Server, electromagnetic interference protection method, and computer-readable storage medium

Abstract

The application discloses a server, an electromagnetic interference protection method and a computer readable storage medium, wherein the server comprises a mainboard, the mainboard comprises a sensor component and a processor component, the processor component is arranged on a first area of the mainboard, the sensor component is arranged on a second area of the mainboard, and the first area is not connected with the second area. A power supply cable is connected with the mainboard. A switch part is connected with the power supply cable, and the on-off state of the switch part is used for controlling the power supply state of the mainboard. In the case that the first electromagnetic field intensity of the first area is greater than or equal to the intensity threshold value, the on-off state of the switch part is switched from the on state to the off state, and the first electromagnetic field intensity is the magnetic field intensity determined based on the second electromagnetic field intensity and the first distance. The application solves the problem that it is difficult to protect the server according to the real electromagnetic environment in the server due to the low accuracy of the collected electromagnetic field intensity parameters.

Description

Technical Field

[0001] This application relates to the field of server technology, and in particular to a server, an electromagnetic interference protection method, and a computer-readable storage medium. Background Technology

[0002] As servers develop towards higher density and higher performance, the power requirement of a single server rack has now exceeded 500KW. Therefore, high-voltage DC power supply architecture has become the preferred solution for high-density data center servers.

[0003] In related technologies, traditional electromagnetic field monitoring solutions mainly involve directly installing electromagnetic field sensors in the core area where components such as the Central Processing Unit (CPU) and Graphics Processing Unit (GPU) are located to obtain electromagnetic field data at that location. However, in highly integrated server motherboards, the core area has extremely limited space, making it almost impossible to provide installation locations for sensors. Forcing their installation not only alters the original mechanical structure and heat dissipation channels but also introduces disturbances to the electromagnetic field from the probe itself, resulting in lower accuracy of the collected electromagnetic field strength parameters and making it difficult to provide security protection for the server based on the actual electromagnetic environment within the server. Summary of the Invention

[0004] This application provides a server, an electromagnetic interference protection method, and a computer-readable storage medium to at least solve the problem that it is difficult to provide security protection for the server based on the actual electromagnetic environment due to the low accuracy of the collected electromagnetic field strength parameters.

[0005] This application provides a server, including: a motherboard, which includes a sensor component and a processor component. The processor component is disposed in a first region of the motherboard, and the sensor component is disposed in a second region of the motherboard. The first region and the second region are not connected. The sensor component is used to collect a second electromagnetic field strength threshold in the second region. A power supply cable is connected to the motherboard and is used to supply power to the motherboard. A switch is connected to the power supply cable, and the on / off state of the switch is used to control the power supply state of the motherboard. Specifically, when the first electromagnetic field strength in the first region is greater than or equal to the strength threshold, the on / off state of the switch switches from a conducting state to an off state. The first electromagnetic field strength is a magnetic field strength determined based on the second electromagnetic field strength and a first distance, where the first distance is the distance between the sensor component and the power supply cable.

[0006] This application also provides an electromagnetic interference protection method applied to the aforementioned server, the electromagnetic interference protection method comprising:

[0007] The second electromagnetic field strength of the second region is acquired by the sensor component; the first electromagnetic field strength of the first region is determined based on the second electromagnetic field strength and the first distance; wherein the first distance is the distance between the sensor component and the power supply cable; when the first electromagnetic field strength is greater than or equal to the strength threshold, the control switch is switched from the on state to the off state.

[0008] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of any of the above methods.

[0009] This application involves placing a sensor component in a second area on the motherboard, excluding the first area. This placement ensures the sensor component is positioned far from the processor component, preventing it from affecting the existing cooling airflow and mechanical structure within the first area, and also avoiding disruption of the existing electromagnetic environment. By detecting the second electromagnetic field strength in the second area using the sensor component located on the periphery, the first electromagnetic field strength in the first area can be indirectly detected. This achieves non-invasive detection of the electromagnetic field strength in the core-sensitive first area of ​​the motherboard, improving the accuracy of electromagnetic field strength detection within the first area. It avoids the problem in related technologies where forcibly placing sensors in the space-constrained core area alters the original electromagnetic environment, leading to distorted measurement data. Flexible control of the power supply cable's on / off state based on the first electromagnetic field strength in the first area enables precise security protection for the server. Attached Figure Description

[0010] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 One of the schematic diagrams of the server structure according to some embodiments of this application is shown;

[0012] Figure 2 A second schematic diagram of the server structure according to some embodiments of this application is shown;

[0013] Figure 3 The third schematic diagram of the server structure is shown in some embodiments of this application;

[0014] Figure 4 The fourth schematic diagram of the server structure is shown in some embodiments of this application;

[0015] Figure 5The fifth schematic diagram shows the structure of a server according to some embodiments of this application;

[0016] Figure 6 Flowcharts of electromagnetic interference protection methods according to some embodiments of this application are shown;

[0017] Figure 7 Flowcharts of electromagnetic interference protection methods according to some embodiments of this application are shown;

[0018] Figure 8 Structural block diagrams of electromagnetic interference protection devices according to some embodiments of this application are shown;

[0019] Figure 9 Structural block diagrams of electronic devices according to some embodiments of this application are shown.

[0020] Figure label:

[0021] 100 Server, 110 Motherboard, 111 First Area, 112 Second Area, 113 First Sub-area, 114 Second Sub-area, 120 Processor Components, 130 Sensor Components, 131 Electromagnetic Field Sensor, 132 Magnetic Field Sub-sensor, 133 Electric Field Sub-sensor, 140 Switching Components, 150 Power Supply Cables, 160 Data Transmission Channels, 170 Signal Conditioning Unit, 180 Processing Unit, 190 Electromagnetic Shielding Structure. Detailed Implementation

[0022] 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 of ordinary skill in the art without creative effort are within the protection scope of this application.

[0023] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0024] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] In response to the increasing power density of servers, more and more servers are choosing high-voltage direct current (HVDC) power supply architectures, such as 800V DC or ±400V DC power. Compared to traditional AC power supply architectures, HVDC power supply architectures reduce the number of AC-to-DC conversions, improve energy efficiency, and reduce power transmission losses and hardware costs. However, HVDC architectures suffer from strong electromagnetic interference (EMI) problems; the DC busbars and power cables carrying high currents generate strong static magnetic fields and induced electric fields around them.

[0026] Due to the highly integrated internal space of servers, core components such as the Central Processing Unit (CPU), Graphics Processing Unit (GPU), and high-speed serial bus in the core area of ​​the server motherboard are extremely sensitive to the electromagnetic environment. The electromagnetic fields generated by the high-voltage DC power supply architecture may cause the following problems:

[0027] Signal Integrity (SI) Issues: Interference with the transmission of high-speed differential signals leads to an increase in the Bit Error Rate (BER).

[0028] Power Integrity (PI) Issues: Noise is introduced into the Power Distribution Network (PDN), affecting the power supply quality of the chip.

[0029] Potential hardware damage issues: Performance degradation of components such as CPUs and GPUs caused by long-term exposure to strong electromagnetic fields.

[0030] During operation, the server needs to continuously monitor the electromagnetic field strength in the core area and use the electromagnetic field strength as a control basis to control the operation of the server, thereby reducing the possibility of server malfunctions caused by electromagnetic interference and damage to components in the core area.

[0031] Traditional electromagnetic field monitoring solutions typically rely on directly installing electromagnetic field sensors in core areas. However, in server designs, the core areas requiring monitoring—such as the CPU / GPU area, memory module area, and high-speed serial link cabling area—are already maximally utilized with extremely high cabling density, leaving almost no physical space to install any type of sensor. Forcing sensors into these core areas would not only alter the existing cooling airflow and mechanical structure but also disrupt the original electromagnetic environment, resulting in "monitoring itself changing the outcome," thus reducing the server's electromagnetic interference protection capabilities.

[0032] To address the technical problems in the aforementioned related technologies, this application proposes a server, which is described below in conjunction with the appendix. Figure 1 To be continued Figure 9 This application will be described in further detail.

[0033] In some embodiments of this application, a server is proposed. Figure 1 One of the schematic diagrams of the server structure of some embodiments of this application is shown, such as Figure 1 As shown, server 100 includes: motherboard 110, power supply cable 150 and switch 140.

