An AI server adaptive to multiple scenarios

Abstract

The utility model relates to a kind of multi-scene adaptation's AI server, it includes: AI server main body, installation frame being provided with dust screen, cleaning mechanism and support mechanism;Cleaning mechanism, cleaning mechanism is set on installation frame;Support mechanism, support mechanism is provided with four groups, and four groups of support mechanism are respectively set at the four corners of AI server main body;Among them, cleaning mechanism includes reciprocating screw rod being rotatably installed in installation frame interior, the outer surface of reciprocating screw rod is installed with slider, the outer surface of slider is installed with cleaning plate, and the outer surface of cleaning plate is provided with bristle. By starting motor, cleaning plate can be driven reciprocating lifting, and then the dust adhered to the surface of dust screen can be swept off and dropped using bristle, then using the extraction effect of dust collection mechanism, the dust that falls off is extracted and collected, to realize the purpose of automatic cleaning of dust, avoid the situation that manual cleaning consumes a lot of time and workload increases, reduce maintenance difficulty.

Description

Technical Field

[0001] This utility model relates to the field of server technology, specifically to an AI server that is adaptable to multiple scenarios. Background Technology

[0002] AI servers are high-performance computing devices designed specifically for artificial intelligence applications. Their core integrates multiple types of acceleration chips through a heterogeneous hardware architecture, breaking through the computing power bottleneck of traditional servers with parallel computing capabilities. They can efficiently process massive amounts of data and complex model training tasks in scenarios such as natural language processing and computer vision. They are also equipped with large-capacity memory, high-speed storage, and optimized network interfaces, supporting distributed computing and real-time inference, providing stable and scalable computing power support for the entire process of AI algorithms from research and development to deployment.

[0003] Chinese patent CN220357532U discloses an AI server adaptable to multiple scenarios. The server absorbs noise generated by the air inlet and outlet through a multi-layer perforated honeycomb sound-absorbing structure installed inside the air inlet front panel and the air outlet back panel. The sound insulation layer and sponge sound-absorbing layer set on the inner surface absorb most of the noise generated inside, thereby reducing the noise generated inside and adapting to a variety of scenarios. The dust filter is taken out by pulling out the pull-out frame, which is convenient for cleaning or replacement.

[0004] The aforementioned server cleans the dust on the filter plate by pulling out the pull-out frame. However, in data centers, AI servers are usually deployed in clusters, which means that manually cleaning the filter plates one by one would consume a lot of time and increase the workload of personnel. In addition, existing AI servers have relatively low bottom support legs for easy transportation, which means that when the AI ​​server is placed on the rack, the bottom space is small, the air circulation is poor, and thus the heat dissipation effect is reduced. Utility Model Content

[0005] This utility model addresses the technical problems existing in the prior art by providing an AI server that is adaptable to multiple scenarios.

[0006] The technical solution of this utility model to solve the above-mentioned technical problems is as follows: A multi-scenario adaptable AI server includes: an AI server body, an installation frame with a dustproof net, a cleaning mechanism, and a support mechanism; The cleaning mechanism is mounted on the installation frame. The support structure consists of four sets, which are located at the four corners of the main body of the AI ​​server. The cleaning mechanism includes a reciprocating screw rotatably installed inside the mounting frame. A slider is installed on the outer surface of the reciprocating screw, and a cleaning plate is installed on the outer surface of the slider. The outer surface of the cleaning plate is provided with bristles, which are in contact with the surface of the dustproof net. A motor is installed on the top of the mounting frame, and the output shaft of the motor is connected to the reciprocating screw. The surface of the AI ​​server body is equipped with a dust-collecting mechanism that works in conjunction with a cleaning plate.

[0007] The beneficial effects of this utility model are: by starting the motor, the cleaning plate can be driven to move up and down repeatedly, and the brush bristles can be used to sweep away and remove the dust attached to the surface of the dustproof net. Then, the dust removal mechanism is used to extract and collect the removed dust, thereby achieving the purpose of automatic dust cleaning. This avoids the situation where manual cleaning consumes a lot of time and increases the workload, and reduces the difficulty of maintenance.

