Thermal power plant circulating cooling water treatment optimization method and system based on big data analysis

Abstract

The invention discloses a thermal power plant circulating cooling water treatment optimization method and system based on big data analysis, relates to the technical field of cooling water treatment optimization, and aims to solve the problem that the actual operation state of a cooling water system cannot be comprehensively reflected. The method comprises the following steps: acquiring oxidation-reduction potential, biological membrane thickness and pressure difference in real time, setting acquisition time, acquiring inlet and outlet temperature data, calculating temperature variation, generating efficiency-increasing driving characteristics by combining the oxidation-reduction potential, analyzing efficiency-increasing inhibition characteristics by fusing the biological membrane thickness and pressure difference, and judging whether to generate a driving signal based on the efficiency-increasing driving characteristics; after a driving signal is generated, fluorine ion concentration is detected to judge water quality, organic carbon concentration is collected, and a conventional or adaptive control strategy is selected in combination with water quality conditions; and when the adaptive control strategy is started, the efficiency improvement optimization time is set, the chloride ion concentration is monitored in real time, the change trend is calculated to judge whether to terminate the efficiency improvement operation, the cooling efficiency is remarkably improved, and corrosion and scaling are reduced.

Description

Technical Field

[0001] This invention relates to the field of cooling water treatment optimization technology, and more specifically, to a method and system for optimizing circulating cooling water treatment in thermal power plants based on big data analysis. Background Technology

[0002] The circulating cooling water system is a crucial component of energy conversion and equipment safety operation in thermal power plants. Its primary function is to cool the turbine condenser and related equipment, ensuring the unit operates safely and efficiently. With the continuous increase in the scale of thermal power units, circulating cooling water systems face multiple challenges, including water pollution, biofilm adhesion, and decreased heat exchange efficiency. During the circulating evaporation process, the cooling water continuously concentrates salts, suspended solids, and microbial metabolic products, leading not only to reduced system efficiency and increased operating energy consumption, but also to excessive pollutant concentrations in regularly discharged wastewater, increasing the treatment load and costs of the plant's wastewater treatment system. Furthermore, the long-term accumulation of these problems can trigger equipment corrosion and unplanned shutdowns, further impacting the coordinated and stable operation of the wastewater treatment process and the cooling system.

[0003] The existing technology has the following shortcomings: Currently, existing technologies typically employ chemical dosing (such as corrosion inhibitors and biocides), physical cleaning, and periodic blowdown to control cooling water systems. However, these methods rely on fixed-time strategies. On one hand, they lack real-time monitoring and response mechanisms for the cooling water's operating status, making it difficult to achieve precise control under dynamic operating conditions. This results in problems only being discovered after a significant drop in heat exchange efficiency, missing the optimal opportunity for intervention and failing to fully reflect the actual operating status of the cooling water system. On the other hand, fixed-cycle blowdown patterns cannot dynamically adjust discharge volumes based on water quality, easily leading to water waste or insufficient blowdown volume. This allows wastewater exceeding standards to enter the wastewater treatment system, exceeding its conventional treatment capacity and affecting the compliance of wastewater treatment with discharge standards. In some cases, untreated wastewater may even backfire and pollute the circulating cooling water system. Therefore, this paper proposes an optimization method and system for circulating cooling water treatment in thermal power plants based on big data analysis. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an optimization method and system for circulating cooling water treatment in thermal power plants based on big data analysis. This method addresses the problems mentioned in the background art by employing multi-parameter fusion monitoring and modeling, intelligent extraction of efficiency-enhancing features, dynamic control strategy switching, and water quality trend discrimination algorithms.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an optimization method for circulating cooling water treatment in thermal power plants based on big data analysis, comprising the following steps: Step S1: Monitor the cooling water system, collect the redox potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger in real time, set the collection time, collect the temperature data of the cooling water inlet and outlet during the collection time, and calculate the temperature change based on the temperature data. Step S2: Based on the temperature change and the redox potential of the cooling water, generate the efficiency improvement driving characteristics, analyze the efficiency improvement inhibition characteristics by combining the biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger, and determine whether to generate a driving signal by combining the efficiency improvement driving characteristics. Step S3: After generating the drive signal, detect the fluoride ion concentration of the cooling water to determine the water quality conditions, collect the organic carbon concentration of the cooling water, and select to start the conventional control strategy or the adaptive control strategy based on the water quality conditions. Step S4: When starting the adaptive control strategy, set the efficiency improvement optimization time, monitor the chloride ion concentration of the cooling water in real time, calculate the chloride ion concentration change trend, and determine whether to stop the efficiency improvement operation based on the chloride ion concentration change trend.

[0006] In a preferred embodiment, in step S1, the redox potential of the cooling water is measured in real time using a redox potential sensor; The ultrasonic signal is emitted to the heat exchange surface of the heat exchanger by an ultrasonic sensor, and the propagation time of the ultrasonic signal is obtained. The thickness of the biofilm on the surface of the heat exchanger is calculated based on the ultrasonic signal propagation time and the preset ultrasonic propagation speed. The pressure values ​​of the inlet and outlet pipes of the heat exchanger are measured by a pressure sensor, and the absolute value of the difference is taken as the pressure difference of the heat exchanger.

[0007] In a preferred embodiment, in step S1, a preset acquisition time is set, and the temperature data of the cooling water inlet and outlet are monitored at the start and end times of the acquisition time by a temperature sensor. The initial temperature difference is obtained by subtracting the cooling water inlet temperature data from the outlet temperature data at the beginning and taking the absolute value. The temperature difference at the end time is obtained by subtracting the cooling water inlet temperature data and outlet temperature data at the end time and taking the absolute value. The absolute value of the difference between the initial temperature difference and the final temperature difference is taken as the temperature change.

