously affects the normal operation of the air-cooled condenser.

[0005] To achieve the above-mentioned purposes, the technical solution adopted by the application is as follows:

[0006] The application provides an air-cooled condenser automatic dosing control method, which comprises the following steps:

[0007] obtaining real-time flow of condensate, real-time frequency of a dosing pump, and real-time concentration of hydrogen peroxide at the outlet of a condensate pump;

[0008] The condensate flow rate, real-time frequency of the dosing pump, and real-time hydrogen peroxide concentration at the condensate pump outlet are input into the neural network prediction model, and the predicted value of the required dosing amount is output.

[0009] Based on the predicted dosage and the predetermined target concentration of hydrogen peroxide, the deviation between the predicted dosage and the target concentration, as well as the rate of change of the deviation, are calculated.

[0010] The deviation between the predicted dosage and the target concentration, as well as the rate of change of the deviation, are input into the fuzzy neural network model, and the change value of the dosing pump frequency is output.

[0011] Based on the frequency change value of the dosing pump and the real-time frequency of the dosing pump, the frequency control value of the dosing pump is obtained; based on the frequency control value of the dosing pump, a frequency control command is generated and sent to the frequency converter.

[0012] Furthermore, the fuzzy neural network model includes an antecedent network and an consequent network;

[0013] The foreground network is used to receive the deviation and rate of change of the predicted dosage and target concentration, and to perform fuzzification processing according to a preset membership function to obtain a fuzzy signal.

[0014] The consequent network is used to perform fuzzy inference calculations on the fuzzy signal to obtain fuzzy output results; and to perform defuzzification processing on the fuzzy output results to output the frequency change value of the dosing pump.

[0015] Furthermore, the preset membership function is a Gaussian function.

[0016] Furthermore, the training process of the fuzzy neural network model employs forward propagation and backward error propagation to learn and train the preset parameters of the fuzzy neural network model.

[0017] Furthermore, the preset parameters of the fuzzy neural network model include the center value of the membership function, the width value of the membership function, and the connection weights in the consequent network.

[0018] Furthermore, the process of obtaining the dosing pump frequency control value based on the dosing pump frequency change value and the dosing pump real-time frequency is as follows:

[0019]

[0020] in, for The frequency control value of the dosing pump at any given time; for Real-time frequency of the dosing pump; for The change in the frequency of the dosing pump at any given time.

[0021] The present invention also provides an automatic chemical dosing control system for an air-cooled condenser, comprising:

[0022] The data acquisition module is used to obtain the real-time flow rate of condensate, the real-time frequency of the dosing pump, and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump.

[0023] The dosage prediction module is used to input the condensate flow rate, the real-time frequency of the dosing pump, and the real-time concentration of hydrogen peroxide at the condensate pump outlet into the neural network prediction model, and output the predicted value of the required dosage.

[0024] The deviation calculation module is used to calculate the deviation between the predicted dosage and the target concentration, as well as the rate of change of deviation, based on the predicted dosage and the predetermined target concentration of hydrogen peroxide.

[0025] The frequency change control module is used to input the deviation between the predicted value of the required dosage and the target concentration, as well as the rate of change of the deviation, into the fuzzy neural network model, and output the frequency change value of the dosing pump.

[0026] The instruction output module is used to obtain the dosing pump frequency control value based on the dosing pump frequency change value and the dosing pump real-time frequency; and to generate and send frequency control instructions to the frequency converter based on the dosing pump frequency control value.

[0027] The present invention also provides an automatic chemical dosing control device for an air-cooled condenser, comprising:

[0028] A processor is used to execute computer programs;

[0029] A computer-readable storage medium storing a computer program, which, when executed by the processor, performs the automatic chemical dosing control method for the air-cooled condenser.

[0030] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the automatic chemical dosing control method for the air-cooled condenser.

