Computing device and temperature detection system

Abstract

The embodiment of the invention provides a computing device and a temperature detection system, the computing device comprises a PCB, at least one temperature detection module, a processor and a programmable logic device, a neural network model runs in the processor, and the at least one temperature detection module is correspondingly arranged in at least one detection area of the PCB; for any temperature detection module, the temperature detection module is used for performing temperature detection processing on the detection area corresponding to the temperature detection module to obtain a first detection signal corresponding to the detection area, and sending the first detection signal to the processor; the processor is used for determining the detection temperature of the PCB through a neural network model according to the first detection signal sent by the at least one temperature detection module, and sending the detection temperature of the PCB to the programmable logic device; and the programmable logic device is used for adjusting the working state of the PCB based on the detection temperature of the PCB. The computing device can realize temperature detection and temperature control of the PCB under the condition of saving the usable area of the PCB.

Description

Technical Field

[0001] This application relates to the field of computing device technology, and more particularly to a computing device and a temperature detection system. Background Technology

[0002] Computing devices (such as servers) may include printed circuit boards (PCBs) on which chips are integrated. These chips have overcurrent, overtemperature, and short-circuit protection to ensure they are not damaged or burned out under abnormal conditions. However, PCBs typically do not have overcurrent, overtemperature, and short-circuit protection. When a short circuit occurs at a node on the PCB, the current flowing through the PCB will cause the PCB temperature to rise rapidly, potentially leading to PCB burnout.

[0003] In related technologies, temperature sensing chips can be installed on various circuits in a PCB to monitor the PCB temperature.

[0004] However, due to the limited area of ​​PCBs, it is impossible to place temperature sensing chips on every circuit, which makes it difficult for computing devices to detect and control the temperature of the PCB. Summary of the Invention

[0005] This application provides a computing device and a temperature detection system that can achieve temperature detection and control of PCBs while saving PCB area.

[0006] In a first aspect, embodiments of this application provide a computing device, including: a printed circuit board (PCB), at least one temperature detection module, a processor, and a programmable logic device (PLD), wherein the processor runs a neural network model, wherein...

[0007] At least one temperature detection module is correspondingly set in at least one detection area of ​​the PCB, and the detection area is the copper area and / or busbar area of ​​the PCB;

[0008] For any given temperature detection module, the temperature detection module is used to perform temperature detection processing on the detection area corresponding to the temperature detection module, obtain the first detection signal corresponding to the detection area, and send the first detection signal to the processor;

[0009] The processor is used to determine the detection temperature of the PCB through a neural network model based on a first detection signal sent by at least one temperature detection module, and to send the detection temperature of the PCB to a programmable logic device.

[0010] Programmable logic controllers are used to regulate the operating status of a PCB based on temperature detection.

[0011] In the above technical solution, by setting at least one temperature detection module in at least one detection area of ​​the PCB, and selecting copper areas and / or busbar areas with high current and high temperature on the PCB, the maximum temperature on the PCB is determined by the temperature detected in at least one detection area. This eliminates the need to individually deploy temperature sensing chips for each circuit on the PCB, saving PCB space in the computing device and enabling miniaturized PCB design. The processor can quickly process the first detection signal sent by at least one temperature detection module through a neural network model to obtain the detected temperature of the PCB, saving data processing time, improving data processing efficiency, and thus improving the efficiency of PCB temperature detection. In this computing device, the processor can also send the detected temperature of the PCB to the programmable logic controller (PLC), so that the PLC can adjust the PCB's operating state in a timely manner based on the detected temperature. For example, if the detected temperature of the PCB is too high, the PLC can power down the PCB or reduce power consumption parameters to avoid PCB burnout due to overheating, thus reducing the probability of PCB burnout and improving the reliability of the computing device. In summary, the computing device provided by this application embodiment can achieve PCB temperature detection and control while saving PCB area.

[0012] In some embodiments, for any given temperature detection module, the temperature detection module includes an infrared emitter and a detection circuit, wherein...

[0013] The infrared emitter is used to send first infrared light to the corresponding detection area of ​​the temperature detection module;

[0014] The detection circuit is used to receive the second infrared light sent by the detection area corresponding to the temperature detection module, and determine the first detection signal corresponding to the detection area corresponding to the temperature detection module based on the second infrared light, and send the first detection signal to the processor. The second infrared light is obtained after the first infrared light interacts with the detection area corresponding to the temperature detection module.

[0015] In the above technical solution, an infrared emitter can be used to perform infrared temperature measurement on the detection area corresponding to the temperature detection module. Compared with using a temperature sensing chip to measure the temperature of the PCB, infrared temperature measurement has higher accuracy and is less susceptible to interference from external environmental factors, giving the temperature detection module better reliability when measuring the temperature of the PCB. By setting up a detection circuit, the second detection signal can be converted into a first detection signal that the processor can recognize, so that the processor can perform data processing subsequently.

[0016] In some embodiments, the detection circuit includes an infrared sensor and a signal converter, the signal converter being connected to the sensor and the processor, respectively.

[0017] The infrared sensor is used to receive second infrared light and to send a second detection signal to a signal converter based on the second infrared light;

[0018] The signal converter is used to perform analog-to-digital conversion on the second detection signal to obtain the first detection signal, and then send the first detection signal to the processor.

[0019] In the above technical solution, the second infrared light can be gradually converted into a first detection signal that the processor can recognize by setting up an infrared sensor and a signal converter, so that the processor can perform data processing in the future, which is beneficial to improving data processing efficiency.

[0020] In some embodiments, determining the detection temperature of the PCB using a neural network model based on a first detection signal sent by at least one temperature detection module includes:

[0021] Input a first detection signal sent by at least one temperature detection module into the neural network model, and obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module output by the neural network model;

[0022] The detection temperature of the PCB is determined based on the detection temperature of at least one detection area.

[0023] In the above technical solution, a neural network model runs in the processor, which enables the processor to quickly and accurately obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module based on the first detection signal sent by at least one temperature detection module. This is beneficial to improving the precision and efficiency of PCB temperature detection, and makes the temperature detection module more accurate in determining the temperature of the PCB.

[0024] In some embodiments, the number of at least one detection area is multiple; determining the detection temperature of the PCB based on the detection temperature of at least one detection area includes:

[0025] The maximum detection temperature among the detection temperatures of multiple detection zones is determined as the PCB detection temperature; or...

[0026] Based on the detection temperatures of multiple detection areas, determine the average detection temperature of these areas, and then use this average temperature as the detection temperature for the PCB; or,

[0027] The detection temperature of the PCB is determined by identifying at least one detection temperature that is greater than the temperature threshold among multiple detection areas.

[0028] In the above technical solution, any one of the three methods can be flexibly used to determine the PCB detection temperature according to the temperature detection scenario and temperature detection requirements, making the process of determining the PCB detection temperature more flexible.

[0029] In some embodiments, sending the detected temperature of the PCB to the programmable logic controller includes:

[0030] When the detected temperature of the PCB is greater than or equal to the temperature threshold, an indication message is sent to the programmable logic device.

[0031] The indication information includes the detected temperature of the PCB, which is used to instruct the programmable logic device to cool the PCB.