[0008] In a preferred embodiment, in step S2, the logarithm of the biofilm thickness on the heat exchanger surface plus 1 is used as the biofilm thickness coefficient, and the logarithm of the redox potential of the cooling water plus 1 is used as the redox potential coefficient. The maximum value of temperature change and the maximum value of heat exchanger pressure difference are retrieved from historical data in the cooling water database. The ratio of the temperature change incremented by 1 to the maximum temperature change is used as the temperature influence parameter, and the ratio of the heat exchanger pressure difference incremented by 1 to the maximum heat exchanger pressure difference is used as the pressure difference influence parameter.

[0009] In a preferred embodiment, in step S2, 1 is subtracted from the temperature effect parameter and the redox potential coefficient respectively, and the results of the subtraction are multiplied to obtain the efficiency improvement driving feature; The product of the biofilm thickness coefficient and the pressure difference effect parameter is used as the efficiency-inhibiting characteristic; The net efficiency improvement driving value is obtained by subtracting the efficiency improvement driving feature from the efficiency improvement inhibition feature. The net efficiency improvement driving value is then compared with a preset driving threshold to determine whether to generate a driving signal. If the net efficiency improvement driving value exceeds the driving threshold, a driving signal is generated; Conversely, no drive signal is generated.

[0010] In a preferred embodiment, in step S3, after the driving signal is generated, the free fluoride ion content in the cooling water is electrochemically responded to by an ion-selective electrode sensor, and the fluoride ion concentration is calculated based on the Nernst equation. The fluoride ion concentration is fuzzified, and fuzzy sets are defined as low, medium, and high. Based on the threshold range and gradient set by experience, the first layer of fuzzy rule base is established to infer the water quality conditions of the cooling water, which include good, medium, and poor.

[0011] In a preferred embodiment, in step S3, all organic carbon elements in the water sample are measured using a high-temperature catalytic combustion-non-dispersive infrared detection method with an organic carbon analyzer, and the total organic carbon mass concentration value is output as the organic carbon concentration. The organic carbon concentration is fuzzified, and the fuzzy sets are defined as low, medium, and high. The water quality conditions and organic carbon concentration are jointly input into the second-layer fuzzy inference model. The control strategy is determined through the rule base, and the output set includes conventional control strategies and adaptive control strategies. The fuzzy membership set of the output control strategy is inferred using the Mamdani-type inference method and the maximum-minimum synthesis method. The centroid method is then used for defuzzification to obtain the output value of the control strategy.

[0012] In a preferred embodiment, in step S4, if the output value of the control strategy is less than or equal to a preset strategy judgment threshold, then the normal control strategy is activated. If the output value of the control strategy is greater than the strategy judgment threshold, the adaptive control strategy will be activated. After activating the adaptation control strategy, set the efficiency improvement and optimization time; During the efficiency improvement and optimization period, the chloride ion concentration in the cooling water was detected by an ion-selective electrode sensor at a fixed sampling interval.

[0013] In a preferred embodiment, in step S4, the initial and final measured values ​​of chloride ion concentration are recorded using the first-order difference method within the efficiency improvement and optimization time period; the final measured value is subtracted from the initial measured value and divided by the duration of the efficiency improvement and optimization time to obtain the trend of chloride ion concentration change. If the chloride ion concentration change trend is less than the preset concentration growth threshold, it is determined that the efficiency improvement process has achieved the target effect, the efficiency improvement operation is stopped, and the steady-state control stage is entered. If the chloride ion concentration change trend is greater than or equal to the concentration growth threshold, the efficiency improvement process has not achieved the target effect, and the efficiency improvement operation should continue.

[0014] The big data analytics-based optimization system for circulating cooling water treatment in thermal power plants includes a data acquisition and monitoring module, a signal determination module, a strategy selection module, and an efficiency improvement termination module. The functions of each module are as follows: The data acquisition and monitoring module monitors the cooling water system, collecting data in real time on the oxidation-reduction potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger. The acquisition time is set, and the temperature data of the cooling water inlet and outlet are collected within the acquisition time. The temperature change is calculated based on the temperature data. The signal determination module generates efficiency-enhancing driving characteristics based on temperature changes and the redox potential of cooling water, analyzes efficiency-enhancing inhibition characteristics by combining the biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger, and determines whether to generate a driving signal based on the efficiency-enhancing driving characteristics. After the strategy selection module generates the drive signal, it detects the fluoride ion concentration of the cooling water to determine the water quality conditions, collects the organic carbon concentration of the cooling water, and selects to start the conventional control strategy or the adaptive control strategy based on the water quality conditions. When the efficiency improvement termination module starts the adaptation control strategy, it sets the efficiency improvement optimization time, monitors the chloride ion concentration of the cooling water in real time, calculates the chloride ion concentration change trend, and determines whether to stop the efficiency improvement operation based on the chloride ion concentration change trend.

