Low-voltage electrical apparatus life prediction method, device and storage medium

Abstract

The application provides a low-voltage electrical appliance life prediction method and device and a storage medium, and relates to the technical field of low-voltage electrical appliances. In the method, the opening and closing data of the low-voltage electrical appliance to be predicted in a plurality of opening and closing cycles in a historical time period is obtained; according to the opening and closing data, a target category to which the low-voltage electrical appliance to be predicted belongs is determined based on a pre-classification model, and the pre-classification model is obtained by training according to a first training sample data set; according to the target category to which the low-voltage electrical appliance to be predicted belongs, a target special prediction model is determined; and according to the opening and closing data, the remaining life parameter of the low-voltage electrical appliance to be predicted is predicted based on the target special prediction model, so that the target category to which the low-voltage electrical appliance to be predicted belongs can be determined according to the pre-classification model, and then the target special prediction model matched with the target category can be selected to predict the remaining life parameter of the low-voltage electrical appliance to be predicted, thereby improving the accuracy of the prediction result.

Description

Technical Field

[0001] This application relates to the field of low-voltage electrical technology, and in particular to a method, apparatus and storage medium for predicting the lifespan of low-voltage electrical appliances. Background Technology

[0002] Low-voltage electrical appliances typically refer to appliances that operate at AC voltages below 1200V or DC voltages below 1500V. They are widely used in industrial production and daily life. However, in some applications where there are high requirements for the stability and safety of equipment operation, such as elevators, high-speed trains, and new energy sources, failure to replace low-voltage electrical appliances in a timely manner before they fail may cause significant losses and inconvenience to enterprise production and people's lives. Therefore, it is necessary to predict the remaining electrical life of low-voltage electrical appliances.

[0003] Currently, the estimated remaining service life of low-voltage electrical appliances is generally estimated based on the appliance's usage time and the expected usage time at the time of manufacture.

[0004] It can be seen that the existing methods for estimating the remaining lifespan of low-voltage electrical appliances are relatively simple and have the problem of inaccurate estimation. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing a method, apparatus, and storage medium for predicting the lifespan of low-voltage electrical appliances, which can improve the accuracy of the prediction results.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0007] In a first aspect, the present invention provides a method for predicting the lifespan of low-voltage electrical appliances, comprising:

[0008] Obtain the opening and closing data of the low-voltage electrical appliance to be predicted within multiple opening and closing cycles over a historical time period;

[0009] Based on the opening and closing data, the target category of the low-voltage electrical appliance to be predicted is determined based on the pre-classification model. The pre-classification model is obtained by training based on the first training sample dataset. The first training sample dataset includes the opening and closing data of the first sample electrical appliances corresponding to multiple first sample electrical appliances in the first historical time period, and the corresponding categories are labeled.

[0010] Based on the target category to which the low-voltage electrical appliance to be predicted belongs, determine the target-specific prediction model;

[0011] Based on the circuit breaker opening and closing data, the remaining life parameters of the low-voltage electrical appliance to be predicted are predicted using the target-specific prediction model. The target-specific prediction model is trained and obtained based on a second training sample dataset. The second training sample dataset includes the circuit breaker opening and closing data of multiple second sample electrical appliances belonging to the target category within a second historical time period, and the corresponding remaining life parameters are labeled.

[0012] In an optional implementation, determining a target-specific prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs includes:

[0013] Based on the target category of the low-voltage electrical appliance to be predicted and the preset mapping relationship, a target dedicated prediction model is determined in at least one dedicated prediction model. The preset mapping relationship includes at least one mapping relationship between the category and the dedicated prediction model.

[0014] In an optional implementation, the method further includes:

[0015] Obtain the first training sample dataset of multiple first sample electrical appliances in multiple opening and closing cycles within the first historical time period. The first training sample dataset includes multiple first sample opening and closing data, and each first sample opening and closing data is labeled with the total life status of the first sample electrical appliance.

[0016] The pre-classification model is trained and obtained based on the first training sample dataset.

[0017] In an optional implementation, the method further includes:

[0018] Obtain a second training sample dataset of multiple second sample electrical appliances belonging to the target category within a second historical time period and within multiple opening and closing cycles. The second training sample dataset includes multiple second sample opening and closing data, and each second sample opening and closing data is labeled with the remaining life parameter corresponding to the second sample electrical appliance.

[0019] Based on the second training sample dataset, a target-specific prediction model is trained and obtained.

[0020] In an optional implementation, acquiring the opening and closing data of the low-voltage electrical appliance to be predicted within multiple opening and closing cycles over a historical time period includes:

[0021] The voltage and / or current data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within the historical time period are acquired by the acquisition device.

[0022] Based on the voltage data and / or current data, the electrical lifetime characteristics of the low-voltage electrical appliance to be predicted are obtained, and the electrical lifetime characteristics are used as the opening and closing data of the low-voltage electrical appliance to be predicted.

[0023] In an optional implementation, after training the pre-classification model based on the first training sample dataset, the method further includes:

[0024] Obtain a third training sample dataset of multiple first sample electrical appliances within a third historical time period in multiple opening and closing cycles. The third training sample dataset includes multiple third sample opening and closing data. Each third sample opening and closing data is labeled with the total life status of the first sample electrical appliance. The third historical time period is a different time period from the first historical time period.

[0025] The pre-classification model is updated based on the third training sample dataset.

[0026] In an optional implementation, at least one of the categories includes: a first total lifetime range and a second total lifetime range, wherein the first total lifetime range is less than the second total lifetime range.

[0027] In an optional implementation, the electrical life characteristics of the low-voltage electrical appliance to be predicted include at least one of the following: contact voltage, contact current, contact resistance, arcing time, arcing energy, and arcing power.

