Method for intelligently determining terminal point of unit start-up flushing and related device

Abstract

The application discloses a kind of unit starting flushing terminal point intelligent determination method and related device, comprising: in the process of unit starting flushing, according to the preset sampling period, the water quality parameter of several flushing water is collected in real time;The several water quality parameters are input into the preset judgment model, the several water quality parameters are fused and handled, and the comprehensive water quality index is calculated;According to the dynamic threshold value of unit starting flushing process and / or the real-time fluctuation state of the water quality parameter;The comprehensive water quality index is compared with the dynamic threshold value, when the comprehensive water quality index is continuously lower than the dynamic threshold value under the preset continuous condition, then it is judged to reach the unit starting flushing terminal point;After judging to reach the unit starting flushing terminal point, output condensate recovery control signal, and the method and related device can accurately determine the unit starting flushing terminal point.

Description

Technical Field

[0001] This invention belongs to the field of automatic control technology for chemical monitoring in power plants, and relates to an intelligent method and related device for determining the end point of unit start-up flushing. Background Technology

[0002] During the startup of power plant units, the condensate system, feedwater system, and related thermal systems typically require flushing to remove residual corrosion products, iron oxides, suspended particles, and other soluble or insoluble impurities. Determining the endpoint of this startup flushing directly impacts the unit's steam and water quality control, demineralized water consumption, and the safe operation of subsequent thermal equipment.

[0003] If the flushing endpoint is determined too early, unremoved corrosion products and contaminants may enter the subsequent thermal system with the condensate, leading to deterioration of steam quality, deposits on heated surfaces, and increased corrosion risk. In severe cases, this can affect the unit's start-up safety and long-term operational reliability. If the flushing endpoint is determined too late, it will result in a large waste of demineralized water and increase the wastewater treatment load and start-up operating costs.

[0004] In existing technologies, the endpoint of start-up flushing often relies on manual judgment by operators or on whether a single water quality parameter, such as conductivity, is below a fixed threshold. This method has the following shortcomings: First, water quality fluctuates significantly during the start-up phase, and short-term compliance of a single parameter cannot fully characterize the overall state of the flushing water; second, the release patterns of different pollutants are not consistent; for example, a decrease in conductivity does not necessarily mean that total iron or suspended corrosion products have been reduced to a safe level; third, fixed thresholds are difficult to adapt to the differences in different units, different shutdown times, different initial contamination levels, and different flushing stages; fourth, manual judgment is subjective and lagging, making it difficult to meet the requirements of automated and refined chemical monitoring and control in power plants.

[0005] Therefore, there is an urgent need for an intelligent method for determining the end point of unit start-up flushing that can integrate multiple water quality parameters, adapt to the dynamic fluctuation characteristics of start-up flushing, have the ability to prevent misjudgment, and can be linked with the condensate recovery system, so as to accurately determine the end point of unit start-up flushing. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide an intelligent method and related device for determining the end point of unit start-up flushing. This method and related device can accurately determine the end point of unit start-up flushing.

[0007] To achieve the above objectives, this invention discloses an intelligent method for determining the endpoint of unit start-up flushing, comprising: During the unit start-up flushing process, several water quality parameters of the flushing water are collected in real time according to the preset sampling cycle; The water quality parameters are input into a preset judgment model, and the water quality parameters are fused to calculate the comprehensive water quality index. The dynamic threshold is determined based on the unit start-up flushing process and / or the real-time fluctuation of the water quality parameters. The comprehensive water quality index is compared with the dynamic threshold. When the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions, it is determined that the unit start-up flushing endpoint has been reached. After determining that the unit start-up flushing endpoint has been reached, a condensate recovery control signal is output.

[0008] Furthermore, the water quality parameters include multiple parameters such as total iron, conductivity, pH value, dissolved oxygen, turbidity, silica and sodium ion concentration.

