Intelligent ammonia addition control method and system based on computational pH-based water vapor system

Abstract

The application discloses a kind of based on computing type pH water vapor system intelligentization ammonia addition control method and system, comprising: the conductivity of water sample, hydrogen conductivity and temperature are obtained;The conductivity of feed water is corrected using the temperature of feed water, to obtain modified conductivity, according to the modified conductivity and hydrogen conductivity of the water sample the pH value of feed water and the ammonia content of current water vapor system are calculated;The historical time series data of unit is obtained, according to the historical time series data of unit, the pH value of feed water and the ammonia content of current water vapor system, predict dynamic feedforward compensation u_FF (t);According to the dynamic feedforward compensation u_FF (t) solving control output u (t);According to the control output u (t) carries out water vapor system's ammonia addition control, the method and system can realize accurate ammonia addition control of full working condition, full process, solve the problem that existing ammonia addition feedback control precision is low, stability is insufficient, to load change response is slow.

Description

Technical Field

[0001] This invention belongs to the field of thermal power plant thermal technology, and relates to an intelligent ammonia addition control method and system for a water-steam system based on computational pH. Background Technology

[0002] In thermal power plant systems, adding ammonia to feedwater is a widely used and essential method for inhibiting metal corrosion and ensuring the safe and economical operation of thermal equipment. Ammonia effectively slows down flow-accelerated corrosion (FAC) in the feedwater system and water-cooled wall tubes by adjusting the pH value of the steam and water, reducing the total iron content of corrosion products, thereby preventing scaling on the water-cooled walls and corrosion failure of thermal equipment. Under complex operating conditions such as deep peak shaving in supercritical units, precise and real-time dynamic control of the ammonia dosage is even more crucial.

[0003] Currently, existing methods for controlling ammonia addition to water vapor systems have the following main technical shortcomings: 1) pH measurement depends on electrodes, resulting in insufficient accuracy and stability: Traditional online pH meters are affected by various factors such as solution resistance, flow rate, temperature, and glass electrode aging, resulting in large measurement lag and easy deviation. This leads to inaccurate feedback reference for ammonia addition closed-loop control, making it difficult to achieve accurate closed-loop control.

[0004] 2) Parameter optimization relies on human experience and is not capable of coping with changes in unit load: The existing automatic ammonia addition system mainly relies on fixed PID parameters for control, which cannot adjust the control parameters in real time according to dynamic operating conditions such as changes in unit load and water quality fluctuations. It is difficult to meet the flexible control requirements under complex operating conditions such as deep peak shaving.

[0005] 3) The control strategy is singular and lacks multi-parameter coordination and prediction capabilities: Existing systems usually only rely on single-point pH or conductivity measurements for feedback adjustment. The feedback signal lags behind the actual water quality changes and has not yet integrated the ability to coordinate and predict trends of multiple parameters such as conductivity, hydrogen conductivity, pH, and ammonia content.

[0006] Current improved technologies exist, such as CN119597039A, which proposes a device to control ammonia addition based on pH calculation using conductivity and hydrogen conductivity, realizing the basic principle of closed-loop control. However, its control strategy is still mainly based on single-parameter feedback, lacks dynamic prediction capabilities for on-site load changes, and has not achieved deep integration with unit operating conditions. Therefore, there is an urgent need to develop an intelligent ammonia addition control method and system based on multi-parameter collaborative sensing, data-driven feedforward prediction, and adaptive closed-loop regulation to achieve precise ammonia addition control across all operating conditions and the entire process. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of the prior art and provide an intelligent ammonia addition control method and system for water vapor systems based on computational pH. This method and system can achieve precise ammonia addition control under all operating conditions and throughout the entire process, solving the problems of low accuracy, insufficient stability, and slow response to load changes in existing ammonia addition feedback control.