[0008] Furthermore, the dust collection mechanism includes multiple suction ports on the side of the cleaning plate facing the dust filter. A flexible hose is connected to the outer surface of the cleaning plate. A miniature fan is mounted on the top of the AI ​​server body, with an integrated cloth bag connected to the output end of the miniature fan and the suction end of the miniature fan connected to the flexible hose. This achieves the purpose of automatically cleaning and collecting dust from the surface of the dust filter, preventing secondary pollution of the surrounding environment and the AI ​​server body caused by the swept dust.

[0009] Furthermore, the suction end of the miniature fan is connected to a split pipe, with flexible hoses connected to both sides along the length of the split pipe. The ends of both hoses are connected to a cleaning plate, dividing the cleaning plate into three equal parts. This ensures that the suction force generated by the miniature fan is evenly distributed, allowing each suction port to effectively extract dust.

[0010] Furthermore, the brush has two sets of bristles, distributed on the upper and lower sides of the suction port. This ensures that it effectively extracts falling dust during the raising and lowering of the cleaning plate.

[0011] Furthermore, both the mounting frame and the micro fan are detachably connected to the AI ​​server body, and the integrated fabric bag is also detachably connected to the micro fan. This facilitates removal from the AI ​​server body for maintenance or replacement of the motor and micro fan.

[0012] Furthermore, grooves are provided on both inner walls of the mounting frame, and both ends of the cleaning plate are positioned within these grooves. This ensures the cleaning plate moves smoothly up and down, driving the motor to clean the entire surface of the dust filter.

[0013] Furthermore, the support mechanism includes a support sleeve mounted on the outer surface of the AI ​​server body. A support rod is inserted inside the support sleeve, and multiple adjustment holes are arrayed on the outer surface of the support rod. Screws are installed on the outer surface of the support sleeve, and the screws are adapted to the adjustment holes. This increases the support height for the AI ​​server body, providing sufficient space at the bottom for airflow and improving heat dissipation.

[0014] Furthermore, anti-slip pads are installed at the bottom of the support rods to increase slip resistance and improve stability. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the overall structure of this utility model; Figure 2 This is a schematic diagram of the mounting frame in this utility model; Figure 3 This is a schematic diagram of the cleaning plate in this utility model; Figure 4 This is a schematic diagram of the support mechanism in this utility model.

[0016] The attached diagram lists the components represented by each number as follows: 1. AI server main body; 2. Mounting frame; 201. Dustproof net; 3. Cleaning mechanism; 301. Reciprocating screw; 302. Slider; 303. Cleaning plate; 304. Brush bristles; 305. Motor; 306. Slide groove; 4. Support mechanism; 401. Support sleeve; 402. Support rod; 403. Adjustment hole; 404. Screw; 405. Anti-slip pad; 5. Dust collection mechanism; 501. Dust collection port; 502. Hose; 503. Miniature fan; 504. Integrated cloth bag; 505. Diverter pipe. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0019] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this technology based on the specific circumstances.

[0020] In the description of this application, spatial relation terms such as "below," "under," "below," "below," "above," "over," etc., are used herein to describe the relationship between one element or feature shown in the figures and other elements or features. It should be understood that, in addition to the orientation shown in the figures, spatial relation terms also include different orientations of the device in use and operation. For example, if the device in the figures is flipped, an element or feature described as "below" or "under" other elements or features would be oriented "over" other elements or features. Therefore, the exemplary terms "below" and "under" can include both upper and lower orientations. Furthermore, the device may also include other orientations (e.g., rotated 90 degrees or other orientations), and the spatial descriptive terms used herein are interpreted accordingly.

