Method and system for identifying abnormal internal temperature of chip
By generating a two-dimensional temperature distribution map, identifying temperature abnormal points inside the chip, the problem of low recognition accuracy in the prior art is solved, and a higher accuracy of temperature abnormal points recognition is achieved.
Patent Information
- Application Number
- CN202411313796.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-20
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-20
AI Technical Summary
The prior art detects the temperature abnormality points inside the chip, and the recognition accuracy is low, and the chip will heat up during the infrared scanning process, resulting in inaccurate identification of the temperature abnormality points.
By obtaining the temperature data and fault alarm information of each position point, multiple temperature distribution information are generated, and the first sub-temperature distribution information and the second sub-temperature distribution information corresponding to the fault range are selected to generate a two-dimensional temperature distribution The graph identifies the temperature abnormal points of the chip.
The recognition accuracy of the internal temperature abnormal points of the chip is improved, and the different temperature distribution information, fault range and abnormal temperature data of the chip are comprehensively considered, so as to optimize the recognition accuracy.
Smart Images

Figure CN119087188A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of integrated circuit chips, and in particular to a method and system for identifying abnormal temperature inside a chip. Background Art
[0002] With the optimization and improvement of chip packaging technology, the chip cannot directly detect the abnormality of the internal structure of the chip from the appearance, and when the chip is heated due to a fault, the heating condition inside the chip cannot be directly detected, resulting in the inability to directly detect the hardware heating point of the chip and the failure location inside the chip. The entire chip can only be replaced directly, resulting in low chip utilization. Therefore, how to detect the temperature abnormality inside the chip is the current research focus.
[0003] The traditional way to detect temperature anomalies inside a chip is to obtain a temperature distribution map of the chip through infrared scanning of the chip, thereby querying the temperature anomalies of the chip. However, the range of temperature anomalies obtained by this method is large, and the infrared scanning process itself will cause the chip to heat up, resulting in low recognition accuracy of temperature anomalies inside the chip. Summary of the invention
[0004] The present invention provides a method and system for identifying abnormal temperature inside a chip to solve the above technical problems and effectively improve the accuracy of identifying abnormal temperature points inside the chip.
[0005] In order to solve the above technical problems, the present invention provides a method for identifying abnormal temperature inside a chip, comprising:
[0006] Obtain temperature data and chip fault alarm information at each location;
[0007] Determine abnormal temperature data from the temperature data, and obtain the chip fault range based on the fault alarm information;
[0008] Based on the temperature data of each location point, a number of temperature distribution information are generated;
[0009] From among the plurality of temperature distribution information, first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to the abnormal temperature data are obtained;
[0010] Generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information;
[0011] Based on the two-dimensional temperature distribution map, each temperature abnormality point of the chip is identified.
[0012] The beneficial effects of the present invention are:
[0013] Compared with the prior art, such as using infrared scanning to identify abnormal temperature points of chips, which will cause the chip to heat up, resulting in lower recognition accuracy; the present invention generates a two-dimensional temperature distribution map based on the first sub-temperature distribution information corresponding to the chip fault range and the second sub-temperature distribution information corresponding to the abnormal temperature data, so that the two-dimensional temperature distribution map has targeted information related to chip abnormalities or failures. Therefore, according to the two-dimensional temperature distribution map, the various temperature abnormal points of the chip are identified, and the temperature distribution of the chip in different temperature distribution information, chip fault ranges and abnormal temperature data can be comprehensively considered, and the possible temperature abnormal points of the chip are globally considered, thereby comprehensively improving the recognition accuracy of the temperature abnormal points inside the chip.
[0014] Further, obtaining the chip fault range based on the fault alarm information includes:
[0015] Based on the fault alarm information, obtain the fault type of the chip;
[0016] Querying a chip fault structure corresponding to the fault type in a preset database;
[0017] Determine the structural range of each structure in the chip;
[0018] In the structural ranges of each structure in the chip, the structural range corresponding to the chip fault structure is used as the chip fault range.
