Health assessment method and device for high-temperature aging test chamber of integrated circuits

Abstract

This invention discloses a health assessment method and apparatus for a high-temperature aging test chamber for integrated circuits, belonging to the field of integrated circuit technology. The method includes: determining the health value of each module in the test chamber and calculating the degradation rate of each module based on the health value; constructing a coupling influence relationship matrix based on the number of modules in the test chamber and the influence coupling coefficient between modules; generating a dynamic weight vector corresponding to the test chamber based on the health value of each module, degradation rate, predefined benchmark weight vector, and the coupling influence relationship matrix; constructing a fuzzy relationship matrix for health levels; generating a comprehensive health evaluation vector based on the dynamic weight vector and the fuzzy relationship matrix for health levels; and determining the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level. This scheme makes the obtained health assessment results more accurate and more consistent with physical reality.

Description

Technical Field

[0001] This invention relates to the field of integrated circuit technology, and in particular to a method and apparatus for health assessment of a high-temperature aging test chamber for integrated circuits. Background Technology

[0002] High-temperature test chambers are complex systems integrating multiple core functional modules such as heating, air circulation, and sealing. In modern predictive maintenance systems, the health status of the heating module, fan module, and sealing module can typically be quantitatively assessed independently using their respective algorithm models, and each module's health index can be output.

[0003] However, complex thermo-fluid-structure interaction effects exist inside high-temperature test chambers. Existing evaluation methods suffer from significant lag and bias. Specifically, they have the following shortcomings:

[0004] Deficiency 1: Ignoring the fault propagation mechanism: For example, performance degradation of the sealing module can lead to heat loss, forcing the heating module to operate under overload for extended periods. When using the static weighted average method for health status assessment, the system cannot detect this "heating risk" caused by "sealing failure" under static weights, resulting in insufficient attention to the heating module.

[0005] Second flaw: The "weakest link" assessment method suffers from severe information loss. Existing health status assessment methods adopt the module with the lowest health level as the "weakest link" in the overall health. Although this method considers the worst-case scenario, it ignores the status information of other modules, resulting in an overly one-sided and extreme assessment result that cannot fully reflect the overall condition of the equipment.

[0006] Thirdly, there is a lack of handling for uncertainties in the evaluation results: the health assessment algorithms for each module inherently contain certain errors and uncertainties. A precise value such as "health score of 0.85" cannot fully express the ambiguity of the state. Existing health status assessment methods typically process these precise values ​​directly when fusing the health scores of each module, lacking the ability to handle ambiguity such as the state possibly falling between "good" and "moderate," thus reducing the robustness of the evaluation conclusions.

[0007] Therefore, there is an urgent need to propose a comprehensive evaluation scheme that can dynamically consider the mutual influence between modules in the high-temperature test chamber and effectively handle the ambiguity of evaluation information, so as to achieve a more accurate and reliable judgment on the overall health status of the high-temperature test chamber. Summary of the Invention

[0008] The purpose of this invention is to provide a health assessment method and apparatus for a high-temperature aging test chamber for integrated circuits, which can solve at least one of the above-mentioned problems in the prior art.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] This invention provides a health assessment method for an integrated circuit high-temperature aging test chamber, wherein the method includes:

[0011] Determine the health value of each module in the test chamber, and calculate the degradation rate of each module based on the health value;

[0012] Based on the number of modules contained in the test chamber and the influence coupling coefficient between each module, a coupling influence relationship matrix is ​​constructed;

[0013] Based on the health value, degradation rate, predefined baseline weight vector, and coupling influence matrix of each module, a dynamic weight vector corresponding to the test chamber is generated.

[0014] Construct a fuzzy relation matrix for health levels; wherein, the fuzzy relation matrix for health levels includes: the membership function of each module under the evaluation level of each health state;

[0015] Based on the dynamic weight vector and the fuzzy relation matrix of health levels, a comprehensive health evaluation vector is generated; the comprehensive health evaluation vector represents the degree of certainty that the overall health status of the test chamber belongs to each evaluation level.

[0016] Based on the comprehensive health evaluation vector and the health score of the test chamber at each of the evaluation levels, the target health value of the test chamber is determined.

[0017] This invention provides a health assessment device for an integrated circuit high-temperature aging test chamber, wherein the device includes:

[0018] The first determining module is used to determine the health value of each module in the test chamber and calculate the deterioration rate of each module based on the health value;

[0019] The first construction module is used to construct a coupling influence relationship matrix based on the number of modules contained in the test chamber and the influence coupling coefficient between each module;

[0020] The first generation module is used to generate a dynamic weight vector corresponding to the test chamber based on the health value, degradation rate, predefined baseline weight vector and the coupling influence relationship matrix of each module.

[0021] The second construction module is used to construct a fuzzy relation matrix of health levels; wherein, the fuzzy relation matrix of health levels includes: the membership function of each module under the evaluation level of each health state;

[0022] The second generation module is used to generate a comprehensive health evaluation vector based on the dynamic weight vector and the health level fuzzy relation matrix; the comprehensive health evaluation vector represents the degree of certainty that the overall health status of the test chamber belongs to each evaluation level;

[0023] The second determining module is used to determine the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level.

[0024] This invention provides an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of any of the above-described integrated circuit high-temperature aging bench test chamber health assessment methods.

[0025] This invention provides a readable storage medium storing a program or instructions, which, when executed by a processor, implement the steps of any of the above-described integrated circuit high-temperature aging test chamber health assessment methods.

[0026] The health assessment scheme for the high-temperature test chamber of the integrated circuit aging bench provided in this embodiment of the invention determines the health value of each module in the test chamber and calculates the degradation rate of each module based on the health value; constructs a coupling influence relationship matrix based on the number of modules in the test chamber and the influence coupling coefficient between each module; generates a dynamic weight vector corresponding to the test chamber based on the health value, degradation rate, predefined benchmark weight vector, and coupling influence relationship matrix of each module; constructs a fuzzy relationship matrix of health levels; generates a comprehensive health evaluation vector based on the dynamic weight vector and the fuzzy relationship matrix of health levels; and determines the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level. Through the health assessment scheme for the high-temperature test chamber of the integrated circuit aging bench provided in this embodiment of the invention, firstly, by introducing dynamic weights, the importance of each module in the comprehensive evaluation can be adjusted according to the real-time health status of each module; and secondly, by constructing a coupling influence relationship matrix to simulate the coupling influence relationship between each module in the test chamber, it can overcome the shortcomings of the traditional static weight method, which cannot reflect changes in operating conditions, making the obtained health assessment results more accurate and more in line with physical reality. Secondly, by introducing a fuzzy relation matrix for health levels, the inherent uncertainty and fuzziness in the health assessment results of individual modules can be effectively handled. A precise input value can be mapped to a fuzzy membership distribution, making the assessment process insensitive to small input fluctuations, thereby making the final assessment conclusion more stable and reliable. Attached Figure Description

[0027] Figure 1This is a flowchart illustrating the steps of a health assessment method for an integrated circuit high-temperature aging bench test chamber according to an embodiment of this application.

