Hydrogen energy power generation system based on water cooling heat dissipation

Abstract

The present application relates to hydrogen energy power generation technical field, especially to a kind of hydrogen energy power generation system based on water cooling heat dissipation, comprising: heat load analysis module is based on the temperature difference of box and rainfall radiation shielding degree determines whether to execute heat load analysis;Thermal sensitive analysis module is based on the hotspot temperature rise rate of box surface temperature field determines whether to carry out thermal sensitive analysis to target box;Based on temperature gradient dispersion determines whether to divide the reference of sensitive unit by the reference of uniform grid reference adjustment is adjusted as the reference of heat feature tracking, based on hotspot focusing coefficient determines whether tracking reference is adjusted as local focusing by global coverage, to obtain several sensitive units, based on heat flow density deviation value determines the instability coupling class of sensitive unit;Model correction module is based on the number of sensitive units determines whether the correction mode is adjusted as partition correction by global correction, partition correction is based on instability coupling degree determines partition correction reference;Heat dissipation control module.The present application improves the precision of temperature prediction model.

Description

Technical Field

[0001] This invention relates to the field of hydrogen energy power generation technology, and in particular to a hydrogen energy power generation system based on water cooling. Background Technology

[0002] With the large-scale deployment of hydrogen energy power generation devices in outdoor scenarios such as backup power supplies for communication base stations, hydrogen-powered streetlights, and off-grid power supply systems in remote areas, the internal temperature of the installation enclosure directly impacts the safety, power generation efficiency, and equipment lifespan of the device. During operation, excessively high stack temperatures accelerate membrane electrode aging, while excessively low temperatures reduce power generation efficiency. Furthermore, the environmental factors experienced by outdoor installation enclosures include air temperature, solar radiation, wind speed, and rainfall, causing highly complex nonlinear temperature variations within the enclosure. Particularly during rainy weather, rainfall generates multiple nonlinear coupling effects on the enclosure temperature, specifically manifested as evaporative cooling at the initial stage of rainfall, the insulating effect of rainwater film during continuous rainfall, and a significant enhancement of convective heat transfer in the high humidity environment after rain. These coupling effects make enclosure temperature prediction extremely difficult, and traditional prediction methods based on single meteorological parameters or empirical formulas are insufficient to meet engineering accuracy requirements.

[0003] Chinese Patent Publication No. CN105848448A discloses a temperature control system for an outdoor hydrogen energy power generation device, including: a cabinet and a hydrogen cabinet; the cabinet is equipped with a main control unit, a fuel cell stack unit, a ventilation unit, and a DC unit, and the cabinet includes a cabinet body, a front door, and a rear door; the front door has multiple air inlets, each equipped with an intake fan, and the rear door has multiple exhaust vents; replaceable filter cotton is installed on the inner side of each air inlet, and a waterproof plate is installed on the outer side; both the front and rear doors adopt a sandwich structure, including inner and outer steel plates and an intermediate sandwich layer, the intermediate sandwich layer being an insulation material layer; it can be seen that the above technical solution has the following problems: the existing technology adopts a passive temperature control mechanism of post-event adjustment, lacks the ability to predict the thermal impact of environmental factors such as rainfall, and treats the cabinet as a uniform control object, unable to perform adaptive zonal control based on spatial temperature distribution differences, resulting in delayed temperature prediction and poor control effect during rainy weather. Summary of the Invention

[0004] To address this issue, the present invention provides a water-cooled hydrogen energy power generation system to overcome the problem in the prior art that the lack of differentiated perception and zonal diagnosis of radiation overload and heat dissipation obstruction on the surface of the enclosure under rainfall scenarios leads to a significant decrease in the accuracy of the temperature prediction model under rainfall.

[0005] To achieve the above objectives, the present invention provides a hydrogen energy power generation system based on water cooling, comprising: The heat load analysis module is used to determine whether to perform heat load analysis based on the temperature difference of the enclosure and the degree of shading from rainfall radiation. The thermal sensitivity analysis module is used in thermal load analysis to determine whether to perform thermal sensitivity analysis on the target box based on the hot spot temperature rise rate of the box surface temperature field; in thermal sensitivity analysis, it determines whether to adjust the sensitive element division benchmark from a uniform grid benchmark to a thermal feature tracking benchmark based on the temperature gradient dispersion; and it determines whether to adjust the tracking benchmark from global coverage to local focus based on the hot spot focusing coefficient. Based on the division benchmark, several sensitive elements are obtained, and the instability coupling category of the sensitive element is determined based on the heat flux density deviation value. The model correction module is used to determine whether the correction method is changed from global correction to partition correction based on the number of sensitive units. In the partition correction, the partition correction benchmark is determined from the instability equilibrium value to the instability category based on the instability coupling degree. The heat dissipation control module is used to generate water-cooling heat dissipation control parameters for the hydrogen energy power generation device based on the received temperature prediction values.

[0006] Furthermore, the heat load analysis module determines to perform heat load analysis in response to the condition that the temperature difference of the enclosure is greater than the preset temperature difference of the enclosure or the rainfall radiation shielding degree is less than the preset rainfall radiation shielding degree. The rainfall radiation shielding degree is determined based on the rainfall intensity and solar radiation intensity; The rainfall radiation shielding degree is positively correlated with the rainfall intensity; The rainfall radiation shielding degree is negatively correlated with the solar radiation intensity.