[0015] The technical effects and advantages of this invention are as follows: This invention monitors the cooling water system, collecting real-time data on the redox potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger. A data collection time is set, and temperature data at the cooling water inlet and outlet are collected within this time. Temperature changes are calculated based on the temperature data. The redox potential of the cooling water is used to generate efficiency-enhancing driving characteristics, while the biofilm thickness on the heat exchanger surface and the pressure difference are used to analyze efficiency-enhancing inhibition characteristics. The efficiency-enhancing driving characteristics are combined to determine whether a driving signal is generated. Once a driving signal is generated, the fluoride ion concentration in the cooling water is detected to assess water quality conditions. The organic carbon concentration in the cooling water is also collected. Based on the water quality conditions, a conventional control strategy or an adaptive control strategy is selected. When the adaptive control strategy is activated, an efficiency-enhancing optimization time is set, and the chloride ion concentration in the cooling water is monitored in real-time to calculate the chloride ion concentration trend. Based on the chloride ion concentration trend, it is determined whether to stop the efficiency-enhancing operation. This significantly improves cooling efficiency, reduces the risk of corrosion and scaling, and achieves dynamic sensing of the circulating cooling water treatment process. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method for optimizing the treatment of circulating cooling water in thermal power plants based on big data analysis, as described in this invention.

[0017] Figure 2 This is a schematic diagram of the modules of the thermal power plant circulating cooling water treatment optimization system based on big data analysis according to the present invention. Detailed Implementation

[0018] 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 embodiments of the present invention, and not all embodiments. 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.

[0019] This invention monitors the cooling water system, collecting real-time data on the redox potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger. A data collection time is set, during which temperature data at the cooling water inlet and outlet is collected. Temperature changes are calculated based on the temperature data. The redox potential of the cooling water is used to generate efficiency-enhancing driving characteristics. The biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger are used to analyze efficiency-enhancing inhibition characteristics. The efficiency-enhancing driving characteristics are combined to determine whether a driving signal is generated. Once a driving signal is generated, the fluoride ion concentration of the cooling water is detected to determine water quality conditions. The organic carbon concentration of the cooling water is also collected. Based on the water quality conditions, a conventional control strategy or an adaptive control strategy is selected. When the adaptive control strategy is activated, an efficiency-enhancing optimization time is set. The chloride ion concentration of the cooling water is monitored in real-time, and the chloride ion concentration change trend is calculated. Based on the chloride ion concentration change trend, it is determined whether to stop the efficiency-enhancing operation, significantly improving cooling efficiency and reducing the risk of corrosion and scaling.

[0020] Example 1: An optimization method for circulating cooling water treatment in thermal power plants based on big data analysis, such as... Figure 1 As shown, it includes the following steps: Step S1: Monitor the cooling water system, collect the redox potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger in real time, set the collection time, collect the temperature data of the cooling water inlet and outlet during the collection time, and calculate the temperature change based on the temperature data. Step S2: Based on the temperature change and the redox potential of the cooling water, generate the efficiency improvement driving characteristics, analyze the efficiency improvement inhibition characteristics by combining the biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger, and determine whether to generate a driving signal by combining the efficiency improvement driving characteristics. Step S3: After generating the drive signal, detect the fluoride ion concentration of the cooling water to determine the water quality conditions, collect the organic carbon concentration of the cooling water, and select to start the conventional control strategy or the adaptive control strategy based on the water quality conditions. Step S4: When starting the adaptive control strategy, set the efficiency improvement optimization time, monitor the chloride ion concentration of the cooling water in real time, calculate the chloride ion concentration change trend, and determine whether to stop the efficiency improvement operation based on the chloride ion concentration change trend.

[0021] The specific implementation is as follows: In step S1, the cooling water system is monitored, including monitoring the redox potential of the cooling water, the biofilm thickness on the heat exchanger surface, the pressure difference of the heat exchanger, and the temperature data of the cooling water inlet and outlet. The oxidation-reduction potential of cooling water is measured in real time by an oxidation-reduction potential sensor to reflect the oxidation-reduction environment of the cooling water and to determine the growth conditions of microorganisms and the effectiveness of bactericides. An ultrasonic signal is emitted by an ultrasonic sensor and penetrates the heat exchange surface of the heat exchanger. The ultrasonic signal is reflected at the interface between the biofilm on the heat exchanger surface and the heat exchange surface. The ultrasonic receiving probe is fixed to the surface of the heat exchanger shell. The ultrasonic signal propagation time is obtained by the signal processing unit. Since the ultrasonic signal propagates back and forth on the heat exchange surface, the ultrasonic signal propagation time is divided by 2 to obtain the one-way propagation time. The product of the one-way propagation time and the preset ultrasonic signal propagation speed is used as the biofilm thickness on the heat exchanger surface. The larger the biofilm thickness on the heat exchanger surface, the lower the heat exchange efficiency of the heat exchanger. It should be explained that an ultrasonic sensing device is a sensing system that uses the propagation characteristics of ultrasonic signals in different media to perform non-contact measurement of the thickness of an object. An ultrasonic sensing device includes an ultrasonic transmitting probe, an ultrasonic receiving probe, a signal processing unit, and a data acquisition terminal; the preset ultrasonic signal propagation speed is a reference value of the ultrasonic signal propagation speed in water medium, which is determined by professionals based on standard physical parameters or environmental measurement results. Pressure sensors are installed at the inlet and outlet pipes of the heat exchanger to measure the pressure values ​​at both ends in real time. The absolute value of the difference between the two pressure values ​​is taken as the pressure difference of the heat exchanger. The data collection time is preset, and the temperature data of the cooling water inlet and outlet are monitored at the start and end of the collection time by temperature sensors. The temperature difference at the start time is obtained by subtracting the cooling water inlet temperature data from the outlet temperature data and taking the absolute value. The temperature difference at the end time is obtained by subtracting the cooling water inlet temperature data from the outlet temperature data and taking the absolute value. The absolute value of the difference between the initial temperature difference and the final temperature difference is taken as the temperature change. The smaller the difference in temperature change, the lower the heat exchange performance of the heat exchanger.