[0008] To achieve the above objectives, this invention discloses an intelligent ammonia addition control method for a water vapor system based on computational pH, comprising: Obtain the electrical conductivity, hydrogen conductivity, and temperature of the water sample; The conductivity of the feedwater is corrected by the temperature of the feedwater to obtain the modified conductivity. The pH value of the feedwater and the ammonia content of the current water vapor system are calculated based on the modified conductivity and hydrogen conductivity of the water sample. The historical time series data of the unit is obtained, and the dynamic feedforward compensation amount u_FF(t) is predicted based on the historical time series data of the unit, the pH value of the feedwater and the current ammonia content of the water-steam system. The control output u(t) is calculated based on the dynamic feedforward compensation amount u_FF(t); The ammonia addition control of the water-steam system is performed based on the control output u(t).

[0009] Furthermore, an online monitoring unit is installed on the water supply pipeline or condensate pipeline after the dosing point. The online monitoring unit includes at least a conductivity electrode, an automatic electro-regenerated cation exchange device, and a hydrogen conductivity electrode to continuously acquire the conductivity, hydrogen conductivity, and temperature of the water sample, respectively.

[0010] Furthermore, based on the unit's historical time series data, the pH value of the feedwater, and the current ammonia content of the water-steam system, the dynamic feedforward compensation amount u_FF(t) is predicted using a vector autoregression (VAR) model or a long short-term memory network (LSTM) time series prediction model.

[0011] Furthermore, based on the dynamic feedforward compensation amount u_FF(t), the control output amount u(t) is calculated by the feedforward-feedback composite controller.

[0012] Furthermore, the expression for the control output u(t) is: u(t)=u_FF(t)+Kp·e(t)+Ki·∫e(t)dt+Kd·de(t) / dt (2) Where Kp, Ki, and Kd are PID parameters.

[0013] Furthermore, when the calculated pH value deviates from the target pH value by |e(t)| beyond the dead zone, the PID parameters are automatically switched according to the sign and magnitude of the deviation.

[0014] Furthermore, when an abnormal increase in conductivity or rapid fluctuation in hydrogen conductivity is detected, a temporary enhancement factor k_add (e.g., 0.8~1.2) is generated, and the control output u(t) is corrected using the temporary enhancement factor k_add.

[0015] This invention discloses an intelligent ammonia addition control system for a water vapor system based on computational pH, comprising: The acquisition module is used to acquire the conductivity, hydrogen conductivity, and temperature of the water sample. The calculation module is used to correct the conductivity of the feedwater using the temperature of the feedwater to obtain the modified conductivity, and to calculate the pH value of the feedwater and the ammonia content of the current water vapor system based on the modified conductivity and hydrogen conductivity of the water sample. The prediction module is used to acquire the historical time series data of the unit and predict the dynamic feedforward compensation amount u_FF(t) based on the historical time series data of the unit, the pH value of the feedwater and the ammonia content of the current water-steam system. The calculation module is used to calculate the control output u(t) based on the dynamic feedforward compensation amount u_FF(t); The control module is used to control the ammonia addition to the water-steam system according to the control output u(t).

[0016] This invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the intelligent ammonia addition control method for a water vapor system based on computational pH.

[0017] This invention discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the intelligent ammonia addition control method for a water vapor system based on computational pH.

[0018] The present invention has the following beneficial effects: The intelligent ammonia addition control method and system for water-steam systems based on computational pH described in this invention, during specific operation, utilizes unit load and flow rate to predict pH value change trends in advance, forming a "feedforward-feedback" collaborative control architecture to compensate for the lag in response of traditional feedback control. Furthermore, this invention jointly analyzes online collaborative monitoring data of conductivity, hydrogen conductivity, pH, and ammonia content with state parameters such as unit load and feedwater flow rate to determine the control output u(t), achieving precise ammonia addition control across all operating conditions and the entire process, thus solving the problems of low accuracy, insufficient stability, and slow response to load changes in existing ammonia addition feedback control. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application 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.

[0020] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0025] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0026] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0029] Example 1 refer to Figure 1 The intelligent ammonia addition control method for a water vapor system based on computational pH as described in this invention includes the following steps: 1) Install an online monitoring unit on the water supply pipeline or condensate pipeline after the dosing point. The online monitoring unit shall include at least a conductivity electrode, an automatic electro-regenerated cation exchange device, and a hydrogen conductivity electrode to continuously acquire the conductivity (S), hydrogen conductivity (CC), and temperature (T) signals of the water sample.

