Direct liquid cooling precision directional cooling heat dissipation method and system

Abstract

The application provides a direct liquid cooling precise directional cooling and heat dissipation method and system, relates to the electronic equipment heat dissipation technical field, and the method comprises the following steps: collecting power consumption data of target devices to be cooled and establishing a power consumption distribution model; determining the target flow of the cooling working medium corresponding to each target device to be cooled according to the power consumption distribution model; based on the Bernoulli equation and the flow resistance network model, the relationship between the target flow and the pipe diameter of the liquid delivery pipe, the hole diameter and the number of the outlet holes on the liquid delivery pipe is established, and the passive flow splitting of the cooling working medium is carried out; the passive flow splitting cooling working medium is directionally sprayed to the surface of the target device to be cooled to carry out cooling and heat dissipation, so that the amount of the cooling working medium is greatly reduced, the cooling performance is significantly improved, and the passive flow splitting and precise directional cooling and heat dissipation of the cooling working medium are realized.

Description

Technical Field

[0001] This invention relates to the field of heat dissipation technology for electronic devices, and in particular to a direct liquid cooling precision directional cooling heat dissipation method and system. Background Technology

[0002] With the rapid development of artificial intelligence, high-performance computing, and large-scale model inference, the power density of a single data center rack has jumped from the traditional 3-5kW to 30-50kW. Traditional air cooling is approaching its physical limits, making direct liquid cooling technology crucial for high-power-density data centers. Existing direct liquid cooling technologies mainly include immersion cooling and spray cooling, both of which have significant drawbacks.

[0003] Immersion cooling involves completely submerging electronic equipment in an insulating coolant, such as mineral oil, synthetic ester oil, or fluorinated liquid. However, this method requires a huge amount of coolant; a 42U rack requires 500-1000L of coolant, weighing 500-900kg, placing extremely high demands on the load-bearing capacity of data center buildings. Furthermore, the uniform distribution of the coolant across all components results in lower flow rates at the points requiring cooling, limiting cooling performance. Additionally, maintenance requires lifting the entire electronic device out, leading to high repair costs.

[0004] Spray cooling allows the cooling medium to flow from top to bottom over the surface of the heat-generating device. However, as the cooling medium flows along the direction of gravity, downstream devices are easily affected by upstream devices. The upstream devices consume the cooling medium, causing its temperature to rise. By the time the cooling medium reaches the downstream, its temperature has already increased by 5-10°C. Furthermore, the obstruction of upstream devices can significantly reduce the flow rate of the cooling medium downstream, resulting in uneven overall cooling and poor heat dissipation for downstream devices.

[0005] Existing liquid cooling plate methods, such as those where the cold plate directly contacts the chip, offer good performance, but require custom-designed cold plates for each chip model, resulting in poor versatility, complex installation, and an inability to address the challenges of retrofitting existing servers.

[0006] Therefore, it is necessary to provide a direct liquid cooling precision directional cooling and heat dissipation method and system to solve the above-mentioned technical problems. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides a direct liquid cooling precision directional cooling and heat dissipation method and system, which solves the problems of large cooling fluid consumption, high building load-bearing requirements, limited cooling performance, and complex flow control in the prior art.

[0008] This invention provides a direct liquid cooling precision directional cooling and heat dissipation method, the method comprising: Collect power consumption data of the target device to be cooled and establish a power consumption distribution model; The target flow rate of the cooling medium corresponding to each of the target devices to be cooled is determined based on the power consumption distribution model. Based on Bernoulli's equation and flow resistance network model, the relationship between the target flow rate and the diameter of the infusion tube, the diameter and number of outlet holes on the infusion tube are established, and the cooling medium is passively diverted and then directionally sprayed onto the surface of the target device to be cooled for cooling and heat dissipation.

[0009] Preferably, the step of collecting power consumption data of the target device to be cooled and establishing a power consumption distribution model includes: Collect the power consumption data of each target device to be cooled under rated operating conditions, peak load conditions and steady-state operating conditions, and summarize them to generate a device power consumption dataset. Based on the device power consumption dataset, the power consumption ratio parameter of each target device to be cooled to the total power consumption of all target devices to be cooled is calculated. Obtain the spatial layout position of each of the target devices to be cooled, and associate and map the spatial layout position of each of the target devices to be cooled with the corresponding power consumption ratio parameter to construct the power consumption distribution model.