[0028] In a second aspect, the present invention provides a lifespan prediction device for low-voltage electrical appliances, comprising:

[0029] The acquisition module is used to acquire the opening and closing data of the low-voltage electrical appliance to be predicted in multiple opening and closing cycles within a historical time period.

[0030] The first determining module is used to determine the target category of the low-voltage electrical appliance to be predicted based on the opening and closing data and a pre-classification model. The pre-classification model is trained and obtained based on a first training sample dataset. The first training sample dataset includes the opening and closing data of the first sample electrical appliances corresponding to multiple first sample electrical appliances within a first historical time period, and the corresponding categories are labeled.

[0031] The second determining module is used to determine a target-specific prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs;

[0032] The prediction module is used to predict the remaining life parameters of the low-voltage electrical appliance to be predicted based on the opening and closing data and the target-specific prediction model. The target-specific prediction model is trained and obtained based on a second training sample dataset. The second training sample dataset includes the second sample opening and closing data of multiple second sample electrical appliances belonging to the target category within a second historical time period, and the corresponding remaining life parameters are labeled.

[0033] In an optional implementation, the second determining module is specifically used to determine a target dedicated prediction model in at least one dedicated prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs and a preset mapping relationship, wherein the preset mapping relationship includes at least one mapping relationship between a category and a dedicated prediction model.

[0034] In an optional implementation, the life prediction device further includes: a first training module, used to acquire a first training sample dataset of multiple first sample electrical appliances in multiple opening and closing cycles within a first historical time period, the first training sample dataset including multiple first sample opening and closing data, each first sample opening and closing data being labeled with the total life status corresponding to the first sample electrical appliance.

[0035] The pre-classification model is trained and obtained based on the first training sample dataset.

[0036] In an optional implementation, the life prediction device further includes: a second training module, used to acquire a second training sample dataset of multiple second sample electrical appliances belonging to the target category within a second historical time period and within multiple opening and closing cycles, the second training sample dataset including multiple second sample opening and closing data, each second sample opening and closing data being labeled with the remaining life parameter corresponding to the second sample electrical appliance.

[0037] Based on the second training sample dataset, a target-specific prediction model is trained and obtained.

[0038] In an optional implementation, the acquisition module is specifically used to acquire voltage data and / or current data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within the historical time period through an acquisition device.

[0039] Based on the voltage data and / or current data, the electrical lifetime characteristics of the low-voltage electrical appliance to be predicted are obtained, and the electrical lifetime characteristics are used as the opening and closing data of the low-voltage electrical appliance to be predicted.

[0040] In an optional implementation, the first training module is further configured to acquire a third training sample dataset of multiple first sample electrical appliances within a third historical time period in multiple opening and closing cycles. The third training sample dataset includes multiple third sample opening and closing data, and each third sample opening and closing data is labeled with the total life status corresponding to the first sample electrical appliance. The third historical time period is a different time period from the first historical time period.

[0041] The pre-classification model is updated based on the third training sample dataset.

[0042] In an optional implementation, at least one of the categories includes: a first total lifetime range and a second total lifetime range, wherein the first total lifetime range is less than the second total lifetime range.

[0043] In an optional implementation, the electrical life characteristics of the low-voltage electrical appliance to be predicted include at least one of the following: contact voltage, contact current, contact resistance, arcing time, arcing energy, and arcing power.

[0044] Thirdly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the life prediction method for low-voltage electrical appliances as described in any of the foregoing embodiments.

[0045] Fourthly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the life prediction method for low-voltage electrical appliances as described in any of the foregoing embodiments.

[0046] The beneficial effects of this application are:

[0047] The low-voltage electrical appliance life prediction method, apparatus, and storage medium provided in this application acquires the opening and closing data of the low-voltage electrical appliance to be predicted in multiple opening and closing cycles within a historical time period; based on the opening and closing data, the target category to which the low-voltage electrical appliance to be predicted belongs is determined based on a pre-classification model, which is trained and obtained from a first training sample dataset; based on the target category to which the low-voltage electrical appliance to be predicted belongs, a target-specific prediction model is determined; based on the opening and closing data, the remaining life parameters of the low-voltage electrical appliance to be predicted are predicted based on the target-specific prediction model, which is trained and obtained from a second training sample dataset. This enables the determination of the target category to which the low-voltage electrical appliance to be predicted belongs based on a pre-classification model, and then, based on the target category, a target-specific prediction model matching that category can be selected to predict the remaining life parameters of the low-voltage electrical appliance to be predicted, thereby improving the accuracy of the prediction results. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments 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.

[0049] Figure 1 A flowchart illustrating a method for predicting the lifespan of low-voltage electrical appliances provided in an embodiment of this application;

[0050] Figure 2 A flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in this application embodiment;

[0051] Figure 3 A flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in this application embodiment;

[0052] Figure 4 A flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in this application embodiment;

[0053] Figure 5 A flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in this application embodiment;

[0054] Figure 6 A schematic diagram illustrating the electrical life prediction results of a low-voltage electrical appliance to be predicted after classification based on a first opening and closing data set, provided in an embodiment of this application.

[0055] Figure 7 A schematic diagram illustrating the electrical life prediction results of a low-voltage electrical appliance to be predicted after classification based on a second switching data set, provided in an embodiment of this application.

[0056] Figure 8 A schematic diagram of the functional modules of a life prediction device for low-voltage electrical appliances provided in an embodiment of this application;

[0057] Figure 9 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some embodiments of this application, and not all 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.

[0059] 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 to illustrate selected embodiments of the 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.

[0060] It should be noted that similar labels 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.

