An electronic component noise test system and test method based on a data model

Abstract

The present invention relates to the technical field of electronic component testing, and discloses an electronic component noise testing system and a testing method based on a data model. The method includes: during the operation of the electronic component, acquiring the current working environment parameter data of the electronic component and inputting it into a pre-trained noise feature extraction model to obtain noise feature data; performing a noise comparison operation according to the noise feature data to obtain a model adjustment parameter of the noise prediction model; performing a difference degree adjustment operation according to the model adjustment parameter to obtain an adjusted noise prediction model; performing a noise prediction operation according to the adjusted noise prediction model to obtain the predicted noise feature of the electronic component. The present invention can improve the accuracy of noise testing.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic component testing, and particularly to a noise testing system and method for electronic components based on a data model. Background Art

[0002] At present, with the rapid development of technology, there is a large demand for electronic components. However, electronic components will generate noise during operation, and the noise changes with environmental conditions such as the temperature, voltage, and current of the device, such as photodetectors, triodes, noise amplifiers, etc. The noise generated by electronic components during operation will interfere with the normal operation of communication systems, especially some precision measurement systems, which have very high requirements for the noise level of electronic components during operation.

[0003] Among the existing noise testing methods, although one method can perform noise testing on various types of components, which helps to optimize the design of components to obtain low-noise and high-performance components, it does not consider the influence of environmental conditions such as the temperature, voltage, and operating current of the device on the noise level, nor does it consider establishing a noise prediction model for electronic components under working environmental conditions, and thus cannot accurately obtain the noise level of electronic components under a certain working environmental condition during testing; another method provides a testing system for a high-power device model, but does not perform noise testing and cannot provide a reference for noise level prediction.

[0004] Although the prior art can achieve obtaining the noise of electronic components, there is no good solution to accurately test the noise level of electronic components under a certain working environmental condition. Summary of the Invention

[0005] The present invention provides a noise testing system and method for electronic components based on a data model to improve the accuracy of noise testing.

[0006] In a first aspect, to solve the above technical problems, the present invention provides a method for testing the noise of electronic components based on a data model, including: during the operation of the electronic components, obtaining the current working environment parameter data of the electronic components and inputting it into a pre-trained noise feature extraction model to obtain noise feature data; performing a noise comparison operation based on the noise feature data to obtain model adjustment parameters for an initial noise prediction model; performing a difference degree adjustment operation based on the model adjustment parameters to obtain an adjusted noise prediction model; performing a noise prediction operation based on the adjusted noise prediction model to obtain the predicted noise features of the electronic components; wherein, the training process of the noise feature extraction model includes: obtaining historical working environment parameter data, where the historical working environment parameter data includes temperature, voltage, and current; performing data preprocessing and parameter range determination operations based on the historical working environment parameter data to obtain a parameter range; performing a parameter numerical interval conversion operation based on the parameter range to obtain the numerical interval corresponding to the parameter.

[0007] As an alternative implementation, the performing a noise comparison operation based on the noise feature data to obtain the model adjustment parameters for the noise prediction model includes: the calculation formula for the model adjustment parameters is: Wherein, is the degree of goodness of the model prediction, is the number of predicted noise data, is the th original noise feature data, is the th predicted noise feature data, is the preset learning rate, is the preset initial model adjustment parameter, is the model adjustment parameter.

[0008] As an alternative implementation, the performing a difference degree adjustment operation based on the model adjustment parameters to obtain an adjusted noise prediction model includes: the formula for the difference degree adjustment operation is: Wherein, is the function of the adjusted noise prediction model, is the preset coefficient, is the noise feature data, is the model adjustment parameter, is the error term.

[0009] As an alternative implementation, the training process of the noise prediction model includes: obtaining historical noise feature data; performing an operation of establishing a judgment set based on the historical noise feature data to obtain an evaluation set; performing an operation of constructing a matrix based on the evaluation set to obtain an evaluation matrix; performing an operation of calculating an entropy value based on the evaluation matrix to obtain an entropy value; performing an operation of calculating a goodness measure based on the entropy value to obtain a goodness measure index; performing an operation of constructing a model based on the evaluation matrix, the entropy value, and the goodness measure index to obtain a noise prediction model; where the evaluation matrix is: where, is the evaluation matrix, the th row and the

[0010] As an alternative implementation, the operation of calculating an entropy value based on the evaluation matrix to obtain an entropy value includes: the entropy value calculation formula is: where, is the entropy value, is the evaluation matrix value in the th row and the is the total number of matrix values in the evaluation matrix.

