Automatic dosing control method for air-cooled condenser and related device

Abstract

The invention belongs to the technical field of air-cooled condensers, and discloses an air-cooled condenser automatic dosing control method and related device.The method comprises the steps that the real-time flow of condensed water, the real-time frequency of a dosing pump and the real-time concentration of hydrogen peroxide at an outlet of a condensed water pump are obtained and input into a neural network prediction model, and a predicted value of the needed dosing amount is obtained through output; calculating the deviation between the predicted value of the required dosage and the target concentration and the deviation change rate according to the predicted value of the required dosage and the predetermined target concentration of hydrogen peroxide; inputting the deviation between the predicted value of the required dosing amount and the target concentration and the deviation change rate into the fuzzy neural network model, and outputting to obtain the frequency change value of the dosing pump; according to the dosing pump frequency change value and the dosing pump real-time frequency, a dosing pump frequency control value is obtained, and then a frequency control instruction is generated and issued to a frequency converter; according to the invention, the self-adaptive capability and robustness of the dosing system are improved while the dosing precision control is improved, and the stable operation of the air-cooled condenser is ensured.

Description

Technical Field

[0001] The invention belongs to the technical field of air-cooled condensers, and in particular relates to an automatic dosing control method for an air-cooled condenser and a related device. Background Art

[0002] Air Condenser (also known as air cooling island) is a condenser that cools and condenses heat medium through natural convection or forced convection heat exchange. It is an important carbon steel equipment in direct air cooling units. Since ammonia has a large relative volatility (about 22.4) under negative pressure conditions of 50°C in air condensers, the pH of the condensate is only 7-8. In a low pH environment, the carbon steel body of the air condenser is very prone to severe flow accelerated corrosion in high-velocity vapor-liquid two-phase flow. Therefore, it is usually necessary to add hydrogen peroxide as an oxidant to the air condenser to inhibit corrosion, reduce the iron content of the condensate, and reduce iron contamination of the fine treatment mixed bed resin, so as to extend the operation cycle of the fine treatment mixed bed.

[0003] At present, the traditional automatic dosing system of air-cooled condenser mainly includes an online hydrogen peroxide meter, a controller, a frequency converter and a dosing pump; wherein the dosing point of hydrogen peroxide is set on the main exhaust pipe of the air-cooled condenser, and the sampling point of the online hydrogen peroxide meter is set at the outlet of the condensate pump; the dosing process usually adopts PID control, feedforward control or compound loop feedback control; for example: during the dosing process, after sampling at the outlet of the condensate pump, the dosing amount is determined according to the content of hydrogen peroxide; then the frequency of the dosing pump is controlled by controlling the frequency converter, thereby controlling the amount of dosing; however, the existing dosing control methods generally have the characteristics of time lag and nonlinearity, resulting in low dosing control accuracy and poor adaptability, and require manual repeated adjustment, which seriously affects the normal operation of the air-cooled condenser. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides an automatic dosing control method and related devices for an air-cooled condenser to solve the technical problems that the existing dosing control methods generally have the characteristics of time lag and nonlinearity, resulting in low dosing control accuracy and poor adaptability, and require repeated manual adjustments, which seriously affects the normal operation of the air-cooled condenser.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: The present invention provides an automatic dosing control method for an air-cooled condenser, comprising: 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 condensate flow rate, 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; According to the predicted value of the required dosage and the predetermined target concentration of hydrogen peroxide, the deviation between the predicted value of the required dosage and the target concentration and the rate of change of the deviation are calculated; The deviation between the predicted value of the required dosage and the target concentration and the deviation change rate are input into the fuzzy neural network model, and the frequency change value of the dosing pump is output; A dosing pump frequency control value is obtained according to the dosing pump frequency change value and the dosing pump real-time frequency; and a frequency control instruction is generated and sent to the frequency converter based on the dosing pump frequency control value.

[0006] Furthermore, the fuzzy neural network model includes a precondition network and a postcondition network; The antecedent network is used to receive the deviation between the predicted value of the required dosage and the target concentration and the deviation change rate, and perform fuzzification processing according to a preset membership function to obtain a fuzzy signal; The post-processing network is used to perform fuzzy reasoning calculation on the fuzzy signal to obtain a fuzzy output result; and to perform clarification processing on the fuzzy output result to output a frequency change value of the dosing pump.