[0034] The motherboard 110 includes a sensor assembly 130 and a processor assembly 120. The processor assembly 120 is located in a first region 111 of the motherboard 110, and the sensor assembly 130 is located in a second region 112 of the motherboard 110. The first region 111 and the second region 112 are not connected. The sensor assembly 130 is used to collect a second electromagnetic field strength threshold value in the second region 112. A power supply cable 150 is connected to the motherboard 110 and is used to supply power to the motherboard 110. A switch 140 is connected to the power supply cable 150, and the on / off state of the switch 140 is used to control the power supply state of the motherboard 110. Specifically, when the first electromagnetic field strength in the first region 111 is greater than or equal to the strength threshold value, the on / off state of the switch 140 switches from a conducting state to an off state. The first electromagnetic field strength is a magnetic field strength determined based on the second electromagnetic field strength and a first distance, where the first distance is the distance between the sensor assembly 130 and the power supply cable 150.

[0035] In this embodiment, the motherboard 110 is the core circuit board that carries various electronic components in the server 100. The sensor assembly 130 is a device capable of sensing the electromagnetic field strength at its location. The processor assembly 120 is the core computing unit on the motherboard 110, including a central processing unit and / or a graphics processing unit. The power cable 150 is a wire used to transmit external power to the motherboard 110. Since the power cable 150 is a cable used to supply power to the motherboard 110 in a high-voltage DC power supply architecture, the power cable 150 is a core source of electromagnetic interference.

[0036] Exemplarily, the main board is a printed circuit board (PCB).

[0037] Exemplarily, the power supply cable 150 includes at least one of the following: a DC bus, a key wire of a power distribution network. It should be noted that at least part of the power supply cable 150 is disposed on the main board 110.

[0038] Exemplarily, the sensor assembly 130 includes an electric field sub-sensor 133 and a magnetic field sub-sensor 132. Specifically, for example: the electric field sub-sensor 133 includes at least one of the following: a capacitive coupling electric field sensor, an optical electric field sensor. The magnetic field sub-sensor 132 includes at least one of the following: a Hall effect sensor, a fluxgate sensor, a magnetoresistive sensor.

[0039] As Figure 1 shown, L1 shows the first distance, L2 shows the second distance, and L1 < L2. L3 shows the third distance. Exemplarily, the third distance is the distance between the processor assembly 120 and the power supply cable 150, and L3 > L2.

[0040] In this embodiment, the main board 110 includes a first region 111 and a second region 112. Among them, the first region 111 is the core region on the main board 110, that is, the first region 111 is used to deploy the processor assembly 120; the second region 112 can be any region on the main board 110 except the core region, and this second region 112 is used to deploy the sensor assembly 130.

[0041] The processor assembly 120 is disposed in the first region 111 of the main board 110. This first region 111 is the core region on the main board 110 with high power consumption and high electromagnetic radiation, and the sensor assembly 130 is disposed in the second region 112 of the main board 110. The first region 111 and the second region 112 are not physically connected, that is, there is a gap between the two regions. In other words, the sensor assembly 130 is not disposed in the core region of the main board 110. Therefore, it is ensured that the sensor assembly 130 will not change the original heat dissipation air duct and mechanical structure, and will not damage the original electromagnetic environment in the first region 111. The power supply cable 150 is laid on the main board 110 to provide power for the entire main board 110 system.

[0042] During the operation of the server 100, the sensor assembly 130 monitors the second electromagnetic field strength in its所在的second region 112. Since the electromagnetic interference received by the processor assembly 120 mainly comes from the radiation of the power supply cable 150, there is a certain law in the spatial distribution of the electromagnetic field strength. That is to say, the first electromagnetic field strength in the first region 111 can be determined based on the second electromagnetic field strength and the first distance between the sensor assembly 130 and the power supply cable 150.

[0043] For example, through prior testing or simulation, a correspondence model can be established between the first distance between the sensor assembly 130 and the power supply cable 150, the second electromagnetic field strength measured by the sensor assembly 130, and the first electromagnetic field strength in the first region 111 where the processor assembly 120 is located. By deploying this correspondence model to the server 100 system, the model enables the server 100 system to calculate the first electromagnetic field strength in the first region 111 based on the measured second electromagnetic field strength and the known first distance.

[0044] In this embodiment, the switch 140 can control the circuit to open and close according to the electrical signal. When the switch 140 is in the on state, the power supply cable 150 and the motherboard 110 are in a conductive state, that is, the power supply cable 150 can supply power to the motherboard 110 at this time; when the switch 140 is in the off state, the power supply cable 150 and the motherboard 110 are in an open circuit state, that is, the power supply cable 150 cannot supply power to the motherboard 110 at this time.

[0045] For example, the switch 140 may be an electronic fuse (eFuse) connected in series in the path of the power supply cable 150.

[0046] Understandably, when the intensity of the first electromagnetic field in the first region 111 is greater than or equal to the intensity threshold, it is determined that the intensity of the first electromagnetic field is too high. This indicates that the electromagnetic environment of the first region 111 where the processor component 120 is located has exceeded the safe range, posing a risk of causing malfunctions and hardware damage to the server 100. At this time, the server 100 system control switch 140 switches from the on state to the off state. The switch 140 disconnects the power supply to the motherboard 110 through the power cable 150, causing the processor component 120 to stop working and preventing the processor component 120 from operating in an electromagnetic environment that exceeds the safe range.

[0047] In this embodiment, a sensor assembly 130 is placed in a second region 112 on the motherboard 110, excluding the first region 111. This placement of the sensor assembly 130 is far from the processor assembly 120, ensuring that it does not affect the existing heat dissipation channels and mechanical structures within the first region 111 where the processor assembly 120 is located, nor does it disrupt the existing electromagnetic environment. By detecting the second electromagnetic field strength in the second region 112 using the sensor assembly 130 located in the peripheral second region 112, the first electromagnetic field strength in the first region 111 is indirectly detected. This achieves non-invasive detection of the electromagnetic field strength in the core-sensitive first region 111 on the motherboard 110, improving the accuracy of electromagnetic field strength detection within the first region 111. It avoids the problem in related technologies where forcibly placing sensors in a space-constrained core area alters the original electromagnetic environment, leading to distorted measurement data. Flexible control of the power supply cable 150's on / off state based on the first electromagnetic field strength of the first region 111 provides precise security protection for the server 100, preventing data errors and hardware damage that may result from electromagnetic interference.

[0048] Figure 2 The second schematic diagram of the server structure according to some embodiments of this application is shown. Figure 3 The third schematic diagram of the server structure shown is one of some embodiments of this application, such as... Figure 2 and Figure 3 As shown, in some embodiments of this application, the first distance is greater than the second distance, wherein the second distance is the distance between the sensor assembly 130 and the processor assembly 120.

[0049] In this embodiment, the first distance is the distance between the sensor assembly 130 and the power supply cable 150, and the second distance is the distance between the sensor assembly 130 and the processor assembly 120. Since the first distance is greater than the second distance, the distance between the sensor assembly 130 and the power supply cable 150 is greater than the distance between the sensor assembly 130 and the processor assembly 120.

[0050] Specifically, the second region 112 of the sensor assembly 130 is positioned closer to the first region 111 and further away from the power supply cable 150. The sensor assembly 130 includes multiple sensors, which are mounted as close as possible to the processor assembly 120, but maintain a non-contact second distance to avoid physically interfering with the processor assembly 120's cooling airflow and mechanical structure. The power supply cable 150 is typically located at the edge of the motherboard 110 or further away from the processor assembly 120, while the sensor assembly 130 is positioned adjacent to the processor assembly 120. That is, the first distance from the sensor assembly 130 to the power supply cable 150 is greater than the second distance from the sensor assembly 130 to the processor assembly 120. In this layout, due to the shorter second distance, the location of the sensor assembly 130 is more directly related to the electromagnetic environment of the core region. The second electromagnetic field strength measured by the sensor assembly 130 in the second region 112 is closer to the second electromagnetic field strength of the first region, improving the accuracy of calculating the first electromagnetic field strength of the first region 111 by inverting the second electromagnetic field strength and the first distance.

[0051] It should be noted that the layout with the first distance greater than the second distance is suitable for high power density and high voltage applications. Since the server 100 has a high power density and high voltage DC power supply architecture, when the power supply cable 150 is the main source of interference, the electromagnetic field generated by the power supply cable 150 can radiate into the first region 111. Therefore, setting the first distance greater than the second distance, so that the sensor component 130 is closer to the first region 111 where the processor component 120 is deployed, can effectively improve the accuracy of calculating the first electromagnetic field strength based on the second electromagnetic field strength.

