Relay contact topography analysis method, apparatus, device, medium, and program

Abstract

The application provides a relay contact topography analysis method, device, equipment, medium and program, belonging to the battery technical field. The relay contact topography analysis method comprises: obtaining a plurality of contact topography characteristics of a relay, each contact topography characteristic in the plurality of contact topography characteristics respectively indicating a corresponding contact surface topography of the relay; determining a first prediction result of the relay based on the plurality of contact topography characteristics, the first prediction result indicating a test type undergone by the relay; determining a second prediction result of the relay based on the first prediction result and the plurality of contact topography characteristics, the second prediction result indicating a test process undergone by the relay. The method can quickly determine the related working conditions of the relay through the contact topography of the relay.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to a method, apparatus, device, medium and program for analyzing the morphology of relay contacts. Background Technology

[0002] Energy conservation and emission reduction are key to sustainable social development. Rechargeable batteries, with their ability to store and release energy as needed, are widely used in various electrical devices and energy storage systems, and are an important component in promoting energy transition and sustainable development. For the new energy industry, battery technology is a crucial factor in its development.

[0003] Relays are widely used in energy storage, solar power generation, charging stations, and new energy vehicles. However, relays have a relatively high failure rate during use. Furthermore, troubleshooting failed relays often involves difficulties in obtaining relevant operating conditions, making it challenging to quickly determine the cause of failure. Summary of the Invention

[0004] This application aims to at least address the technical problem in the prior art where the relevant operating conditions of a relay cannot be determined. Therefore, one objective of this application is to provide a method for analyzing the morphology of relay contacts, so as to quickly determine the relevant operating conditions of the relay through the contact morphology.

[0005] An embodiment of the first aspect of this application provides a method for analyzing the morphology of relay contacts, comprising: acquiring multiple contact morphology features of a relay, each of the multiple contact morphology features indicating the corresponding contact surface morphology of the relay; determining a first prediction result of the relay based on the multiple contact morphology features, the first prediction result indicating the test type that the relay has undergone; and determining a second prediction result of the relay based on the first prediction result and the multiple contact morphology features, the second prediction result indicating the test process that the relay has undergone.

[0006] In the technical solution of this application embodiment, the test types and test procedures that the relay undergoes are determined step by step in stages based on the contact morphology characteristics of the relay. While accurately obtaining the relevant operating conditions experienced by the relay, the accuracy and efficiency of the analysis results for the relevant operating conditions are improved through multi-level step-by-step analysis.

[0007] In some embodiments, determining a first prediction result for a relay based on multiple contact morphology features includes: determining a first target variable, which indicates the type of test performed on the relay; determining at least one first feature variable associated with the first target variable from the multiple contact morphology features; and determining the first prediction result using a decision tree model based on the first target variable and the at least one first feature variable. By determining feature vectors associated with the test type from multiple contact morphology features, and having the decision tree model output the prediction result for the test type, the decision tree model can use the most relevant features during prediction, reducing the influence of redundant features and improving the accuracy and precision of the prediction results.

[0008] In some embodiments, determining a second prediction result for a relay based on a first prediction result and multiple contact morphology features includes: determining at least one target feature variable associated with the first prediction result from the multiple contact morphology features based on the first prediction result; and determining the second prediction result based on the at least one target feature variable. Selecting features related to the test type from the contact morphology features based on the prediction result for the test type, and using these features to predict specific test procedures, allows the prediction process for test procedures to use the most relevant features, improving the prediction efficiency and capability for test procedures.

[0009] In some embodiments, determining at least one target feature variable associated with the first prediction result from multiple contact morphology features based on the first prediction result includes: in response to the first prediction result being a first test type, determining contact morphology features related to the breaking current of the relay from multiple contact morphology features to obtain at least one target feature variable; in response to the first prediction result being a second test type, determining contact morphology features related to the capacitive load of the relay from multiple contact morphology features to obtain at least one target feature variable; and in response to the first prediction result being a third test type, determining contact morphology features related to the overload tolerance of the relay from multiple contact morphology features to obtain at least one target feature variable. Dynamically adjusting the feature set used in the current prediction based on the prediction result of the test type obtained from the previous prediction allows for a comprehensive consideration of the prediction results at each level, thereby obtaining a more accurate prediction result for the test process.

[0010] In some embodiments, the second prediction result includes the relay's test current and / or the number of tests. Determining the second prediction result based on at least one target feature variable includes: determining the relay's test current based on at least one target feature variable; and / or determining the relay's number of tests based on at least one target feature variable. By predicting the test current and the number of tests conducted on the relay, the relevant operating conditions experienced by the relay can be accurately obtained, and the causes of relay failure can be further identified.

[0011] In some embodiments, determining the test current of a relay based on at least one target feature variable includes: determining a second target variable, which indicates the current level during relay testing; and determining the test current of the relay using a decision tree model based on the second target variable and at least one target feature variable. By determining the target variable indicating the test current level and combining it with target feature variables associated with the test type, the decision tree model can output a prediction result for the test current. This allows the decision tree model to use the features most relevant to the test current during prediction, reducing the influence of redundant features and improving the accuracy and precision of the prediction results.

[0012] In some embodiments, determining the second target variable includes: determining the second target variable in response to a first test result being any one of a first test type, a second test type, and a third test type. The second target variable related to the current level is determined only when the first test result indicating the test type is a specific test type, in order to predict the current level. Subsequent prediction processes can be determined based on different prediction results, thereby improving both prediction accuracy and prediction efficiency.

[0013] In some embodiments, determining the number of tests for a relay based on at least one target feature variable includes: determining a third target variable, which indicates the number of operations performed when testing the relay; and determining the number of tests for the relay using a decision tree model based on the third target variable and at least one target feature variable. By determining a target variable indicating the number of operations and combining it with a target feature variable associated with the test type, the decision tree model can output a prediction of the number of tests. This allows the decision tree model to use the features most relevant to the number of tests during prediction, reducing the influence of redundant features and improving the accuracy and precision of the prediction results.

[0014] In some embodiments, determining the third target variable includes: determining the third target variable in response to a first test result being either a first test type or a second test type. The third target variable, related to the number of tests, is determined only when the first test result indicating the test type is a specific test type, in order to predict the number of tests. Subsequent prediction processes can be determined based on different prediction results, thereby improving both prediction accuracy and prediction efficiency.