[0007] Furthermore, the preset membership function is a Gaussian function.

[0008] Furthermore, the training process of the fuzzy neural network model adopts forward propagation and reverse error propagation to learn and train the preset parameters of the fuzzy neural network model.

[0009] Furthermore, the preset parameters of the fuzzy neural network model include the central value of the membership function, the width value of the membership function and the connection weights in the consequent network.

[0010] Furthermore, the process of obtaining the frequency control value of the dosing pump according to the frequency change value of the dosing pump and the real-time frequency of the dosing pump is as follows:

[0011] in, for The dosing pump frequency control value at the moment; for Real-time frequency of dosing pump at every moment; for The frequency change value of the dosing pump at the moment.

[0012] The present invention also provides an automatic dosing control system for an air-cooled condenser, comprising: Data acquisition module, 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; A 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 outlet of the condensate pump into a neural network prediction model, and output a predicted value of the required dosage; The deviation calculation module is used to calculate the deviation and the deviation change rate between the predicted value of the required dosage and the target concentration according to the predicted value of the required dosage and the predetermined target concentration of hydrogen peroxide; A frequency change control module is used to input the deviation between the predicted value of the required dosage and the target concentration and the deviation change rate into the fuzzy neural network model, and output the frequency change value of the dosing pump; The instruction output module is used to obtain a dosing pump frequency control value according to the dosing pump frequency change value and the dosing pump real-time frequency; based on the dosing pump frequency control value, generate and send a frequency control instruction to the frequency converter.

[0013] The present invention also provides an automatic dosing control device for an air-cooled condenser, comprising: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the automatic dosing control method for the air-cooled condenser is executed.

[0014] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the automatic dosing control method for an air-cooled condenser is implemented.

[0015] The present invention also provides a computer program product, characterized in that the computer program product includes a computer program, and when the computer program is executed by a processor, the automatic drug dosing control method for the air-cooled condenser is implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides an automatic dosing control method for an air-cooled condenser. Based on the condensate flow rate, the real-time frequency of a dosing pump and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump, and by utilizing the data fitting and prediction capabilities of a neural network prediction model, a dynamic and accurate prediction of a required dosing amount is achieved, thereby effectively improving the adaptability to the operating conditions of the air-cooled condenser. Secondly, based on the prediction result of the required dosing amount, a dosing pump frequency control value is obtained through a fuzzy neural network to achieve accurate control of the dosing pump, thereby ensuring accurate control of the dosing amount. The present invention combines a neural network prediction model with a fuzzy neural network to effectively improve the dosing precision control, while being able to continuously learn according to environmental changes, thereby improving 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.

[0017] The automatic dosing control system for an air-cooled condenser, the automatic dosing control device for an air-cooled condenser, the computer-readable storage medium and the computer program product provided by the present invention have all the advantages of the automatic dosing control method for an air-cooled condenser. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flow chart of the automatic dosing control method for an air-cooled condenser provided in Example 1; Figure 2 A structural block diagram of an automatic dosing control system for an air-cooled condenser provided in Example 2; Figure 3 This is a structural block diagram of the automatic dosing control device for an air-cooled condenser provided in Example 3. DETAILED DESCRIPTION

[0020] In order 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 described clearly and completely in combination with the drawings in the embodiments of this application; obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] Example 1 As attached Figure 1 As shown, this embodiment 1 provides an automatic dosing control method for an air-cooled condenser, comprising the following steps: Step 1: Acquire real-time operation data of the automatic dosing system of the air-cooled condenser, wherein the real-time operation data of the automatic dosing system of the air-cooled condenser includes 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.

[0022] Step 2: preprocess the real-time operation data of the automatic dosing system for the air-cooled condenser to obtain the preprocessed real-time operation data. The process of preprocessing the real-time operation data of the automatic dosing system for the air-cooled condenser includes data cleaning and normalization, including missing value filling, outlier deletion and standardization. It should be noted that the present invention does not impose fixed restrictions on the preprocessing process of the real-time operation data, which will not be elaborated here.

[0023] Step 3: input the pre-processed real-time operation data into the neural network prediction model, use the neural network prediction model to predict the required dosage, and output the predicted value of the required dosage. 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.