[0061] Figure 1 This is a flowchart illustrating a method for predicting the lifespan of low-voltage electrical appliances provided in an embodiment of this application. The executing entity of this method can be a processing unit with data processing capabilities within the low-voltage electrical appliance, such as a processor, etc., and is not limited thereto. Optionally, the executing entity of this method can also be electronic devices such as computers or servers, depending on the actual application scenario. Figure 1 As shown, the method may include:

[0062] S101. Obtain the opening and closing data of the low-voltage electrical appliance to be predicted in multiple opening and closing cycles within a historical time period.

[0063] The low-voltage electrical appliance to be predicted can be any appliance operating at AC voltage below 1200V or DC voltage below 1500V, such as switches, contactors, and relays; there is no limitation on this. Optionally, the historical time period can be a week, a month, etc., and its value can vary depending on the historical operating time of the low-voltage electrical appliance to be predicted. Of course, in some embodiments, the value of the historical time period can also be defined by the user.

[0064] In some embodiments, a data acquisition unit can be set in the low voltage to be predicted. During the historical time period, the opening and closing data of the low voltage electrical appliance to be predicted can be obtained through the data acquisition unit each time it is opened or closed.

[0065] S102. Based on the opening and closing data, determine the target category of the low-voltage electrical appliance to be predicted based on the pre-classification model. The pre-classification model is obtained by training based on the first training sample dataset.

[0066] The first training sample dataset includes the first sample opening and closing data of multiple first sample electrical appliances within the first historical time period, and is labeled with the corresponding categories.

[0067] The type of the first sample electrical appliance can be the same as the type of the low-voltage electrical appliance to be predicted. For example, if the type of the low-voltage electrical appliance to be predicted is a relay, the type of the first sample electrical appliance can be a relay; if the type of the low-voltage electrical appliance to be predicted is a contactor, the type of the first sample electrical appliance can be a contactor. In this way, it can be ensured that when the target category of the low-voltage electrical appliance is determined based on the trained pre-classification model, a relatively accurate prediction result can be obtained.

[0068] Optionally, the first historical time period can be a week, a month, or three months, etc., without limitation. The category labeled on the first sample electrical appliance can represent the operating condition and total lifespan status of the first sample electrical appliance. Optionally, the operating condition status can include two states: normal operating condition and abnormal operating condition. Normal operating condition indicates that the opening and closing data of the first sample electrical appliance meets preset conditions, while abnormal operating condition indicates that the opening and closing data of the first sample electrical appliance does not meet preset conditions. The total lifespan status can include two states: a first lifespan status and a second lifespan status. The first lifespan status indicates that the total number of opening and closing operations of the first sample electrical appliance is less than a first preset threshold; the second lifespan status indicates that the total number of opening and closing operations of the first sample electrical appliance is greater than the first preset threshold. That is, comparing these two total lifespan statuses, the first lifespan status can be understood as a short lifespan status, and the second lifespan status can be understood as a long lifespan status. Optionally, the value of the first preset threshold can be 800, 1000, etc., without limitation, and can vary depending on the actual application scenario.

[0069] It is understandable that the opening and closing data can reflect the operating parameters of the low-voltage electrical appliances to be predicted to a certain extent. Therefore, a pre-classification model can be trained based on the opening and closing data of the first sample electrical appliances corresponding to the first sample within the first historical time period. The opening and closing data of the low-voltage electrical appliances to be predicted can be input into the pre-classification model, and the target category of the low-voltage electrical appliances to be predicted can be determined through the pre-classification model.

[0070] In some embodiments, if the categories labeled with the first sample electrical appliance include two categories: normal operating condition and abnormal operating condition, optionally, the target category to which the low-voltage electrical appliance to be predicted belongs can be abnormal operating condition. In some embodiments, if the categories labeled with the first sample electrical appliance include two categories: first lifespan state and second lifespan state, optionally, the target category to which the low-voltage electrical appliance to be predicted belongs can be the first lifespan state, that is, the short lifespan state.

[0071] S103. Determine the target-specific prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs.

[0072] Based on the above explanation, after determining the target category to which the low-voltage electrical appliance to be predicted belongs, a target-specific prediction model can be determined according to the target category. This enables the determination of a target-specific prediction model that matches the target category, which means that a preliminary classification can be carried out.

[0073] S104. Based on the opening and closing data, predict the remaining life parameters of the low-voltage electrical appliances to be predicted using the target-specific prediction model.

[0074] The target-specific prediction model can be trained using a second training sample dataset. This dataset includes the opening and closing data of multiple second-sample electrical appliances belonging to the target category within a second historical time period, labeled with their corresponding remaining lifespan parameters. The type of the second-sample electrical appliance can be the same as the type of the low-voltage electrical appliance to be predicted, and the second historical time period can be a week, a month, three months, etc., without limitation. For further explanation of this part, please refer to the description of the first-sample electrical appliance mentioned above; it will not be repeated here. The remaining lifespan parameters labeled for the second-sample electrical appliances can indicate the remaining working time, remaining number of operating cycles, etc., without limitation.

[0075] Optionally, the second training sample dataset may include a portion of the first sample data from the first training sample dataset, thereby improving the efficiency of obtaining the second training sample dataset. Of course, in some embodiments, the second training sample dataset and the first training sample dataset may be different, which is not limited here. Furthermore, referring to the above description, it can be seen that since the target-specific prediction model is trained based on the second sample opening and closing data corresponding to multiple second sample electrical appliances belonging to the target category, the feature data corresponding to the target category can be fully utilized. Therefore, when predicting the remaining life parameters of the low-voltage electrical appliances to be predicted based on this target-specific prediction model, the accuracy of the prediction results can be improved, that is, a more accurate remaining life parameter can be obtained.