[0007] Furthermore, the thermal sensitivity analysis module responds to the condition that the hot spot temperature rise rate is greater than the preset hot spot temperature rise rate, and determines to perform thermal sensitivity analysis on the target enclosure.

[0008] Furthermore, the thermal sensitivity analysis module determines the sensitive unit division benchmark as a uniform grid benchmark when the temperature gradient dispersion is less than the preset temperature gradient dispersion. The temperature gradient dispersion is determined based on the temperature gradient amplitude at each sampling point on the surface of the enclosure.

[0009] Furthermore, the thermal sensitivity analysis module determines the sensitive unit division benchmark as the thermal feature tracking benchmark when the temperature gradient dispersion is greater than or equal to the preset temperature gradient dispersion.

[0010] Furthermore, the thermal sensitivity analysis module determines the tracking benchmark as global coverage when the hot spot focusing coefficient is less than the preset hot spot focusing coefficient. If the hot spot focus coefficient is greater than or equal to the preset hot spot focus coefficient, the tracking benchmark is determined to be local focus; The hotspot focusing coefficient is determined based on the hotspot temperature rise rate and the temperature gradient dispersion.

[0011] Furthermore, the heat-sensitive analysis module determines the instability coupling type as radiation overload instability when the heat flux density deviation value is greater than the preset heat flux density deviation value. If the response heat flux density deviation is less than or equal to the preset heat flux density deviation, the instability coupling type is determined to be heat dissipation hindrance type instability. The heat flux density deviation value is determined based on the heat flux density corresponding to each sensitive unit.

[0012] Furthermore, the model correction module responds to the condition that the number of sensitive units is less than the preset number of sensitive units and determines that the correction method is global correction.

[0013] Furthermore, the model correction module determines the correction method as partition correction when the number of sensitive units is greater than or equal to the preset number of sensitive units.

[0014] Furthermore, the model correction module determines the partition correction benchmark as the instability equilibrium value when the instability coupling degree is less than the preset instability coupling degree in response to the condition. When the response instability coupling degree is greater than or equal to the preset instability coupling degree, the partition correction benchmark is determined as the instability category; The degree of instability coupling is determined based on the heat flux density deviation value corresponding to each sensitive unit.

[0015] Compared with the prior art, the beneficial effects of the present invention are that it reflects the driving force of heat dissipation or heat absorption from the box to the environment through the box temperature difference, and reflects the degree of attenuation of solar radiation by the current rainfall through the rainfall radiation shading degree. Based on the box temperature difference and the rainfall radiation shading degree, it determines whether to perform heat load analysis, avoiding invalid heat load calculation when the box and the environment are close to thermal equilibrium and the rainfall shading effect is not significant, and reducing the computing power consumption of the system's sensing layer.

[0016] This invention's thermal sensitivity analysis module reflects the urgency of thermal anomalies at the highest temperature point on the enclosure surface over time by using the hotspot temperature rise rate. Based on this rate, it determines whether thermal sensitivity analysis should be performed on the target enclosure, avoiding ineffective zoning diagnosis for enclosures without significant thermal spike characteristics and improving the targeting and timeliness of thermal sensitivity analysis triggering. It also reflects the spatial non-uniformity of temperature changes on the enclosure surface by using temperature gradient dispersion, determining whether the sensitive cell partitioning benchmark should be adjusted from a uniform grid benchmark to a thermal feature tracking benchmark. Furthermore, it reflects the combined characteristics of the urgency of thermal spikes over time and the spatial dispersion of temperature gradients by using the hotspot focusing coefficient, determining whether the thermal feature tracking benchmark should be adjusted from global coverage to local focusing, avoiding misclassifying adjacent normal areas into abnormal sensitive cells and improving the spatial accuracy of sensitive cell partitioning. Finally, it determines the instability coupling type of the sensitive cell—whether it is radiation overload instability or heat dissipation hindrance instability—by using the heat flux density deviation value, improving the accuracy of subsequent model corrections.

[0017] The model correction module of this invention reflects the thermal anomaly area on the surface of the enclosure by the number of sensitive units, and determines whether the correction method should be adjusted from global correction to regional correction based on the number of sensitive units. It reflects the relative degree of deviation of the measured heat flow of each sensitive unit from the theoretical heat flow and its instability direction by the instability coupling degree, and determines whether the regional correction benchmark should be adjusted from the instability equilibrium value to the instability category based on the instability coupling degree. This overcomes the technical defect of the prior art that uses a uniform correction direction for all anomaly areas, which aggravates the prediction deviation, and improves the accuracy of the enclosure temperature prediction model under rainy weather. Attached Figure Description

[0018] Figure 1 This is a module connection diagram of the hydrogen energy power generation system based on water cooling heat dissipation according to the present invention; Figure 2 This is a flowchart illustrating the process of determining whether to perform heat load analysis based on the temperature difference within the enclosure and the degree of shading from rainfall radiation, as described in this invention. Figure 3 This is a flowchart illustrating the process of determining the sensitive unit partitioning criterion based on the temperature gradient dispersion according to the present invention. Figure 4 This is a flowchart illustrating how the correction method is determined based on the number of sensitive units in this invention. Detailed Implementation

