A method and device for intelligent assessment of short-circuit risk of MLCC capacitors

Abstract

This application provides a method and device for intelligent assessment of short-circuit risk of MLCC capacitors. The method includes: acquiring the insulation resistance and leakage current values ​​of the MLCC capacitors and comparing them with thresholds; marking the capacitors based on the threshold comparison results; assessing the short-circuit risk of the capacitors by combining the collected multi-dimensional feature data of the marked capacitors; obtaining the short-circuit risk probability and comparing it with thresholds; issuing a risk warning based on the threshold comparison results; determining the key influencing characteristics of MLCC short-circuit risk by combining the SHAP value; if no risk warning is issued, counting the number of times the average increase rate of the risk probability continuously exceeds a preset increase rate threshold and comparing it with a preset number threshold; if the number exceeds the preset number threshold, issuing a manual verification prompt; and determining the common influencing characteristics of capacitor short-circuit risk based on the SHAP values ​​corresponding to each input feature of the random forest model under different operating conditions and transmitting them to the monitoring terminal. This application can achieve the purpose of intelligent and accurate assessment of MLCC capacitor short-circuit risk.

Description

Technical Field

[0001] This application relates to the field of intelligent risk assessment technology for MLCC capacitors, and more specifically, to an intelligent assessment method and apparatus for short-circuit risk of MLCC capacitors. Background Technology

[0002] Multilayer ceramic capacitors (MLCCs) are common electronic components widely used in various electronic devices. However, MLCCs pose a certain risk of short circuits during use, which can lead to equipment malfunctions or even safety accidents. Traditional detection methods often struggle to assess the short-circuit risk of MLCCs in a timely and accurate manner, typically only detecting it after obvious signs of failure have appeared, by which time damage to the equipment may have already occurred. Therefore, there is an urgent need for a method and device capable of proactively and intelligently assessing the short-circuit risk of MLCCs. Summary of the Invention

[0003] The purpose of this application is to provide an intelligent assessment method and device for short-circuit risk of MLCC capacitors. By collecting the operating status data of MLCC capacitors in real time and using a pre-built risk assessment model, the method achieves intelligent and accurate assessment of capacitor short-circuit risk. It has the advantages of strong real-time performance, high accuracy, and timely early warning. It can be widely used in the maintenance and management of various electronic devices, effectively reducing the risk of failure caused by capacitor short circuits and improving the reliability and safety of equipment.

[0004] This application also provides a method for intelligent assessment of short-circuit risk of MLCC capacitors, including the following steps:

[0005] Obtain the insulation resistance and leakage current values ​​of the MLCC capacitor and compare them with threshold values. Mark the capacitors according to the threshold comparison results.

[0006] Multi-dimensional feature data of the labeled capacitors are collected, and the short-circuit risk of the capacitors is assessed by combining the insulation resistance value and leakage current value to obtain the short-circuit risk probability.

[0007] The short-circuit risk probability is compared with a preset short-circuit risk probability threshold, and a risk warning is issued based on the threshold comparison result.

[0008] Optionally, in the intelligent assessment method for short-circuit risk of MLCC capacitors described in this application, the step of obtaining the insulation resistance value and leakage current value of the MLCC capacitor and comparing them with a threshold, and marking the capacitor according to the threshold comparison result, includes:

[0009] The insulation resistance value and leakage current value are compared with preset insulation resistance threshold and leakage current threshold, respectively;

[0010] If the insulation resistance value is less than the first threshold of insulation resistance and the leakage current value is greater than the second threshold of leakage current, a high risk alarm for capacitor short circuit will be sent.

[0011] If the insulation resistance value is greater than or equal to the second threshold of insulation resistance and the leakage current value is less than or equal to the first threshold of leakage current, then a non-short circuit condition determination is made.

[0012] Otherwise, mark the capacitors.

[0013] Optionally, in the intelligent assessment method for short-circuit risk of MLCC capacitors described in this application, the step of collecting multi-dimensional feature data of the marked capacitors and combining the insulation resistance value and leakage current value to assess the short-circuit risk of the capacitors and obtain the short-circuit risk probability includes:

[0014] Multidimensional feature data includes performance parameter data, working environment data, and usage history data;

[0015] The insulation resistance value, leakage current value, performance parameter data, working environment data, and usage history data are input into a preset random forest model for processing to obtain the short circuit risk probability.