[0028] Figure 2 This is a flowchart of a fault-tolerant control method for a high-temperature aging test chamber for integrated circuits provided in an embodiment of this application;

[0029] Figure 3 This is a flowchart illustrating the fault-tolerant control method for the high-temperature aging test chamber of integrated circuits provided in this application embodiment;

[0030] Figure 4 This is a structural diagram of the hybrid spatiotemporal encoder provided in the embodiments of this application;

[0031] Figure 5 This is a network structure diagram of hybrid spatiotemporal coding and multi-task collaborative reconstruction provided in the embodiments of this application;

[0032] Figure 6 This is a structural block diagram of a health assessment device for an integrated circuit high-temperature aging bench test chamber, according to an embodiment of this application. Detailed Implementation

[0033] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0034] This invention provides a health assessment scheme for a high-temperature aging test chamber for integrated circuits. This scheme evaluates the health status of the high-temperature test chamber based on dynamic weights and fuzzy comprehensive evaluation. The scheme uses the health assessment results of each independent module within the high-temperature aging test chamber as input, and achieves dual dynamic adjustment of weights by constructing a "coupling influence matrix" and a "deterioration gradient factor." The main steps are summarized as follows: Input vectorization: Obtain the real-time health of the three modules and construct a time series. Two-dimensional feature extraction: Calculate the "health deviation" and "health deterioration rate." Coupling variable weight calculation: Calculate the "load pressure" of each module on other modules using the coupling influence matrix, generating dynamic weights. Fuzzy comprehensive evaluation: Introduce a membership function to handle the uncertainty of the assessment. Initial fault cause diagnosis: Based on the weight offset, distinguish between "intrinsic faults" and "affected faults."

[0035] The following description, in conjunction with the accompanying drawings, details the health assessment scheme for the high-temperature aging bench test chamber for integrated circuits provided in this application through specific embodiments and application scenarios.

[0036] As attached Figure 1 As shown, the health assessment method for the integrated circuit high-temperature aging test chamber according to an embodiment of this application includes the following steps:

[0037] Step 101: Determine the health value of each module in the test chamber, and calculate the degradation rate of each module based on the health value.

[0038] The health assessment method for the high-temperature aging bench test chamber of the integrated circuit provided in this embodiment of the invention is applied to an electronic device. The electronic device includes a processor and a memory. The memory stores a health assessment program or instruction for the high-temperature aging bench test chamber of the integrated circuit. When the processor executes the health assessment program or instruction for the high-temperature aging bench test chamber of the integrated circuit, the health assessment method flow for the high-temperature aging bench test chamber of the integrated circuit is realized.

[0039] It should be noted that the health assessment scheme for the integrated circuit high-temperature aging bench test chamber provided in this application embodiment is not only applicable to the health assessment of the test chamber, but also applicable to the health status assessment of other complex electromechanical systems composed of multiple modules, such as CNC machine tools and wind turbines.

[0040] In one optional embodiment, the method for determining the health value of each module in the test chamber and calculating the corresponding degradation rate of each module based on the health value can be as follows: for each module in the test chamber, determine the difference between the current health value of the module and the health value collected in the previous time window; and determine the degradation rate of the module by the ratio of the difference to the duration of the collection time window.

[0041] In actual implementation, the quantitative health index, i.e. the health value, at a certain moment can be obtained from the independent health assessment algorithm of each module. Assuming that at time t, the normalized health index is obtained from the independent health status algorithm of each module, with a range of [0,1], where 1 indicates that the module health status is optimal.

[0042] Taking the test chamber, which includes a heating module, a fan module, and a sealing module, as an example, the health values ​​of the three modules are obtained as follows. The health indicators of the three modules are represented as follows, and the values ​​corresponding to the three health indicators are the health values.

[0043] Heating module health status: H heat

[0044] Fan module health: H fan

[0045] Sealing module health status: H seal

[0046] To extract more information from the limited data, a degradation gradient is introduced into the input data. A time window Δt is defined, and the degradation rate v of each module is calculated. i (t):

[0047]

[0048] If v iA value greater than 0 indicates that health is declining.

[0049] In this step, the above formula is used to calculate the degradation rate of each module based on the health value of each module.

[0050] Step 102: Based on the number of modules contained in the test chamber and the influence coupling coefficient between each module, construct the coupling influence relationship matrix.

[0051] The constructed coupling influence matrix is ​​the coupling influence matrix C based on the operating mechanism.

[0052] In one optional embodiment, constructing the coupling influence matrix based on the number of modules contained in the test chamber and the influence coupling coefficient between each module may include the following sub-steps:

[0053] Sub-step 1: Determine the size of the coupling influence matrix based on the number of modules contained in the test chamber;

[0054] Wherein, the coupling influence relationship matrix is ​​an N×N matrix, where N is the number of modules;

[0055] Sub-step 2: Combine the influence coupling coefficients between modules with the correlation relationships between modules in pairs, and use them as elements in the coupling influence relationship matrix.

[0056] In this embodiment, considering that the weight vector is not static but dynamically adjusted according to the real-time health status of each module, a coupling influence matrix C is introduced. Matrix C defines the impact of the performance degradation of module j on the weight of module i. Since the test chamber includes three modules, and the health values ​​of the three modules are inputs, a 3×3 matrix C is constructed, where C... ij The coupling coefficient representing the influence of module j on module i:

[0057]

[0058] For example, C 13 This represents the coupling coefficient between the sealing module and the heating module. Due to the strong coupling between the two, it can be assigned a value of 0.8. This is because the failure of the sealing module will lead to an increase in the load on the heating module and a sharp increase in the risk of overload. Therefore, the weight of the heating module must be given special attention.

[0059] C 12 This represents the coupling coefficient between the fan module and the heating module, which can be assigned a value of 0.6, because reduced air circulation inside the test chamber can lead to localized overheating.

[0060] C 21 C 31 Each can be assigned a value of 0.1, because a failure in the heating module has a relatively small impact on the fan module and the sealing module. 21 C 31The corresponding influence coupling is weak coupling.

[0061] Step 103: Based on the health value, degradation rate, predefined baseline weight vector, and coupling influence matrix of each module, generate the dynamic weight vector corresponding to the test chamber.

[0062] Most variable weighting methods are simple linear additions. This application uses an exponential state-variable weighting vector algorithm to generate a dynamic weight vector corresponding to the test chamber, so as to achieve an amplification effect for more severe faults.