[0076] Based on the above explanation, it can be understood that since the target category of the low-voltage electrical appliance to be predicted can be determined according to the pre-classification model, the target-specific prediction model that matches the target category can be selected to predict the remaining life parameters of the low-voltage electrical appliance to be predicted. Therefore, a more accurate prediction result can be obtained.

[0077] In summary, this application provides a method for predicting the lifespan of low-voltage electrical appliances. The method includes: acquiring the opening and closing data of the low-voltage electrical appliance to be predicted within multiple opening and closing cycles over a historical time period; determining the target category of the low-voltage electrical appliance to be predicted based on the opening and closing data and a pre-classification model, wherein the pre-classification model is trained using a first training sample dataset; determining a target-specific prediction model based on the target category of the low-voltage electrical appliance to be predicted; and predicting the remaining lifespan parameters of the low-voltage electrical appliance to be predicted based on the target-specific prediction model and the opening and closing data, wherein the target-specific prediction model is trained using a second training sample dataset. This method enables the determination of the target category of the low-voltage electrical appliance to be predicted based on the pre-classification model, and then allows selection of a matching target-specific prediction model to predict the remaining lifespan parameters of the low-voltage electrical appliance based on the target category, thereby improving the accuracy of the prediction results.

[0078] Optionally, based on the target category to which the low-voltage electrical appliance to be predicted belongs, a target-specific prediction model is determined, including:

[0079] Based on the target category of the low-voltage electrical appliance to be predicted and the preset mapping relationship, a target-specific prediction model is determined in at least one dedicated prediction model. The preset mapping relationship includes at least one mapping relationship between the category and the dedicated prediction model.

[0080] The lifetime prediction method provided in this application embodiment can provide a dedicated prediction model set and a preset mapping relationship. The dedicated prediction model set can include at least one dedicated prediction model, and the preset mapping relationship can include at least one mapping relationship between a category and a dedicated prediction model. That is, after determining the target category to which the low-voltage electrical appliance to be predicted belongs, a target dedicated prediction model that matches it can be determined from at least one dedicated prediction model according to the preset mapping relationship.

[0081] For example, if the target category of the low-voltage electrical appliance to be predicted is the first life state, that is, the short life state, then the remaining life parameters of the low-voltage electrical appliance to be predicted can be determined according to the first dedicated prediction model that matches the first life state, which is the short life model.

[0082] Figure 2 This is a flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in an embodiment of this application. Optionally, as... Figure 2 As shown, the above method also includes:

[0083] S201. Obtain the first training sample dataset of multiple first sample electrical appliances in multiple opening and closing cycles within the first historical time period.

[0084] The first training sample dataset includes multiple first sample circuit breaker opening and closing data. Each first sample circuit breaker opening and closing data is labeled with the total lifespan state corresponding to the first sample electrical appliance. The total lifespan state can include two states: the first lifespan state and the second lifespan state. For an explanation of this part, please refer to the relevant explanations above, which will not be repeated here.

[0085] S202. Based on the first training sample dataset, train and obtain the pre-classification model.

[0086] Optionally, during specific training, based on the first training sample dataset, techniques such as Recurrent Neural Networks (RNN), Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks can be used, without limitation.

[0087] Figure 3 This is a flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in this application. Optionally, as... Figure 3 As shown, the above method also includes:

[0088] S301. Obtain the second training sample dataset of multiple second sample electrical appliances belonging to the target category within the second historical time period and in multiple opening and closing cycles.

[0089] The second training sample dataset includes multiple second sample circuit breaker opening and closing data, and each second sample circuit breaker opening and closing data is labeled with the remaining life parameter corresponding to the second sample electrical appliance.

[0090] S302. Based on the second training sample dataset, train and obtain a target-specific prediction model.

[0091] In some embodiments, the second sample electrical appliance and the first sample electrical appliance can be the same sample electrical appliance. The first sample circuit breaker data belonging to the target category in the first training sample dataset can be used as the second sample circuit breaker data in the second training sample dataset. This allows for the reuse of the first sample circuit breaker data, improving the efficiency of users obtaining the first training sample dataset. It is understood that if the target category of the low-voltage electrical appliance to be predicted is the second lifespan state, i.e., the long lifespan state, then a second training sample dataset of multiple second sample electrical appliances belonging to the second lifespan state within multiple circuit breaker cycles can be obtained to train a target-specific prediction model.

[0092] Optionally, the target-specific prediction model and other category-specific prediction models can be implemented based on RNN, DNN, CNN, LSTM networks, etc., and the specific implementation method is not limited here. In some embodiments, the pre-classification model and the target-specific prediction model can be implemented based on the same network model, which can achieve network model reuse, simplify the process of building each model for users, and improve the efficiency of model construction. Of course, it should be noted that, depending on different application scenarios, the pre-classification model and the target-specific prediction model can be implemented based on different network models, which can give full play to the characteristics of each network model and improve the accuracy of the prediction results of this application.

[0093] Of course, it should be noted that for the dedicated prediction models corresponding to other categories, please refer to the training process of the target dedicated prediction model, which will not be repeated here. In addition, referring to the above explanation of the relationship between the first training sample dataset and the second training sample dataset, optionally, the first sample opening and closing data belonging to each category in the first training sample dataset can be used as the sample opening and closing data in the training sample dataset corresponding to each type of dedicated prediction model.

[0094] Table 1 is a table showing the target category of a low-voltage electrical appliance to be predicted according to an embodiment of this application. As shown in Table 1, there are 19 low-voltage electrical appliances to be predicted, corresponding to numbers 1 to 19 respectively. The third low-voltage electrical appliance to be predicted (corresponding to number 3) and the seventh low-voltage electrical appliance to be predicted (corresponding to number 7) are used as examples for illustration.