[0010] Preferably, the step of calculating the power consumption ratio parameter of each target device to be cooled to the total power consumption of all target devices to be cooled based on the device power consumption dataset includes: The power consumption data of each target device to be cooled under the rated operating condition, the peak load condition and the steady-state operating condition are weighted according to the preset operating condition weight to obtain the target power consumption corresponding to each target device to be cooled. The target power consumption corresponding to each of the target devices to be cooled is summed to obtain the total power consumption of all the target devices to be cooled; The power consumption ratio parameter corresponding to each of the target devices to be cooled is obtained by performing a ratio calculation with the target power consumption corresponding to each target device to be cooled as the numerator and the total power consumption as the denominator.

[0011] Preferably, determining the target flow rate of the cooling medium corresponding to each of the target devices to be cooled based on the power consumption distribution model includes: The power consumption ratio parameters corresponding to each of the target devices to be cooled and the total power consumption E of all the target devices to be cooled are retrieved from the power consumption distribution model. The density ρ, specific heat capacity at constant pressure c, and the design allowable temperature rise T of the cooling medium after flowing through the target device to be cooled are obtained. Based on the principle of thermal balance, and according to the total power consumption E, the density ρ of the cooling medium, the specific heat capacity at constant pressure c, and the design allowable temperature rise T, the total target flow rate L of the cooling medium is calculated: ; The total target flow rate is multiplied by the power consumption ratio parameter corresponding to each of the target devices to be cooled to obtain the target flow rate of the cooling medium corresponding to each target device to be cooled.

[0012] Preferably, establishing the relationship between the target flow rate and the diameter of the infusion tube, the diameter and number of outlet orifices on the infusion tube, based on Bernoulli's equation and flow resistance network model, includes: Obtain the density ρ of the cooling working fluid and the orifice flow coefficient μ of the outlet orifice. Based on Bernoulli's energy equation, construct the output flow rate q of the outlet orifice in relation to the orifice diameter d and the working pressure difference at the outlet orifice. Based on the relationship between the outlet orifice and the output flow rate q, the output flow rate q is calculated. ; Based on the single-orifice flow rate calculation model and combined with the pressure equalization mechanism of the parallel flow resistance network, it is determined that the working pressure difference of each outlet orifice arranged in parallel along the same infusion tube is consistent. The output flow rates of each outlet orifice are summed to obtain the relationship between the total output flow rate Q of the infusion tube and the orifice diameter d and the number n of the outlet orifices: ; Based on the multi-orifice parallel total flow model, the fluid friction resistance formula is introduced to calculate the friction pressure loss of the corresponding pipe section under different pipe diameters of the infusion pipe. Combined with the system working pressure difference at the inlet of the infusion pipe, the actual working pressure difference of each outlet orifice is obtained and substituted into the multi-orifice parallel total flow model to construct a flow distribution model between the pipe diameter of the infusion pipe, the orifice diameter and number of the outlet orifices. Substitute the target flow rate of each of the target devices to be cooled into the flow distribution model, and inversely solve to obtain the matching combination of the pipe diameter of the infusion tube, the orifice diameter and the number of the outlet orifice, and establish the relationship between the target flow rate and the pipe diameter of the infusion tube, the orifice diameter and the number of the outlet orifice.

[0013] Preferably, the fluid friction loss formula is used to calculate the friction loss of the corresponding pipe section under different pipe diameters in the infusion pipe. The corresponding calculation formula is as follows: ; In the formula, is the friction factor; l is the length of the corresponding pipe section; D is the diameter of the infusion pipe; v is the average flow velocity of the cooling medium in the infusion pipe.

[0014] A direct liquid cooling precision directional cooling heat dissipation system includes: a main inlet for receiving a cooling medium; a main pipe connected to the main inlet; at least one delivery pipe, one end of which is connected to the main pipe and the other end of which extends to the vicinity of the target device to be cooled; and at least one outlet hole disposed on the delivery pipe for directionally spraying the cooling medium onto the surface of the target device to be cooled.

[0015] Preferably, a distributor is provided between the main pipeline and each of the infusion pipes, the distributor being used to distribute the cooling working fluid to each of the infusion pipes; the diameter of the infusion pipe is a tapered or variable diameter structure with a small diameter in the middle section and a large diameter at both ends; the middle section of the infusion pipe is formed by bonding or sewing.

[0016] Preferably, the infusion tube is made of a flexible non-metallic insulating material, which is at least one of fiber cloth, rubber, and plastic; the cooling medium is one of synthetic ester oil, fluoride, and deionized water.