[0019] The present invention identifies the fault type corresponding to the fault alarm information and the chip fault structure of the chip, thereby determining the chip fault range, improving the accuracy of identifying the chip fault range, and further optimizing the range information of the chip temperature anomaly point, thereby improving the accuracy of identifying the chip temperature anomaly point.
[0020] Furthermore, the temperature distribution information is generated based on the temperature data of each position point, including:
[0021] Get the number of location points and the location information of each location point;
[0022] Based on the number of location points and the location information of each location point, generating a plurality of location point groups;
[0023] For each position point group, based on the position information and temperature data of each position point in the position point group, a temperature fitting strategy is used to obtain fitting temperature data of each position point to generate a plurality of temperature distribution information.
[0024] The present invention generates temperature distribution information by fitting temperature data of different position points, thereby improving the comprehensiveness of temperature distribution information of each position point of the identification chip, avoiding the problem that single temperature distribution information cannot characterize the local temperature distribution characteristics of the chip, thereby improving the accuracy of subsequent screening of temperature data of each position point, and improving the globality of chip temperature distribution information under the condition of temperature data of different position points.
[0025] Furthermore, the generating of a plurality of position point groups based on the number of position points and the position information of each position point includes:
[0026] Determine the center point of the chip;
[0027] Divide the chip into four areas based on the cross axis of the chip, and determine the area to which each position point belongs;
[0028] Based on the position information, obtain the position information of each position point relative to the central position point;
[0029] Based on the position information of each location point and the area to which each location point belongs, determining location points that cannot be grouped together among the location points; wherein, location points belonging to the same area cannot be grouped together;
[0030] Determine the minimum number of position points for each position point group, and based on the minimum number of position points, perform permutation and combination processing on each position point to obtain a number of initial position point groups;
[0031] In each initial position point group, the initial position point group containing position points that cannot be grouped together is deleted to obtain a plurality of position point groups.
[0032] The present invention avoids the limitation of the acquired temperature distribution information and the problem of overly obvious local temperature data by deleting the position point group corresponding to the position points that are too close to each other, thereby improving the reliability and authenticity of the fitted temperature data.
[0033] Further, the obtaining of first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to the abnormal temperature data includes:
[0034] At each location point, obtaining the fault location point included in the chip fault range;
[0035] Based on a plurality of temperature distribution information, the temperature data of the fault location point is obtained from the temperature data of each location point to obtain the first sub-temperature distribution information corresponding to the chip fault range;
[0036] In each position point, determine the abnormal position point corresponding to the abnormal temperature data, and obtain the abnormal point position information of the abnormal position point in the position information of each position point;
[0037] Based on the plurality of temperature distribution information and abnormal point position information, second sub-temperature distribution information corresponding to the abnormal temperature data is obtained.
[0038] The present invention obtains first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information of the position point corresponding to the abnormal temperature data, thereby improving the comprehensiveness of the screening sub-temperature distribution information; and the obtained first sub-temperature distribution information and second sub-temperature distribution information are highly correlated with the chip fault and abnormal temperature, so that the subsequently obtained two-dimensional temperature distribution map can specifically characterize the information related to the chip abnormality or failure, thereby improving the accuracy of identifying the temperature abnormality points inside the chip.
[0039] Furthermore, for each position point group, based on the position information and temperature data of each position point in the position point group, obtaining fitting temperature data of each position point through a temperature fitting strategy includes:
[0040] Obtain historical temperature distribution information of the chip;
[0041] Based on the historical temperature distribution information, the average value of the temperature data difference between adjacent location points is obtained;
[0042] For each position point group, based on the position information of each position point in the position point group, the temperature data of each position point and the average value of the temperature data difference between each adjacent position point, the initial fitting temperature data of each other position point corresponding to each position point is obtained;
[0043] Based on the temperature data of each position point and the initial fitting temperature data of each other position point corresponding to each position point, the fitting temperature data of each position point is determined.