[0024] The construction process of the neural network prediction model is as follows: Step 31, obtaining historical operation data of the automatic dosing system of the air-cooled condenser; constructing an initial neural network model; wherein the initial neural network model adopts one of the BP neural network model, the LSTM neural network model or the GRU neural network model.

[0025] Step 32: Analyze and process the historical operation data of the automatic dosing system of the air-cooled condenser to obtain historical operation index data and historical operation abnormality data; and generate a dosing abnormality analysis knowledge base based on the historical operation abnormality data.

[0026] Step 33: train the initial neural network model based on the prime number historical operation index data, the historical operation abnormality data and the dosing abnormality analysis knowledge base to learn the mapping relationship between the historical operation index data and the historical operation abnormality data, and obtain the trained initial neural network model, that is, obtain the neural network prediction model.

[0027] Step 4: Calculate the deviation and the deviation change rate between the predicted value of the required dosage and the target concentration according to the predicted value of the required dosage and the predetermined target concentration of hydrogen peroxide. Preferably, the predetermined target concentration of hydrogen peroxide is 0.1-2.0 mg / L.

[0028] Specifically, the calculation process of the deviation between the predicted value of the required dosage and the target concentration is as follows:

[0029] in, for The deviation between the predicted value of the dosage required at the moment and the target concentration; for The predicted value of the required dosage at the time; for A predetermined target concentration of hydrogen peroxide at a given time.

[0030] The calculation process of the deviation change rate between the predicted value of the required dosage and the target concentration is as follows:

[0031] in, for The deviation change rate between the predicted value of the dosage required at the moment and the target concentration; for The deviation between the predicted value of the dosage required at the moment and the target concentration; For the time interval.

[0032] Step 5: Input the deviation and deviation change rate between the predicted value of the required dosage and the target concentration into the fuzzy neural network model, so as to predict the dosage frequency change of the dosage pump using the fuzzy neural network model, and output the dosage pump frequency change value. The fuzzy neural network model includes a precondition network and a postcondition network, and the precondition network is used to receive the deviation and deviation change rate between the predicted value of the required dosage and the target concentration, and perform fuzzification processing according to a preset membership function to obtain a fuzzy signal.

[0033] Specifically, the antecedent network includes an antecedent input layer, a membership layer, a fuzzy rule layer and antecedent output layer; wherein the membership layer is pre-configured with a preset membership function; preferably, the preset membership function is a Gaussian function; the consequent network is used to perform fuzzy reasoning calculation on the fuzzy signal to obtain a fuzzy output result, and to clarify the fuzzy output result to output a frequency change value of the dosing pump; specifically, the consequent network includes an consequent input layer, a hidden layer and a fuzzy neural output layer.

[0034] In this embodiment 1, the input of the fuzzy neural network model is the deviation between the predicted value of the required dosage and the target concentration and the deviation change rate, and the output is the change value of the dosing pump frequency; the training process of the fuzzy neural network model adopts forward propagation and reverse error propagation to learn and train the preset parameters of the fuzzy neural network model; wherein, the preset parameters of the fuzzy neural network model include the central value of the membership function and the width value 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 real-time update of the fuzzy rules is realized, so that the model can better adapt to the environment, thereby achieving the control effect.

[0035] Specifically, the process of training and updating the center value and the width value of the membership function is as follows:

[0036]

[0037] in, for The central value of the membership function at the moment; for The central value of the membership function at the moment; is the learning rate, take 0.7; for The instantaneous square difference of the moments; for The width value of the membership function at the moment; for The width value of the membership function at the moment; is the expected value of the central value of the membership function.

[0038] Specifically, the process of training and updating the connection weights in the subsequent network is as follows:

[0039]

[0040] in, for The connection weights between the input layer and the hidden layer of the consequent network at time t; for The connection weights between the input layer and the hidden layer of the consequent network at time t; is the target expected value of the connection weight between the input layer and the hidden layer of the subsequent network; is the number of nodes in the fuzzy rule layer; for System error value at time; for The output value of the connection weight of the nodes in the fuzzy rule generation layer at each moment; It is the feature data dimension of the subsequent input layer.

[0041] It should be noted that the center value of the membership function and the width value of the membership function in the antecedent network and the initial values ​​of the connection weights in the consequent network are all set by random initialization.