[0019] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0020] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0021] Please see Figure 1 The diagram shown is a module connection diagram of a water-cooled hydrogen energy power generation system according to an embodiment of the present invention. The present invention provides a water-cooled hydrogen energy power generation system, comprising: The heat load analysis module is used to determine whether to perform heat load analysis based on the temperature difference of the enclosure and the degree of shading from rainfall radiation. The thermal sensitivity analysis module is used in thermal load analysis to determine whether to perform thermal sensitivity analysis on the target box based on the hot spot temperature rise rate of the box surface temperature field; in thermal sensitivity analysis, it determines whether to adjust the sensitive element division benchmark from a uniform grid benchmark to a thermal feature tracking benchmark based on the temperature gradient dispersion; and it determines whether to adjust the tracking benchmark from global coverage to local focus based on the hot spot focusing coefficient. Based on the division benchmark, several sensitive elements are obtained, and the instability coupling category of the sensitive element is determined based on the heat flux density deviation value. The model correction module is used to determine whether the correction method is changed from global correction to partition correction based on the number of sensitive units. In the partition correction, the partition correction benchmark is determined from the instability equilibrium value to the instability category based on the instability coupling degree. The heat dissipation control module is used to generate water-cooling heat dissipation control parameters for the hydrogen energy power generation device based on the received temperature prediction values.

[0022] In this embodiment of the invention, heat load analysis is adaptively triggered by the temperature difference of the enclosure and the shading effect of rainfall, avoiding invalid heat load calculations when the enclosure and the environment are close to thermal equilibrium and the shading effect of rainfall is weak; the temperature rise rate of hot spots determines whether to trigger heat sensitivity analysis; the sensitive cell division benchmark is adjusted from a uniform grid benchmark to a thermal feature tracking benchmark by the temperature gradient dispersion; the search radius of the thermal feature tracking benchmark is adjusted from global coverage to local focus by the hot spot focusing coefficient, so as to accurately define the spatial boundary of the thermal peak when the thermal peak is concentrated and rapid, avoiding the misclassification of adjacent normal areas into abnormal sensitive cells; the instability coupling category is determined by the heat flux density deviation value as radiation overload instability or heat dissipation hindrance instability; the correction method is adjusted from global correction to regional correction by the number of sensitive cells; the regional correction benchmark is adjusted from the instability equilibrium value to the instability category by the instability coupling degree, overcoming the technical defect of the prior art that uses a uniform correction direction for all abnormal areas, which exacerbates the prediction deviation, and improving the accuracy of the enclosure temperature prediction model under rainy weather.

[0023] In this embodiment of the invention, the heat dissipation control module generates water-cooling heat dissipation control parameters based on the received temperature prediction values. The temperature prediction values ​​include the spatial coordinates of each sensitive unit in the enclosure, the corresponding zone temperature prediction values, the instability coupling category label, and the acquisition timestamp. The water-cooling heat dissipation system of the hydrogen energy power generation device includes a water-cooled circulating pump, which is a variable frequency centrifugal pump, installed at the inlet end of the main coolant pipeline at the bottom of the enclosure; an electric regulating valve, which is a ball valve driven by a linear electric actuator, installed at the inlet end of each water-cooled branch, used to regulate the coolant flow rate of each branch; and a cooling fan, which is an axial flow fan, installed behind the radiator and at the exhaust port at the top of the enclosure to form a forced air-cooling circulation. The heat dissipation control module generates control parameters for each actuator, which include the opening command of each electric regulating valve, the speed command of the water-cooled circulating pump, and the PWM duty cycle command of the cooling fan.

[0024] Specifically, the heat load analysis module determines to perform heat load analysis in response to conditions where the chamber temperature difference is greater than a preset chamber temperature difference or the rainfall radiation shielding degree is less than a preset rainfall radiation shielding degree. The rainfall radiation shielding degree is determined based on the rainfall intensity and solar radiation intensity; The rainfall radiation shielding degree is positively correlated with the rainfall intensity; The rainfall radiation shielding degree is negatively correlated with the solar radiation intensity.

[0025] In this embodiment of the invention, the heat load analysis module includes a temperature difference detection unit for acquiring the chamber temperature difference. The acquisition process includes determining the chamber temperature difference based on the average surface temperature of the chamber and the ambient temperature. The chamber temperature difference is positively correlated with the heat exchange driving force. In this embodiment, the difference between the average surface temperature of the chamber and the ambient temperature is calculated and denoted as the chamber temperature difference. The average surface temperature of the chamber is the average value of the surface temperatures collected by temperature sensors deployed at multiple points on the chamber surface, and the ambient temperature is the value collected by an ambient temperature sensor installed outside the chamber. It can be understood that the chamber temperature difference is used to determine the driving force of heat exchange between the chamber surface and the environment. A larger chamber temperature difference indicates that the chamber surface temperature is significantly higher or lower than the ambient temperature, indicating a significant thermal driving force for the chamber to dissipate heat to or absorb heat from the environment. In this case, the internal temperature of the chamber is significantly affected by the external environment, and heat load analysis is required to accurately perceive the thermal state of the chamber.