[0032] In the above technical solution, the processor can send an instruction to the programmable logic device in a timely manner when the temperature of the PCB is greater than or equal to the temperature threshold, so that the programmable logic device can cool down the PCB. This can avoid the phenomenon of PCB burning due to excessive PCB temperature, reduce the probability of PCB burning, and improve the reliability of computing device operation.

[0033] In some embodiments, adjusting the operating state of the PCB based on the detected temperature of the PCB includes:

[0034] The PCB is powered down based on the indication information, or the power consumption parameters of the PCB, including current and / or voltage, are reduced based on the indication information.

[0035] In the above technical solution, the programmable logic device can flexibly adjust the working state of the PCB according to the detected temperature of the PCB to achieve the cooling treatment of the PCB, which is conducive to improving the flexibility of temperature control of the PCB.

[0036] In some embodiments, the indication information also includes an identifier of a target detection area, which is a detection area in at least one detection area where the detection temperature is greater than or equal to a temperature threshold.

[0037] Controlling PCB power-down based on indication information includes: controlling the power-down of devices on the PCB located within the target detection area based on the identifier of the target detection area in the indication information; or,

[0038] The power consumption parameters of the PCB are reduced based on the indication information, including: reducing the power consumption parameters of devices located within the target detection area on the PCB based on the identification of the target detection area in the indication information.

[0039] In the above technical solution, the programmable logic device can perform temperature reduction processing on different areas of the PCB according to the instruction information sent by the processor, making the temperature control of the PCB more flexible.

[0040] In some embodiments, at least one detection region includes at least one of the following regions:

[0041] The bus copper area of ​​the central processing unit (CPU);

[0042] The bus copper area of ​​the digital processing unit (DPU) at the operating voltage input of the PCB;

[0043] The copper area at the PCB's operating voltage input;

[0044] The busbar area at the operating voltage input of the PCB.

[0045] In the above technical solution, the copper area and / or busbar area with large current and high temperature in the PCB can be selected as at least one detection area corresponding to at least one temperature detection module, so as to reflect the detection temperature of the PCB as accurately as possible through the detection temperature of the at least one detection area.

[0046] Secondly, embodiments of this application provide a temperature detection system applied in a computing device. The computing device includes a printed circuit board (PCB) and a programmable logic device. The temperature detection system includes at least one temperature detection module and a processor.

[0047] At least one temperature detection module is correspondingly set in at least one detection area of ​​the PCB, and the detection area is the copper area and / or busbar area of ​​the PCB;

[0048] For any given temperature detection module, the temperature detection module is used to detect the temperature of the detection area corresponding to the temperature detection module, obtain the first detection signal corresponding to the detection area, and send the first detection signal to the processor;

[0049] The processor is used to determine the detected temperature of the PCB using a neural network model based on a first detection signal sent by at least one temperature detection module, and to send the detected temperature of the PCB to a programmable logic device.

[0050] In some embodiments, for any given temperature detection module, the temperature detection module includes an infrared emitter and a detection circuit, wherein...

[0051] The infrared emitter is used to send first infrared light to the corresponding detection area of ​​the temperature detection module;

[0052] The detection circuit is used to receive the second infrared light sent by the detection area corresponding to the temperature detection module, and determine the first detection signal corresponding to the detection area corresponding to the temperature detection module based on the second infrared light, and send the first detection signal to the processor. The second infrared light is obtained after the first infrared light interacts with the detection area corresponding to the temperature detection module.

[0053] In some embodiments, the detection circuit includes an infrared sensor and a signal converter, the signal converter being connected to the sensor and the processor, respectively.

[0054] The infrared sensor is used to receive second infrared light and to send a second detection signal to a signal converter based on the second infrared light;

[0055] The signal converter is used to perform analog-to-digital conversion on the second detection signal to obtain the first detection signal, and then send the first detection signal to the processor.

[0056] In some embodiments, determining the detection temperature of the PCB using a neural network model based on a first detection signal sent by at least one temperature detection module includes:

[0057] Input a first detection signal sent by at least one temperature detection module into the neural network model, and obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module output by the neural network model;

[0058] The detection temperature of the PCB is determined based on the detection temperature of at least one detection area.

[0059] In some embodiments, the number of at least one detection area is multiple; determining the detection temperature of the PCB based on the detection temperature of at least one detection area includes:

[0060] The maximum detection temperature among the detection temperatures of multiple detection zones is determined as the PCB detection temperature; or...

[0061] Based on the detection temperatures of multiple detection areas, determine the average detection temperature of these areas, and then use this average temperature as the detection temperature for the PCB; or,

[0062] The detection temperature of the PCB is determined by identifying at least one detection temperature that is greater than the temperature threshold among multiple detection areas.

[0063] In some embodiments, sending the detected temperature of the PCB to the programmable logic controller includes:

[0064] When the detected temperature of the PCB is greater than or equal to the temperature threshold, an indication message is sent to the programmable logic device.

[0065] The indication information includes the detected temperature of the PCB, which is used to instruct the programmable logic device to cool the PCB.

[0066] Thirdly, embodiments of this application provide a temperature detection method applied to a processor in a computing device, the method comprising:

[0067] Receive a first detection signal sent by at least one temperature detection module;

[0068] The detection temperature of the PCB is determined by a neural network model based on a first detection signal sent by at least one temperature detection module.

[0069] Send the detected temperature of the PCB to the programmable logic controller.

[0070] In some embodiments, determining the detection temperature of the PCB using a neural network model based on a first detection signal sent by at least one temperature detection module includes:

[0071] Input a first detection signal sent by at least one temperature detection module into the neural network model, and obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module output by the neural network model;

[0072] The detection temperature of the PCB is determined based on the detection temperature of at least one detection area.

[0073] In some embodiments, determining the detection temperature of the PCB based on the detection temperature of at least one detection area includes:

[0074] The maximum detection temperature among the detection temperatures of multiple detection zones is determined as the PCB detection temperature; or...

[0075] Based on the detection temperatures of multiple detection areas, determine the average detection temperature of these areas, and then use this average temperature as the detection temperature for the PCB; or,

[0076] The detection temperature of the PCB is determined by identifying at least one detection temperature that is greater than the temperature threshold among multiple detection areas.

[0077] In some embodiments, sending the detected temperature of the PCB to the programmable logic controller includes:

[0078] When the detected temperature of the PCB is greater than or equal to the temperature threshold, an indication message is sent to the programmable logic device.

[0079] The indication information includes the detected temperature of the PCB, which is used to instruct the programmable logic device to cool the PCB.

[0080] The temperature detection method provided in this application embodiment can execute the technical solution executed by the processor in the first or second aspect, and its beneficial effects are similar, so it will not be described again here.

[0081] Fourthly, embodiments of this application provide a temperature control method applied to a programmable logic device in a computing device, the method comprising:

[0082] Receive the detected temperature of the PCB sent by the processor;

[0083] PCB-based temperature detection for regulating PCB operating status.

[0084] In some embodiments, receiving the detected temperature of the PCB sent by the processor includes:

[0085] The system receives instruction information sent by the processor; the instruction information includes the detected temperature of the PCB, and is used to instruct the programmable logic device to perform cooling treatment on the PCB.

[0086] In some embodiments, adjusting the operating state of the PCB based on the detected temperature of the PCB includes:

[0087] The PCB is powered down based on the indication information, or the power consumption parameters of the PCB, including current and / or voltage, are reduced based on the indication information.