[0022] It should be noted that the cooling water system is a circulating water system used to remove heat in industrial production and equipment operation. It absorbs heat generated by the equipment through cooling water and then releases the heat into the environment through a heat exchanger, achieving effective heat transfer and dissipation. The oxidation-reduction potential sensor is based on the principle of electrode electrochemical reaction, reflecting the oxidation-reduction state of the water by measuring the potential difference between electrodes. The pressure sensor is a sensing device used to measure the pressure of media such as liquids, gases, or steam; in this example, it is used to collect the pressure values ​​of the inlet and outlet pipes of the heat exchanger. The preset acquisition time refers to the time window set by professionals monitoring the inlet and outlet temperature data of the cooling water. The temperature sensor is a device that converts temperature changes into measurable electrical signals, used to measure the temperature data of the cooling water inlet and outlet.

[0023] In step S2, the biofilm thickness on the heat exchanger surface and the redox potential of the cooling water are each incremented by 1, and then dimensionless processing is achieved by logarithmic standardization. The logarithm of the biofilm thickness on the heat exchanger surface after incrementing by 1 is used as the biofilm thickness coefficient, and the logarithm of the redox potential of the cooling water after incrementing by 1 is used as the redox potential coefficient. Specifically, the physical meaning of adding 1 is to avoid calculation anomalies caused by the presence of zero or near-zero values ​​in the original monitoring data, so that the parameters remain continuous, distinguishable and have stable mathematical processing conditions within the overall range. The physical meaning of logarithmic transformation is to transform the magnitude of the original absolute dimension into a relative scale that reflects its growth rate or intensity of change, so that biofilm growth and redox environment changes can be compared and analyzed in a unified response scale, making it suitable as a robust feature input for system state evaluation. The maximum value of temperature change and the maximum value of heat exchanger pressure difference are retrieved from the historical data of the cooling water database. The ratio of the temperature change plus 1 to the maximum value of temperature change is used as the temperature influence parameter, and the ratio of the heat exchanger pressure difference plus 1 to the maximum value of heat exchanger pressure difference is used as the pressure difference influence parameter. Furthermore, the physical meaning of adding 1 is to ensure that when the temperature and pressure difference are in a low range or fluctuate slightly, they can still be effectively captured by the system and not be regarded as having zero impact; the physical meaning of maximum value normalization is to use historical extreme values ​​as a benchmark to map the current monitoring status to relative levels such as close to normal operation, slight deviation, significant deviation, and approaching extreme values, thereby forming a scaled expression that can reflect the degree of operational deviation and supporting a unified comparison between real-time operational status and long-term operational statistics. The smaller the temperature-affected parameter, the worse the heat exchange performance. The heat exchange performance can be optimized through efficiency control. The smaller the oxidation-reduction potential coefficient, the worse the sterilization ability of the cooling water, which further affects the heat exchange performance. The cooling water system can be restored to normal state through efficiency control. By analyzing the temperature-affected parameter and the oxidation-reduction potential coefficient to generate efficiency-driving characteristics, it can be determined whether to implement efficiency control for the cooling water.

[0024] Furthermore, the combination of temperature-related parameters and redox potential coefficients can comprehensively reflect the performance degradation trend of the heat exchanger and the deterioration trend of the cooling water quality. When the temperature side shows a significant decrease in heat exchange efficiency, and the water quality side shows a weakening of the oxidizing environment, the resulting efficiency improvement driving characteristics can present a combined state of "performance degradation trend plus water quality deterioration trend" in the system, which can be used to determine whether it is necessary to perform efficiency improvement operations. A larger biofilm thickness coefficient indicates a greater amount of biofouling on the heat exchanger surface, posing a risk of blockage. If efficiency-enhancing control operations are performed, the biofilm may not detach completely, leading to local blockage or increased corrosion of the heat exchange surface. A larger pressure difference parameter indicates a risk of obstructed cooling water flow or local blockage of channels. If efficiency-enhancing control operations are performed, the reagent may remain in local areas or the equipment may be overloaded due to a sudden increase in local flow velocity, posing a potential risk of equipment damage or unstable operation. Both the biofilm thickness coefficient and the pressure difference parameter are positively correlated with the efficiency-enhancing inhibition characteristics. By generating efficiency-enhancing inhibition characteristics through the biofilm thickness coefficient and pressure difference parameter, it is possible to determine whether to perform efficiency-enhancing operations on the cooling water. It should be noted that both of the above parameters have strong structural safety attributes: the larger the biofilm thickness coefficient, the greater the fouling on the heat exchange surface and the more concentrated the structural load; the larger the pressure difference influence parameter, the more it indicates that the water flow is restricted and the risk of local flow velocity distortion increases. Therefore, improving efficiency may lead to secondary blockage, local erosion, or local accumulation of chemical agents. Therefore, the inhibition feature is used to identify the risks that make it unsuitable to carry out efficiency improvement in the current state, making control decisions safer and more reliable. The difference between 1 and the temperature effect parameter and the redox potential coefficient is multiplied together to obtain the efficiency improvement driving characteristic. The product of the biofilm thickness coefficient and the pressure difference effect parameter is used as the efficiency inhibition characteristic.

[0025] Among them, the above difference calculation can be used to characterize the remaining improvement space of system performance degradation. That is, when the temperature influence parameter and redox potential coefficient are low, it reflects that the system is in a significant performance degradation range, and the result formed by the difference can measure the degree of improvement that can be achieved through efficiency improvement. In contrast, the product of the inhibition characteristics can characterize the risk intensity that may hinder the implementation of efficiency improvement in the system structure or flow state. The relative measurement of the two can form the net efficiency improvement driving value, which is used to identify whether there is still a rationality to implement efficiency improvement under the premise of ensuring safety. It should be explained that the monitored quantities such as biofilm growth thickness, redox potential, temperature change, and heat exchanger pressure difference not only have different dimensions, but their numerical distributions also exhibit nonlinearity and differences across orders of magnitude. To ensure that these heterogeneous parameters can be uniformly processed within the same evaluation model, this application does not intend to achieve statistical standardization with a mean of 0 and a standard deviation of 1. Instead, it maps the original physical quantities to a unified response scale through steps such as adding 1, taking the logarithm, and normalizing the maximum value.