[0026] In this embodiment of the invention, obtaining the preset cabinet temperature difference includes: collecting cabinet temperature difference data when the heat dissipation control effect of the target cabinet meets the standard within a historical operating cycle; removing outliers; calculating the average value of the cabinet temperature difference data; and recording the obtained average value as the preset cabinet temperature difference. In this embodiment, the historical operating cycle refers to the time range covered by the complete heat load analysis completed by the system before the current moment. Those skilled in the art can set the historical operating cycle based on the seasonal change cycle of the environment, which will not be elaborated further. It is understood that standards commonly used by those skilled in the art, such as the cabinet temperature change rate, can be set as the evaluation criteria for whether the heat dissipation control effect meets the standard. How to determine whether the heat dissipation control effect meets the standard is a matter already known to those skilled in the art, and will not be elaborated further.

[0027] In this embodiment of the invention, the heat load analysis module includes a radiation sensing unit for acquiring the rainfall radiation shading degree. The acquisition process includes determining the rainfall radiation shading degree based on the rainfall intensity and solar radiation intensity, wherein the rainfall radiation shading degree and the rainfall radiation shading effect are positively correlated. In this embodiment, the rainfall intensity is calculated as the ratio of the numerator to the solar radiation intensity, denoted as the rainfall radiation shading degree. The rainfall intensity is a value collected by a piezoelectric rain gauge installed on the top of the enclosure, and the solar radiation intensity is a value collected by a solar radiation sensor installed on the top of the enclosure. It can be understood that the rainfall radiation shading degree is used to determine the degree of attenuation of direct solar radiation by the current rainfall. The larger the rainfall radiation shading degree, the more significant the shading effect of the rain clouds and raindrops on solar radiation, and the lower the actual radiative heat received by the enclosure surface. In this case, the heat load mainly comes from the heating of the internal electrode stack rather than external radiation. The smaller the rainfall radiation shading degree, the weaker the shading effect of the rainfall on solar radiation, and the heating effect of solar radiation on the enclosure surface needs to be considered.

[0028] In this embodiment of the invention, the process of obtaining the preset rainfall radiation shielding degree includes: collecting the rainfall radiation shielding degree of the target box in the historical operation cycle when the heat dissipation control effect meets the standard, removing outliers, calculating the average value of the rainfall radiation shielding degree, and recording the obtained average value as the preset rainfall radiation shielding degree.

[0029] Specifically, the thermal sensitivity analysis module responds to the condition that the hot spot temperature rise rate is greater than the preset hot spot temperature rise rate, and determines to perform thermal sensitivity analysis on the target enclosure.

[0030] In this embodiment of the invention, the thermal sensitivity analysis module includes a hotspot detection unit for acquiring the hotspot temperature rise rate. The acquisition process includes: determining the hotspot temperature rise rate based on the temperature change curve of the hotspot within a preset time window, wherein the hotspot temperature rise rate is positively correlated with the urgency of the thermal anomaly. In this embodiment, the temperature change curve of the hotspot within the preset time window is calculated, and the derivative of the curve with respect to time is obtained by differential differentiation, denoted as the hotspot temperature rise rate. The hotspot is identified by real-time acquisition of the temperature at various measuring points by a temperature sensor array deployed on the surface of the enclosure, identifying the measuring point with the highest surface temperature at the current moment. It can be understood that the hotspot temperature rise rate is used to determine the urgency of the temperature rise at the highest temperature point on the enclosure surface over time. A higher hot spot temperature rise rate indicates a rapidly rising local thermal spike on the surface of the enclosure, suggesting that the thermal anomaly is imminent and may be caused by factors such as local overload of the fuel cell stack, blockage of the water cooling channel, or sudden exposure to an external heat source. In this case, thermal sensitivity analysis needs to be triggered to perform a detailed spatial diagnosis of the hot spot area. A lower hot spot temperature rise rate indicates that the surface temperature of the enclosure changes gradually and there are no significant thermal spike characteristics, so thermal sensitivity analysis is not required.

[0031] In this embodiment of the invention, the process of obtaining the preset time window includes: constructing a thermal simulation scenario for an outdoor hydrogen energy power generation device; applying a step heat source and a pulse heat source at different locations on the surface of the enclosure to simulate the hot spot temperature rise process under different operating conditions; using the calculated stability of the hot spot temperature rise rate under different time window lengths as an evaluation index; and selecting the time window length corresponding to the evaluation index meeting the requirements, which is denoted as the preset time window. In this embodiment, how to determine whether the evaluation index meets the requirements is content already known to those skilled in the art and will not be elaborated further.

[0032] In this embodiment of the invention, hot spot temperature rise rate data of the target enclosure when the heat dissipation control effect meets the standard during the historical operation cycle are collected, outliers are removed, the average value is calculated, and the obtained average value is recorded as the preset hot spot temperature rise rate.

[0033] Specifically, the thermal sensitivity analysis module determines the sensitive unit division benchmark as a uniform grid benchmark when the temperature gradient dispersion is less than the preset temperature gradient dispersion. The temperature gradient dispersion is determined based on the temperature gradient amplitude at each sampling point on the surface of the enclosure.