[0017] Preferably, the outlet hole is disposed on the wall of the infusion tube, and the spray direction of the outlet hole is perpendicular to the pipe axis of the infusion tube; and / or disposed at the end of the infusion tube, and the spray direction of the outlet hole is parallel to the pipe axis of the infusion tube; the diameter of each outlet hole is the same or different; a micro atomizing nozzle is disposed at the outlet end of the outlet hole, and the micro atomizing nozzle is used to atomize the cooling working fluid and spray it directionally onto the surface of the target device to be cooled.

[0018] Compared with related technologies, the direct liquid cooling precision directional cooling and heat dissipation method and system provided by the present invention have the following beneficial effects: This invention collects power consumption data of the target device to be cooled and establishes a power consumption distribution model; determines the target flow rate of the cooling medium corresponding to each target device to be cooled based on the power consumption distribution model; establishes the relationship between the target flow rate and the diameter of the infusion tube, the diameter and number of outlet holes on the infusion tube based on Bernoulli's equation and flow resistance network model; and passively diverts the cooling medium, and directionally sprays the passively diverted cooling medium onto the surface of the target device to be cooled for cooling and heat dissipation, thereby significantly reducing the amount of cooling medium used, significantly improving cooling performance, and realizing passive diversion and precise directional cooling and heat dissipation of the cooling medium.

[0019] This invention precisely delivers the cooling medium to the vicinity of each target device via a delivery pipe, allowing it to directly act on the heating surface and eliminate upstream and downstream thermal interference. Simultaneously, the cooling medium flow rate can be independently set according to the device's power consumption, ensuring heat transfer intensity in high heat flux density areas. It eliminates the need for immersion or spraying of the entire equipment, precisely delivering the cooling medium only according to the actual power consumption requirements of each device, significantly reducing the total amount of medium used and substantially lowering building load-bearing requirements. It also reduces ineffective circulation flow within the cooling system, lowering the flow and power consumption requirements of the circulation pump, improving the overall energy efficiency ratio of the cooling system, and thus improving the power utilization efficiency of the data center. The delivery pipes of this invention use flexible non-metallic insulating material, which can be bent and laid in any position, eliminating the need for customized cold plates for each device. This makes it suitable for new deployments and retrofitting of existing equipment. Furthermore, the use of non-metallic insulating material in conjunction with an insulating cooling medium avoids the risk of electrical short circuits. The outlet orifice diameter is set according to the power consumption ratio of each target device, achieving natural flow division through Bernoulli's equation and pressure difference, eliminating the need for valve, sensor, or pump control systems, thus reducing system complexity and cost. Attached Figure Description

[0020] Figure 1 A flowchart of a direct liquid cooling precision directional cooling and heat dissipation method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a direct liquid cooling precision directional cooling and heat dissipation system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention.

[0021] In the diagram: 1. Main inlet; 2. Main pipe; 3. Infusion pipe; 4. Outlet orifice; 5. Dispenser; 6. Miniature atomizing nozzle. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] like Figure 1 The diagram shown is a flowchart of a direct liquid cooling precision directional cooling and heat dissipation method provided in an embodiment of the present invention. Figure 1The execution subject of the method shown can be a software and / or hardware device. The execution subject of this invention can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S3 are detailed as follows: S1: Collect power consumption data of the target device to be cooled and establish a power consumption distribution model.

[0024] The process of collecting power consumption data of the target device to be cooled and establishing a power consumption distribution model includes: Collect the power consumption data of each target device to be cooled under rated operating conditions, peak load conditions and steady-state operating conditions, and summarize them to generate a device power consumption dataset. Based on the device power consumption dataset, the power consumption ratio parameter of each target device to be cooled to the total power consumption of all target devices to be cooled is calculated. Obtain the spatial layout position of each of the target devices to be cooled, and associate and map the spatial layout position of each of the target devices to be cooled with the corresponding power consumption ratio parameter to construct the power consumption distribution model.

[0025] The calculation of the target power consumption ratio of each target device to be cooled relative to the total power consumption of all target devices to be cooled, based on the device power consumption dataset, includes: The power consumption data of each target device to be cooled under the rated operating condition, the peak load condition and the steady-state operating condition are weighted according to the preset operating condition weight to obtain the target power consumption corresponding to each target device to be cooled. The target power consumption corresponding to each of the target devices to be cooled is summed to obtain the total power consumption of all the target devices to be cooled; The power consumption ratio parameter corresponding to each of the target devices to be cooled is obtained by performing a ratio calculation with the target power consumption corresponding to each target device to be cooled as the numerator and the total power consumption as the denominator.

