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

Abstract

The application provides a low-voltage electrical appliance electrical life prediction method, device and equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: obtaining a feature sequence corresponding to a low-voltage electrical appliance to be detected according to electrical data in a closing and opening process of the low-voltage electrical appliance to be detected, wherein the feature sequence comprises at least one electrical life feature; determining a trend sequence corresponding to each feature sequence according to each electrical life feature; analyzing and obtaining a feature sequence to be used according to the trend sequence and the closeness of the corresponding feature sequence; and obtaining the electrical life corresponding to the low-voltage electrical appliance to be detected according to the feature sequence to be used and a preset prediction model, wherein the preset prediction model is obtained by training a feature sequence corresponding to sample electrical data. Compared with the prior art, the method avoids the problems of prediction result accuracy and referenceability.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a method, apparatus, device, and storage medium for predicting the electrical life of low-voltage electrical appliances. Background Technology

[0002] Low-voltage electrical products are widely used in industrial production and daily life. If they are not replaced in time before they fail, it may cause losses and inconvenience to enterprise production and people's lives. In order to replace low-voltage electrical products in time before they fail, it is necessary to know the remaining lifespan of low-voltage electrical products. Therefore, it is necessary to predict the electrical lifespan of low-voltage electrical products.

[0003] In existing technologies, feature parameters that affect the electrical life of AC contactors are generally extracted, a prediction model for the remaining electrical life of AC contactors based on a deep long short-term memory neural network is constructed, and the electrical life is directly predicted based on the prediction model and feature data.

[0004] However, because the accuracy of the feature data cannot be guaranteed, the accuracy and reliability of the prediction results obtained by this method are not high. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing a method, apparatus, device, and storage medium for predicting the electrical life of low-voltage electrical appliances, thereby solving the problems of accuracy and reliability of prediction results in the prior art.

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

[0007] In a first aspect, one embodiment of this application provides a method for predicting the electrical life of low-voltage electrical appliances, the method comprising:

[0008] Based on the electrical data during the opening and closing process of the low-voltage electrical appliance to be tested, a feature sequence corresponding to the low-voltage electrical appliance to be tested is obtained, and the feature sequence includes at least one electrical lifetime feature.

[0009] Based on each of the electrical lifetime characteristics, determine the trend sequence corresponding to each of the characteristic sequences;

[0010] Based on the similarity between the trend sequence and the corresponding feature sequence, the feature sequence to be used is obtained through analysis;

[0011] The electrical lifetime of the low-voltage electrical appliance to be detected is obtained based on the feature sequence to be used and the preset prediction model, wherein the preset prediction model is obtained by training the feature sequence corresponding to the sample electrical data.

[0012] Optionally, the step of analyzing and obtaining the feature sequence to be used based on the similarity between the trend sequence and the corresponding feature sequence includes:

[0013] Based on the trend sequence and the corresponding feature sequence, determine the distance between each trend sequence and the corresponding feature sequence;

[0014] Feature sequences whose distance is less than or equal to a preset threshold are identified as feature sequences to be used.

[0015] Optionally, determining the trend sequence corresponding to each of the characteristic sequences based on each of the electrical lifetime characteristics includes:

[0016] Obtain the maximum value, minimum value, and sequence length of the electrical lifetime feature in each feature sequence;

[0017] The differences between features in the trend sequence are determined based on the maximum value, minimum value, and sequence length.

[0018] Based on the maximum value, minimum value, and the difference between each feature, the generated arithmetic progression sequence is determined to be the trend sequence corresponding to the feature sequence.

[0019] Optionally, before obtaining the electrical lifetime of the low-voltage electrical appliance to be detected based on the feature sequence to be used and the preset prediction model, the method further includes:

[0020] If the feature sequence to be used includes multiple sequences, then the feature sequence to be used is subjected to dimensionality reduction processing according to the dimensions of the multiple feature sequences to be used; wherein, the dimension of the feature sequence to be used is determined according to the number of feature sequences to be used.

[0021] The step of obtaining the electrical lifetime of the low-voltage electrical appliance to be detected based on the feature sequence to be used and the preset prediction model includes:

[0022] Based on the dimension-reduced feature sequence to be used and the preset prediction model, the electrical lifetime of the low-voltage electrical appliance to be detected is obtained.

[0023] Optionally, the step of reducing the dimensionality of the feature sequences to be used based on the dimensions of the plurality of feature sequences to be used includes:

[0024] The coordinate axes of the multiple feature sequences to be used are transformed, and the coordinate information of each feature point on the transformed coordinate axis on the preset coordinate axis is obtained as the coordinate information after dimensionality reduction.