[0063] Define the baseline weight vector W i 0 The importance of each module to overall performance under ideal conditions can be determined by using the analytic hierarchy process or by inviting domain experts to score the data, thus obtaining a set of benchmark weight vectors W. i 0 ={W heat 0 W fan 0 W seal 0 The baseline weights represent the inherent importance of each module. Based on the predefined baseline weight vector, the health values ​​and degradation rates of each module, the dynamic weight vector corresponding to the test chamber is generated.

[0064] In one optional embodiment, the method for generating the dynamic weight vector corresponding to the test chamber based on the health value, degradation rate, predefined baseline weight vector, and coupling influence matrix of each module may include the following steps:

[0065] Step 1: For each module, determine the corresponding penalty factor based on the module's health value, degradation rate, and coupling influence matrix.

[0066] In practical implementation, a feasible way to determine the penalty factor for each module based on its health value, degradation rate, and coupling influence matrix may include the following sub-steps:

[0067] Sub-step 11: For each module, calculate its own severity based on the module's health value and the preset amplitude sensitivity coefficient;

[0068] Sub-step 12: Calculate the module's own deterioration rate based on the module's degradation rate and the preset trend sensitivity coefficient;

[0069] Sub-step 13: Based on the health values ​​and coupling influence matrix of other modules in the test chamber besides the module, calculate the coupling load pressure caused by other modules to the module;

[0070] Sub-step 14: Determine the penalty factor corresponding to the module based on its own severity, its own deterioration rate, and the coupled load pressure.

[0071] The penalty factor P for each module i It consists of two parts: its own degradation level + the coupled load pressure caused by other modules. The relationship is expressed as follows:

[0072]

[0073] Wherein, α is the amplitude sensitivity coefficient, which is the degree of influence of the health status itself; β is the trend sensitivity coefficient, which is used to provide early warning of rapidly deteriorating situations.

[0074] Step 2: Calculate the dynamic weight of the module based on the penalty factor, the module's baseline weight value in the predefined baseline weight vector, and the adjustment constant.

[0075] The baseline weight vector is W i 0 ={W heat 0 W fan 0 W seal 0 The penalty factor for each module is P. i The generated dynamic weights can be represented as W. dynamic Specifically, the dynamic weights corresponding to the calculation module can be calculated using an exponential scaling function:

[0076]

[0077] Where k is an adjustment constant, the specific value of which can be flexibly adjusted according to the accuracy requirements of the experiment.

[0078] The use of an exponential state-variable weighting function is intended to introduce a strong penalty mechanism. This overcomes the "state amortization effect" of the traditional constant weighting model, ensuring that when a single critical module experiences a serious failure or is at high coupling risk, its weight can increase rapidly and non-linearly, thereby dominating the overall health assessment results and reflecting the "weakest link effect" of the system.

[0079] Step 3: Normalize the dynamic weights corresponding to each module in the test chamber to generate the dynamic weight vector corresponding to the test chamber.

[0080] Finally, normalization is performed to obtain the final dynamic weight vector W. final W final The dynamic weights W in final,i It can be represented as:

[0081]

[0082] Step 104: Construct a fuzzy relation matrix for health levels.

[0083] The fuzzy relation matrix of health levels includes the membership function of each module under the evaluation level of each health state.

[0084] In one optional embodiment, constructing the health level fuzzy relation matrix includes the following sub-steps:

[0085] Sub-step 1: Treat each module in the test chamber as an evaluation object and construct an evaluation object set; wherein the set includes N evaluation objects;

[0086] This sub-step involves constructing a factor set U, also known as the evaluation object set, i.e., U = {heating module, fan module, sealing module}. In the evaluation algorithm, this can be vectorized as U = {u1, u2, u3}.

[0087] Sub-step 2: Define the evaluation levels for Y health states;

[0088] This sub-step involves constructing an evaluation set V: defining the levels of equipment health status, i.e., V = {Excellent, Good, Average, Poor, Terrible} evaluation levels.

[0089] Sub-step 3: Based on the membership function of each module under the evaluation level of each health status, construct an N×Y health level fuzzy relation matrix.

[0090] This sub-step constructs the membership matrix, i.e., the health level fuzzy relation matrix R. Specifically, for each level (Excellent, Good, Average, Poor, Poor) in the evaluation set V, each module sets a membership function, such as a trapezoidal membership function, to convert the input precise health value H... i This is transformed into membership degrees at each level. Constructing separate membership functions based on the importance of different modules allows for the precise capture of crucial information. For example, in R... heat ={r heat-优 ,r heat-良 ,r heat-中 ,r heat-差 ,r heat-劣 Finally, the health level fuzzy relation matrix is ​​formed: the membership vectors of the three modules are arranged in rows to form a 3x5 health level fuzzy relation matrix R.

[0091] Step 105: Generate a comprehensive health evaluation vector based on the dynamic weight vector and the fuzzy relation matrix of health levels.

[0092] Among them, the comprehensive health evaluation vector represents the degree of certainty of the overall health status of the test chamber belonging to each evaluation level.

[0093] This step is the fuzzy synthesis step, which involves the dynamic weight vector W. final Performing fuzzy matrix multiplication with the health level fuzzy relation matrix R yields the final comprehensive evaluation vector B=W. final ×R.

[0094] B={b 优 ,b 良 ,b 中 ,b 差 ,b 劣}

[0095] Among them, the comprehensive evaluation vector B can also be called the comprehensive health evaluation vector, and each element b in vector B j This represents the certainty that the overall health status of the test chamber belongs to the j-th evaluation level.

[0096] Step 106: Determine the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber at each evaluation level.

[0097] Once the target health value of the test chamber is determined, it can be directly output as the overall quantitative health score of the test chamber. Alternatively, the corresponding health level can be determined based on the target health value, and the overall health level of the test chamber can be output as: Excellent, Good, etc. Of course, both can be output so that technicians can understand the health status of the test chamber in a timely manner.

[0098] This step is the defuzzification process. The comprehensive health evaluation vector B only describes the fuzzy distribution of the state. To make monitoring and analysis more intuitive, the fuzzy vector is transformed into a precise health value, and a weighted average method is used to calculate the final health value, i.e., the target health value. An example formula for calculating the target health value is as follows:

[0099]

[0100] In a preferred embodiment, the health assessment method for the high-temperature test chamber of the integrated circuit aging bench provided in this application may further include the calculation process of the weight drift amount corresponding to each module, as follows: For each module, the weight drift amount corresponding to the module is calculated based on the dynamic weight corresponding to the module and the benchmark weight value of the module in the predefined benchmark weight vector.