[0044] The present invention obtains the average value of the temperature data difference between each adjacent position point based on the historical temperature distribution information, and determines the fitting temperature data of other position points corresponding to each position point by obtaining the average value of the temperature data difference between each adjacent position point based on the historical temperature distribution information, thereby improving the authenticity of the fitting temperature data of other position points.
[0045] Further, generating a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information includes:
[0046] For each temperature distribution information, generating target temperature data of each position point based on an average value of temperature data differences between adjacent position points, the first sub-temperature distribution information, and the second sub-temperature distribution information;
[0047] Based on the position information of each position point, the target temperature data of each position point is distributed and arranged in a two-dimensional space to generate a two-dimensional temperature distribution map.
[0048] In the present invention, the first sub-temperature distribution information and the second sub-temperature distribution information are highly correlated with chip failure and abnormal temperature, so that the two-dimensional temperature distribution map generated based on the first sub-temperature distribution information and the second sub-temperature distribution information can specifically characterize the information related to chip abnormality or failure, thereby improving the accuracy of identifying temperature abnormality points inside the chip.
[0049] Further, the identifying each temperature abnormality point of the chip based on the two-dimensional temperature distribution map includes:
[0050] In the target temperature data of each position point, an initial temperature abnormal point corresponding to the abnormal temperature data is obtained;
[0051] In the two-dimensional temperature distribution map, determining an abnormal temperature region including each initial temperature abnormal point;
[0052] Based on the target temperature data of each position point in each abnormal temperature area, obtaining the temperature gradient change information of each abnormal temperature area;
[0053] Based on the temperature gradient change information of each abnormal temperature region, a position point corresponding to the gradient center point in each abnormal temperature region is determined to identify each temperature abnormal point of the chip.
[0054] The present invention is based on a two-dimensional temperature distribution map and determines the temperature abnormal points by identifying the gradient center point of each abnormal temperature area, thereby improving the accuracy of identifying the temperature abnormal points.
[0055] Further, the determining of the position point corresponding to the gradient center point in each abnormal temperature region based on the temperature gradient change information of each abnormal temperature region includes:
[0056] Based on the temperature gradient change information of each abnormal temperature area, a temperature decreasing trend line and a temperature increasing trend line of each abnormal temperature area are obtained;
[0057] The intersection point of the temperature decreasing trend line and the temperature increasing trend line is determined as the position point corresponding to the gradient center point in each abnormal temperature region.
[0058] Accordingly, in order to solve the above technical problems, the present invention also provides a system for identifying abnormal temperature inside a chip, comprising: a data acquisition module, a data processing module, a graph generation module and an abnormality identification module;
[0059] Wherein, the data acquisition module is used to obtain temperature data and chip fault alarm information at each location;
[0060] The data processing module is used to determine abnormal temperature data from the temperature data, and obtain the chip fault range based on the fault alarm information; based on the temperature data of each position point, generate a number of temperature distribution information;
[0061] The map generation module is used to obtain first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to abnormal temperature data from a plurality of temperature distribution information; and generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information;
[0062] The abnormality identification module is used to identify each temperature abnormality point of the chip based on the two-dimensional temperature distribution map. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] Figure 1 : A flow chart of an embodiment of a method for identifying abnormal internal temperature of a chip provided by the present invention;
[0064] Figure 2 : A schematic structural diagram of an embodiment of a system for identifying abnormal internal temperature of a chip provided by the present invention. DETAILED DESCRIPTION
[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0066] The traditional way to detect temperature anomalies inside a chip is to obtain a temperature distribution map of the chip through infrared scanning of the chip, thereby querying the temperature anomalies of the chip. However, the range of temperature anomalies obtained by this method is large, and the infrared scanning process itself will cause the chip to heat up, resulting in low recognition accuracy of temperature anomalies inside the chip.
[0067] Embodiment 1
[0068] In order to solve the above technical problems, the present invention provides a method and system for identifying abnormal temperature inside a chip to solve the above technical problems and effectively improve the accuracy of identifying abnormal temperature points inside the chip.