[0042] It should also be noted that in the training process of the fuzzy neural network model, the objective function is defined as follows:

[0043]

[0044] in, is the mean square error; is the number of samples; for The expected output value of hydrogen peroxide at the time; for The sampling output value of hydrogen peroxide at the moment.

[0045] Step 6: Calculate the dosing pump frequency control value based on the dosing pump frequency change value and the dosing pump real-time frequency; generate and send a frequency control instruction to the frequency converter based on the dosing pump frequency control value. The frequency control instruction is used to trigger the frequency converter to adjust the dosing frequency of the dosing pump so that the dosing pump operates at the dosing pump frequency control value.

[0046] Specifically, the process of calculating the dosing pump frequency control value is as follows:

[0047] in, for The dosing pump frequency control value at the moment; for Real-time frequency of dosing pump at every moment; for The frequency change value of the dosing pump at the moment.

[0048] In this embodiment 1, according to 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, and by utilizing the powerful data fitting and prediction capabilities of the neural network prediction model, the purpose of accurately predicting the required dosing amount is achieved; after obtaining the predicted value of the required dosing amount, the deviation and the deviation change rate are considered through the fuzzy neural network model, so that the dosing control system not only pays attention to the current state, but also can foresee future trends, thereby making more stable and accurate control decisions, which helps to reduce fluctuations in the dosing process and improve the stability of the system; the present invention can continuously adjust the dosing strategy according to real-time data, has good adaptability to changes in working conditions, and ensures that the dosing effect is always maintained in the best state; secondly, the fuzzy neural network has good control effect and robustness for systems such as nonlinearity, time lag, and difficult to establish mathematical models. The neural network has good self-learning, adaptability and fault tolerance. The neural network and the fuzzy neural network are integrated, so that the dosing system can better utilize empirical rules to achieve better control effects, and can also continuously learn according to changes in the environment, so that the control strategy is continuously optimized during long-term operation, and the adaptability and robustness of the dosing system are improved.

[0049] The automatic dosing control method for the air-cooled condenser described in Example 1 realizes accurate, stable and adaptive control of the dosing process by combining the neural network prediction model and the fuzzy neural network model, which not only improves the control accuracy and stability, but also reduces the operating cost, enhances the system reliability, and contributes to environmental protection and sustainable development.

[0050] Example 2 As attached Figure 2As shown, this embodiment 2 provides an automatic dosing control system for an air-cooled condenser, including a data acquisition module, a data processing module, a dosing amount prediction module, a deviation calculation module, a frequency control module and an instruction output module.

[0051] A data acquisition module is used to obtain real-time operating data of the automatic dosing system of the air-cooled condenser; a data processing module is used to perform data preprocessing on the real-time operating data of the automatic dosing system of the air-cooled condenser to obtain preprocessed real-time operating data; a dosing amount prediction module is used to input the preprocessed real-time operating data into the neural network prediction model, use the neural network prediction model to predict the required dosing amount, and output the required dosing amount prediction value; a deviation calculation module is used to calculate the deviation and deviation change rate between the required dosing amount prediction value and the target concentration based on the required dosing amount prediction value and the predetermined hydrogen peroxide target concentration; a frequency control module is used to input the deviation and deviation change rate between the required dosing amount prediction value and the target concentration into the fuzzy neural network model, so as to use the fuzzy neural network model to predict the dosing frequency change of the dosing pump, and output the dosing pump frequency change value; an 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; based on the dosing pump frequency control value, a frequency control instruction is generated and issued to the frequency converter.

[0052] Example 3 As attached Figure 3 As shown, this embodiment 3 provides an automatic dosing control device for an air-condenser, including: a memory for storing a computer program; a processor for implementing the steps of the automatic dosing control method for an air-condenser when executing the computer program, or the processor implements the functions of each module in the above-mentioned automatic dosing control system for an air-condenser when executing the computer program.

[0053] Specifically, when the processor executes the computer program, the steps of the automatic dosing control method for the air-cooled condenser are implemented, for example: Acquire real-time operation data of the automatic dosing system of the air-cooled condenser; perform data preprocessing on the real-time operation data of the automatic dosing system of the air-cooled condenser to obtain preprocessed real-time operation data; input the preprocessed real-time operation data into a neural network prediction model, use the neural network prediction model to predict the required dosing amount, and output the required dosing amount prediction value; calculate the deviation and deviation change rate between the required dosing amount prediction value and the target concentration based on the required dosing amount prediction value and the predetermined hydrogen peroxide target concentration; input the deviation and deviation change rate between the required dosing amount prediction value and the target concentration into a fuzzy neural network model, use the fuzzy neural network model to predict the dosing frequency change of the dosing pump, and output the dosing pump frequency change value; calculate the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump; generate and issue a frequency control instruction to the frequency converter based on the dosing pump frequency control value.