[0011] As an alternative implementation, the operation of calculating a goodness measure based on the entropy value to obtain a goodness measure index includes: the goodness measure calculation formula is: where, is the goodness measure index, is the entropy value.

[0012] As an alternative implementation, the operation of constructing a model based on the evaluation matrix, the entropy value, and the goodness measure index to obtain a noise prediction model includes: the model construction formula is: where, is the noise prediction model, is the entropy value matrix under the subjective weight set, is the entropy value matrix under the objective weight set, W1 is the subjective weight set, W2 is the objective weight set, is the entropy value, is a preset proportionality coefficient, is the goodness measure index.

[0013] As an alternative implementation, the operation of performing a parameter numerical interval conversion based on the parameter range to obtain the numerical interval corresponding to the parameter includes: the parameter numerical interval conversion formula is: wherein, is the numerical interval, is the minimum value of the parameter range, is the maximum value of the parameter range, is the th data in the parameter range.

[0014] As an alternative implementation, performing a support vector machine regression operation according to the numerical interval to obtain a noise feature extraction model, including: the support vector machine regression formula is: wherein, is the noise feature extraction model, is the number of support vectors, and is a preset Lagrange multiplier, is the kernel function, is the bias term, is the newly input sample data, is the th data in the numerical interval.

[0015] In a second aspect, the present invention provides an electronic component noise test system based on a data model, including: a data acquisition module for acquiring current working environment parameter data of the electronic component during the operation of the electronic component; a model establishment module for establishing a noise feature extraction model and a noise prediction model; a model optimization module for optimizing the noise prediction model to obtain an adjusted noise prediction model; a noise prediction module for performing a noise prediction operation according to the adjusted noise prediction model to obtain the predicted noise feature of the electronic component; wherein, the training process of the noise feature extraction model includes: acquiring historical working environment parameter data, the historical working environment parameter data including temperature, voltage, and current; performing data preprocessing and parameter range determination operations according to the historical working environment parameter data to obtain a parameter range; performing parameter numerical interval conversion operations according to the parameter range to obtain a numerical interval corresponding to the parameter; performing a support vector machine regression operation according to the numerical interval to obtain a noise feature extraction model.

[0016] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the method for testing the noise of an electronic component based on a data model as described above.

[0017] Fourthly, the present invention also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method for testing the noise of electronic components based on a data model as described above.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method for testing the noise of electronic components based on a data model, including: during the operation of the electronic component, obtaining the current working environment parameter data of the electronic component and inputting it into a pre-trained noise feature extraction model to obtain noise feature data; performing a noise comparison operation according to the noise feature data to obtain a model adjustment parameter of the noise prediction model; performing a difference degree adjustment operation according to the model adjustment parameter to obtain an adjusted noise prediction model; performing a noise prediction operation according to the adjusted noise prediction model to obtain the predicted noise feature of the electronic component; wherein, the training process of the noise feature extraction model includes: obtaining historical working environment parameter data, which includes temperature, voltage, and current; performing data preprocessing and parameter range determination operations according to the historical working environment parameter data to obtain a parameter range; performing a parameter numerical interval conversion operation according to the parameter range to obtain a numerical interval corresponding to the parameter; performing a support vector machine regression operation according to the numerical interval to obtain a noise feature extraction model.

[0019] In the present invention, the method for testing the noise of electronic components based on a data model has the following advantages: First, by obtaining the noise characteristic data of electronic components under different working environment parameters (such as temperature, current, voltage, etc.) and applying this data to the construction of a noise prediction model, the accuracy of noise testing can be effectively improved. This method not only reduces the common errors in traditional noise testing but also greatly reduces the difficulty of testing because the data model can provide accurate noise characteristic predictions under various environmental conditions, thus avoiding a large number of cumbersome manual tests and experimental processes. Second, this method can achieve real-time prediction of the working environment parameters of the electronic components to be detected, thereby providing a more accurate environmental condition basis for noise testing. This prediction ability can significantly improve the efficiency of noise testing and avoid the cumbersome steps of adjusting environmental parameters one by one in traditional testing. Third, by optimizing the simulation parameters, the testing process can also be made more efficient, reducing unnecessary repeated tests and saving time and resources. Implementing the method for testing the noise of electronic components according to the above method depends on the already established noise characteristic extraction model and noise prediction model, and accurate noise prediction is carried out by combining these two models. Through continuous optimization of the noise prediction model, the accuracy of testing is further improved, making the noise test results more reliable. At the same time, by predicting and adjusting the working environment parameters, not only can the accuracy of noise testing be improved, but the testing process can also be completed in a shorter time, thus greatly improving the overall testing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flowchart of a method for testing the noise of electronic components based on a data model provided by an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of the training of a noise characteristic extraction model provided by an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of the training of a noise prediction model provided by an embodiment of the present invention;