[0052] For example, when the power of server 100 is greater than 1MW or the voltage is greater than 1000V, a layout in which the first distance is greater than the second distance is adopted.

[0053] In this embodiment, by setting the first distance between the sensor assembly 130 and the power supply cable 150 to be greater than the second distance between the sensor assembly 130 and the processor assembly 120, the sensor assembly 130 can be positioned as close as possible to the first region 111 while maintaining a non-invasive location, thereby further improving the accuracy of sensing the electromagnetic environment of the first region 111.

[0054] like Figure 1 and Figure 2As shown, in some embodiments of this application, the first region 111 includes a first sub-region 113 and a second sub-region 114. The processor component 120 is located within the first sub-region 113. The server 100 further includes: a data transmission channel 160 disposed in the second sub-region 114; at least a portion of the second region 112 is located around the periphery of the first sub-region 113, and at least two electromagnetic field sensors 131 in the sensor component 130 are disposed around the periphery of the processor component 120; and at least a portion of the second region 112 is located around the periphery of the second sub-region 114, and at least two electromagnetic field sensors 131 in the sensor component 130 are disposed around the periphery of the data transmission channel 160.

[0055] In this embodiment, the first region 111 is the core functional area on the motherboard 110. The first region 111 includes a first sub-region 113 and a second sub-region 114. The first sub-region 113 is the area where the processor component 120 is located, and the second sub-region 114 is the area where the data transmission channel 160 is located.

[0056] For example, data transmission channel 160 is a physical link for high-speed data transmission between various components on motherboard 110, such as the cabling area where a PCIe (Peripheral Component Interconnect Express) channel or memory bus is located.

[0057] The sensor assembly 130 includes multiple independent sensors capable of sensing electric or magnetic fields, and these sensor units are arranged corresponding to a first sub-region 113 and a second sub-region 114 within the first region 111. At least a portion of the second region 112 is located around the periphery of the first sub-region 113.

[0058] Specifically, at least two electromagnetic field sensors 131 in sensor assembly 130 are arranged to surround the processor assembly 120, forming a monitoring ring. Similarly, at least another portion of the second region 112 is located around the second sub-region 114. At least two more electromagnetic field sensor units 131 in sensor assembly 130 are arranged to surround the data transmission channel 160, forming another monitoring ring. This arrangement of sensors adjacent to and surrounding key sub-regions constitutes a "sensor fence" for the core functional area.

[0059] In this embodiment, at least two electromagnetic field sensors 131 surrounding the first sub-region 113 are capable of measuring the electromagnetic field strength immediately adjacent to the boundary of the processor assembly 120. At least two electromagnetic field sensors 131 surrounding the second sub-region 114 are capable of measuring the electromagnetic field strength immediately adjacent to the boundary of the data transmission channel 160. Because the sensors are spatially very close to the monitored critical sub-regions, the second electromagnetic field strength data they collect can most directly reflect the electromagnetic field distribution at the processor assembly 120 and the data transmission channel 160.

[0060] By arranging at least two electromagnetic field sensors 131 in the sensor assembly 130 around the periphery of the processor assembly 120, and by arranging at least two more electromagnetic field sensors 131 in the sensor assembly 130 around the periphery of the data transmission channel 160, the field distribution on the boundaries of the corresponding first sub-region 113 and second sub-region 114 can be obtained. In the inversion calculation, the solution domain of the electromagnetic field inverse problem is limited to the annular region formed by the periphery of the first region 111 and the chassis boundary of the server 100, thereby greatly reducing the uncertainty and complexity of the inversion calculation, and thus more directly reflecting the overall electromagnetic environment level in which the sensitive device is actually located.

[0061] It should be noted that the at least two electromagnetic field sensors 131 surrounding the processor assembly 120 in the sensor assembly 130 include an electric field sub-sensor 133 and a magnetic field sub-sensor 132, and the at least two electromagnetic field sensors 131 surrounding the data transmission channel 160 also include an electric field sub-sensor 133 and a magnetic field sub-sensor 132, thereby ensuring that the sensor assembly 130 can collect the electromagnetic field strength near the processor assembly 120 and the electromagnetic field strength near the data transmission channel 160.

[0062] In this embodiment, by arranging some sensors of the sensor assembly 130 around the processor assembly 120 and others around the data transmission channel 160, the electromagnetic field data collected by the sensor assembly 130 can more directly reflect the combined electromagnetic field level at the boundary between the first sub-region 113 and the second sub-region 114. Furthermore, since the solution domain required by the computational model is limited to a ring-shaped area close to the core region, the uncertainty and complexity of the inversion calculation itself are reduced, thereby improving the accuracy of the first electromagnetic field strength determined by the second electromagnetic field strength.

[0063] This application embodiment solves the spatial conflict and electromagnetic interference problems faced by directly installing sensors inside high-density cabling areas by establishing independent, non-intrusive monitoring rings around the first sub-region 113 and the second sub-region 114 that require key protection. This provides a reliable data foundation for achieving accurate electromagnetic safety protection inside the server 100.

[0064] like Figure 1 and Figure 3 As shown, in some embodiments of this application, the second region 112 and the first region 111 are arranged side by side, and the difference between the first distance and the third distance is less than the difference threshold. The third distance is the distance between the processor component 120 and the power supply cable 150.

[0065] In this embodiment, the second region 112 and the first region 111 are arranged side by side on the motherboard 110, and the difference between the first distance and the third distance is less than the difference threshold. This means that the first distance between the sensor assembly 130 and the power supply cable 150 is approximately equal to the third distance between the processor assembly 120 and the power supply cable 150.

[0066] In this embodiment, the sensor assembly 130 and the processor assembly 120 are arranged side by side on the motherboard 110, and the sensor assembly 130 and the processor assembly 120 are arranged side by side along the extension direction of the power supply cable 150.

[0067] With the sensor assembly 130 and processor assembly 120 arranged side-by-side, the distances from the sensor assembly 130 and processor assembly 120 to the power supply cable 150 are relatively close. Furthermore, the power supply cable 150 is the primary source of electromagnetic interference for the processor assembly 120. Therefore, the electromagnetic environments of the sensor assembly 130 and processor assembly 120 are highly similar. Consequently, the average value of at least two second electromagnetic field intensities collected by the sensor assembly 130 can be used as the first electromagnetic field intensity.

[0068] like Figure 3 As shown, for example, L1 is the first distance and L3 is the third distance, where L1 is approximately equal to L3, and both L1 and L3 are greater than L2.

[0069] For example, when determining the first electromagnetic field strength based on the second electromagnetic field strength and the first distance, the numerical relationship between the first distance and the third distance can be determined first. If the difference between the first distance and the third distance is less than the difference threshold, the average of the at least two second electromagnetic field strengths collected can be calculated to determine the first electromagnetic field strength.

[0070] In this embodiment, by arranging the sensor component 130 and the processor component 120 side by side and ensuring that the difference between the first distance and the third distance is less than the difference threshold, the sensor component 130 and the processor component 120 can be placed in similar electromagnetic environments. At this time, the average value of at least two second electromagnetic field intensities collected by the sensor component 130 can be used as the first electromagnetic field intensity, which simplifies the calculation process of the first electromagnetic field intensity.

[0071] Figure 4 The fourth schematic diagram of the server structure according to some embodiments of this application is shown. Figure 5 The fifth schematic diagram of the server structure shown is one of some embodiments of this application, such as... Figure 4 and Figure 5 As shown, in some embodiments of this application, the first distance is less than the second distance, wherein the second distance is the distance between the sensor assembly 130 and the processor assembly 120.

[0072] In this embodiment, the first distance is the distance between the sensor assembly 130 and the power supply cable 150, and the second distance is the distance between the sensor assembly 130 and the processor assembly 120. Since the first distance is smaller than the second distance, the distance between the sensor assembly 130 and the power supply cable 150 is closer than the distance between the sensor assembly 130 and the processor assembly 120.

[0073] Specifically, sensor assembly 130 is positioned close to power cable 150, which is a known strong source of electromagnetic interference on motherboard 110. In this configuration, the second electromagnetic field strength detected by sensor assembly 130 is the electromagnetic field strength located immediately adjacent to power cable 150. Due to the relatively small distance between sensor assembly 130 and the interference source, the measured signal strength is very high. Other secondary interference sources and noise in the environment are extremely weak compared to this primary interference signal, resulting in a very high signal-to-noise ratio for the measured signal.