[0101] In actual implementation, the weight shift Δw corresponding to the module can be calculated using the following formula. i

[0102]

[0103] The calculated weight drift of each module can be used as the basis for subsequent test chamber fault type judgment.

[0104] In addition to outputting the overall health level of the integrated circuit high-temperature aging test chamber (e.g., "Good") and / or the overall quantitative health score (e.g., 82.5), the health assessment method can also provide more assessment and diagnostic reference information. Specifically, when the output overall health level is lower than a preset standard (e.g., "Good") or the quantitative score is lower than a specific threshold (e.g., 75), the diagnostic analysis trigger condition is met, and the system will automatically trigger the diagnostic analysis program and output maintenance recommendation information.

[0105] In an optional embodiment, after determining the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber at each evaluation level, the health assessment method for the integrated circuit high-temperature aging bench test chamber provided in this application embodiment further includes: a fault type judgment and maintenance suggestion generation process, as follows:

[0106] If the target health value and / or target health evaluation level of the test chamber meet the diagnostic analysis trigger conditions, the fault type of the test chamber is determined based on the health value and weight drift of each module; maintenance suggestions are generated based on the fault type.

[0107] The fault types include: internally-driven faults and coupled-affected faults. For each module, whether it has failed can be determined by whether its corresponding health value is within the normal range; if it is outside the normal range, the module is considered to have failed; if it is within the normal range, the module is considered not to have failed. The normal range can be a range preset by those skilled in the art, and the specific value can be flexibly set by those skilled in the art; this application embodiment does not impose specific limitations on this. For modules that have not failed, whether the weight drift corresponding to the module has increased abnormally can be used to determine whether other modules coupled with it have failed. Specifically, if the weight drift corresponding to the module increases abnormally, it indicates that other modules coupled with it have failed; conversely, if the weight drift corresponding to the module does not increase abnormally, it indicates that other modules coupled with it have not failed. For example, when the weight drift corresponding to the module is greater than a preset weight drift threshold, it indicates that the weight drift has increased abnormally.

[0108] Specifically, for internally-driven faults, the corresponding test chamber characteristics are: module i itself malfunctions; the output maintenance suggestion can be: replace or repair module i.

[0109] For coupled-affected faults, the corresponding test chamber characteristics are: the health status H of module i. i Within the normal range, but its Δw iAn abnormally high level of activity indicates that another module j has failed, and the importance of module i has been elevated through the coupling matrix. Module i is currently operating under high load. The recommended maintenance output is: focus on checking the source of the coupling, module j, and perform preventative maintenance on module i.

[0110] The health assessment method for an integrated circuit high-temperature aging bench test chamber provided in this invention determines the health value of each module in the test chamber and calculates the degradation rate of each module based on the health value; constructs a coupling influence relationship matrix based on the number of modules in the test chamber and the influence coupling coefficient between each module; generates a dynamic weight vector corresponding to the test chamber based on the health value, degradation rate, predefined benchmark weight vector, and coupling influence relationship matrix of each module; constructs a fuzzy relationship matrix of health levels; generates a comprehensive health evaluation vector based on the dynamic weight vector and the fuzzy relationship matrix of health levels; and determines the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level. Through the health assessment scheme for an integrated circuit high-temperature aging bench test chamber provided in this invention, firstly, by introducing dynamic weights, the importance of each module in the comprehensive assessment can be adjusted according to its real-time health status; and secondly, by constructing a coupling influence relationship matrix to simulate the coupling influence relationship between each module in the test chamber, the shortcomings of the traditional static weight method in failing to reflect changes in operating conditions can be overcome, making the obtained health assessment results more accurate and more consistent with physical reality. Secondly, by introducing a fuzzy relation matrix for health levels, the inherent uncertainty and fuzziness in the health assessment results of individual modules can be effectively handled. A precise input value can be mapped to a fuzzy membership distribution, making the assessment process insensitive to minor input fluctuations, thus resulting in a more stable and reliable final assessment conclusion. Thirdly, it provides richer decision-making information. The output is not just a simple score or grade; its comprehensive health evaluation vector B (e.g., {Excellent: 0.2, Good: 0.7, Average: 0.1, Poor: 0, Inferior: 0}) itself contains rich information, revealing the tendency of the equipment's condition. Decision-makers can use this to determine whether the equipment is "stable in a good condition" or "tends to slide towards an average condition." Furthermore, in cases of abnormal conditions, it supplements the anomaly analysis results, providing effective reference for the formulation of maintenance strategies. Fourthly, it has good versatility and scalability. The dynamic weight + fuzzy evaluation framework in this method is not only applicable to high-temperature test chambers but can also be applied to other complex electromechanical systems composed of multiple modules. Meanwhile, its dynamic weight adjustment rule base is open and can be easily modified and expanded according to the characteristics of different devices, making it highly adaptable.

[0111] This application also provides a fault-tolerant control method for an integrated circuit high-temperature aging test chamber, which can be executed after the health assessment is performed by the above-mentioned integrated circuit high-temperature aging test chamber health assessment method.

[0112] Figure 2 This application provides a flowchart of a fault-tolerant control method for a high-temperature aging test chamber for integrated circuits, which includes the following steps:

[0113] Step S201: Determine the desired heating power of the heater in the integrated circuit high temperature aging test chamber based on the temperature setting value of the heater in the integrated circuit high temperature aging test chamber;

[0114] In one embodiment of this application, determining the desired heating power of the heater in the integrated circuit high-temperature aging test chamber based on the temperature setpoint of the heater includes:

[0115] The actual temperature of the heater in the high-temperature aging test chamber of the integrated circuit is collected, and the temperature difference of the heater is determined based on the actual temperature and the temperature set value.

[0116] The desired heating power of the heater is obtained by inputting the temperature difference of the heater into an anti-integral saturation PI controller.

[0117] Step S202: By inputting the obtained operating data of the heater in the high-temperature aging test chamber of the integrated circuit into the pre-built and trained fusion prediction model, the degradation parameter prediction results of the heater are obtained, and the degradation parameter prediction results are corrected by introducing the Arrhenius model to obtain the corrected degradation parameter prediction results.

[0118] In one embodiment of this application, the degradation parameter prediction results are corrected by introducing an Arrhenius model, resulting in the following corrected degradation parameter prediction results:

[0119] By introducing the Arrhenius model, the first degradation rate of the heater at the current actual temperature and the second degradation rate at the reference temperature are calculated respectively.

[0120] Based on the first degradation rate and the second degradation rate, a temperature correction coefficient is calculated, and the degradation parameter prediction result is corrected using the temperature correction coefficient to obtain the initial corrected degradation parameter prediction result.

[0121] The initial modified degradation parameter prediction results are corrected in real time using the gradient descent algorithm to obtain the corrected degradation parameter prediction results.