[0030] The system collects the aforementioned sensor data in real time at a frequency of up to 1Hz and integrates the signals into a field programmable logic controller (PLC) or distributed control system (DCS) to form a multi-dimensional data stream with timestamps.

[0031] 2) Based on the law of independent ion movement and the physical relationship model between the conductivity and pH value of ammonia solution, as shown in Equation (1), the control unit automatically calculates the pH value of the water supply by using the real-time collected conductivity (S) and hydrogen conductivity (CC).

[0032] pH=-lg(Ksp)+lg(K / 271.4)=8.56639+lg(K)(1) Where K is the conductivity of ammonia-containing pure water.

[0033] The system incorporates a temperature compensation module that, based on a pre-established conductivity-temperature nonlinear compensation model, corrects the measured raw conductivity signal in real time, eliminating errors introduced by temperature fluctuations. Simultaneously, the system can calculate the ammonia content (NH3) of the current water vapor system in parallel, enabling pH-coordinated monitoring.

[0034] 3) Set up an edge computing gateway on the upper layer of PLC / DCS and run a vector autoregression (VAR) model or a long short-term memory network (LSTM) time series prediction model based on machine learning. The model uses historical time series data such as unit load (L), feedwater flow (F) and condensate flow (Q) within the cycle, as well as real-time calculated pH value and ammonia content as input features.

[0035] After offline training (using a backpropagation algorithm based on historical running data), the model is used for online inference to predict the pH value change trend in advance for the next 1 to 10 minutes, thus obtaining the dynamic feedforward compensation amount u_FF(t).

[0036] 4) The core layer of the control system executes variable-gain PID control based on conductivity-pH dual feedback, incorporating fuzzy logic or RBF neural networks to achieve online self-tuning of PID parameters (Kp, Ki, Kd). The core processing logic is as follows: Set the target pH control range (e.g., feedwater pH = 9.0-9.5, condensate pH = 8.8-9.3), and design the expression for the control output u(t) after being solved by the feedforward-feedback composite controller as follows: u(t)=u_FF(t)+Kp·e(t)+Ki·∫e(t)dt+Kd·de(t) / dt (2) Where u_FF(t) is the dynamic feedforward compensation amount output by the prediction model.

[0037] When the calculated pH value deviates from the target pH value by |e(t)| beyond the dead zone, the PID parameters are automatically switched according to the sign and magnitude of the deviation, and strong / weak control rules are enabled (e.g., "tuning mode" is enabled when the deviation is >0.2, and "sleep mode" is enabled when the deviation is <0.1); the system actuator (frequency drive of the ammonia metering pump) receives the control command, accurately outputs and adds ammonia solution.

[0038] 5) The system has embedded intelligent auxiliary control logic to monitor multi-parameter measurements in real time. When abnormal hydrological conditions such as abnormal increase in conductivity or rapid fluctuation of hydrogen conductivity are detected, the system automatically intervenes to execute constraint control, generating a temporary enhancement coefficient k_add (e.g., 0.8~1.2), and using the temporary enhancement coefficient k_add to correct the output u(t) of the composite controller.

[0039] The configurable constraint strategies for the efficiency enhancement logic include, but are not limited to: (a) when the conductivity exceeds the warning limit, prioritize increasing the feedforward compensation ratio; (b) when the calculated ammonia content exceeds the preset upper limit, temporarily lock the opening of the ammonia addition regulating valve or reduce the frequency of the ammonia addition pump to prevent ammonia from exceeding the standard.

[0040] In addition, the present invention sets up an industrial control computer or an integrated intelligent touch screen as an operator monitoring station, which displays dynamic structured data curves in real time (including real-time trends of key indicators such as pH, conductivity, hydrogen conductivity, and ammonia content of feedwater / condensate), and supports abnormal early warning push, historical data tracing, and automatic report generation.