[0095] Based on the foregoing explanation, if the first preset threshold is 800, it can be seen from Table 1 that the total number of lifetimes predicted by the pre-classification model for the third low-voltage electrical appliance to be predicted is 472.25, which is less than 800. Therefore, it can be determined that the target category to which the third low-voltage electrical appliance to be predicted belongs is the second lifetime state, that is, the short lifetime category. Furthermore, a dedicated prediction model corresponding to the second lifetime state can be used to predict the remaining lifetime parameters of the third low-voltage electrical appliance to be predicted. Specifically, the dedicated prediction model corresponding to the second lifetime state can be used to predict and obtain the total number of lifetimes corresponding to the third low-voltage electrical appliance to be predicted. Then, based on the total number of lifetimes and the number of lifetimes already recorded in real time during the use of the third low-voltage electrical appliance to be predicted, the remaining lifetime parameters of the third low-voltage electrical appliance to be predicted can be calculated. As can be seen from Table 1, compared with the total number of lifetimes of the third low-voltage electrical appliance predicted by the pre-classification model (472.25), the total number of lifetimes of the third low-voltage electrical appliance predicted by the dedicated prediction model corresponding to the second lifetime state (633.85) is closer to the actual total number of lifetimes of the third low-voltage electrical appliance recorded during the test (641).

[0096] Furthermore, as shown in Table 1, the total number of lifetimes predicted by the pre-classification model for the seventh low-voltage electrical appliance is 1660.06, which is greater than 800. Therefore, the target category of the seventh low-voltage electrical appliance can be determined to be the first lifetime state, i.e., the long-life category. Further, a dedicated prediction model corresponding to the first lifetime state can be used to predict the remaining lifetime parameters of the seventh low-voltage electrical appliance. Specifically, the dedicated prediction model corresponding to the first lifetime state can first be used to predict the total number of lifetimes for the seventh low-voltage electrical appliance. Then, based on this total number of lifetimes and the number of lifetimes already recorded in real time during the use of the seventh low-voltage electrical appliance, the remaining lifetime parameters of the seventh low-voltage electrical appliance can be calculated. Combining Table 1, it can be seen that compared to the total number of lifetimes predicted by the pre-classification model (1660.06), the total number of lifetimes predicted by the dedicated prediction model corresponding to the first lifetime state (1348.94) is closer to the actual total number of lifetimes recorded during the experiment (1390).

[0097] In summary, it can be seen that the prediction results obtained by using the pre-classification model and the target-specific prediction model separately differ significantly. Therefore, it is necessary to improve the accuracy of the prediction results by combining the pre-classification model and the target-specific prediction model. In the experiment, compared with the actual total number of predictions of each low-voltage electrical appliance to be predicted recorded during the experiment, the average error of the total number of predictions of the total number of predictions of the low-voltage electrical appliances to be predicted using a single pre-classification model was 23.45%, while the average error of the total number of predictions of the low-voltage electrical appliances to be predicted using the method provided in the embodiments of this application (i.e., the combination of the pre-classification model and the target-specific prediction model) was 14.25%. It can be seen that applying the embodiments of this application can effectively improve the accuracy of the prediction results.

[0098] Table 1

[0099]

[0100] Figure 4 This is a flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in an embodiment of this application. Optionally, as... Figure 4 As shown, the acquisition of the opening and closing data of the low-voltage electrical appliance to be predicted within multiple opening and closing cycles over a historical time period includes:

[0101] S401. The voltage and / or current data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within a historical time period are acquired through the acquisition device.

[0102] The data acquisition device may include a voltage acquisition device and / or a current acquisition device. The voltage acquisition device can acquire voltage data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within a historical time period, and the current acquisition device can acquire current data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within a historical time period. The voltage acquisition device and / or current acquisition device can be flexibly selected for acquiring voltage and / or current data according to the actual application scenario.

[0103] Optionally, the voltage acquisition device may include: at least one acquisition terminal, an overvoltage protection circuit, an amplifier circuit, and a signal processing circuit connected in series. One end of the at least one acquisition terminal is electrically connected to the detection terminal of the low-voltage electrical appliance to be predicted, and the other end is electrically connected to one end of the overvoltage protection circuit. The other end of the overvoltage protection circuit is electrically connected to the amplifier circuit. Taking a circuit breaker or contactor as an example, the detection terminal of the low-voltage electrical appliance to be predicted can be a contact or a busbar.

[0104] In some embodiments, the aforementioned current acquisition device can be connected in series in the circuit containing the low-voltage electrical appliance to be predicted, for acquiring circuit current data. Optionally, the current acquisition device may include a current transformer and a signal processing amplifier circuit. The current transformer may be an open-type current transformer or a Rogowski air-core current transformer, wherein the Rogowski air-core current transformer is also known as a Rogowski coil. Of course, it should be noted that, depending on the actual application scenario, the aforementioned current transformer may also be a sensor. For example, the current acquisition device may include a Hall current sensor and a signal processing amplifier circuit, which can be flexibly selected according to the actual application scenario and are not limited here.

[0105] S402. Based on voltage data and / or current data, obtain the electrical life characteristics of the low-voltage electrical appliance to be predicted, and use the electrical life characteristics as the opening and closing data of the low-voltage electrical appliance to be predicted.

[0106] Based on the above description, after acquiring voltage and / or current data, the electrical life characteristics of the low-voltage electrical appliance to be predicted can be obtained. This allows the electrical life characteristics to reflect the operating state parameters of the low-voltage electrical appliance in multiple dimensions. The electrical life characteristics can be used as the opening and closing data of the low-voltage electrical appliance to be predicted. Subsequently, based on the opening and closing data, when determining the target category of the low-voltage electrical appliance to be predicted and the remaining life parameters of the low-voltage electrical appliance to be predicted, a more accurate prediction result can be obtained.