[0031] The present invention also provides a computer program product, characterized in that the computer program product includes a computer program, which, when executed by a processor, implements the automatic chemical dosing control method for the air-cooled condenser.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0033] This invention provides an automatic chemical dosing control method for air-cooled condensers. Based on condensate flow rate, real-time frequency of the dosing pump, and real-time hydrogen peroxide concentration at the condensate pump outlet, and utilizing the data fitting and prediction capabilities of a neural network prediction model, it achieves dynamic and accurate prediction of the required dosing amount, effectively improving the adaptability to the operating conditions of the air-cooled condenser. Secondly, based on the predicted dosing amount, a fuzzy neural network is used to obtain the dosing pump frequency control value, achieving precise control of the dosing pump and thus ensuring accurate control of the dosing amount. This invention, through the combination of a neural network prediction model and a fuzzy neural network, effectively improves the precision control of dosing while continuously learning from environmental changes, enhancing the adaptability and robustness of the dosing system, greatly reducing the need for manual operation, and ensuring the stable operation of the air-cooled condenser.

[0034] The automatic chemical dosing control system, automatic chemical dosing control equipment, computer-readable storage medium, and computer program product provided by this invention possess all the advantages of the aforementioned automatic chemical dosing control method for air-cooled condensers. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 A flowchart of the automatic chemical dosing control method for an air-cooled condenser provided in Example 1;

[0037] Figure 2 This is a structural block diagram of the automatic chemical dosing control system for the air-cooled condenser provided in Example 2;

[0038] Figure 3 The diagram shows the structure of the automatic chemical dosing control device for the air-cooled condenser provided in Example 3. Detailed Implementation

[0039] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0040] Example 1

[0041] As attached Figure 1 As shown, this embodiment 1 provides an automatic chemical dosing control method for an air-cooled condenser, including the following steps:

[0042] Step 1: Obtain real-time operating data of the automatic chemical dosing system for the air-cooled condenser. This real-time operating data includes the real-time condensate flow rate, the real-time frequency of the dosing pump, and the real-time hydrogen peroxide concentration at the condensate pump outlet.

[0043] Step 2: Perform data preprocessing on the real-time operating data of the automatic dosing system for the air-cooled condenser to obtain preprocessed real-time operating data. The data preprocessing process includes data cleaning and normalization, specifically missing value filling, outlier deletion, and standardization. It should be noted that this invention does not impose fixed limitations on the preprocessing procedure for real-time operating data, and will not be elaborated upon here.

[0044] Step 3: Input the preprocessed real-time operating data into the neural network prediction model, use the neural network prediction model to predict the required dosage, and output the predicted dosage value. The neural network prediction model is a trained BP neural network model, a trained LSTM neural network model, or a trained GRU neural network model.

[0045] The construction process of the neural network prediction model is as follows:

[0046] Step 31: Obtain historical operating data of the automatic chemical dosing system for the air-cooled condenser; construct an initial neural network model; wherein the initial neural network model adopts one of the following: BP neural network model, LSTM neural network model or GRU neural network model.

[0047] Step 32: Analyze and process the historical operating data of the automatic chemical dosing system for the air-cooled condenser to obtain historical operating index data and historical operating anomaly data; generate a chemical dosing anomaly analysis knowledge base based on the historical operating anomaly data.

[0048] Step 33: Train the initial neural network model based on historical prime number operation index data, historical operation anomaly data, and a knowledge base for drug dosing anomaly analysis to learn the mapping relationship between the historical operation index data and the historical operation anomaly data, thereby obtaining the trained initial neural network model, which is the neural network prediction model.

[0049] Step 4: Based on the predicted required dosage and the predetermined target hydrogen peroxide concentration, calculate the deviation between the predicted dosage and the target concentration, as well as the rate of change of the deviation. Preferably, the predetermined target hydrogen peroxide concentration is 0.1-2.0 mg / L.

[0050] Specifically, the calculation process for the deviation between the predicted required dosage and the target concentration is as follows:

[0051]

[0052] in, for The deviation between the predicted dosage and the target concentration at any given time; for The predicted dosage of the drug to be administered at the specified time; for The predetermined target concentration of hydrogen peroxide at a given time.

[0053] The calculation process for the rate of change of the deviation between the predicted required dosage and the target concentration is as follows:

[0054]

[0055] in, for The rate of change between the predicted dosage required at any given time and the target concentration; for The deviation between the predicted dosage and the target concentration at any given time; For time intervals.