[0015] In some embodiments, obtaining multiple contact morphological features of a relay includes at least one of the following: obtaining multiple contact morphological features from a pre-established database; obtaining multiple contact morphological features based on a pre-input image of the relay; or obtaining multiple contact morphological features based on manually input feature values. Using multiple methods to obtain the contact morphological features of a relay can be applied to different application scenarios, improving the adaptability and flexibility of the analysis method.

[0016] In some embodiments, the multiple contact morphology features include at least one of the following: electrical contact parameters of the relay contacts; morphological parameters of the relay contacts; and manually identified parameters. Using different types of contact morphology features allows for accurate characterization of the relay contact morphology, improving the accuracy of prediction results.

[0017] In some embodiments, the analysis method further includes: after acquiring multiple contact morphological features of the relay, preprocessing the multiple contact morphological features. Preprocessing the acquired contact morphological features can improve data quality and facilitate subsequent analysis and identification.

[0018] In some embodiments, preprocessing the multiple contact morphology features includes at least one of the following: data cleaning of the multiple contact morphology features; converting non-numerical contact morphology features into numerical contact morphology features; and converting the multiple contact morphology features into matrix form. By fully preprocessing the contact morphology features, the data input to the decision tree model becomes more accurate, further improving the reliability and accuracy of the prediction results.

[0019] An embodiment of the second aspect of this application provides an analysis apparatus for relay contact morphology, comprising: a first module for acquiring multiple contact morphology features of a relay, each of the multiple contact morphology features indicating the corresponding contact surface morphology of the relay; a second module for determining a first prediction result of the relay based on the multiple contact morphology features, the first prediction result indicating the test type undergone by the relay; and a third module for determining a second prediction result of the relay based on the first prediction result and the multiple contact morphology features, the second prediction result indicating the test process undergone by the relay.

[0020] An embodiment of the third aspect of this application provides a computing device, including: at least one processor; and at least one memory communicatively connected to the at least one processor, the at least one memory storing instructions that, when executed individually or jointly by the at least one processor, cause the computing device to perform the analysis method described in the above embodiments.

[0021] An embodiment of the fourth aspect of this application provides a computer-readable storage medium storing instructions that, when executed individually or jointly by one or more processors of a computing device, cause the computing device to perform the analysis method described in the above embodiments.

[0022] An embodiment of the fifth aspect of this application provides a computer program product including instructions that, when executed individually or jointly by one or more processors of a computing device, cause the computing device to perform the analysis method described above.

[0023] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0024] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0025] Figure 1 This is a flowchart illustrating the method for analyzing the morphology of relay contacts in some embodiments of this application;

[0026] Figure 2 This is a schematic diagram of the process for determining the first prediction result in some embodiments of this application;

[0027] Figure 3 This is a schematic diagram of the process for determining the second prediction result in some embodiments of this application;

[0028] Figure 4 This is a flowchart illustrating the process of determining target feature variables in some embodiments of this application;

[0029] Figure 5 This is a schematic diagram of the process for determining the second prediction result in some embodiments of this application;

[0030] Figure 6 This is a flowchart illustrating the process of determining the test current of a relay in some embodiments of this application;

[0031] Figure 7 This is a flowchart illustrating the process of determining the number of tests for a relay according to some embodiments of this application;

[0032] Figure 8 This is a schematic diagram of the process for obtaining contact morphology features in some embodiments of this application;

[0033] Figure 9 This is a schematic diagram of the process for preprocessing contact morphology features according to some embodiments of this application;

[0034] Figure 10 This is a schematic diagram illustrating the morphological features of multiple contact points in some embodiments of this application;

[0035] Figure 11 This is a schematic diagram of a relay contact under a first test type in some embodiments of this application;

[0036] Figure 12This is a schematic diagram of relay contacts under a second test type in some embodiments of this application;

[0037] Figure 13 This is a schematic diagram of a relay contact under a third test type in some embodiments of this application;

[0038] Figure 14 This is a schematic block diagram of a relay contact morphology analysis device according to some embodiments of this application;

[0039] Figure 15 This is a schematic block diagram of a computing device according to some embodiments of this application. Detailed Implementation

[0040] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0042] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0043] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0044] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0045] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0046] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0047] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0048] Currently, the application of rechargeable batteries is becoming increasingly widespread, judging from market trends. They are not only used in energy storage systems for hydropower, thermal power, wind power, and solar power plants, but also extensively in various electronic devices, such as electric bicycles, electric motorcycles, and electric vehicles, as well as in military equipment and aerospace. As the application areas of rechargeable batteries continue to expand, the market demand is also constantly increasing.

[0049] Relays are widely used in energy storage, solar power generation, charging stations, and new energy vehicles. For example, in new energy vehicles, relays can be used in discharge circuits, fast charging circuits, and slow charging circuits. A typical new energy vehicle uses 5-8 relays. Relays have a relatively high failure rate during use, mainly due to issues such as contact adhesion or welding. However, troubleshooting failed relays often involves difficulties in obtaining relevant operating conditions, making it hard to quickly determine the cause of failure.

[0050] To enable rapid analysis of relay failure causes, a connection can be established between the surface morphology of the relay contacts and the test processes the relay has undergone, i.e., the operating conditions the relay has experienced. The contact surfaces of abnormal relays can be characterized by multiple contact morphology features. The types of tests and test procedures that the relay has undergone can be predicted in layers. Thus, the features used in the next prediction can be dynamically adjusted based on the prediction results, ultimately obtaining the prediction results of the test processes that the relay has undergone.

[0051] Using this analytical method, the prediction process can be decomposed into multiple levels of step-by-step prediction. This allows for a better capture of the complex dependencies between various features, comprehensively considering the prediction results at each level. This ensures that each level of prediction utilizes its most relevant features, reducing the impact of redundant features and significantly improving prediction capability and accuracy, resulting in accurate predictions. Based on the prediction results, the relevant operating conditions experienced by the relay can be accurately assessed, and the cause of relay failure can be quickly determined.

[0052] The relay contact morphology analysis method disclosed in this application can be used, but is not limited to, for analyzing relays used in electrical devices or energy storage devices such as vehicles, ships, or aircraft. Using the relay contact morphology analysis method disclosed in this application helps improve the accuracy and efficiency of the analysis results regarding the relevant operating conditions experienced by the relay.

[0053] This application provides a method for analyzing the morphology of relay contacts. (Reference) Figure 1 The method 100 for analyzing the morphology of relay contacts includes steps 110 to 130.