[0041] In this embodiment, the edge computing gateway seamlessly connects with the power plant's plant-level monitoring information system (SIS) and safety production management platform via the MQTT or OCDA / UA industrial standard protocol, constructing a unified three-level control system of group-region-grassroots, supporting intelligent analysis of larger data volumes.

[0042] In this embodiment, the feedforward prediction model adopts an active learning strategy, which uses new data whose prediction error exceeds the threshold after each ammonia addition control as training samples, and performs incremental training of the model during low unit load or shutdown windows to continuously improve prediction accuracy.

[0043] In this embodiment, the variable gain PID controller automatically switches to "fast follow mode" when the unit undergoes deep peak shaving or rapid load change, increases the proportion of feedforward component, shortens dynamic response time, and ensures that the pH value of the feedwater quickly recovers to the target range after a sudden change in operating conditions.

[0044] This invention has the following characteristics: pH feedback accuracy is significantly improved: the conductivity-based calculation-based pH measurement overcomes the shortcomings of traditional glass electrode method, such as large measurement lag and frequent maintenance, and still has high accuracy under low conductivity conditions of water supply. Rapid adaptive capability: AI feedforward control effectively compensates for the response delay problem of traditional feedback control when the load changes suddenly, and significantly reduces pH overshoot during unit start-up or deep peak shaving. Full-condition adaptive control: The variable gain PID controller can dynamically adjust the control parameters according to the real-time operating conditions such as unit load and feedwater flow, so as to avoid the accelerated flow and corrosion of the feedwater system due to untimely ammonia addition under deep peak shaving conditions. Data-driven decision support: significantly reduces the frequency of operator intervention, improves the level of system automation and intelligence, reduces ammonia consumption, and saves operating costs.

[0045] Confirmatory Experiment This embodiment is used for intelligent ammonia injection control based on load feedforward in the feedwater system of a supercritical 600MW unit. The specific process is as follows: 1) Online monitoring of multiple parameters and accurate pH calculation; During system operation, the automatically regenerating cation exchanger installed after the dosing point continuously introduces water samples into the intelligent instrument cabinet. The online conductivity electrode acquires the specific conductivity S (μS / cm) of the feed water sample, the hydrogen conductivity electrode acquires the hydrogen conductivity CC (μS / cm) signal corresponding to the remaining impurities after ammonia removal, and the temperature sensor simultaneously collects the water sample temperature T.

[0046] The PLC collects the above parameters in real time at a sampling rate of 1Hz. After temperature compensation, it automatically calculates the current pH value in real time according to the formula pH=8.56639+lg(K), where K is the conductivity value contributed by the alkalizing agent (ammonia) (calculated from the difference between specific conductivity and hydrogen conductivity). The system also outputs the estimated ammonia content (NH3) in the current water sample and displays it on the host computer monitoring interface.

[0047] 2) AI model training and load feedforward parameter settings; During the offline learning phase, key data sequences (load signals, feedwater flow, feedwater pump frequency, etc.) under all operating conditions are collected from the historical load change cycle (spanning at least 3 months) of the unit, and a time-series prediction model LSTM is developed. The model is trained on an edge computing server with the training objective of predicting the pH trend for the next 5 minutes. After training, the model is solidified and deployed to the edge gateway.

[0048] 3) Adaptive PID control based on feedforward-feedback; During real-time operation, the DCS provides a target pH setpoint (e.g., 9.2). The LSTM prediction model takes the historical data of unit load and feedwater flow rate over the past 15 minutes as input and outputs the predicted pH change slope (ΔpH_pred) for the next 5-10 minutes in advance.

[0049] Based on this, the system obtains the feedforward compensation term u_FF for parameter tuning, thereby realizing feedforward compensation for the lag element.

[0050] Meanwhile, the PID parameters (ΔKp, ΔKi, ΔKd) are tuned in real time based on the online learning capability of the RBF network, and the gain adaptive logic is integrated and superimposed with the feedforward component to form the final control output.