[0107] Optionally, the electrical life characteristics of the low-voltage electrical appliance to be predicted may include at least one of the following: contact voltage, contact current, contact resistance, arcing time, arcing energy, and arcing power.

[0108] Among them, contact voltage represents the voltage across the low-voltage electrical appliance during the closing period; contact current represents the current across the low-voltage electrical appliance during the closing period; contact resistance represents the ratio of the effective value of the contact voltage to the effective value of the contact current; arcing time, taking a relay as an example, represents the time from when the moving contact opens to when the arc is extinguished, which is the time when an arc is generated between the contacts of the low-voltage electrical appliance at the moment of power failure (e.g., at the moment of circuit breaking), and arcing energy represents the integral of the arcing power over the arcing time; arcing power represents the product of the voltage across the low-voltage electrical appliance and the current across the low-voltage electrical appliance when an arc occurs during the arcing time.

[0109] Of course, it should be noted that in some embodiments, other electrical lifetime characteristics can be obtained based on voltage data and / or current data, or, depending on the type of low-voltage electrical appliance, other electrical lifetime characteristics can be obtained, which are not limited here.

[0110] Figure 5 This is a flowchart illustrating another method for predicting the lifespan of low-voltage electrical appliances provided in this application. Optionally, as... Figure 5 As shown, after training and obtaining the pre-classification model based on the first training sample dataset, the above method further includes:

[0111] S501. Obtain the third training sample dataset of multiple first sample electrical appliances in multiple opening and closing cycles within the third historical time period.

[0112] The third training sample dataset includes multiple third sample circuit breaker opening and closing data. Each third sample circuit breaker opening and closing data is labeled with the total lifespan parameter corresponding to the first sample electrical appliance. The third historical time period is different from the first historical time period. Optionally, the third historical time period can be a period after or before the first historical time period, without limitation. Of course, this application does not limit the length of the first and third historical time periods. Optionally, the first historical time period can be a historical week, the third historical time period can be a historical month, etc., and can be flexibly set according to the actual application scenario.

[0113] S502. Update the pre-classification model based on the third training sample dataset.

[0114] In some embodiments, considering that the prediction accuracy of the pre-classification model obtained when trained solely on a first training sample dataset within a first historical time period is not high, a third training sample dataset can be obtained, and the pre-classification model can be updated based on this third training sample dataset to correct the pre-classification model. Based on this description, it can be understood that the accuracy can be improved when determining the target category of the low-voltage electrical appliance to be predicted based on the updated pre-classification model.

[0115] Of course, this application does not limit the timing of each update. Depending on the actual application scenario, updates can be performed periodically. For example, after the first sample electrical appliance performs 100 new opening and closing operations, the opening and closing data corresponding to those 100 operations can be obtained as the third training sample dataset to be used for updating the pre-classification model. Of course, the specific update method is not limited to this; it can also be a scheduled update, such as once a week.

[0116] It should also be noted that, depending on the actual application scenario, the opening and closing data of the low-voltage electrical appliance to be predicted can also be obtained in real time. In this case, the opening and closing data of the low-voltage electrical appliance to be predicted in multiple opening and closing cycles within a historical time period, as well as the real-time opening and closing data, can be combined with the pre-classification model to determine the classification of the low-voltage electrical appliance to be predicted. This allows for obtaining a more accurate target category based on more and newer opening and closing data. Furthermore, when determining the remaining life parameters of the low-voltage electrical appliance to be predicted based on this target category, a more accurate prediction result can be obtained. The following will illustrate this with specific experiments.

[0117] Figure 6 A schematic diagram illustrating the electrical life prediction results of a low-voltage electrical appliance to be predicted after classification based on a first opening and closing data set, provided in an embodiment of this application. Figure 7 This illustration shows a prediction result of the electrical life of a low-voltage electrical appliance to be predicted after classification based on a second circuit breaker dataset, as provided in an embodiment of this application. The first circuit breaker dataset includes multiple first circuit breaker data sets, and the second circuit breaker dataset includes the first circuit breaker dataset and multiple second circuit breaker data sets. The multiple first circuit breaker data sets are the circuit breaker data corresponding to the low-voltage electrical appliance to be predicted within a first historical time period (e.g., 8:00 AM to 12:00 PM), and the multiple second circuit breaker data sets are the circuit breaker data corresponding to the low-voltage electrical appliance to be predicted after the first historical time period (e.g., 1:00 PM to 3:00 PM), which can also be understood as the most recently acquired circuit breaker data. Figure 6 and Figure 7As shown in the figure, the horizontal axis represents the number of times the low-voltage electrical appliance to be predicted has been used, and the vertical axis represents the ratio of the remaining number of times the low-voltage electrical appliance to be predicted has been used to the total number of times it has been used. The value ranges from 0 to 1. S1 and S4 represent the relationship between the first ratio of the remaining number of times the low-voltage electrical appliance to be predicted has been used to the total number of times it has been used in the actual test and the number of times the low-voltage electrical appliance to be predicted has been used. It can be seen from the figure that S1 and S4 are straight lines, that is, the ratio of the remaining number of times the low-voltage electrical appliance to be predicted has been used to the total number of times it has been used to the total number of times it has been used is linearly related to the number of times the low-voltage electrical appliance to be predicted has been used. S3 represents the relationship between the second ratio of the remaining number of times the low-voltage electrical appliance to be predicted has been used to the total number of times it has been used to the total number of times it has been used, determined by the pre-classification model provided in the embodiment of this application based on the first opening and closing data set during the application process, and the number of times the low-voltage electrical appliance to be predicted has been used. S2 is the fitted straight line obtained by fitting the S3 curve.

