SEC-based air cooling island flushing system optimization algorithm
By combining air-cooled island operation data and infrared imaging technology with a multimodal mapping library and dynamic threshold control, precise zonal rinsing of the air-cooled island was achieved, solving the problems of inefficiency and resource waste in existing rinsing strategies and improving the system's economy and intelligence.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INNER MONGOLIA DATANG INT TUOKETUO POWER GENERATION
- Filing Date
- 2025-12-15
- Publication Date
- 2026-05-12
AI Technical Summary
Existing air-cooled island flushing strategies fail to effectively balance flushing benefits and energy costs, resulting in inefficient or even negative-return flushing. They cannot achieve precise cleaning on demand, lack closed-loop feedback and adaptive capabilities, and the optimization effect decays over long-term operation.
By collecting operational status data and infrared thermal imaging images of the air-cooled island, the distribution of dirt thermal resistance is inverted. Combined with the multimodal SEC cleaning effect mapping library, the energy efficiency ratio is calculated, dynamic thresholds are set, differentiated flushing control commands are generated, and online correction is performed to achieve precise zoning perception and adaptive flushing.
It enables precise on-demand rinsing, reduces energy and water consumption, improves cleaning targeting and heat exchange recovery, and enhances the economic efficiency and intelligence of air-cooled systems.
Smart Images
Figure CN122015570A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent operation and maintenance technology for air-cooled systems of thermal power units, and in particular to an optimization algorithm for an air-cooled island flushing system based on SEC. Background Technology
[0002] As the core heat exchange equipment in direct air-cooled units, the air-cooled island's performance directly affects the condenser vacuum and the unit's coal consumption. With the large-scale construction of air-cooled thermal power units in coal-rich but water-scarce western regions of my country, the problem of fouling on air-cooled islands in high-dust, high-wind-sand environments is becoming increasingly prominent, leading to decreased heat exchange efficiency, increased back pressure, and consequently, increased coal consumption for power generation. To maintain the performance of the air-cooled system, regular flushing has become a routine maintenance practice. Existing flushing strategies mostly employ timed control or start-stop logic based on fixed terminal difference thresholds. Some advanced systems introduce infrared thermography to assist in judging the overall contamination level, but flushing decisions still rely solely on whether the system is dirty, lacking a quantitative assessment of the energy efficiency cost of the flushing process itself. In recent years, although some studies have attempted to use water consumption or pump power as optimization targets, a systematic intelligent control framework centered on unit energy consumption efficiency has not yet been formed.
[0003] The current technology system still has shortcomings. For example, the flushing triggering mechanism does not consider the balance between flushing benefits and energy consumption costs, which often leads to inefficient or even negative-return flushing, resulting in waste of electricity and water resources. It cannot achieve precise cleaning on demand. The flushing strategy lacks closed-loop feedback and adaptive capabilities, making it difficult to adjust with equipment aging, seasonal changes or water quality fluctuations. The optimization effect decays significantly under long-term operation. Summary of the Invention
[0004] In view of the aforementioned existing problems, the present invention is proposed.
[0005] Therefore, this invention provides an optimization algorithm for an air-cooled island flushing system based on SEC to solve the problems that the flushing triggering mechanism does not consider the balance between flushing benefits and energy consumption costs, often leading to inefficient or even negative-return flushing, resulting in waste of electricity and water resources, inability to achieve precise cleaning on demand, lack of closed-loop feedback and adaptive capability in the flushing strategy, difficulty in adjusting with equipment aging, seasonal changes or water quality fluctuations, and significant decay of optimization effect under long-term operation.
[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an optimization algorithm for an air-cooled island flushing system based on SEC, comprising: Collect operational status data, environmental parameters, and surface infrared thermal imaging images of the air-cooled island; Based on infrared thermal imaging images and condenser cooling air outlet temperature, the fouling thermal resistance distribution in each region of the air-cooled island is inverted, and multiple flushing zones are divided in combination with the physical structure of the air-cooled island, and the local fouling index of each flushing zone is calculated. Based on a pre-built multimodal SEC cleaning effect mapping library, the dirt type is determined according to the local dirt index of each rinsing zone, and the corresponding optimal rinsing mode is matched for each rinsing zone. Based on historical heat transfer performance data, the heat exchange efficiency gain of each flushing zone after adopting the optimal flushing mode corresponding to the zone is predicted, and the energy efficiency benefit ratio of each flushing zone is calculated by combining the energy consumption estimate of the flushing process. Set a dynamic energy efficiency benefit threshold, compare the energy efficiency benefit ratio of each flushing zone with the dynamic energy efficiency benefit threshold, and identify the flushing zones that meet the flushing triggering conditions. For the identified flushing zones, a joint flushing control command is generated, which includes the zone identifier, the optimal flushing mode, the target water pressure, the target water flow rate, and the flushing duration, and then sent to the flushing actuator to perform differentiated flushing. After the differentiated flushing is completed, the actual heat exchange efficiency gain and actual flushing energy consumption are evaluated based on the condenser cooling air outlet temperature and infrared thermal imaging images collected after flushing. The multimodal SEC cleaning effect mapping library and dynamic energy efficiency benefit threshold are then corrected online.