[0026] In practical applications, power consumption data for each target device to be cooled is collected under rated operating conditions, peak load conditions, and steady-state operating conditions. Rated operating conditions correspond to the heat generation level of the device under its nominal operating state; peak load conditions correspond to the maximum heat generation power of the device when operating at full load; and steady-state operating conditions correspond to the continuous heat generation characteristics of the device during long-term stable operation. These conditions can cover the operating states of devices in application scenarios such as data center servers and battery modules. The power consumption data from multiple operating conditions is categorized and summarized to generate a standardized device power consumption dataset, thus avoiding redundancy or inadequacy in heat dissipation capacity caused by designing for a single operating condition.

[0027] Based on the device power consumption dataset, the power consumption data under these operating conditions are weighted according to preset operating condition weights to obtain the target power consumption for each device to be cooled. The preset operating condition weights can be set according to the corresponding operating conditions; for example, the steady-state operating condition has the highest weight to match the actual needs of long-term equipment operation. The target power consumption of all devices to be cooled is summed to obtain the total power consumption. Then, the ratio of the target power consumption of each device (numerator) to the total power consumption (denominator) is calculated to obtain the power consumption ratio parameter for each device. This parameter directly reflects the proportion of each device's heat dissipation demand in the total heat dissipation demand.

[0028] The spatial layout of each target device to be cooled within the corresponding equipment is obtained, including the planar coordinates, installation height, and relative arrangement of each device. The spatial layout of each device is then mapped one-to-one with its corresponding power consumption ratio parameters, forming a power distribution model with both spatial and thermal attributes. This model can be used to design the layout path and outlet location of flexible infusion tubing, thereby ensuring precise alignment of the outlet with the corresponding device and eliminating upstream and downstream thermal interference.

[0029] S2, determine the target flow rate of the cooling medium corresponding to each of the target devices to be cooled according to the power consumption distribution model.

[0030] The step of determining the target flow rate of the cooling medium corresponding to each of the target devices to be cooled based on the power consumption distribution model includes: The power consumption ratio parameters corresponding to each of the target devices to be cooled and the total power consumption E of all the target devices to be cooled are retrieved from the power consumption distribution model. The density ρ, specific heat capacity at constant pressure c, and the design allowable temperature rise T of the cooling medium after flowing through the target device to be cooled are obtained. Based on the principle of thermal balance, and according to the total power consumption E, the density ρ of the cooling medium, the specific heat capacity at constant pressure c, and the design allowable temperature rise T, the total target flow rate L of the cooling medium is calculated: ; The total target flow rate is multiplied by the power consumption ratio parameter corresponding to each of the target devices to be cooled to obtain the target flow rate of the cooling medium corresponding to each target device to be cooled.

[0031] From the power distribution model, the power consumption ratio parameters corresponding to each target device to be cooled, as well as the total power consumption E of all target devices to be cooled, are retrieved. Simultaneously, the density ρ, specific heat capacity at constant pressure c, and the design-allowed temperature rise T of the cooling medium after flowing through the target device are obtained. Here, density and specific heat capacity at constant pressure are inherent physical properties of the selected cooling medium; the design-allowed temperature rise is a preset maximum temperature rise threshold at the medium outlet, used to constrain the upper temperature limit of the cooling medium after heat absorption, ensuring that the device surface temperature remains within a safe operating range, thus matching the temperature control requirements of scenarios such as high-power-density servers.

[0032] Based on the principle of thermal balance, where the total heat generated by all target devices to be cooled in the system is equal to the total heat absorbed by the cooling medium after it flows through the system, the total target flow rate of the cooling medium is calculated by taking into account the total power consumption, the density of the cooling medium, the specific heat capacity at constant pressure, and the design allowable temperature rise. This allows the minimum circulation flow rate that meets the heat dissipation requirements of all devices to be determined based on the total heat dissipation requirements of the system. This effectively reduces the ineffective circulation flow in traditional immersion and spray solutions, lowers the flow rate and power consumption requirements of the circulation pump, and significantly improves the PUE (Power Usage Effectiveness) of the data center.