[0034] In this embodiment of the invention, the thermal sensitivity analysis module includes a gradient analysis unit for obtaining temperature gradient dispersion. The acquisition process includes: determining the temperature gradient dispersion based on the standard deviation of the temperature gradient amplitude at each sampling point relative to the average temperature gradient amplitude, wherein the temperature gradient dispersion is positively correlated with the degree of thermal non-uniformity. In this embodiment, the standard deviation of the temperature gradient amplitude at each sampling point relative to the average temperature gradient amplitude is calculated, and the obtained standard deviation is recorded as the temperature gradient dispersion. The temperature gradient amplitude is the temperature value obtained at each sampling point through a temperature sensor array deployed on the surface of the enclosure. For each sampling point, the temperature difference between it and its adjacent sampling points is calculated and divided by the physical distance between the two sampling points to obtain the temperature gradient amplitude at that point. It can be understood that the temperature gradient dispersion is used to determine the degree of spatial non-uniformity of the temperature change on the enclosure surface. The larger the temperature gradient dispersion, the more significant the difference in temperature gradient between different areas of the enclosure surface, indicating a clear non-uniform distribution of thermal features. In other words, some areas experience drastic temperature changes while others change gradually. In this case, a thermal feature tracking benchmark is needed to adaptively capture the spatial boundaries of thermal peaks, avoiding the loss of boundary details in areas of drastic temperature changes due to insufficient sampling by the uniform grid. The smaller the temperature gradient dispersion, the more consistent the temperature gradient between different areas of the enclosure surface, indicating a uniform spatial distribution of thermal states. In this case, a uniform grid benchmark can meet the requirements for zonal diagnosis without increasing computational complexity.

[0035] In this embodiment of the invention, the process of obtaining the preset temperature gradient dispersion includes: constructing a thermal simulation scenario of an outdoor hydrogen energy power generation device, using the accuracy of the boundary positioning of the thermal anomaly area as the evaluation index, selecting the temperature gradient dispersion corresponding to the evaluation index meeting the requirements, and recording it as the preset temperature gradient dispersion.

[0036] In this embodiment of the invention, the process of dividing the thermal sensitivity analysis module into sensitive units based on a uniform grid reference includes: using each measuring point of the temperature sensor array deployed on the surface of the enclosure as a grid node, dividing the enclosure surface into several rectangular grid units of equal area according to a preset number of rows and columns. The preset number of rows and columns is determined by the geometric dimensions of the enclosure surface and the deployment density of the temperature sensor array, ensuring that each grid unit contains at least one temperature sensor measuring point. Each grid unit is spatially non-overlapping and completely covers the entire surface area of ​​the enclosure.

[0037] Specifically, the thermal sensitivity analysis module determines the sensitive unit division benchmark as the thermal feature tracking benchmark when the temperature gradient dispersion is greater than or equal to the preset temperature gradient dispersion.

[0038] Specifically, the thermal sensitivity analysis module determines the tracking benchmark as global coverage when the hot spot focusing coefficient is less than the preset hot spot focusing coefficient. If the hot spot focus coefficient is greater than or equal to the preset hot spot focus coefficient, the tracking benchmark is determined to be local focus; The hotspot focusing coefficient is determined based on the hotspot temperature rise rate and the temperature gradient dispersion.

[0039] In this embodiment of the invention, the thermal sensitivity analysis module includes a focusing analysis unit for obtaining a hotspot focusing coefficient. The acquisition process includes determining the hotspot focusing coefficient based on the hotspot temperature rise rate and the temperature gradient dispersion. The hotspot focusing coefficient is positively correlated with the degree of thermal peak focusing. In this embodiment, the hotspot temperature rise rate is calculated as the ratio of the molecule to the temperature gradient dispersion, denoted as the hotspot focusing coefficient. It can be understood that the hotspot focusing coefficient is used to quantify the comprehensive characteristics of the thermal peak's urgency in the time dimension and the degree of temperature gradient dispersion in the spatial dimension. A larger hotspot focusing coefficient indicates a faster hotspot temperature rise and a more concentrated temperature gradient, resulting in a sharp, rapid, and concentrated thermal peak, meaning the thermal anomaly is highly focused on a small area on the surface of the enclosure with clear boundaries. A smaller hotspot focusing coefficient indicates a slower hotspot temperature rise or a more diffuse hotspot, with less pronounced thermal peak characteristics.

[0040] In this embodiment of the invention, the process of obtaining the preset heat flux density deviation value includes: constructing a thermal simulation scenario of an outdoor hydrogen energy power generation device, using the identification accuracy of the unstable coupling category as the evaluation index, selecting the heat flux density deviation value corresponding to the evaluation index meeting the requirements, and recording it as the preset heat flux density deviation value.

[0041] In this embodiment of the invention, the process of dividing sensitive units based on global coverage by the thermal sensitivity analysis module includes: extracting all local temperature maxima in the temperature field, filtering out points with temperatures lower than the global average, and forming a set of heat source seed points; defining an anisotropic growth metric for each type of seed point, which is the ratio of the radial temperature gradient of the point to the difference between the temperature at the center point and the ambient temperature; all seed points simultaneously start growth, with the growth direction along the direction of the fastest decrease in temperature gradient, and constrained by isotherm affinity, wherein the isotherm affinity constraint requires the temperature of the growth point to be higher than a dynamic value, which is adaptively determined based on the difference between the temperature of the seed point and the global average temperature; when the growth regions of different seed points overlap, they are merged using the boundary line of the temperature gradient vector field to form independent sensitive units.