[0023] Figure 4 is a schematic structural diagram of a system for testing the noise of electronic components based on a data model provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] It should be noted that currently, with the rapid development of technology, there is a large demand for electronic components. However, there is noise in the working process of electronic components, and the noise changes with environmental conditions such as the temperature, voltage, and current of the device, such as photodetectors, triodes, noise amplifiers, etc. The noise in the working process of electronic components will interfere with the normal operation of the communication system. Especially for some precision measurement systems, the requirement for the noise level during the operation of electronic components is very high. Among the existing noise testing methods, although one can perform noise testing on various types of components, which helps to optimize the component design to obtain low-noise and high-performance components, it does not consider the influence of environmental conditions such as the temperature, voltage, and working current of the device on the noise level, nor does it consider establishing a noise prediction model for electronic components under working environmental conditions, and thus cannot accurately obtain the noise level of electronic components under a certain working environmental condition during testing; the other method, although it provides a testing system for a high-power device model, does not perform noise testing and cannot provide a reference for noise level prediction. Although the existing technology can achieve obtaining the noise of electronic components, there is no good solution to accurately test the noise level of electronic components under a certain working environmental condition.

[0026] In view of the above problems, referring to Figure 1 , the first embodiment of the present invention provides a method for testing the noise of electronic components based on a data model, including the following steps:

[0027] S1. During the operation of the electronic component, obtain the current working environmental parameter data of the electronic component and input it into a pre-trained noise feature extraction model to obtain noise feature data;

[0028] S2. According to the noise feature data, perform a noise comparison operation to obtain the model adjustment parameters of the initial noise prediction model;

[0029] S3. According to the model adjustment parameters, perform a difference degree adjustment operation to obtain an adjusted noise prediction model;

[0030] S4. According to the adjusted noise prediction model, perform a noise prediction operation to obtain the predicted noise features of the electronic component.

[0031] In step S1, during the operation of the electronic component, obtain the current working environmental parameter data of the electronic component and input it into a pre-trained noise feature extraction model to obtain noise feature data.

[0032] In the above embodiments, the test system obtains the current working environment parameter data (such as temperature, voltage, current, etc.) of the electronic component, and inputs this data into a pre-trained noise feature extraction model. The model predicts and extracts the corresponding noise feature data according to the environmental changes, so that the noise feature data can be accurately extracted. These noise feature data can be used to monitor the working state of the electronic component under different environmental conditions, discover potential faults or performance problems in advance, optimize the data distortion problem during the component test process, thereby improving the accuracy of the noise test. At the same time, by predicting the working environment parameters of the environment, the noise test efficiency can be improved and the simulation parameters can be optimized.

[0033] As Figure 2 shown, during the working process of the electronic component in step S1, the current working environment parameter data of the electronic component is obtained and input into a pre-trained noise feature extraction model to obtain noise feature data. The noise feature extraction model includes:

[0034] S11, obtaining historical working environment parameter data, where the historical working environment parameter data includes temperature, voltage, and current;

[0035] S12, performing data preprocessing and parameter range determination operations according to the historical working environment parameter data to obtain a parameter range;

[0036] S13, performing parameter value interval conversion operations according to the parameter range to obtain a numerical interval corresponding to the parameter;

[0037] S14, performing support vector machine regression operations according to the numerical interval to obtain a noise feature extraction model.

[0038] In step S12, according to the historical working environment parameter data, data preprocessing and parameter range determination operations are performed to obtain a parameter range.

[0039] It should be specifically noted that the data preprocessing is crucial, and its specific steps are as follows: First, perform data cleaning first. For missing values, if the amount is small, the corresponding records can be deleted, or they can be filled with the mean, median, or replaced with model prediction values. Then, through the box plot for outliers, identify them according to the upper and lower quartiles and the interquartile range. Mis-measured data can be directly excluded, while special extreme values need to be judged whether to be retained according to the actual situation. Finally, perform standardization operations to convert the data into a distribution with a mean of 0 and a standard deviation of 1, eliminating the unit magnitude difference. After this treatment, the data is more suitable for training the model, improving the accuracy of obtaining noise data, and providing an effective data basis for the subsequent training of the model. Among them, the formula for the standardization operation is: The meanings of the parameters inside are represents the data after standardization, represents the data before standardization, represents the mathematical expectation of the data before standardization, represents the variance of the data before standardization.