[0033] The calculated total target flow rate is multiplied by the power consumption ratio parameter corresponding to each target device to be cooled to obtain the target flow rate of the cooling medium for each device. This allows high heat-consuming devices to obtain more cooling medium, avoiding the problems of insufficient heat dissipation for high-heat devices and redundant flow for low-heat devices caused by uniform flow distribution. It also enables precise flow distribution of the cooling medium without the need for active valve or pump control system intervention.

[0034] S3. Based on Bernoulli's equation and flow resistance network model, establish the relationship between the target flow rate and the diameter of the infusion tube, the diameter and number of outlet holes on the infusion tube, and passively divert the cooling medium, and directionally spray the passively diverted cooling medium onto the surface of the target device to be cooled for cooling and heat dissipation.

[0035] The process of establishing the relationship between the target flow rate and the diameter of the infusion tubing, the diameter and number of outlet orifices on the infusion tubing, based on Bernoulli's equation and flow resistance network model, includes: Obtain the density ρ of the cooling working fluid and the orifice flow coefficient μ of the outlet orifice. Based on Bernoulli's energy equation, construct the output flow rate q of the outlet orifice in relation to the orifice diameter d and the working pressure difference at the outlet orifice. Based on the relationship between the outlet orifice and the output flow rate q, the output flow rate q is calculated. ; Based on the single-orifice flow rate calculation model and combined with the pressure equalization mechanism of the parallel flow resistance network, it is determined that the working pressure difference of each outlet orifice arranged in parallel along the same infusion tube is consistent. The output flow rates of each outlet orifice are summed to obtain the relationship between the total output flow rate Q of the infusion tube and the orifice diameter d and the number n of the outlet orifices: ; Based on the multi-orifice parallel total flow model, the fluid friction resistance formula is introduced to calculate the friction pressure loss of the corresponding pipe section under different pipe diameters of the infusion pipe. Combined with the system working pressure difference at the inlet of the infusion pipe, the actual working pressure difference of each outlet orifice is obtained and substituted into the multi-orifice parallel total flow model to construct a flow distribution model between the pipe diameter of the infusion pipe, the orifice diameter and number of the outlet orifices. Substitute the target flow rate of each of the target devices to be cooled into the flow distribution model, and inversely solve to obtain the matching combination of the pipe diameter of the infusion tube, the orifice diameter and the number of the outlet orifice, and establish the relationship between the target flow rate and the pipe diameter of the infusion tube, the orifice diameter and the number of the outlet orifice.

[0036] The fluid friction loss formula is introduced to calculate the friction loss of the corresponding pipe section under different pipe diameters in the infusion pipe. The corresponding calculation formula is as follows: ; In the formula, is the friction factor; l is the length of the corresponding pipe section; D is the diameter of the infusion pipe; v is the average flow velocity of the cooling medium in the infusion pipe.

[0037] The density of the cooling medium and the orifice flow coefficient of the outlet orifice are obtained. Based on Bernoulli's energy equation, a quantitative relationship is constructed between the output flow rate of a single outlet orifice and the orifice diameter and working pressure difference. The orifice flow coefficient can be determined according to the processing form and edge structure of the outlet orifice.

[0038] Based on the pressure equalization mechanism of parallel flow resistance network, that is, the working pressure difference of each outlet hole arranged in parallel along the same infusion tube is consistent. The output flow of each outlet hole is superimposed and summed to obtain the correlation between the total output flow of a single infusion tube and the diameter and number of outlet holes. Thus, the joint control law of hole diameter and number of holes on the total flow can be clarified.

[0039] Based on a multi-orifice parallel total flow model, the fluid friction loss formula is introduced to calculate the friction loss of each pipe section under different pipe diameters. Combined with the system working pressure difference at the inlet of the infusion pipe, the actual working pressure difference of the outlet orifices at different locations is corrected and substituted into the multi-orifice parallel total flow model. Friction loss is directly related to the infusion pipe diameter; the smaller the pipe diameter, the higher the flow velocity and the greater the friction loss. This correction accurately reflects the impact of the pipe diameter on the flow distribution of each outlet orifice, forming a flow distribution model that simultaneously covers the infusion pipe diameter, outlet orifice diameter, and number of outlet orifices, to adapt to the needs of complex structures such as tapered variable diameter infusion pipes.