[0051] 4) Constraints and trip protection of efficiency enhancement logic; In one test, the unit load rapidly increased from 400MW to 550MW, and the feedwater flow rate quickly climbed from 1100t / h to 1650t / h. Because the LSTM prediction model anticipated the pH decline trend and added compensating ammonia before receiving the deviation value, the pH control fluctuation range was ultimately reduced from ±0.25 in the traditional method to within ±0.08. Compared to methods relying solely on manual intervention or without feedforward prediction, this effectively avoided the corrosion risk caused by real-time pH levels below 9.0. Early warnings can also be provided in the multi-parameter monitoring software to alert operators and prevent ammonia exceedances.

[0052] 5) Human-computer interaction and remote operation and maintenance; After all the above steps, the on-site industrial control computer screen displays multiple key trend curves in real time, including feedwater pH, equivalent ammonia content, unit load, and automatic regulating valve opening. Process information can be uploaded to the SIS or centralized monitoring platform. Alarm reminders are automatically pushed when efficiency enhancement logic is implemented or when critical equipment malfunctions. Maintenance personnel can access the equipment and browse operational information via touchscreen or mobile terminal.

[0053] Effect verification: In a continuous industrial test of a 600MW coal-fired unit, after adopting this invention, the feedwater pH value could be stably controlled within the target range of 9.0~9.3. The relative standard deviation (RSD) of pH fluctuation was reduced from 0.13 under manual or traditional PID control to less than 0.02, and the overall operating condition pass rate increased from less than 85% to over 98.5%. Ammonia consumption decreased by an average of 12.5%, and operating costs were significantly reduced. During deep peak shaving of the unit (load change rate > 6% / min), the system can bring the pH value back to the target range within 15 seconds, fully meeting the stringent requirements of modern supercritical units for feedwater chemical conditions.

[0054] Example 2 The intelligent ammonia addition control system for a water vapor system based on computational pH as described in this invention includes: The acquisition module is used to acquire the conductivity, hydrogen conductivity, and temperature of the water sample. The calculation module is used to correct the conductivity of the feedwater using the temperature of the feedwater to obtain the modified conductivity, and to calculate the pH value of the feedwater and the ammonia content of the current water vapor system based on the modified conductivity and hydrogen conductivity of the water sample. The prediction module is used to acquire the historical time series data of the unit and predict the dynamic feedforward compensation amount u_FF(t) based on the historical time series data of the unit, the pH value of the feedwater and the ammonia content of the current water-steam system. The calculation module is used to calculate the control output u(t) based on the dynamic feedforward compensation amount u_FF(t); The control module is used to control the ammonia addition to the water-steam system according to the control output u(t).

[0055] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0056] Example 3 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, it implements the steps of the intelligent ammonia addition control method for a water-steam system based on computational pH. For example, the method includes: acquiring the conductivity, hydrogen conductivity, and temperature of a water sample; correcting the conductivity of the feedwater using the feedwater temperature to obtain a modified conductivity; calculating the pH value of the feedwater and the current ammonia content of the water-steam system based on the modified conductivity and hydrogen conductivity of the water sample; acquiring historical time-series data of the unit; predicting a dynamic feedforward compensation amount u_FF(t) based on the historical time-series data of the unit, the pH value of the feedwater, and the current ammonia content of the water-steam system; calculating the control output amount u(t) based on the dynamic feedforward compensation amount u_FF(t); and performing ammonia addition control of the water-steam system based on the control output amount u(t). The memory may include main memory, such as high-speed random access memory (RAM), or non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry-standard architecture bus, a peripheral component interconnection standard bus, or an extended industry-standard architecture bus. The bus can be categorized as an address bus, data bus, or control bus. The memory stores programs; specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0057] Example 4 A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the intelligent ammonia addition control method for a water-steam system based on computational pH. For example, the method includes: acquiring the conductivity, hydrogen conductivity, and temperature of a water sample; correcting the conductivity of the feedwater using the feedwater temperature to obtain a modified conductivity; calculating the pH value of the feedwater and the current ammonia content of the water-steam system based on the modified conductivity and hydrogen conductivity of the water sample; acquiring historical time-series data of the unit; predicting a dynamic feedforward compensation amount u_FF(t) based on the historical time-series data, the pH value of the feedwater, and the current ammonia content of the water-steam system; calculating a control output amount u(t) based on the dynamic feedforward compensation amount u_FF(t); and performing ammonia addition control of the water-steam system based on the control output amount u(t). 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.