[0088] In some embodiments, the indication information also includes an identifier of a target detection area, which is a detection area in at least one detection area where the detection temperature is greater than or equal to a temperature threshold.

[0089] Controlling PCB power-down based on indication information includes: controlling the power-down of devices on the PCB located within the target detection area based on the identifier of the target detection area in the indication information; or,

[0090] The power consumption parameters of the PCB are reduced based on the indication information, including: reducing the power consumption parameters of devices located within the target detection area on the PCB based on the identification of the target detection area in the indication information.

[0091] The temperature control method provided in this application embodiment can execute the technical solution executed by the programmable logic device in the first aspect, and its beneficial effects are similar, so it will not be described again here.

[0092] Fifthly, embodiments of this application provide a temperature detection device applied in a processor of a computing device, the method comprising:

[0093] A transceiver module is used to receive a first detection signal sent by at least one temperature detection module;

[0094] The processing module is used to determine the detection temperature of the PCB through a neural network model based on the first detection signal sent by at least one temperature detection module.

[0095] The transceiver module is also used to send the detected temperature of the PCB to the programmable logic device.

[0096] The temperature detection device provided in this application embodiment can perform the technical solution shown in any of the third aspects, and its beneficial effects are similar, so it will not be described again here.

[0097] Sixthly, embodiments of this application provide a temperature control device applied in a programmable logic controller in a computing device, the method comprising:

[0098] The transceiver module is used to receive the detected temperature of the PCB sent by the processor.

[0099] The processing module is used to adjust the working state of the PCB based on the detected temperature of the PCB.

[0100] The temperature control device provided in this application embodiment can perform the technical solution shown in any of the fourth aspects, and its beneficial effects are similar, so it will not be described again here.

[0101] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions that, when executed by a computer, implement the method as shown in any of the third or fourth aspects.

[0102] The computer-readable storage medium provided in the embodiments of this application can perform the technical solutions shown in any of the third or fourth aspects, and the beneficial effects are similar, so they will not be described again here.

[0103] Eighthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method as shown in any of the third or fourth aspects.

[0104] The computer program product provided in the embodiments of this application can execute the technical solutions shown in any of the third or fourth aspects, and the beneficial effects are similar, so they will not be described again here.

[0105] The computing device and temperature detection system provided in this application embodiment include: a PCB, at least one temperature detection module, a processor, and a programmable logic device (PLD). The processor runs a neural network model, and the at least one temperature detection module is correspondingly disposed in at least one detection area on the PCB, the detection area being a copper area and / or a busbar area on the PCB. The computing device can detect the temperature of at least one detection area on the PCB through the at least one temperature detection module, obtaining a first detection signal corresponding to the at least one detection area; and the processor, based on the first detection signal corresponding to the at least one detection area, determines the detection temperature of the PCB through the neural network model, and sends the PCB detection temperature to the PLD; the PLD can also adjust the operating state of the PCB based on the PCB detection temperature. This computing device can achieve temperature detection and temperature control of the PCB while saving PCB space. Attached Figure Description

[0106] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0107] Figure 1 This is one of the structural schematic diagrams of a computing device provided in the embodiments of this application;

[0108] Figure 2 This is a schematic diagram of a detection area on a PCB provided in an embodiment of this application;

[0109] Figure 3 This is one of the structural schematic diagrams of the temperature detection module provided in the embodiments of this application;

[0110] Figure 4 This is the second schematic diagram of the structure of the temperature detection module provided in the embodiments of this application;

[0111] Figure 5 This is the third schematic diagram of the structure of the temperature detection module provided in the embodiments of this application;

[0112] Figure 6 A schematic flowchart of a temperature detection method provided in an embodiment of this application;

[0113] Figure 7 A schematic diagram of a BP neural network provided in an embodiment of this application;

[0114] Figure 8 A schematic diagram of a neuron provided for an embodiment of this application;

[0115] Figure 9 A schematic flowchart of a temperature control method provided in an embodiment of this application;

[0116] Figure 10 This is a schematic diagram of the structure of a temperature detection system provided in an embodiment of this application;

[0117] Figure 11 This is a schematic diagram of the structure of a temperature detection device provided in an embodiment of this application;

[0118] Figure 12 This is a schematic diagram of a temperature control device provided in an embodiment of this application. Detailed Implementation

[0119] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0120] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0121] It should be noted that the data involved in one or more embodiments of this specification (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0122] It should be noted that in the embodiments of this application, the term "at least one" refers to one or more, and "more than one" refers to two or more.

[0123] This application provides a computing device including a PCB, at least one temperature detection module, a processor, and a programmable logic device (PLD). The processor runs a neural network model. In this computing device, at least one temperature detection module is correspondingly positioned in at least one detection area on the PCB. This detection area is selected from copper areas and / or busbar areas on the PCB with high current and high temperature. The maximum temperature on the PCB is determined by the detected temperature of the at least one detection area, thus eliminating the need to individually place a temperature sensing chip for each circuit on the PCB. Furthermore, as an example, the temperature detection module can be a surface-mount design, which can be attached to the copper areas or busbars of the PCB, thus not occupying PCB board area, saving PCB space and enabling miniaturized PCB design. In this computing device, each temperature detection module can perform temperature detection processing on its corresponding detection area to obtain a first detection signal corresponding to the detection area of ​​each temperature detection module, and send the first detection signal to the processor. The processor can quickly process the first detection signal sent by the at least one temperature detection module through the neural network model to obtain the detected temperature of the PCB, which helps to save data processing time, improve data processing efficiency, and thus improve the efficiency of PCB temperature detection. In this computing device, the processor can also send the detected temperature of the PCB to the programmable logic controller (PLC), enabling the PLC to adjust the PCB's operating state in a timely manner based on the detected temperature. For example, if the detected PCB temperature is too high, the PLC can power down the PCB or reduce its power consumption parameters to prevent the PCB from burning out due to overheating. This helps reduce the probability of PCB burnout and improves the reliability of the computing device. In summary, the computing device provided in this application embodiment can achieve PCB temperature detection and control while saving PCB area.

[0124] The technical solutions of this application will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0125] Figure 1 This is one of the structural schematic diagrams of a computing device provided in an embodiment of this application. Please refer to... Figure 1 The computing device 10 may include a PCB 100, at least one temperature detection module 101, a processor 102, and a programmable logic device 103.

[0126] like Figure 1 As shown, the processor 102 can be connected to each temperature detection module 101 and programmable logic device 103 respectively, and the processor 102 and programmable logic device 103 can be located on the PCB.

[0127] The following is a detailed introduction to each component within the computing device.

[0128] (1) PCB 100

[0129] The computing device in this application embodiment can be a server, and the PCB can be the motherboard in the server. From an architectural perspective, the server can be a rack server, a high-density server, a tower server, or a full-rack server; from a functional perspective, the server can be a general-purpose server or an artificial intelligence (AI) server, etc.

[0130] (2) At least one temperature detection module 101

[0131] At least one temperature detection module 101 may be correspondingly disposed in at least one detection area of ​​the PCB, wherein the detection area is the copper area and / or busbar area of ​​the PCB.

[0132] In some embodiments, at least one detection area may include at least one of the following areas: the bus copper area of ​​the central processing unit (CPU); the bus copper area of ​​the digital processing unit (DPU) at the working voltage input of the PCB; the input copper area at the working voltage input of the PCB; and the bus area at the working voltage input of the PCB.

