Computing device

By setting an insulating shell between the electrodes of the busbar to form a cooling cavity, the refrigerant can be directly contained to absorb heat and dissipate it through a heat exchanger. This solves the problem of low heat dissipation efficiency of the busbar and achieves efficient heat dissipation and improved reliability at high power consumption nodes.

CN122069686APending Publication Date: 2026-05-19XFUSION DIGITAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XFUSION DIGITAL TECH CO LTD
Filing Date
2026-01-28
Publication Date
2026-05-19

AI Technical Summary

Technical Problem

The bus has low heat dissipation efficiency and cannot meet the heat dissipation requirements of high-power nodes.

Method used

An insulating shell is set between the first and second electrodes of the busbar to form a cooling chamber, which directly contains the refrigerant to absorb heat and dissipates heat through a heat exchanger. The insulating layer and sealing structure prevent short circuits and corrosion.

Benefits of technology

It improves the heat dissipation efficiency of the bus, meets the heat dissipation requirements of high-power nodes, reduces current transmission loss, enhances the reliability and current carrying capacity of the bus, and reduces the hazards in the power transmission process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122069686A_ABST
    Figure CN122069686A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides computing equipment, the computing equipment comprises a cabinet, a power supply device and computing nodes, and the power supply device comprises a busbar and an insulating shell. The busbar comprises a first electrode and a second electrode which are arranged oppositely, and the first electrode and the second electrode are electrically connected with the computing node. A gap is formed between the first electrode and the second electrode, the insulating shell is connected with the first electrode and the second electrode respectively, and the insulating shell is used for sealing the gap. A cooling cavity is defined by the insulating shell, the first electrode and the second electrode, and the cooling cavity is used for containing refrigerants. According to the technical scheme, the heat dissipation efficiency of the busbar can be improved, and the busbar heat dissipation requirement under a high-power-consumption node in computing equipment can be met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of server technology. , In particular, it relates to a computing device. Background Technology

[0002] Busbars, also known as power supply busbars, are responsible for receiving input power and efficiently distributing it to various devices in a server rack, while also addressing the safety, efficiency, and maintenance issues of distributed power supply. However, the heat dissipation efficiency of these busbars is not high, making them unsuitable for high-power nodes. Summary of the Invention

[0003] The purpose of this application is to provide a computing device to improve the heat dissipation efficiency of the bus and meet the bus heat dissipation requirements under high power consumption nodes.

[0004] This application provides a computing device. It includes a cabinet, a power supply unit, and computing nodes. The power supply unit includes a bus and an insulating housing. The bus includes a first electrode and a second electrode disposed opposite to each other, and the computing node is electrically connected to both the first and second electrodes. A gap exists between the first and second electrodes, and the insulating housing is connected to both the first and second electrodes, sealing the gap. The insulating housing, the first electrode, and the second electrode form a cooling chamber for containing refrigerant.

[0005] In the technical solution of this application embodiment, the computing node is electrically connected to the first electrode and the second electrode included in the bus, enabling the bus to supply power to the computing node. The first electrode and the second electrode are respectively connected to an insulating shell, allowing insulation to seal the gap between the first electrode and the second electrode. In this case, the insulating shell, the first electrode, and the second electrode can form a cooling chamber. Therefore, when the cooling chamber contains refrigerant, the refrigerant can directly contact the first electrode and the second electrode. Thus, compared to the method of placing a liquid cooling plate between the first electrode and the second electrode, the direct contact between the first electrode and the second electrode and the refrigerant allows the refrigerant to rapidly absorb the heat released by the first electrode and the second electrode when the bus supplies power to the computing node.

[0006] As can be seen, in the computing device of this application embodiment, the first and second electrodes in the power supply device are in direct contact with the refrigerant, maximizing the heat transfer of the first and second electrodes to the refrigerant, which is then dissipated through a heat exchanger. This effectively improves the heat dissipation efficiency of the bus and meets the bus heat dissipation requirements under high-power nodes. Moreover, since the insulating shell is connected to the first and second electrodes respectively, short circuits between the first and second electrodes can be prevented, ensuring normal power supply to the bus.

[0007] In one possible implementation, a first insulating layer is formed on the surface of the cooling cavity in the region where the first electrode faces the cooling cavity. This reduces the likelihood of a chemical reaction between the refrigerant and the surface of the first electrode, preventing corrosion of the first electrode by the refrigerant. Similarly, when a second insulating layer is formed on the surface of the second electrode facing the cooling cavity, the second insulating layer can prevent corrosion of the second electrode by the refrigerant.

[0008] In one possible implementation, the insulating shell includes side plates and insulating end plates. The first electrode has a first slot on its side facing the gap, and the second electrode has a second slot on its side facing the gap. The side plates can then be inserted into the first and second slots, thereby improving the sealing capability of the side plates over the side of the gap between the first and second electrodes. Simultaneously, the end plates are connected to the end faces of the first and second electrodes respectively, ensuring that the end faces of the gap between the first and second electrodes are sealed and preventing refrigerant leakage.