[0016] Optionally, in the intelligent assessment method for short-circuit risk of MLCC capacitors described in this application, the step of comparing the short-circuit risk probability with a preset short-circuit risk probability threshold and issuing a risk warning based on the threshold comparison result includes:

[0017] The short circuit risk probability is compared with a preset short circuit risk probability threshold. If the short circuit risk probability is greater than or equal to the preset first short circuit risk probability threshold, a high risk alarm for capacitor short circuit is triggered.

[0018] If the short circuit risk probability is less than the preset first threshold but greater than the preset second threshold, a manual verification prompt will be issued.

[0019] Optionally, the intelligent assessment method for short-circuit risk of MLCC capacitors described in this application further includes:

[0020] If the short-circuit risk probability is greater than the preset second threshold for short-circuit risk probability, then obtain the SHAP value corresponding to each input feature of the random forest model;

[0021] The SHAP value is compared with the preset SHAP threshold. The input feature corresponding to the SHAP value that exceeds the SHAP threshold is taken as the key impact feature of MLCC short circuit risk and transmitted to the monitoring terminal.

[0022] Optionally, the intelligent assessment method for short-circuit risk of MLCC capacitors described in this application further includes:

[0023] If the short circuit risk probability is less than or equal to the preset second threshold of short circuit risk probability, then the average risk probability is calculated based on the short circuit risk probability within the preset time period.

[0024] The increase rate of the average risk probability is calculated based on the average risk probability over a preset time period.

[0025] The system counts the number of times the average increase rate of risk probability exceeds a preset threshold within a preset time period, and compares this number with a preset threshold for the number of occurrences. If the number of occurrences exceeds the preset threshold, a manual verification prompt is issued.

[0026] Optionally, the intelligent assessment method for short-circuit risk of MLCC capacitors described in this application further includes:

[0027] Obtain the short-circuit risk probability of MLCC capacitors under different operating conditions and the SHAP value corresponding to each input feature of the random forest model;

[0028] Input features whose SHAP values ​​are all greater than the SHAP set value under different operating conditions are taken as common influencing features;

[0029] The common impact characteristics and their corresponding SHAP values ​​under different operating conditions are transmitted to the monitoring terminal.

[0030] Secondly, this application provides an intelligent assessment device for short-circuit risk of MLCC capacitors, comprising:

[0031] The data acquisition module is used to collect insulation resistance values, leakage current values, and multi-dimensional characteristic data;

[0032] The data storage module is used to store the collected data and risk assessment results.

[0033] The data processing module is used to assess the short-circuit risk of MLCC capacitors;

[0034] The communication and interaction module is used to transmit the short-circuit risk assessment results to the monitoring terminal;

[0035] The early warning module is used to issue high-risk alarms for capacitor short circuits and to prompt manual verification.

[0036] Optionally, in the intelligent assessment device for short-circuit risk of MLCC capacitors described in this application, the data processing module is used for:

[0037] The insulation resistance value and leakage current value are compared with preset insulation resistance threshold and leakage current threshold, respectively;

[0038] The insulation resistance value, leakage current value, and multi-dimensional feature data are input into a preset random forest model for processing to obtain the short circuit risk probability.

[0039] The short circuit risk probability is compared with a preset first threshold and a preset second threshold to determine the relationship between the short circuit risk probability and the threshold.

[0040] If the short circuit risk probability is less than or equal to the preset second threshold of short circuit risk probability, then the average risk probability is calculated based on the short circuit risk probability within the preset time period.

[0041] The increase rate of the average risk probability is calculated based on the average risk probability over a preset time period.

[0042] The number of times the average increase rate of risk probability exceeds a preset increase rate threshold within a preset time period is counted and compared with a preset number threshold.

[0043] Obtain the short-circuit risk probability of MLCC capacitors under different operating conditions and the SHAP value corresponding to each input feature of the random forest model;

[0044] Input features whose SHAP values ​​are all greater than the SHAP set value under different operating conditions are taken as common influence features.