[0074] It should be noted that the layout where the first distance is less than the second distance is suitable for low-to-medium power density, high-voltage applications. Since the server 100 has a low-to-medium power density, low-to-medium voltage DC power supply architecture, when the power supply cable 150 is the main source of interference, the electromagnetic field generated by the power supply cable 150 is difficult to radiate into the first area 111. Therefore, setting the first distance to be less than the second distance, so that the sensor component 130 is closer to the power supply cable 150, can effectively reduce the interference of other secondary interference sources and noise in the environment on the detected electromagnetic field strength.

[0075] like Figure 4 and Figure 5 As shown, L1 is the first distance, and L2 is the second distance. <L2。

[0076] For example, when the power of server 100 is less than 1MW and the voltage is less than 1000V, a layout in which the first distance is less than the second distance is adopted.

[0077] In this embodiment, by placing the sensor assembly 130 closer to the power cable 150 relative to the processing assembly, the second electromagnetic field strength collected by the sensor assembly 130 is made closer to the interfering electromagnetic field generated by the power cable 150. Therefore, the second electromagnetic field strength collected by the sensor assembly 130 is less affected by other interference sources and has a higher signal-to-noise ratio, further improving the accuracy of the first electromagnetic field strength determined based on the second electromagnetic field strength.

[0078] like Figure 4 and Figure 5 As shown, in some embodiments of this application, at least two electromagnetic field sensors 131 in the sensor assembly 130 are located on both sides of the power supply cable 150; or at least two electromagnetic field sensors 131 in the sensor assembly 130 are located on one side of the power supply cable 150.

[0079] In this embodiment, the sensor assembly 130 is relatively close to the power supply cable 150, that is, the first distance is less than the second distance. At least two electromagnetic field sensors 131 in the sensor assembly 130 can be located on opposite sides of the power supply cable 150; or at least two electromagnetic field sensors 131 in the sensor assembly 130 can both be located on the same side of the power supply cable 150.

[0080] When at least two electromagnetic field sensors 131 are located on both sides of the power supply cable 150, the at least two electromagnetic field sensors 131 can collect electromagnetic field data that differ in spatial vector direction, that is, the at least two second electromagnetic field intensities provided by the at least two electromagnetic field sensors 131 have certain differences. Specifically, for magnetic field strength, the magnetic field lines on both sides of the power supply cable 150 are in opposite directions. This arrangement can obtain more comprehensive spatial field distribution information. When calculating the first electromagnetic field intensity of the first region 111 using the at least two second electromagnetic field intensities provided by the at least two electromagnetic field sensors 131, the data from the sensors on both sides can be mutually verified and calibrated, which helps to correct the calculation results and reduce calculation deviations or uncertainties caused by a single sensor placement location.

[0081] When at least two electromagnetic field sensors 131 are located on the same side of the power supply cable 150, this configuration is suitable for scenarios where the layout space of the motherboard 110 is limited or where centralized monitoring is required in a specific direction. The at least two electromagnetic field sensors 131 can be arranged along the extension direction of the power supply cable 150, and the distances between the at least two electromagnetic field sensors 131 and the power supply cable 150 can be the same or different. This arrangement can acquire information on the gradient change of the electromagnetic field intensity on one side of the power supply cable 150, providing more detailed electromagnetic field distribution parameters when calculating the first electromagnetic field intensity based on the second electromagnetic field intensity.

[0082] In this embodiment, at least two electromagnetic field sensors 131 in the sensor assembly 130 can be distributed on one or both sides of the power supply cable 150, which improves the flexibility and freedom of the layout of the sensor assembly 130 near the power supply cable 150. It allows for the selection of better sensor placement points according to the actual layout of the server 100 motherboard 110, and further improves the accuracy of determining the first electromagnetic field strength while avoiding the sensor assembly 130 from intruding into the first core area 111.

[0083] like Figures 1 to 5 As shown, in some embodiments of this application, the server 100 further includes a signal conditioning unit 170 and a processing unit 180.

[0084] The input terminal of the signal conditioning unit 170 is connected to the output terminals of at least two electromagnetic field sensors 131 in the sensor assembly 130; the input terminal of the processing unit 180 is connected to the output terminal of the signal conditioning unit 170, and the output terminal of the processing unit 180 is connected to the control terminal of the switch 140.

[0085] In this embodiment, the signal conditioning unit 170 is a circuit or chip used to preprocess the raw electrical signals acquired and output by at least two electromagnetic field sensors 131.

[0086] Specifically, the input of the signal conditioning unit 170 is connected to the output of at least two electromagnetic field sensors 131 in the sensor assembly 130. Specifically, each sensor is connected to a high-resolution, multi-channel synchronous data acquisition chip, which serves as the signal conditioning unit 170. The signal conditioning unit 170 is responsible for amplifying the analog signals output by the sensors to achieve an amplitude suitable for processing; simultaneously filtering the analog signals output by the sensors to eliminate high-frequency noise and prevent signal aliasing; and ensuring synchronous sampling of sensor signals from all channels to guarantee the temporal consistency of all data.

[0087] In this embodiment, the processing unit 180 is a processor with logic operation and control capabilities.

[0088] Specifically, the input terminal of the processing unit 180 is connected to the output terminal of the signal conditioning unit 170. The sensor signal conditioned by the signal conditioning unit 170 is transmitted to the processing unit 180 through a digital interface. The output terminal of the processing unit 180 is connected to the control terminal of the switch 140. When the judgment logic result of the processing unit 180 is that the first electromagnetic field strength is greater than or equal to the strength threshold, the processing unit 180 sends a control signal to the control terminal of the switch 140. This control signal drives the switch 140 to switch from the on state to the off state, thereby cutting off the power supply to the motherboard 110.

[0089] For example, the processing unit 180 can be a Baseboard Management Controller (BMC) on the motherboard 110 of the server 100 or a dedicated embedded microcontroller / Field-Programmable Gate Array (FPGA). The processing unit 180 is responsible for configuring the acquisition parameters of the signal conditioning unit 170 via a digital bus such as I2C (Inter-Integrated Circuit) or SPI (Serial Peripheral Interface), and receiving sensor data from all channels after conditioning and digitization.

[0090] In this embodiment, the signal conditioning unit 170 ensures the quality and temporal consistency of sensor data collected by at least two electromagnetic field sensors 131 through amplification, filtering, and synchronous sampling, thereby improving the accuracy of the second electromagnetic field strength. The processing unit 180 undertakes complex algorithm calculations and logical judgment tasks, namely, determining the first electromagnetic field strength based on the second electromagnetic field strength, and controlling the switching device 140 based on the comparison result of the first electromagnetic field strength and the strength threshold. This enables the entire server 100 to automatically and accurately perform monitoring and protection functions, thereby achieving effective monitoring and security protection of the internal electromagnetic environment of the server 100 without installing sensors in the core first area 111.

[0091] In some embodiments of this application, the server 100 further includes an electromagnetic shielding structure 190, which covers the surface of the power supply cable 150.

[0092] In this embodiment, the electromagnetic shielding structure 190 is a shell or covering layer made of conductive or magnetically conductive material used to suppress the propagation of high-frequency electromagnetic waves. The power supply cable 150 is a conductor used to transmit electrical energy.

[0093] Specifically, the electromagnetic shielding structure 190 is wrapped around the surface of the power supply cable 150, forming a continuous wrapping layer. This structure can be represented as a woven metal mesh or metal foil strip, and its function is to form a closed conductive path.

[0094] When a changing current flows through the power supply cable 150, an alternating electromagnetic field is generated and radiated into the surrounding space, forming electromagnetic interference noise. The electromagnetic shielding structure 190, through absorption and reflection effects, confines the high-frequency electromagnetic noise generated by the power supply cable 150 within its sheath or guides it to a grounding path, thereby suppressing the radiation intensity of the noise into the external free space.

[0095] In this embodiment, by providing an electromagnetic shielding structure 190 on the power supply cable 150, the background electromagnetic noise level reaching the second region 112 where the sensor assembly 130 is located is reduced. This reduces the noise component originating from the power supply cable 150 in the second electromagnetic field strength signal measured by the sensor assembly 130, effectively improving the signal-to-noise ratio of the measurement signal. The higher signal-to-noise ratio provides more accurate and reliable raw data input for subsequent inversion calculation of the first electromagnetic field strength in the first region 111 based on the second electromagnetic field strength.