[0040] In step S13, according to the parameter range, a parameter value interval conversion operation is performed to obtain the corresponding value interval of the parameter.

[0041] In one implementation manner, the performing the parameter value interval conversion operation according to the parameter range to obtain the corresponding value interval of the parameter includes: The parameter value interval conversion formula is: where, is the value interval, is the minimum value of the parameter range, is the maximum value of the parameter range, is the th data in the parameter range.

[0042] It should be specifically noted that the parameter range is , and the parameters include current, voltage, and temperature.

[0043] In step S2, according to the noise characteristic data, a noise comparison operation is performed to obtain the model adjustment parameters of the noise prediction model.

[0044] In one implementation manner, the performing the noise comparison operation according to the noise characteristic data to obtain the model adjustment parameters of the noise prediction model includes: The calculation formula of the model adjustment parameters is: where, is the degree of goodness of the model prediction, is the number of predicted noise data, the th is the th original noise characteristic data, is the th predicted noise characteristic data, is the preset learning rate, is the preset initial model adjustment parameter,

[0045] In the above embodiments, it is first necessary to collect the noise feature data, and then use the regression analysis method in the selection of the noise prediction model. The noise prediction model can capture the relationship between the noise source and its influence, so as to provide accurate noise prediction. The adjustment of the noise prediction model is crucial. Parameters such as the learning rate and the complexity of the model will directly affect the prediction accuracy. After performing multiple noise comparison operations, the optimal model adjustment parameters are obtained, providing a basis for adjusting the parameters in the next step to optimize the noise prediction model, and finally improving the accuracy of the test noise.

[0046] Specifically, the learning rate is a very crucial hyperparameter in the process of machine learning training models. It determines the step size of parameter updates in each iteration of the model (for example, each iteration of the gradient descent algorithm). Its role is to adjust the parameters according to the gradient of the loss function with respect to the parameters, so that the value of the loss function continuously decreases. If the learning rate is too large, it may cause the model to "skip" the optimal solution during training, resulting in non-convergence or oscillation around the optimal solution; if the learning rate is too small, the training process of the model will become very slow and more iterations are required to achieve better results. In this noise comparison formula, the preset learning rate is combined with the model adjustment parameters to adjust the model. It controls the speed at which the model adjusts according to the difference between the predicted value and the actual value. When calculating the goodness of the model, the learning rate affects the update amplitude of the model adjustment parameters. If the preset learning rate is large, then when adjusting the model adjustment parameters based on the prediction error each time, the change amount of the model adjustment parameters will be relatively large, and the model can adapt to the data faster, but there are also certain risks, such as over-adjustment may lead to model instability; on the contrary, if the preset learning rate is small, the change amount of the model adjustment parameters is relatively small, the model adjusts slowly, but it can converge more stably to a better state. Balancing the speed and stability of model adjustment during model training affects the prediction effect of the model on noise data, and further affects the final calculation result of the goodness of the model.

[0047] It should also be specifically noted that regression analysis is a statistical analysis method used to study the relationships between variables. It mainly establishes a mathematical model to describe the dependence relationship between a dependent variable and one or more independent variables. In the selection of a noise prediction model, the regression analysis method plays an important role. It can help find the quantitative relationships between the factors (such as independent variables like operating current, voltage, temperature, etc.) related to the noise characteristics (dependent variable) of electronic components. The model established through regression analysis can accurately predict characteristics such as the magnitude and frequency of noise based on the specific values of these factors. This method can also evaluate the influence degree of each independent variable on the noise and help determine the key factors. This is beneficial for focusing on these key factors during model construction and optimization, thereby predicting noise more accurately and providing a reliable basis for controlling and reducing noise.

[0048] As Figure 2 shown, in step S1, according to the noise characteristic data, a noise comparison operation is performed to obtain the model adjustment parameters of the noise prediction model. The noise prediction model includes:

[0049] S21, obtaining historical noise characteristic data;

[0050] S22, according to the historical noise characteristic data, performing an operation to establish a judgment set to obtain an evaluation set;

[0051] S23, according to the evaluation set, performing an operation to construct a matrix to obtain an evaluation matrix;

[0052] S24, according to the evaluation matrix, performing an operation to calculate the entropy value to obtain the entropy value;

[0053] S25, according to the entropy value, performing an operation to calculate the goodness to obtain the goodness index;

[0054] S26, according to the evaluation matrix, the entropy value, and the goodness index, performing an operation to construct a model to obtain a noise prediction model.

[0055] In step S21, historical noise characteristic data is obtained.