[0026] Among them, the addition of 1 is used to avoid the infeasibility of calculation in logarithmic operations caused by zero or extremely low values, and to ensure that the low range of change is still calculable; the logarithmic transformation is used to compress the order of magnitude difference between different physical quantities, so that their change trend is presented in a way of relative intensity; the maximum value normalization uses the historical extreme value of long-term statistics as a reference to convert the current monitoring quantity into a dimensionless proportion of "relative deviation degree".

[0027] Through the above scaling process, although the monitoring parameters do not meet the strict standardization conditions in a mathematical and statistical sense, they have been mapped to the same comparable response range, enabling them to participate in the determination of operating status in a unified analysis model, thereby achieving the goal of comprehensive evaluation of multi-source information of the cooling water system.

[0028] The net efficiency improvement driving value is obtained by subtracting the efficiency improvement driving feature from the efficiency improvement inhibition feature. The net efficiency improvement driving value is then compared with a preset driving threshold to determine whether to generate a driving signal. If the net efficiency improvement driving value exceeds the driving threshold, a driving signal is generated; Conversely, no drive signal is generated.

[0029] Specifically, a net efficiency improvement driving value greater than the threshold means that the system is currently in an operating window where heat exchange performance has declined significantly, but the structure and flow state are still within an acceptable range. If the threshold is not reached, it means that the performance has not declined to the point where efficiency improvement is required or the risk level is high, and it is not advisable to improve efficiency at this time. This mechanism can ensure that efficiency improvement operations are both necessary and feasible. It should be noted that the cooling water database is an integrated database platform used to store real-time monitoring data and historical data of the cooling water system. In this example, it is used to obtain the maximum value of temperature change and the maximum value of heat exchanger pressure difference in the historical data. The preset drive threshold is a value set by professionals based on experience or experimental data to determine whether the current state of the system meets the conditions for triggering efficiency improvement control.

[0030] In step S3, after the driving signal is generated, the concentration of fluoride ions in the circulating cooling water is detected. The free fluoride ion content in the cooling water is electrochemically responded to by an ion-selective electrode sensor installed in the cooling water pipeline, and the fluoride ion concentration is calculated based on the Nernst equation.

[0031] Fluoride ions are non-metallic anions that reflect possible abnormal water quality conditions in cooling water systems, including fluctuations in water sources, abnormal addition of chemical agents, and equipment seal leaks. The fluoride ion concentration is fuzzified by defining fuzzy sets as low, medium, and high, and quantified using triangular membership functions. Based on the set threshold range, a first-layer fuzzy rule base is established.

[0032] The threshold range is determined in this embodiment by the frequency distribution curve of fluoride ion concentration in historical operating data and industry limit standards, and will not be elaborated here.

[0033] The cooling water quality conditions are derived from the first-layer fuzzy rule base. The fuzzy set includes good, medium, and poor. Examples of fuzzy rules are as follows: If the fluoride ion concentration is low, the water quality is good. If the fluoride ion concentration is medium, then the water quality conditions are medium. If the fluoride ion concentration is high, the water quality is poor. By calculating the membership degree and using the maximum-minimum synthesis method, the membership degree of each fuzzy output item is obtained. Then, the centroid method is used for defuzzification to obtain the water quality condition score with a value range of [0,1]. The water quality condition is determined based on the water quality judgment range.

[0034] In this embodiment, the water quality determination interval uses the three-part method to set the boundary value, which corresponds to the center point of the fuzzy set. It can be adjusted based on the frequency distribution statistics of historical data during the operation of the cooling system and the industrial cooling water control limit in the published standard.

[0035] It should be noted that an ion-selective electrode sensor is an electrochemical sensing device built on the principle of ion-selective membranes. Its core structure includes a membrane material that has the ability to selectively respond to specific ions. The Nernst equation is a fundamental electrochemical formula that describes the relationship between the reversible electrode potential and the activity of ions participating in the electrode reaction. In the test solution, the target ion crosses the electrode membrane and establishes a potential difference with the reference solution inside the electrode. This potential difference has a logarithmic relationship with the activity of the target ion in the solution, which conforms to the Nernst equation and can be used to calculate the concentration value of the target ion.

[0036] After determining the water quality conditions by fluoride ion concentration, the organic carbon concentration in the cooling water was further collected. The organic carbon elements in the water sample were measured by an organic carbon analyzer using a high-temperature catalytic combustion-non-dispersive infrared detection method. The total organic carbon mass concentration value was output as the organic carbon concentration. The organic carbon concentration reflects the organic matter load level in the water and is associated with the microbial growth potential, biofilm formation risk, and chemical agent consumption. The organic carbon concentration was fuzzified and its fuzzy set was defined as low, medium, and high.

[0037] It should be noted that an organic carbon analyzer is an instrument used to detect the total organic carbon content in water samples. It calculates the organic carbon concentration by completely oxidizing the carbon elements in the organic components of the water sample into carbon dioxide and measuring the amount of carbon dioxide generated. The high-temperature catalytic combustion-non-dispersive infrared detection method is a composite analytical method for measuring organic carbon, which includes a high-temperature catalytic combustion process and a non-dispersive infrared detection process. It is widely used in organic carbon analyzers.