[0007] As a preferred embodiment of the SEC-based air-cooled island flushing system optimization algorithm described in this invention, the specific steps for collecting air-cooled island operating status data, environmental parameters, and surface infrared thermal imaging images are as follows: The current steam saturation temperature is obtained by temperature sensors deployed in the condenser system. The steam saturation temperature is determined by the unit back pressure gauge; The measured outlet temperature of the cooling air was obtained by a temperature probe installed in the outlet duct of the air cooler. And the input power signal of the flushing water pump is collected in real time through the power monitoring module; The instantaneous volumetric flow rate of the flushing water is obtained by using an electromagnetic flow meter, and the current ambient wind speed, relative humidity, and atmospheric dust concentration are obtained by simultaneously calling the plant-level meteorological station interface. The infrared thermal imaging array mounted on the air-cooled island platform is activated to scan the surface of all air-cooled fins at a rate of half a minute, and outputs a two-dimensional surface temperature distribution image after radiometric calibration and non-uniformity correction.
[0008] As a preferred embodiment of the SEC-based air-cooled island flushing system optimization algorithm described in this invention, the steps include: retrieving the fouling thermal resistance distribution in each region of the air-cooled island based on infrared thermal imaging images and condenser cooling air outlet temperatures, dividing the air-cooled island into multiple flushing zones based on its physical structure, and calculating the local fouling index of each flushing zone. Based on the layout of the air-cooled island fan units and the arrangement of the tube bundles, the entire air-cooled island is divided into several non-overlapping geometric flushing zones, each zone corresponding to a sub-region in the infrared image. For each sub-region, calculate the average surface temperature of the sub-region; Based on the steady-state heat transfer principle, the equivalent fouling thermal resistance of each zone is calculated by using the steam saturation temperature, cooling air outlet temperature, average surface temperature, and the known cleanliness convective heat transfer coefficient of the equipment. By combining the current ambient wind speed and dust concentration, an environmentally weighted correction is applied to the fouling thermal resistance to obtain the local fouling index for each zone. The formula is as follows: ; in, For the thermal resistance of dirt, The steam saturation temperature For the first Average surface temperature of the zone To cool the air outlet temperature, The reference convective heat transfer coefficient is the standard convective heat transfer coefficient under clean conditions for air-cooled fins. The reference convective heat transfer coefficient is an inherent parameter of the equipment.
[0009] As a preferred embodiment of the SEC-based air-cooled island flushing system optimization algorithm described in this invention, the steps of determining the dirt type based on the local dirt index of each flushing zone according to the pre-built multimodal SEC-cleaning effect mapping library, and matching the corresponding optimal flushing mode for each flushing zone are as follows: Before the system was put into operation, the cleaning effect of three flushing modes—high-pressure jet, low-pressure spray, and ultrasonic atomization—was tested on-site for typical dirt types. The flushing energy consumption and end-point difference improvement of each mode were recorded, and the unit benefit energy consumption ratio was calculated. The unit efficiency energy consumption ratio is organized into a multimodal SEC cleaning effect mapping library according to the type of dirt and the flushing mode; During the runtime phase, the local dirt index of the current partition is input into the pre-trained dirt classification model, and the corresponding dirt category is output. Query the mapping library to obtain the unit efficiency energy consumption ratio of dirt categories under each flushing mode, and select the flushing mode with the lowest unit efficiency energy consumption ratio as the optimal flushing mode for this partition.
[0010] As a preferred embodiment of the SEC-based air-cooled island flushing system optimization algorithm described in this invention, the steps of predicting the heat exchange efficiency gain of each flushing zone after adopting the optimal flushing mode corresponding to the zone based on historical heat transfer performance data, and calculating the energy efficiency benefit ratio of each flushing zone in combination with the energy consumption estimate of the flushing process, are as follows: Based on the historical operation database of power plants, a predictive model is established between fouling thermal resistance and terminal temperature improvement. Using the current zone's fouling thermal resistance and optimal flushing mode as input, the improvement in the back-end temperature difference after cleaning is predicted, and the predicted improvement is converted into a condenser heat exchange efficiency gain. Improvement in end difference The conversion relationship is as follows: ; in, This is the current benchmark value for condenser thermal efficiency. The current actual terminal difference is calculated by real-time data collection. The current condenser thermal efficiency baseline value and the actual terminal difference are calculated by real-time data collection. and Calculated; Based on the unit flow energy consumption coefficient, target water flow rate, and recommended flushing duration corresponding to the optimal flushing mode, the total energy consumption required for this flushing is estimated. The estimation formula is: ; in, To match the optimal flushing mode The corresponding energy consumption coefficient per unit flow rate, For the target water flow rate, Recommended rinsing time; Divide the heat exchange efficiency gain by the estimated energy consumption to obtain the energy efficiency benefit ratio of the zone. The energy efficiency benefit ratio represents the thermal efficiency improvement brought about by the unit flushing energy consumption. The flushing is deemed worthwhile based on the energy efficiency benefit ratio. The formula is: ; in, For heat exchange efficiency gain, Total energy consumption required for rinsing.