[0054] Step 110: Obtain multiple contact morphological features of the relay. Each contact morphological feature in the multiple contact morphological features indicates the corresponding contact surface morphology of the relay.

[0055] Step 120: Based on multiple contact morphology features, determine the first prediction result of the relay. The first prediction result indicates the type of test the relay has undergone.

[0056] Step 130: Based on the first prediction result and multiple contact morphology features, determine the second prediction result for the relay. The second prediction result indicates the test process that the relay has undergone.

[0057] A relay is an electrical control device commonly used in control circuits. It enables the control of a large current with a small current, playing roles such as automatic adjustment, safety protection, and circuit switching. The contacts are a crucial component of a relay. Relay contacts are typically in a normally open or normally closed state and can be understood as the points that connect or disconnect signals. They usually consist of one or more pairs of metal contacts. The performance of the contacts is affected by factors such as contact material, contact pressure, load type, operating frequency, and atmospheric environment. During relay use, abnormalities may occur, leading to faults such as contact corrosion or contact welding.

[0058] Because relay contacts develop several fixed and distinguishable morphological features after being subjected to current surges, the test process experienced by the relay can be predicted by the surface morphology of the contacts. This can also be understood as the relevant operating conditions that led to the formation of this surface morphology, such as the magnitude of the current flowing through the contacts and the number of times the current flows through the contacts. Analysis method 100 is a method for analyzing the test process experienced by the relay (i.e., the specific operating conditions experienced by the relay) based on the surface morphology of the relay contacts. The application scenarios of this disclosure include relay testing scenarios and relay usage scenarios. In relay usage scenarios, "test type" and "test procedure" can also indicate typical operating conditions and specific operating parameters occurring at the relay contacts.

[0059] In step 110, contact morphology features characterizing the surface morphology of the relay contacts can be obtained. For a used relay, the contact morphology changes due to current flow. Contact morphology features can include characteristics related to contact surface height, flatness, and ablation area. In the example, contact morphology features can be selected from the following: contact resistance, skewness (Ssk), kurtosis (Sku), maximum peak height (Sp), maximum recess height (Sv), maximum height (Sz), arithmetic mean height (Sa), material ratio (SMr1), peak material volume (Vmp), core material volume (Vmc), ablation area percentage, surface area ratio, sputtering, and black edges. Among these:

[0060] Contact resistance represents the measured contact resistance of the contact point;

[0061] Skewness is used to assess the deviation of the height distribution on the contact surface;

[0062] Kurtosis is used to evaluate the sharpness of the height distribution on the contact surface, that is, the sharpness of the surface profile;

[0063] Maximum peak height represents the maximum value of the peak height on the contact surface;

[0064] The maximum recess height represents the maximum depth of the recess on the contact surface;

[0065] The maximum height is equal to the sum of the maximum peak height and the maximum concave depth.

[0066] The arithmetic mean height represents the arithmetic mean of the absolute vertical coordinates of the evaluation area on the contact surface used for analysis;

[0067] Material ratio represents the area ratio of the protruding peaks on the contact surface to the core region (which can be understood as the central part of the contact surface height distribution after specific filtering).

[0068] Peak material volume refers to the material volume of the protruding peak on the contact surface when the material ratio is a specific percentage (usually 10%).

[0069] The core material volume represents the material volume of the core area of ​​the contact surface when the material ratio is a specific percentage (usually 80%).

[0070] The ablation area percentage represents the ratio of the ablation area on the contact surface to the total area of ​​the measurement area.

[0071] The surface area ratio represents the ratio of the surface area of ​​the measurement area to the total area of ​​the measurement area;

[0072] Splashing is a human-identifiable factor used to indicate whether there is obvious splashing on the contact surface;

[0073] The black border is a human-identified factor used to indicate whether there is a black ablation edge on the contact surface.

[0074] After obtaining the required contact morphology features, in step 120, the type of test the relay will undergo is predicted based on these contact morphology features. In some embodiments, the test type for the relay may include "DC interruption test," "capacitive connection test," and "overload withstand test." Specifically, in the "DC interruption test," the relay contacts can be controlled to disconnect the circuit; in the "capacitive connection test," the relay can be connected to a DC or AC power grid, and the relay contacts will be subjected to a large current surge at the moment of connection; in the "overload withstand test," the relay can be placed in an overload operating scenario exceeding its rated capacity, such as continuous heating, applying an input current exceeding the rated current, or applying high voltage. It should be understood that in other embodiments, the relay may also undergo other types of tests, and this disclosure does not limit this.

[0075] After determining the type of test the relay will undergo, in step 130, the test procedure the relay will undergo will be predicted based on the predicted test type and the contact morphology characteristics of the relay. The test procedure refers to the specific test process performed on the relay under the test type obtained in step 120, and may include, for example, the applied current value, voltage value, number of tests, and test load. In some embodiments, other analysis results regarding the contact surface morphology may also be obtained in step 130, such as whether the contacts are welded.

[0076] The specific implementation methods for steps 110 to 130 will be detailed below.

[0077] By analyzing the contact morphology of the relay, the types and procedures of tests performed by the relay are determined in stages. This multi-level, step-by-step analysis accurately captures the relevant operating conditions experienced by the relay, improving the accuracy and efficiency of the analysis results. Even with large datasets and diverse analysis results, accurate and efficient analysis remains achievable.

[0078] According to some embodiments of this application, reference is made to Figure 2 Step 120 includes steps 210 to 230.

[0079] Step 210: Determine the first target variable. The first target variable is used to indicate the type of test performed on the relay.

[0080] Step 220: Determine at least one first feature variable associated with the first target variable from multiple contact morphology features.

[0081] Step 230: Determine the first prediction result using a decision tree model based on the first target variable and at least one first feature variable.

[0082] Decision tree model is a commonly used machine learning algorithm. It constructs a tree-structured model by learning the relationship between feature variables and target variables to predict the category or value of unknown data. In step 120, the decision tree model can be used to predict the type of test the relay will undergo.

[0083] In step 210, the first target variable, which is the target variable required by the decision tree model when predicting the test type, indicates the types of tests that can be performed on the relay. In the example described above, the test types may include "DC interruption test", "capacitive connection test", and "overload withstand test".

[0084] As mentioned above, relay contacts will produce several fixed and distinguishable morphological features after being subjected to current surges. Figures 11 to 13The diagrams illustrate the contact morphology of the relay after undergoing the "DC interruption test", "capacitive connection test", and "overload withstand test", respectively. It can be seen that the surface morphology of the contacts will be different after undergoing different types of tests.