[0122] In one embodiment of this application, the corrected degradation parameter prediction result includes:

[0123] It includes real-time degradation parameters that estimate resistance and power degradation rate, degradation trend curves that include estimated resistance and power degradation rate over a future period, and dynamic fault warning thresholds that include mild and severe warnings.

[0124] In one embodiment of this application, after obtaining the corrected degradation parameter prediction result, the method further includes:

[0125] When the estimated resistance exceeds the mild or severe warning level, a pre-set warning mechanism is activated to ensure the normal operation of the system.

[0126] When the deviation between the estimated resistance and the actual measured value exceeds a set threshold, the prediction deviation correction mechanism is activated. The actual measured value is used to update the operating data of the heater input to the trained fusion prediction model. At the same time, the parameters introduced into the Arrhenius model are fine-tuned so that the deviation between the corrected estimated resistance and the actual measured value does not exceed the set threshold.

[0127] Step S203: Based on the expected heating power of the heater and the predicted result of the corrected degradation parameters, the current error of the heater is obtained, and the current error of the heater and the predicted result of the corrected degradation parameters are used to perform fault-tolerant control on the integrated circuit high-temperature aging test chamber.

[0128] In one embodiment of this application, fault-tolerant control of the integrated circuit high-temperature aging test chamber is performed using the current error of the heater and the predicted result of the corrected degradation parameters, including:

[0129] Using the current error of the heater and the predicted result of the corrected degradation parameter, a current control law for heating the heater is calculated so that the heater is heated according to the current control law, thereby obtaining the actual current of the heater;

[0130] Using the actual current of the heater, it is determined whether fault-tolerant control is required for the integrated circuit high-temperature aging test chamber. If it is determined that fault-tolerant control is required for the integrated circuit high-temperature aging test chamber, the fault warning information is further used to determine the type of fault-tolerant control.

[0131] Based on the determined fault-tolerant control type, fault-tolerant control is applied to the high-temperature aging test chamber for the integrated circuit.

[0132] In one embodiment of this application, the current control law for heating the heater is calculated using the current error of the heater and the predicted result of the corrected degradation parameters, including:

[0133] Using the current error and the rate of change of the current error of the heater, the sliding surface is calculated, and using the sliding surface, the basic control gain term and the exponential decay term are calculated respectively.

[0134] Using the predicted results of the corrected degradation parameters, the degradation compensation term is calculated;

[0135] By accumulating the basic control gain term, the exponential decay term, and the degradation compensation term, a current control law for heating the heater is obtained.

[0136] The following is combined with Figures 3-5 The embodiments of this application will be further explained and described.

[0137] Figure 3 The flowchart of the fault-tolerant control method for the high-temperature aging test chamber of integrated circuits provided in this application embodiment is as follows: Figure 3 As shown, it includes two parts: outer loop temperature control and inner loop power / current control.

[0138] Part 1: Outer Loop Temperature Control: As the top-level control module of the system, the core task of the outer loop temperature control is to calculate the expected power output of the heater based on the temperature target required by the experiment, and to provide a clear control direction for the inner loop. Its design details directly determine the final accuracy of temperature control.

[0139] Temperature error calculation: The input signal includes "temperature setpoint T" ref (Preset by the test program, supporting stepped heating / constant temperature / cooling modes, such as heating at 5℃ / min to 100℃ and holding at that temperature for 2 hours) and "Actual temperature T" act (Data is collected by distributed thermocouples inside the chamber, positioned at key locations around the specimen, and the average value is taken to eliminate the influence of uneven temperature distribution). To avoid sensor noise (such as instantaneous jumps), T... act A first-order low-pass filter (cutoff frequency 0.1Hz) is used, and then the formula is applied. Calculate the temperature error to ensure the error signal is smooth and reliable (fluctuation ≤ ±0.2℃).

[0140] Anti-integral saturation PI controller: Since the high-temperature test chamber has no active cooling device and relies on natural heat dissipation for cooling, the control input (heating power) can only be "increased" and not "decreased." The derivative element is prone to control mismatch during the cooling phase (e.g., the derivative output triggers heating when the temperature drops, which actually delays cooling). Therefore, a PI controller is adopted, and an "integral separation" anti-saturation strategy is introduced:

[0141] when|e T |>5℃ (large error, such as during the heating stage): Only the proportional element (P gain) is activated to quickly increase the heating power and shorten the heating time;

[0142] when|e T |≤5℃ (small error, such as during the heat preservation stage): Activate the proportional-integral circuit (I gain) to eliminate steady-state error through integration (such as temperature deviation ≤±0.5℃ during the heat preservation stage) and avoid temperature overshoot caused by integral saturation (overshoot ≤2℃).

[0143] When the heating power reaches the upper limit, the controller automatically pauses the integral calculation (freezes the current integral value) and only retains the proportional adjustment: to avoid the continuous accumulation of integral terms (i.e., "integral saturation") caused by "the temperature has not reached the target but the power has been saturated"; when the temperature rises and the power demand is lower than the upper limit, the integral action is resumed to ensure that it can quickly converge to the target value after exiting the saturation state.

[0144] Desired power output P ref The output of the anti-integral saturation PI controller is "the desired heating power P". ref Its value range is dynamically adjusted based on the heater's rated power (1000W) and the testing phase:

[0145] Warming phase: Rapidly increase the temperature inside the chamber and ensure a stable heating rate (e.g., 5℃ / min, with a deviation ≤ ±0.5℃ / min).

[0146] Insulation stage: It only compensates for heat loss from the cabinet (heat dissipation power of about 200W) and maintains stable temperature;

[0147] Cooling phase: P ref =0, turn off heating, rely on natural heat dissipation to cool down, and ensure that the cooling rate meets the test requirements (e.g., 2℃ / min, deviation ≤ ±0.3℃ / min).

[0148] Part Two: Inner Loop Power / Current Control: The power / current inner loop, as the system's underlying execution module, deploys the core algorithm of this application (adaptive sliding mode control). Its task is to quickly offset local disturbances such as heater degradation and power supply fluctuations, ensuring that the actual power accurately tracks the desired power, thus guaranteeing temperature stability from the source. This is based on the heater's "pure resistive load" characteristic (power and current satisfy P=I). 2 R (where R is the heater resistance) This application uses closed-loop control to stabilize the current flowing through the heater, ensuring that the power accurately tracks the desired target from the source, while also offsetting local disturbances such as degradation and power fluctuations.

[0149] (1) Logic for converting power error to current target

[0150] The control objective of the inner loop changes from "tracking the desired power P" to "tracking the desired power P". ref "Transformed into "tracking the desired current I" refThe core principle is to establish a dynamic relationship between power and current based on the state of resistor degradation, thereby avoiding control deviations caused by heater resistor degradation.