[0009] In one possible implementation, the power supply device further includes a first seal and a second seal. The first seal is disposed on the inner wall of the first slot, and the side plate contacts the first seal, which can effectively improve the sealing performance of the side plate and prevent poor sealing between the side plate and the first slot. Similarly, when the second seal is disposed on the inner wall of the second slot, the side plate contacts the second seal, which can also prevent poor sealing between the side plate and the second slot.

[0010] In one possible implementation, the power supply device may further include a heat exchanger whose heat dissipation channels are connected to a cooling chamber. The heat exchanger is used to dissipate heat from the refrigerant within the cooling chamber. Since the heat dissipation channels of the heat exchanger are connected to the cooling chamber containing the refrigerant, when the refrigerant is heated, it can enter the heat dissipation channels of the heat exchanger under thermal drive, allowing the heat exchanger to dissipate heat from the refrigerant. In this way, the coolant absorbing heat can be cooled by the heat exchanger.

[0011] In one possible implementation, the heat exchanger includes a liquid-cooled plate and a bladder disposed on the surface of the liquid-cooled plate, the bladder being in communication with a cooling chamber. In this case, when the first and second electrodes conduct heat to the refrigerant, the heated refrigerant can flow into the bladder, and the liquid-cooled plate can be used to cool the refrigerant entering the bladder, thereby ensuring the cooling effect of the refrigerant.

[0012] In one possible implementation, the first electrode is provided with a first channel communicating with the cooling chamber. The power supply device further includes a first pipe connected to the first channel, and the first pipe communicating with the heat dissipation channel of the heat exchanger. When the first channel of the first electrode is in communication with the cooling chamber, the first channel can provide a passage for the first pipe to communicate with the cooling chamber, ensuring that the first pipe can introduce the refrigerant in the cooling chamber into the heat dissipation channel of the heat exchanger, so that the heat exchanger can cool the refrigerant.

[0013] In one possible implementation, the first conduit includes a liquid-cooled reflux pipe, which is connected to both the cooling chamber and the heat exchanger's heat dissipation channel. Connecting the cooling chamber and the heat exchanger's heat dissipation channel via the liquid-cooled reflux pipe allows hotter refrigerant in the cooling chamber to enter the heat exchanger's heat dissipation channel for cooling, and conversely, allows cooled refrigerant in the heat exchanger's heat dissipation channel to flow back to the cooling chamber via the condensate reflux pipe. Therefore, connecting the cooling chamber and the heat exchanger's heat dissipation channel via the liquid-cooled reflux pipe reduces unnecessary piping into the cooling chamber and prevents potential refrigerant leaks.

[0014] In one possible implementation, the second electrode is provided with a second channel communicating with the cooling chamber. The power supply device also includes a second pipe connected to the second channel, which is connected to the heat dissipation channel of the heat exchanger. This method separates the flow paths of the hotter refrigerant and the cooled refrigerant, preventing mutual interference between the two.

[0015] In one possible implementation, the first electrode has a first end face facing the heat exchanger. The opening of the first channel on the surface of the heat exchanger is located on the first end face. For example, when the heat exchanger is located above the first electrode, the opening of the first channel on the surface of the heat exchanger is also located at the top of the first electrode. Therefore, when the refrigerant is heated, the refrigerant may turn into hot vapor, making it easier for it to actively enter the first pipe through the first channel and continue upward until it enters the heat dissipation channel of the heat exchanger.

[0016] In one possible implementation, the second electrode has a second end face facing away from the heat exchanger. The opening of the second channel on the surface of the heat exchanger is located on the second end face. For example, when the heat exchanger is located above the first electrode, the opening of the second channel on the surface of the heat exchanger is located at the bottom of the second electrode. Therefore, after the refrigerant dissipates heat through the heat exchanger, the refrigerant may change from hot vapor to refrigerant liquid, increasing its density. Thus, under the influence of gravity, it can more actively enter the second channel through the first pipe and eventually enter the cooling chamber.

[0017] In one possible implementation, the surface of the first electrode facing the cooling cavity is a recessed structure, which can increase the contact area between the liquid coolant in the cooling cavity and the first electrode, thereby maximizing heat dissipation from the first electrode.