[0085] Therefore, in step 220, a first characteristic variable associated with the test type can be determined from the acquired contact morphology features. This first characteristic variable can distinguish different test types, allowing the corresponding test type to be predicted based on these features. In one example, for the three test types mentioned above, the maximum recess height (Sv) in the surface morphology features differs significantly (e.g., for the DC breaking test, Sv = 39.684 μm; for the capacitive connection test, Sv = 96.383 μm; for the overload withstand test, Sv = 184.171 μm). Therefore, the maximum recess height can be determined as a first characteristic variable. Similarly, other first characteristic variables can be determined from the contact morphology features. It should be understood that the first characteristic variable can be predicted using a single characteristic variable or by combining multiple characteristic variables for comprehensive prediction; this disclosure does not limit this.

[0086] The first feature variable and the first target variable are the feature variables and target variables used by the decision tree model. By inputting them into the decision tree model, the decision tree model can output the corresponding prediction results and obtain the test type that the relay has undergone.

[0087] It should be understood that although referred to as "test type" here, in the actual use of relays, it can also represent the typical operating conditions that occur at the relay contacts when the relay is in use. The use cases of this disclosure are not limited to test scenarios.

[0088] In some embodiments, the decision tree model may be obtained by training with sample contact morphology features generated from multiple sample relays that have undergone different testing processes.

[0089] By identifying feature vectors associated with the test type from multiple contact morphology features, and then using a decision tree model to output the prediction results for the test type, the decision tree model can use the most relevant features during prediction, reduce the influence of redundant features, and improve the accuracy and precision of the prediction results.

[0090] According to some embodiments of this application, reference is made to Figure 3 Step 130 includes steps 310 to 320.

[0091] Step 310: Based on the first prediction result, determine at least one target feature variable associated with the first prediction result from multiple contact morphology features.

[0092] Step 320: Determine the second prediction result based on at least one target feature variable.

[0093] After determining the type of test the relay will undergo, in step 310, target feature variables associated with that test type will be identified from the acquired contact morphology features, and these target feature variables will be used to predict the test process. In step 320, the test process the relay will undergo will be predicted based on these target feature variables.

[0094] The specific implementation methods of steps 310 to 320 will be detailed below.

[0095] Based on the prediction results of the test type, relevant features are selected from the contact morphology features to predict the specific test process, instead of using a globally unified feature set for analysis. This allows the prediction process of the test process to use the most relevant features, improving the prediction efficiency and predictive ability of the test process.

[0096] According to some embodiments of this application, reference is made to Figure 4 Step 310 includes steps 410 to 430.

[0097] Step 410: In response to the first prediction result being the first test type, determine the contact morphology features related to the relay's breaking current from multiple contact morphology features to obtain at least one target feature variable.

[0098] Step 420: In response to the first prediction result being the second test type, determine the contact morphology features related to the capacitive load of the relay from multiple contact morphology features to obtain at least one target feature variable.

[0099] Step 430: In response to the first prediction result being the third test type, determine the contact morphology features related to the overload tolerance of the relay from multiple contact morphology features to obtain at least one target feature variable.

[0100] Continuing with the example of the three test types mentioned above—"DC interruption test," "capacitive connection test," and "overload withstand test"—the first predicted result will be one of these three test types. In this example, the first test type can indicate a DC interruption test, the second test type can indicate a capacitive connection test, and the third test type can indicate an overload withstand test.

[0101] When the test type predicted in step 120 is the first test type, characteristic variables related to the relay's breaking current can be determined as target characteristic variables from the acquired multiple contact morphology features. These characteristic variables can effectively affect factors such as the breaking capacity and the number of times the current flows through the contacts. Therefore, these characteristic variables can be used as target characteristic variables to obtain the second prediction result. In one example, factors related to the relay's breaking current include contact breaking time, bounce time, contact material, electrical wear and mechanical wear generated by the contacts, etc. Therefore, contact morphology features related to these factors can be used as target characteristic variables, such as material ratio, maximum recess height, maximum height, and ablation area ratio.

[0102] When the predicted test type in step 120 is the second test type, characteristic variables related to the capacitive load of the relay can be determined as target characteristic variables from the multiple contact morphology features obtained. These characteristic variables can effectively affect factors such as the impact capability of the current flowing through the contacts and the durability of the contacts. Therefore, these characteristic variables can be used as target characteristic variables to obtain the second prediction result. In one example, factors related to the capacitive load of the relay include contact material, contact resistance, surge current, surge time, etc. Therefore, contact morphology features related to these factors can be used as target characteristic variables, such as contact resistance, material ratio, ablation area ratio, etc.

[0103] When the predicted test type in step 120 is the third test type, characteristic variables related to the overload tolerance of the relay can be determined as target characteristic variables from the multiple contact morphology features obtained. These characteristic variables include high-temperature resistance and material strength related to the relay under overload conditions. These characteristic variables can be used as target characteristic variables to obtain the second prediction result. In one example, factors related to the overload tolerance of the relay include contact material, operating temperature, and operating current. Therefore, contact morphology features related to these factors can be used as target characteristic variables, such as material ratio, ablation area ratio, presence of black edges, and spatter.

[0104] It should be understood that in other embodiments, the first prediction result may also include more types of tests. Depending on the different types of tests, different contact morphology features of the relay can be determined as target feature variables from the multiple contact morphology features obtained. This disclosure does not limit this.

[0105] Based on the prediction results of the test type obtained from the previous prediction, the feature set used for this prediction is dynamically adjusted, which can comprehensively consider the prediction results of each level, thereby obtaining more accurate prediction results of the test process.

[0106] According to some embodiments of this application, the second prediction result includes the relay's test current and / or the number of tests. (See reference...) Figure 5 Step 320 includes steps 510 and / or 520.

[0107] Step 510: Determine the test current of the relay based on at least one target characteristic variable.

[0108] Step 520: Determine the number of tests for the relay based on at least one target feature variable.

[0109] Since abnormalities such as contact surface erosion of relays are mainly caused by factors such as large current, the second prediction result can include the relay's test current and the number of tests. For example, the test current can include current-related indicators such as the magnitude of the current flowing through the relay contacts and the duration of the current, and the number of tests can include the number of times current is applied to the relay contacts.