[0045] Optionally, in the intelligent assessment device for short-circuit risk of MLCC capacitors described in this application, the early warning module is used for:

[0046] If the short circuit risk probability is greater than or equal to the preset first threshold for short circuit risk probability, a high risk alarm for capacitor short circuit will be issued.

[0047] If the short circuit risk probability is less than the preset first threshold and greater than the preset second threshold, a manual verification prompt will be issued.

[0048] If the number of times the average increase rate of risk probability exceeds the preset increase rate threshold is greater than the preset number threshold, a manual verification prompt will be issued.

[0049] As can be seen from the above, the intelligent assessment method and device for short-circuit risk of MLCC capacitors provided in this application realizes intelligent and accurate assessment of capacitor short-circuit risk by collecting the operating status data of MLCC capacitors in real time and using a pre-built risk assessment model. It has the advantages of strong real-time performance, high accuracy and timely early warning. It can be widely used in the maintenance and management of various electronic devices, effectively reducing the risk of failure caused by capacitor short circuits and improving the reliability and safety of equipment.

[0050] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart of the intelligent assessment method for short-circuit risk of MLCC capacitors provided in the embodiments of this application;

[0053] Figure 2 A flowchart illustrating the threshold comparison process in the intelligent assessment method for short-circuit risk of MLCC capacitors provided in this application embodiment;

[0054] Figure 3 A flowchart illustrating the process of obtaining the short-circuit risk probability using the intelligent assessment method for short-circuit risk of MLCC capacitors provided in this application embodiment;

[0055] Figure 4 This is a structural diagram of the intelligent assessment device for short-circuit risk of MLCC capacitors provided in the embodiments of this application. Detailed Implementation

[0056] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0057] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0058] Please refer to Figure 1 , Figure 1This is a flowchart of an intelligent assessment method for short-circuit risk of MLCC capacitors according to some embodiments of this application. This intelligent assessment method for short-circuit risk of MLCC capacitors is used in terminal devices, such as computers and mobile terminals. The intelligent assessment method for short-circuit risk of MLCC capacitors includes the following steps:

[0059] S11. Obtain the insulation resistance value and leakage current value of the MLCC capacitor and perform threshold comparison. Mark the capacitor according to the threshold comparison result.

[0060] S12. Collect multi-dimensional feature data of the marked capacitor, and combine the insulation resistance value and leakage current value to assess the short circuit risk of the capacitor and obtain the short circuit risk probability.

[0061] S13. Compare the short circuit risk probability with a preset short circuit risk probability threshold, and issue a risk warning based on the threshold comparison result.

[0062] It should be noted that this application first obtains the insulation resistance and leakage current values ​​of MLCC capacitors to facilitate rapid initial screening of capacitors with high short-circuit risk and those that are qualified. Capacitors requiring further risk assessment are then marked. Multi-dimensional feature data of the marked capacitors are collected, and a pre-trained random forest model is used to predict short-circuit risk, obtaining the probability of short-circuit risk. A threshold comparison is then performed, and a risk warning is issued based on the threshold comparison results. For capacitors with potential risks, the SHAP value corresponding to each input feature of the random forest model is further obtained. Input features with SHAP values ​​exceeding the SHAP threshold are used as key influencing features of MLCC short-circuit risk and transmitted to the monitoring terminal for relevant personnel to analyze. Based on this information, more targeted preventive measures are formulated. If no risk warning is issued, the number of times the average increase rate of the risk probability exceeds the preset increase rate threshold is counted and compared with the preset number threshold. If the number exceeds the preset number threshold, it indicates that the probability of short circuit risk is continuously rising. In this case, manual verification and prompting are carried out. Based on the SHAP value corresponding to each input feature of the random forest model under different operating conditions, the common impact features of capacitor short circuit risk are determined and transmitted to the monitoring terminal to help relevant personnel understand the key influencing factors of capacitor short circuit risk in a timely manner. Based on the changes in these common features, the potential capacitor short circuit risk can be assessed and warned in advance so that corresponding preventive measures can be taken to avoid failure.