[0133] For example, the operating voltage of the PCB can be 12V, and the operating voltage input can be represented as "12V-IN".

[0134] Figure 2 This is a schematic diagram of a detection area on a PCB provided in an embodiment of this application. Please refer to... Figure 2 The PCB can be set with four detection areas: the CPU bus copper area; the 12V-IN-DPU bus copper area; the 12V-IN entrance copper area; and the 12V-IN bus area.

[0135] Optionally, such as Figure 2 As shown, the area occupied by the detection area on the PCB can vary, and correspondingly, the size of the temperature detection module corresponding to different detection areas can also vary. The larger the area occupied by the detection area, the larger the size of the temperature detection module corresponding to the detection area can be.

[0136] For any given temperature detection module, the temperature detection module can be used to perform temperature detection processing on the detection area corresponding to the temperature detection module, obtain the first detection signal corresponding to the detection area, and send the first detection signal to the processor.

[0137] In some embodiments, during the design of the computing device, historical temperature detection data of the PCB can also be acquired. This historical temperature detection data may include historical detection temperatures and / or historical power consumption data of multiple regions on the PCB. For any one of the multiple regions, temperature detection parameters for that region can be determined based on the multiple historical detection temperatures; or, power consumption detection parameters for that region can be determined based on the multiple historical power consumption data. Furthermore, at least one detection region can be determined among the multiple regions based on the temperature detection parameters and / or power consumption detection parameters of the multiple regions, and at least one temperature detection module can be correspondingly set in that at least one detection region.

[0138] For example, historical power consumption data may include, but is not limited to, at least one of the following: voltage, current, and clock frequency.

[0139] For example, the temperature detection parameters may include at least one of the following: temperature variation range, average detection temperature, and maximum detection temperature.

[0140] For any region among multiple regions, if the temperature variation range of the region is large, that is, the difference between the maximum detection temperature and the minimum detection temperature of the region is greater than the temperature difference threshold, the region can be identified as a detection region; or, if the average detection temperature of the region exceeds the temperature threshold, the region can be identified as a detection region; or, if the maximum detection temperature of the region exceeds the temperature threshold, the region can also be identified as a detection region.

[0141] Optionally, the temperature threshold can be a parameter pre-configured in the processor by the user, and the temperature threshold can be less than the critical temperature for PCB combustion.

[0142] For example, the critical temperature for PCB combustion is 85°C, and the temperature threshold can be 80°C.

[0143] For example, power consumption detection parameters may include at least one of the following: power consumption variation range, average power consumption, and maximum power consumption.

[0144] For any one of the multiple regions, if the power consumption variation range of the region is large, that is, the difference between the maximum power consumption and the minimum power consumption of the region is greater than the power consumption variation threshold, the region can be identified as a detection region; or, if the average power consumption of the region exceeds the power consumption threshold, the region can be identified as a detection region; or, if the maximum power consumption of the region exceeds the power consumption threshold, the region can also be identified as a detection region.

[0145] Optionally, the power consumption threshold can be determined by a temperature threshold. For example, the power consumption of the PCB can be detected when the PCB is at a temperature threshold, and the power consumption can be determined as the power consumption threshold.

[0146] In some embodiments, any temperature detection module may include an infrared emitter and a detection circuit.

[0147] Figure 3 For one of the structural schematic diagrams of the temperature detection module provided in the embodiments of this application, please refer to [link / reference]. Figure 3 The temperature detection module 101 may include an infrared emitter 1011 and a detection circuit 1012.

[0148] In some embodiments, the infrared emitter 1011 and the detection circuit 1012 may be disposed above the detection area corresponding to the temperature detection module.

[0149] The infrared emitter 1011 can be used to send a first infrared light to the corresponding detection area of ​​the temperature detection module.

[0150] The detection circuit 1012 can be used to receive the second infrared light sent by the detection area corresponding to the temperature detection module, determine the first detection signal corresponding to the detection area corresponding to the temperature detection module based on the second infrared light, and send the first detection signal to the processor.

[0151] The second infrared light can be obtained by the interaction between the first infrared light and the detection area corresponding to the temperature detection module. It can be understood that when the first infrared light shines on the detection area corresponding to the temperature detection module on the PCB, part of the infrared light in the first infrared light can be absorbed or scattered by the PCB, and another part of the infrared light in the first infrared light can be reflected by the PCB to form the second infrared light. The intensity of the second infrared light can be less than the intensity of the first infrared light.

[0152] The first detection signal can be a digital signal, which is a form of signal represented by discrete numerical values.

[0153] For example, the first detection signal can be represented by logic levels, such as high level (1) and low level (0).

[0154] For example, the first detection signal can also be represented by binary numbers, such as a digital signal sequence consisting of 0s and 1s.

[0155] Optionally, the detection circuit may include an infrared sensor and a signal converter.

[0156] Figure 4 For the second structural schematic diagram of the temperature detection module provided in the embodiments of this application, please refer to [link / reference]. Figure 4 ,exist Figure 3 Based on the structure of the temperature detection module 101 shown, the detection circuit 1012 may include an infrared sensor 1012-1 and a signal converter 1012-2.

[0157] The infrared sensor 1012-1 can be used to receive second infrared light and send a second detection signal to a signal converter based on the second infrared light.

[0158] The signal converter 1012-2 can be used to perform analog-to-digital conversion on the second detection signal to obtain the first detection signal, and send the first detection signal to the processor.

[0159] The second detection signal can be an analog signal, which differs from the representation of a digital signal. An analog signal is a continuously changing signal form.

[0160] For example, the second detection signal may be a current signal and / or a voltage signal.

[0161] In some embodiments, the infrared sensor 1012-1 can receive second infrared light and generate a corresponding second detection signal (e.g., a current signal and / or a voltage signal) based on the intensity of the second infrared light. The intensity of the second infrared light is positively correlated with the intensity of the second detection signal. For example, the greater the intensity of the second infrared light, the greater the intensity of the second detection signal.

[0162] The temperature detection module provided in this application embodiment can perform infrared temperature measurement on the detection area corresponding to the temperature detection module through an infrared emitter and an infrared sensor. Compared with using a temperature sensing chip to measure the temperature of the PCB, infrared temperature measurement has higher accuracy and is less susceptible to interference from external environmental factors, making the temperature detection module more reliable when measuring the temperature of the PCB. By setting a signal converter, the second detection signal can be converted into a first detection signal that the processor can recognize, so as to facilitate subsequent data processing by the processor.

[0163] For example, the infrared sensor can be a patch infrared sensor, and the infrared emitter can be a patch infrared emitter.

[0164] Optionally, the signal converter 1012-2 may further include an amplifier circuit and an analog-to-digital converter (ADC) circuit.

[0165] Figure 5 This is the third schematic diagram of the temperature detection module provided in the embodiments of this application. Please refer to... Figure 5 ,exist Figure 4Based on the structure of the temperature detection module 101 shown, the signal converter 1012-2 may include an amplifier circuit 1012-2-1 and an ADC circuit 1012-2-2. The amplifier circuit 1012-2-1 may be connected to the infrared sensor 1012-1 and the ADC circuit 1012-2-2 respectively, and the ADC circuit 1012-2-2 may also be connected to the processor 102.