[0009] Furthermore, the preset judgment model includes a parameter normalization module, a parameter weight configuration module, a fluctuation penalty module, and an endpoint confirmation module. The parameter normalization module is used to convert water quality parameters of different dimensions into dimensionless evaluation values. The parameter weight configuration module is used to allocate weights according to the degree of influence of each water quality parameter on the risk of flushing water recycling. The fluctuation penalty module is used to correct the comprehensive water quality index when water quality parameters rebound or change abruptly.

[0010] Furthermore, the preset judgment model is any one or a combination of expert rule base model, weighted fusion model, mathematical compensation model, and machine learning model.

[0011] Furthermore, when the preset judgment model is a weighted fusion model, the comprehensive water quality index is: I(t)=Σwi·fi(xi(t))+λR(t), where I(t) is the comprehensive water quality index at time t, xi(t) is the real-time sampled value of the i-th water quality parameter, fi(·) is the normalization function corresponding to the i-th water quality parameter, wi is the weight coefficient of the i-th water quality parameter, R(t) is the water quality parameter fluctuation penalty term, and λ is the fluctuation penalty coefficient.

[0012] Furthermore, the dynamic threshold is: T(t) = T0 + α·σI(t) + β·B(t) + γ·S(t), where T(t) is the dynamic threshold at time t, T0 is the baseline threshold determined based on historical start-up flushing endpoint samples, σI(t) is the standard deviation of the comprehensive water quality index within the current sliding window, B(t) is the initial pollution level correction term, S(t) is the flushing stage correction term, and α, β and γ are correction coefficients.

[0013] Furthermore, the preset continuous conditions include: the comprehensive water quality index is lower than the dynamic threshold for N consecutive sampling periods, or the average value of the comprehensive water quality index within a preset sliding time window is lower than the dynamic threshold and the fluctuation amplitude is less than the preset stable threshold.

[0014] This invention discloses an intelligent system for determining the end point of unit start-up flushing, comprising: The data acquisition module is used to collect several water quality parameters of the flushing water in real time according to a preset sampling cycle during the unit start-up flushing process. The fusion module is used to input the several water quality parameters into a preset judgment model, perform fusion processing on the several water quality parameters, and calculate the comprehensive water quality index. The determination module is used to determine the dynamic threshold based on the unit start-up flushing process and / or the real-time fluctuation of the water quality parameters; The determination module is used to compare the comprehensive water quality index with the dynamic threshold. When the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions, it is determined that the unit start-up flushing endpoint has been reached. The output module is used to output a condensate recovery control signal after determining that the unit start-up flushing endpoint has been reached.

[0015] 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 determination method for the end point of the unit start-up flushing.

[0016] The present invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent determination method for the end point of unit start-up flushing.

[0017] The present invention has the following beneficial effects: The intelligent determination method and related device for the end point of unit start-up flushing described in this invention uses at least two water quality parameters for integrated determination during specific operation. This method can simultaneously reflect information such as ionic impurities, corrosion products, and water acidity / alkalinity, avoiding one-sided judgments caused by relying solely on a single conductivity threshold. Furthermore, it introduces dynamic thresholds related to the start-up flushing process and real-time fluctuations, adapting to different units, different start-up conditions, and different initial pollution levels, thus improving the adaptability of the determination method. In addition, setting preset continuous conditions can reduce the risk of premature recovery due to short-term water quality fluctuations during start-up. It also enables linkage with the condensate recovery system and continues water quality monitoring and back-off protection after recovery, facilitating online, real-time, and fully automated control of the power plant's chemical monitoring process and reducing demineralized water waste. Attached Figure Description

[0018] 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.

[0019] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the condensate recovery linkage control and back-off protection of the present invention. Detailed Implementation

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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)."

[0026] 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.

[0027] 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.