[0063] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the threshold comparison process in some embodiments of the intelligent assessment method for short-circuit risk of MLCC capacitors according to this application. According to embodiments of the present invention, obtaining the insulation resistance value and leakage current value of the MLCC capacitor and performing a threshold comparison, and marking the capacitor based on the threshold comparison result, includes:

[0064] S21. Compare the insulation resistance value and leakage current value with the preset insulation resistance threshold and leakage current threshold, respectively;

[0065] S22. If the insulation resistance value is less than the first threshold of insulation resistance and the leakage current value is greater than the second threshold of leakage current, a high risk alarm for capacitor short circuit will be sent.

[0066] S23. If the insulation resistance value is greater than or equal to the second threshold of insulation resistance and the leakage current value is less than or equal to the first threshold of leakage current, then a non-short circuit condition determination is performed.

[0067] S24. Otherwise, mark the capacitor.

[0068] It should be noted that obtaining the insulation resistance and leakage current values ​​of MLCC capacitors is necessary for a rapid initial screening of capacitors with a high risk of short circuits and those that are qualified. If a capacitor is found to have an insulation resistance that is significantly too low and a leakage current that is too high, it can be determined that the capacitor has a high risk of short circuits. If a capacitor has a high insulation resistance and a low leakage current, it is determined to be in a non-short circuit state. Capacitors that are not determined to be in a high-risk state or a non-short circuit state are marked for further evaluation.

[0069] Specifically, an insulation resistance first threshold and an insulation resistance second threshold are extracted based on the insulation resistance threshold, wherein the insulation resistance first threshold is less than the insulation resistance second threshold; and a leakage current first threshold and a leakage current second threshold are extracted based on the leakage current threshold, wherein the leakage current first threshold is less than the leakage current second threshold.

[0070] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the intelligent short-circuit risk assessment method for MLCC capacitors in some embodiments of this application, used to obtain the short-circuit risk probability. According to embodiments of the present invention, the step of collecting multi-dimensional feature data of the marked capacitor and combining it with the insulation resistance value and leakage current value to assess the short-circuit risk of the capacitor and obtain the short-circuit risk probability includes:

[0071] S31. Multi-dimensional feature data includes performance parameter data, working environment data, and usage history data;

[0072] S32. Input the insulation resistance value, leakage current value, performance parameter data, working environment data, and usage history data into a preset random forest model for processing to obtain the short circuit risk probability.

[0073] It should be noted that a random forest model is used to further assess the risk of the labeled capacitors. Performance parameter data includes capacitor deviation, voltage deviation, ESR change rate, loss tangent, and capacitor surface temperature difference; operating environment data includes real-time operating temperature and humidity; and historical usage data includes cumulative operating time, charge / discharge cycle count, and historical short-circuit count. The random forest model is trained using a large amount of historical sample data, including insulation resistance, leakage current, performance parameter data, operating environment data, historical usage data, and actual short-circuit probabilities.

[0074] According to an embodiment of the present invention, the step of comparing the short-circuit risk probability with a preset short-circuit risk probability threshold and issuing a risk warning based on the threshold comparison result includes:

[0075] The short circuit risk probability is compared with a preset short circuit risk probability threshold. If the short circuit risk probability is greater than or equal to the preset first short circuit risk probability threshold, a high risk alarm for capacitor short circuit is triggered.

[0076] If the short circuit risk probability is less than the preset first threshold but greater than the preset second threshold, a manual verification prompt will be issued.

[0077] It should be noted that the short-circuit risk probability is compared with a preset short-circuit risk probability threshold, and a risk warning is issued based on the comparison result. Specifically, a first short-circuit risk probability threshold and a second short-circuit risk probability threshold are extracted based on the short-circuit risk probability threshold. The second short-circuit risk probability threshold is less than the first short-circuit risk probability threshold. If the short-circuit risk probability is less than the preset first short-circuit risk probability threshold but greater than the preset second short-circuit risk probability threshold, it indicates that there is a certain risk, and further manual verification is required.

[0078] According to an embodiment of the present invention, it further includes:

[0079] If the short-circuit risk probability is greater than the preset second threshold for short-circuit risk probability, then obtain the SHAP value corresponding to each input feature of the random forest model;

[0080] The SHAP value is compared with the preset SHAP threshold. The input feature corresponding to the SHAP value that exceeds the SHAP threshold is taken as the key impact feature of MLCC short circuit risk and transmitted to the monitoring terminal.