[0021] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the present invention with unnecessary detail. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0022] Example 1 Figure 1 This invention provides a multi-scenario adaptable AI server structure diagram. Figure 2 This is a schematic diagram of the mounting frame in this utility model. Figure 3 This is a schematic diagram of the cleaning plate in this utility model. Figures 1 to 3 As shown, the device includes: an AI server body 1, a mounting frame 2 with a dustproof net 201, a cleaning mechanism 3, and a support mechanism 4; Cleaning mechanism 3 is mounted on mounting frame 2; Support mechanism 4, there are four sets of support mechanism 4, and the four sets of support mechanism 4 are respectively set at the four corners of the AI ​​server body 1; The cleaning mechanism 3 includes a reciprocating screw 301 rotatably mounted inside the mounting frame 2. A slider 302 is mounted on the outer surface of the reciprocating screw 301, and a cleaning plate 303 is mounted on the outer surface of the slider 302. The outer surface of the cleaning plate 303 is provided with bristles 304, which are in contact with the surface of the dustproof mesh 201. A motor 305 is mounted on the top of the mounting frame 2, and the output shaft of the motor 305 is connected to the reciprocating screw 301. The surface of the AI ​​server body 1 is provided with a vacuuming mechanism 5 that cooperates with the cleaning plate 303.

[0023] In use, the motor 305 is controlled by the controller. The staff can turn on the motor 305 on each AI server body 1 at the same time through the controller. By starting the motor 305, the cleaning plate 303 can be driven to move up and down back and forth. Then, the brush bristles 304 can sweep away and remove the dust attached to the surface of the dustproof net 201. Then, the suction mechanism 5 is used to extract and collect the dust, thereby achieving the purpose of automatic dust cleaning. This avoids the time and workload increase caused by manual cleaning and reduces the difficulty of maintenance.

[0024] Figure 2 This is a schematic diagram of the mounting frame in this utility model. Figure 3 This is a schematic diagram of the cleaning plate in this utility model. Figure 2 and Figure 3As shown, the dust collection mechanism 5 includes multiple suction ports 501 on the side of the cleaning plate 303 facing the dustproof net 201. A hose 502 is connected to the outer surface of the cleaning plate 303. A micro fan 503 is installed on the top of the AI ​​server body 1. The output end of the micro fan 503 is connected to an integrated cloth bag 504. The suction end of the micro fan 503 is connected to the hose 502. The micro fan 503 is also controlled by the controller. When the motor 305 is started, the micro fan 503 is started at the same time. The suction force generated by the micro fan 503 acts on the suction port 501. The dust swept away by the brush bristles 304 is directly drawn into the suction port 501 under the action of suction force, and then enters the hose 502 from the suction port 501. Finally, it is collected in the integrated cloth bag 504. Therefore, the purpose of automatically cleaning and collecting the dust on the surface of the dustproof net 201 is achieved, avoiding secondary pollution of the surrounding environment and the AI ​​server body 1 caused by the swept dust. The flexible hose 502 is angled and of sufficient length to adapt to the raising and lowering of the cleaning plate 303 without bending, ensuring unobstructed suction. The suction end of the miniature fan 503 is connected to a diversion pipe 505, with flexible hoses 502 connected to both sides of the diversion pipe 505 along its length. Both ends of the flexible hoses 502 are connected to the cleaning plate 303, dividing it into three equal parts. This ensures even distribution of suction power from the miniature fan 503, allowing each suction port 501 to effectively remove dust. Two sets of bristles 304 are provided, distributed on the upper and lower sides of the suction port 501, effectively removing falling dust during the raising and lowering of the cleaning plate 303. The mounting frame 2 and the micro fan 503 are detachably connected to the AI ​​server body 1. The integrated cloth bag 504 is also detachably connected to the micro fan 503. The mounting frame 2, cleaning mechanism 3, and support mechanism 4 are modularly designed and mounted on the AI ​​server body 1, facilitating their removal for maintenance or replacement of the motor 305 and micro fan 503. When the integrated cloth bag 504 accumulates a large amount of dust, it can be removed for cleaning. Connection methods include bolt connections and snap-fit ​​connections, which are common existing technologies and will not be elaborated upon here. The inner walls on both sides of the mounting frame 2 are provided with sliding grooves 306. Both ends of the cleaning plate 303 are positioned within these grooves. The sliding grooves 306 limit the movement of the cleaning plate 303, ensuring smooth lifting and lowering. This allows the motor 305 to clean the entire surface of the dust filter 201, preventing the cleaning plate 303 from tilting and resulting in unsatisfactory cleaning.