[0028] Example 1 refer to Figure 1 and Figure 2 The intelligent determination method for the end point of unit start-up flushing according to the present invention includes the following steps: 1) During the unit start-up flushing process, collect several water quality parameters of the flushing water in real time according to the preset sampling cycle; 2) Input the aforementioned water quality parameters into a preset judgment model, perform fusion processing on the aforementioned water quality parameters, and calculate the comprehensive water quality index; 3) Based on the unit start-up flushing process and / or the real-time fluctuation of the water quality parameters, adaptively generate or update dynamic thresholds corresponding to the current flushing stage; 4) Compare the comprehensive water quality index with the dynamic threshold. When the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions, it is determined that the unit start-up flushing endpoint has been reached. 5) After determining that the unit start-up flushing endpoint has been reached, output the condensate recovery control signal.

[0029] In this embodiment, the water quality parameters include multiple parameters such as total iron, conductivity, pH value, dissolved oxygen, turbidity, silica and sodium ion concentration.

[0030] In this embodiment, before step 2), the method further includes: preprocessing the water quality parameters, wherein the preprocessing includes at least one of outlier removal, missing value compensation, sliding filtering, benchmark correction and dimensional normalization.

[0031] In this embodiment, the preset judgment model includes a parameter normalization module, a parameter weight configuration module, a fluctuation penalty module, and an endpoint confirmation module. The parameter normalization module is used to convert water quality parameters of different dimensions into dimensionless evaluation values. The parameter weight configuration module is used to allocate weights according to the degree of influence of each water quality parameter on the risk of flushing water recycling. The fluctuation penalty module is used to correct the comprehensive water quality index when water quality parameters rebound or change abruptly.

[0032] In this embodiment, the preset judgment model is any one or a combination of expert rule base model, weighted fusion model, mathematical compensation model, and machine learning model.

[0033] In this embodiment, when the preset judgment model is a weighted fusion model, the comprehensive water quality index is calculated as follows: I(t)=Σwi·fi(xi(t))+λR(t), where I(t) is the comprehensive water quality index at time t, xi(t) is the real-time sampled value of the i-th water quality parameter, fi(·) is the normalization function corresponding to the i-th water quality parameter, wi is the weight coefficient of the i-th water quality parameter, R(t) is the water quality parameter fluctuation penalty term, and λ is the fluctuation penalty coefficient.

[0034] In this embodiment, the dynamic threshold is generated based on at least one of the following: historical start-up flushing endpoint samples, initial pollution level of water quality parameters, current flushing duration, current flushing stage, and fluctuation range of comprehensive water quality index within the sliding window.

[0035] In this embodiment, the dynamic threshold is updated as follows: T(t) = T0 + α·σI(t) + β·B(t) + γ·S(t), where T(t) is the dynamic threshold at time t, T0 is the baseline threshold determined based on historical start-up flushing endpoint samples, σI(t) is the standard deviation of the comprehensive water quality index within the current sliding window, B(t) is the initial pollution level correction term, S(t) is the flushing stage correction term, and α, β and γ are correction coefficients.

[0036] In this embodiment, the preset continuous conditions include: the comprehensive water quality index is lower than the dynamic threshold for N consecutive sampling periods, or the average value of the comprehensive water quality index within a preset sliding time window is lower than the dynamic threshold and the fluctuation amplitude is less than the preset stable threshold.

[0037] In this embodiment, before determining that the unit start-up flushing endpoint has been reached, the method further includes: confirming the stability of the change trends of the at least two water quality parameters; if any water quality parameter shows a sudden increase, rebound, monotonic disruption, or change rate exceeding a preset change rate limit, the flushing endpoint determination is delayed, and steps 1) to 4) are re-executed.

[0038] In this embodiment, when the sampling value of at least one water quality parameter is missing, exceeds the limit, or is determined to be an instrument malfunction, the confidence level of the comprehensive water quality index is calculated based on the remaining valid water quality parameters; when the confidence level is lower than the preset confidence threshold, the condensate recovery control signal is not output, and an instrument verification or manual confirmation prompt is generated.

[0039] In this embodiment, the condensate recovery control signal includes at least one of the following: condensate recovery valve opening command, flushing discharge valve closing command, flushing pump operation status adjustment command, alarm cancellation command, and operation monitoring system recording command.