[0038] The water quality conditions derived from fluoride ion concentration and organic carbon concentration are jointly input into the second-layer fuzzy inference model. The control strategy is determined through a rule base, and the output set includes conventional control strategies and adaptive control strategies. An example of the fuzzy rules is as follows: If the water quality is good and the organic carbon concentration is low, then the control strategy is the conventional control strategy. If the water quality conditions are moderate and the organic carbon concentration is moderate, then the control strategy is the conventional control strategy. If the water quality is poor and the organic carbon concentration is high, then the control strategy is the adaptive control strategy. If the water quality is medium and the organic carbon concentration is high, then the control strategy is an adaptive control strategy.

[0039] In the fuzzy inference process, the Mamdani-type inference method and the maximum-minimum synthesis method are used to infer the fuzzy membership set of the output control strategy. The centroid method is used for defuzzification to obtain the control strategy output value with a value range of [0,1].

[0040] A policy decision threshold is set. In this embodiment, the policy decision threshold is set to the median value of the fuzzy output, which can be dynamically set through historical running data and optimized training.

[0041] If the output value of the control strategy is less than or equal to the strategy judgment threshold, the normal control strategy is activated; if the output value of the control strategy is greater than the strategy judgment threshold, the adaptive control strategy is activated.

[0042] Furthermore, to enable those skilled in the art to clearly understand the specific implementation of adaptive control, this embodiment provides the execution logic and parameter adjustment method of adaptive control after the second-layer fuzzy inference outputs the control strategy. Adaptive control is not an abstract enhancement control, but rather dynamically adjusts operating parameters such as reagent dosage, flushing cycle, and circulation ratio based on the water quality condition score and the fuzzy quantification result of organic carbon concentration. Specifically, adaptive control uses the control strategy output value Cs∈[0,1] as the adjustment factor and constructs parameter adjustment coefficients;

[0043] in, To adapt the scaling factor, Based on the basic compensation coefficient (set by calling historical operating data, which will not be elaborated here), the parameter adjustment coefficient is obtained. Taking the dosage of the drug as an example, the dosage under adaptive control is:

[0044] in, This is the base dosage under conventional control strategies. To adapt to controlled drug dosage, This is the magnification factor. The larger the value, the greater the increase in drug dosage;

[0045] In the formula, To adapt to the controlled rinsing cycle, Basic flushing cycle, To shorten the coefficient, The larger the denominator, the larger the value. The smaller the value, the more frequent the flushing. In other words, the worse the water quality and the more the control strategy output is biased towards adaptive control, the shorter the flushing cycle will be. For the circulation ratio, the discharge ratio is increased through adaptive control, and its dynamic setting formula is as follows: ; in, This is the scaling factor (determined by engineering experience and operational optimization, and will not be elaborated here). To adapt to the cycle ratio under control, Based on the basic cycle ratio, As an incremental item, it is used to increase the proportion of sewage discharge and accelerate system renewal when water quality deteriorates. That is, the worse the water quality, the larger the increment, the higher the circulation rate, and the enhanced control capability. Through the above parameterized formula, those skilled in the art can directly calculate and execute the corresponding adaptive control measures based on the control strategy output value obtained by fuzzy reasoning. The dynamic control process under the scenario of significant water quality fluctuation can be realized without relying on experience judgment. Therefore, the adaptive control of this embodiment has clear input, reasoning logic, computable parameters and actual execution actions, ensuring that those skilled in the art can reproduce it accordingly. No further details are provided here. The conventional control strategy maintains the stability of the cooling water system by setting basic operating parameters. Under the conventional control strategy, the efficiency optimization judgment process based on the chloride ion concentration change trend is not initiated, avoiding system disturbances caused by unnecessary adjustment operations, thereby minimizing resource consumption and maintaining steady-state operation control.

[0046] The above process, by establishing a multi-level fuzzy inference model based on water quality factors, realizes comprehensive intelligent evaluation of water quality conditions and selection of flexible control strategies, thereby improving the response capability of the circulating cooling water system to complex water quality fluctuations and the accuracy of efficiency control.

[0047] It should be noted that the triangular membership function is a commonly used fuzzy membership function, used to represent the degree of membership of an element in a fuzzy set to a certain semantic label; the Mamdani-type inference method is a widely used fuzzy rule inference method, the core of which is to perform fuzzy mapping and fuzzy output on the input membership based on the rule set; the maximum-minimum synthesis method is a logical operation method in fuzzy inference used to synthesize the relationship between multiple rule premises and conclusions, the core idea of ​​which is to use the minimum value operation to represent the rule matching strength and the maximum value operation to aggregate multiple rule results; the centroid method is a commonly used defuzzification technique, which uses the centroid position of the fuzzy output function graph to represent the precise value of the output variable, and is used to convert the fuzzy output set into a single precise numerical result, which will not be elaborated here.

[0048] In step S4, after the adaptive control strategy is started, the efficiency improvement optimization time is set, which represents the maximum duration for the adaptive control strategy to be executed continuously. The specific value is set as the ratio of cooling water volume to cooling water circulation flow rate plus the response lag time. The cooling water volume, cooling water circulation flow rate and response lag time are obtained based on engineering design documents and experimental measurements.

[0049] During the efficiency improvement and optimization period, the chloride ion concentration in the circulating cooling water is continuously measured at fixed sampling intervals. The free chloride ion content is electrochemically responded to by an ion-selective electrode sensor, and the chloride ion concentration is calculated based on the Nernst equation.