[0096] The following describes the process by which the processing unit determines the strength of the first electromagnetic field based on the strength of the second electromagnetic field:

[0097] According to the Biot-Sava law, replacing the wires in the server with an infinitely long straight wire model, the expression for its magnetic field strength (1) is as follows:

[0098] (1)

[0099] in, B The magnetic field strength, μ 0 represents the permeability in vacuum. I bus This represents the current current value within the power supply cable. r This represents the distance from the conductor.

[0100] However, the power cables inside servers are limited in size, and the surrounding environment, including metal chassis, ground planes, and other wires, is complex. This significantly alters the electromagnetic field distribution, leading to deviations in the calculation results of the ideal formula. To address this issue, a position-dependent first position correction coefficient is introduced. k B This transforms the theoretical formula into a high-precision, practical model. Taking a sensor assembly comprising three electromagnetic field sensors as an example, the obtained magnetic induction intensities are respectively... B 1. B 2. B 3. The first distances between the three electromagnetic field sensors and the power supply cables are respectively...r 1. r 2. r 3. The expressions (2), (3), and (4) for the three magnetic field strengths collected by the three electromagnetic field sensors are as follows:

[0101] (2)

[0102] (3)

[0103] (4)

[0104] in, B 1. B 2. B 3 represents the magnetic field strength collected by three electromagnetic field sensors. k B This is the correction factor for the first position. μ 0 represents the permeability in vacuum. I bus This represents the current current value within the power supply cable. r 1. r 2. r 3 represents the first distance corresponding to the three sensors.

[0105] Introducing the first constant in the target constant C B The expression for the first constant (5) is as follows:

[0106] (5)

[0107] in, C B It is the first constant. k B This is the correction factor for the first position. μ 0 represents the permeability in vacuum. I bus This represents the current current value within the power supply cable.

[0108] Combining the above expressions (2), (3), (4) and (5), the first constant is estimated using the least squares method. The estimation expression for the first constant (6) is as follows:

[0109] ； (6)

[0110] in, This is an estimated value for the first constant. r i is the first i Each sensor corresponds to the first distance. B i For the firsti The magnetic field strength collected by each sensor It is calculated using the least squares method.

[0111] The magnetic field strength in the first region can be calculated using the following expression (7):

[0112] (7)

[0113] in, This is an estimated value for the first constant. This is the third distance value. B CPU The magnetic field strength is in the first region.

[0114] The electric field strength in the first electromagnetic field strength is calculated based on Gauss's law. However, the power supply cables inside the server are of limited size, and the surrounding environment, including the metal chassis, ground plane, and other wires, significantly alters the electromagnetic field distribution, leading to deviations in the ideal formula calculation results. To address this issue, a position-dependent second position correction coefficient is introduced. k E The expressions (8), (9), and (10) for the three magnetic field strengths collected by the three electric field sensors are as follows:

[0115] (8)

[0116] (9)

[0117] (10)

[0118] in, E 1. E 2. E 3 represents the electric field intensity collected by the three electric field sensors. k E This is the correction factor for the second position. The dielectric constant in vacuum. The charge density in the conductor. r 1. r 2. r 3 represents the first distance corresponding to the three sensors.

[0119] Introducing the second constant in the target constant C E The expression for the second constant (11) is as follows:

[0120] (11)

[0121] in, C E It is the second constant.k E This is the correction factor for the second position. The dielectric constant in vacuum. Let be the charge density in the conductor.

[0122] Combining the above expressions (8), (9), (10) and (11), the second constant is estimated using the least squares method. The estimation expression for the second constant (12) is as follows:

[0123] (12)

[0124] in, This is an estimated value for the second constant. r i is the first i Each sensor corresponds to the first distance. E i For the first i The electric field intensity collected by each sensor.

[0125] The electric field strength in the first region can be calculated using the following expression (13):

[0126] (13)

[0127] in, This is an estimated value for the second constant. This is the third distance value. E CPU Let be the electric field strength in the first region.

[0128] It should be noted that in the scheme where the first and second regions are arranged side by side, if the difference between the first distance and the third distance is less than the difference threshold, it can be seen from the above expression that the electromagnetic field strength is related to the distance from the power supply cable. In this layout, the distance between the sensor component and the power supply cable is approximately equal to the distance between the processor component and the power supply cable. Therefore, the average value of the second electromagnetic field strength collected by at least two electromagnetic field sensors can be used as the first electromagnetic field strength. The calculation expressions (14) and (15) are as follows:

[0129] (14)

[0130] (15)

[0131] in, B CPU The magnetic field strength in the first region, E CPU The electric field strength in the first region is... E i For the first iThe electric field intensity collected by each sensor B i For the first i The magnetic field strength collected by each sensor.

[0132] In some embodiments of this application, an electromagnetic interference protection method is proposed. Figure 6 Flowcharts of electromagnetic interference protection methods according to some embodiments of this application are shown, such as... Figure 6 As shown, electromagnetic interference protection methods include:

[0133] S601, acquire the second electromagnetic field strength of the second region collected by the sensor assembly;

[0134] In this embodiment, the motherboard includes a first region and a second region. The first region is the core region on the motherboard, i.e., the first region is used to deploy processor components. The second region can be any region on the motherboard other than the core region, and this second region is used to deploy sensor components. During server operation, the sensor components monitor the intensity of a second electromagnetic field in the second region where they are located.

[0135] S602, determine the first electromagnetic field strength of the first region based on the second electromagnetic field strength and the first distance; wherein, the first distance is the distance between the sensor assembly and the power supply cable;

[0136] In this embodiment, since the electromagnetic interference received by the processor component mainly comes from the radiation of the power supply cable, the electromagnetic field strength has a certain regularity in spatial distribution. That is to say, the first electromagnetic field strength in the first region can be determined based on the second electromagnetic field strength and the first distance between the sensor component and the power supply cable.

[0137] S603, when the first electromagnetic field strength is greater than or equal to the strength threshold, the control switch is switched from the on state to the off state.

[0138] In this embodiment, the switching element is a component that controls the on / off state of the circuit according to the electrical signal. When the switching element is in the on state, the power supply cable is in a conductive state with the motherboard, that is, the power supply cable can supply power to the motherboard at this time; when the switching element is in the off state, the power supply cable is in an open circuit state with the motherboard, that is, the power supply cable cannot supply power to the motherboard at this time.

[0139] For example, the switching element can be an electrical fuse (eFuse), which is connected in series in the path of the power supply cable.

[0140] Understandably, when the intensity of the first electromagnetic field in the first region is greater than or equal to the intensity threshold, it is determined to be too high. This indicates that the electromagnetic environment of the first region where the processor component is located has exceeded the safe range, posing a risk of server malfunction and hardware damage. At this time, the server system control switch switches from the on state to the off state. The switch disconnects the power supply to the motherboard through the power cable, causing the processor component to stop working and preventing it from operating in an electromagnetic environment beyond the safe range.

[0141] In this embodiment, a sensor component is placed in a second region on the motherboard, excluding the first region. This placement ensures the sensor component is far from the processor component, preventing it from affecting the existing heat dissipation channels and mechanical structure within the first region where the processor component is located, and also avoids disrupting the existing electromagnetic environment. By detecting the second electromagnetic field strength in the second region using the sensor component located in the peripheral area, the first electromagnetic field strength in the first region is indirectly detected. This achieves non-invasive detection of the electromagnetic field strength in the core-sensitive first region of the motherboard, improving the accuracy of electromagnetic field strength detection within the first region. It avoids the problem in related technologies where forcibly placing sensors in the space-constrained core area alters the original electromagnetic environment, leading to distorted measurement data. Flexible control of the power supply cable's on / off state based on the first electromagnetic field strength in the first region provides precise security protection for the server, preventing data errors and hardware damage that may be caused by electromagnetic interference.

[0142] In some embodiments of this application, the sensor assembly includes at least two electromagnetic field sensors, which are respectively used to collect at least two second electromagnetic field sub-intensities in the second electromagnetic field strength, and the first distance includes at least two fourth distances between the at least two electromagnetic field sensors and the power supply cable respectively.

[0143] The first electromagnetic field strength of the first region is determined based on the second electromagnetic field strength and the first distance, including:

[0144] A target constant is determined based on at least two second electromagnetic field strengths and at least two corresponding fourth distances; wherein the target constant is used to characterize the inherent magnetic field strength of the power supply cable when the current value is passed through it, and the inherent electric field strength of the power supply cable at the current charge density; a first electromagnetic field strength is determined based on the target constant and a third distance; wherein the third distance is the distance between the processor component and the power supply cable.