[0056] It should be noted that the historical noise characteristic data is obtained by simulating the noise characteristic data of electronic components. First, a precise simulation environment that conforms to the actual working conditions is built. Based on the detailed information such as the physical characteristics, material parameters, and electrical specifications of the electronic components, after a large number of virtual time-step iterative operations, tracking the dynamic changes of multiple physical fields such as the electromagnetic field, stress field, and thermal field inside the components, capturing the acoustic wave fluctuations caused by electromagnetic vibration, thermal expansion and contraction, etc., and comprehensively analyzing from microscopic particle vibration to macroscopic acoustic wave radiation, finally calculating and outputting historical noise characteristic data that conforms to the actual situation.

[0057] In step S22, based on the historical noise feature data, an evaluation set establishment operation is performed to obtain an evaluation set.

[0058] In the above embodiment, the historical noise feature data is obtained by collecting, recording, and analyzing noise data within a certain period in the past. These data include information such as noise levels, frequency characteristics, and time-domain characteristics under different times, locations, and environmental conditions. By deeply mining and statistically analyzing these noise feature data, the relationships between noise features, noise sources, and environmental factors can be established. When establishing the evaluation set, these historical noise feature data will be used to label and classify samples of different noise types and group them according to different noise situations, thereby constructing a multi-dimensional and multi-level evaluation set. This evaluation set will serve as the basic data for training the noise prediction model, helping the model learn the mapping relationship between noise patterns and noise sources. By using this evaluation set, the trained noise prediction model can more accurately predict new noise data, thereby improving the testing of electronic component noise by this testing system.

[0059] In step S23, based on the evaluation set, a matrix construction operation is performed to obtain an evaluation matrix.

[0060] In one implementation, the evaluation matrix is: Wherein, is the evaluation matrix, The th row and th column of the evaluation matrix value.

[0061] It should be specifically noted that the evaluation set is established based on obtaining the noise values of electronic components under different working environment parameter conditions (including various environmental parameters such as different temperatures, voltages, and currents).

[0062] In step S24, based on the evaluation matrix, an entropy value calculation operation is performed to obtain an entropy value.

[0063] In one implementation, the performing the entropy value calculation operation based on the evaluation matrix to obtain an entropy value includes: The entropy value calculation formula is: Wherein, is the entropy value, is the th row and th column of the evaluation matrix value, is the total number of matrix values in the evaluation matrix.

[0064] In step S25, based on the entropy value, a goodness calculation operation is performed to obtain a goodness index.

[0065] In one embodiment, performing a goodness calculation operation based on the entropy value to obtain a goodness index, including: The goodness calculation formula is: Wherein, is the goodness index, is the entropy value.

[0066] In step S26, based on the evaluation matrix, the entropy value, and the goodness index, perform a model construction operation to obtain a noise prediction model.

[0067] In one embodiment, performing a model construction operation based on the evaluation matrix, the entropy value, and the goodness index to obtain a noise prediction model, including: The model construction formula is: Wherein, is the noise prediction model, is the entropy value matrix under the subjective weight set, is the entropy value matrix under the objective weight set, W1 is the subjective weight set, and W2 is the objective weight set, is the entropy value, is the preset proportionality coefficient, is the goodness index.

[0068] In step S3, based on the model adjustment parameters, perform a difference degree adjustment operation to obtain an adjusted noise prediction model.

[0069] In one embodiment, performing a difference degree adjustment operation based on the model adjustment parameters to obtain an adjusted noise prediction model, including: The difference degree adjustment operation formula is: Wherein, is the function of the adjusted noise prediction model, is the preset coefficient, is the noise feature data, is the model adjustment parameter, is the error term.

[0070] In the above embodiments, first, a large amount of noise data is collected and preprocessed to clean out outliers and noise points, ensuring the accuracy and representativeness of the data. This data can be obtained through sensors and monitoring devices, where the noise data includes key features such as the spectrum, intensity, and volatility of the noise. When performing the differential degree adjustment operation, first, a comparative analysis is carried out on data from different sources to find the differences between different data, and the difference information is used to optimize and adjust the parameters of the model. The weights, hyperparameters in the model are adjusted, and new features are introduced, so that the model can more accurately predict the noise performance in different situations. Through this method, the model can better adapt to diverse noise environments and improve the prediction accuracy. Through the optimization operation of this noise prediction model, the accuracy of the noise test of electronic devices can be further improved.