[0018] In one possible implementation, the surface of the second electrode facing the cooling cavity is recessed. This increases the contact area between the liquid coolant in the cooling cavity and the second electrode, thereby maximizing heat dissipation from the second electrode. Attached Figure Description

[0019] Further details, features, and advantages of this application are claimed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 A schematic diagram of the data center structure provided in an embodiment of this application is shown; Figure 2A A schematic diagram of the structure of a computing device according to an embodiment of this application is shown; Figure 2B A schematic diagram of the internal structure of a computing device according to an embodiment of this application is shown; Figure 3 A schematic diagram of a power supply device according to an embodiment of this application is shown; Figure 4 Another structural schematic diagram of the power supply device according to an embodiment of this application is shown; Figure 5 A top view of the power supply device according to an embodiment of this application is shown; Figure 6 A schematic diagram of the bus structure according to an embodiment of this application is shown; Figure 7 A schematic diagram showing the distribution of the first and second fasteners according to an embodiment of this application is provided. Figure 8 A schematic flowchart of a bus cooling method according to an embodiment of this application is shown; Figure 9 This paper shows a schematic diagram of the connection structure of the first pipe and the second pipe on the busbar according to an embodiment of this application; Figure 10 A schematic diagram of another possible bus structure according to an embodiment of this application is shown. Detailed Implementation

[0020] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0021] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0022] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this application are used only to distinguish different devices, units, or elements, and are not intended to limit the order of functions performed by these devices, units, or elements, or their interdependencies.

[0023] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0024] Before introducing the embodiments of this application, the relevant terms involved in the embodiments of this application are first explained as follows: A busbar, also known as a terminal block, is a special circuit assembly device. It is mainly composed of insulating materials, metal conductors, and connecting components. Its working principle is to connect the wires of multiple circuits to the busbar in a centralized manner, so as to realize the centralized distribution and transmission of current, thereby achieving the purpose of organizing and managing the circuit.

[0025] A reflux condenser typically consists of two layers of glass tubes. The inner tube carries the high-temperature gas, while the outer tube dissipates heat via cooling water or air. Based on their structural shape, reflux condensers can be classified into straight, spherical, and serpentine types, suitable for various experimental needs.

[0026] This application provides a computing device. Optionally, the computing device can be a server rack, network rack, full-server rack, or console rack. Taking a full-server rack as an example, the computing devices installed therein can be various types such as desktop servers, blade servers, and high-density servers.

[0027] Figure 1 A schematic diagram of the data center structure provided in an embodiment of this application is shown. Figure 1 As shown, data center 100 is a facility for arranging various racks and related components, such as communication racks, storage racks, or server racks. The data center 100 provided in this embodiment may include at least one computing device 102 located within a computer room 101. The computing device 102 may be located within the computer room.

[0028] like Figure 1As shown, the computer room 101 can be equipped with only one computing device 102 or multiple computing devices 102. When multiple computing devices 102 are set up in the computer room 101, the multiple computing devices 102 can be arranged in a row or multiple rows, and the computing nodes accommodated by each computing device 102 can be the same, partially the same, or all different.

[0029] like Figure 1 As shown, computing devices 102 are widely used in fields such as cloud computing, high-performance computing (HPC), big data, and artificial intelligence due to their high space utilization. The following example uses a rack-mounted server to illustrate the rack structure.

[0030] Figure 2A A schematic diagram of the structure of a computing device according to an embodiment of this application is shown. Figure 2B A schematic diagram of the internal structure of a computing device according to an embodiment of this application is shown. Figure 2A and Figure 2B As shown, the computing device 200 in this embodiment may include a cabinet 201, a power supply device 202, and a load. The power supply device 202 is disposed on the inner wall of the cabinet 201, and is connected to the load. The power supply device 202 is used to supply power to the load.

[0031] Optional, such as Figure 2A As shown, the cabinet 201 can be a cuboid, and it can have one or more loads. When there are multiple loads, the power supply unit 202 can be connected to multiple loads to supply power to them. Taking multiple loads as an example, the multiple loads can be distributed along the height direction Z of the cabinet.

[0032] Optional, such as Figure 2A and Figure 2B As shown, the load type may include compute node 203. Depending on the application scenario, the compute node may be at least one of high-power nodes such as edge computing nodes, artificial intelligence computing nodes, and high-performance computing nodes, but is not limited to these. Depending on the type of compute node, it may be a server, switch, or storage device, but is not limited to these.

[0033] Figure 3 A schematic diagram of a power supply device according to an embodiment of this application is shown. Figure 4 Another structural schematic diagram of the power supply device according to an embodiment of this application is shown. For example... Figure 3 and Figure 4 As shown, the power supply device 300 in this embodiment includes a busbar 301 and an insulating shell 302. The insulating shell 302 can be made of insulating materials, such as heat-resistant plastic, heat-resistant rubber, or heat-resistant ceramics, but is not limited to these.

[0034] like Figure 3 and Figure 4 As shown, the bus 301 in this embodiment may include a first electrode 3011 and a second electrode 3012 disposed opposite to each other. The computing node 203 is electrically connected to the first electrode 3011 and the second electrode 3012 included in the bus 301. There is a gap between the first electrode 3011 and the second electrode 3012. Both the first electrode 3011 and the second electrode 3012 may be disposed at... Figure 2A On the frame of the cabinet 201 shown.