[0011] As a preferred embodiment of the SEC-based air-cooled island flushing system optimization algorithm described in this invention, the specific steps of setting a dynamic energy efficiency benefit threshold, comparing the energy efficiency benefit ratio of each flushing zone with the benchmark convective heat transfer coefficient, and identifying flushing zones that meet the flushing triggering conditions are as follows: The initial dynamic energy efficiency benefit threshold is the moving average of the energy efficiency benefit ratios from historical effective flushing events. In each flushing decision cycle, the dynamic energy efficiency benefit threshold is updated using an exponential smoothing method based on the actual energy efficiency benefit ratios of the most recent effective flushes. The update rules are as follows: ; in, For the cause of forgetting, This represents the average energy efficiency benefit ratio of the most recent effective flushing events. Indicates the first The energy efficiency benefit judgment benchmark adopted by the system when making the flushing decision; The calculated energy efficiency benefit ratio for each zone is compared with the current dynamic threshold. If the energy efficiency benefit ratio of a zone is higher than the current dynamic threshold, it is determined that the current flushing has a positive net energy efficiency benefit, and this zone is included in the set of zones to be flushed.
[0012] As a preferred embodiment of the SEC-based air-cooled island flushing system optimization algorithm described in this invention, the following steps are taken: For the identified flushing zones, a joint flushing control command is generated, including zone identifier, optimal flushing mode, target water pressure, target water flow rate, and flushing duration, and then sent to the flushing actuator to perform differentiated flushing. Iterate through each partition in the set of partitions to be rinsed, and extract the process parameters associated with its optimal rinsing mode from the multimodal SEC cleaning effect mapping library, including the target rinsing water pressure, the target rinsing water flow rate, and the recommended rinsing duration. Encapsulate the zone physical identifier, flushing mode number, target water pressure, target water flow rate, and flushing duration into a single structured control command; All control commands are sent in parallel to the local execution unit of the corresponding partition through the industrial communication protocol. The local execution unit includes an electric regulating valve, a variable frequency water pump driver, and a nozzle start / stop controller. The execution unit independently adjusts the valve opening, water pump speed, and nozzle opening / closing status according to instructions.
[0013] As a preferred embodiment of the optimization algorithm for the SEC-based air-cooled island flushing system described in this invention, the following steps are taken: After differentiated flushing is completed, based on the condenser cooling air outlet temperature and infrared thermal imaging image collected after flushing, the actual heat exchange efficiency gain and actual flushing energy consumption are evaluated. Accordingly, the multimodal SEC cleaning effect mapping library and dynamic energy efficiency benefit threshold are corrected online. The specific steps are as follows: After completing all zone flushing operations and waiting for the thermal field to stabilize, the cooling air outlet temperature was collected again. Infrared images of the surface of the air-cooled island; Calculate the actual improvement in the difference between the ends. ,in, This refers to the outlet temperature of the cooling air before rinsing. This refers to the outlet temperature of the cooling air after rinsing. The actual heat transfer efficiency gain is derived based on the actual improvement in terminal temperature difference. The formula is: ; in, This is the current benchmark value for condenser thermal efficiency. This represents the actual end difference before rinsing. This represents the actual improvement in terminal differences; The integral value of the water pump's electrical power during the rinsing process is read synchronously to obtain the actual rinsing energy consumption. And calculate the actual energy efficiency benefit ratio. The formula is: ; in, The actual electrical energy consumed during the flushing execution phase is obtained by real-time integration by the electrical energy monitoring module. This represents the actual heat exchange efficiency gain. If the relative deviation between the actual energy efficiency benefit ratio and the predicted value exceeds the preset tolerance, the model correction mechanism is triggered. The model correction mechanism updates the unit benefit energy consumption ratio of the corresponding dirt type and flushing mode in the mapping library, or includes the actual energy efficiency benefit ratio of this effective flushing in the statistical sample of the dynamic threshold.
[0014] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the SEC-based air-cooled island flushing system optimization algorithm as described in the first aspect of the present invention.
[0015] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the SEC-based air-cooled island flushing system optimization algorithm as described in the first aspect of the present invention.