[0145] In this embodiment, the sensor assembly includes at least two electromagnetic field sensors, which are installed in different positions. Therefore, the first distance includes at least two fourth distances between the at least two electromagnetic field sensors and the power supply cable, respectively.

[0146] It should be noted that the at least two electromagnetic field sensors include at least one electric field sensor and at least one magnetic field sensor, that is, the at least two second electromagnetic field sub-intensities include at least one second magnetic field sub-intensity and at least one second electric field sub-intensity.

[0147] For example, the target constants include a first constant and a second constant. The first constant is used to characterize the inherent magnetic field strength in the power supply cable when the current value is passed through it; the second constant is used to characterize the inherent magnetic field strength in the power supply cable when the current value is passed through it. The expression for the first constant is given in expression (5), and the expression for the second constant is given in expression (11).

[0148] In this embodiment, since the target constant can characterize the inherent magnetic field strength and inherent electric field strength of the power supply cable under the current conditions, and the third distance between the processor component and the power supply cable has been pre-existing in the server system, the corresponding first electromagnetic field strength can be calculated based on the third distance value and the target constant.

[0149] For example, the first electromagnetic field strength includes the magnetic field strength of the first region and the electric field strength within the first region. The calculation expression for the magnetic field strength within the first region is given in expression (7), and the calculation expression for the electric field strength within the first region is given in expression (13).

[0150] In this embodiment, the target constant can be calculated using the fourth distance between each electromagnetic field sensor in the sensor assembly and the power supply cable, as well as the second electromagnetic field strength collected by each electromagnetic field sensor. This target parameter can characterize the inherent magnetic field strength in the power supply cable when the current value is passed through it. Therefore, the first electromagnetic field strength in the first region can be calculated by inversion based on the third distance between the processor assembly and the power supply cable. This method of determining the first electromagnetic field strength is applicable to different layouts of the sensor assembly, further improving the flexibility of the sensor assembly layout.

[0151] In some embodiments of this application, the target constant includes a first constant, which characterizes the inherent magnetic field strength in the power supply cable when the current value is passed through it, and at least two second electromagnetic field strengths include at least two second magnetic field strengths.

[0152] The target constant is determined based on at least two second electromagnetic field strengths and at least two corresponding fourth distances, including:

[0153] Determine at least two first expressions for at least two second magnetic field sub-intensities, magnetic permeability, a first position correction coefficient, at least two fourth distances, and the current value, as well as a first constant and a second expression for the magnetic permeability and the current value; wherein the first position correction coefficient is used to characterize the positional relationship between the electromagnetic field sensor that collects at least two second magnetic field sub-intensities and the power supply cable; and determine the first constant by least squares method based on the at least two first expressions and the second expression.

[0154] In this embodiment, the current value is the current value in the power supply cable. The permeability can be the permeability under vacuum, and the first position correction coefficient is associated with the deployment position of the electromagnetic field sensor that collects the strength of the second magnetic field element.

[0155] Specifically, based on the Biot-Sava law, at least two first expressions are constructed corresponding to at least two electromagnetic sensors, and a second expression for the first constant is established. The first expression characterizes the relationship between the actually acquired second magnetic field strength, current value, permeability, first position correction coefficient, and fourth distance value, where the first position correction coefficient and current value are unknown parameters, and the remaining parameters are known parameters. The second expression characterizes the relationship between the first constant and the permeability and current value, where the current value and the first constant are unknown parameters. Then, based on the first and second expressions, the specific value of the first constant can be estimated using the least squares method.

[0156] For example, the first expression is given in expressions (2), (3), and (4). The second expression is given in expression (5). Combining the above expressions (2), (3), (4) and expression (5), the first constant is estimated by the least squares method. The estimation expression for the first constant is given in expression (6).

[0157] In this embodiment, at least two first expressions are constructed using multiple second magnetic field sub-intensities, permeability, first position correction coefficients, at least two fourth distances, and current values ​​collected by multiple electromagnetic field sensors. A second expression is also constructed using a first constant, permeability, and current value. The first constant can be obtained by solving the least squares method, enabling it to characterize the inherent magnetic field strength in the power supply cable under the current operating conditions of the server when the current current value is passed through. This facilitates subsequent reconstruction of the magnetic field strength in the first electromagnetic field intensity within the first region based on the inherent magnetic field strength and the third distance value, and improves the accuracy of the obtained magnetic field strength in the first electromagnetic field intensity.

[0158] In some embodiments of this application, the target constant includes a second constant, which is used to characterize the inherent electric field strength of the power supply cable at the current charge density, and at least two second electromagnetic field strengths include at least two second electric field strengths;

[0159] The target constant is determined based on at least two second electromagnetic field strengths and at least two corresponding fourth distances, including:

[0160] Determine at least two third expressions for at least two second electric field sub-intensities, dielectric constant, second position correction coefficient, at least two fourth distances, and current charge density, as well as a fourth expression for the second constant and dielectric constant and current charge density; wherein, the second position correction coefficient is used to characterize the positional relationship between the electromagnetic field sensor that collects at least two second electric field sub-intensities and the power supply cable; and determine the second constant by least squares method based on at least two third expressions and fourth expressions.

[0161] In this embodiment, the current charge density is the charge density value in the power supply cable. The dielectric constant can be the dielectric constant under vacuum, and the second position correction coefficient is associated with the deployment position of the electromagnetic field sensor that collects the intensity of the second electric field.

[0162] Specifically, based on Gauss's law, at least two third expressions are constructed corresponding to at least two electromagnetic sensors, and a fourth expression for the second constant is established. This third expression characterizes the relationship between the actually acquired second electric field strength, current charge density, dielectric constant, second position correction coefficient, and fourth distance value, where the second position correction coefficient and current charge density are unknown parameters, and the remaining parameters are known parameters. This second expression characterizes the relationship between the second constant and the current charge density and dielectric constant, where the current charge density and the second constant are unknown parameters. At this point, based on the third and fourth expressions, the specific value of the second constant can be estimated using the least squares method.

[0163] For example, the third expression is shown in expressions (8), (9), and (10). The second expression is shown in expression (11). Combining the above expressions (8), (9), (10) and expression (11), the second constant is estimated by the least squares method. The estimation expression for the second constant is shown in expression (12).

[0164] In this embodiment, at least two corresponding third expressions are constructed using multiple second electric field sub-intensities, dielectric constants, second position correction coefficients, at least two fourth distances, and the current charge density collected by multiple electromagnetic field sensors. A fourth expression is also constructed using the second constant, dielectric constant, and current charge density. The second constant can be obtained by solving the least squares method, enabling it to characterize the inherent electric field intensity in the power supply cable under the current charge density of the server's operating conditions. This facilitates subsequent reconstruction of the electric field intensity in the first electromagnetic field intensity within the first region based on the inherent electric field intensity and the third distance values, and improves the accuracy of the obtained electric field intensity in the first electromagnetic field intensity.

[0165] In some embodiments of this application, the sensor assembly includes at least two electromagnetic field sensors, which are respectively used to collect at least two second electromagnetic field sub-intensities in the second electromagnetic field intensity;

[0166] The first electromagnetic field strength of the first region is determined based on the second electromagnetic field strength and the first distance, including:

[0167] If the difference between the first distance and the third distance is less than the difference threshold, at least two second electromagnetic field strengths are obtained; wherein the third distance is the distance between the processor component and the power supply cable; the average value of the at least two second electromagnetic field strengths is determined as the first electromagnetic field strength.

[0168] In this embodiment, when the difference between the first distance and the third distance is determined to be less than the difference threshold, the first distance between the sensor component and the power supply cable is determined to be approximately equal to the third distance between the processor component and the power supply cable.

[0169] The sensor assembly and processor assembly are located close to the power supply cable, and the power supply cable is the main source of electromagnetic interference for the processor assembly. Therefore, the electromagnetic environments of the sensor assembly and processor assembly are highly similar. Thus, the average value of at least two second electromagnetic field intensities collected by the sensor assembly can be used as the first electromagnetic field intensity.

[0170] Specifically, in a scheme where the first and second regions are arranged side-by-side, if the difference between the first and third distances is less than a threshold value, and the electromagnetic field strength is known to be correlated with the distance to the power supply cable, and the distance between the sensor assembly and the power supply cable is approximately equal to the distance between the processor assembly and the power supply cable, the average of the strengths of at least two second electromagnetic field sub-intensities collected by at least two electromagnetic field sensors can be used as the first electromagnetic field strength.