[0035] Optional, such as Figure 3 and Figure 4 As shown, the first electrode 3011 and the second electrode 3012 can be strip electrodes. The first electrode 3011 and the second electrode 3012 are mounted on, for example... Figure 2A When the rack 201 shown is mounted on the frame, the stripe directions of the first electrode 3011 and the second electrode 3012 are both aligned with the direction shown. Figure 2A The cabinets shown have the same height in the Z direction. The materials of the first electrode 3011 and the second electrode 3012 can be conductive materials, which can include conductive metals such as copper, iron, and aluminum.

[0036] Optional, such as Figure 3 and Figure 4 As shown, the first electrode 3011 and the second electrode 3012 can be along the following path: Figure 2A The cabinet shown has multiple terminals along its height Z for connection to a power distribution unit, which can be electrically connected to each computing node 203. For example, when the first electrode 3011 is positive and the second electrode 3012 is negative, the first electrode 3011 can be connected to the positive terminal of the power distribution unit, and the second electrode 3012 can be connected to the negative terminal of the power distribution unit.

[0037] like Figure 3 and Figure 4 As shown, the insulating shell 302 in this embodiment can be connected to the first electrode 3011 and the second electrode 3012 respectively. Thus, under the isolation effect of the insulating shell 302, the first electrode 3011 and the second electrode 3012 are less likely to short-circuit, allowing the bus 301 to normally supply power to the computing node 203. The insulating shell 302 can be used for sealing, allowing the insulating shell 302, the first electrode 3011, and the second electrode 3012 to form a cooling chamber.

[0038] like Figure 3 and Figure 4As shown, the cooling chamber in this embodiment can contain refrigerant. When the insulating shell 302, the first electrode 3011, and the second electrode 3012 can form a cooling chamber, the refrigerant contained in the cooling chamber can directly contact the first electrode 3011 and the second electrode 3012. In this way, compared to the method of setting a liquid cooling plate between the first electrode 3011 and the second electrode 3012, the first electrode 3011 and the second electrode 3012 are in direct contact with the refrigerant, and the refrigerant can quickly absorb the heat released by the first electrode 3011 and the second electrode 3012.

[0039] As can be seen, in the computing device of this embodiment, the computing node 203 is electrically connected to the first electrode 3011 and the second electrode 3012 of the bus 301, so that the bus 301 can supply power to the computing node 203. The power supply device 300 directly contacts the refrigerant through the first electrode 3011 and the second electrode 3012. When the bus supplies power to the computing node, the thermal resistance of the intermediate interface can be minimized, allowing the heat from the first electrode 3011 and the second electrode 3012 to be actively conducted to the refrigerant to the maximum extent, and then dissipated through the heat exchanger 303. This achieves [the desired effect]. The shortest and most efficient heat flow path is used to maintain the temperature of bus 301 at a low level, thereby effectively improving the heat dissipation efficiency of bus 301. Secondly, the heat absorption efficiency of the refrigerant is the same in different regions of the first electrode 3011 and the second electrode 3012, which can avoid the problem of local overheating of the first electrode 3011 and the second electrode 3012, thereby greatly improving the reliability and current carrying capacity of bus 301. Finally, when the temperature of bus 301 is relatively low, the loss in the current transmission process can be reduced, the power transmission efficiency can be improved, and the heat dissipation requirements of bus 301 under high power consumption nodes can be met.

[0040] Furthermore, unlike the liquid cooling plate disposed between the first electrode 3011 and the second electrode 3012, in this embodiment of the busbar 301, the first electrode 3011 and the second electrode 3012 are connected by an insulating shell 302, and the liquid cooling cavity between the first electrode 3011 and the second electrode 3012 is used to contain refrigerant, so that the refrigerant will not corrode the insulating shell 302, thereby ensuring the reliability and stability of the busbar 301. Moreover, the refrigerant in the liquid cooling cavity is in contact with the inner wall of the insulating shell 302, making it less likely for charge to accumulate on the insulating shell 302, thereby reducing the risk of the insulating shell 302 becoming charged, reducing unnecessary hazards, and improving system safety.

[0041] It should be noted that the refrigerant can be a refrigerant liquid, which can be a two-phase refrigerant liquid or an alcohol-based coolant, but is not limited to these. Here, the two-phase refrigerant liquid can be a two-phase fluorinated liquid or a gas-liquid phase change material, etc. Taking a two-phase fluorinated liquid as an example, when the two-phase fluorinated liquid is converted into a two-phase fluorinated liquid as a refrigerant, it can absorb the heat from the first electrode 3011 and the second electrode 3012 to the maximum extent, thereby improving the heat dissipation effect of the busbar 301.

[0042] In one possible implementation, such as Figure 3 and Figure 4 As shown, in this embodiment of the application, a first insulating layer is formed on the surface of the cooling cavity facing the first electrode 3011, and a second insulating layer is formed on the surface of the second electrode 3012 facing the cooling cavity. This reduces the probability of a chemical reaction between the refrigerant and the surface of the first electrode 3011, preventing corrosion of the first electrode 3011 by the refrigerant. Similarly, when a second insulating layer is formed on the surface of the second electrode 3012 facing the cooling cavity, the second insulating layer can prevent corrosion of the second electrode 3012 by the refrigerant.