[0025] Example 2 Based on Embodiment 1, the present invention can be further improved in the following ways, such as... Figure 4As shown, the support mechanism 4 includes a support sleeve 401 mounted on the outer surface of the AI ​​server body 1. A support rod 402 is inserted inside the support sleeve 401. Multiple adjustment holes 403 are arrayed on the outer surface of the support rod 402. Screws 404 are mounted on the outer surface of the support sleeve 401, and the screws 404 are adapted to the adjustment holes 403. An anti-slip pad 405 is provided at the bottom of the support rod 402.

[0026] The support height of the AI ​​server body 1 can be adjusted by screwing the screw 404 into the adjustment hole 403 at the appropriate height. During transportation, the support rod 402 can be completely stored in the support sleeve 401, saving space. When the AI ​​server body 1 is installed, the support rod 402 can be pulled out to an appropriate length according to the installation space, thereby increasing the support height of the AI ​​server body 1 and providing sufficient space for airflow at the bottom to improve heat dissipation. The anti-slip pad 405 increases the anti-slip ability and improves stability.

[0027] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the above embodiments are merely exemplary embodiments or examples, and the scope of this utility model is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A multi-scenario adaptable AI server, characterized in that, include: AI server main body (1), mounting frame (2) with dustproof net (201), cleaning mechanism (3) and support mechanism (4); Cleaning mechanism (3), the cleaning mechanism (3) is disposed on the mounting frame (2); The support mechanism (4) is provided in four sets, and the four sets of the support mechanism (4) are respectively located at the four corners of the AI ​​server body (1); The cleaning mechanism (3) includes a reciprocating screw (301) rotatably installed inside the mounting frame (2). A slider (302) is installed on the outer surface of the reciprocating screw (301). A cleaning plate (303) is installed on the outer surface of the slider (302). Brush bristles (304) are provided on the outer surface of the cleaning plate (303). The brush bristles (304) are in contact with the surface of the dustproof net (201). A motor (305) is installed on the top of the mounting frame (2). The output shaft of the motor (305) is connected to the reciprocating screw (301). The surface of the AI ​​server body (1) is provided with a dust collection mechanism (5) that cooperates with the cleaning plate (303).

2. The AI ​​server for multi-scenario adaptation according to claim 1, characterized in that, The dust collection mechanism (5) includes multiple dust collection ports (501) opened on the side of the cleaning plate (303) facing the dustproof net (201). A hose (502) is connected to the outer surface of the cleaning plate (303). A micro fan (503) is installed on the top of the AI ​​server body (1). An integrated cloth bag (504) is connected to the output end of the micro fan (503). The suction end of the micro fan (503) is connected to the hose (502).

3. The AI ​​server for multi-scenario adaptation according to claim 2, characterized in that, The intake end of the micro fan (503) is connected to a diversion pipe (505), and both sides of the diversion pipe (505) are connected to the hoses (502) in the length direction. The ends of the two hoses (502) are connected to the cleaning plate (303), and the two hoses (502) divide the cleaning plate (303) into three equal parts.

4. The AI ​​server for multi-scenario adaptation according to claim 3, characterized in that, The brush bristles (304) are provided in two sets, and the two sets of brush bristles (304) are distributed on the upper and lower sides of the suction port (501).

5. The AI ​​server for multi-scenario adaptation according to claim 3, characterized in that, The mounting frame (2) and the micro fan (503) are detachably connected to the main body of the AI ​​server (1), and the integrated cloth bag (504) is detachably connected to the micro fan (503).

6. The AI ​​server for multi-scenario adaptation according to claim 1, characterized in that, The inner walls on both sides of the mounting frame (2) are provided with grooves (306), and both ends of the cleaning plate (303) are located in the grooves (306).

7. The AI ​​server for multi-scenario adaptation according to claim 1, characterized in that, The support mechanism (4) includes a support sleeve (401) installed on the outer surface of the AI ​​server body (1). A support rod (402) is inserted inside the support sleeve (401). Multiple adjustment holes (403) are arrayed on the outer surface of the support rod (402). Screws (404) are installed on the outer surface of the support sleeve (401). The screws (404) are adapted to the adjustment holes (403).

8. The AI ​​server for multi-scenario adaptation according to claim 7, characterized in that, The bottom of the support rod (402) is provided with an anti-slip pad (405).

Images