[0151] a. Calculation of expected current:

[0152] According to the theoretical relationship between power and current, P=I 2 R, Derivation of the formula for the desired current:

[0153] Among them, R est The "current estimated resistance of the heater" output by the parameter degradation prediction layer (dynamically updated with degradation), P ref This refers to the "desired heating power" output from the outer temperature loop.

[0154] Example: If P ref =500W, R after degradation est =1.2R0 (R0 is the initial resistance), then By dynamically adjusting I ref To offset the power loss caused by increased resistance.

[0155] b. Current error calculation:

[0156] Collect the actual current I of the heater act Calculate the current error:

[0157] Compared to "power error", current error more directly reflects the energy input status at the load end, which can reduce "power calculation lag" (such as power error calculation deviation caused by voltage fluctuations) and improve control response speed.

[0158] (2) Adaptive sliding mode current controller

[0159] Leveraging the robustness of adaptive sliding mode, the sliding surface design and control law are optimized for current control objectives. The core principle is to dynamically adapt to the heater's degradation state in real time through "current error," ensuring no current overshoot and no chattering during tracking. Specific design details are as follows: Figure 4 As shown.

[0160] a. Sliding surface design:

[0161] Abandoning the traditional power sliding surface, a dual-state sliding surface of "current error + current change rate" is adopted to enhance the tracking capability of current dynamics:

[0162]

[0163] in, λ is the rate of change of current error (calculated in real time using a differential algorithm), and λ is the slope of the sliding surface (which varies with R). est Dynamic adjustment: Rest As R increases, λ increases synchronously, improving the current response speed; est When stable, λ decreases to avoid current overshoot.

[0164] b. Current control law (suppresses chattering + resists degradation):

[0165] A composite control law combining an exponential reaching law and a degradation parameter correction is used to control the actuator's actual output current I. act Tracking target value I ref This eliminates high-frequency chattering in sliding mode and also counteracts changes in load characteristics caused by degradation.

[0166]

[0167] Meaning and function of each parameter:

[0168] k1, k2: Basic control gain (dynamically adjusted according to the current level; in high current scenarios, k1 and k2 increase synchronously to ensure matching control strength).

[0169] : Exponential decay term (when At that time, this term rapidly approaches 0, eliminating current chattering.

[0170] Δu deg Degradation compensation term (based on R) est Calculation of deviation from initial resistance R0: This compensates for voltage loss caused by increased resistance in advance, preventing the current from failing to track the target due to "insufficient voltage".

[0171] Online parameter estimation (real-time correction R) est ):

[0172] Combined with current sampling value I act The voltage sampling value U across the heater act R is corrected in real time using the gradient descent algorithm. est :

[0173]

[0174] in, To estimate the step size (a small value ensures stable estimation), R is made using this formula. est Real-time approximation of the actual resistance value ensures I ref Calculation accuracy is improved to avoid current control failure caused by resistance estimation errors.

[0175] (3) Collaboration with other modules

[0176] R output of the degradation prediction layer est With power degradation ΔPdeg Real-time input adaptive sliding mode controller:

[0177] aR est Used to correct I ref Calculate (to avoid increased resistance leading to I) ref Low power (insufficient power).

[0178] b.ΔP deg Used to adjust the degradation compensation term Δu deg (ΔP) deg When it increases, Δu deg Synchronous increase to ensure that the current control force matches the degree of degradation.

[0179] When the fault-tolerant module detects an "inner loop anomaly" (judgment criterion: current error |e) I |>10%I ref Or current fluctuation amplitude >15% ref ), triggering the following fault-tolerant actions:

[0180] a. If the fault is "current sampling failure", switch to the backup current sampling circuit, and simultaneously use the degradation prediction R... est With voltage sampling value U act Estimate To ensure uninterrupted current feedback;

[0181] b. If the error is "current regulation module failure", switch to the backup current regulation module (same specifications as the main module, pre-calibrated) and reset the adaptive sliding mode controller parameters.

[0182] c. If the error is "heater failure", switch to the backup heater and reset the degradation prediction layer.

[0183] Among them, the parameter degradation prediction model in the inner-loop power / current control: The degradation parameter prediction module is the core of "early detection of degradation, guidance of control and fault tolerance". Through a closed-loop process of "data acquisition → preprocessing → fusion modeling → result output → feedback correction", it achieves accurate prediction of heater resistance and temperature sensor errors. The specific design is as follows: Figure 5 As shown:

[0184] (1) Data acquisition and preprocessing

[0185] ① Data Acquisition Parameters and Hardware Configuration

[0186] Based on the degradation characteristics of key components of the high-temperature test chamber, the core parameters to be collected and the hardware requirements are determined:

[0187]

[0188] ② Data preprocessing process

[0189] The raw data collected contains noise (such as voltage fluctuations caused by electromagnetic interference) and missing data (such as momentary sensor disconnection), requiring three levels of preprocessing to ensure data validity.

[0190] a. Outlier removal: The “3σ criterion” is used to identify outlier data (such as voltage instantaneously exceeding the rated value by 120%), and the moving average of the five adjacent data points is used to replace them;

[0191] b. Noise filtering: Kalman filtering (to suppress high-frequency electromagnetic noise) is used for voltage and current signals, and first-order low-pass filtering (cutoff frequency 0.1Hz, to eliminate interference from ambient temperature fluctuations) is used for temperature signals.

[0192] c. Data normalization: Map all parameters to the [0,1] interval (e.g., ... U mac U min (This is ±20% of the heater's rated voltage) to avoid affecting the model training accuracy due to differences in dimensions (such as voltage V, time min).

[0193] (2) “LSTM+Arrhenius” fusion prediction model

[0194] The architecture adopts a "serialized fusion" approach: first, the nonlinear temporal law of degradation is learned through LSTM, and then the degradation rate under high temperature environment is corrected through the Arrhenius model, which takes into account both the generalization of data-driven approaches and the physical interpretability of model-driven approaches.

[0195] ① First stage: LSTM neural network (data-driven layer)

[0196] Function: Based on historical operating data, fit the relationship between heater resistance R and time t. run The nonlinear degradation curve.

[0197] Input layer: Dimensions are [number of samples, time step, number of features], where "time step" takes historical data from the past 60 minutes (i.e., 60 time points, corresponding to t). run (1-minute interval); Number of features: 4 (normalized U) norm I norm T norm t run,norm );

[0198] Hidden layers: 2 layers of LSTM units, 32 neurons per layer, using the ReLU activation function to avoid gradient vanishing;

[0199] Output layer: 1 neuron, outputting "predicted heater resistance R for the next 10 minutes". LSTM ”;

[0200] Training strategy: Dataset partitioning: 70% of historical data is used for training, 20% for validation, and 10% for testing;

[0201] Loss function: Mean Squared Error (MSE), i.e. , where R pred To predict the resistance value, R true This is the measured resistance value;

[0202] Optimizer: Adam optimizer, with an initial learning rate of 0.001 that decays by 10% every 100 rounds to ensure training convergence and avoid overfitting.