[0040] In this embodiment, after outputting the condensate recovery control signal, the water quality parameters in the flushing water are continuously collected. When the comprehensive water quality index is higher than the dynamic threshold again, any key water quality parameter exceeds the preset safety limit, or the water quality parameter change rate exceeds the backoff limit, the recovery pause signal or the control signal to switch to the discharge state is output.

[0041] Example 2 During the start-up flushing process of a power plant unit, the total iron concentration, conductivity, and pH value of the flushing water are collected online at a sampling cycle of 1 minute. The system sends the collected data to the intelligent judgment module at the end of the start-up flushing and automatically determines whether condensate recycling is allowed based on the comprehensive water quality index and dynamic threshold.

[0042] At each sampling time t, the following water quality parameters are collected: total iron concentration Fe(t), conductivity C(t), and pH value pH(t). The total iron concentration is used to reflect the release of iron corrosion products in the system, the conductivity is used to reflect the level of ionic impurities in the water, and the pH value is used to reflect the acidity / alkalinity of the water and its corrosion tendency.

[0043] The collected water quality parameters were preprocessed. First, outliers were removed from data that clearly exceeded the instrument's range or the physical reasonable range. Second, short-term missing data were compensated by interpolation of adjacent valid sample values. Third, continuous data were filtered using a moving average. Finally, parameters of different dimensions were converted into dimensionless evaluation values.

[0044] Parameters with higher values ​​indicate a higher degree of pollution and can be normalized using the following method: fi(xi(t)) = [xi(t) - xi min ] / [xi max - xi min ] For parameters such as pH value that have a suitable range, the following deviation function can be used: f pH (pH(t)) = |pH(t) - pH0| / ΔpH max Where pH0 is the target pH value, and ΔpH max To allow for a range of deviations, the above processing allows water quality parameters with different dimensions and different directions of change to be uniformly incorporated into the calculation of the comprehensive water quality index.

[0045] This embodiment uses a weighted fusion model to calculate the comprehensive water quality index, and the calculation formula is as follows: I(t) = 0.45·f Fe (Fe(t)) + 0.35·f C ( C (t)) + 0.20·f pH ( pH (t)) + 0.10·R(t) Where I(t) is the comprehensive water quality index at time t, and the smaller the value, the more suitable the current flushing water is for recycling; R(t) is the fluctuation penalty term, which reflects whether there is a significant rebound or sudden change in water quality parameters in a recent period. The fluctuation penalty term is: R(t) = |I0(t) - I0(t-1)| Wherein, I0(t) is the basic comprehensive water quality index before the addition of the fluctuation penalty term. When the total iron concentration or conductivity suddenly increases or rebounds, R(t) increases, thereby improving the comprehensive water quality index and preventing the system from prematurely determining the end of flushing just because the water quality parameters decrease at a certain moment.

[0046] In this embodiment, the dynamic threshold is generated based on historical start-up flushing data, current water quality fluctuations, and flushing stage correction terms, namely: T(t) = T0+ α·σI(t) + β·B(t) + γ·S(t) Where T(t) is the dynamic threshold at time t; T0 is the baseline threshold determined based on historical start-up flushing endpoint samples of similar units; σI(t) is the standard deviation of the comprehensive water quality index within the current sliding window; B(t) is the initial pollution level correction term; S(t) is the flushing stage correction term; and α, β, and γ are correction coefficients.

[0047] During the initial start-up flushing phase, water quality parameters fluctuate significantly, leading to a corresponding increase in σI(t), at which point the system enters a state of observation and flushing maintenance. In the later stages of flushing, the comprehensive water quality index gradually decreases and its fluctuations diminish, the dynamic threshold stabilizes, and the system enters a state of endpoint confirmation. Therefore, the dynamic threshold can adapt to differences in pre-startup shutdown time, initial contamination levels, and flushing stages among different units.

[0048] This embodiment sets the following endpoint determination conditions: First, the comprehensive water quality index is below the dynamic threshold for N consecutive sampling periods; second, the standard deviation of the comprehensive water quality index is less than the preset stability threshold within the preset sliding time window; third, the total iron concentration, conductivity, and pH value do not show any sudden changes or rebounds exceeding the preset change rate limits; fourth, any key water quality parameter does not exceed the preset safety limit. Only when all the above conditions are met simultaneously will the system determine that the unit start-up flushing endpoint has been reached.

