Condensate water quality degradation prediction method and device and storage medium

Abstract

The invention provides a condensation water quality degradation prediction method and device and a storage medium, and relates to the technical field of thermal power plant water quality analysis. The method comprises the following steps: collecting real-time index data of condensed water, importing historical index data, and carrying out data standardization processing on the real-time index data of the condensed water to obtain standardized data of the condensed water; constructing a condensed water quality degradation early warning model group, performing water quality degradation prediction on the standardized data of the condensed water based on the condensed water quality degradation early warning model group to obtain a prediction result, and performing mixed bed failure time calculation; and matching measure guidance information according to a prediction result, and sending the matched measure guidance information and the calculated mixed bed failure time to a specified client terminal. According to the invention, dimension and value differences are eliminated through standardized processing of real-time index data of condensed water, an early warning model group is constructed to predict water quality degradation from multiple angles, the mixed bed failure time is calculated according to a result, measures are matched to guide a sending terminal, and operators are helped to respond in time.

Description

TECHNICAL FIELD

[0001] The present application mainly relates to the technical field of water quality analysis of thermal power plants, and particularly relates to a condensate water quality deterioration prediction method, device and storage medium. BACKGROUND

[0002] The condensate water system is an important part of the boiler feed water system, and the deterioration of the water quality thereof will affect the feed water and steam quality. If not handled in time, the failure of the mixed bed will cause salt to enter the feed water system, resulting in problems such as turbine blade corrosion and salt accumulation. The causes of condensate water pollution include that the condenser is not tight, the drain system equipment is corroded, the condenser vacuum system is not tight, and the condensate water quality is poor, which will cause changes in water quality indicators such as conductivity and hydrogen conductivity.

[0003] The traditional monitoring method relies on manual experience to qualitatively analyze the water quality indicators and estimate the mixed bed failure time, and has defects such as low diagnosis efficiency of water quality deterioration causes, large error in estimation of mixed bed failure time, and lag in manual response. Although the existing online monitoring system can collect and analyze data in real time, it lacks feedback and guidance for the operation personnel, and has lag in abnormal alarm response of water quality and insufficient prediction accuracy of mixed bed failure time, which easily leads to delay in leak stopping operation, causes penetration failure of the mixed bed and chain deterioration of the feed water quality, and threatens the safe operation of the unit. SUMMARY

[0004] The present application mainly relates to the technical field of water quality analysis of thermal power plants, and particularly relates to a condensate water quality deterioration prediction method, device and storage medium.

[0005] The technical solution of the present application to solve the above technical problems is as follows: a condensate water quality deterioration prediction method, comprising the following steps: Collecting real-time index data of condensate water, importing historical index data of condensate water, performing data standardization processing on the real-time index data of condensate water based on the historical index data of condensate water, and obtaining condensate water standardized data; Building a condensate water quality deterioration early warning model group, performing water quality deterioration prediction on the condensate water standardized data based on the condensate water quality deterioration early warning model group, and obtaining a prediction result; Determining whether to perform mixed bed failure time calculation according to the prediction result; Matching measure guidance information according to the prediction result, and sending the matched measure guidance information and the calculated mixed bed failure time to a designated customer terminal.

[0006] Another technical solution of the present application to solve the above technical problems is as follows: a condensate water quality deterioration prediction device, characterized by comprising: a data standardization module configured to collect real-time indicator data of the condensate water, import historical indicator data of the condensate water, and perform data standardization processing on the real-time indicator data of the condensate water based on the historical indicator data of the condensate water to obtain standardized data of the condensate water; a measure guidance module configured to match measure guidance information according to the prediction result, and send the matched measure guidance information and the calculated invalidation time of the mixed bed to a designated client terminal.

[0007] Another technical solution of the present application to solve the above technical problems is as follows: a condensate water quality deterioration prediction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the condensate water quality deterioration prediction method as described above when executing the computer program.

[0008] Another technical solution of the present application to solve the above technical problems is as follows: a computer readable storage medium storing a computer program, wherein the computer program is executable by a processor to implement the condensate water quality deterioration prediction method as described above.