[0110] After determining the type of test the relay will undergo, the test current and / or number of tests for the relay in that test can be further determined based on the target characteristic variables related to that test type determined in step 310. The specific process for determining the test current and the number of tests will be detailed below.

[0111] It should be understood that although referred to as "test current" or "number of tests" here, in the actual use of relays, it can also refer to indicators related to the current flowing through the relay contacts when the relay is in use, the number of times the current flows through the relay contacts, etc. The use scenarios of this disclosure are not limited to testing scenarios.

[0112] In some embodiments, steps 510 and 520 can be performed individually, for example, predicting only the test current and / or only the number of tests; or they can be performed sequentially, for example, predicting the number of tests after predicting the test current, which is not limited in this disclosure.

[0113] By predicting the test current and the number of tests conducted on the relay, the relevant operating conditions experienced by the relay can be accurately obtained, and the cause of relay failure can be further identified.

[0114] According to some embodiments of this application, reference is made to Figure 6 Step 510 includes steps 610 to 620.

[0115] Step 610: Determine the second target variable. The second target variable is used to indicate the current level during relay testing.

[0116] Step 620: Determine the test current of the relay using a decision tree model based on the second target variable and at least one target feature variable.

[0117] In step 610, the second objective variable, which is the target variable required by the decision tree model to predict the test current, can indicate the current level during relay testing or can be understood as the current level flowing through the relay. It should be understood that when this analysis method 100 is applied to relay usage scenarios or failure analysis scenarios, the second objective variable also indicates the current level flowing through the relay contacts during relay use.

[0118] As described above, in step 310, the target feature variables associated with the determined test type are obtained. These target feature variables and the second target variable are also the feature variables and target variables used by the decision tree model. Inputting these into the decision tree model allows it to output the corresponding prediction result, thus obtaining the test current of the relay.

[0119] In some embodiments, the decision tree model may be obtained by training with sample contact morphology features generated from multiple sample relays that have undergone different testing processes.

[0120] By identifying the target variable that indicates the test current level and combining it with the target feature variable associated with the test type, the decision tree model can output the prediction result for the test current. This allows the decision tree model to use the features most relevant to the test current during prediction, reducing the influence of redundant features and improving the accuracy and precision of the prediction results.

[0121] According to some embodiments of this application, step 610 includes: determining a second target variable in response to a first test result being any one of a first test type, a second test type, and a third test type.

[0122] In the example described above, the first test type indicates a DC breaking test, the second test type indicates a capacitive switching test, and the third test type indicates an overload withstand test. All three test types involve current flowing through the relay. Therefore, if the first prediction result indicates that the relay undergoes any one of these three test types, the second target variable can be determined to predict the relay's test current.

[0123] Only when the first test result indicating the test type is a specific test type is the second target variable related to the current level determined to predict the current level. The subsequent prediction process can be determined based on the different prediction results, thereby improving both prediction accuracy and prediction efficiency.

[0124] According to some embodiments of this application, reference is made to Figure 7 Step 520 includes steps 710 to 720.

[0125] Step 710: Determine the third target variable. The third target variable is used to indicate the number of operations performed during relay testing.

[0126] Step 720: Determine the number of tests for the relay using a decision tree model based on the third objective variable and at least one objective feature variable.

[0127] In step 710, the third objective variable, which is the target variable required by the decision tree model to predict the number of tests, can indicate the number of operations performed during relay testing. It should be understood that when this analysis method 100 is applied to relay usage scenarios or failure analysis scenarios, the third objective variable also indicates the number of times the relay contacts are used, and can also be understood as the number of times current flows through the contacts.

[0128] As mentioned above, in step 310, the target feature variable associated with the determined test type is obtained. The target feature variable and the third target variable are also the feature variables and target variables used by the decision tree model. Inputting these into the decision tree model allows it to output the corresponding prediction result, thus obtaining the number of times the relay is tested.

[0129] In some embodiments, the decision tree model may be obtained by training with sample contact morphology features generated from multiple sample relays that have undergone different testing processes.

[0130] By identifying the target variable indicating the number of operations and combining it with the target feature variable associated with the test type, the decision tree model can output the prediction result for the number of tests. This allows the decision tree model to use the features most relevant to the number of tests when making predictions, reducing the influence of redundant features and improving the accuracy and precision of the prediction results.

[0131] According to some embodiments of this application, step 710 includes: determining a third target variable in response to a first test result being either a first test type or a second test type.

[0132] In the example above, the first test type indicates a DC breaking test, the second test type indicates a capacitive switching test, and the third test type indicates an overload withstand test. For the first two test types, the number of tests is involved, i.e., the number of times current flows through the relay contacts. For the third test type, since the relay is typically only subjected to an overload withstand test once, the number of tests can be determined as 1, and does not need to be predicted by the decision tree model. Therefore, if the first prediction result indicates that the relay has undergone either the first or second test type, the third objective variable can be determined to predict the number of tests performed on the relay.

[0133] A third target variable related to the number of tests is determined only when the first test result indicating the test type is a specific test type. This allows for prediction of the number of tests. The subsequent prediction process can be determined based on the different prediction results, thereby improving both prediction accuracy and efficiency.

[0134] According to some embodiments of this application, reference is made to Figure 8 Step 110 includes at least one of steps 810 to 830.

[0135] Step 810: Obtain multiple contact point morphological features from a pre-established database.

[0136] Step 820: Obtain multiple contact morphology features based on the pre-input image of the relay.

[0137] Step 830: Obtain multiple contact point morphology features based on manually input feature values.

[0138] The method for obtaining the contact morphology features can be arbitrarily selected from steps 810 to 830.

[0139] In step 810, the database stores different contact morphological features of relays, which can be directly read from the database and applied to the analysis of relay contact morphology.

[0140] In step 820, the image of the relay can be analyzed to determine the corresponding contact morphology features. For example, machine learning models can be used to determine the contact morphology features based on the relay image. It should be understood that the relay image can include two-dimensional and three-dimensional images of the relay contacts, and this disclosure does not limit this. In one example, the relay to be analyzed can be scanned and modeled to obtain its three-dimensional image. By analyzing the three-dimensional image, multiple contact morphology features can be obtained.

[0141] In step 830, the contact morphology features can also be manually input. For example, the black edge and splatter conditions mentioned above can be determined and input manually. When there is splatter (black ablation edge) on the contact surface, feature value 1 can be manually input; when there is no splatter (black ablation edge) on the contact surface, feature value 0 can be manually input; when it is uncertain whether there is splatter (black ablation edge) on the contact surface, feature value 2 can be manually input.