[0171] For example, the first electromagnetic field strength includes the first magnetic field sub-strength and the first electric field sub-strength. The calculation expression for the first magnetic field sub-strength is given in expression (14), and the calculation expression for the first electric field sub-strength is given in expression (15).

[0172] In this embodiment of the application, when the difference between the first distance and the third distance is less than the difference threshold, the sensor assembly and the processor assembly can be in a similar electromagnetic environment. At this time, the average value of the strength of at least two second electromagnetic field sub-fields collected by at least two electromagnetic field sensors in the sensor assembly can be used as the first electromagnetic field strength, which simplifies the calculation process of the first electromagnetic field strength.

[0173] In some embodiments of this application, the first electromagnetic field strength includes a first magnetic field sub-strength and a first electric field sub-strength, and the strength threshold includes a magnetic field strength threshold and an electric field strength threshold; when the first electromagnetic field strength is greater than or equal to the strength threshold, controlling the switching element to switch from a conducting state to an off state includes:

[0174] When the strength of the first magnetic field sub-element is greater than or equal to the magnetic field strength threshold, and / or when the strength of the first electric field sub-element is greater than or equal to the electric field strength threshold, the control switch is switched from the on state to the off state.

[0175] In this embodiment, the first electromagnetic field strength is a comprehensive physical quantity, comprising a first magnetic field sub-strength and a first electric field sub-strength. The first magnetic field sub-strength characterizes the magnetic field strength component of the first region where the processor component is located, and the first electric field sub-strength characterizes the electric field strength component of the first region. The intensity threshold is also specified as two independent sub-thresholds: a magnetic field strength threshold and an electric field strength threshold.

[0176] Specifically, during the threshold judgment logic, the first magnetic field sub-intensity and the first electric field sub-intensity are evaluated independently. The judgment logic is as follows: when the first magnetic field sub-intensity is greater than or equal to the magnetic field strength threshold, and / or when the first electric field sub-intensity is greater than or equal to the electric field strength threshold, the processing unit determines that the triggering condition is met. In summary, as long as either the magnetic field or electric field sub-intensity exceeds its respective safety threshold, or both exceed the threshold, subsequent protection actions will be triggered.

[0177] In this embodiment of the application, corresponding magnetic field strength thresholds and electric field strength thresholds are set by the first magnetic field sub-strength and the first electric field sub-strength in the first electromagnetic field strength, respectively, so that the system can more accurately capture various potential electromagnetic interference risks, thereby enhancing the protection of the core area of ​​the server and ensuring the reliability of security protection decisions in complex electromagnetic environments.

[0178] In some embodiments of this application, an electromagnetic interference protection method is proposed. Figure 7 Flowcharts of electromagnetic interference protection methods according to some embodiments of this application are shown, such as... Figure 7 As shown, electromagnetic interference protection methods also include:

[0179] Step 701: Determine the incoming power level and voltage level of the server.

[0180] Step 702: Determine whether the power is greater than 1MW or the voltage is greater than 1000V. If the result is yes, proceed to step 703; if the result is no, proceed to step 707.

[0181] Step 703: Adopt a layout where the first distance is greater than the second distance.

[0182] In this embodiment, in the layout of step 703, the sensor component is closer to the processor component.

[0183] Step 704: The sensor assembly and the processor assembly are arranged along the extension direction of the power supply cable.

[0184] In this embodiment, in the layout of step 704, the first distance between the sensor assembly and the power supply cable is approximately equal to the third distance between the processor assembly and the power supply cable;

[0185] Step 705: The average value of at least two second electromagnetic field sub-intensities collected by the sensor assembly is determined as the first electromagnetic field intensity of the first region.

[0186] Step 706: The sensor assembly is arranged around the periphery of the first region where the processor assembly is located.

[0187] Step 707: Adopt a layout where the first distance is less than the second distance.

[0188] In this embodiment, in the layout of step 707, the sensor assembly is close to the power supply cable, and at least two electromagnetic field sensors in the sensor assembly can be distributed on both sides or one side of the power supply cable.

[0189] Step 708: Calculate the first electromagnetic field strength of the first region using the inverse model.

[0190] In this embodiment, when calculating the first electromagnetic field strength in step 708, it is necessary to first estimate the target constants for characterizing the inherent magnetic field strength of the power supply cable when the current current value passes through it, and the inherent electric field strength of the power supply cable at the current charge density, based on the second electromagnetic field strength collected by at least two electromagnetic field sensors and at least two fourth distances between the at least two electromagnetic field sensors and the power supply cable, respectively; then, the first electromagnetic field strength is determined based on the target constants and the third distance; wherein, the third distance is the distance between the processor component and the power supply cable.

[0191] This application effectively solves the challenge of electromagnetic field monitoring in high-power, high-voltage DC servers, achieving non-intrusive and reliable sensing of the core area and avoiding layout conflicts and signal integrity issues. By employing an indirect peripheral measurement method, it eliminates the need to directly install sensors and cables in core areas such as processor components, memory regions, and high-speed signal cabling areas, thereby avoiding layout conflicts, heat dissipation airflow interference, and risks of signal and power integrity degradation caused by physical space occupation. It overcomes the limitations of traditional point-based measurements, transforming sparsely distributed peripheral sensor measurement data into electromagnetic field distribution results for the core area, providing more comprehensive data for system optimization and fault analysis. This application also provides a flexible and scalable monitoring strategy that can adapt to different server power and design evolution requirements. The proposed layout modes—surrounding the core area and close to the interference source—can be flexibly selected or combined according to specific power levels, voltage levels, and diagnostic objectives, making the solution not only applicable to current high-voltage DC systems but also adaptable to future technological developments with higher voltages and currents, demonstrating good scalability and applicability.

[0192] Embodiments of this application also provide an apparatus. Figure 8 Structural block diagrams of electromagnetic interference protection devices according to some embodiments of this application are shown, such as... Figure 8 As shown, the electromagnetic interference protection device 800 includes: an acquisition module 801, a determination module 802, and a control module 803.

[0193] The acquisition module 801 is used to acquire the second electromagnetic field intensity of the second region collected by the sensor component.

[0194] The determining module 802 is used to determine the first electromagnetic field strength of the first region based on the second electromagnetic field strength and the first distance; wherein, the first distance is the distance between the sensor assembly and the power supply cable;

[0195] The control module 803 is used to control the switching element to switch from the on state to the off state when the first electromagnetic field strength is greater than or equal to the strength threshold.

[0196] In this embodiment, a sensor component is placed in a second region on the motherboard, excluding the first region. This placement ensures the sensor component is far from the processor component, preventing it from affecting the existing heat dissipation channels and mechanical structure within the first region where the processor component is located, and also avoids disrupting the existing electromagnetic environment. By detecting the second electromagnetic field strength in the second region using the sensor component located in the peripheral area, the first electromagnetic field strength in the first region is indirectly detected. This achieves non-invasive detection of the electromagnetic field strength in the core-sensitive first region of the motherboard, improving the accuracy of electromagnetic field strength detection within the first region. It avoids the problem in related technologies where forcibly placing sensors in the space-constrained core area alters the original electromagnetic environment, leading to distorted measurement data. Flexible control of the power supply cable's on / off state based on the first electromagnetic field strength in the first region provides precise security protection for the server, preventing data errors and hardware damage that may be caused by electromagnetic interference.

[0197] Figure 8 The file download device shown in the embodiment can be used to execute the technical solution of the above-described electromagnetic interference protection method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0198] Embodiments of this application also provide an electronic device. Figure 9 Structural block diagrams of electronic devices according to some embodiments of this application are shown, such as Figure 9 As shown, the electronic device 900 includes a memory 901 and a processor 902. The memory 901 stores a computer program, and the processor 902 is configured to run the computer program to perform the steps in any of the above method embodiments.

[0199] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above-described embodiments of the server fault detection method when running.

[0200] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0201] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above-described server fault detection method embodiments.

[0202] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above-described server fault detection method embodiments.