[0043] Optional, such as Figure 3 and Figure 4 As shown, an insulating coating can be formed on the surface of the cooling cavity in the area of ​​the first electrode 3011 facing the cooling cavity, and an insulating coating can be formed on the surface of the second electrode 3012 facing the cooling cavity. Thus, when the insulating shell 302, the first electrode 3011, and the second electrode 3012 form the cooling cavity, the insulating coating can reduce the chemical reaction between the refrigerant and the surface material of the first electrode 3011. At this point, the refrigerant inside the cooling cavity will not react with either the insulating shell 302 or the first and second electrodes 3011, effectively ensuring the heat dissipation reliability of the busbar 301.

[0044] In one possible implementation, Figure 5 A top view of the power supply device according to an embodiment of this application is shown. Figure 6 A schematic diagram of the bus structure according to an embodiment of this application is shown. Figure 5 and Figure 6 As shown, the insulating shell 302 in this embodiment may include a side plate 3021 and an end plate ( Figure 5 (Not shown). The first electrode 3011 has a first slot K1 on the side facing the gap, and the second electrode 3012 has a second slot K2 on the side facing the gap. The end plates are respectively connected to the end face of the first electrode 3011 and the end face of the second electrode 3012.

[0045] like Figure 5 and Figure 6As shown, when the side plate 3021 is inserted into the first slot K1 and the second slot K2, the side plate 3021 provides good sealing capability for the side of the gap between the first electrode 3011 and the second electrode 3012, preventing air and liquid leakage from the cooling chamber. Simultaneously, the end plates are connected to the end faces of the first electrode 3011 and the second electrode 3012 respectively, ensuring that the end faces of the gap between the first electrode 3011 and the second electrode 3012 are sealed, preventing refrigerant leakage. The insertion method also facilitates the installation and removal of the insulating shell 302 from the first electrode 3011 and the second electrode 3012.

[0046] Optional, such as Figure 5 and Figure 6 As shown, the power supply device 300 also includes a first seal ( Figure 5 (not shown) and second seal ( Figure 5 (Not shown). The first seal is located on the inner wall of the first slot K1, and the side plate 3021 contacts the first seal. This effectively improves the sealing performance of the side plate 3021 and prevents poor sealing between the side plate 3021 and the first slot K1. Similarly, when the second seal is located on the inner wall of the second slot K2, the side plate 3021 contacts the second seal, which also prevents poor sealing between the side plate 3021 and the second slot K2.

[0047] In one example, the aforementioned seal can be an elastic seal, such as an elastic gasket, or a sealant. By providing seals in the first slot K1 and the second slot K2, the sealing performance of the side plate 3021 can be effectively improved.

[0048] Optional, such as Figure 5 As shown, the insulating shell 302 in this embodiment may further include a first fixing member A and a second fixing member B. The side plate 3021 can be tightly connected to the side of the first electrode 3011 through the first fixing member A, and the side plate 3021 can also be tightly connected to the side of the second electrode 3012 through the second fixing member B. This connection method can improve the sealing performance of the sealing shell and prevent air and liquid leakage from the cooling chamber.

[0049] In one example, Figure 7 A schematic diagram showing the distribution of the first and second fasteners according to an embodiment of this application is illustrated. Figures 5-7 As shown, there can be multiple first fasteners A, which can be distributed along a preset direction in the area of ​​the side plate 3021 that contacts the first electrode 3011, and there can be multiple second fasteners B, which can be distributed along a preset direction in the area of ​​the side plate 3021 that contacts the second electrode 3012.

[0050] like Figures 5-7As shown, the shape, position, and quantity of the first fixing member A and the second fixing member B can be configured according to actual conditions and are not limited here. For example, when both the first electrode 3011 and the second electrode 3012 are strip electrodes, the preset direction can be the same as the extension direction of the strip electrodes. This can ensure the sealing of the first electrode 3011 and the second electrode 3012 in the strip direction and avoid air and liquid leakage problems caused by poor local sealing.

[0051] Optional, such as Figure 5 and Figure 6 As shown, side plate 3021 may include a first side plate 3021A and a second side plate 3021B. Two first slots K1 may be provided on the side of the first electrode 3011 facing the gap, and two second slots K2 may be provided on the side of the second electrode 3012 facing the gap. The first and second sides of the first electrode 3011 can be connected via the side of the first electrode 3011 facing the gap, and the first and second sides of the second electrode 3012 can be connected via the side of the second electrode 3012 facing the gap.

[0052] like Figure 5 and Figure 6 As shown, for the two first slots K1, one first slot K1 is close to the first side of the first electrode 3011, and the other first slot K1 is close to the second side of the first electrode 3011. For the two second slots K2, one second slot K2 is close to the first side of the first electrode 3011, and the other second slot K2 is close to the second side of the first electrode 3011. One end of the first side plate 3021A and one end of the second side plate 3021B are respectively engaged with the two first slots K1, and the other ends of the first side plate 3021A and the second side plate 3021B are respectively engaged with the two second slots K2.