[0071] Specifically, the error of the noise prediction model of electronic components initially calculated by this method is 10%, which meets the engineering measurement requirements. This means that in practical applications, this prediction error is sufficient to ensure the accuracy of noise monitoring and control and can meet the requirements of most projects. However, in order to further improve the accuracy of the prediction model and provide more accurate noise prediction results in more stringent application scenarios, the optimization coefficient can be adjusted by the method in S3 to reduce the prediction error of the noise spectral density of electronic components, thereby improving the accuracy and efficiency of the entire noise control system.

[0072] S4. According to the adjusted noise prediction model, perform a noise prediction operation to obtain the predicted noise characteristics of the electronic components.

[0073] In the above embodiments, first, the operating data of electronic components under different working conditions, including multiple parameters such as current, voltage, and temperature, are collected, and combined with historical noise test data to train and optimize the model. The adjusted noise prediction model can quickly predict the noise characteristics of electronic components under specific conditions according to real-time data input. Through the optimized noise prediction model, the noise can be tested more accurately and the test efficiency can be improved.

[0074] The working process of the present invention is described below by taking a relatively common scenario as an example. Please refer to Figure 1 , Figure 1 is a schematic flow chart of a method for testing the noise of electronic components based on a data model.

[0075] Step 1: When an electronic component enters the noise test system, the system starts to obtain the current working environment parameter data of the electronic component and inputs it into the pre-trained noise feature extraction model to obtain noise feature data;

[0076] Step 2: While the system inputs the noise feature data obtained in Step 1 into the noise prediction model for testing under different working environments, the noise prediction model starts to perform optimization operations to obtain an optimized noise prediction model;

[0077] Step 3: The system uses the optimized noise prediction model as the final prediction model, starts noise detection, and transmits the obtained predicted noise features to the electronic device;

[0078] Step 4: The electronic device obtains the predicted noise features obtained from noise testing in the electronic component system and saves them to the cloud server for user reference.

[0079] In summary, the present invention provides a method for testing the noise of electronic components based on a data model, including: during the operation of the electronic components, obtaining the current working environment parameter data of the electronic components and inputting it into a pre-trained noise feature extraction model to obtain noise feature data; performing a noise comparison operation based on the noise feature data to obtain the model adjustment parameters of the noise prediction model; performing a difference degree adjustment operation based on the model adjustment parameters to obtain an adjusted noise prediction model; performing a noise prediction operation based on the adjusted noise prediction model to obtain the predicted noise features of the electronic components; wherein, the training process of the noise feature extraction model includes: obtaining historical working environment parameter data, where the historical working environment parameter data includes temperature, voltage, and current; performing data preprocessing and parameter range determination operations based on the historical working environment parameter data to obtain a parameter range; performing a parameter numerical interval conversion operation based on the parameter range to obtain the numerical interval corresponding to the parameter; performing a support vector machine regression operation based on the numerical interval to obtain a noise feature extraction model.

[0080] The embodiment of the present invention also provides a system for testing the noise of electronic components based on a data model, as Figure 4 shown, which is a structural block diagram of a system for testing the noise of electronic components based on a data model provided by the embodiment of the present invention, including: a data acquisition module 1, configured to obtain the current working environment parameter data of the electronic components during the operation of the electronic components; a model establishment module 2, configured to establish a noise feature extraction model and a noise prediction model; a model optimization module 3, configured to optimize the noise prediction model to obtain an adjusted noise prediction model; a noise prediction module 4, configured to perform a noise prediction operation based on the adjusted noise prediction model to obtain the predicted noise features of the electronic components.

[0081] In an alternative embodiment, the model establishment module 2 is further configured to: obtain historical working environment parameter data, where the historical working environment parameter data includes temperature, voltage, and current; perform data preprocessing and parameter range determination operations according to the historical working environment parameter data to obtain a parameter range; and perform parameter value interval conversion operations according to the parameter range to obtain a numerical interval corresponding to the parameter.

[0082] In an alternative embodiment, the model establishment module 2 is further configured to: The training process of the noise prediction model includes: obtaining historical noise feature data; performing an evaluation set establishment operation according to the historical noise feature data to obtain an evaluation set; performing a matrix construction operation according to the evaluation set to obtain an evaluation matrix; performing an entropy value calculation operation according to the evaluation matrix to obtain an entropy value; performing a goodness calculation operation according to the entropy value to obtain a goodness index; and performing a model construction operation according to the evaluation matrix, the entropy value, and the goodness index to obtain a noise prediction model; where the evaluation matrix is: Where, is the evaluation matrix, The row and the column of the evaluation matrix value.