[0203] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0204] The foregoing has provided a detailed description of a fault detection method, apparatus, and electronic device for a storage server. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A server, characterized by The application relates to a power supply cable, a switch and a mainboard. The mainboard comprises a sensor assembly and a processor assembly, the processor assembly is arranged in a first region of the mainboard, the sensor assembly is arranged in a second region of the mainboard, the first region is not connected with the second region, and the sensor assembly is used for collecting a second electromagnetic field intensity threshold value of the second region. The power supply cable is connected with the mainboard and is used for supplying power to the mainboard. The switch is connected with the power supply cable, and the on-off state of the switch is used for controlling the power supply state of the mainboard. When the first electromagnetic field intensity of the first region is greater than or equal to an intensity threshold value, the on-off state of the switch is switched from a conduction state to a disconnection state, the first electromagnetic field intensity is a magnetic field intensity determined based on the second electromagnetic field intensity and a first distance, and the first distance is a distance between the sensor assembly and the power supply cable. The sensor assembly comprises at least two electromagnetic field sensors, the at least two electromagnetic field sensors are respectively used for collecting at least two second electromagnetic field sub-intensity values in the second electromagnetic field intensity, and the first distance comprises at least two fourth distances between the at least two electromagnetic field sensors and the power supply cable. The first electromagnetic field intensity of the first region is determined according to the second electromagnetic field intensity and the first distance, comprising: A target constant is determined according to the at least two second electromagnetic field sub-intensity values and the at least two fourth distances, wherein the target constant is used for representing an inherent magnetic field intensity of the power supply cable when a current value is passed and an inherent electric field intensity of the power supply cable when a current density is passed; The first electromagnetic field intensity is determined according to the target constant and a third distance, wherein the third distance is a distance between the processor assembly and the power supply cable, the target constant comprises a first constant, the first constant is used for representing the inherent magnetic field intensity of the power supply cable when the current value is passed, and the at least two second electromagnetic field sub-intensity values comprise at least two second magnetic field sub-intensity values; The target constant is determined according to the at least two second electromagnetic field sub-intensity values and the at least two fourth distances, comprising: At least two first expressions of the at least two second magnetic field sub-intensity values, a magnetic permeability, a first position correction coefficient, the at least two fourth distances and a current value, and a second expression of the first constant and the magnetic permeability and the current value are determined, wherein the first position correction coefficient is used for representing a position relationship between the electromagnetic field sensors collecting the at least two second magnetic field sub-intensity values and the power supply cable; The first constant is determined by a least square method according to the at least two first expressions and the second expression.

2. The server of claim 1, wherein, The first distance is greater than a second distance, wherein the second distance is a distance between the sensor assembly and the processor assembly.

3. The server of claim 2, wherein, The first region comprises a first sub-region and a second sub-region, the processor assembly is located in the first sub-region, and the server further comprises: a data transmission channel arranged in the second sub-region; at least part of the second region is located on the periphery of the first sub-region, and at least two electromagnetic field sensors in the sensor assembly are arranged on the periphery of the processor assembly; and at least part of the second region is located on the periphery of the second sub-region, and at least two electromagnetic field sensors in the sensor assembly are arranged on the periphery of the data transmission channel.

4. The server of claim 2, wherein, The second region is arranged side by side with the first region, and the difference between the first distance and the third distance is less than a difference threshold, and the third distance is the distance between the processor assembly and the power cable.

5. The server of claim 1, wherein, The first distance is less than the second distance, wherein the second distance is the distance between the sensor assembly and the processor assembly.

6. The server of claim 5, wherein, At least two electromagnetic field sensors in the sensor assembly are located on both sides of the power cable; or at least two electromagnetic field sensors in the sensor assembly are located on one side of the power cable.

7. The server of any one of claims 1 to 6, characterized in that, Further comprising: a signal conditioning unit, an input end of the signal conditioning unit being connected to an output end of at least two electromagnetic field sensors in the sensor assembly; a processing unit, an input end of the processing unit being connected to an output end of the signal conditioning unit, and an output end of the processing unit being connected to a control end of the switch.

8. The server of any one of claims 1 to 6, wherein, Further comprising: an electromagnetic shielding structure, arranged on the surface of the power cable.

9. An electromagnetic interference shielding method, characterized by, The electromagnetic interference protection method is applied to the server of any one of claims 1 to 8, and the method comprises: obtaining a second electromagnetic field intensity of a second region collected by a sensor assembly; determining a first electromagnetic field intensity of a first region according to the second electromagnetic field intensity and a first distance; wherein the first distance is the distance between the sensor assembly and the power cable; in a case where the first electromagnetic field intensity is greater than or equal to an intensity threshold, controlling the switch to switch from a conduction state to a disconnection state; the sensor assembly comprises at least two electromagnetic field sensors, the at least two electromagnetic field sensors are respectively used to collect at least two second electromagnetic field sub-intensities in the second electromagnetic field intensity, and the first distance comprises at least two fourth distances between the at least two electromagnetic field sensors and the power cable respectively; the determination of the first electromagnetic field intensity of the first region according to the second electromagnetic field intensity and the first distance comprises: determining a target constant according to the at least two second electromagnetic field sub-intensities and the at least two fourth distances respectively; wherein the target constant is used to represent the inherent magnetic field intensity of the power cable when a current value is passed through, and the inherent electric field intensity of the power cable when a current density is passed through; determining the first electromagnetic field intensity according to the target constant and a third distance; wherein the third distance is the distance between the processor assembly and the power cable; the target constant comprises a first constant, and the first constant is used to represent the inherent magnetic field intensity of the power cable when the current value is passed through, and the at least two second electromagnetic field sub-intensities comprise at least two second magnetic field sub-intensities. The target constant is determined according to the at least two second electromagnetic field sub-strengths and the corresponding at least two fourth distances, and the target constant comprises a first constant, and the first constant is used to represent an inherent magnetic field strength of the power supply cable at a current current value. At least two first expressions of the at least two second magnetic field sub-strengths, a magnetic permeability, a first position correction coefficient, the at least two fourth distances and a current current value, and a second expression of the first constant and the magnetic permeability and the current current value are determined, and the first position correction coefficient is used to represent a positional relationship between an electromagnetic field sensor collecting the at least two second magnetic field sub-strengths and the power supply cable. The first constant is determined by a least square method according to the at least two first expressions and the second expression.

10. The electromagnetic interference shielding method of claim 9, wherein, The target constant comprises a second constant, the second constant is used to represent an inherent electric field strength of the power supply cable at a current charge density, and the at least two second electromagnetic field sub-strengths comprise at least two second electric field sub-strengths. The target constant is determined according to the at least two second electromagnetic field sub-strengths and the corresponding at least two fourth distances, and the target constant comprises a first constant, and the first constant is used to represent an inherent magnetic field strength of the power supply cable at a current current value. At least two third expressions of the at least two second electric field sub-strengths, a dielectric constant, a second position correction coefficient, the at least two fourth distances and a current charge density, and a fourth expression of the second constant and the dielectric constant and the current charge density are determined, and the second position correction coefficient is used to represent a positional relationship between an electromagnetic field sensor collecting the at least two second electric field sub-strengths and the power supply cable. The second constant is determined by a least square method according to the at least two third expressions and the fourth expression.

11. The electromagnetic interference shielding method of claim 9, wherein, The sensor assembly comprises at least two electromagnetic field sensors, and the at least two electromagnetic field sensors are respectively used to collect at least two second electromagnetic field sub-strengths in the second electromagnetic field strength. The first electromagnetic field strength of the first region is determined according to the second electromagnetic field strength and a first distance, and the first electromagnetic field strength comprises a first magnetic field sub-strength and a first electric field sub-strength. The at least two second electromagnetic field sub-strengths are obtained in a case that a difference between the first distance and a third distance is less than a difference threshold, and the third distance is a distance between the processor assembly and the power supply cable. An average value of the at least two second electromagnetic field sub-strengths is determined as the first electromagnetic field strength.

12. The electromagnetic interference shielding method according to any one of claims 9 to 11, characterized in that, The first electromagnetic field strength comprises a first magnetic field sub-strength and a first electric field sub-strength, and the strength threshold comprises a magnetic field strength threshold and an electric field strength threshold. The switch piece is controlled to be switched from the conducting state to the disconnected state in a case that the first electromagnetic field strength is greater than or equal to a strength threshold, and the strength threshold comprises a magnetic field strength threshold and an electric field strength threshold. The switch piece is controlled to be switched from the conducting state to the disconnected state in a case that the first magnetic field sub-strength is greater than or equal to the magnetic field strength threshold and / or the first electric field sub-strength is greater than or equal to the electric field strength threshold.

13. A computer-readable storage medium, characterized in that, The computer program stored in the computer readable storage medium is executed by the processor to implement the steps of the electromagnetic interference protection method according to any one of claims 9 to 12.

Images