[0203] ② Second stage: Arrhenius model (physical correction layer)

[0204] Function: Based on the physical characteristics of high-temperature environments, correct the prediction results of LSTM and solve the problem of "increased prediction bias of LSTM under extreme high temperatures".

[0205] Arrhenius model formula:

[0206] Degradation rate k and absolute temperature T abs ( The relationship is:

[0207]

[0208] Where: A: Pre-exponential factor (obtained from heater material handbook);

[0209] E a Activation energy (determined through high-temperature accelerated aging tests);

[0210] R g Gas constant: 8.314 J / (mol·K);

[0211] Correction logic: Calculate the "temperature correction factor" ", where k current k is the degradation rate at the current temperature. ref The degradation rate at a reference temperature (e.g., 100°C);

[0212] Correct the LSTM prediction results with α:

[0213] (3) Prediction result output and early warning mechanism

[0214] ① The core output parameter module updates the prediction results every 10 minutes, outputting three types of key information:

[0215] Real-time degradation parameter: R est (Estimated resistance of heater) (Power degradation, P)rated (Rated power of the heater).

[0216] Degradation trend curve: Outputs R for the next 1 hour est ΔP deg The change curve provides the control module with "long-term degradation prediction";

[0217] Fault warning threshold: Based on component failure criteria (e.g., heater resistance exceeding 120% of the initial value is considered a near-fault), a dynamic warning threshold is generated by combining prediction results—when R... est A "mild warning" is triggered when R is ≥1.15R0 (where R0 is the initial resistance); when R... est When the value is ≥1.2R0, a "severe warning" is triggered.

[0218] ② Prediction bias correction mechanism

[0219] When the deviation between the predicted value and the actual measured value exceeds 5% (e.g. , When measuring the actual resistance, activate the correction to ensure prediction accuracy:

[0220] Using the actual measured value R meas Update the historical input data of the LSTM;

[0221] Fine-tuning the activation energy E of the Arrhenius model a (Adjustment range ≤ 5%), so that the corrected R est With R meas The deviation should be within 5% to avoid long-term forecast drift.

[0222] (4) Collaboration with other modules

[0223] ①Supports inner-loop adaptive sliding mode control:

[0224] R est Real-time input to the inner loop for calculation At the same time, adjust the slope of the sliding surface. (λ0 is the initial slope);

[0225] Optimize outer loop PI parameters: when When power degradation is severe, a "degradation signal" is sent to the outer loop, and the outer loop automatically increases the proportional gain K of the PI controller. p (Increase by 10%-20%) to improve temperature response speed and offset the effects of insufficient power.

[0226] ② Coordination with fault-tolerant control module

[0227] Provides a basis for preventative fault tolerance: When a "severe warning" is triggered, a "heater is about to fail" signal is sent to the fault tolerance module; the fault tolerance module preheats the backup heater and loads the initial resistance parameters of the backup heater, shortening the original "fault switching time ≤ 0.5 seconds" to ≤ 0.2 seconds, thus avoiding temperature runaway.

[0228] Assisted fault location: When the fault-tolerant module detects an abnormal current (e.g., current is 0), it combines the degradation prediction's "R" est Historical trends (such as the recent 1hR) est (Continued increase) can be quickly identified as "gradual heater failure caused by degradation", avoiding the problem of "misjudging the fault type based solely on real-time signals" in the original solution, and improving the accuracy of fault-tolerant decision-making.

[0229] Figure 6 The structural block diagram of the health assessment device for the integrated circuit high-temperature aging bench test chamber in this application embodiment is shown.

[0230] The integrated circuit high-temperature aging bench test chamber health assessment device provided in this application includes the following functional modules:

[0231] The first determining module 601 is used to determine the health value of each module in the test chamber and calculate the deterioration rate of each module based on the health value;

[0232] The first construction module 602 is used to construct a coupling influence relationship matrix based on the number of modules contained in the test chamber and the influence coupling coefficient between each module;

[0233] The first generation module 603 is used to generate a dynamic weight vector corresponding to the test chamber based on the health value, degradation rate, predefined baseline weight vector and the coupling influence relationship matrix of each module.

[0234] The second construction module 604 is used to construct a health level fuzzy relation matrix; wherein, the health level fuzzy relation matrix includes: the membership function of each module under the evaluation level of each health state;

[0235] The second generation module 605 is used to generate a comprehensive health evaluation vector based on the dynamic weight vector and the health level fuzzy relation matrix; the comprehensive health evaluation vector represents the degree of certainty that the overall health status of the test chamber belongs to each evaluation level;

[0236] The second determining module 606 is used to determine the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level.

[0237] Optionally, the first determining module includes:

[0238] The first submodule is used to determine the difference between the current health value of each module in the test chamber and the health value collected in the previous time window.

[0239] The second submodule is used to determine the degradation rate of the module by dividing the difference by the duration of the acquisition time window.

[0240] Optionally, the first generation module includes:

[0241] The third submodule is used to determine the penalty factor corresponding to each module based on the health value, degradation rate and coupling influence matrix of each module.

[0242] The fourth submodule is used to calculate the dynamic weight corresponding to the module based on the penalty factor, the module's baseline weight value in the predefined baseline weight vector, and the adjustment constant.

[0243] The fifth submodule is used to normalize the dynamic weights corresponding to each module in the test chamber and generate the dynamic weight vector corresponding to the test chamber.

[0244] Optionally, the third submodule is specifically used for:

[0245] For each module, the severity of the module is calculated based on the module's health value and a preset amplitude sensitivity coefficient.

[0246] The self-deterioration rate of the module is calculated based on the degradation rate of the module and a preset trend sensitivity coefficient;

[0247] Based on the health values ​​of other modules in the test chamber besides the module mentioned above and the coupling influence relationship matrix, calculate the coupling load pressure exerted by other modules on the module mentioned above;

[0248] The penalty factor corresponding to the module is determined based on its own severity, its own deterioration rate, and the coupled load pressure.

[0249] Optionally, the second building module is specifically used for:

[0250] Each module in the test chamber is considered as an evaluation object, and an evaluation object set is constructed; wherein, the set includes N evaluation objects;

[0251] Define the evaluation levels of Y health states;

[0252] Based on the membership function of each module under each health status evaluation level, an N×Y health level fuzzy relation matrix is ​​constructed.