[0009] The present application has the following beneficial effects: by standardizing the real-time indicator data of the condensate water, the dimensional and numerical range differences between different indicator data can be eliminated, so that different types of indicator data are comparable, and a good data foundation is laid for subsequent water quality deterioration prediction; The construction of the condensate water quality deterioration early warning model group can predict from multiple possible angles that may lead to water quality deterioration, improve the comprehensiveness and accuracy of prediction, and more timely and accurately find signs of water quality deterioration; According to the prediction result, it is determined whether to perform the invalidation time calculation of the mixed bed, and the corresponding measure guidance information is matched and sent to the designated client terminal, which provides clear decision basis and operation guidance for the operating personnel, helps to take measures in a timely manner to cope with water quality deterioration problems, and reduces the risks caused by water quality deterioration. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 A flowchart of the condensate water quality deterioration prediction method provided by the embodiment of the present application is provided. Figure 2 A module block diagram of the condensate water quality deterioration prediction device provided by the embodiment of the present application is provided. DETAILED DESCRIPTION

[0011] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0012] The present invention addresses the problem that deterioration of condensate quality in thermal power plants can easily lead to failure of the mixed bed, thereby causing deterioration of feed water quality, and proposes a method for predicting condensate quality deterioration. The condensate quality deterioration early warning model group of the present invention collects and analyzes data such as condensate conductivity, dissolved oxygen, hardness, sodium ions, and hydrogen conductivity. Based on different water quality deterioration characteristics, it provides feedback on possible causes of condensate quality deterioration and provides an accurate algorithm for the failure time of the mixed bed in the fine treatment system. By providing water quality deterioration factors and mixed bed failure time, it helps operating personnel to promptly check for leaks and eliminate defects in the condensate system to avoid endangering the safety of unit operation due to mixed bed failure. This is explained in detail below through multiple embodiments.

[0013] Example 1: Figure 1 As shown, an embodiment of the present invention provides a method for predicting condensate quality degradation, comprising the following steps: Collecting real-time condensate index data, importing historical condensate index data, and performing data standardization processing on the real-time condensate index data based on the historical condensate index data to obtain standardized condensate data; Constructing a condensate water quality deterioration early warning model group, and performing water quality deterioration prediction on the condensate water standardized data based on the condensate water quality deterioration early warning model group to obtain a prediction result; Determining whether to perform mixed bed failure time calculation according to the prediction result; Matching measure guidance information according to the prediction result, and sending the matched measure guidance information and the calculated mixed bed failure time to a designated client terminal.

[0014] In this embodiment, by standardizing the real-time condensate index data, the differences in dimensions and numerical ranges between different index data can be eliminated, making different types of index data comparable, and laying a good data foundation for subsequent water quality deterioration prediction. Constructing a condensate water quality deterioration early warning model group can predict from multiple angles that may lead to water quality deterioration, improving the comprehensiveness and accuracy of the prediction and enabling more timely and accurate detection of signs of water quality deterioration; Based on the prediction results, it is determined whether to calculate the mixed bed failure time, and the corresponding action guidance information is sent to the designated customer terminal, providing operators with clear decision-making basis and operational guidance, helping to take timely measures to address water quality deterioration and reduce the risks caused by water quality deterioration.

[0015] Preferably, the data standardization processing of the real-time indicator data of the condensate water based on the condensate water historical indicator data obtains condensate water standardized data, including: The data standardization processing of the real-time indicator data of the condensate water based on the standardization formula and the condensate water historical indicator data obtains condensate water standardized data, and the standardization formula is: Wherein, Z is the real-time indicator data of the condensate water, and the real-time indicator data of the condensate water includes the collected hydrogen conductivity C H , conductivity C, sodium ion concentration Na + , dissolved oxygen DO and hardness Hd; Z H-hist is the historical indicator data of the condensate water, and the historical indicator data of the condensate water includes the historical value of hydrogen conductivity C H-hist , the historical value of conductivity C hist , the historical value of sodium ion concentration Na + hist , the historical value of dissolved oxygen DO hist and the historical value of hardness Hd hist , min (ZH-hist) , max(Z H-hist ) represents the extreme value of removing data drift; Z' is the condensate water standardized data, and the condensate water standardized data includes the standardized value of hydrogen conductivity C' H , the standardized value of conductivity C', the standardized value of sodium ion concentration Ba + ', the standardized value of dissolved oxygen DO' and the standardized value of hardness Hd'.