[0054] Specifically, when the processor executes the computer program, the functions of each module in the automatic dosing control system for the air-cooled condenser are realized, for example: A data acquisition module is used to obtain real-time operating data of the automatic dosing system of the air-cooled condenser; a data processing module is used to perform data preprocessing on the real-time operating data of the automatic dosing system of the air-cooled condenser to obtain preprocessed real-time operating data; a dosing amount prediction module is used to input the preprocessed real-time operating data into the neural network prediction model, use the neural network prediction model to predict the required dosing amount, and output the required dosing amount prediction value; a deviation calculation module is used to calculate the deviation and deviation change rate between the required dosing amount prediction value and the target concentration based on the required dosing amount prediction value and the predetermined hydrogen peroxide target concentration; a frequency control module is used to input the deviation and deviation change rate between the required dosing amount prediction value and the target concentration into the fuzzy neural network model, so as to use the fuzzy neural network model to predict the dosing frequency change of the dosing pump, and output the dosing pump frequency change value; an 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; based on the dosing pump frequency control value, a frequency control instruction is generated and issued to the frequency converter.

[0055] Exemplarily, the computer program may 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 may be a series of computer program instruction segments capable of completing preset functions, and the instruction segments are used to describe the execution process of the computer program in the air-cooled condenser automatic dosing control device.

[0056] For example, the computer program can be divided into a data acquisition module, a data processing module, a dosage prediction module, a deviation calculation module, a frequency control module and an instruction output module, and the specific functions of each module are as follows: a data acquisition module, used to obtain the real-time operation data of the automatic dosing system of the air-cooled condenser; a data processing module, used to perform data preprocessing on the real-time operation data of the automatic dosing system of the air-cooled condenser to obtain the preprocessed real-time operation data; a dosage prediction module, used to input the preprocessed real-time operation data into a neural network prediction model, use the neural network prediction model to predict the required dosage, and output the required dosage prediction value; A deviation calculation module is used to calculate the deviation and deviation change rate of the predicted value of the required dosing amount and the target concentration according to the predicted value of the required dosing amount and the predetermined target concentration of hydrogen peroxide; a frequency control module is used to input the deviation and deviation change rate of the predicted value of the required dosing amount and the target concentration into a fuzzy neural network model, so as to use the fuzzy neural network model to predict the dosing frequency change of the dosing pump and output the dosing pump frequency change value; an instruction output module is used to calculate the dosing pump frequency control value according to the dosing pump frequency change value and the real-time frequency of the dosing pump; based on the dosing pump frequency control value, a frequency control instruction is generated and sent to the frequency converter.

[0057] The automatic dosing control device for air-cooled condenser can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The automatic dosing control device for air-cooled condenser can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above is an example of an automatic dosing control device for air-cooled condenser, and does not constitute a limitation on the automatic dosing control device for air-cooled condenser, and can include more components than the above, or combine certain components, or different components, for example, the automatic dosing control device for air-cooled condenser can also include input and output devices, network access devices, buses, etc.

[0058] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The processor is the control center of the automatic dosing control device for air-cooled condensers, and uses various interfaces and lines to connect various parts of the automatic dosing control device for air-cooled condensers.

[0059] The memory can be used to store the computer program and / or module, and the processor implements various functions of the air-to-condenser automatic dosing control device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.