[0166] The amplifier circuit 1012-2-1 can be used to amplify the second detection signal to obtain a third detection signal, the signal strength of the third detection signal being greater than that of the second detection signal.

[0167] The ADC circuit 1012-2-2 can be used to perform analog-to-digital conversion on the third detection signal to obtain the first detection signal.

[0168] It should be noted that the amplification circuit in the embodiments of this application can be any circuit that can be used to realize the intensity amplification of analog signals, and the ADC circuit can be any circuit that can be used to realize the conversion of analog signals to digital signals. The embodiments of this application do not limit the type and specific implementation of the amplification circuit and the type and specific implementation of the ADC circuit.

[0169] In this temperature detection module, by setting up an amplifier circuit and an ADC circuit, the first detection signal obtained by the signal converter can be made more stable.

[0170] (3) Processor 102

[0171] For example, the processor may include, but is not limited to, a micro control unit (MCU).

[0172] The processor 102 can be used to determine the detection temperature of the PCB 100 through a neural network model based on a first detection signal sent by at least one temperature detection module 101, and to send the detection temperature of the PCB 100 to the programmable logic device 103.

[0173] This application also provides a temperature detection method, which can be applied to a processor. The following describes the method in conjunction with... Figure 6 This paper explains the temperature detection method.

[0174] Figure 6 This is a schematic flowchart illustrating a temperature detection method provided in an embodiment of this application. Please refer to [link / reference]. Figure 6 This method can be executed by a processor in a computing device, and the method may include the following steps:

[0175] S601, Receive a first detection signal sent by at least one temperature detection module.

[0176] Specifically, a signal converter can be set in the temperature detection module, and the processor can receive the first detection signal sent by the signal converter in at least one temperature detection module.

[0177] S602. Input the first detection signal sent by at least one temperature detection module into the neural network model to obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module output by the neural network model.

[0178] Optionally, the processor can input the first detection signal into the neural network model in real time; or, the processor can input the first detection signal into the neural network model periodically according to a preset period (e.g., 1 millisecond).

[0179] In some embodiments, before executing step S602, the processor 102 may also be used to acquire training data; perform iterative training on the initial model based on the training data until the optimal solution is obtained, and determine the model corresponding to the optimal solution as a neural network model.

[0180] The training data may include multiple test first detection signals and the test temperature corresponding to each test first detection signal.

[0181] Optionally, the tester can conduct multiple experiments on the temperature detection module and generate training data based on the results of each experiment. For example, the temperature detection module can emit first infrared light to PCBs at different test temperatures via an infrared emitter, receive second infrared light emitted by PCBs at each test temperature via an infrared sensor, and convert the second infrared light into a corresponding first detection signal via a signal converter. For each experiment, the tester can obtain the following set of experimental results: test temperature, first infrared light, second infrared light, second detection signal (analog signal), third detection signal (analog signal), and first detection signal (digital signal). The tester can generate the training data based on the first detection signal and test temperature from the multiple experimental results.

[0182] Understandably, during the iterative training of the initial model, the model parameters can be optimized. In the iterative training of the initial model, the optimal solution refers to the solution where the model parameters achieve optimal performance under given conditions. In other words, when the model obtains the optimal solution, the optimal model parameters can be obtained. When processing the input data based on these optimal model parameters, the loss between the model's predicted result (e.g., the predicted temperature obtained based on the first detection signal) and the expected result (e.g., the tested temperature) can be minimized.

[0183] For example, the initial model can be a back propagation (BP) neural network. This BP neural network can simulate the human brain's processing of various problems and possesses some of the basic characteristics of the human brain. BP neural networks belong to nonlinear dynamic systems; they can autonomously learn the characteristics between various data, adapt to various environments, and obtain the optimal solution through continuous iteration.

[0184] Below, in conjunction with Figure 7 and Figure 8 The parameters in the BP neural network will be explained.

[0185] Figure 7 This is a schematic diagram of a BP neural network provided in an embodiment of this application. Please refer to [link / reference]. Figure 7 A backpropagation (BP) neural network can include an input layer, hidden layers, and an output layer. The input layer receives input data and passes it to subsequent hidden or output layers; the hidden layers are located between the input and output layers and assist the output layer in processing the data; the output layer outputs the final result.

[0186] The input layer, hidden layer, and output layer can each contain multiple neurons, each of which can receive input data and generate output data.

[0187] Each neuron in the input layer and each neuron in the hidden layer have a first connection weight, which can be used to indicate the connection strength from a neuron in the input layer to a neuron in the hidden layer.

[0188] Each neuron in the hidden layer has a second connection weight with each neuron in the output layer. This second connection weight can be used to indicate the connection strength from a neuron in the hidden layer to a neuron in the output layer.

[0189] Each neuron in the input layer has a third connection weight with each neuron in the output layer. This third connection weight can be used to indicate the connection strength from a neuron in the input layer to a neuron in the output layer.

[0190] Please see Figure 7 In a BP neural network, each layer (input layer, hidden layer, or output layer) can include multiple neurons, allowing the BP neural network to process multiple input data simultaneously.

[0191] Below, in conjunction with Figure 8 The process of processing neurons is explained.

[0192] Figure 8 This is a schematic diagram of a neuron provided as an embodiment of this application. Please refer to [link / reference]. Figure 8The following data can be input into the neuron: n input data (X1 to Xn), the weight corresponding to each input data (weight1 to weightn), and the threshold θ of the neuron, to obtain the output data y.

[0193] A threshold can be used to adjust the activation level of the neuron; for example, the threshold can be -1.

[0194] Please see Figure 8 Each neuron can receive multiple input data and process these multiple input data to obtain output data. In the embodiments of this application, the processor can receive multiple first detection signals sent by multiple temperature detection modules. The processor can input multiple first detection signals sent by a temperature detection module within a certain time period (e.g., 1 millisecond) into a neuron of the input layer of a BP neural network. The input layer and output layer of the BP neural network, or the input layer, hidden layer, and output layer of the BP neural network, can process the multiple first detection signals input by the temperature detection module to obtain the detection temperature of the detection area corresponding to the temperature detection module.

[0195] The processor can also use a neural network model to synchronously process the first detection signals sent by multiple temperature detection modules. For example, the processor can input multiple first detection signals sent by one temperature detection module into a neuron in the input layer of a BP neural network for processing; and input multiple first detection signals sent by another temperature detection module into another neuron in the input layer of the BP neural network for processing. This helps to speed up the processor's determination of the detection temperature of the detection area corresponding to each temperature detection module, thereby improving the speed of determining the PCB temperature.

[0196] In some embodiments, the momentum of each neuron in the hidden layer can satisfy the following formula:

[0197]

[0198] Among them, S j w can represent the momentum of the j-th neuron in the hidden layer; ji This can represent the connection weight between the j-th neuron in the hidden layer and the i-th neuron in the input layer; x i θ can represent the i-th input data; j It can represent the threshold of the j-th neuron in the hidden layer.

[0199] In some embodiments, the output value of each neuron in the hidden layer can satisfy the following formula:

[0200]

[0201] Among them, b jThis can represent the output data of the j-th neuron in the hidden layer.

[0202] In some embodiments, the momentum of each neuron in the output layer can satisfy the following formula:

[0203]

[0204] Among them, S k w can represent the momentum of the k-th neuron in the output layer; kj θ can represent the connection weights between the k-th neuron in the output layer and the j-th neuron in the hidden layer; k It can represent the threshold of the k-th neuron in the output layer.