[0042] In this embodiment of the invention, the process of dividing sensitive units based on local focusing in the thermal sensitivity analysis module includes: selecting the hottest heat source seed point as the local focusing core; using this hot spot as the center, along the heat flow diffusion direction, defining the area enclosed by the closed isotherm formed by sampling points that satisfy the preset gradient mutation value as the thermal core sensitive unit, and the isotherm is denoted as the thermal core boundary; generating radial detection lines from the thermal core boundary along the outward normal direction, and defining the ratio of the difference between the thermal core boundary temperature and the current point temperature to the current point temperature gradient amplitude as the energy attenuation characteristic quantity on each detection line; calculating the rate of change of this characteristic quantity along the detection line, and extracting the local maximum point on the rate of change curve as the thermal influence boundary point in the detection direction; connecting all thermal influence boundary points with a closed B-spline curve to form the local focusing boundary, and the annular area between this boundary and the thermal core boundary is adaptively divided into multiple sensitive units according to the local curvature change characteristics of the energy attenuation characteristic quantity curve on each detection line. In this embodiment, temperature field sample data at known heat source distribution locations on the surface of the box are collected, and the recall rate of thermal core boundary identification is used as the evaluation index. The gradient change rate corresponding to the recall rate meeting the requirements is selected and recorded as the preset gradient mutation value.

[0043] Specifically, the heat-sensitive analysis module determines the instability coupling type as radiation overload instability when the heat flux density deviation value is greater than the preset heat flux density deviation value. If the response heat flux density deviation is less than or equal to the preset heat flux density deviation, the instability coupling type is determined to be heat dissipation hindrance type instability. The heat flux density deviation value is determined based on the heat flux density corresponding to each sensitive unit.

[0044] In this embodiment of the invention, the heat sensitivity analysis module includes a density analysis unit for obtaining a heat flux density deviation value. The acquisition process includes: determining the heat flux density deviation value based on the measured heat flux density and the theoretical heat flux density, wherein the heat flux density deviation value is positively correlated with the degree of instability. In this embodiment, the difference between the measured heat flux density and the theoretical heat flux density is calculated and recorded as the heat flux density deviation value. The measured heat flux density is the value obtained by collecting data from each sensitive unit using patch-type heat flux meters deployed on the wall of the enclosure, with each heat flux meter's placement corresponding to a temperature measurement point. The direction of heat flow into the enclosure is taken as the positive direction. The theoretical heat flux density is the algebraic sum of solar radiation absorbed heat flux, convective heat dissipation flux, and long-wave radiation dissipation heat. The theoretical heat flux density is calculated based on current environmental parameters, including air temperature, humidity, wind speed, solar radiation intensity, and rainfall intensity, using a heat transfer theory model. It can be understood that the heat flux density deviation value is used to determine the degree and direction of deviation of the actual heat exchange intensity of each sensitive unit from the theoretical expectation. When the heat flux density deviation value is positive, it indicates that the measured heat flux of the sensitive unit is higher than the theoretical expectation, that is, there is additional heat input or excess heat generation in the area; when the heat flux density deviation value is negative, it indicates that the measured heat flux of the sensitive unit is lower than the theoretical expectation, that is, heat dissipation in the area is blocked or heat is trapped inside the box and cannot be discharged.

[0045] In this embodiment of the invention, the process of obtaining the preset heat flux density deviation value includes: constructing a thermal simulation scenario of an outdoor hydrogen energy power generation device, using the identification accuracy of the unstable coupling category as the evaluation index, selecting the heat flux density deviation value corresponding to the evaluation index meeting the requirements, and recording it as the preset heat flux density deviation value.

[0046] In this embodiment of the invention, the process of the thermal sensitivity analysis module determining the unstable coupling category includes: for any sensitive unit, if the heat flux density deviation value is greater than the preset heat flux density deviation value, it is determined that the sensitive unit is dominated by external radiation overload, and the root cause of thermal instability is radiation overload type instability; if its heat flux density deviation value is less than or equal to the preset heat flux density deviation value, it is determined that the sensitive unit is dominated by internal heat dissipation obstruction, and the root cause of thermal instability is heat dissipation obstruction type instability.

[0047] Specifically, the model correction module determines the correction method as global correction when the number of sensitive units is less than the preset number of sensitive units.

[0048] In this embodiment of the invention, the model correction module's global correction process includes: acquiring the heat flux density deviation values ​​of all sensitive units and calculating the average value as a global heat flux deviation characteristic; inputting the global heat flux deviation characteristic into the temperature prediction model; and, based on the sign and amplitude of the global heat flux deviation characteristic, performing a one-time correction on the equivalent total thermal resistance and equivalent total heat capacity in the temperature prediction model. Specifically, when the global heat flux deviation characteristic is positive, the equivalent total thermal resistance is increased to characterize the increased heat dissipation burden caused by the aggravated external heat input; when the global heat flux deviation characteristic is negative, the equivalent total thermal resistance is decreased to characterize the attenuation of heat dissipation capacity caused by internal heat accumulation. The corrected temperature prediction model directly outputs the overall temperature prediction value of the enclosure as the input basis for the heat dissipation control module.