[0060] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0061] Example 4 This embodiment 4 also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the automatic dosing control method for an air-cooled condenser are implemented, for example: Acquire real-time operation data of the automatic dosing system of the air-cooled condenser; perform data preprocessing on the real-time operation data of the automatic dosing system of the air-cooled condenser to obtain preprocessed real-time operation data; input the preprocessed real-time operation data into a neural network prediction model, use the neural network prediction model to predict the required dosing amount, and output the required dosing amount prediction value; calculate the deviation and deviation change rate between the required dosing amount prediction value and the target concentration based on the required dosing amount prediction value and the predetermined hydrogen peroxide target concentration; input the deviation and deviation change rate between the required dosing amount prediction value and the target concentration into a fuzzy neural network model, use the fuzzy neural network model to predict the dosing frequency change of the dosing pump, and output the dosing pump frequency change value; calculate the dosing pump frequency control value based on the dosing pump frequency change value and the real-time frequency of the dosing pump; generate and issue a frequency control instruction to the frequency converter based on the dosing pump frequency control value.

[0062] If the modules / units integrated in the automatic dosing control system for air-cooled condensers are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0063] Based on such understanding, the present invention implements all or part of the processes in the above-mentioned automatic dosing control method for air-cooled condenser, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned automatic dosing control method for air-cooled condenser can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or preset intermediate form, etc.

[0064] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0065] It should be noted that the content contained in the computer-readable storage medium can 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, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0066] Example 5 This embodiment 5 provides a computer product, which computer program product includes a computer program, which is 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 the processor 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.

[0067] It should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0068] The automatic dosing control method for an air-cooled condenser provided by the present invention collects the real-time flow rate of condensate, the real-time frequency of a dosing pump and the real-time concentration of hydrogen peroxide at the outlet of the condensate pump during the automatic dosing process of the air-cooled condenser, and dynamically adjusts the frequency of the dosing pump according to the collected real-time data, thereby realizing dosing control based on a real-time monitoring and feedback mechanism, and effectively improving the reliability and safety of the system.

[0069] The above embodiment is only one of the implementation methods that can realize the technical solution of the present invention. The scope of protection claimed by the present invention is not limited only to this embodiment, but also includes changes, replacements and other implementation methods that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention.

Claims

1. An automatic 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 condensate flow rate, 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; According to the predicted value of the required dosage and the predetermined target concentration of hydrogen peroxide, the deviation between the predicted value of the required dosage and the target concentration and the rate of change of the deviation are calculated; The deviation between the predicted value of the required dosage and the target concentration and the deviation change rate are input into the fuzzy neural network model, and the frequency change value of the dosing pump is output; A dosing pump frequency control value is obtained according to the dosing pump frequency change value and the dosing pump real-time frequency; and a frequency control instruction is generated and sent to the frequency converter based on the dosing pump frequency control value.

2. The automatic dosing control method for an air-cooled condenser according to claim 1, characterized in that: The fuzzy neural network model includes a pre-network and a post-network; The antecedent network is used to receive the deviation between the predicted value of the required dosage and the target concentration and the deviation change rate, and perform fuzzification processing according to a preset membership function to obtain a fuzzy signal; The post-processing network is used to perform fuzzy reasoning calculation on the fuzzy signal to obtain a fuzzy output result; and to perform clarification processing on the fuzzy output result to output a frequency change value of the dosing pump.

3. The automatic dosing control method for an air-cooled condenser according to claim 2, characterized in that: The preset membership function is a Gaussian function.

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

5. The automatic dosing control method for an air-cooled condenser according to claim 4, characterized in that: The preset parameters of the fuzzy neural network model include the central value of the membership function, the width value of the membership function and the connection weights in the consequent network.

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

7. An automatic dosing control system for an air-cooled condenser, characterized in that: include: Data acquisition module, 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; A 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 outlet of the condensate pump into a neural network prediction model, and output a predicted value of the required dosage; The deviation calculation module is used to calculate the deviation and the deviation change rate between the predicted value of the required dosage and the target concentration according to the predicted value of the required dosage and the predetermined target concentration of hydrogen peroxide; A frequency change control module is used to input the deviation between the predicted value of the required dosage and the target concentration and the deviation change rate into the fuzzy neural network model, and output the frequency change value of the dosing pump; The instruction output module is used to obtain a dosing pump frequency control value according to the dosing pump frequency change value and the dosing pump real-time frequency; based on the dosing pump frequency control value, generate and send a frequency control instruction to the frequency converter.

8. An automatic dosing control device for an air-cooled condenser, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the automatic dosing control method for an air-cooled condenser according to any one of claims 1 to 6 is executed.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the automatic dosing control method for an air-cooled condenser as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the automatic dosing control method for an air-cooled condenser according to any one of claims 1 to 6 is implemented.

Images