[0056] Step 5: Input the deviation and rate of change of the predicted dosage and target concentration of the required dosage into the fuzzy neural network model to predict the dosing frequency change of the dosing pump and output the dosing pump frequency change value. The fuzzy neural network model includes an antecedent network and a consequent network. The antecedent network receives the deviation and rate of change of the predicted dosage and target concentration and performs fuzzification processing according to a preset membership function to obtain a fuzzy signal.

[0057] Specifically, the pre-processor network includes a pre-processor input layer, a membership layer, a fuzzy rule layer, and a pre-processor output layer; wherein, the membership layer is pre-configured with a preset membership function; preferably, the preset membership function is a Gaussian function; the post-processor network is used to perform fuzzy inference calculations on the fuzzy signal to obtain fuzzy output results, and to perform defuzzification processing on the fuzzy output results to output the dosing pump frequency change value; specifically, the post-processor network includes a post-processor input layer, a hidden layer, and a fuzzy neural output layer.

[0058] In this embodiment 1, the input of the fuzzy neural network model is the deviation between the predicted dosage and the target concentration, and the rate of change of the deviation; the output is the change in the dosing pump frequency. The training process of the fuzzy neural network model employs forward propagation and backward error propagation to learn and train the preset parameters of the fuzzy neural network model. The preset parameters of the fuzzy neural network model include the center value and width of the membership function in the antecedent network, and the connection weights in the consequent network. By adjusting the preset parameters of the fuzzy neural network model, the fuzzy rules are updated in real time, enabling the model to better adapt to the environment and thus achieve the desired control effect.

[0059] Specifically, the process of training and updating the center value and width value of the membership function is as follows:

[0060]

[0061]

[0062] in, for The central value of the membership function at time t; for The central value of the membership function at time t; The learning rate is set to 0.7. for The instantaneous squared difference at time t; for The width of the membership function at time t; for The width of the membership function at time t; Let be the expected value of the central value of the membership function.

[0063] Specifically, the process of training and updating the connection weights in the consequent network is as follows:

[0064]

[0065]

[0066] in, for The connection weights between the input layer and hidden layer of the consequent network at time 1; for The connection weights between the input layer and hidden layer of the consequent network at time 1; The target expected value for the connection weights between the input layer and hidden layer of the consequent network; This represents the number of nodes in the fuzzy rule layer. for The system error value at time; for The output value of the connection weights of the nodes in the time-fuzzy rule generation layer; The feature data dimension of the input layer of the consequent.

[0067] It should be noted that the initial values ​​of the membership function center and width in the antecedent network, as well as the initial values ​​of the connection weights in the consequent network, are all set through random initialization.

[0068] It should also be noted that, during the training process of the fuzzy neural network model, the objective function is defined as follows:

[0069]

[0070]

[0071] in, Mean square error; The number of samples; for The expected output value of hydrogen peroxide at time t; for The sampled output value of hydrogen peroxide at a given time.

[0072] Step 6: Calculate the dosing pump frequency control value based on the frequency change value and the real-time frequency of the dosing pump; generate and send a frequency control command to the frequency converter based on the dosing pump frequency control value. The frequency control command triggers the frequency converter to adjust the dosing frequency of the dosing pump, causing the dosing pump to operate at the dosing pump frequency control value.

[0073] Specifically, the process of calculating the frequency control value of the dosing pump is as follows:

[0074]

[0075] in, for The frequency control value of the dosing pump at any given time; for Real-time frequency of the dosing pump; for The change in the frequency of the dosing pump at any given time.

[0076] In this embodiment 1, based on the real-time condensate flow rate, real-time dosing pump frequency, and real-time hydrogen peroxide concentration at the condensate pump outlet, and utilizing the powerful data fitting and prediction capabilities of the neural network prediction model, the required dosing amount is accurately predicted. After obtaining the predicted dosing amount, the fuzzy neural network model considers the deviation and the rate of change of deviation, enabling the dosing control system to not only focus on the current state but also anticipate future trends, thereby making more stable and accurate control decisions. This helps reduce fluctuations during the dosing process and improves system stability. This invention can continuously adjust the dosing strategy based on real-time data, exhibiting good adaptability to changes in operating conditions and ensuring that the dosing effect remains at its optimal state. Furthermore, fuzzy neural networks have good control effects and robustness for nonlinear, time-delayed, and mathematically difficult-to-establish systems. Neural networks have good self-learning, adaptability, and fault tolerance. By integrating neural networks and fuzzy neural networks, the dosing system can better utilize empirical rules to achieve better control effects while continuously learning according to environmental changes. This allows for continuous optimization of the control strategy during long-term operation, improving the adaptability and robustness of the dosing system.