[0049] In this embodiment of the invention, the thermal resistance amplitude correction adjustment process includes: the adjusted equivalent total thermal resistance is the product of the original equivalent total thermal resistance and the adjustment parameter. The adjustment parameter is the product of the ratio of the preset temperature deviation to the current measured temperature prediction deviation and the thermal resistance adjustment coefficient. When the measured temperature prediction deviation exceeds the preset temperature deviation, it indicates that the current thermal resistance setting is too low, causing the model response to be too fast or too high; when the measured temperature prediction deviation is less than the preset temperature deviation, it indicates that the current thermal resistance setting is too high, causing the model response to be sluggish. A thermal simulation scenario is constructed, and the convergence effect of the temperature prediction deviation under different coefficient values ​​is used as an evaluation index. The thermal resistance adjustment coefficient corresponding to the requirement that the evaluation index meets the requirements is selected.

[0050] Specifically, the model correction module determines the correction method as partition correction when the number of sensitive units is greater than or equal to the preset number of sensitive units.

[0051] In this embodiment of the invention, the process of model correction module based on partition correction includes: dividing the surface of the box into several non-overlapping correction partitions according to the spatial distribution of each sensitive unit on the surface of the box, each correction partition containing at least one sensitive unit, and the sensitive units in the same correction partition being spatially continuous; for each correction partition, calculating the average value of the heat flux density deviation of all sensitive units in the partition as the average heat flux deviation characteristic of the partition; if the average heat flux deviation characteristic is positive, increasing the local equivalent thermal resistance corresponding to the partition; if the average heat flux deviation characteristic is negative, decreasing the local equivalent thermal resistance corresponding to the partition; after each correction partition independently completes the correction of local equivalent thermal resistance and equivalent heat capacity, the local temperature prediction values ​​of each partition are fused by linear spatial interpolation to obtain the full-field temperature prediction distribution of the box surface.

[0052] In this embodiment, the process of obtaining the preset number of sensitive units includes: constructing a thermal simulation scenario of an outdoor hydrogen energy power generation device under different combinations of rainfall intensity and solar radiation intensity; gradually changing the value of the number of sensitive units in each simulation scenario; using the prediction accuracy of the temperature prediction model after correction as the evaluation index; selecting the number of sensitive units corresponding to the prediction accuracy meeting the requirements; and recording this as the preset number of sensitive units.

[0053] Specifically, the model correction module determines the partition correction benchmark as the instability equilibrium value when the instability coupling degree is less than the preset instability coupling degree in response to the condition that the instability coupling degree is less than the preset instability coupling degree. When the response instability coupling degree is greater than or equal to the preset instability coupling degree, the partition correction benchmark is determined as the instability category; The degree of instability coupling is determined based on the heat flux density deviation value corresponding to each sensitive unit.

[0054] In this embodiment of the invention, the model correction module includes a coupling analysis unit for obtaining the instability coupling degree. The acquisition process includes determining the instability coupling degree based on the heat flux density deviation value and the theoretical heat flux density value. The instability coupling degree is positively correlated with the degree of instability. In this embodiment, the ratio of the absolute value of the heat flux density deviation value to the absolute value of the theoretical heat flux density value is calculated and denoted as the instability coupling degree. It can be understood that the instability coupling degree is used to determine the relative degree of deviation of the measured heat flux from the theoretical heat flux of each sensitive unit and its instability direction. The larger the absolute value of the instability coupling degree, the more serious the deviation of the measured heat flux from the theoretical expectation, and the higher the urgency of parameter adjustment.

[0055] In this embodiment of the invention, the process of obtaining the preset instability coupling degree includes: constructing a thermal simulation scenario of an outdoor hydrogen energy power generation device, and applying radiation overload conditions and heat dissipation inhibition conditions of different intensities to different areas on the surface of the enclosure to simulate different degrees of instability. Under each simulation scenario, the absolute value of the instability coupling degree is gradually increased, and the instability coupling degree corresponding to when the temperature prediction accuracy is used as the evaluation index is selected, and recorded as the preset instability coupling degree.

[0056] In this embodiment of the invention, the process by which the model correction module determines the partition correction benchmark based on the instability equilibrium value includes: calculating the average value of the ratio of the current heat flux density deviation value of all sensitive units to the theoretical heat flux density value, and using the average value as the unified correction benchmark for each correction partition; each correction partition determines the adjustment direction of the local equivalent thermal resistance according to the sign of the unified correction benchmark, that is, when the benchmark is positive, the thermal resistance is increased, and when the benchmark is negative, the thermal resistance is decreased; each correction partition determines the adjustment range of the local equivalent thermal resistance according to the absolute value of the unified correction benchmark, and all partitions adopt the same adjustment range.