[0069] Please refer to Figure 1 , is a flow chart of an embodiment of a method for identifying abnormal internal temperature of a chip provided by an embodiment of the present invention. Figure 1 As shown, the method for identifying abnormal chip internal temperature includes steps 101 to 106, specifically:
[0070] Step 101: Acquire temperature data and chip fault alarm information at each location;
[0071] Step 102: determining abnormal temperature data from the temperature data, and obtaining a chip fault range based on the fault alarm information;
[0072] Step 103: Generate a plurality of temperature distribution information based on the temperature data of each position point;
[0073] Step 104: acquiring, from among the plurality of temperature distribution information, first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to the abnormal temperature data;
[0074] Step 105: Generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information;
[0075] Step 106: Based on the two-dimensional temperature distribution map, identify temperature abnormal points of the chip.
[0076] Compared with the prior art, such as using infrared scanning to identify abnormal temperature points of chips, which will cause the chip to heat up, resulting in lower recognition accuracy; the present invention generates a two-dimensional temperature distribution map based on the first sub-temperature distribution information corresponding to the chip fault range and the second sub-temperature distribution information corresponding to the abnormal temperature data, so that the two-dimensional temperature distribution map has targeted information related to chip abnormalities or failures. Therefore, according to the two-dimensional temperature distribution map, the various temperature abnormal points of the chip are identified, and the temperature distribution of the chip in different temperature distribution information, chip fault ranges and abnormal temperature data can be comprehensively considered, and the possible temperature abnormal points of the chip are globally considered, thereby comprehensively improving the recognition accuracy of the temperature abnormal points inside the chip.
[0077] Furthermore, in step 101, when obtaining chip fault alarm information, temperature data transmitted by temperature sensors preset at different positions of the chip are obtained to obtain current temperature data of multiple positions of the chip detected by the sensor. Then, the alarm content corresponding to the alarm information of the chip is collected to obtain chip fault alarm information.
[0078] Further, in step 102, the chip fault range is obtained based on the fault alarm information, including:
[0079] Based on the fault alarm information, obtain the fault type of the chip;
[0080] Querying a chip fault structure corresponding to the fault type in a preset database;
[0081] Determine the structural range of each structure in the chip;
[0082] In the structural ranges of each structure in the chip, the structural range corresponding to the chip fault structure is used as the chip fault range.
[0083] In this embodiment, the chip fault structure corresponding to each fault type is stored in the preset database; the chip structure of the chip is the structural information of each hardware constituting the chip; this embodiment presets the structural range corresponding to each structure.
[0084] The present invention identifies the fault type corresponding to the fault alarm information and the chip fault structure of the chip, thereby determining the chip fault range, improving the accuracy of identifying the chip fault range, and further optimizing the range information of the chip temperature anomaly point, thereby improving the accuracy of identifying the chip temperature anomaly point.
[0085] Further, in step 102, the abnormal temperature data is temperature data greater than a preset temperature threshold.
[0086] Furthermore, in step 103, based on the temperature data of each location point, a plurality of temperature distribution information is generated, including:
[0087] Get the number of location points and the location information of each location point;
[0088] Based on the number of location points and the location information of each location point, generating a plurality of location point groups;
[0089] For each position point group, based on the position information and temperature data of each position point in the position point group, a temperature fitting strategy is used to obtain fitting temperature data of each position point to generate a plurality of temperature distribution information.
[0090] This embodiment generates several location point groups based on the number of location points and the location information of each location point. For example, if the location points include a, b, c, d, e and f, then the location point groups include: 1. a, b, 2. a, b, c, 3, a, b, c, d, 4. a, b, c, d, e, 5. a, c, 6. a, d ..., na, b, c, d, e, f. The location point groups are the combination information obtained by arranging and combining the location points according to a number greater than the minimum number of location points.