[0049] Once the system determines that the start-up flushing endpoint has been reached, it automatically outputs a control signal to the condensate recovery system. This control signal may include opening the condensate recovery valve, closing or adjusting the flushing discharge valve, adjusting the flushing pump's operating status, deactivating the flushing stage alarm, and recording the endpoint determination time and key water quality parameters to the operation monitoring system.

[0050] After the recovery valve is opened, the system continues to monitor the total iron concentration, conductivity and pH value online. If the comprehensive water quality index is higher than the dynamic threshold again, or any key water quality parameter exceeds the safety limit, the system outputs a recovery pause signal, switches the condensate back to the discharge state, and prompts the operators to check.

[0051] During a startup flushing process, both total iron concentration and conductivity are high at the initial stage, resulting in a high overall water quality index. As flushing progresses, conductivity decreases first, but total iron concentration experiences a short-term rebound. If a single conductivity fixed threshold is used for determination, a recovery command might be issued prematurely before the total iron concentration stabilizes. Using this invention, because the overall water quality index considers total iron, conductivity, and pH simultaneously, and incorporates a fluctuation penalty term and a continuous stability condition, the system does not output a recovery control signal during the total iron concentration rebound phase. Only after multiple water quality parameters stabilize and the overall water quality index continuously falls below the dynamic threshold does the system determine that the flushing endpoint has been reached and output a condensate recovery control signal.

[0052] Therefore, this invention can reduce unnecessary flushing time and demineralized water consumption while ensuring water quality safety, and improve the automation level and reliability of the unit start-up flushing process.

[0053] Example 3 The intelligent determination system for the end point of unit start-up flushing according to the present invention includes: The data acquisition module is used to collect several water quality parameters of the flushing water in real time according to a preset sampling cycle during the unit start-up flushing process. The fusion module is used to input the several water quality parameters into a preset judgment model, perform fusion processing on the several water quality parameters, and calculate the comprehensive water quality index. The determination module is used to determine the dynamic threshold based on the unit start-up flushing process and / or the real-time fluctuation of the water quality parameters; The determination module is used to compare the comprehensive water quality index with the dynamic threshold. When the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions, it is determined that the unit start-up flushing endpoint has been reached. The output module is used to output a condensate recovery control signal after determining that the unit start-up flushing endpoint has been reached.

[0054] 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.

[0055] Example 4 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 determination method for the end point of unit start-up flushing. For example, the method includes: during the unit start-up flushing process, collecting several water quality parameters of the flushing water in real time according to a preset sampling period; inputting the several water quality parameters into a preset judgment model, performing fusion processing on the several water quality parameters, and calculating a comprehensive water quality index; determining a dynamic threshold based on the unit start-up flushing process and / or the real-time fluctuation state of the water quality parameters; comparing the comprehensive water quality index with the dynamic threshold; and determining that the end point of unit start-up flushing has been reached when the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions; and outputting a condensate recovery control signal after determining that the end point of unit start-up flushing has been reached. 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.

[0056] Example 5 A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the intelligent determination method for the end point of unit start-up flushing. For example, the method includes: during the unit start-up flushing process, collecting several water quality parameters of the flushing water in real time according to a preset sampling period; inputting the several water quality parameters into a preset judgment model, performing fusion processing on the several water quality parameters, and calculating a comprehensive water quality index; determining a dynamic threshold based on the unit start-up flushing process and / or the real-time fluctuation state of the water quality parameters; comparing the comprehensive water quality index with the dynamic threshold, and determining that the end point of unit start-up flushing has been reached when the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions; and outputting a condensate recovery control signal after determining that the end point of unit start-up flushing has been reached. 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.

[0057] 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.

[0058] 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.

[0059] 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 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment 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.

[0061] 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.