[0053] In one example, such as Figure 5 and Figure 6 As shown, the end plate may include a top plate 3022A and a bottom plate 3022B. The top plate 3022A may be disposed on the top of the first electrode 3011 and the top of the second electrode 3012, and the bottom plate 3022B may be disposed on the bottom of the first electrode 3011 and the top of the second electrode 3012. In testing, the top plate 3022A, the bottom plate 3022B, the first side plate 3021A, and the second side plate 3021B together constitute an insulating shell 302 body to seal the gap between the first electrode 3011 and the second electrode 3012, so that the first side plate 3021A, the second side plate 3021B, the top plate 3022A, the bottom plate 3022B, the first electrode 3011, and the second electrode 3012 form a cooling cavity.

[0054] It should be noted that, as Figure 5 and Figure 6As shown, in this embodiment of the application, both the first slot K1 and the second slot K2 can be U-shaped slots or slots of other shapes. All parts of the insulating shell 302 are made of insulating material to minimize unnecessary safety hazards (such as the insulating shell 302 being electrified) and to avoid accidents.

[0055] In one possible implementation, such as Figure 3 and Figure 4 As shown, the power supply device 300 in this embodiment of the application further includes a heat exchanger 303, the heat dissipation channel of which is connected to the cooling chamber. The heat exchanger 303 is used to dissipate heat from the refrigerant in the cooling chamber.

[0056] When the refrigerant absorbs the heat released by the first electrode 3011 and the second electrode 3012, the refrigerant becomes heated. Therefore, the refrigerant can enter the heat dissipation channel of the heat exchanger 303 under thermal drive, allowing the heat exchanger 303 to dissipate heat from the refrigerant. In this way, the coolant that has absorbed heat can be cooled by the heat exchanger 303 and flow back into the cooling chamber.

[0057] The following example uses two-phase refrigerant, combined with... Figure 8 This application describes a cooling method for bus 301 according to an embodiment. For example... Figure 5 As shown, the cooling method of busbar 301 in this embodiment includes steps 801 to 803.

[0058] In step 801, when the busbar 301 is powered, the first electrode 3011 and the second electrode 3012 included in the busbar 301 will start to heat up, so that the two-phase refrigerant in the cooling chamber can absorb the heat absorbed by the first electrode 3011 and the second electrode 3012.

[0059] In step 802, when the temperature of the refrigerant reaches the vaporization temperature, the two-phase refrigerant vaporizes into hot vapor and enters the heat dissipation channel of the heat exchanger 303.

[0060] In step 803, the heat exchanger 303 absorbs the heat from the hot vapor, causing the hot vapor to condense into a two-phase refrigerant, which then flows back into the cooling chamber. At this time, the refrigerant in the cooling chamber begins to absorb the heat released by the first electrode 3011 and the second electrode 3012 again. This cycle repeats, allowing the refrigerant to continuously and adequately cool and dissipate heat from the first electrode 3011 and the second electrode 3012.

[0061] In one alternative embodiment, the heat exchanger in this application can be a liquid cooling system located outside the computing device. It can be connected to the cooling chamber via a water supply manifold, and the cooling chamber can be connected to the liquid cooling system via a water return manifold. The water supply manifold delivers refrigerant from the liquid cooling system into the cooling chamber to adequately cool the first and second electrodes. The water return manifold delivers heat-absorbing refrigerant from the cooling chamber back to the liquid cooling system, allowing the liquid cooling system to cool the heat-absorbing refrigerant before it is returned to the cooling chamber via the water supply manifold. Therefore, in this application embodiment, the liquid cooling chamber can be connected to the liquid cooling system of the computing device via water supply and return manifolds, allowing the power supply device 300 to be integrated with the liquid cooling system of the computing device. This enables the management of the heat dissipation capacity of the busbar 301 using the computer's liquid cooling system.

[0062] In one alternative approach, such as Figure 3 and Figure 4 As shown, the heat exchanger 303 in this embodiment may include a liquid cooling plate 3031 and a bladder 3032 disposed on the surface of the liquid cooling plate 3031, the bladder 3032 being in communication with a cooling chamber. When the first electrode 3011 and the second electrode 3012 conduct heat to the refrigerant, the refrigerant vaporizes into hot vapor, which can flow into the bladder 3032. The liquid cooling plate 3031 can then be used to cool the refrigerant entering the bladder 3032, thereby ensuring the cooling effect of the refrigerant.

[0063] Optional, such as Figure 3 and Figure 4 As shown, the liquid cooling plate 3031 can be a liquid cooling plate, which can be connected to the external liquid inlet pipe R1 and the external liquid outlet pipe R2 respectively. In this way, cooling water can be sent into the liquid cooling plate 3031 through the external liquid inlet pipe R1 and absorb the heat of the hot steam, and then sent out of the liquid cooling plate 3031 through the external liquid outlet pipe R2.