[0057] In this embodiment of the invention, the process by which the model correction module determines the partition correction benchmark based on the instability category includes: for each correction partition, counting the number of sensitive units belonging to radiation overload instability and the number of sensitive units belonging to heat dissipation hindrance instability within that partition; if the proportion of radiation overload instability units in that partition is greater than the proportion of heat dissipation hindrance instability units, then the average value of the instability coupling degree of all radiation overload instability units in that partition is used as the correction benchmark for that partition; if the proportion of heat dissipation hindrance instability units in that partition is greater than the proportion of radiation overload instability units, then the average value of the instability coupling degree of all heat dissipation hindrance instability units in that partition is used as the correction benchmark for that partition; if the proportions of the two types of instability units in that partition are equal, then the median value of the instability coupling degree of all sensitive units in that partition is used as the correction benchmark for that partition; each correction partition independently adjusts the local equivalent thermal resistance according to its own correction benchmark, wherein when the correction benchmark is positive, the equivalent thermal resistance is increased, and when the correction benchmark is negative, the equivalent thermal resistance is decreased, and the adjustment magnitude corresponds to the absolute value of the correction benchmark.

[0058] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0059] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A hydrogen energy power generation system based on water cooling, characterized in that, include: The heat load analysis module is used to determine whether to perform heat load analysis based on the temperature difference of the enclosure and the degree of shading from rainfall radiation. The thermal sensitivity analysis module is used in thermal load analysis to determine whether to perform thermal sensitivity analysis on the target box based on the hot spot temperature rise rate of the box surface temperature field; in thermal sensitivity analysis, it determines whether to adjust the sensitive element division benchmark from a uniform grid benchmark to a thermal feature tracking benchmark based on the temperature gradient dispersion; and it determines whether to adjust the tracking benchmark from global coverage to local focus based on the hot spot focusing coefficient. Based on the division benchmark, several sensitive elements are obtained, and the instability coupling category of the sensitive element is determined based on the heat flux density deviation value. The model correction module is used to determine whether the correction method is changed from global correction to partition correction based on the number of sensitive units. In the partition correction, the partition correction benchmark is determined from the instability equilibrium value to the instability category based on the instability coupling degree. The heat dissipation control module is used to generate water-cooling heat dissipation control parameters for the hydrogen energy power generation device based on the received temperature prediction values.

2. The hydrogen energy power generation system based on water cooling according to claim 1, characterized in that, The heat load analysis module determines to perform heat load analysis in response to conditions where the temperature difference between the enclosures is greater than the preset temperature difference or the rainfall radiation shielding is less than the preset rainfall radiation shielding. The rainfall radiation shielding degree is determined based on the rainfall intensity and solar radiation intensity; The rainfall radiation shielding degree is positively correlated with the rainfall intensity; The rainfall radiation shielding degree is negatively correlated with the solar radiation intensity.

3. The hydrogen energy power generation system based on water cooling according to claim 2, characterized in that, The thermal sensitivity analysis module responds to the condition that the hot spot temperature rise rate is greater than the preset hot spot temperature rise rate, and determines to perform thermal sensitivity analysis on the target enclosure.

4. The hydrogen energy power generation system based on water cooling according to claim 3, characterized in that, The thermal sensitivity analysis module determines the sensitive element division benchmark as a uniform grid benchmark when the temperature gradient dispersion is less than the preset temperature gradient dispersion. The temperature gradient dispersion is determined based on the temperature gradient amplitude at each sampling point on the surface of the enclosure.

5. The hydrogen energy power generation system based on water cooling according to claim 4, characterized in that, The thermal sensitivity analysis module determines the sensitive unit division benchmark as the thermal feature tracking benchmark when the temperature gradient dispersion is greater than or equal to the preset temperature gradient dispersion.

6. The hydrogen energy power generation system based on water cooling according to claim 5, characterized in that, The thermal sensitivity analysis module determines the tracking benchmark as global coverage when the hot spot focusing coefficient is less than the preset hot spot focusing coefficient. If the hot spot focus coefficient is greater than or equal to the preset hot spot focus coefficient, the tracking benchmark is determined to be local focus; The hotspot focusing coefficient is determined based on the hotspot temperature rise rate and the temperature gradient dispersion.

7. The hydrogen energy power generation system based on water cooling according to claim 6, characterized in that, The heat-sensitive analysis module determines the instability coupling type as radiation overload instability when the heat flux density deviation value is greater than the preset heat flux density deviation value. If the response heat flux density deviation is less than or equal to the preset heat flux density deviation, the instability coupling type is determined to be heat dissipation hindrance type instability. The heat flux density deviation value is determined based on the heat flux density corresponding to each sensitive unit.

8. The hydrogen energy power generation system based on water cooling according to claim 7, characterized in that, The model correction module determines the correction method as global correction when the number of sensitive units is less than the preset number of sensitive units.

9. The hydrogen energy power generation system based on water cooling according to claim 8, characterized in that, The model correction module determines the correction method as partition correction when the number of sensitive units is greater than or equal to the preset number of sensitive units.

10. The hydrogen energy power generation system based on water cooling according to claim 9, characterized in that, The model correction module determines the partition correction benchmark as the instability equilibrium value when the response instability coupling degree is less than the preset instability coupling degree. When the response instability coupling degree is greater than or equal to the preset instability coupling degree, the partition correction benchmark is determined as the instability category; The degree of instability coupling is determined based on the heat flux density deviation value corresponding to each sensitive unit.

Images