[0016] In the embodiment, the real-time indicator data is standardized processed based on the standardization formula and the historical indicator data of the condensate water, so as to eliminate the dimension influence, make the data processing process more scientific and reasonable, and better reflect the actual characteristics and change trend of the data; Through the combination of the historical data and the standardization formula, the influence of noise and abnormal value in the data can be effectively reduced, the accuracy and reliability of the data are improved, and better data support is provided for subsequent prediction analysis.

[0017] Preferably, the condensate water quality deterioration prediction based on the condensate water quality deterioration early warning model group obtains a prediction result, including: The condensate water quality deterioration early warning model group includes a condenser vacuum system leakage judgment model, a condensate water quality difference judgment model, a closed circulating cooling water leakage judgment model and an open circulating cooling water leakage judgment model, The condensate water standardized data is substituted into the condenser vacuum system leakage judgment model, and if the conditions in the condenser vacuum system leakage judgment model are met: Then the prediction is a condenser vacuum system leakage, wherein C' H is a hydrogen conductivity normalized value, C' is a conductivity normalized value, Na + ' is a sodium ion concentration normalized value, DO' is a dissolved oxygen normalized value, Hd' is a hardness normalized value, ε1, δ1 are set threshold values; The condensate water normalized data is substituted into the condensate water makeup water quality difference judgment model, and if the conditions in the condensate water makeup water quality difference judgment model are met: Then the prediction is a condensate water makeup water quality difference, wherein ε2 is a set threshold value; The condensate water normalized data is substituted into the closed circulation cooling water leakage judgment model, and if the conditions in the closed circulation cooling water leakage judgment model are met: Then the prediction is a closed circulation cooling water leakage, ε3, δ2 are set threshold values; The condensate water normalized data is substituted into the open circulation cooling water leakage judgment model, and if the conditions in the open circulation cooling water leakage judgment model are met: Then the prediction is an open circulation cooling water leakage.

[0018] Table 1 is the principle of the condensate water quality deterioration early warning model group and the corresponding measure guidance information of the prediction result, which can be used to further understand the condensate water quality deterioration early warning model group.

[0019] Table 1 When the prediction result is a condenser vacuum system leakage, the corresponding measure guidance information is: according to DL / T932-2405 “Condenser and Vacuum System Operation and Maintenance Guidelines” to make appropriate treatment.

[0020] When the prediction result is a condensate water makeup water quality difference, the mixed bed failure time is calculated, and the mixed bed failure time is fed back.

[0021] When the prediction result is a closed circulation cooling water leakage into the condensate water system, the mixed bed failure time is calculated, the mixed bed failure time is fed back, and the specific treatment method in GB / T 12145-2016 “Water and Steam Quality Standard for Thermal Power Generating Units and Steam Power Equipment” is given according to the condensate water quality monitoring index.

[0022] When the prediction result is that the open cycle cooling water leaks into the condensate water system, the mixed bed failure time calculation is performed, the mixed bed failure time is fed back, and the specific processing method in GB / T 12145-2016 “Water and steam quality standard for thermal power generating units and steam power equipment” is given according to the condensate water quality monitoring index.

[0023] In the embodiment, the condensate water quality deterioration early warning model group contains multiple judgment models, which can accurately judge the specific reasons for water quality deterioration, such as condenser vacuum system leakage and poor condensate water quality, according to different water quality index changes. Different judgment models correspond to different water quality deterioration reasons, so that the early warning result is more targeted, the operator can quickly locate the problem according to the early warning result, take corresponding solving measures, and improve the efficiency of handling water quality deterioration problems.