[0058] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0060] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0061] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0062] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0063] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

[0064] The above description is merely a preferred embodiment of the present invention and does not constitute any limitation on the present invention. Any simple modifications, alterations, or equivalent structural changes made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for intelligent ammonia addition control of a water vapor system based on computational pH, characterized in that, include: Obtain the electrical conductivity, hydrogen conductivity, and temperature of the water sample; The conductivity of the feedwater is corrected by the temperature of the feedwater to obtain the modified conductivity. The pH value of the feedwater and the ammonia content of the current water vapor system are calculated based on the modified conductivity and hydrogen conductivity of the water sample. The historical time series data of the unit is obtained, and the dynamic feedforward compensation amount u_FF(t) is predicted based on the historical time series data of the unit, the pH value of the feedwater and the current ammonia content of the water-steam system. The control output u(t) is calculated based on the dynamic feedforward compensation amount u_FF(t); The ammonia addition control of the water-steam system is performed based on the control output u(t).

2. The intelligent ammonia addition control method for a water vapor system based on computational pH according to claim 1, characterized in that, An online monitoring unit is installed on the water supply pipeline or condensate pipeline after the dosing point. The online monitoring unit includes at least a conductivity electrode, an automatic electro-regenerated cation exchange device, and a hydrogen conductivity electrode to continuously acquire the conductivity, hydrogen conductivity, and temperature of the water sample.

3. The intelligent ammonia addition control method for a water vapor system based on computational pH according to claim 1, characterized in that, Based on the unit's historical time-series data, the pH value of the feedwater, and the current ammonia content of the water-steam system, the dynamic feedforward compensation amount u_FF(t) is predicted using a vector autoregression (VAR) model or a long short-term memory network (LSTM) time-series prediction model based on machine learning.

4. The intelligent ammonia addition control method for a water vapor system based on computational pH according to claim 1, characterized in that, Based on the dynamic feedforward compensation amount u_FF(t), the control output amount u(t) is calculated by the feedforward-feedback composite controller.

5. The intelligent ammonia addition control method for a water vapor system based on computational pH according to claim 4, characterized in that, The expression for the control output u(t) is: u(t)=u_FF(t)+Kp·e(t)+Ki·∫e(t)dt+Kd·de(t) / dt (2) Where Kp, Ki, and Kd are PID parameters.

6. The intelligent ammonia addition control method for a water vapor system based on computational pH according to claim 5, characterized in that, When the calculated pH value deviates from the target pH value by |e(t)| beyond the dead zone, the PID parameters are automatically switched according to the sign and magnitude of the deviation.

7. The intelligent ammonia addition control method for a water vapor system based on computational pH according to claim 4, characterized in that, When an abnormal increase in conductivity or rapid fluctuation in hydrogen conductivity is detected, a temporary enhancement factor k_add (e.g., 0.8~1.2) is generated, and the control output u(t) is corrected using the temporary enhancement factor k_add.

8. An intelligent ammonia addition control system for a water vapor system based on computational pH, characterized in that, include: The acquisition module is used to acquire the conductivity, hydrogen conductivity, and temperature of the water sample. The calculation module is used to correct the conductivity of the feedwater using the temperature of the feedwater to obtain the modified conductivity, and to calculate the pH value of the feedwater and the ammonia content of the current water vapor system based on the modified conductivity and hydrogen conductivity of the water sample. The prediction module is used to acquire the historical time series data of the unit and predict the dynamic feedforward compensation amount u_FF(t) based on the historical time series data of the unit, the pH value of the feedwater and the ammonia content of the current water-steam system. The calculation module is used to calculate the control output u(t) based on the dynamic feedforward compensation amount u_FF(t); The control module is used to control the ammonia addition to the water-steam system according to the control output u(t).

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent ammonia control method for a water vapor system based on computational pH as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent ammonia addition control method for a water vapor system based on computational pH as described in any one of claims 1-7.

Images