[0091] This embodiment uses the fitting temperature data of all position points as the temperature distribution information of the chip.
[0092] The present invention generates temperature distribution information by fitting temperature data of different position points, thereby improving the comprehensiveness of temperature distribution information of each position point of the identification chip, avoiding the problem that single temperature distribution information cannot characterize the local temperature distribution characteristics of the chip, thereby improving the accuracy of subsequent screening of temperature data of each position point, and improving the globality of chip temperature distribution information under the condition of temperature data of different position points.
[0093] Furthermore, the generating of a plurality of position point groups based on the number of position points and the position information of each position point includes:
[0094] Determine the center point of the chip;
[0095] Divide the chip into four areas based on the cross axis of the chip, and determine the area to which each position point belongs;
[0096] Based on the position information, obtain the position information of each position point relative to the central position point;
[0097] Based on the position information of each location point and the area to which each location point belongs, determining location points that cannot be grouped together among the location points; wherein, location points belonging to the same area cannot be grouped together;
[0098] Determine the minimum number of position points for each position point group, and based on the minimum number of position points, perform permutation and combination processing on each position point to obtain a number of initial position point groups;
[0099] In each initial position point group, the initial position point group containing position points that cannot be grouped together is deleted to obtain a plurality of position point groups.
[0100] The present invention avoids the limitation of the acquired temperature distribution information and the problem of overly obvious local temperature data by deleting the position point group corresponding to the position points that are too close to each other, thereby improving the reliability and authenticity of the fitted temperature data.
[0101] Further, in step 104, the obtaining of first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to the abnormal temperature data includes:
[0102] For each temperature distribution information, at each position point, obtain the fault position point included in the chip fault range;
[0103] Based on a plurality of temperature distribution information, the temperature data of the fault location point is obtained from the temperature data of each location point to obtain the first sub-temperature distribution information corresponding to the chip fault range;
[0104] In each position point, determine the abnormal position point corresponding to the abnormal temperature data, and obtain the abnormal point position information of the abnormal position point in the position information of each position point;
[0105] Based on the plurality of temperature distribution information and abnormal point position information, second sub-temperature distribution information corresponding to the abnormal temperature data is obtained.
[0106] The present invention obtains first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information of the position point corresponding to the abnormal temperature data, thereby improving the comprehensiveness of the screening sub-temperature distribution information; and the obtained first sub-temperature distribution information and second sub-temperature distribution information are highly correlated with the chip fault and abnormal temperature, so that the subsequently obtained two-dimensional temperature distribution map can specifically characterize the information related to the chip abnormality or failure, thereby improving the accuracy of identifying the temperature abnormality points inside the chip.
[0107] Furthermore, for each position point group, based on the position information and temperature data of each position point in the position point group, obtaining fitting temperature data of each position point through a temperature fitting strategy includes:
[0108] Obtain historical temperature distribution information of the chip;
[0109] Based on the historical temperature distribution information, the average value of the temperature data difference between adjacent location points is obtained;
[0110] For each position point group, based on the position information of each position point in the position point group, the temperature data of each position point and the average value of the temperature data difference between each adjacent position point, the initial fitting temperature data of each other position point corresponding to each position point is obtained;
[0111] Based on the temperature data of each position point and the initial fitting temperature data of each other position point corresponding to each position point, the fitting temperature data of each position point is determined.
[0112] In this embodiment, the temperature data difference between adjacent position points in the historical temperature distribution information is identified, and based on the temperature data difference between adjacent position points corresponding to different historical temperature distribution information, the average value of the temperature data difference between adjacent position points is obtained.
[0113] The present invention obtains the average value of the temperature data difference between each adjacent position point based on the historical temperature distribution information, and determines the fitting temperature data of other position points corresponding to each position point by obtaining the average value of the temperature data difference between each adjacent position point based on the historical temperature distribution information, thereby improving the authenticity of the fitting temperature data of other position points.