[0083] In an alternative embodiment, the model establishment module 2 is further configured to: The performing an entropy value calculation operation according to the evaluation matrix to obtain an entropy value includes: The entropy value calculation formula is: Where, is the entropy value, is the row and the column of the evaluation matrix value, is the total number of matrix values in the evaluation matrix.

[0084] In an alternative embodiment, the model establishment module 2 is further configured to: The performing a goodness calculation operation according to the entropy value to obtain a goodness index includes: The goodness calculation formula is Where, is the goodness index, is the entropy value.

[0085] In an alternative embodiment, the model establishment module 2 is further configured to: The performing a model construction operation according to the evaluation matrix, the entropy value, and the goodness index to obtain a noise prediction model includes: The model construction formula is: Where, is the noise prediction model, is the entropy value matrix under the subjective weight set, is the entropy value matrix under the objective weight set, W1 is the subjective weight set, and W2 is the objective weight set. is the entropy value. is the preset proportionality coefficient. is the goodness index.

[0086] In an alternative embodiment, the model building module 2 is further configured to: perform a parameter value interval conversion operation according to the parameter range to obtain a corresponding numerical interval for the parameter, including: the parameter value interval conversion formula is: where is the numerical interval, is the minimum value of the parameter range, is the maximum value of the parameter range, is the th data in the parameter range.

[0087] In an alternative embodiment, the model building module 2 is further configured to: perform a support vector machine regression operation according to the numerical interval to obtain a noise feature extraction model, including: the support vector machine regression formula is: where is the noise feature extraction model, is the number of support vectors, and is the preset Lagrange multiplier, is the kernel function, is the bias term, is the newly input sample data, is the th data in the numerical interval.

[0088] In an alternative embodiment, the model optimization module 3 is further configured to: perform a noise comparison operation according to the noise feature data to obtain a model adjustment parameter for the noise prediction model, including: the calculation formula for the model adjustment parameter is: where is the degree of goodness of the model prediction, is the number of predicted noise data, is noise data, is the th original noise feature data, is the th predicted noise feature data, is the preset learning rate, is the preset initial model adjustment parameter, is the model adjustment parameter.

[0089] In an alternative embodiment, the model optimization module 3 is further configured to: adjust the degree of difference according to the model adjustment parameters to obtain an adjusted noise prediction model, including: the formula for the degree of difference adjustment operation is: Wherein, is a function of the adjusted noise prediction model, is a preset coefficient, is noise feature data, is the model adjustment parameter, is an error term.

[0090] An embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic component noise test method based on a data model as described in the above embodiment is implemented.

[0091] Exemplarily, the computer program may be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0092] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device, and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine certain components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0093] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device using various interfaces and circuits.

[0094] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory, the processor realizes various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as hard disks, memory, plug-in hard disks, Smart Media Cards (SMCs), Secure Digital (SD) cards, Flash Cards, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0095] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0096] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0097] In the present invention, the method for testing the noise of electronic components based on a data model has the following advantages: First, by obtaining the noise characteristic data of electronic components under different working environment parameters (such as temperature, current, voltage, etc.) and applying this data to the construction of a noise prediction model, the accuracy of noise testing can be effectively improved. This method not only reduces the common errors in traditional noise testing but also greatly reduces the difficulty of testing because the data model can provide accurate noise characteristic predictions under various environmental conditions, thus avoiding a large number of cumbersome manual tests and experimental processes. Second, this method can achieve real-time prediction of the working environment parameters of the electronic components to be detected, thereby providing a more accurate environmental condition basis for noise testing. This prediction ability can significantly improve the efficiency of noise testing and avoid the cumbersome steps of adjusting environmental parameters one by one in traditional testing. Third, by optimizing the simulation parameters, the testing process can also be made more efficient, reducing unnecessary repeated tests and saving time and resources. The method for testing the noise of electronic components implemented according to the above method depends on the already established noise characteristic extraction model and noise prediction model, and combines these two models for accurate noise prediction. By continuously optimizing the noise prediction model, the accuracy of testing is further improved, making the noise test results more reliable. At the same time, by predicting and adjusting the working environment parameters, not only can the accuracy of noise testing be improved, but the testing process can also be completed in a shorter time, thus greatly improving the overall testing efficiency.