[0118] Continue to refer to Figure 7 As shown, S6 represents the relationship between the third ratio of the remaining number of times the low-voltage electrical appliance to be predicted to the total number of times it has been used, determined by the pre-classification model provided in this application embodiment based on the second opening and closing data set during the application process, and the relationship between the number of times the low-voltage electrical appliance to be predicted has been used. S5 is the fitted straight line obtained by fitting the curve S6. From Figure 6 and Figure 7 As can be seen, the S3 and S6 curves differ significantly, and experimental verification shows that the S6 curve is closer to the actual operating conditions, meaning that the fitted line S5 corresponding to S6 is more accurate. In other words, determining the remaining life parameters of the low-voltage electrical appliances to be predicted based on the second opening and closing data set yields more accurate results. Therefore, determining the remaining life parameters of the low-voltage electrical appliances to be predicted based on more and newer opening and closing data can improve the accuracy of the prediction results.

[0119] Optionally, at least one category includes: a first total lifetime range and a second total lifetime range, wherein the first total lifetime range is shorter than the second total lifetime range.

[0120] In some embodiments, each category may specifically correspond to a total lifespan range. In some embodiments, at least one category may include: a first total lifespan range and a second total lifespan range, wherein the first total lifespan range is less than the second total lifespan range. For example, the first total lifespan range may correspond to the second lifespan state mentioned above, i.e., the short lifespan state, and optionally, its value may be 600 to 800 times; the second total lifespan range may correspond to the first lifespan state mentioned above, i.e., the long lifespan state, and optionally, its value may be 800 to 1500 times. Based on this description, if the total lifespan count of a low-voltage electrical appliance to be predicted is determined to be 700 times based on the pre-classification model, it can be determined that the category corresponding to the low-voltage electrical appliance to be predicted is the first total lifespan range.

[0121] Of course, this application does not limit the number of categories. Optionally, in some embodiments, it may include multiple total lifetime ranges such as 3 or 5.

[0122] Figure 8 This is a functional module diagram of a low-voltage electrical appliance life prediction device provided in an embodiment of this application. The basic principle and technical effects of this device are the same as those in the aforementioned corresponding method embodiments. For the sake of brevity, parts not mentioned in this embodiment can be referred to the corresponding content in the method embodiments. Figure 8 As shown, the lifetime prediction device 100 includes:

[0123] The acquisition module 110 is used to acquire the opening and closing data of the low-voltage electrical appliance to be predicted in multiple opening and closing cycles within a historical time period.

[0124] The first determining module 120 is used to determine the target category of the low-voltage electrical appliance to be predicted based on the opening and closing data and a pre-classification model. The pre-classification model is trained and obtained based on a first training sample dataset. The first training sample dataset includes the opening and closing data of the first sample electrical appliances corresponding to multiple first sample electrical appliances in a first historical time period, and the corresponding categories are labeled.

[0125] The second determining module 130 is used to determine a target-specific prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs;

[0126] The prediction module 140 is used to predict the remaining life parameters of the low-voltage electrical appliance to be predicted based on the opening and closing data and the target-specific prediction model. The target-specific prediction model is trained and obtained based on a second training sample dataset. The second training sample dataset includes the second sample opening and closing data of multiple second sample electrical appliances belonging to the target category within a second historical time period, and the corresponding remaining life parameters are labeled.

[0127] In an optional implementation, the second determining module 130 is specifically used to determine a target dedicated prediction model in at least one dedicated prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs and a preset mapping relationship, wherein the preset mapping relationship includes at least one mapping relationship between a category and a dedicated prediction model.

[0128] In an optional implementation, the life prediction device further includes: a first training module, used to acquire a first training sample dataset of multiple first sample electrical appliances in multiple opening and closing cycles within a first historical time period, the first training sample dataset including multiple first sample opening and closing data, each first sample opening and closing data being labeled with the total life status corresponding to the first sample electrical appliance.

[0129] The pre-classification model is trained and obtained based on the first training sample dataset.

[0130] In an optional implementation, the life prediction device further includes: a second training module, used to acquire a second training sample dataset of multiple second sample electrical appliances belonging to the target category within a second historical time period and within multiple opening and closing cycles, the second training sample dataset including multiple second sample opening and closing data, each second sample opening and closing data being labeled with the remaining life parameter corresponding to the second sample electrical appliance.

[0131] Based on the second training sample dataset, a target-specific prediction model is trained and obtained.

[0132] In an optional implementation, the acquisition module 110 is specifically used to acquire voltage data and / or current data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within the historical time period through an acquisition device.

[0133] Based on the voltage data and / or current data, the electrical lifetime characteristics of the low-voltage electrical appliance to be predicted are obtained, and the electrical lifetime characteristics are used as the opening and closing data of the low-voltage electrical appliance to be predicted.

[0134] In an optional implementation, the first training module is further configured to acquire a third training sample dataset of multiple first sample electrical appliances within a third historical time period in multiple opening and closing cycles. The third training sample dataset includes multiple third sample opening and closing data, and each third sample opening and closing data is labeled with the total life status corresponding to the first sample electrical appliance. The third historical time period is a different time period from the first historical time period.

[0135] The pre-classification model is updated based on the third training sample dataset.

[0136] In an optional implementation, at least one of the categories includes: a first total lifetime range and a second total lifetime range, wherein the first total lifetime range is less than the second total lifetime range.

[0137] In an optional implementation, the electrical life characteristics of the low-voltage electrical appliance to be predicted include at least one of the following: contact voltage, contact current, contact resistance, arcing time, arcing energy, and arcing power.