[0064] In one example, the external liquid inlet pipe R1 can be connected to the refrigeration system via a water supply manifold, and the external liquid outlet pipe R2 can also be connected to the refrigeration system via a return water manifold. In this way, the liquid cooling plate 3031 of the power supply device 300 can be integrated with the liquid cooling system of the computing device, thus enabling the management of the heat dissipation capacity of the busbar 301 using the computer's liquid cooling system.

[0065] In one possible implementation, such as Figure 3 and Figure 4As shown, the first electrode 3011 in this embodiment of the application is provided with a first channel communicating with the cooling chamber. In this case, the power supply device 300 further includes a first pipe L1 connected to the first channel, and the first pipe L1 communicates with the heat dissipation channel of the heat exchanger 303. For example, when the heat exchanger 303 includes a liquid cooling plate 3031 and a bladder 3032, the first pipe L1 can communicate with the bladder 3032.

[0066] like Figure 3 and Figure 4 As shown, when the first channel provided by the first electrode 3011 is connected to the cooling cavity, the first channel can provide a channel for the first pipe L1 to communicate with the cooling cavity, ensuring that the first pipe L1 can introduce the refrigerant in the cooling cavity into the heat dissipation channel of the heat exchanger 303, so that the heat exchanger 303 can cool the refrigerant.

[0067] Optionally, the first electrode 3011 has a first end face facing the heat exchanger 303. The opening of the first channel on the surface of the heat exchanger 303 is located on the first end face. For example, when the heat exchanger 303 is located above the first electrode 3011, the opening of the first channel on the surface of the heat exchanger 303 is also located at the top of the first electrode 3011. Therefore, when the first pipe L1 enters the inlet channel of the heat exchanger 303 as liquid-cooled vapor, the refrigerant may become hot vapor under the condition that the refrigerant is heated, making it easier for the refrigerant to actively enter the first pipe L1 through the first channel and continue to move upward until it enters the heat dissipation channel of the heat exchanger 303.

[0068] Optional, Figure 9 A schematic diagram of the connection structure of the first and second pipes on the manifold according to an embodiment of this application is shown. Figure 3 and Figure 9 As shown, the first electrode 3011 is provided with a first channel communicating with the cooling chamber, and the second electrode 3012 is provided with a second channel communicating with the cooling chamber. At this time, the power supply device 300 also includes a second pipe L2 connected to the second channel, and the second pipe L2 is connected to the heat dissipation channel of the heat exchanger 303. In this way, the flow path of the hotter refrigerant and the flow path of the cooled refrigerant can be separated, preventing mutual interference between the hotter and cooled refrigerants.

[0069] It should be noted that the first pipe in this embodiment can also be located on the top plate, so that the refrigerant may turn into hot vapor and directly enter the first pipe through the end plate, which can reduce the impact of the heat of the hot vapor on the first electrode.

[0070] In one example, such as Figure 9 As shown, the first pipe L1 can pass through the first channel and communicate with the cooling chamber, and provide an air intake channel for hot steam to flow from the cooling chamber into the heat exchanger 303 (the air intake direction is as shown by the first arrow).x As shown), the second channel can connect to the cooling chamber through the second channel and provide a return channel for the refrigerant to flow into the cooling chamber from the return pipe (the return direction is as shown by the second arrow). y direction shown).

[0071] In one example, such as Figure 9 As shown, the second electrode 3012 has a second end face facing away from the heat exchanger 303. The opening of the second channel on the surface of the heat exchanger 303 is located on the second end face. For example, when the heat exchanger 303 is located above the first electrode 3011, the opening of the second channel on the surface of the heat exchanger 303 is located at the bottom of the second electrode 3012. Therefore, after the refrigerant dissipates heat through the heat exchanger 303, the hot vapor may change from gas to refrigerant liquid, and its density increases. Therefore, under the action of gravity, it can actively enter the second channel through the first pipe L1 and finally enter the cooling chamber.

[0072] Optional, such as Figure 4 As shown, the first pipe L1 includes a liquid-cooled return pipe L0, which is connected to the cooling chamber and the heat dissipation channel of the heat exchanger 303. The liquid-cooled return pipe L0 connects the cooling chamber and the heat dissipation channel of the heat exchanger 303, allowing the hotter refrigerant in the cooling chamber to enter through it (the air intake direction is as shown by the first arrow). x As shown, the direction of liquid return is indicated by the second arrow. y (As shown) The refrigerant is cooled through the heat dissipation channel of the heat exchanger 303, and the cooled refrigerant in the heat dissipation channel of the heat exchanger 303 can also be returned to the cooling chamber through the condensation return pipe. Therefore, by connecting the cooling chamber and the heat dissipation channel of the heat exchanger 303 through the liquid cooling return pipe L0, unnecessary pipes connected to the cooling chamber can be reduced, and the potential accidental leakage of refrigerant can be prevented.