[0024] Preferably, the determination of whether to perform mixed bed failure time calculation according to the prediction result comprises: If the prediction result is at least one of poor condensate water quality, closed cycle cooling water leakage and open cycle cooling water leakage, the mixed bed failure parameter calculation is performed through a mixed bed failure time calculation model, the mixed bed failure time calculation model comprises a negative bed failure time calculation formula, a positive bed failure time calculation formula and a mixed bed failure time calculation formula, The negative bed failure time is calculated by the negative bed failure time calculation formula, and the negative bed failure time calculation formula is: Wherein, η1 is the mixed bed negative resin breakthrough coefficient, σ 总进(t) is the total inlet water conductivity of the mixed bed from use to failure, σ 总出(t) is the total outlet water conductivity of the mixed bed from use to failure, σ 用进(t) is the total outlet water conductivity of the mixed bed from use to the present, λ NaCl is the molar conductivity of NaCl, is the molar conductivity of (NH3)2CO3, σ 进 (t) is the current inlet water conductivity of the mixed bed, σ 出 (t) is the current outlet water conductivity of the mixed bed; The negative bed failure time is calculated by the negative bed failure time calculation formula, and the negative bed failure time calculation formula is: Wherein, η2 is the mixed bed positive resin breakthrough coefficient, q is the feed water flow, c 钠 is the instantaneous sodium ion content, pH 总 is the average pH value at the failure of the mixed bed, pH 用 is the average pH value of the mixed bed from operation to the present, pH标 the instantaneous pH value of the mixed bed at present; The mixed bed failure time is calculated by a mixed bed failure time calculation formula: t3 = K1t1 + K2t2, wherein, K1 is a negative resin correction coefficient, and K2 is a positive resin correction coefficient.

[0025] The model incorporates real-time parameters such as conductivity, pH value, ion concentration, etc., and can dynamically adjust the calculation results as the water quality deterioration process progresses. For example, when the circulating cooling water leaks into the condenser, causing a sudden increase in sodium ion concentration, the positive bed failure time calculation formula will shorten the prediction time in real time.

[0026] Taking a seawater cooling unit as an example, when NaCl seeps into the condenser due to leakage, the model accurately quantifies the impact of salt on the resin through the NaCl parameter, reducing the error by more than 40% compared to traditional empirical estimation.

[0027] In this embodiment, through the mixed bed failure time calculation model, including the negative bed failure time calculation formula, the positive bed failure time calculation formula and the mixed bed failure time calculation formula, various factors such as resin breakthrough coefficient, conductivity, pH value, etc. can be considered comprehensively, and the failure time of the mixed bed can be accurately calculated; The accurate mixed bed failure time calculation provides accurate time reference for the operation personnel, so that they can arrange the maintenance and replacement of the mixed bed in advance, avoid the deterioration of the feed water quality caused by the failure of the mixed bed, and ensure the safe and stable operation of the unit.

[0028] In step S5, if the prediction result is at least one of the condensate water quality, the circulating cooling water leakage and the open cooling water leakage, the index deviation of the condensate water real-time index data is calculated by an index deviation formula to obtain the index deviation, and the index deviation formula is: wherein, θ is the index deviation, Z is the condensate water real-time index data, the condensate water real-time index data includes the collected hydrogen conductivity C H , conductivity C, sodium ion concentration Na + , dissolved oxygen DO and hardness Hd, Z H-std is a reference value (usually taking the national standard GB / T12145-2016 or the unit design standard value), the reference value includes the hydrogen conductivity reference value, the conductivity reference value, the sodium ion concentration reference value, the dissolved oxygen reference value and the hardness reference value, If the index deviation θ is greater than the set warning threshold θ', a warning is generated and sent to the designated customer terminal.

[0029] The setting logic of the warning threshold is: Gradual threshold system: Multiple warning thresholds are set based on the impact of water quality indicators on unit safety (e.g., a mild warning threshold of 50% and a severe warning threshold of 100%). For example, if the hydrogen conductivity reference value is 0.15μS / cm, a mild warning is triggered if the real-time value reaches 0.2μS / cm (50% deviation); a severe warning is triggered if it reaches 0.3μS / cm (100% deviation).

[0030] Dynamic correction mechanism: The threshold value can be adaptively adjusted based on historical operating data. For example, if the hydrogen conductivity of a unit remains stable at 0.15μS / cm during long-term operation, the system can dynamically correct the reference value to 0.15μS / cm to avoid false alarms due to differences in equipment characteristics.

[0031] In this embodiment, the deviation of the real-time indicator data of condensate water is calculated by the indicator deviation formula, which can timely discover the degree of deviation between the indicator data and the reference value. When the deviation is greater than the set warning threshold, an early warning is generated and sent, thereby realizing timely discovery of water quality abnormalities.

[0032] Timely warnings enable operators to take measures to address water quality problems before they become serious, thus avoiding further expansion of the problem, reducing the risks of equipment corrosion, unit failure, etc. caused by water quality deterioration, and improving the safety and reliability of the system.