[0081] It should be noted that for capacitors posing a high risk and requiring further manual verification, the SHAP value corresponding to each input feature of the random forest model is obtained. Input features with SHAP values ​​exceeding the SHAP threshold are considered key influencing features of MLCC short-circuit risk and transmitted to the monitoring terminal. This allows relevant personnel to develop more targeted preventative measures based on this information. The SHAP value represents the marginal contribution of each feature in the prediction. After training the random forest model, the SHAP value corresponding to each feature can be obtained using the TreeExplainer function of the SHAP library. Furthermore, the input features of the random forest model include insulation resistance values, leakage current values, as well as the aforementioned performance parameter data, operating environment data, and usage history data.

[0082] According to an embodiment of the present invention, it further includes:

[0083] If the short circuit risk probability is less than or equal to the preset second threshold of short circuit risk probability, then the average risk probability is calculated based on the short circuit risk probability within the preset time period.

[0084] The increase rate of the average risk probability is calculated based on the average risk probability over a preset time period.

[0085] The system counts the number of times the average increase rate of risk probability exceeds a preset threshold within a preset time period, and compares this number with a preset threshold for the number of occurrences. If the number of occurrences exceeds the preset threshold, a manual verification prompt is issued.

[0086] It should be noted that if the short-circuit risk probability is less than or equal to the preset second threshold for short-circuit risk probability, it indicates that the short-circuit risk probability is low. To avoid missed detections, the number of times the average increase rate of the risk probability exceeds the preset increase rate threshold is further counted and compared with the preset number threshold. In this embodiment, if the number of times the average increase rate of the risk probability exceeds the preset increase rate threshold exceeds 3 consecutive times, it indicates that the short-circuit risk probability is continuously rising, and a manual verification prompt is made. Specifically, if the average risk probability decreases, the increase rate is negative; if the average risk probability increases, the increase rate is positive.

[0087] According to an embodiment of the present invention, it further includes:

[0088] Obtain the short-circuit risk probability of MLCC capacitors under different operating conditions and the SHAP value corresponding to each input feature of the random forest model;

[0089] Input features whose SHAP values ​​are all greater than the SHAP set value under different operating conditions are taken as common influencing features;

[0090] The common impact characteristics and their corresponding SHAP values ​​under different operating conditions are transmitted to the monitoring terminal.

[0091] It should be noted that the common impact features of capacitor short-circuit risk are determined based on the SHAP values ​​corresponding to each input feature of the random forest model under different operating conditions and transmitted to the monitoring terminal. This helps relevant personnel to understand the key influencing factors of capacitor short-circuit risk in a timely manner. Based on the changes in these common features, potential capacitor short-circuit risks can be assessed and warned in advance so that corresponding preventive measures can be taken to avoid failure.

[0092] According to an embodiment of the present invention, it further includes:

[0093] Obtain the short-circuit risk probability corresponding to different process parameters under different operating conditions;

[0094] The average short-circuit risk probability is calculated by averaging the short-circuit risk probability under different operating conditions to obtain the average short-circuit risk probability.

[0095] The average short-circuit risk probability corresponding to different process parameters is sorted according to its numerical value. The process parameter with the smallest average short-circuit risk probability is selected as the best candidate process parameter and transmitted to the monitoring terminal.

[0096] It should be noted that the average risk probability of each process parameter under different operating conditions is calculated to obtain the average short-circuit risk probability of each process parameter. The process parameter with the smallest average short-circuit risk probability is selected as the optimal candidate process parameter.

[0097] Please refer to Figure 4 , Figure 4 This is a framework structural diagram of an intelligent assessment device for short-circuit risk of MLCC capacitors in some embodiments of this application. The present invention also discloses an intelligent assessment device for short-circuit risk of MLCC capacitors, comprising:

[0098] Data acquisition module 41 is used to acquire insulation resistance value, leakage current value and multi-dimensional characteristic data;

[0099] Data storage module 42 is used to store the collected data and risk assessment results;

[0100] Data processing module 43 is used to assess the short-circuit risk of MLCC capacitors;

[0101] Communication and interaction module 44 is used to transmit short-circuit risk assessment results to the monitoring terminal;

[0102] The early warning module 45 is used to issue high-risk alarms for capacitor short circuits and to prompt manual verification.