[0062] 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.

[0063] 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 intelligently determining the end point of unit start-up flushing, characterized in that, include: During the unit's start-up flushing process, several water quality parameters of the flushing water are collected in real time according to a preset sampling cycle; The water quality parameters are input into a preset judgment model, and the water quality parameters are fused to calculate the comprehensive water quality index. The dynamic threshold is determined based on the unit start-up flushing process and / or the real-time fluctuation of the water quality parameters. The comprehensive water quality index is compared with the dynamic threshold. When the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions, it is determined that the unit start-up flushing endpoint has been reached. After determining that the unit start-up flushing endpoint has been reached, a condensate recovery control signal is output.

2. The intelligent determination method for the end point of unit start-up flushing according to claim 1, characterized in that, The water quality parameters include multiple parameters such as total iron, conductivity, pH value, dissolved oxygen, turbidity, silica, and sodium ion concentration.

3. The intelligent determination method for the end point of unit start-up flushing according to claim 1, characterized in that, The preset judgment model includes a parameter normalization module, a parameter weight configuration module, a fluctuation penalty module, and an endpoint confirmation module. The parameter normalization module is used to convert water quality parameters of different dimensions into dimensionless evaluation values. The parameter weight configuration module is used to allocate weights according to the degree of influence of each water quality parameter on the risk of flushing water recycling. The fluctuation penalty module is used to correct the comprehensive water quality index when water quality parameters rebound or change abruptly.

4. The intelligent determination method for the end point of unit start-up flushing according to claim 1, characterized in that, The preset judgment model is any one or a combination of expert rule base model, weighted fusion model, mathematical compensation model, and machine learning model.

5. The intelligent determination method for the end point of unit start-up flushing according to claim 4, characterized in that, When the preset judgment model is a weighted fusion model, the comprehensive water quality index is: I(t)=Σwi·fi(xi(t))+λR(t), where I(t) is the comprehensive water quality index at time t, xi(t) is the real-time sampled value of the i-th water quality parameter, fi(·) is the normalization function corresponding to the i-th water quality parameter, wi is the weight coefficient of the i-th water quality parameter, R(t) is the water quality parameter fluctuation penalty term, and λ is the fluctuation penalty coefficient.

6. The intelligent determination method for the end point of unit start-up flushing according to claim 1, characterized in that, The dynamic threshold is: T(t) = T0 + α·σI(t) + β·B(t) + γ·S(t), where T(t) is the dynamic threshold at time t, T0 is the baseline threshold determined based on historical start-up flushing endpoint samples, σI(t) is the standard deviation of the comprehensive water quality index within the current sliding window, B(t) is the initial pollution level correction term, S(t) is the flushing stage correction term, and α, β and γ are correction coefficients.

7. The intelligent determination method for the end point of unit start-up flushing according to claim 1, characterized in that, The preset continuous conditions include: the comprehensive water quality index is lower than the dynamic threshold for N consecutive sampling periods, or the average value of the comprehensive water quality index within a preset sliding time window is lower than the dynamic threshold and the fluctuation amplitude is less than the preset stable threshold.

8. A smart system for determining the end point of unit start-up flushing, characterized in that, include: The data acquisition module is used to collect several water quality parameters of the flushing water in real time according to a preset sampling cycle during the unit start-up flushing process. The fusion module is used to input the several water quality parameters into a preset judgment model, perform fusion processing on the several water quality parameters, and calculate the comprehensive water quality index. The determination module is used to determine the dynamic threshold based on the unit start-up flushing process and / or the real-time fluctuation of the water quality parameters; The determination module is used to compare the comprehensive water quality index with the dynamic threshold. When the comprehensive water quality index is continuously lower than the dynamic threshold under preset continuous conditions, it is determined that the unit start-up flushing endpoint has been reached. The output module is used to output a condensate recovery control signal after determining that the unit start-up flushing endpoint has been reached.

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 determination method for the end point of unit start-up flushing 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 determination method for the end point of unit start-up flushing as described in any one of claims 1-7.

Images