[0205] In some embodiments, the output values ​​of each neuron in the output layer can satisfy the following formula:

[0206]

[0207] Among them, y k It can represent the output data of the k-th neuron in the hidden layer.

[0208] In some embodiments, during iterative training of the BP neural network, the parameters of the BP neural network can be optimized to obtain the optimal solution.

[0209] The parameters of a BP neural network can include: the error of the output layer, the error of the hidden layer, the connection weights between the output layer and the hidden layer, the threshold of each neuron in the output layer, the connection weights between the hidden layer and the input layer, and the threshold of each neuron in the hidden layer.

[0210] The parameters of the BP neural network will be explained in detail below.

[0211] Alternatively, the error of the output layer can satisfy the following formula:

[0212] d k =(o k -y k )y k (1-y k )

[0213] Where, d k It can represent the error of the output layer; o k This can represent the expected result that the tester expects the output layer to produce; for example, the expected result could be the test temperature from the training data. k It can represent the actual result output by the output layer; for example, the actual result can be the predicted temperature of the BP neural network.

[0214] Alternatively, the error of the hidden layer can satisfy the following formula:

[0215]

[0216] Among them, e j It can represent the error of the hidden layer.

[0217] In some embodiments, the connection weights between the output layer and the hidden layer can be modified, and the modified connection weights between the output layer and the hidden layer can satisfy the following formula:

[0218] Δw kj =α·d k ·b j

[0219] Where, Δw kj α can be the correction value for the connection weight between the k-th neuron in the output layer and the j-th neuron in the hidden layer; α can be the correction coefficient of the output layer.

[0220] In some embodiments, the threshold of each neuron in the output layer can be modified, and the modified threshold can satisfy the following formula:

[0221] Δθ k =α·d k

[0222] Where, Δθ k It can be a correction value for the threshold of the k-th neuron in the output layer.

[0223] In some embodiments, the connection weights between the hidden layer and the input layer can be modified, and the modified connection weights between the hidden layer and the input layer can satisfy the following formula:

[0224] Δw ji =β·e j ·x i

[0225] Where, Δw ji β can be the correction value for the connection weight between the j-th neuron in the hidden layer and the i-th neuron in the input layer; β can be the correction coefficient of the hidden layer.

[0226] In some embodiments, the threshold of each neuron in the hidden layer can be modified, and the modified threshold can satisfy the following formula:

[0227] Δθ j =β·e j

[0228] Where, Δθ j It can be a correction value for the threshold of the j-th neuron in the hidden layer.

[0229] S603. Determine the detection temperature of the PCB based on the detection temperature of at least one detection area.

[0230] In some embodiments, if the number of at least one detection area is 1, the detection temperature of that detection area can be determined as the detection temperature of the PCB.

[0231] In some embodiments, if there are multiple detection areas, the processor 102 can determine the detection temperature of the PCB in any of the following ways.

[0232] Method 1: Determine the maximum detection temperature among the detection temperatures of multiple detection areas as the detection temperature of the PCB.

[0233] For example, temperature detection modules are set in four detection areas on the PCB. These four detection areas are selected from copper and / or busbar areas on the PCB where the current is relatively high and the temperature is relatively high. That is, the temperature of these four detection areas is usually higher than the temperature of other areas on the PCB. Therefore, the maximum detection temperature in these four detection areas can represent the maximum temperature of the PCB.

[0234] In some embodiments, the computing device can determine whether to perform temperature control on the PCB by detecting the maximum temperature of the PCB. In this case, method 1 can be used to determine the detected temperature of the PCB.

[0235] Method 2: Determine the average detection temperature of multiple detection areas based on their detection temperatures, and use this average detection temperature as the detection temperature of the PCB.

[0236] In some embodiments, the average value of the detection temperatures of multiple detection areas can be used to control the temperature of the PCB. In this case, method 2 can be used to determine the detection temperature of the PCB.

[0237] Method 3: Determine the PCB detection temperature as the detection temperature of the PCB if at least one of the detection temperatures of multiple detection areas is greater than the temperature threshold.

[0238] Optionally, the temperature threshold can be a parameter pre-configured by the user in the processor, and this temperature threshold can be lower than the critical temperature for PCB combustion. For example, if the critical temperature for PCB combustion is 85°C, the temperature threshold can be 80°C.

[0239] In some embodiments, the critical temperature for PCB combustion can be obtained from the PCB's instruction manual.

[0240] In some embodiments, the computing device can identify detection areas on the PCB where the detection temperature exceeds a temperature threshold, and perform temperature control on these detection areas. In this case, method 3 can be used to determine the detection temperature of the PCB.

[0241] The temperature detection method provided in this application embodiment can flexibly adopt any one of the above three methods to determine the detection temperature of the PCB according to the temperature detection scenario and temperature detection requirements, making the process of determining the detection temperature of the PCB more flexible.

[0242] In this method, a neural network model runs in the processor, which enables the processor to quickly and accurately obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module based on the first detection signal sent by at least one temperature detection module. This helps to improve the precision and efficiency of PCB temperature detection, making the temperature detection module more accurate in determining the temperature of the PCB.

[0243] S604: Send the detected temperature of the PCB to the programmable logic controller.

[0244] In some embodiments, the processor may send an instruction to the programmable logic device when the detected temperature of the PCB is greater than or equal to a temperature threshold; wherein the instruction may include the detected temperature of the PCB, and the instruction may be used to instruct the programmable logic device to perform a cooling process on the PCB.

[0245] In this temperature detection module, the processor can promptly send an instruction to the programmable logic controller (PLC) when the PCB temperature is greater than or equal to a temperature threshold. The PLC then cools the PCB, thus preventing it from burning out due to overheating, reducing the probability of PCB burnout, and improving the reliability of the computing device.

[0246] In some embodiments, the computing device may further include a memory that can be used to store the detected temperature of the PCB.

[0247] In some embodiments, the processor can also be used to delete the temperature of the PCB from memory if the detected temperature of the PCB is below a temperature threshold.

[0248] Understandably, if the PCB's detected temperature is below the temperature threshold, the PCB will be in normal operating condition. In this case, the processor does not need to send the detected PCB temperature to the programmable logic controller (PLC), thus avoiding occupying the PLC's storage space and saving PLC storage resources. Furthermore, to further save processor space, a smaller memory can be configured for the processor. If the PCB temperature is below the temperature threshold, the detected PCB temperature can be deleted from the memory to avoid occupying that memory's storage resources.

[0249] Compared to some computing devices that use temperature sensors to collect PCB temperatures and have the data processed by the Baseboard Management Controller (BMC) or Complex Programmable Logic Device (CPLD), the temperature detection method provided in this application can be implemented using a processor within the computing device. This processor can rapidly process at least one first detection signal sent by the temperature detection module using a neural network model to obtain the detected PCB temperature, resulting in higher efficiency. Furthermore, the processor can filter the collected PCB temperatures, sending indication information to the programmable logic device only when the detected PCB temperature is greater than or equal to a temperature threshold. This avoids useless data (e.g., PCB temperatures below the temperature threshold) consuming significant storage resources of the programmable logic device. This method also eliminates the need for data filtering by the BMC within the computing device, thus saving BMC processing resources.