[0098] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A noise testing method for electronic components based on a data model, characterized in that: include: During the operation of the electronic component, current operating environment parameter data of the electronic component is obtained and input into a pre-trained noise feature extraction model to obtain noise feature data; According to the noise characteristic data, a noise comparison operation is performed to obtain a model adjustment parameter of an initial noise prediction model; according to the model adjustment parameter, a difference degree adjustment operation is performed to obtain an adjusted noise prediction model; According to the adjusted noise prediction model, a noise prediction operation is performed to obtain the predicted noise characteristics of the electronic components; wherein the training process of the noise characteristic extraction model includes: obtaining historical working environment parameter data, the historical working environment parameter data including temperature, voltage and current; according to the historical working environment parameter data, data preprocessing and parameter range determination operations are performed to obtain the parameter range; according to the parameter range, a parameter numerical interval conversion operation is performed to obtain the numerical interval corresponding to the parameter; according to the numerical interval, a support vector machine regression operation is performed to obtain the noise characteristic extraction model.

2. The electronic component noise testing method based on data model according to claim 1, characterized in that: The step of performing a noise comparison operation according to the noise characteristic data to obtain a model adjustment parameter of the noise prediction model includes: a calculation formula of the model adjustment parameter is: ; ;in, How good is the model's prediction? To predict the number of noise data, For the The original noise characteristic data, For the predicted Noise characteristic data, is the preset learning rate, Adjust the parameters for the preset initial model, Parameters are adjusted for the model.

3. The electronic component noise testing method based on data model according to claim 1, characterized in that: The step of adjusting the parameters according to the model and performing a difference degree adjustment operation to obtain an adjusted noise prediction model includes: the difference degree adjustment operation formula is: ;in, is the function of the adjusted noise prediction model, is the preset coefficient, is the noise characteristic data, Adjust parameters for the model, is the error term.

4. The electronic component noise testing method based on data model according to claim 1, characterized in that: The training process of the noise prediction model includes: obtaining historical noise feature data; performing a judgment set establishment operation according to the historical noise feature data to obtain an evaluation set; performing a matrix construction operation according to the evaluation set to obtain an evaluation matrix; performing an entropy value calculation operation according to the evaluation matrix to obtain an entropy value; performing a goodness calculation operation according to the entropy value to obtain a goodness index; performing a model construction operation according to the evaluation matrix, the entropy value and the goodness index to obtain a noise prediction model; wherein the evaluation matrix is: in, is the evaluation matrix, No. Line The rating matrix value of the column.

5. The electronic component noise testing method based on data model according to claim 4, characterized in that: The entropy value calculation operation is performed according to the evaluation matrix to obtain the entropy value, including: the entropy value calculation formula is: in, is the entropy value, For the Line The evaluation matrix value of the column, is the total number of matrix values ​​in the evaluation matrix.

6. The electronic component noise testing method based on data model according to claim 4, characterized in that: The goodness calculation operation is performed according to the entropy value to obtain the goodness index, including: the goodness calculation formula is: in, is the goodness index, is the entropy value.

7. The electronic component noise testing method based on data model according to claim 4, characterized in that: The model building operation is performed according to the evaluation matrix, the entropy value and the goodness index to obtain a noise prediction model, including: the model building formula is: ; ; ;in, is the noise prediction model, is the entropy matrix under the subjective weight set, is the entropy matrix under the objective weight set, W1 is the subjective weight set, W2 is the objective weight set, is the entropy value, is the preset scale factor, is the goodness index.

8. The electronic component noise testing method based on data model according to claim 1, characterized in that: The parameter value interval conversion operation is performed according to the parameter range to obtain the value interval corresponding to the parameter, including: the parameter value interval conversion formula is: in, is the numerical interval, is the minimum value of the parameter range, is the maximum value of the parameter range, is the first data.

9. The electronic component noise testing method based on data model according to claim 1, characterized in that: The support vector machine regression operation is performed according to the numerical interval to obtain a noise feature extraction model, including: the support vector machine regression formula is: in, is the noise feature extraction model, is the number of support vectors, and is the default Lagrange multiplier, is the kernel function, is the bias term, is the newly input sample data, is the first data.

10. An electronic component noise test system based on a data model, characterized in that: include: A data acquisition module, used to acquire current working environment parameter data of the electronic component during its working process; Model building module, used to build noise feature extraction model and noise prediction model; A model optimization module is used to optimize the noise prediction model to obtain an adjusted noise prediction model; a noise prediction module is used to perform a noise prediction operation according to the adjusted noise prediction model to obtain the predicted noise characteristics of the electronic components; wherein the training process of the noise characteristic extraction model includes: obtaining historical working environment parameter data, the historical working environment parameter data including temperature, voltage and current; performing data preprocessing and parameter range determination operations according to the historical working environment parameter data to obtain a parameter range; performing a parameter value interval conversion operation according to the parameter range to obtain a value interval corresponding to the parameter; According to the numerical interval, a support vector machine regression operation is performed to obtain a noise feature extraction model.

Images