[0016] The beneficial effects of this invention are as follows: By constructing an intelligent flushing optimization algorithm for air-cooled islands with unit flushing energy consumption as the core, the flushing decision is transformed for the first time from the traditional experience-based judgment of whether it is dirty to an energy efficiency benefit-driven mechanism of whether it is worth washing. This achieves closed-loop optimization of precise perception of dirt in different zones, adaptive matching of flushing modes, dynamic threshold control of flushing triggers, and online model correction. Compared with existing technologies, this effectively avoids inefficient or negative-benefit flushing, reduces the consumption of electricity and water resources during the flushing process, and improves the cleaning targeting and heat exchange recovery effect through differentiated execution strategies. Thus, while ensuring the vacuum performance of the unit, it significantly improves the economic efficiency and intelligence level of the air-cooled system. Attached Figure Description
[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart of the optimization algorithm for the SEC-based air-cooled island flushing system in Example 1. Detailed Implementation
[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.
[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.
[0022] Example 1, referring to Figure 1 As an embodiment of the present invention, this embodiment provides an optimization algorithm for an air-cooled island flushing system based on SEC, including the following steps: S1. Collect operating status data, environmental parameters, and surface infrared thermal imaging images of the air-cooled island.
[0023] Furthermore, the current steam saturation temperature is obtained through temperature sensors deployed in the condenser system. The steam saturation temperature is determined by the unit back pressure gauge; The measured outlet temperature of the cooling air was obtained by a temperature probe installed in the outlet duct of the air cooler. And the input power signal of the flushing water pump is collected in real time through the power monitoring module; The instantaneous volumetric flow rate of the flushing water is obtained by using an electromagnetic flow meter, and the current ambient wind speed, relative humidity, and atmospheric dust concentration are obtained by simultaneously calling the plant-level meteorological station interface. The infrared thermal imaging array mounted on the air-cooled island platform is activated to scan the surface of all air-cooled fins at a rate of half a minute, and outputs a two-dimensional surface temperature distribution image after radiometric calibration and non-uniformity correction.
[0024] It should be noted that by simultaneously acquiring condenser steam saturation temperature, cooling air outlet temperature, flushing water pump power, flushing water flow rate, as well as ambient wind speed, humidity, and dust concentration, and combining this with periodic scanning of the air-cooled island surface using high-frequency infrared thermal imaging, a multi-dimensional and high-precision perception of equipment operating status and pollution distribution is achieved. This comprehensive data acquisition mechanism overcomes the limitations of traditional methods that rely solely on a single differential indicator or a fixed time interval, providing a comprehensive and reliable input basis for subsequent refined fouling assessment and intelligent flushing decisions.
[0025] S2. Based on the infrared thermal imaging image and the condenser cooling air outlet temperature, the fouling thermal resistance distribution in each area of the air-cooled island is inverted, and multiple flushing zones are divided in combination with the physical structure of the air-cooled island. The local fouling index of each flushing zone is calculated.
[0026] Furthermore, based on the layout of the air-cooled island fan units and the arrangement of the tube bundles, the entire air-cooled island is divided into several non-overlapping geometric flushing zones, each zone corresponding to a sub-region in the infrared image. For each sub-region, calculate the average surface temperature of the sub-region; Based on the steady-state heat transfer principle, the equivalent fouling thermal resistance of each zone is calculated by using the steam saturation temperature, cooling air outlet temperature, average surface temperature, and the known cleanliness convective heat transfer coefficient of the equipment. By combining the current ambient wind speed and dust concentration, an environmentally weighted correction is applied to the fouling thermal resistance to obtain the local fouling index for each zone. The formula is as follows: ; in, For the thermal resistance of dirt, The steam saturation temperature For the first Average surface temperature of the zone To cool the air outlet temperature, The reference convective heat transfer coefficient is the standard convective heat transfer coefficient under clean conditions for air-cooled fins. The reference convective heat transfer coefficient is an inherent parameter of the equipment.
[0027] It should be noted that, based on infrared thermal images and cooling air outlet temperatures, and combined with the physical structure of the air-cooled island to divide the rinsing areas, and using the steady-state heat transfer principle to inversely calculate the thermal resistance of dirt in each area, the influence of ambient wind speed and dust concentration on dirt deposition is further integrated for weighted correction, thereby obtaining a more realistic local dirt index. This method breaks through the extensive assumption of treating the entire air-cooled island as a uniform contaminant in existing technologies, and for the first time achieves quantitative identification of the heterogeneity of dirt spatial distribution, laying a technical foundation for precise zoned cleaning.
[0028] S3. Based on the pre-built multimodal SEC cleaning effect mapping library, the dirt type is determined according to the local dirt index of each rinsing zone, and the corresponding optimal rinsing mode is matched for each rinsing zone.