[0077] The automatic chemical dosing control method for air-cooled condensers described in Example 1 achieves precise, stable, and adaptive control of the dosing process by combining a neural network prediction model and a fuzzy neural network model. This not only improves control accuracy and stability but also reduces operating costs, enhances system reliability, and contributes to environmental protection and sustainable development.

[0078] Example 2

[0079] As attached Figure 2 As shown in the figure, this embodiment 2 provides an automatic chemical dosing control system for an air-cooled condenser, including a data acquisition module, a data processing module, a chemical dosing prediction module, a deviation calculation module, a frequency control module, and an instruction output module.

[0080] The system comprises the following modules: a data acquisition module for acquiring real-time operating data of the automatic chemical dosing system for air-cooled condensers; a data processing module for preprocessing the real-time operating data of the automatic chemical dosing system to obtain preprocessed real-time operating data; a dosing quantity prediction module for inputting the preprocessed real-time operating data into a neural network prediction model to predict the required dosing quantity and outputting the predicted dosing quantity; a deviation calculation module for calculating the deviation and rate of change between the predicted dosing quantity and the target concentration, based on the predicted dosing quantity and the predetermined target hydrogen peroxide concentration; a frequency control module for inputting the deviation and rate of change between the predicted dosing quantity and the target concentration into a fuzzy neural network model to predict the dosing frequency change of the dosing pump and outputting the dosing pump frequency change value; and an instruction output module for calculating the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump, and generating and issuing a frequency control instruction to the frequency converter based on the dosing pump frequency control value.

[0081] Example 3

[0082] As attached Figure 3 As shown, this embodiment 3 provides an automatic dosing control device for an air-cooled condenser, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the automatic dosing control method for the air-cooled condenser, or for the processor to execute the computer program to implement the functions of each module in the above-mentioned automatic dosing control system for the air-cooled condenser.

[0083] Specifically, when the processor executes the computer program, it implements the steps of the above-mentioned automatic chemical dosing control method for air-cooled condensers, for example:

[0084] The system acquires real-time operating data of the automatic chemical dosing system for the air-cooled condenser; preprocesses the real-time operating data to obtain preprocessed real-time operating data; inputs the preprocessed real-time operating data into a neural network prediction model to predict the required dosage and outputs the predicted dosage value; calculates the deviation and rate of change between the predicted dosage and the target concentration based on the predicted dosage and a predetermined hydrogen peroxide target concentration; inputs the deviation and rate of change between the predicted dosage and the target concentration into a fuzzy neural network model to predict the dosing frequency change of the dosing pump and outputs the dosing pump frequency change value; calculates the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump; and generates and sends a frequency control command to the frequency converter based on the dosing pump frequency control value.

[0085] Specifically, when the processor executes the computer program, it implements the functions of each module in the above-mentioned automatic chemical dosing control system for air-cooled condensers, for example:

[0086] The system comprises the following modules: a data acquisition module for acquiring real-time operating data of the automatic chemical dosing system for air-cooled condensers; a data processing module for preprocessing the real-time operating data of the automatic chemical dosing system to obtain preprocessed real-time operating data; a dosing quantity prediction module for inputting the preprocessed real-time operating data into a neural network prediction model to predict the required dosing quantity and outputting the predicted dosing quantity; a deviation calculation module for calculating the deviation and rate of change between the predicted dosing quantity and the target concentration, based on the predicted dosing quantity and the predetermined target hydrogen peroxide concentration; a frequency control module for inputting the deviation and rate of change between the predicted dosing quantity and the target concentration into a fuzzy neural network model to predict the dosing frequency change of the dosing pump and outputting the dosing pump frequency change value; and an instruction output module for calculating the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump, and generating and issuing a frequency control instruction to the frequency converter based on the dosing pump frequency control value.