[0138] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0139] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0140] Figure 9 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. This electronic device can be integrated into the aforementioned lifetime prediction device. Figure 9 As shown, the electronic device may include a processor 210, a storage medium 220, and a bus 230. The storage medium 220 stores machine-readable instructions executable by the processor 210. When the electronic device is running, the processor 210 communicates with the storage medium 220 via the bus 230, and the processor 210 executes the machine-readable instructions to perform the steps of the above method embodiment. The specific implementation and technical effects are similar and will not be described in detail here.

[0141] Optionally, this application also provides a storage medium storing a computer program, which, when run by a processor, executes the steps of the above-described method embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0143] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0144] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0145] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0146] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0147] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application. 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 further definition and explanation in subsequent figures. The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for predicting the lifespan of low-voltage electrical appliances, characterized in that, include: Obtain the opening and closing data of the low-voltage electrical appliance to be predicted within multiple opening and closing cycles over a historical period; Based on the opening and closing data, the target category of the low-voltage electrical appliance to be predicted is determined based on the pre-classification model. The pre-classification model is obtained by training based on the first training sample dataset. The first training sample dataset includes the opening and closing data of the first sample electrical appliances corresponding to multiple first sample electrical appliances in the first historical time period, and the corresponding categories are labeled. Based on the target category to which the low-voltage electrical appliance to be predicted belongs, a target-specific prediction model is determined; Based on the opening and closing data, the remaining life parameters of the low-voltage electrical appliance to be predicted are predicted based on the target-specific prediction model. The target-specific prediction model is trained and obtained based on the second training sample dataset. The second training sample dataset includes the second sample opening and closing data of multiple second sample electrical appliances belonging to the target category within the second historical time period, and the corresponding remaining life parameters are labeled. The step of determining a target-specific prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs includes: Based on the target category to which the low-voltage electrical appliance to be predicted belongs and the preset mapping relationship, a target dedicated prediction model is determined in at least one dedicated prediction model. The preset mapping relationship includes a mapping relationship between at least one category and a dedicated prediction model. The at least one category includes: a first total lifespan range and a second total lifespan range, wherein the first total lifespan range is less than the second total lifespan range.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the first training sample dataset of multiple first sample electrical appliances in multiple opening and closing cycles within the first historical time period. The first training sample dataset includes multiple first sample opening and closing data, and each first sample opening and closing data is labeled with the total life status of the first sample electrical appliance. The pre-classification model is trained and obtained based on the first training sample dataset.

3. The method according to claim 1, characterized in that, The method further includes: Obtain a second training sample dataset of multiple second sample electrical appliances belonging to the target category within a second historical time period and within multiple opening and closing cycles. The second training sample dataset includes multiple second sample opening and closing data, and each second sample opening and closing data is labeled with the remaining life parameter corresponding to the second sample electrical appliance. Based on the second training sample dataset, a target-specific prediction model is trained and obtained.

4. The method according to claim 1, characterized in that, The acquisition of the opening and closing data of the low-voltage electrical appliance to be predicted within multiple opening and closing cycles over a historical time period includes: The voltage and / or current data of the low-voltage electrical appliance to be predicted during multiple opening and closing cycles within the historical time period are acquired by the acquisition device. Based on the voltage data and / or current data, the electrical lifetime characteristics of the low-voltage electrical appliance to be predicted are obtained, and the electrical lifetime characteristics are used as the opening and closing data of the low-voltage electrical appliance to be predicted.

5. The method according to claim 2, characterized in that, After training the pre-classification model based on the first training sample dataset, the process further includes: Obtain a third training sample dataset of multiple first sample electrical appliances within a third historical time period in multiple opening and closing cycles. The third training sample dataset includes multiple third sample opening and closing data. Each third sample opening and closing data is labeled with the total life status of the first sample electrical appliance. The third historical time period is a different time period from the first historical time period. The pre-classification model is updated based on the third training sample dataset.

6. The method according to claim 4, characterized in that, The electrical life characteristics of the low-voltage electrical appliance to be predicted include at least one of the following: contact voltage, contact current, contact resistance, arcing time, arcing energy, and arcing power.

7. A lifespan prediction device for low-voltage electrical appliances, characterized in that, include: The acquisition module is used to acquire the opening and closing data of the low-voltage electrical appliance to be predicted in multiple opening and closing cycles within a historical time period. The first determining module is used to determine the target category of the low-voltage electrical appliance to be predicted based on the opening and closing data and a pre-classification model. The pre-classification model is trained and obtained based on a first training sample dataset. The first training sample dataset includes the opening and closing data of the first sample electrical appliances corresponding to multiple first sample electrical appliances within a first historical time period, and the corresponding categories are labeled. The second determining module is used to determine a target-specific prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs; The prediction module is used to predict the remaining life parameters of the low-voltage electrical appliance to be predicted based on the opening and closing data and the target-specific prediction model. The target-specific prediction model is trained and obtained based on the second training sample dataset. The second training sample dataset includes the second sample opening and closing data of multiple second sample electrical appliances belonging to the target category within the second historical time period, and the corresponding remaining life parameters are labeled. The second determining module is specifically used to determine a target dedicated prediction model in at least one dedicated prediction model based on the target category to which the low-voltage electrical appliance to be predicted belongs and a preset mapping relationship. The preset mapping relationship includes a mapping relationship between at least one category and a dedicated prediction model. The at least one category includes: a first total lifespan range and a second total lifespan range, wherein the first total lifespan range is smaller than the second total lifespan range.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the life prediction method for low-voltage electrical appliances as described in any one of claims 1-6.

Images