[0114] Further, in step 105, generating a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information includes:
[0115] For each temperature distribution information, generating target temperature data of each position point based on an average value of temperature data differences between adjacent position points, the first sub-temperature distribution information, and the second sub-temperature distribution information;
[0116] Based on the position information of each position point, the target temperature data of each position point is distributed and arranged in a two-dimensional space to generate a two-dimensional temperature distribution map.
[0117] In this embodiment, for each temperature distribution information, based on the average value of the temperature data difference between each adjacent position point, the first sub-temperature distribution information and the second sub-temperature distribution information, an implementation method of generating the target temperature data of each position point is as follows: for each temperature distribution information, based on the average value of the temperature data difference between each adjacent position point, the first sub-temperature distribution information corresponding to the temperature distribution information and the second sub-temperature distribution information corresponding to the temperature distribution information, generate candidate target temperature data for each position point; based on the candidate target temperature data of each position point corresponding to each temperature distribution information, obtain the target temperature data of each position point; specifically, the method of generating the candidate target temperature data of each position point is to fit the temperature data of each position point in each sub-temperature distribution information corresponding to each temperature distribution information to obtain the target temperature data of each position point.
[0118] In the present invention, the first sub-temperature distribution information and the second sub-temperature distribution information are highly correlated with chip failure and abnormal temperature, so that the two-dimensional temperature distribution map generated based on the first sub-temperature distribution information and the second sub-temperature distribution information can specifically characterize the information related to chip abnormality or failure, thereby improving the accuracy of identifying temperature abnormality points inside the chip.
[0119] Further, in step 106, identifying each temperature abnormality point of the chip based on the two-dimensional temperature distribution map includes:
[0120] In the target temperature data of each position point, an initial temperature abnormal point corresponding to the abnormal temperature data is obtained;
[0121] In the two-dimensional temperature distribution map, determining an abnormal temperature region including each initial temperature abnormal point;
[0122] Based on the target temperature data of each position point in each abnormal temperature area, obtaining the temperature gradient change information of each abnormal temperature area;
[0123] Based on the temperature gradient change information of each abnormal temperature region, a position point corresponding to the gradient center point in each abnormal temperature region is determined to identify each temperature abnormal point of the chip.
[0124] The present invention is based on a two-dimensional temperature distribution map and determines the temperature abnormal points by identifying the gradient center point of each abnormal temperature area, thereby improving the accuracy of identifying the temperature abnormal points.
[0125] Further, the determining of the position point corresponding to the gradient center point in each abnormal temperature region based on the temperature gradient change information of each abnormal temperature region includes:
[0126] Based on the temperature gradient change information of each abnormal temperature area, a temperature decreasing trend line and a temperature increasing trend line of each abnormal temperature area are obtained;
[0127] The intersection point of the temperature decreasing trend line and the temperature increasing trend line is determined as the position point corresponding to the gradient center point in each abnormal temperature region.
[0128] The method for identifying abnormal temperature inside a chip provided by an embodiment of the present invention can be applied to the application environment of identifying abnormal temperature points inside an IoT chip. The method for identifying abnormal temperature inside a chip can be applied to a terminal, a server, or a system including a terminal and a server, and implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc.
[0129] Accordingly, in order to solve the above technical problems, the embodiment of the present invention also provides a system for identifying abnormal temperature inside a chip. Figure 2 , which is a structural schematic diagram of an embodiment of a system for identifying abnormal internal temperature of a chip provided by the present invention.
[0130] like Figure 2 As shown, the chip internal temperature abnormality recognition system 20 includes: a data acquisition module 201, a data processing module 202, a graph generation module 203 and an abnormality recognition module 204;
[0131] Wherein, the data acquisition module 201 is used to acquire temperature data and chip fault alarm information at each location;
[0132] The data processing module 202 is used to determine abnormal temperature data from the temperature data, and obtain the chip fault range based on the fault alarm information; based on the temperature data of each position point, generate a number of temperature distribution information;
[0133] The map generation module 203 is used to obtain first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to abnormal temperature data from a plurality of temperature distribution information; and generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information;
[0134] The abnormality identification module 204 is used to identify temperature abnormal points of the chip based on the two-dimensional temperature distribution map.