[0087] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing preset functions, wherein the instruction segments describe the execution process of the computer program in the automatic chemical dosing control device for the air-cooled condenser.

[0088] For example, the computer program can be divided into a data acquisition module, a data processing module, a dosing prediction module, a deviation calculation module, a frequency control module, and an instruction output module. The specific functions of each module are as follows: The data acquisition module is used to acquire real-time operating data of the automatic dosing system for air-cooled condensers; the data processing module is used to preprocess the real-time operating data of the automatic dosing system for air-cooled condensers to obtain preprocessed real-time operating data; the dosing prediction module is used to input the preprocessed real-time operating data into a neural network prediction model, use the neural network prediction model to predict the required dosing amount, and output the predicted value of the required dosing amount. The deviation calculation module is used to calculate the deviation and the rate of change of the required dosage from the target concentration based on the predicted dosage and the predetermined target hydrogen peroxide concentration. The frequency control module is used to input the deviation and the rate of change of the required dosage from the target concentration into a fuzzy neural network model to predict the dosing frequency change of the dosing pump and output the dosing pump frequency change value. The instruction output module is used to calculate the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump; and generate and issue a frequency control instruction to the frequency converter based on the dosing pump frequency control value.

[0089] The automatic dosing control device for air-cooled condensers can be a desktop computer, laptop, handheld computer, or cloud server, etc. The automatic dosing control device for air-cooled condensers may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above are examples of automatic dosing control devices for air-cooled condensers and do not constitute a limitation on such devices. It may include more components than described above, or combine certain components, or use different components. For example, the automatic dosing control device for air-cooled condensers may also include input / output devices, network access devices, buses, etc.

[0090] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of the automatic dosing control equipment for the air-cooled condenser, connecting all parts of the equipment via various interfaces and lines.

[0091] The memory can be used to store the computer program and / or modules. The processor realizes various functions of the automatic dosing control device for the air-cooled condenser by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory.

[0092] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.); the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMediaCards (SMC), Secure Digital (SD) cards, FlashCards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0093] Example 4

[0094] This embodiment 4 also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the steps of the automatic chemical dosing control method for an air-cooled condenser, for example:

[0095] The system acquires real-time operating data of the automatic chemical dosing system for the air-cooled condenser; preprocesses the real-time operating data to obtain preprocessed real-time operating data; inputs the preprocessed real-time operating data into a neural network prediction model to predict the required dosage and outputs the predicted dosage value; calculates the deviation and rate of change between the predicted dosage and the target concentration based on the predicted dosage and a predetermined hydrogen peroxide target concentration; inputs the deviation and rate of change between the predicted dosage and the target concentration into a fuzzy neural network model to predict the dosing frequency change of the dosing pump and outputs the dosing pump frequency change value; calculates the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump; and generates and sends a frequency control command to the frequency converter based on the dosing pump frequency control value.

[0096] If the modules / units integrated in the automatic chemical dosing control system for the air-cooled condenser are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0097] Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned automatic chemical dosing control method for air-cooled condensers, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-mentioned automatic chemical dosing control method for air-cooled condensers. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or preset intermediate form, etc.

[0098] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0099] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0100] Example 5

[0101] This embodiment 5 provides a computer product, which includes a computer program stored in a computer-readable storage medium. The processor of the air-cooled condenser automatic dosing control device reads the computer program from the computer-readable storage medium and executes the computer program, so that the air-cooled condenser automatic dosing control device can execute the air-cooled condenser automatic dosing control method described in embodiment 1, which will not be repeated here.

[0102] It should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods.

[0103] The automatic chemical dosing control method for air-cooled condensers provided by this invention collects real-time condensate flow rate, real-time frequency of the dosing pump, and real-time hydrogen peroxide concentration at the condensate pump outlet during the automatic chemical dosing process of the air-cooled condenser, and dynamically adjusts the dosing pump frequency based on the collected real-time data, thereby realizing dosing control based on a real-time monitoring and feedback mechanism, which effectively improves the reliability and safety of the system.