[0029] Furthermore, before the system was put into operation, on-site experiments were conducted to test the cleaning effects of three flushing modes—high-pressure jet, low-pressure spray, and ultrasonic atomization—for typical types of dirt. The flushing energy consumption and end-point difference improvement under each mode were recorded, and the unit benefit energy consumption ratio was calculated. The unit efficiency energy consumption ratio is organized into a multimodal SEC cleaning effect mapping library according to the type of dirt and the flushing mode; During the runtime phase, the local dirt index of the current partition is input into the pre-trained dirt classification model, and the corresponding dirt category is output. Query the mapping library to obtain the unit efficiency energy consumption ratio of dirt categories under each flushing mode, and select the flushing mode with the lowest unit efficiency energy consumption ratio as the optimal flushing mode for this partition.
[0030] It should be noted that by establishing a cleaning effect database covering different types of dirt and multiple flushing modes before the system is put into operation, and using the unit benefit energy consumption ratio as the core evaluation indicator, the system automatically matches the flushing method with the lowest energy consumption and the best effect according to the real-time dirt type during operation. This abandons the inefficient practice of the traditional island-wide uniform mode, improves the utilization efficiency of flushing resources, and effectively reduces unnecessary waste of energy and water resources.
[0031] S4. Based on historical heat transfer performance data, predict the heat exchange efficiency gain of each flushing zone after adopting the optimal flushing mode corresponding to the zone, and calculate the energy efficiency benefit ratio of each flushing zone by combining the estimated energy consumption of the flushing process.
[0032] Furthermore, based on the power plant's historical operation database, a predictive model is established between fouling thermal resistance and the improvement in terminal temperature difference. Using the current zone's fouling thermal resistance and optimal flushing mode as input, the improvement in the back-end temperature difference after cleaning is predicted, and the predicted improvement is converted into a condenser heat exchange efficiency gain. Improvement in end difference The conversion relationship is as follows: ; in, This is the current benchmark value for condenser thermal efficiency. The current actual terminal difference is calculated by real-time data collection. The current condenser thermal efficiency baseline value and the actual terminal difference are calculated by real-time data collection. and Calculated; Based on the unit flow energy consumption coefficient, target water flow rate, and recommended flushing duration corresponding to the optimal flushing mode, the total energy consumption required for this flushing is estimated. The estimation formula is: ; in, To match the optimal flushing mode The corresponding energy consumption coefficient per unit flow rate, For the target water flow rate, Recommended rinsing time; Divide the heat exchange efficiency gain by the estimated energy consumption to obtain the energy efficiency benefit ratio of the zone. The energy efficiency benefit ratio represents the thermal efficiency improvement brought about by the unit flushing energy consumption. The flushing is deemed worthwhile based on the energy efficiency benefit ratio. The formula is: ; in, For heat exchange efficiency gain, Total energy consumption required for rinsing.
[0033] It should be noted that the improvement in heat exchange efficiency after flushing of each zone is predicted based on historical operating data, and the energy consumption of the corresponding flushing mode is estimated to calculate the energy efficiency benefit ratio of each zone. This is used as the basis for judging whether to perform flushing. For the first time, the flushing decision has been changed from whether it is dirty to whether it is worth flushing. This ensures that the operation is triggered only when the thermal performance gain is sufficient to cover the flushing cost, thus fundamentally avoiding inefficient or negative-return flushing behavior.
[0034] S5. Set a dynamic energy efficiency benefit threshold, compare the energy efficiency benefit ratio of each flushing zone with the dynamic energy efficiency benefit threshold, and identify the flushing zones that meet the flushing triggering conditions.
[0035] Furthermore, the dynamic energy efficiency benefit threshold is initialized as the moving average of the energy efficiency benefit ratios from historical effective flushing events. In each flushing decision cycle, the dynamic energy efficiency benefit threshold is updated using an exponential smoothing method based on the actual energy efficiency benefit ratios of the most recent effective flushes. The update rules are as follows: ; in, For the cause of forgetting, This represents the average energy efficiency benefit ratio of the most recent effective flushing events. Indicates the first The energy efficiency benefit judgment benchmark adopted by the system when making the flushing decision; The calculated energy efficiency benefit ratio for each zone is compared with the current dynamic threshold. If the energy efficiency benefit ratio of a zone is higher than the current dynamic threshold, it is determined that the current flushing has a positive net energy efficiency benefit, and this zone is included in the set of zones to be flushed.
[0036] It should be noted that a dynamically updated energy efficiency benefit threshold is used as the flushing trigger benchmark. This threshold is adaptively adjusted based on the actual performance of historical effective flushing events, and can be continuously optimized as equipment ages, seasons change, or environmental conditions change. Compared with a fixed threshold scheme, this design enhances the system's adaptability and decision-making accuracy in long-term operation, ensuring that the optimization effect does not decay over time.
[0037] S6. For the identified flushing zones, generate a joint flushing control command that includes zone identifier, optimal flushing mode, target water pressure, target water flow rate and flushing duration, and send it to the flushing actuator to perform differentiated flushing.