[0135] Each module in the chip internal temperature abnormality identification system can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.
[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0137] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0138] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0139] The present invention obtains the chip fault range through the chip fault alarm information, thereby optimizing the range information of the chip temperature anomaly points, and improving the accuracy of identifying the chip temperature anomaly points; through the temperature data of each position point, multiple temperature distribution information is generated, which improves the globality of identifying the chip temperature distribution information under the condition of temperature data of different position points, and avoids the problem that a single temperature distribution information cannot characterize the local temperature distribution characteristics of the chip; then, the present invention screens the first sub-temperature distribution information corresponding to the fault range and the second sub-temperature distribution information of the abnormal temperature data from a plurality of temperature distribution information, which not only improves the pertinence of the temperature distribution information of the fault range, but also improves the global consideration of other possible temperature anomalies of the chip; then, a two-dimensional temperature distribution map of the chip is generated based on multiple sub-temperature distribution information, and each temperature anomaly point of the chip is identified based on the two-dimensional temperature distribution map, thereby comprehensively considering the temperature distribution of the chip in different temperature distribution information, chip fault range and abnormal temperature data, thereby comprehensively improving the accuracy of identifying the temperature anomaly points inside the chip.
[0140] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the protection scope of the present invention. It should be understood that although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps. It is particularly pointed out that for those skilled in the art, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for identifying abnormal temperature inside a chip, characterized in that: include: Obtain temperature data and chip fault alarm information at each location; Determine abnormal temperature data from the temperature data, and obtain the chip fault range based on the fault alarm information; Based on the temperature data of each location point, a number of temperature distribution information are generated; From among the plurality of temperature distribution information, first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to the abnormal temperature data are obtained; Generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information; Based on the two-dimensional temperature distribution map, each temperature abnormality point of the chip is identified.
2. A method for identifying abnormal internal temperature of a chip as claimed in claim 1, characterized in that: The obtaining of the chip fault range based on the fault alarm information includes: Based on the fault alarm information, obtain the fault type of the chip; Querying a chip fault structure corresponding to the fault type in a preset database; Determine the structural range of each structure in the chip; In the structural ranges of each structure in the chip, the structural range corresponding to the chip fault structure is used as the chip fault range.
3. The method for identifying abnormal internal temperature of a chip according to claim 1, characterized in that: Based on the temperature data of each location point, a plurality of temperature distribution information is generated, including: Get the number of location points and the location information of each location point; Based on the number of location points and the location information of each location point, generating a plurality of location point groups; For each position point group, based on the position information and temperature data of each position point in the position point group, a temperature fitting strategy is used to obtain fitting temperature data of each position point to generate a plurality of temperature distribution information.
4. A method for identifying abnormal internal temperature of a chip as claimed in claim 3, characterized in that: The generating of a plurality of position point groups based on the number of position points and the position information of each position point includes: Determine the center point of the chip; Divide the chip into four areas based on the cross axis of the chip, and determine the area to which each position point belongs; Based on the position information, obtain the position information of each position point relative to the central position point; Based on the position information of each location point and the area to which each location point belongs, determining location points that cannot be grouped together among the location points; wherein, location points belonging to the same area cannot be grouped together; Determine the minimum number of position points for each position point group, and based on the minimum number of position points, perform permutation and combination processing on each position point to obtain a number of initial position point groups; In each initial position point group, the initial position point group containing position points that cannot be grouped together is deleted to obtain a plurality of position point groups.