[0142] Figure 10 This illustrates an interface with the morphological characteristics of an input touch point. In Figure 10 In the example shown, the method for obtaining all the contact morphology features can be arbitrarily selected from steps 810 to 830 above.

[0143] Using multiple methods to obtain the contact morphology characteristics of relays can be applied to different application scenarios, improving the adaptability and flexibility of the analysis method.

[0144] According to some embodiments of this application, the plurality of contact morphological features include at least one of the following:

[0145] Electrical contact parameters of the relay contacts;

[0146] The morphological parameters of the relay contacts;

[0147] Parameters are identified manually.

[0148] As mentioned above, contact morphology features can include characteristics related to contact surface height, flatness, ablation area, etc.

[0149] In this example, contact morphology features can be selected from the following: contact resistance, skewness (Ssk), kurtosis (Sku), maximum peak height (Sp), maximum recess height (Sv), maximum height (Sz), arithmetic mean height (Sa), material ratio (SMr1), peak material volume (Vmp), core material volume (Vmc), ablation area percentage, surface area ratio, sputtering, and black edge. In this example, contact resistance is an electrical contact parameter, skewness (Ssk), kurtosis (Sku), maximum peak height (Sp), maximum recess height (Sv), maximum height (Sz), arithmetic mean height (Sa), material ratio (SMr1), peak material volume (Vmp), core material volume (Vmc), ablation area percentage, and surface area ratio are morphology parameters, and sputtering and black edge are manually identified parameters.

[0150] By using different types of contact morphology features, the contact morphology of relays can be accurately characterized, thereby improving the accuracy of prediction results.

[0151] According to some embodiments of this application, the analysis method 100 further includes:

[0152] After step 110: preprocess the morphological features of multiple contact points.

[0153] Since the obtained contact morphology features may not be suitable for direct analysis, they need to be preprocessed.

[0154] Preprocessing the acquired contact morphology features can improve data quality and facilitate subsequent analysis and identification.

[0155] According to some embodiments of this application, preprocessing multiple contact morphology features includes a first process 900. (See reference...) Figure 9 The first process 900 includes at least one of steps 910 to 930.

[0156] Step 910: Perform data cleaning on the morphological features of multiple contact points.

[0157] Step 920: Convert the non-numerical contact morphology features among the multiple contact morphology features into numerical contact morphology features.

[0158] Step 930: Convert the morphological features of multiple contact points into a matrix form.

[0159] Data preprocessing can include data cleaning, numerical type conversion, matrix form conversion, etc.

[0160] In step 910, data cleaning may include data deduplication, missing value filling, data formatting, data consistency checking, and data denoising. Specifically, data deduplication involves identifying and deleting duplicate data; missing value filling involves checking for missing contact morphology features and filling them in, for example, different test types use different data, and some parameters may not be needed, resulting in empty corresponding contact morphology features, which need to be filled to facilitate analysis by the decision tree model; data formatting involves unifying the data format to a consistent format, such as setting all numbers to retain a consistent number of digits; data consistency checking involves checking the contact morphology features to ensure they are logically reasonable, such as identifying errors like negative contact resistance; and data denoising involves reducing random errors or biases in the data.

[0161] In step 920, since some contact morphology features may be obtained in a non-numerical form, such as the presence of black edges or the absence of splashes on the contact surface when acquiring the contact surface morphology, these non-numerical contact morphology features can be converted into numerical forms. For example, the presence of black edges on the contact surface can be represented by 1, and the absence of splashes on the contact surface can be represented by 0. In some embodiments, a similar conversion method can also be adopted for the first prediction result, second prediction result, first target variable, second target variable, and third target variable mentioned above. For example, if the test type indicated by the first target variable is a first test type (e.g., DC breaking test), a second test type (e.g., capacitive connection test), or a third test type (e.g., overload withstand test), they can be represented by 1, 2, and 3, respectively.

[0162] In step 930, some contact morphology features can be represented in matrix form to facilitate subsequent analysis by the decision tree model.

[0163] By fully preprocessing the contact point morphology features, the data input to the decision tree model becomes more accurate, further improving the reliability and accuracy of the prediction results.

[0164] Based on the same technical concept, this application provides an apparatus for analyzing the morphology of relay contacts. Embodiments of the apparatus for analyzing the morphology of relay contacts can be referred to those of the method for analyzing the morphology of relay contacts; repeated details will not be elaborated further. Reference Figure 14 The relay contact morphology analysis device 1400 includes a first module 1410, a second module 1420 and a third module 1430.

[0165] The first module 1410 is used to acquire multiple contact morphological features of the relay. Each of the multiple contact morphological features indicates the corresponding contact surface morphology of the relay.

[0166] The second module 1420 is used to determine a first prediction result for the relay based on multiple contact morphology features. The first prediction result indicates the type of test the relay has undergone.

[0167] The third module 1430 is used to determine a second prediction result for the relay based on the first prediction result and multiple contact morphology features. The second prediction result indicates the test process that the relay has undergone.

[0168] The first module 1410, the second module 1420, and the third module 1430 in the relay contact morphology analysis device 1400 can correspond to steps 110 to 130 in the relay contact morphology analysis method 100, and will not be described in detail here for the sake of brevity. It should be understood that, corresponding to the embodiment of the relay contact morphology analysis method 100, the embodiment of the relay contact morphology analysis device 1400 may also include more modules.

[0169] It should be noted that the functions of the modules discussed herein can be divided into multiple modules, and / or at least some functions of multiple modules can be combined into a single module. The specific actions performed by a particular module discussed herein include the specific module itself performing the action, or alternatively, the specific module calling or otherwise accessing another component or module that performs the action (or performs the action in conjunction with the specific module). Therefore, a specific module performing an action can include the specific module performing the action itself and / or another module that performs the action, called or otherwise accessed by the specific module.

[0170] It should also be understood that this article can describe various technologies in the general context of software and hardware components or program modules. The above regarding... Figure 14The described modules can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these modules can be implemented as computer program code / instructions configured to execute in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuit. Hardware logic / circuit may include integrated circuit chips (which include processors (e.g., Central Processing Unit (CPU), microcontrollers, microprocessors, digital signal processors (DSPs), etc.), memory, one or more communication interfaces, and / or one or more components of other circuitry), and may optionally execute received program code and / or include embedded firmware to perform functions.