[0103] It should be noted that the intelligent assessment device for short-circuit risk of MLCC capacitors achieves the purpose of intelligent assessment of short-circuit risk of MLCC capacitors through various device modules.

[0104] According to an embodiment of the present invention, the data processing module is used for:

[0105] The insulation resistance value and leakage current value are compared with preset insulation resistance threshold and leakage current threshold, respectively;

[0106] The insulation resistance value, leakage current value, and multi-dimensional feature data are input into a preset random forest model for processing to obtain the short circuit risk probability.

[0107] The short circuit risk probability is compared with a preset first threshold and a preset second threshold to determine the relationship between the short circuit risk probability and the threshold.

[0108] If the short circuit risk probability is less than or equal to the preset second threshold of short circuit risk probability, then the average risk probability is calculated based on the short circuit risk probability within the preset time period.

[0109] The increase rate of the average risk probability is calculated based on the average risk probability over a preset time period.

[0110] The number of times the average increase rate of risk probability exceeds a preset increase rate threshold within a preset time period is counted and compared with a preset number threshold.

[0111] Obtain the short-circuit risk probability of MLCC capacitors under different operating conditions and the SHAP value corresponding to each input feature of the random forest model;

[0112] Input features whose SHAP values ​​are all greater than the SHAP set value under different operating conditions are taken as common influence features.

[0113] It should be noted that the data processing module runs a risk assessment model, analyzes and calculates the input feature data to obtain the short-circuit risk probability, and then performs analysis and calculation based on the short-circuit risk probability.

[0114] According to an embodiment of the present invention, the early warning module is used for:

[0115] If the short circuit risk probability is greater than or equal to the preset first threshold for short circuit risk probability, a high risk alarm for capacitor short circuit will be issued.

[0116] If the short circuit risk probability is less than the preset first threshold and greater than the preset second threshold, a manual verification prompt will be issued.

[0117] If the number of times the average increase rate of risk probability exceeds the preset increase rate threshold is greater than the preset number threshold, a manual verification prompt will be issued.

[0118] It should be noted that the MLCC capacitor short-circuit risk intelligent assessment device realizes the risk warning function based on the processing results of the data processing module.

[0119] This invention discloses an intelligent assessment method and device for short-circuit risk of MLCC capacitors. By collecting real-time operating status data of MLCC capacitors and utilizing a pre-built risk assessment model, it achieves intelligent and accurate assessment of capacitor short-circuit risk. It has the advantages of strong real-time performance, high accuracy, and timely early warning. It can be widely used in the maintenance and management of various electronic devices, effectively reducing the risk of failure caused by capacitor short circuits and improving the reliability and safety of equipment.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0121] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. A method for intelligent assessment of short-circuit risk in MLCC capacitors, characterized in that, Includes the following steps: Obtain the insulation resistance and leakage current values ​​of the MLCC capacitor and compare them with threshold values. Mark the capacitors according to the threshold comparison results. The insulation resistance value and leakage current value are compared with preset insulation resistance threshold and leakage current threshold, respectively; If the insulation resistance value is less than the first threshold of insulation resistance and the leakage current value is greater than the second threshold of leakage current, a high risk alarm for capacitor short circuit will be sent. If the insulation resistance value is greater than or equal to the second threshold of insulation resistance and the leakage current value is less than or equal to the first threshold of leakage current, then a non-short circuit condition determination is made. Otherwise, mark the capacitors; Multi-dimensional feature data of the labeled capacitors are collected, and the short-circuit risk of the capacitors is assessed by combining the insulation resistance value and leakage current value to obtain the short-circuit risk probability. The short circuit risk probability is compared with a preset short circuit risk probability threshold, and a risk warning is given based on the threshold comparison result. The short circuit risk probability is compared with a preset short circuit risk probability threshold. If the short circuit risk probability is greater than or equal to the preset first short circuit risk probability threshold, a high risk alarm for capacitor short circuit is triggered. If the short circuit risk probability is less than the preset first threshold and greater than the preset second threshold, a manual verification prompt will be issued. If the short circuit risk probability is less than or equal to the preset second threshold of short circuit risk probability, then the average risk probability is calculated based on the short circuit risk probability within the preset time period. The increase rate of the average risk probability is calculated based on the average risk probability over a preset time period. The system counts the number of times the average increase rate of risk probability exceeds a preset threshold within a preset time period, and compares this number with a preset threshold for the number of occurrences. If the number of occurrences exceeds the preset threshold, a manual verification prompt is issued.