[0050] Chloride ion concentration reflects the level of inorganic salt accumulation or corrosion byproduct release in cooling water. To analyze the concentration change trend, the first-order difference method is used to calculate the average rate of change of chloride ion concentration as the chloride ion concentration change trend. Specifically, within the set efficiency improvement and optimization time period, the initial and final measured values ​​of chloride ion concentration are recorded. The initial measured value refers to the chloride ion concentration collected at the beginning of the efficiency improvement and optimization time, and the final measured value refers to the chloride ion concentration collected at the end of the efficiency improvement and optimization time. The final measured value is subtracted from the initial measured value and divided by the duration of the efficiency improvement and optimization time to obtain the chloride ion concentration change trend.

[0051] It should be noted that the first-order difference method refers to a method that characterizes the rate or trend of change of a variable over time by calculating the difference between the values ​​of two adjacent time points in a discrete time series. In this embodiment, it is used to evaluate the change range of the target ion concentration in cooling water within a specified time interval.

[0052] A preset concentration growth threshold is set to indicate whether the chloride ion concentration has achieved the target effect during the efficiency improvement process. The threshold is set based on the chloride ion concentration increase rate data under successful conditions in the historical efficiency improvement process, and the average value is taken as the concentration growth threshold. If the average rate of change is less than the concentration growth threshold, it is determined that the efficiency improvement process has achieved the target effect, the efficiency improvement operation is stopped, and the steady-state control stage is entered. If the average rate of change is greater than or equal to the concentration growth threshold, the efficiency improvement process has not achieved the target effect, and the efficiency improvement operation should continue.

[0053] By using an efficiency improvement judgment mechanism based on the trend of chloride ion concentration changes, the impact of the efficiency improvement control process on the cooling water quality can be fed back in real time, ensuring that the control strategy not only improves efficiency but also does not cause secondary problems such as equipment corrosion, thereby improving the dynamic adaptability and operational safety of the control strategy.

[0054] Example 2: Optimization system for circulating cooling water treatment in thermal power plants based on big data analysis, such as... Figure 2 As shown, it includes a data acquisition and monitoring module, a signal determination module, a strategy selection module, and an efficiency improvement and termination module. The functions of each module are as follows: The data acquisition and monitoring module monitors the cooling water system, collecting data in real time on the oxidation-reduction potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger. The acquisition time is set, and the temperature data of the cooling water inlet and outlet are collected within the acquisition time. The temperature change is calculated based on the temperature data. The signal determination module generates efficiency-enhancing driving characteristics based on temperature changes and the redox potential of cooling water, analyzes efficiency-enhancing inhibition characteristics by combining the biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger, and determines whether to generate a driving signal based on the efficiency-enhancing driving characteristics. After the strategy selection module generates the drive signal, it detects the fluoride ion concentration of the cooling water to determine the water quality conditions, collects the organic carbon concentration of the cooling water, and selects to start the conventional control strategy or the adaptive control strategy based on the water quality conditions. When the efficiency improvement termination module starts the adaptation control strategy, it sets the efficiency improvement optimization time, monitors the chloride ion concentration of the cooling water in real time, calculates the chloride ion concentration change trend, and determines whether to stop the efficiency improvement operation based on the chloride ion concentration change trend.

[0055] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0056] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and inventive constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0057] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0058] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0059] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An optimization method for circulating cooling water treatment in thermal power plants based on big data analysis, characterized by: Includes the following steps: Step S1: Monitor the cooling water system, collect the redox potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger in real time, set the collection time, collect the temperature data of the cooling water inlet and outlet during the collection time, and calculate the temperature change based on the temperature data. Step S2: Based on the temperature change and the redox potential of the cooling water, generate the efficiency improvement driving characteristics, analyze the efficiency improvement inhibition characteristics by combining the biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger, and determine whether to generate a driving signal by combining the efficiency improvement driving characteristics. Step S3: After generating the drive signal, detect the fluoride ion concentration of the cooling water to determine the water quality conditions, collect the organic carbon concentration of the cooling water, and select to start the conventional control strategy or the adaptive control strategy based on the water quality conditions. Step S4: When starting the adaptive control strategy, set the efficiency improvement optimization time, monitor the chloride ion concentration of the cooling water in real time, calculate the chloride ion concentration change trend, and determine whether to stop the efficiency improvement operation based on the chloride ion concentration change trend.

2. The method for optimizing circulating cooling water treatment in thermal power plants based on big data analysis according to claim 1, characterized in that: In step S1, the redox potential of the cooling water is measured in real time using a redox potential sensor; The ultrasonic signal is emitted to the heat exchange surface of the heat exchanger by an ultrasonic sensor, and the propagation time of the ultrasonic signal is obtained. The thickness of the biofilm on the surface of the heat exchanger is calculated based on the ultrasonic signal propagation time and the preset ultrasonic propagation speed. The pressure values ​​of the inlet and outlet pipes of the heat exchanger are measured by a pressure sensor, and the absolute value of the difference is taken as the pressure difference of the heat exchanger.

3. The method for optimizing the treatment of circulating cooling water in thermal power plants based on big data analysis according to claim 1, characterized in that: In step S1, a preset acquisition time is set, and the temperature data of the cooling water inlet and outlet are monitored at the start and end times of the acquisition time using temperature sensors. The initial temperature difference is obtained by subtracting the cooling water inlet temperature data from the outlet temperature data at the beginning and taking the absolute value. The temperature difference at the end time is obtained by subtracting the cooling water inlet temperature data and outlet temperature data at the end time and taking the absolute value. The absolute value of the difference between the initial temperature difference and the final temperature difference is taken as the temperature change.