[0033] Example 2: Figure 2 As shown, an embodiment of the present invention further provides a condensate water quality deterioration prediction device, comprising: a data standardization module, configured to collect real-time condensate water index data, import condensate water historical index data, perform data standardization processing on the real-time condensate water index data based on the condensate water historical index data, and obtain condensate water standardized data; a prediction analysis module, configured to construct a condensate water quality deterioration early warning model group, perform water quality deterioration prediction on the condensate water standardized data based on the condensate water quality deterioration early warning model group, obtain a prediction result, and determine whether to perform mixed bed failure time calculation according to the prediction result; The measure guidance module is used to match the measure guidance information according to the prediction result, and send the matched measure guidance information and the calculated mixed bed failure time to a designated client terminal.

[0034] Preferably, the step of performing data standardization on the real-time condensate index data based on the historical condensate index data to obtain standardized condensate data includes: The condensate real-time index data is subjected to data standardization based on a standardization formula and the condensate historical index data to obtain condensate standardized data. The standardization formula is: Among them, Z is the real-time index data of condensed water, which includes the collected hydrogen conductivity CH , conductivity C, sodium ion concentration Na + , dissolved oxygen DO and hardness Hd; Z H-hist is the condensed water historical index data, the condensed water historical index data comprising hydrogen conductivity historical value C H-hist , conductivity historical value C hist , sodium ion concentration historical value Na + hist , dissolved oxygen historical value DO hist and hardness historical value Hd hist , min(Z H-hist ), max(Z H-hist ) represent the extreme values of removing data drift; Z' is the condensed water standardized data, the condensed water standardized data comprising hydrogen conductivity standardized value C' H , conductivity standardized value C', sodium ion concentration standardized value Na + ', dissolved oxygen standardized value DO' and hardness standardized value HD'.

[0035] Preferably, the condensed water quality deterioration early warning model group based on the condensed water quality deterioration prediction of the condensed water standardized data obtains a prediction result, comprising: The condensed water quality deterioration early warning model group comprises a condenser vacuum system leakage judgment model, a condensed water makeup water quality difference judgment model, a closed circulating cooling water leakage judgment model and an open circulating cooling water leakage judgment model, The condensed water standardized data is substituted into the condenser vacuum system leakage judgment model, and if the conditions in the condenser vacuum system leakage judgment model are met: then it is predicted that the condenser vacuum system leaks, wherein C' H is the hydrogen conductivity standardized value, C' is the conductivity standardized value, Na + ' is the sodium ion concentration standardized value, DO' is the dissolved oxygen standardized value, Hd' is the hardness standardized value, and ε1 and δ1 are set threshold values; The condensed water standardized data is substituted into the condensed water makeup water quality difference judgment model, and if the conditions in the condensed water makeup water quality difference judgment model are met: then it is predicted that the condensed water makeup water quality is poor, wherein ε2 is a set threshold value; The condensed water standardized data is substituted into the closed circulating cooling water leakage judgment model, and if the conditions in the closed circulating cooling water leakage judgment model are met: then it is predicted that the circulating cooling water leaks, and ε3 and δ2 are set threshold values; The condensate water standardization data is substituted into the open cooling water leakage judgment model, and if the condition in the open cooling water leakage judgment model is met: then it is predicted that open cooling water leakage occurs.

[0036] Embodiment 3: The embodiment of the present application also provides a condensate water quality deterioration prediction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the condensate water quality deterioration prediction method is realized.

[0037] Embodiment 4: The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the condensate water quality deterioration prediction method is realized.

[0038] The condensate water quality deterioration prediction device and the storage medium described above can refer to the specific description of the condensate water quality deterioration prediction method and the beneficial effects thereof, which will not be repeated here.

[0039] It should be noted that in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0041] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0042] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0043] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0044] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the present application, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and various program codes that can be stored in the medium.

[0045] The above is only the preferred embodiment of the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting condensate water quality deterioration, characterized in that: The steps include: Collecting real-time condensate index data, importing historical condensate index data, and performing data standardization processing on the real-time condensate index data based on the historical condensate index data to obtain standardized condensate data; Constructing a condensate water quality deterioration early warning model group, and performing water quality deterioration prediction on the condensate water standardized data based on the condensate water quality deterioration early warning model group to obtain a prediction result; Determining whether to perform mixed bed failure time calculation according to the prediction result; Matching measure guidance information according to the prediction result, and sending the matched measure guidance information and the calculated mixed bed failure time to a designated client terminal.