[0038] Furthermore, each partition in the set of partitions to be rinsed is traversed, and the process parameters associated with its optimal rinsing mode are extracted from the multimodal SEC cleaning effect mapping library, including the target rinsing water pressure, the target rinsing water flow rate, and the recommended rinsing duration. Encapsulate the zone physical identifier, flushing mode number, target water pressure, target water flow rate, and flushing duration into a single structured control command; All control commands are sent in parallel to the local execution unit of the corresponding partition through the industrial communication protocol. The local execution unit includes an electric regulating valve, a variable frequency water pump driver, and a nozzle start / stop controller. The execution unit independently adjusts the valve opening, water pump speed, and nozzle opening / closing status according to instructions.
[0039] It should be noted that for the selected flushing zone, a complete control command is generated, including the zone location, flushing mode, target water pressure, target water flow rate and duration, and sent to the corresponding actuator for independent control. This enables differentiated flushing of different areas on demand, according to quality and quantity, which completely changes the extensive mode of traditional island-wide synchronous flushing and greatly improves the targeting of cleaning and the rationality of resource allocation.
[0040] S7. After the differentiated flushing is completed, based on the condenser cooling air outlet temperature and infrared thermal imaging image collected after flushing, evaluate the actual heat exchange efficiency gain and actual flushing energy consumption, and perform online correction on the multimodal SEC cleaning effect mapping library and dynamic energy efficiency benefit threshold.
[0041] Furthermore, after completing all zone flushing operations and waiting for the thermal field to stabilize, the cooling air outlet temperature is collected again. Infrared images of the surface of the air-cooled island; Calculate the actual improvement in the difference between the ends. ,in, This refers to the outlet temperature of the cooling air before rinsing. This refers to the outlet temperature of the cooling air after rinsing. The actual heat transfer efficiency gain is derived based on the actual improvement in terminal temperature difference. The formula is: ; in, This is the current benchmark value for condenser thermal efficiency. This represents the actual end difference before rinsing. This represents the actual improvement in terminal differences; The integral value of the water pump's electrical power during the rinsing process is read synchronously to obtain the actual rinsing energy consumption. And calculate the actual energy efficiency benefit ratio. The formula is: ; in, The actual electrical energy consumed during the flushing execution phase is obtained by real-time integration by the electrical energy monitoring module. This represents the actual heat exchange efficiency gain. If the relative deviation between the actual energy efficiency benefit ratio and the predicted value exceeds the preset tolerance, the model correction mechanism is triggered. The model correction mechanism updates the unit benefit energy consumption ratio of the corresponding dirt type and flushing mode in the mapping library, or includes the actual energy efficiency benefit ratio of this effective flushing in the statistical sample of the dynamic threshold.
[0042] It should be noted that after rinsing, the actual heat exchange performance improvement and real energy consumption are evaluated by comparing the cooling air outlet temperature before and after rinsing with infrared images. Based on this, the cleaning effect database and decision threshold are corrected online. The closed-loop feedback mechanism enables the system to have continuous learning and self-optimization capabilities, ensuring that the algorithm continuously approaches the optimal SEC control level in long-term operation and maintains an efficient and stable economic operating state.
[0043] This embodiment also provides a computer device applicable to the optimization algorithm of the air-cooled island flushing system based on SEC, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the optimization algorithm of the air-cooled island flushing system based on SEC as proposed in the above embodiment.
[0044] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device's casing, or an external keyboard, touchpad, or mouse.
[0045] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the optimization algorithm for the SEC-based air-cooled island rinsing system proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0046] In summary, this invention, by constructing an intelligent flushing optimization algorithm for air-cooled islands with unit flushing energy consumption as its core, transforms the flushing decision from the traditional experience-based judgment of dirtiness to an energy efficiency benefit-driven mechanism based on whether flushing is worthwhile. It achieves closed-loop optimization of precise zone dirt perception, adaptive matching of flushing modes, dynamic threshold control of flushing triggers, and online model correction. Compared with existing technologies, it effectively avoids inefficient or negative-benefit flushing, reduces the consumption of electricity and water resources during the flushing process, and improves the cleaning targeting and heat exchange recovery effect through differentiated execution strategies. Thus, while ensuring the vacuum performance of the unit, it significantly improves the economic efficiency and intelligence level of the air-cooled system.