4. The method for optimizing circulating cooling water treatment in thermal power plants based on big data analysis according to claim 3, characterized in that: In step S2, the logarithm of the biofilm thickness on the heat exchanger surface plus 1 is used as the biofilm thickness coefficient, and the logarithm of the redox potential of the cooling water plus 1 is used as the redox potential coefficient. The maximum value of temperature change and the maximum value of heat exchanger pressure difference are retrieved from historical data in the cooling water database. The ratio of the temperature change incremented by 1 to the maximum temperature change is used as the temperature influence parameter, and the ratio of the heat exchanger pressure difference incremented by 1 to the maximum heat exchanger pressure difference is used as the pressure difference influence parameter.

5. The method for optimizing circulating cooling water treatment in thermal power plants based on big data analysis according to claim 4, characterized in that: In step S2, 1 is subtracted from the temperature effect parameter and the redox potential coefficient respectively, and the results of the subtraction are multiplied to obtain the efficiency improvement driving characteristic; The product of the biofilm thickness coefficient and the pressure difference effect parameter is used as the efficiency-inhibiting characteristic; The net efficiency improvement driving value is obtained by subtracting the efficiency improvement driving feature from the efficiency improvement inhibition feature. The net efficiency improvement driving value is then compared with a preset driving threshold to determine whether to generate a driving signal. If the net efficiency improvement driving value exceeds the driving threshold, a driving signal is generated; Conversely, no drive signal is generated.

6. The method for optimizing circulating cooling water treatment in thermal power plants based on big data analysis according to claim 1, characterized in that: In step S3, after the driving signal is generated, the free fluoride ion content in the cooling water is electrochemically responded to by an ion-selective electrode sensor, and the fluoride ion concentration is calculated based on the Nernst equation. The fluoride ion concentration is fuzzified, and fuzzy sets are defined as low, medium, and high. Based on the threshold range and gradient set by experience, the first layer of fuzzy rule base is established to infer the water quality conditions of the cooling water, which include good, medium, and poor.

7. The method for optimizing the treatment of circulating cooling water in thermal power plants based on big data analysis according to claim 6, characterized in that: In step S3, all organic carbon elements in the water sample are measured using a high-temperature catalytic combustion-non-dispersive infrared detection method with an organic carbon analyzer, and the total organic carbon mass concentration value is output as the organic carbon concentration. The organic carbon concentration is fuzzified, and the fuzzy sets are defined as low, medium, and high. The water quality conditions and organic carbon concentration are jointly input into the second-layer fuzzy inference model. The control strategy is determined through the rule base, and the output set includes conventional control strategies and adaptive control strategies. The fuzzy membership set of the output control strategy is inferred using the Mamdani-type inference method and the maximum-minimum synthesis method. The centroid method is then used for defuzzification to obtain the output value of the control strategy.

8. The method for optimizing the treatment of circulating cooling water in thermal power plants based on big data analysis according to claim 7, characterized in that: In step S4, if the output value of the control strategy is less than or equal to the preset strategy judgment threshold, the normal control strategy is activated. If the output value of the control strategy is greater than the strategy judgment threshold, the adaptive control strategy will be activated. After activating the adaptation control strategy, set the efficiency improvement and optimization time; During the efficiency improvement and optimization period, the chloride ion concentration in the cooling water was detected by an ion-selective electrode sensor at a fixed sampling interval.

9. The method for optimizing the treatment of circulating cooling water in thermal power plants based on big data analysis according to claim 8, characterized in that: In step S4, the initial and final measured values ​​of chloride ion concentration are recorded using the first-order difference method within the efficiency improvement and optimization time period. Subtracting the initial measurement from the final measurement and dividing by the duration of the efficiency improvement and optimization time yields the trend of chloride ion concentration changes. If the chloride ion concentration change trend is less than the preset concentration growth threshold, it is determined that the efficiency improvement process has achieved the target effect, the efficiency improvement operation is stopped, and the steady-state control stage is entered. If the chloride ion concentration change trend is greater than or equal to the concentration growth threshold, the efficiency improvement process has not achieved the target effect, and the efficiency improvement operation should continue.

10. A big data analysis-based optimization system for circulating cooling water treatment in thermal power plants, used to implement the big data analysis-based optimization method for circulating cooling water treatment in thermal power plants as described in any one of claims 1-9, characterized in that: It includes a data acquisition and monitoring module, a signal determination module, a strategy selection module, and an efficiency improvement and termination module. The functions of each module are as follows: The data acquisition and monitoring module monitors the cooling water system, collecting data in real time on the oxidation-reduction potential of the cooling water, the biofilm thickness on the heat exchanger surface, and the pressure difference of the heat exchanger. The acquisition time is set, and the temperature data of the cooling water inlet and outlet are collected within the acquisition time. The temperature change is calculated based on the temperature data. The signal determination module generates efficiency-enhancing driving characteristics based on temperature changes and the redox potential of cooling water, analyzes efficiency-enhancing inhibition characteristics by combining the biofilm thickness on the heat exchanger surface and the pressure difference of the heat exchanger, and determines whether to generate a driving signal based on the efficiency-enhancing driving characteristics. After the strategy selection module generates the drive signal, it detects the fluoride ion concentration of the cooling water to determine the water quality conditions, collects the organic carbon concentration of the cooling water, and selects to start the conventional control strategy or the adaptive control strategy based on the water quality conditions. When the efficiency improvement termination module starts the adaptation control strategy, it sets the efficiency improvement optimization time, monitors the chloride ion concentration of the cooling water in real time, calculates the chloride ion concentration change trend, and determines whether to stop the efficiency improvement operation based on the chloride ion concentration change trend.

Images