[0040] By substituting the target flow rate corresponding to each target device to be cooled into the flow distribution model, and through numerical inversion, the matching combination of pipe diameter, orifice diameter, and orifice number that meets the flow accuracy requirements is obtained, establishing a quantitative relationship between the target flow rate and the pipe diameter of the delivery pipe, and the orifice diameter and number of the outlet orifice. This inversion process can achieve precise passive flow distribution of the cooling medium by configuring only geometric parameters, without the intervention of valve, sensor, or pump control system.

[0041] like Figure 2 The diagram shown is a structural schematic of a direct liquid cooling precision directional cooling heat dissipation system provided in an embodiment of the present invention. The system includes: a main inlet 1 for receiving the cooling medium; a main pipe 2 connected to the main inlet 1; at least one liquid delivery pipe 3, one end of which is connected to the main pipe 2 and the other end extends to the vicinity of the target device to be cooled; and at least one outlet hole 4, which is disposed on the liquid delivery pipe 3 for directionally spraying the cooling medium onto the surface of the target device to be cooled.

[0042] A distributor 5 is provided between the main pipeline 2 and each of the infusion pipes 3. The distributor 5 is used to distribute the cooling working fluid to each of the infusion pipes 3. The diameter of the infusion pipe 3 is a tapered or variable diameter structure with a small diameter in the middle section and a large diameter at both ends. The middle section of the infusion pipe 3 is formed by bonding or sewing.

[0043] The infusion tube 3 is made of a flexible non-metallic insulating material, which is at least one of fiber cloth, rubber, and plastic; the cooling medium is one of synthetic ester oil, fluoride, and deionized water.

[0044] The outlet hole 4 is disposed on the wall of the infusion tube 3, and the spray direction of the outlet hole 4 is perpendicular to the pipe axis of the infusion tube 3; and / or disposed at the end of the infusion tube 3, and the spray direction of the outlet hole 4 is parallel to the pipe axis of the infusion tube 3; the diameter of each outlet hole 4 may be the same or different; a micro atomizing nozzle 6 is disposed at the outlet end of the outlet hole 4, and the micro atomizing nozzle 6 is used to atomize the cooling working fluid and spray it directionally onto the surface of the target device to be cooled.

[0045] Figure 2 The system of the illustrated embodiment can be used to perform corresponding operations. Figure 1 The steps in the method embodiment shown.

[0046] In practical applications, the system's main transport route includes a main inlet 1 and a main pipeline 2. Main inlet 1 is the system input terminal for the cooling medium, used to connect to the external circulating liquid supply pipeline to receive the cooling medium delivered under stable pressure. Downstream of main inlet 1, it is sealed to main pipeline 2, which is the system's main transport pipeline. Its diameter is larger than that of each downstream liquid delivery pipe 3, used to uniformly and steadily deliver the cooling medium to the distributor 5, ensuring a stable working pressure differential at each branch inlet.

[0047] A distributor 5 is installed between the main pipeline 2 and each infusion pipe 3. The distributor 5 is a single-inlet, multi-outlet diversion component. Its inlet end is sealed to the main pipeline 2, and each outlet end is sealed to the corresponding infusion pipe 3. It is used to initially distribute the cooling medium in the main pipeline 2 to each infusion pipe 3 to achieve coarse diversion of the cooling medium. Then, in conjunction with the outlet hole 4 on the infusion pipe 3, it achieves precise diversion of the cooling medium.

[0048] The system is equipped with at least one infusion tube 3. In this embodiment, two infusion tubes 3 are arranged in parallel. One end of each infusion tube 3 is sealed to the outlet of the distributor 5, and the other end extends independently to the vicinity of the corresponding target device to be cooled. The infusion tube 3 is made of flexible non-metallic insulating material, and the optional material includes at least one of fiber cloth, rubber, and plastic. It has the characteristic of being able to be freely bent and deformed, which can adapt to the complex spatial layout structure inside the cabinet. There is no need to customize rigid pipes for each device. At the same time, it has the characteristics of insulation and safety, and can avoid the risk of electrical short circuit when used with insulating cooling medium. The diameter of the infusion tube 3 is a tapered or variable diameter structure with a small diameter in the middle section and a large diameter at both ends. The large diameter at both ends facilitates a reliable sealing connection with the distributor 5 and the end structure, while the small diameter in the middle section can increase the flow rate of the working medium in the tube and optimize the resistance distribution along the friction. Moreover, the small channel structure in the middle section is formed by bonding or sewing, which is compatible with the processing characteristics of flexible materials.