[0047] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
Claims
1. An optimization algorithm for an air-cooled island flushing system based on SEC, characterized in that: include: Collect operational status data, environmental parameters, and surface infrared thermal imaging images of the air-cooled island; Based on infrared thermal imaging images and condenser cooling air outlet temperature, the fouling thermal resistance distribution in each region of the air-cooled island is inverted, and multiple flushing zones are divided in combination with the physical structure of the air-cooled island, and the local fouling index of each flushing zone is calculated. Based on a pre-built multimodal SEC cleaning effect mapping library, the dirt type is determined according to the local dirt index of each rinsing zone, and the corresponding optimal rinsing mode is matched for each rinsing zone. Based on historical heat transfer performance data, the heat exchange efficiency gain of each flushing zone after adopting the optimal flushing mode corresponding to the zone is predicted, and the energy efficiency benefit ratio of each flushing zone is calculated by combining the energy consumption estimate of the flushing process. Set a dynamic energy efficiency benefit threshold, compare the energy efficiency benefit ratio of each flushing zone with the dynamic energy efficiency benefit threshold, and identify the flushing zones that meet the flushing triggering conditions. For the identified flushing zones, a joint flushing control command is generated, which includes the zone identifier, the optimal flushing mode, the target water pressure, the target water flow rate, and the flushing duration, and then sent to the flushing actuator to perform differentiated flushing. After the differentiated flushing is completed, the actual heat exchange efficiency gain and actual flushing energy consumption are evaluated based on the condenser cooling air outlet temperature and infrared thermal imaging images collected after flushing. The multimodal SEC cleaning effect mapping library and dynamic energy efficiency benefit threshold are then corrected online.
2. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 1, characterized in that: The specific steps for collecting the air-cooled island's operating status data, environmental parameters, and surface infrared thermal imaging images are as follows: The current steam saturation temperature is obtained by temperature sensors deployed in the condenser system. The steam saturation temperature is determined by the unit back pressure gauge; The measured outlet temperature of the cooling air was obtained by a temperature probe installed in the outlet duct of the air cooler. The input power signal of the flushing water pump is collected in real time through the power monitoring module; The instantaneous volumetric flow rate of the flushing water is obtained by using an electromagnetic flow meter, and the current ambient wind speed, relative humidity, and atmospheric dust concentration are obtained by simultaneously calling the plant-level meteorological station interface. The infrared thermal imaging array mounted on the air-cooled island platform is activated to scan the surface of all air-cooled fins at a rate of half a minute, and outputs a two-dimensional surface temperature distribution image after radiometric calibration and non-uniformity correction.
3. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 2, characterized in that: The method involves inverting the fouling thermal resistance distribution in each region of the air-cooled island based on infrared thermal imaging images and condenser cooling air outlet temperatures, and dividing the air-cooled island into multiple flushing zones based on its physical structure, calculating the local fouling index of each flushing zone. The specific steps are as follows: Based on the layout of the air-cooled island fan units and the arrangement of the tube bundles, the entire air-cooled island is divided into several non-overlapping geometric flushing zones, each zone corresponding to a sub-region in the infrared image. For each sub-region, calculate the average surface temperature of the sub-region; Based on the steady-state heat transfer principle, the equivalent fouling thermal resistance of each zone is calculated by using the steam saturation temperature, cooling air outlet temperature, average surface temperature, and the known cleanliness convective heat transfer coefficient of the equipment. By combining the current ambient wind speed and dust concentration, an environmentally weighted correction is applied to the fouling thermal resistance to obtain the local fouling index for each zone. The formula is as follows: ; in, For the thermal resistance of dirt, The steam saturation temperature For the first Average surface temperature of the zone, To cool the air outlet temperature, The reference convective heat transfer coefficient is the standard convective heat transfer coefficient under clean conditions for air-cooled fins. The reference convective heat transfer coefficient is an inherent parameter of the equipment.
4. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 3, characterized in that: The method, based on a pre-built multimodal SEC-cleaning effect mapping library, determines the dirt type according to the local dirt index of each rinsing zone and matches the corresponding optimal rinsing mode for each rinsing zone. The specific steps are as follows: Before the system was put into operation, the cleaning effect of three flushing modes—high-pressure jet, low-pressure spray, and ultrasonic atomization—was tested on-site for typical dirt types. The flushing energy consumption and end-point difference improvement of each mode were recorded, and the unit benefit energy consumption ratio was calculated. The unit efficiency energy consumption ratio is organized into a multimodal SEC cleaning effect mapping library according to the type of dirt and the flushing mode; During the runtime phase, the local dirt index of the current partition is input into the pre-trained dirt classification model, and the corresponding dirt category is output. Query the mapping library to obtain the unit efficiency energy consumption ratio of dirt categories under each flushing mode, and select the flushing mode with the lowest unit efficiency energy consumption ratio as the optimal flushing mode for this partition.
5. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 4, characterized in that: The steps are as follows: Based on historical heat transfer performance data, predict the heat exchange efficiency gain of each flushing zone after adopting the optimal flushing mode corresponding to the zone, and calculate the energy efficiency benefit ratio of each flushing zone by combining the estimated energy consumption of the flushing process. Based on the historical operation database of power plants, a predictive model is established between fouling thermal resistance and terminal temperature improvement. Using the current zone's fouling thermal resistance and optimal flushing mode as input, the improvement in the back-end temperature difference after cleaning is predicted, and the predicted improvement is converted into a condenser heat exchange efficiency gain. Improvement in end difference The conversion relationship is as follows: ; in, This is the current benchmark value for condenser thermal efficiency. The current actual terminal difference is calculated by real-time data collection. The current condenser thermal efficiency baseline value and the actual terminal difference are determined by data collection. and Calculated; Based on the unit flow energy consumption coefficient, target water flow rate, and recommended flushing duration corresponding to the optimal flushing mode, the total energy consumption required for this flushing is estimated. The estimation formula is: ; in, To match the optimal flushing mode The corresponding energy consumption coefficient per unit flow rate, For the target water flow rate, Recommended rinsing time; Divide the heat exchange efficiency gain by the estimated energy consumption to obtain the energy efficiency benefit ratio of the zone. The energy efficiency benefit ratio represents the thermal efficiency improvement brought about by the unit flushing energy consumption. The flushing is deemed worthwhile based on the energy efficiency benefit ratio. The formula is: ; in, For heat exchange efficiency gain, Total energy consumption required for rinsing.
6. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 5, characterized in that: The process of setting a dynamic energy efficiency benefit threshold, comparing the energy efficiency benefit ratio of each flushing zone with the benchmark convective heat transfer coefficient, and identifying flushing zones that meet the flushing triggering conditions involves the following steps: The initial dynamic energy efficiency benefit threshold is the moving average of the energy efficiency benefit ratios from historical effective flushing events. In each flushing decision cycle, the dynamic energy efficiency benefit threshold is updated using an exponential smoothing method based on the actual energy efficiency benefit ratios of the most recent effective flushes. The update rules are as follows: ; in, For the cause of forgetting, This represents the average energy efficiency benefit ratio of the most recent effective flushing events. Indicates the first The energy efficiency benefit judgment benchmark adopted by the system when making the flushing decision; The calculated energy efficiency benefit ratio for each zone is compared with the current dynamic threshold. If the energy efficiency benefit ratio of a zone is higher than the current dynamic threshold, it is determined that the current flushing has a positive net energy efficiency benefit, and this zone is included in the set of zones to be flushed.
7. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 6, characterized in that: For the identified flushing zones, a joint flushing control command is generated, including zone identifier, optimal flushing mode, target water pressure, target water flow rate, and flushing duration, and then sent to the flushing actuator to perform differentiated flushing. The specific steps are as follows: Iterate through each partition in the set of partitions to be rinsed, and extract the process parameters associated with its optimal rinsing mode from the multimodal SEC cleaning effect mapping library, including the target rinsing water pressure, the target rinsing water flow rate, and the recommended rinsing duration. Encapsulate the zone physical identifier, flushing mode number, target water pressure, target water flow rate, and flushing duration into a single structured control command; All control commands are sent in parallel to the local execution unit of the corresponding partition through the industrial communication protocol. The local execution unit includes an electric regulating valve, a variable frequency water pump driver, and a nozzle start / stop controller. The execution unit independently adjusts the valve opening, water pump speed, and nozzle opening / closing status according to instructions.
8. The optimization algorithm for the air-cooled island flushing system based on SEC as described in claim 7, characterized in that: After the differentiated flushing is completed, based on the condenser cooling air outlet temperature and infrared thermal imaging image collected after flushing, the actual heat exchange efficiency gain and actual flushing energy consumption are evaluated. Based on this, the multimodal SEC cleaning effect mapping library and dynamic energy efficiency benefit threshold are corrected online. The specific steps are as follows: After completing all zone flushing operations and waiting for the thermal field to stabilize, the cooling air outlet temperature was collected again. Infrared images of the surface of the air-cooled island; Calculate the actual improvement in the difference between the ends. ,in, This refers to the outlet temperature of the cooling air before rinsing. This refers to the outlet temperature of the cooling air after rinsing. The actual heat transfer efficiency gain is derived based on the actual improvement in terminal temperature difference. The formula is: ; in, This is the current benchmark value for condenser thermal efficiency. This represents the actual end difference before rinsing. This represents the actual improvement in terminal differences; The integral value of the water pump's electrical power during the rinsing process is read synchronously to obtain the actual rinsing energy consumption. And calculate the actual energy efficiency benefit ratio. The formula is: ; in, The actual electrical energy consumed during the flushing execution phase is obtained by real-time integration by the electrical energy monitoring module. This represents the actual heat exchange efficiency gain. If the relative deviation between the actual energy efficiency benefit ratio and the predicted value exceeds the preset tolerance, the model correction mechanism is triggered. The model correction mechanism updates the unit benefit energy consumption ratio of the corresponding dirt type and flushing mode in the mapping library, or includes the actual energy efficiency benefit ratio of this effective flushing in the statistical sample of the dynamic threshold.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the SEC-based air-cooled island flushing system optimization algorithm as described in any one of claims 1 to 8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the SEC-based air-cooled island flushing system optimization algorithm as described in any one of claims 1 to 8.