[0171] This application provides a computing device 1500, such as... Figure 15 As shown. Figure 15 An example configuration of a computing device 1500 that can be used to implement the relay contact morphology analysis method 100 described herein is shown. For example, the relay contact morphology analysis apparatus 1400 described above may be implemented wholly or at least partially by the computing device 1500 or a similar device or system.

[0172] The computing device 1500 may include at least one processor 1505 capable of communicating with each other, such as via a bus 1504 or other suitable connection, a memory 1507, multiple communication interfaces 1502, a display device 1501, other input / output (I / O) devices 1503, and one or more mass storage devices 1506. Instructions are stored on the memory 1507 that, when executed by the processor 1505, cause the processor 1505 to perform a method for analyzing the morphology of relay contacts as described in the above embodiments.

[0173] The computing device 1500 can be a variety of different types of devices. Examples of the computing device 1500 include, but are not limited to: desktop computers, server computers, laptop or netbook computers, mobile devices (e.g., tablet computers, cellular or other wireless phones (e.g., smartphones), notebook computers, mobile stations), wearable devices (e.g., glasses, watches), entertainment devices (e.g., entertainment appliances, set-top boxes communicatively coupled to a display device, game consoles), televisions or other display devices, automotive computers, and so on.

[0174] Processor 1505 may be a single processing unit or multiple processing units, and all processing units may include single or multiple computing units or multiple cores. Processor 1505 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. Among other capabilities, processor 1505 may be configured to acquire and execute computer-readable instructions stored in memory 1507, mass storage device 1506, or other computer-readable media, such as program code of operating system 1508, program code of application program 1509, program code of other program 1510, etc.

[0175] Memory 1507 and mass storage device 1506 are examples of computer-readable storage media for storing instructions executed by processor 1505 to perform the various functions described above. For example, memory 1507 may generally include both volatile and non-volatile memory (e.g., RAM, ROM, etc.). Furthermore, mass storage device 1506 may generally include hard disk drives, solid-state drives, removable media, including external and removable drives, memory cards, flash memory, floppy disks, optical disks (e.g., CDs, DVDs), storage arrays, network-attached storage, storage area networks, etc. Both memory 1507 and mass storage device 1506 may be collectively referred to herein as memory or computer-readable storage media, and may be non-transitory media capable of storing computer-readable, processor-executable program instructions as computer program code, which may be executed by processor 1505 as a specific machine configured to perform the operations and functions described in the examples herein.

[0176] Multiple programs can be stored on mass storage device 1506. These programs include operating system 1508, one or more application programs 1509, other programs 1510, and program data 1511, and they can be loaded into memory 1507 for execution. Examples of such application programs or program modules may include, for example, computer program logic (e.g., computer program code or instructions) for implementing the following components / functions: relay contact morphology analysis device 1400 (including first module 1410, second module 1420, and third module 1430), relay contact morphology analysis method 100 (including any suitable steps of relay contact morphology analysis method 100), and / or other embodiments described herein.

[0177] Although Figure 15The data is illustrated as being stored in memory 1507 of computing device 1500, but operating system 1508, application program 1509, other program 1510 and program data 1511 or portions thereof may be implemented using any form of computer-readable medium accessible by computing device 1500.

[0178] One or more communication interfaces 1502 are used for exchanging data with other devices, such as via a network, direct connection, etc. Such communication interfaces can be one or more of the following: any type of network interface (e.g., a network interface card (NIC)), wired or wireless (such as IEEE 802.11 Wireless LAN (WLAN)) wireless interface, Wi-MAX interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, Bluetooth™ interface, Near Field Communication (NFC) interface, etc. Communication interface 1502 can facilitate communication across various network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. Communication interface 1502 can also provide communication with external storage devices (not shown), such as storage arrays, network-attached storage, storage area networks, etc.

[0179] In some examples, a display device 1501, such as a monitor, may be included for displaying information and images to the user. Other I / O devices 1503 may be devices that receive various inputs from the user and provide various outputs to the user, and may include touch input devices, gesture input devices, cameras, keyboards, remote controls, mice, printers, audio input / output devices, and so on.

[0180] The techniques described herein can be supported by these various configurations of computing device 1500, and are not limited to specific examples of the techniques described herein. For example, the functionality can also be implemented wholly or partially on a “cloud” using a distributed system. A cloud includes and / or represents a platform for resources. The platform abstracts the underlying functionality of the cloud’s hardware (e.g., servers) and software resources. Resources may include applications and / or data that can be used when performing computational processing on servers remote from computing device 1500. Resources may also include services provided via the Internet and / or via subscriber networks such as cellular or Wi-Fi networks. The platform can abstract resources and functionality to connect computing device 1500 to other computing devices. Therefore, the implementation of the functionality described herein can be distributed throughout the cloud. For example, the functionality can be implemented partly on computing device 1500 and partly through a platform that abstracts the functionality of the cloud.

[0181] This application also provides a computer-readable storage medium storing instructions that, when executed individually or jointly by one or more processors of a computing device, cause the computing device to perform the methods described in any of the above embodiments.

[0182] Computer-readable storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD, or other optical storage devices, magnetic cassettes, magnetic tapes, disk storage devices or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by computer equipment.

[0183] This application also provides a computer program product including instructions that, when executed individually or jointly by one or more processors of a computing device, cause the computing device to perform the methods as described in any of the above embodiments.

[0184] A specific embodiment of this application is described below. It should be understood that this specific embodiment is described for illustrative purposes only and should not be construed as limiting the scope of this application.

[0185] like Figures 11 to 13 As shown, relay contacts will produce different surface morphologies after undergoing different test types. Therefore, the test process that the relay has undergone can be determined based on the relay's surface morphology.

[0186] First, the morphological features of multiple relay contacts are acquired. These features can include electrical contact parameters, morphological parameters, and manually identified parameters, specifically including contact resistance, skewness (Ssk), kurtosis (Sku), maximum peak height (Sp), maximum recess height (Sv), maximum height (Sz), arithmetic mean height (Sa), material ratio (SMr1), peak material volume (Vmp), core material volume (Vmc), ablation area percentage, surface area ratio, sputtering, and black edge characteristics. After acquiring the contact morphological features, preprocessing can be performed, such as data cleaning, converting non-numerical contact morphological features to numerical features, and converting them to matrix form.