[0253] Optionally, the first building module is specifically used for:

[0254] The size of the coupling influence matrix is ​​determined based on the number of modules contained in the test chamber; wherein the coupling influence matrix is ​​an N×N matrix, and N is the number of modules;

[0255] The influence coupling coefficient between modules is paired with the correlation relationship between modules and used as each element in the coupling influence relationship matrix.

[0256] Optionally, the device further includes:

[0257] The weight calculation module is used to calculate the weight drift of each module based on the dynamic weight of the module and the benchmark weight value of the module in the predefined benchmark weight vector.

[0258] Optionally, the device further includes:

[0259] The type determination module is used to determine the fault type of the test chamber after the second determination module determines the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level. When the target health value of the test chamber and / or the target health evaluation level of the test chamber meet the diagnostic analysis triggering conditions, the module determines the fault type of the test chamber based on the health value and weight drift corresponding to each module. The fault type includes: internal cause-dominated fault and coupled-affected fault.

[0260] A suggestion generation module is used to generate maintenance suggestions based on the fault type.

[0261] In the embodiments of this application Figure 6 The integrated circuit high-temperature aging test chamber health assessment device shown can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0262] The embodiments provided in this application Figure 6 The integrated circuit high-temperature aging bench test chamber health assessment device shown can achieve Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0263] Optionally, embodiments of this application also provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the processes performed by the aforementioned integrated circuit high-temperature aging bench test chamber health assessment device and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0264] It should be noted that the electronic device in this application embodiment includes the server described above.

[0265] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0266] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0267] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A health assessment method for an integrated circuit high-temperature aging test chamber, characterized in that, The method includes: Determine the health value of each module in the test chamber, and calculate the degradation rate of each module based on the health value; Based on the number of modules contained in the test chamber and the influence coupling coefficient between each module, a coupling influence relationship matrix is ​​constructed; For each module, the severity of the module is calculated based on the module's health value and a preset amplitude sensitivity coefficient. The self-deterioration rate of the module is calculated based on the degradation rate of the module and a preset trend sensitivity coefficient; Based on the health values ​​of other modules in the test chamber besides the module mentioned above and the coupling influence relationship matrix, calculate the coupling load pressure exerted by other modules on the module mentioned above; Based on its own severity, its own deterioration rate, and the coupled load pressure, the penalty factor corresponding to the module is determined; Based on the penalty factor, the baseline weight value of the module in the predefined baseline weight vector, and the adjustment constant, the dynamic weight corresponding to the module is calculated; The dynamic weights corresponding to each module in the test chamber are normalized to generate the dynamic weight vector corresponding to the test chamber. Construct a fuzzy relation matrix for health levels; wherein, the fuzzy relation matrix for health levels includes: the membership function of each module under the evaluation level of each health state; Based on the dynamic weight vector and the fuzzy relation matrix of health levels, a comprehensive health evaluation vector is generated; the comprehensive health evaluation vector represents the degree of certainty that the overall health status of the test chamber belongs to each evaluation level. Based on the comprehensive health evaluation vector and the health score of the test chamber at each of the evaluation levels, the target health value of the test chamber is determined.

2. The method according to claim 1, characterized in that, The steps of determining the health value of each module in the test chamber and calculating the corresponding degradation rate of each module based on the health value include: For each module in the test chamber, determine the difference between the current health value of the module and the health value collected in the previous time window; The quotient of the difference and the duration of the acquisition time window is determined as the degradation rate of the module.

3. The method according to claim 1, characterized in that, The steps for constructing a fuzzy relation matrix for health levels include: Each module in the test chamber is considered as an evaluation object, and an evaluation object set is constructed; wherein, the set includes N evaluation objects; Define the evaluation levels of Y health states; Based on the membership function of each module under each health status evaluation level, an N×Y health level fuzzy relation matrix is ​​constructed.

4. The method according to claim 1, characterized in that, The steps for constructing a coupling influence matrix based on the number of modules contained in the test chamber and the influence coupling coefficients between the modules include: The size of the coupling influence matrix is ​​determined based on the number of modules contained in the test chamber; wherein the coupling influence matrix is ​​an N×N matrix, and N is the number of modules; The influence coupling coefficient between modules is paired with the correlation relationship between modules and used as each element in the coupling influence relationship matrix.

5. The method according to claim 1, characterized in that, The method further includes: For each module, the weight drift is calculated based on the dynamic weight of the module and the baseline weight value of the module in the predefined baseline weight vector.

6. The method according to claim 5, characterized in that, After determining the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber at each evaluation level, the method further includes: When the target health value and / or the target health evaluation level of the test chamber meet the diagnostic analysis triggering conditions, the fault type of the test chamber is determined based on the health value and weight drift of each module. The fault type includes: internal cause-dominated fault and coupled-affected fault. Maintenance recommendations are generated based on the fault type.

7. A health assessment device for a high-temperature aging test chamber for integrated circuits, characterized in that, The device includes: The first determining module is used to determine the health value of each module in the test chamber and calculate the deterioration rate of each module based on the health value; The first construction module is used to construct a coupling influence relationship matrix based on the number of modules contained in the test chamber and the influence coupling coefficient between each module; The first generation module includes a third sub-module, a fourth sub-module, and a fifth sub-module; The third submodule is used to calculate the severity of each module based on its health value and a preset amplitude sensitivity coefficient, calculate its degradation rate based on its degradation rate and a preset trend sensitivity coefficient, calculate the coupling load pressure exerted on the module by other modules based on the health values ​​of other modules in the test chamber and the coupling influence relationship matrix, and determine the penalty factor corresponding to the module based on its severity, degradation rate, and coupling load pressure. The fourth sub-module is used to calculate the dynamic weight corresponding to the module based on the penalty factor, the module's baseline weight value in the predefined baseline weight vector, and the adjustment constant. The fifth sub-module is used to normalize the dynamic weights corresponding to each module in the test chamber and generate the dynamic weight vector corresponding to the test chamber. The second construction module is used to construct a fuzzy relation matrix of health levels; wherein, the fuzzy relation matrix of health levels includes: the membership function of each module under the evaluation level of each health state; The second generation module is used to generate a comprehensive health evaluation vector based on the dynamic weight vector and the health level fuzzy relation matrix; the comprehensive health evaluation vector represents the degree of certainty that the overall health status of the test chamber belongs to each evaluation level; The second determining module is used to determine the target health value of the test chamber based on the comprehensive health evaluation vector and the health score of the test chamber under each evaluation level.

8. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions are executed by the processor to perform the steps of any one of the integrated circuit high-temperature aging bench test chamber health assessment methods according to claims 1-6.

Images