[0104] The above embodiments are merely one of the implementation methods for achieving the technical solution of the present invention. The scope of protection claimed by the present invention is not limited to this embodiment, but also includes any variations, substitutions and other implementation methods that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention.

Claims

1. An automatic chemical dosing control method for an air-cooled condenser, characterized in that, include: Obtain the real-time flow rate of condensate, the real-time frequency of the dosing pump, and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump; The real-time flow rate of condensate, the real-time frequency of the dosing pump, and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump are input into the neural network prediction model, and the predicted value of the required dosing amount is output. Based on the predicted dosage and the predetermined target concentration of hydrogen peroxide, the deviation between the predicted dosage and the target concentration, as well as the rate of change of the deviation, are calculated. The deviation between the predicted dosage and the target concentration, as well as the rate of change of the deviation, are input into the fuzzy neural network model, and the change value of the dosing pump frequency is output. Based on the frequency change value of the dosing pump and the real-time frequency of the dosing pump, the frequency control value of the dosing pump is obtained; based on the frequency control value of the dosing pump, a frequency control command is generated and sent to the frequency converter. The fuzzy neural network model includes a pre-evolution network and a post-evolution network; The foreground network is used to receive the deviation and rate of change of the predicted dosage and target concentration, and to perform fuzzification processing according to a preset membership function to obtain a fuzzy signal. The consequent network is used to perform fuzzy inference calculations on the fuzzy signal to obtain fuzzy output results; and to perform defuzzification processing on the fuzzy output results to output the frequency change value of the dosing pump. The preset membership function is a Gaussian function.

2. The automatic chemical dosing control method for an air-cooled condenser according to claim 1, characterized in that, The training process of the fuzzy neural network model uses forward propagation and backward error propagation to learn and train the preset parameters of the fuzzy neural network model.

3. The automatic chemical dosing control method for an air-cooled condenser according to claim 2, characterized in that, The preset parameters of the fuzzy neural network model include the center value of the membership function, the width value of the membership function, and the connection weights in the consequent network.

4. The automatic chemical dosing control method for an air-cooled condenser according to claim 1, characterized in that, The process of obtaining the dosing pump frequency control value based on the dosing pump frequency change value and the dosing pump real-time frequency is as follows: in, for The frequency control value of the dosing pump at any given time; for Real-time frequency of the dosing pump; for The change in the frequency of the dosing pump at any given time.

5. An automatic chemical dosing control system for an air-cooled condenser, characterized in that, include: The data acquisition module is used to obtain the real-time flow rate of condensate, the real-time frequency of the dosing pump, and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump. The dosage prediction module is used to input the real-time flow rate of the condensate, the real-time frequency of the dosing pump, and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump into the neural network prediction model, and output the predicted value of the required dosage. The deviation calculation module is used to calculate the deviation between the predicted dosage and the target concentration, as well as the rate of change of deviation, based on the predicted dosage and the predetermined target concentration of hydrogen peroxide. The frequency change control module is used to input the deviation between the predicted value of the required dosage and the target concentration, as well as the rate of change of the deviation, into the fuzzy neural network model, and output the frequency change value of the dosing pump. The instruction output module is used to obtain the dosing pump frequency control value based on the dosing pump frequency change value and the dosing pump real-time frequency; and to generate and send frequency control instructions to the frequency converter based on the dosing pump frequency control value. The fuzzy neural network model includes a pre-evolution network and a post-evolution network; The foreground network is used to receive the deviation and rate of change of the predicted dosage and target concentration, and to perform fuzzification processing according to a preset membership function to obtain a fuzzy signal. The consequent network is used to perform fuzzy inference calculations on the fuzzy signal to obtain fuzzy output results; and to perform defuzzification processing on the fuzzy output results to output the frequency change value of the dosing pump. The preset membership function is a Gaussian function.

6. An automatic chemical dosing control device for an air-cooled condenser, characterized in that, include: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, performs the automatic chemical dosing control method for an air-cooled condenser as described in any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the automatic chemical dosing control method for air-cooled condensers as described in any one of claims 1-4.

8. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the automatic chemical dosing control method for an air-cooled condenser as described in any one of claims 1-4.

Images