[0187] A first target variable is determined to indicate the type of test performed on the relay. A first feature variable associated with the first target variable is determined from multiple acquired contact morphology features. The first target variable and the first feature variable are used as input to a decision tree model, which outputs the corresponding first prediction result, i.e., the type of test the relay has undergone.

[0188] After determining the type of test the relay underwent, target characteristic variables related to that test type were identified from the acquired contact morphology features. When the test type is the first test type, characteristic variables related to the relay's breaking current were identified as target characteristic variables from the acquired contact morphology features. When the test type is the second test type, characteristic variables related to the relay's capacitive load were identified as target characteristic variables from the acquired contact morphology features. When the test type is the third test type, characteristic variables related to the relay's overload tolerance were identified as target characteristic variables from the acquired contact morphology features.

[0189] If the first prediction result indicates that the relay has undergone any of the three types of tests, a second target variable indicating the current level flowing through the relay can be determined, and the relay's test current can be predicted. The second target variable and the target feature variable are used as inputs to the decision tree model, which outputs the corresponding second prediction result, i.e., the relay's test current.

[0190] If the first prediction result indicates that the relay has undergone either the first test type or the second test type, a third target variable can be determined to indicate the number of operations performed during relay testing, thus predicting the number of tests performed on the relay. The third target variable and the target feature variable are used as inputs to the decision tree model, which outputs the corresponding second prediction result, i.e., the number of tests performed on the relay.

[0191] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for analyzing the morphology of relay contacts, characterized in that, include: Multiple contact morphological features of a relay are obtained, and each of the multiple contact morphological features indicates the corresponding contact surface morphology of the relay. Based on the morphological features of the multiple contacts, a first prediction result of the relay is determined, and the first prediction result indicates the type of test that the relay has undergone. Based on the first prediction result and the morphological features of the plurality of contacts, a second prediction result for the relay is determined, and the second prediction result indicates the test process that the relay has undergone.

2. The analytical method according to claim 1, characterized in that, The determination of the first prediction result of the relay based on the morphological features of the multiple contact points includes: Determine a first target variable, which indicates the type of test performed on the relay; Determine at least one first feature variable associated with the first target variable from the plurality of contact morphology features; The first prediction result is determined using a decision tree model based on the first target variable and the at least one first feature variable.

3. The analytical method according to claim 1, characterized in that, The step of determining the second prediction result of the relay based on the first prediction result and the morphological features of the plurality of contacts includes: Based on the first prediction result, at least one target feature variable associated with the first prediction result is determined from the plurality of contact morphology features; The second prediction result is determined based on the at least one target feature variable.

4. The analytical method according to claim 3, characterized in that, The step of determining at least one target feature variable associated with the first prediction result from the plurality of contact point morphology features based on the first prediction result includes: In response to the first prediction result being a first test type, contact morphology features related to the breaking current of the relay are determined from the plurality of contact morphology features to obtain the at least one target feature variable; In response to the first prediction result being the second test type, contact morphology features related to the capacitive load of the relay are determined from the plurality of contact morphology features to obtain the at least one target feature variable; In response to the first prediction result being the third test type, contact morphology features related to the overload tolerance of the relay are determined from the plurality of contact morphology features to obtain the at least one target feature variable.

5. The analytical method according to claim 3, characterized in that, The second prediction result includes the test current and / or number of tests of the relay, and determining the second prediction result based on the at least one target feature variable includes: Based on the at least one target characteristic variable, determine the test current of the relay; and / or The number of tests for the relay is determined based on the at least one target feature variable.

6. The analytical method according to claim 5, characterized in that, Determining the test current of the relay based on the at least one target feature variable includes: Determine a second target variable, which is used to indicate the current level when testing the relay; The test current of the relay is determined using a decision tree model based on the second target variable and the at least one target feature variable.

7. The analytical method according to claim 6, characterized in that, The determination of the second target variable includes: In response to the first test result being any of the first test type, the second test type, and the third test type, the second target variable is determined.

8. The analytical method according to claim 5, characterized in that, Determining the number of tests for the relay based on the at least one target feature variable includes: A third target variable is determined, which indicates the number of operations performed during the test of the relay; The number of tests for the relay is determined using a decision tree model based on the third objective variable and the at least one objective feature variable.

9. The analytical method according to claim 8, characterized in that, The determination of the third target variable includes: In response to the first test result being either the first test type or the second test type, the third target variable is determined.

10. The analytical method according to any one of claims 1-9, characterized in that, The acquisition of multiple contact morphological features of the relay includes at least one of the following: Obtain the morphological features of the multiple contact points from a pre-established database; The morphological features of the plurality of contacts are obtained based on the pre-input image of the relay; The morphological features of the multiple contact points are obtained based on the feature values ​​input manually.

11. The analytical method according to any one of claims 1-9, characterized in that, The plurality of contact morphological features include at least one of the following: The electrical contact parameters of the relay contacts; The morphological parameters of the relay contacts; Parameters are identified manually.

12. The analytical method according to any one of claims 1-9, characterized in that, The analytical method further includes: After acquiring the morphological features of multiple contacts of the relay: The morphological features of the multiple contact points are preprocessed.

13. The analytical method according to claim 12, characterized in that, The preprocessing of the plurality of contact point morphology features includes at least one of the following: Data cleaning is performed on the morphological features of the multiple contact points; Convert the non-numerical contact morphology features among the multiple contact morphology features into numerical contact morphology features. The morphological features of the multiple contact points are converted into a matrix form.

14. An analytical device for relay contact morphology, characterized in that, include: The first module is used to acquire multiple contact morphological features of a relay, wherein each contact morphological feature indicates the corresponding contact surface morphology of the relay. The second module is used to determine a first prediction result of the relay based on the morphological features of the plurality of contacts, wherein the first prediction result indicates the type of test that the relay has undergone; The third module is used to determine a second prediction result for the relay based on the first prediction result and the morphological features of the plurality of contacts. The second prediction result indicates the test process that the relay has undergone.

15. A computing device, characterized in that, include: At least one processor; as well as At least one memory communicatively connected to the at least one processor, the at least one memory storing instructions that, when executed individually or jointly by the at least one processor, cause the computing device to perform the analysis method of any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, The device stores instructions that, when executed individually or jointly by one or more processors of the computing device, cause the computing device to perform the analysis method according to any one of claims 1 to 13.

17. A computer program product, characterized in that, The instruction includes instructions that, when executed individually or jointly by one or more processors of a computing device, cause the computing device to perform the analysis method of any one of claims 1 to 13.

Images