[0049] Each infusion tube 3 is provided with at least one outlet hole 4. In this embodiment, the outlet holes 4 are arranged in parallel along the axial direction of the infusion tube 3, and their spray direction is perpendicular to the pipe axis of the infusion tube 3. The outlet holes 4 can also be set at the end of the infusion tube 3, with the spray direction parallel to the pipe axis. The two arrangement methods can be used alone or in combination. The orifice diameter of each outlet hole 4 can be set to be the same or different according to the power consumption ratio parameter of the corresponding target device to be cooled. The combination of orifice diameter and number jointly determines the output flow rate at a single point, realizing the passive and precise diversion of the cooling medium. A micro atomizing nozzle 6 is provided at the outlet end of the outlet hole 4. The micro atomizing nozzle 6 is used to break the cooling medium into uniform droplets and spray them directionally onto the surface of the target device to be cooled, increasing the spray contact area and improving the device cooling efficiency. The cooling medium used in the system is one of synthetic ester oil, fluoride, or deionized water, all of which have electrical insulation properties and are suitable for applications where electronic equipment is directly contacted for cooling.

[0050] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor performs the steps described in any of the above.

[0051] like Figure 3 The diagram shown is a hardware structure schematic of an electronic device according to an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32, and a computer program; wherein... The memory 32 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0052] Processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0053] Alternatively, the memory 32 can be either standalone or integrated with the processor 31.

[0054] When the memory 32 is a device independent of the processor 31, the device may further include: Bus 33 is used to connect the memory 32 and the processor 31.

[0055] A readable storage medium storing a computer program, which, when executed by a processor, is used to perform the steps described in any of the above.

[0056] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0057] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0058] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A direct liquid cooling method for precise directional cooling and heat dissipation, characterized in that, The method includes: Collect power consumption data of the target device to be cooled and establish a power consumption distribution model; The target flow rate of the cooling medium corresponding to each of the target devices to be cooled is determined based on the power consumption distribution model. Based on Bernoulli's equation and flow resistance network model, the relationship between the target flow rate and the diameter of the infusion tube, the diameter and number of outlet holes on the infusion tube are established, and the cooling medium is passively diverted and then directionally sprayed onto the surface of the target device to be cooled for cooling and heat dissipation.

2. The direct liquid cooling precision directional cooling and heat dissipation method according to claim 1, characterized in that, The process of collecting power consumption data of the target device to be cooled and establishing a power consumption distribution model includes: Collect the power consumption data of each target device to be cooled under rated operating conditions, peak load conditions and steady-state operating conditions, and summarize them to generate a device power consumption dataset. Based on the device power consumption dataset, the power consumption ratio parameter of each target device to be cooled to the total power consumption of all target devices to be cooled is calculated. Obtain the spatial layout position of each of the target devices to be cooled, and associate and map the spatial layout position of each of the target devices to be cooled with the corresponding power consumption ratio parameter to construct the power consumption distribution model.

3. The direct liquid cooling precision directional cooling and heat dissipation method according to claim 2, characterized in that, The calculation of the target power consumption ratio of each target device to be cooled relative to the total power consumption of all target devices to be cooled, based on the device power consumption dataset, includes: The power consumption data of each target device to be cooled under the rated operating condition, the peak load condition and the steady-state operating condition are weighted according to the preset operating condition weight to obtain the target power consumption corresponding to each target device to be cooled. The target power consumption corresponding to each of the target devices to be cooled is summed to obtain the total power consumption of all the target devices to be cooled; The power consumption ratio parameter corresponding to each of the target devices to be cooled is obtained by performing a ratio calculation with the target power consumption corresponding to each target device to be cooled as the numerator and the total power consumption as the denominator.

4. The direct liquid cooling precision directional cooling and heat dissipation method according to claim 2, characterized in that, The step of determining the target flow rate of the cooling medium corresponding to each of the target devices to be cooled based on the power consumption distribution model includes: The power consumption ratio parameters corresponding to each of the target devices to be cooled and the total power consumption E of all the target devices to be cooled are retrieved from the power consumption distribution model. The density ρ, specific heat capacity at constant pressure c, and the design allowable temperature rise T of the cooling medium after flowing through the target device to be cooled are obtained. Based on the principle of thermal balance, and according to the total power consumption E, the density ρ of the cooling medium, the specific heat capacity at constant pressure c, and the design allowable temperature rise T, the total target flow rate L of the cooling medium is calculated: ； The total target flow rate is multiplied by the power consumption ratio parameter corresponding to each of the target devices to be cooled to obtain the target flow rate of the cooling medium corresponding to each target device to be cooled.