2. The intelligent assessment method for short-circuit risk of MLCC capacitors according to claim 1, characterized in that, The multi-dimensional feature data of the collected and labeled capacitors are combined with the insulation resistance value and leakage current value to assess the short-circuit risk of the capacitors and obtain the short-circuit risk probability, including: Multidimensional feature data includes performance parameter data, working environment data, and usage history data; The insulation resistance value, leakage current value, performance parameter data, working environment data, and usage history data are input into a preset random forest model for processing to obtain the short circuit risk probability.

3. The intelligent assessment method for short-circuit risk of MLCC capacitors according to claim 2, characterized in that, Also includes: If the short-circuit risk probability is greater than the preset second threshold for short-circuit risk probability, then obtain the SHAP value corresponding to each input feature of the random forest model; The SHAP value is compared with the preset SHAP threshold. The input feature corresponding to the SHAP value that exceeds the SHAP threshold is taken as the key impact feature of MLCC short circuit risk and transmitted to the monitoring terminal.

4. The intelligent assessment method for short-circuit risk of MLCC capacitors according to claim 3, characterized in that, Also includes: Obtain the short-circuit risk probability of MLCC capacitors under different operating conditions and the SHAP value corresponding to each input feature of the random forest model; Input features whose SHAP values ​​are all greater than the SHAP set value under different operating conditions are taken as common influencing features; The common impact characteristics and their corresponding SHAP values ​​under different operating conditions are transmitted to the monitoring terminal.

5. An intelligent assessment device for short-circuit risk of MLCC capacitors, characterized in that, include: The data acquisition module is used to collect insulation resistance values, leakage current values, and multi-dimensional characteristic data; The data storage module is used to store the collected data and risk assessment results. The data processing module is used to assess the short-circuit risk of the MLCC capacitor by comparing the insulation resistance value and leakage current value with preset insulation resistance threshold and leakage current threshold, respectively. The insulation resistance value, leakage current value, and multi-dimensional feature data are input into a preset random forest model for processing to obtain the short circuit risk probability. The short-circuit risk probability is compared with a preset first threshold and a preset second threshold to determine the relationship between the short-circuit risk probability and the threshold. If the short circuit risk probability is less than or equal to the preset second threshold of short circuit risk probability, then the average risk probability is calculated based on the short circuit risk probability within the preset time period. The increase rate of the average risk probability is calculated based on the average risk probability over a preset time period. The number of times the average increase rate of risk probability exceeds a preset increase rate threshold within a preset time period is counted and compared with a preset number threshold. Obtain the short-circuit risk probability of MLCC capacitors under different operating conditions and the SHAP value corresponding to each input feature of the random forest model; Input features whose SHAP values ​​are all greater than the SHAP set value under different operating conditions are taken as common influencing features; The communication and interaction module is used to transmit the short-circuit risk assessment results to the monitoring terminal; The early warning module is used to issue high-risk alarms for capacitor short circuits and to prompt manual verification.

6. The intelligent assessment device for short-circuit risk of MLCC capacitors according to claim 5, characterized in that, The early warning module is used for: If the short circuit risk probability is greater than or equal to the preset first threshold for short circuit risk probability, a high-risk alarm for capacitor short circuit will be issued. If the short circuit risk probability is less than the preset first threshold and greater than the preset second threshold, a manual verification prompt will be issued. If the number of times the average increase rate of risk probability exceeds the preset increase rate threshold is greater than the preset number threshold, a manual verification prompt will be issued.

Images