[0250] (4) Programmable Logic 103

[0251] For example, the programmable logic device 103 can be a complex programmable logic device (CPLD).

[0252] The programmable logic unit 103 can be used to receive the detected temperature of the PCB sent by the processor and adjust the operating state of the PCB based on the detected temperature of the PCB.

[0253] The programmable logic controller 103 can adjust the operating state of the PCB as follows: control the PCB to power down; or reduce the power consumption parameters of the PCB.

[0254] This application embodiment also provides a temperature control method, which can be applied to a programmable logic device 103. The following describes the method in conjunction with... Figure 9 The temperature control method will be explained.

[0255] Figure 9 Please refer to the flowchart of a temperature control method provided in this application embodiment. Figure 9 The method can be executed by a programmable logic device 103 in a computing device, and the method may include the following steps:

[0256] S901, Receives the detected temperature of the PCB sent by the processor.

[0257] In some embodiments, the programmable logic device (PLD) can receive instruction information sent by the processor, which may include the detected temperature of the PCB. The instruction information can be used to instruct the PLD to perform cooling treatment on the PCB.

[0258] S902, PCB-based temperature detection and adjustment of PCB operating status.

[0259] In some embodiments, the programmable logic device 103 performs at least one of the following operations to adjust the operating state of the PCB: controlling the PCB to power down based on indication information; or, reducing the power consumption parameters of the PCB based on indication information.

[0260] Power consumption parameters may include current and / or voltage. Optionally, power consumption parameters may also include clock frequency.

[0261] For example, the programmable logic unit 103 may store power-down control instructions for the PCB, and the programmable logic unit 103 may execute the power-down control instructions to control the PCB to power down.

[0262] For example, a programmable logic device can perform at least one of the following operations to reduce the power consumption parameters of a PCB: reduce the operating voltage of each device on the PCB; reduce the operating current of each device on the PCB; reduce the clock frequency of some devices on the PCB.

[0263] For example, if the detected temperature of multiple detection areas in the PCB is greater than the temperature threshold, the programmable logic device can power down the entire PCB to quickly cool it down; if only a few detection areas in the multiple detection areas of the PCB have a detected temperature greater than the temperature threshold, the programmable logic device can reduce the power consumption parameters of the PCB to cool it down.

[0264] In the computing device provided in this application embodiment, the programmable logic device can flexibly adjust the working state of the PCB according to the detected temperature of the PCB to achieve the cooling treatment of the PCB, which is beneficial to improving the flexibility of temperature control of the PCB.

[0265] In some embodiments, the indication information may also include an identifier of a target detection area, which is a detection area in at least one detection area where the detection temperature is greater than or equal to a temperature threshold.

[0266] The processor can pre-store mapping relationships, which can include the identifiers of multiple detection areas and the identifiers of the temperature detection modules corresponding to each detection area.

[0267] The processor can determine the detection temperature of the detection area corresponding to the temperature detection module based on at least one first detection signal sent by the temperature detection module; if the detection temperature of the detection area is greater than the temperature threshold, the detection area can be identified as the target detection area, and the identifier of the target detection area and the detection temperature of the target detection area can be sent to the programmable logic device.

[0268] When the indication information includes an identifier of the target detection area, the programmable logic device 103 controls the PCB to power down based on the indication information, which may include: controlling the devices on the PCB located within the target detection area to power down based on the identifier of the target detection area in the indication information.

[0269] For example, there are 4 detection areas on the PCB. The detection temperature of detection area 1 and detection area 2 is higher than the temperature threshold, while the detection temperature of detection area 3 and detection area 4 is normal. The programmable logic device 103 can control the devices in detection area 1 and detection area 2 to be powered down.

[0270] When the indication information includes an identifier of the target detection area, the programmable logic device 103 reduces the power consumption parameters of the PCB based on the indication information. This may include: reducing the power consumption parameters of devices located within the target detection area on the PCB based on the identifier of the target detection area in the indication information.

[0271] For example, there are 4 detection areas on the PCB. The detection temperatures of detection areas 1 and 2 are higher than the temperature threshold, while the detection temperatures of detection areas 3 and 4 are normal. The programmable logic device 103 can perform at least one of the following operations on the devices in detection areas 1 and 2: reduce the operating voltage, reduce the operating current, and reduce the clock frequency.

[0272] In the computing device provided in this application embodiment, the programmable logic device can perform cooling processing on different areas of the PCB according to the instruction information sent by the processor, making the temperature control of the PCB more flexible.

[0273] This application also provides a temperature detection system that can be applied to a computing device. The structure of the temperature detection system can be as follows: Figure 11 As shown.

[0274] Figure 10 For a schematic diagram of a temperature detection system provided in an embodiment of this application, please refer to [link / reference]. Figure 10The temperature detection system may include at least one temperature detection module 101 and a processor 102. The temperature detection system may be applied in a computing device 10, which may include a PCB 100 and a programmable logic device 103.

[0275] like Figure 1 As shown, at least one temperature detection module 101 can be correspondingly disposed in at least one detection area of ​​the PCB, the detection area being the copper area and / or busbar area in the PCB.

[0276] It should be noted that the specific structure and working process of the temperature detection module 101 and the processor 102 in the embodiments of this application can be referred to the specific structure and working process of the temperature detection module 101 and the processor 102 in the embodiments of the computing device described above, and will not be repeated in the embodiments of this application.

[0277] It should be noted that the temperature detection system provided in this application embodiment can be applied to the server field, as well as other fields such as wireless base stations or routers. This application embodiment does not limit the application field of the temperature detection system.

[0278] Figure 11 For a schematic diagram of a temperature detection device provided in an embodiment of this application, please refer to [link / reference]. Figure 11 The temperature detection device 1100 can be applied in the processor 102, and the temperature detection device 1100 may include:

[0279] Transceiver module 1101 is used to receive a first detection signal sent by at least one temperature detection module;

[0280] The processing module 1102 is used to determine the detection temperature of the PCB through a neural network model based on a first detection signal sent by at least one temperature detection module.

[0281] The transceiver module 1101 is also used to send the detected temperature of the PCB to the programmable logic device.

[0282] In some embodiments, the processing module 1102 is specifically used for:

[0283] Input a first detection signal sent by at least one temperature detection module into the neural network model, and obtain the detection temperature of at least one detection area corresponding to at least one temperature detection module output by the neural network model;

[0284] The detection temperature of the PCB is determined based on the detection temperature of at least one detection area.

[0285] In some embodiments, the processing module 1102 is further configured to:

[0286] The maximum detection temperature among the detection temperatures of multiple detection zones is determined as the PCB detection temperature; or...

[0287] Based on the detection temperatures of multiple detection areas, determine the average detection temperature of these areas, and then use this average temperature as the detection temperature for the PCB; or,

[0288] The detection temperature of the PCB is determined by identifying at least one detection temperature that is greater than the temperature threshold among multiple detection areas.

[0289] In some embodiments, the transceiver module 1101 is specifically used for:

[0290] When the detected temperature of the PCB is greater than or equal to the temperature threshold, an indication message is sent to the programmable logic device.

[0291] The indication information includes the detected temperature of the PCB, which is used to instruct the programmable logic device to cool the PCB.

[0292] The temperature detection device 1100 provided in this application embodiment can implement the temperature detection method implemented by the processor in the above embodiment, and its beneficial effects are similar, so it will not be described again here.