2. The method for predicting condensate quality deterioration according to claim 1, characterized in that: The step of performing data standardization processing on the real-time condensate index data based on the historical condensate index data to obtain the standardized condensate data comprises: performing data standardization processing on the real-time condensate index data based on a standardization formula and the historical condensate index data to obtain the standardized condensate data, wherein the standardization formula is: Among them, Z is the real-time index data of condensate water; Z H-hist is the historical index data of condensate water, min(Z H-hist )、max(Z H-hist ) represents the removal of extreme values ​​of data drift; Z′ is the condensate normalized data.

3. The method for predicting condensate quality deterioration according to claim 2, characterized in that: The condensate water quality deterioration early warning model group is used to predict the water quality deterioration of the condensate water standardized data to obtain a prediction result, including: The condensate water quality deterioration early warning model group includes a condenser vacuum system leakage judgment model, a condensate make-up water poor quality judgment model, a closed-circuit cooling water leakage judgment model, and an open-circuit cooling water leakage judgment model. Substitute the condensate standardized data into the condenser vacuum system leakage judgment model. If the conditions in the condenser vacuum system leakage judgment model are met: It is predicted that the condenser vacuum system is leaking, where C′ H is the normalized value of hydrogen conductivity, C′ is the normalized value of conductivity, Na +′ is the normalized value of sodium ion concentration, DO′ is the normalized value of dissolved oxygen, Hd′ is the normalized value of hardness, ε1 and δ1 are the set thresholds; Substitute the condensate water standardization data into the condensate water replenishment water quality poor judgment model. If the conditions in the condensate water replenishment water quality poor judgment model are met: The prediction is that the condensate makeup water quality is poor, where ε2 is the set threshold; Substitute the condensate standardized data into the closed-circuit cooling water leakage judgment model. If the conditions in the closed-circuit cooling water leakage judgment model are met: The prediction is that the closed cycle cooling water leaks in, and ε3 and δ2 are the set thresholds; Substitute the condensate standardized data into the open-circulation cooling water leakage judgment model. If the conditions in the open-circulation cooling water leakage judgment model are met: It is predicted that the open cycle cooling water is leaking.

4. The method for predicting condensate quality deterioration according to claim 3, characterized in that: The determining whether to perform mixed bed failure time calculation according to the prediction result includes: If the prediction result is at least one of the following: poor condensate makeup water quality, closed-loop cooling water leakage, and open-loop cooling water leakage, the mixed bed failure parameters are calculated using a mixed bed failure time calculation model. The mixed bed failure time calculation model includes an anion bed failure time calculation formula, a cation bed failure time calculation formula, and a mixed bed failure time calculation formula. The anion bed failure time calculation formula is used to calculate the anion bed failure time. The anion bed failure time calculation formula is: Among them, η1 is the mixed bed anion resin penetration coefficient, σ 总进(t) is the total influent conductivity of the mixed bed until failure, σ 总出(t) is the total effluent conductivity of the mixed bed from use to failure, σ 用进(t) is the total effluent conductivity of the mixed bed up to the current time, λ NaCl is the molar conductivity of NaCl, is the molar conductivity of (NH3)2CO3, σ 进 (t) is the current influent conductivity of the mixed bed, σ 出 (t) is the current conductivity of the mixed bed outlet water; The failure time of the negative bed is calculated by the positive bed failure time calculation formula, and the positive bed failure time calculation formula is: Among them, η2 is the mixed bed cation resin penetration coefficient, q is the feed water flow rate, c 钠 is the instantaneous content of sodium ions, pH 总 is the average pH value when the mixed bed fails, pH 用 The average pH value of the mixed bed during operation. 标 The mixed bed runs to the current instantaneous pH value; The failure time of the anion bed is calculated by the mixed bed failure time calculation formula, which is: t3=K1t1+K2t2, Among them, K1 is the correction coefficient of anionic resin, and K2 is the correction coefficient of cationic resin.