5. The direct liquid cooling precision directional cooling and heat dissipation method according to claim 1, characterized in that, The process of establishing the relationship between the target flow rate and the diameter of the infusion tubing, the diameter and number of outlet orifices on the infusion tubing, based on Bernoulli's equation and flow resistance network model, includes: Obtain the density ρ of the cooling working fluid and the orifice flow coefficient μ of the outlet orifice. Based on Bernoulli's energy equation, construct the output flow rate q of the outlet orifice in relation to the orifice diameter d and the working pressure difference at the outlet orifice. The output flow rate q of the outlet orifice is calculated based on the relationship between the two parameters. ； Based on the single-orifice flow rate calculation model and combined with the pressure equalization mechanism of the parallel flow resistance network, it is determined that the working pressure difference of each outlet orifice arranged in parallel along the same infusion tube is consistent. The output flow rates of each outlet orifice are summed to obtain the relationship between the total output flow rate Q of the infusion tube and the orifice diameter d and the number n of the outlet orifices: ； Based on the multi-orifice parallel total flow model, the fluid friction resistance formula is introduced to calculate the friction pressure loss of the corresponding pipe section under different pipe diameters of the infusion pipe. Combined with the system working pressure difference at the inlet of the infusion pipe, the actual working pressure difference of each outlet orifice is obtained and substituted into the multi-orifice parallel total flow model to construct a flow distribution model between the pipe diameter of the infusion pipe, the orifice diameter and number of the outlet orifices. Substitute the target flow rate of each of the target devices to be cooled into the flow distribution model, and inversely solve to obtain the matching combination of the pipe diameter of the infusion tube, the orifice diameter and the number of the outlet orifice, and establish the relationship between the target flow rate and the pipe diameter of the infusion tube, the orifice diameter and the number of the outlet orifice.

6. The direct liquid cooling precision directional cooling and heat dissipation method according to claim 5, characterized in that, The fluid friction loss formula is introduced to calculate the friction loss of the corresponding pipe section under different pipe diameters in the infusion pipe. The corresponding calculation formula is as follows: ； In the formula, is the friction factor; l is the length of the corresponding pipe section; D is the diameter of the infusion pipe; v is the average flow velocity of the cooling medium in the infusion pipe.

7. A direct liquid-cooled precision directional cooling and heat dissipation system, characterized in that, The system is applied to a direct liquid cooling precision directional cooling heat dissipation method as described in any one of claims 1-6, the system comprising: a main inlet (1) for receiving a cooling medium; a main pipe (2) connected to the main inlet (1); at least one inlet pipe (3), one end of which is connected to the main pipe (2) and the other end of which extends to the vicinity of the target device to be cooled; and at least one outlet hole (4), the outlet hole (4) being disposed on the inlet pipe (3) for directionally spraying the cooling medium onto the surface of the target device to be cooled.

8. The direct liquid-cooled precision directional cooling and heat dissipation system according to claim 7, characterized in that, A distributor (5) is provided between the main pipeline (2) and each of the infusion pipes (3), and the distributor (5) is used to distribute the cooling working fluid to each of the infusion pipes (3); the diameter of the infusion pipe (3) is a tapered or variable diameter structure with a small diameter in the middle section and a large diameter at both ends; the middle section of the infusion pipe (3) is formed by bonding or sewing.

9. The direct liquid-cooled precision directional cooling and heat dissipation system according to claim 7, characterized in that, The infusion tube (3) is made of flexible non-metallic insulating material, which is at least one of fiber cloth, rubber, and plastic; the cooling medium is one of synthetic ester oil, fluoride, and deionized water.

10. The direct liquid-cooled precision directional cooling and heat dissipation system according to claim 7, characterized in that, The outlet hole (4) is disposed on the wall of the infusion tube (3), and the spray direction of the outlet hole (4) is perpendicular to the pipe axis of the infusion tube (3); and / or disposed at the end of the infusion tube (3), and the spray direction of the outlet hole (4) is parallel to the pipe axis of the infusion tube (3); the diameter of each outlet hole (4) is the same or different; a micro atomizing nozzle (6) is disposed at the outlet end of the outlet hole (4), and the micro atomizing nozzle (6) is used to atomize the cooling working medium and spray it directionally onto the surface of the target device to be cooled.

Images