[0293] Figure 12 For a schematic diagram of a temperature control device provided in an embodiment of this application, please refer to [link / reference]. Figure 12 The temperature control device 1200 can be applied in the programmable logic controller 103, and the temperature control device 1200 may include:

[0294] The transceiver module 1201 is used to receive the detected temperature of the PCB sent by the processor;

[0295] Processing module 1202 is used to adjust the working state of the PCB based on the detected temperature of the PCB.

[0296] In some embodiments, the transceiver module 1201 is specifically used for:

[0297] The system receives instruction information sent by the processor; the instruction information includes the detected temperature of the PCB, and is used to instruct the programmable logic device to perform cooling treatment on the PCB.

[0298] In some embodiments, the processing module 1202 is specifically used for:

[0299] The PCB is powered down based on the indication information, or the power consumption parameters of the PCB, including current and / or voltage, are reduced based on the indication information.

[0300] In some embodiments, the indication information further includes an identifier of a target detection area, wherein the target detection area is a detection area in at least one detection area where the detection temperature is greater than or equal to a temperature threshold; the processing module 1202 is specifically used for:

[0301] Controlling PCB power-down based on indication information includes: controlling the power-down of devices on the PCB located within the target detection area based on the identifier of the target detection area in the indication information; or,

[0302] The power consumption parameters of the PCB are reduced based on the indication information, including: reducing the power consumption parameters of devices located within the target detection area on the PCB based on the identification of the target detection area in the indication information.

[0303] The temperature control device 1200 provided in this application embodiment can implement the temperature control method implemented by the programmable logic device in the above embodiment, and its beneficial effects are similar, so they will not be described again here.

[0304] Optionally, the processor mentioned above can be a microcontroller unit (MCU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0305] This application provides a computer-readable storage medium storing computer-executable instructions; when executed by a processor, the computer-executable instructions are used to implement the temperature detection method or temperature control method as shown in the above embodiments.

[0306] This application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it causes the computer to perform the temperature detection method or temperature control method as shown in the above embodiments.

[0307] All or part of the steps in the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, it performs the steps of the above-described method embodiments; and the aforementioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof.

[0308] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable device, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0309] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0310] These computer program instructions may also be loaded onto a computer or other programmable device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0311] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of this application, and are not intended to limit them. Although the embodiments of this application have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A computing device, characterized in that, include: The system comprises a printed circuit board (PCB), at least one temperature detection module, a processor, and a programmable logic device (PLD), wherein the processor runs a neural network model. The at least one temperature detection module is correspondingly disposed in at least one detection area of ​​the PCB, wherein the detection area is the copper area and / or busbar area of ​​the PCB; For any given temperature detection module, the temperature detection module is used to perform temperature detection processing on the detection area corresponding to the temperature detection module, obtain a first detection signal corresponding to the detection area, and send the first detection signal to the processor; The processor is configured to determine the detection temperature of the PCB using a neural network model based on a first detection signal sent by the at least one temperature detection module, and to send the detection temperature of the PCB to the programmable logic device. The programmable logic device is used to adjust the operating state of the PCB based on the detected temperature of the PCB.

2. The computing device according to claim 1, characterized in that, For any given temperature detection module, the temperature detection module includes an infrared emitter and a detection circuit, wherein, The infrared emitter is used to send a first infrared light to the corresponding detection area of ​​the temperature detection module; The detection circuit is used to receive the second infrared light emitted by the detection area corresponding to the temperature detection module, determine the first detection signal corresponding to the detection area corresponding to the temperature detection module based on the second infrared light, and send the first detection signal to the processor. The second infrared light is obtained by the interaction between the first infrared light and the detection area corresponding to the temperature detection module.

3. The computing device according to claim 2, characterized in that, The detection circuit includes an infrared sensor and a signal converter, wherein the signal converter is connected to both the sensor and the processor. The infrared sensor is used to receive the second infrared light and to send a second detection signal to the signal converter based on the second infrared light. The signal converter is used to perform analog-to-digital conversion on the second detection signal to obtain the first detection signal, and to send the first detection signal to the processor.

4. The computing device according to any one of claims 1-3, characterized in that, Based on the first detection signal sent by the at least one temperature detection module, the detection temperature of the PCB is determined by a neural network model, including: The first detection signal sent by the at least one temperature detection module is input into the neural network model to obtain the detection temperature of the at least one detection area corresponding to the at least one temperature detection module output by the neural network model. The detection temperature of the PCB is determined based on the detection temperature of the at least one detection area.

5. The computing device according to claim 4, characterized in that, The number of the at least one detection area is multiple; the detection temperature of the PCB is determined based on the detection temperature of the at least one detection area, including: The maximum detection temperature among the detection temperatures of multiple detection areas is determined as the detection temperature of the PCB; or, Based on the detection temperatures of the multiple detection areas, the average detection temperature of the multiple detection areas is determined, and this average detection temperature is used as the detection temperature of the PCB; or, The detection temperature of the PCB is determined by identifying at least one detection temperature among the multiple detection areas that is greater than a temperature threshold.

6. The computing device according to any one of claims 1-5, characterized in that, Sending the detected temperature of the PCB to the programmable logic device includes: If the detected temperature of the PCB is greater than or equal to the temperature threshold, an indication message is sent to the programmable logic device. The indication information includes the detected temperature of the PCB, and the indication information is used to instruct the programmable logic device to perform a cooling process on the PCB.

7. The computing device according to claim 6, characterized in that, Adjusting the operating state of the PCB based on the detected temperature of the PCB includes: The PCB may be powered down based on the indicated information, or the power consumption parameters of the PCB may be reduced based on the indicated information, wherein the power consumption parameters include current and / or voltage.

8. The computing device according to claim 7, characterized in that, The indication information also includes an identifier of the target detection area, which is a detection area in the at least one detection area where the detection temperature is greater than or equal to the temperature threshold; Controlling the PCB to power down based on the indication information includes: controlling the devices on the PCB located within the target detection area to power down based on the identifier of the target detection area in the indication information; or, Reducing the power consumption parameters of the PCB based on the indication information includes: reducing the power consumption parameters of devices located within the target detection area on the PCB based on the identifier of the target detection area in the indication information.

9. The computing device according to any one of claims 1-8, characterized in that, The at least one detection area includes at least one of the following areas: The bus copper area of ​​the central processing unit (CPU); The bus copper area of ​​the digital processing unit (DPU) at the working voltage input of the PCB; The copper area at the working voltage input of the PCB; The busbar area at the operating voltage input of the PCB.

10. A temperature detection system, characterized in that, Applied in computing devices, the computing devices include printed circuit boards (PCBs) and programmable logic devices, and the temperature detection system includes at least one temperature detection module and a processor, wherein... The at least one temperature detection module is correspondingly disposed in at least one detection area of ​​the PCB, wherein the detection area is the copper area and / or busbar area of ​​the PCB; For any given temperature detection module, the temperature detection module is used to perform temperature detection on the detection area corresponding to the temperature detection module, obtain a first detection signal corresponding to the detection area, and send the first detection signal to the processor; The processor is configured to determine the detection temperature of the PCB using a neural network model based on a first detection signal sent by the at least one temperature detection module, and to send the detection temperature of the PCB to the programmable logic device.

Images