5. The method for predicting condensate quality deterioration according to claim 3, characterized in that: The method further includes the following steps: if the prediction result is at least one of poor condensate make-up water quality, closed-circuit cooling water leakage, and open-circuit cooling water leakage, the deviation of the condensate real-time index data is calculated using an index deviation formula to obtain an index deviation. The index deviation formula is: Among them, θ is the index deviation, Z is the real-time index data of condensed water, and the real-time index data of condensed water includes the collected hydrogen conductivity C H , conductivity C, sodium ion concentration Na + , dissolved oxygen DO and hardness Hd, Z H-std is a reference value, which includes a hydrogen conductivity reference value, a conductivity reference value, a sodium ion concentration reference value, a dissolved oxygen reference value, and a hardness reference value. If the indicator deviation θ is greater than the set warning threshold θ′, an early warning is generated and sent to the designated customer terminal.

6. A condensate water quality deterioration prediction device, characterized in that: include: a data standardization module for collecting real-time condensate index data and importing historical condensate index data, performing data standardization processing on the real-time condensate index data based on the historical condensate index data to obtain standardized condensate data; a prediction analysis module for constructing a condensate quality deterioration early warning model group, performing water quality deterioration prediction on the standardized condensate data based on the condensate quality deterioration early warning model group to obtain a prediction result, and determining whether to perform mixed bed failure time calculation based on the prediction result; The measure guidance module is used to match the measure guidance information according to the prediction result, and send the matched measure guidance information and the calculated mixed bed failure time to a designated client terminal.

7. The condensate water quality deterioration prediction device according to claim 6, characterized in that: The step of performing data standardization processing on the real-time condensate index data based on the historical condensate index data to obtain the standardized condensate data comprises: performing data standardization processing on the real-time condensate index data based on a standardization formula and the historical condensate index data to obtain the standardized condensate data, wherein the standardization formula is: Among them, Z is the real-time index data of condensed water, which includes the collected hydrogen conductivity C H , conductivity C, sodium ion concentration Na + , dissolved oxygen DO and hardness Hd; Z H-hist Condensate historical index data, including the historical value of hydrogen conductivity C H-hist , conductivity history value C hist , sodium ion concentration historical value Na + hist , dissolved oxygen historical value DO hist and hardness history value Hd hist ,min(Z H-hist )、max(Z H-hist ) represents the extreme value of data drift removal; Z′ is the condensate water standardization data, which includes the hydrogen conductivity standardization value C′ H , conductivity standardization value C', sodium ion concentration standardization value Na +′ , dissolved oxygen standardized value DO′ and hardness standardized value Hd′.

8. The condensate water quality deterioration prediction device according to claim 7, characterized in that: The condensate water quality deterioration early warning model group is used to predict the water quality deterioration of the condensate water standardized data to obtain a prediction result, including: The condensate water quality deterioration early warning model group includes a condenser vacuum system leakage judgment model, a condensate make-up water poor quality judgment model, a closed-circuit cooling water leakage judgment model, and an open-circuit cooling water leakage judgment model. Substitute the condensate standardized data into the condenser vacuum system leakage judgment model. If the conditions in the condenser vacuum system leakage judgment model are met: It is predicted that the condenser vacuum system is leaking, where C′ H is the normalized value of hydrogen conductivity, C′ is the normalized value of conductivity, Na +′ is the normalized value of sodium ion concentration, DO′ is the normalized value of dissolved oxygen, Hd′ is the normalized value of hardness, ε1 and δ1 are the set thresholds; Substitute the condensate water standardization data into the condensate water replenishment water quality poor judgment model. If the conditions in the condensate water replenishment water quality poor judgment model are met: The prediction is that the condensate makeup water quality is poor, where ε2 is the set threshold; Substitute the condensate standardized data into the closed-circuit cooling water leakage judgment model. If the conditions in the closed-circuit cooling water leakage judgment model are met: The prediction is that the closed cycle cooling water leaks in, and ε3 and δ2 are the set thresholds; Substitute the condensate standardized data into the open-circulation cooling water leakage judgment model. If the conditions in the open-circulation cooling water leakage judgment model are met: It is predicted that the open cycle cooling water is leaking.

9. A device for predicting condensate quality deterioration, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for predicting condensate quality deterioration according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for predicting condensate quality degradation according to any one of claims 1 to 5 is implemented.

Images