[0073] It should be noted that the first pipe L1 in this embodiment includes a liquid-cooled reflux pipe L0, which can also be disposed on an end plate and communicate with the cooling chamber. When the refrigerant absorbs heat dissipated by the first and second electrodes in the cooling chamber, it can directly pass through the end plate into the liquid-cooled reflux pipe L0. The liquid-cooled reflux capacity of the liquid-cooled reflux pipe L0 dissipates heat from the heated refrigerant, allowing the cooled refrigerant to flow back into the cooling chamber through the liquid-cooled reflux pipe L0. This method can reduce the impact of the heated refrigerant on the first and second electrodes when it flows out of the cooling chamber.

[0074] Optionally, the end plate can be either a top plate 3022A or a bottom plate 3022B. That is, the liquid cooling return pipe L0 can be installed on the top plate 3022A and pass through the top plate 3022A to communicate with the cooling cavity, or it can be installed on the bottom plate 3022B and pass through the bottom plate 3022B to communicate with the cooling cavity.

[0075] For example, when the liquid-cooled return pipe L0 is located on the top plate and connected to the cooling chamber, after the refrigerant turns into hot vapor, the hot vapor actively diffuses in the upward direction. However, since the liquid-cooled return pipe L0 is located on the top plate and connected to the cooling chamber, the hot vapor can pass through the top plate 3022A more quickly and enter the liquid-cooled return pipe L0. The hot vapor is cooled into liquid by the liquid-cooled return capacity of the liquid-cooled return pipe L0 and then flows back into the cooling chamber through the liquid-cooled return pipe L0.

[0076] In one possible implementation, Figure 10 A schematic diagram of another possible bus structure according to an embodiment of this application is shown. For example... Figure 10 As shown, in the busbar 301, the surface of the first electrode 3011 facing the cooling cavity has a recessed structure, which can increase the contact area between the liquid coolant in the cooling cavity and the first electrode 3011, thereby maximizing the heat dissipation of the first electrode 3011.

[0077] Similarly, such as Figure 10 As shown, the surface of the second electrode 3012 facing the cooling cavity has a recessed structure, which can increase the contact area between the liquid coolant in the cooling cavity and the second electrode 3012, thereby maximizing the heat dissipation of the second electrode 3012.

[0078] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A computing device, characterized in that, The device includes a server rack, a power supply unit, and computing nodes. The power supply unit and the computing nodes are located inside the server rack. The power supply unit includes a bus and an insulating shell. The bus includes a first electrode and a second electrode arranged opposite to each other. The computing nodes are electrically connected to the first electrode and the second electrode, respectively. There is a gap between the first electrode and the second electrode. The insulating shell is connected to the first electrode and the second electrode respectively. The insulating shell is used to seal the gap. The insulating shell, the first electrode and the second electrode form a cooling cavity. The cooling cavity is used to contain refrigerant.

2. The computing device according to claim 1, characterized in that, A first insulating layer is formed on the surface of the first electrode facing the cooling cavity; and / or, A second insulating layer is formed on the surface of the second electrode facing the cooling cavity.

3. The computing device according to claim 1, characterized in that, The insulating shell includes a side plate and an end plate, the first electrode has a first slot on the side facing the interval, and the second electrode has a second slot on the side facing the interval. The side plate is inserted into the first slot and the second slot, and the end plate is connected to the end face of the first electrode and the end face of the second electrode, respectively.

4. The computing device according to claim 3, characterized in that, The power supply device further includes a first seal and a second seal. The first seal is disposed on the inner wall of the first slot, and the side plate is in contact with the first seal. The second seal is disposed on the inner wall of the second slot, and the side plate is in contact with the second seal.

5. The computing device according to any one of claims 1 to 4, characterized in that, The power supply device also includes a heat exchanger, the heat exchanger's heat dissipation channel being connected to the cooling chamber, and the heat exchanger being used to dissipate heat from the refrigerant in the cooling chamber.

6. The computing device according to claim 5, characterized in that, The first electrode is provided with a first channel communicating with the cooling chamber, and the power supply device further includes: a first pipe connected to the first channel, the first pipe communicating with the heat dissipation channel of the heat exchanger.

7. The computing device according to claim 6, characterized in that, The first pipe includes a liquid-cooled reflux pipe, which is connected to the cooling chamber and the heat dissipation channel of the heat exchanger.

8. The computing device according to claim 6, characterized in that, The second electrode is provided with a second channel communicating with the cooling cavity, and the power supply device further includes a second pipe connected to the second channel, the second pipe communicating with the heat dissipation channel of the heat exchanger.

9. The computing device according to claim 6, characterized in that, The first electrode has a first end face facing the heat exchanger, and the opening of the first channel on the surface of the heat exchanger is located on the first end face.

10. The computing device according to any one of claims 1 to 9, characterized in that, The surface of the first electrode facing the cooling cavity has a recessed structure; and / or, The surface of the second electrode facing the cooling cavity has a recessed structure.