5. The method for identifying abnormal internal temperature of a chip as claimed in claim 3, characterized in that: The obtaining of first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to the abnormal temperature data includes: At each location point, obtaining the fault location point included in the chip fault range; Based on a plurality of temperature distribution information, temperature data of a fault location point is obtained from the temperature data of each location point to obtain first sub-temperature distribution information corresponding to the chip fault range; In each position point, determine the abnormal position point corresponding to the abnormal temperature data, and obtain the abnormal point position information of the abnormal position point in the position information of each position point; Based on the plurality of temperature distribution information and abnormal point position information, second sub-temperature distribution information corresponding to the abnormal temperature data is obtained.
6. A method for identifying abnormal chip internal temperature as claimed in claim 3, characterized in that: For each position point group, based on the position information and temperature data of each position point in the position point group, obtaining fitting temperature data of each position point through a temperature fitting strategy includes: Obtain historical temperature distribution information of the chip; Based on the historical temperature distribution information, the average value of the temperature data difference between adjacent location points is obtained; For each position point group, based on the position information of each position point in the position point group, the temperature data of each position point and the average value of the temperature data difference between each adjacent position point, the initial fitting temperature data of each other position point corresponding to each position point is obtained; Based on the temperature data of each position point and the initial fitting temperature data of each other position point corresponding to each position point, the fitting temperature data of each position point is determined.
7. A method for identifying abnormal internal temperature of a chip as claimed in claim 6, characterized in that: The generating a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information comprises: For each temperature distribution information, generating target temperature data of each position point based on an average value of temperature data differences between adjacent position points, the first sub-temperature distribution information, and the second sub-temperature distribution information; Based on the position information of each position point, the target temperature data of each position point is distributed and arranged in a two-dimensional space to generate a two-dimensional temperature distribution map.
8. A method for identifying abnormal internal temperature of a chip as claimed in claim 7, characterized in that: The step of identifying each temperature abnormality point of the chip based on the two-dimensional temperature distribution map includes: In the target temperature data of each position point, an initial temperature abnormal point corresponding to the abnormal temperature data is obtained; In the two-dimensional temperature distribution map, determining an abnormal temperature region including each initial temperature abnormal point; Based on the target temperature data of each position point in each abnormal temperature area, obtaining the temperature gradient change information of each abnormal temperature area; Based on the temperature gradient change information of each abnormal temperature region, a position point corresponding to the gradient center point in each abnormal temperature region is determined to identify each temperature abnormal point of the chip.
9. A method for identifying abnormal temperature inside a chip as claimed in claim 8, characterized in that: The step of determining a position point corresponding to the gradient center point in each abnormal temperature region based on the temperature gradient change information of each abnormal temperature region comprises: Based on the temperature gradient change information of each abnormal temperature area, a temperature decreasing trend line and a temperature increasing trend line of each abnormal temperature area are obtained; The intersection point of the temperature decreasing trend line and the temperature increasing trend line is determined as the position point corresponding to the gradient center point in each abnormal temperature region.
10. A system for identifying abnormal temperature inside a chip, characterized in that: include: Data acquisition module, data processing module, graph generation module and anomaly recognition module; Wherein, the data acquisition module is used to obtain temperature data and chip fault alarm information at each location; The data processing module is used to determine abnormal temperature data from the temperature data, and obtain the chip fault range based on the fault alarm information; based on the temperature data of each position point, generate a number of temperature distribution information; The map generation module is used to obtain first sub-temperature distribution information corresponding to the chip fault range and second sub-temperature distribution information corresponding to abnormal temperature data from a plurality of temperature distribution information; and generate a two-dimensional temperature distribution map based on the first sub-temperature distribution information and the second sub-temperature distribution information; The abnormality identification module is used to identify each temperature abnormality point of the chip based on the two-dimensional temperature distribution map.
Citation Information
Patent Citations
Array type three-dimensional temperature field detection system for intelligent electric cabinet
CN110487423A
Chip temperature field distribution detection method and device, medium and chip
CN115078965A
Chip failure positioning method
CN117630635A
Chip packaging test system and method
CN118550780A
Monitoring system and method for wellsite equipment
US20220259947A1
Cited By
Abnormality detection method, electronic device, storage medium and program product
CN121275183A