[0025] Optionally, the electrical lifetime characteristics include one or more of the following: contact voltage characteristics, contact current characteristics, contact resistance characteristics, arcing time characteristics, low-energy arcing ratio characteristics, high-energy arcing ratio characteristics, high and low energy arcing probability characteristics, and time-frequency domain characteristics.

[0026] Optionally, the probability characteristics of high and low energy arcing are determined based on the number of times low-energy and high-energy arcing occur during the opening and closing of the low-voltage electrical appliance to be tested, so as to indicate the probability of occurrence of high-energy or low-energy arcing as the number of operations increases.

[0027] Optionally, obtaining the feature sequence corresponding to the low-voltage electrical appliance under test based on the electrical data during the opening and closing process of the low-voltage electrical appliance under test includes:

[0028] Acquire the voltage and current data generated when the low-voltage electrical appliance under test is switched on and off;

[0029] Based on the voltage and current data, at least one electrical lifetime feature is extracted and the feature sequence is generated.

[0030] Secondly, another embodiment of this application provides a low-voltage electrical life prediction device, the device comprising: an acquisition module and a determination module, wherein:

[0031] The acquisition module is used to acquire the feature sequence corresponding to the low-voltage electrical appliance under test based on the electrical data during the opening and closing process of the low-voltage electrical appliance under test. The feature sequence includes at least one electrical lifetime feature.

[0032] The determining module is used to determine the trend sequence corresponding to each of the characteristic sequences based on each of the electrical lifetime characteristics;

[0033] The acquisition module is specifically used to analyze and acquire a feature sequence to be used based on the similarity between the trend sequence and the corresponding feature sequence; and to acquire the electrical lifetime of the low-voltage electrical appliance to be detected based on the feature sequence to be used and a preset prediction model, wherein the preset prediction model is acquired by training the feature sequence corresponding to the sample electrical data.

[0034] Optionally, the determining module is specifically used to determine the distance between each trend sequence and the corresponding feature sequence based on the trend sequence and the corresponding feature sequence; and to determine the feature sequence whose distance is less than or equal to a preset threshold as the feature sequence to be used.

[0035] Optionally, the acquisition module is specifically used to acquire the maximum value, minimum value and sequence length of the electrical lifetime feature in each feature sequence;

[0036] The determining module is specifically used to determine the difference between each feature in the trend sequence based on the maximum value, minimum value and sequence length; and to determine the generated arithmetic progression sequence as the trend sequence corresponding to the feature sequence based on the maximum value, minimum value and the difference between each feature.

[0037] Optionally, the apparatus further includes: a processing module, configured to perform dimensionality reduction processing on the feature sequences to be used according to the dimensions of the multiple feature sequences to be used if the feature sequences to be used include multiple features; wherein the dimensions of the feature sequences to be used are determined according to the number of feature sequences to be used;

[0038] The acquisition module is specifically used to acquire the electrical lifetime of the low-voltage electrical appliance to be detected based on the dimension-reduced feature sequence to be used and the preset prediction model.

[0039] Optionally, the device further includes: a transformation module, used to transform the coordinate axes of the multiple feature sequences to be used, and to obtain the coordinate information of each feature point on the transformed coordinate axis on the preset coordinate axis as the coordinate information after dimensionality reduction.

[0040] Optionally, the electrical lifetime characteristics include one or more of the following: contact voltage characteristics, contact current characteristics, contact resistance characteristics, arcing time characteristics, low-energy arcing ratio characteristics, high-energy arcing ratio characteristics, high and low energy arcing probability characteristics, and time-frequency domain characteristics.

[0041] Optionally, the probability characteristics of high and low energy arcing are determined based on the number of times low-energy and high-energy arcing occur during the opening and closing of the low-voltage electrical appliance to be tested, so as to indicate the probability of occurrence of high-energy or low-energy arcing as the number of operations increases.

[0042] Optionally, the device further includes: an extraction module, wherein:

[0043] The acquisition module is specifically used to acquire the voltage and current data generated when the low-voltage electrical appliance to be tested is switched on and off.

[0044] The extraction module is used to extract at least one electrical lifetime feature based on the voltage and current data and generate the feature sequence.

[0045] Thirdly, another embodiment of this application provides a low-voltage electrical life prediction device, including: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the low-voltage electrical life prediction 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 any of the methods described in the first aspect above.

[0046] Fourthly, another embodiment of this application provides a storage medium storing a computer program, which, when executed by a processor, performs the steps of any of the methods described in the first aspect above.

[0047] The beneficial effects of this application are as follows: By using the low-voltage electrical life prediction method provided in this application, before the preset model predicts the electrical life based on the feature sequence, the feature sequences are screened according to the trend sequence corresponding to each feature sequence. Only the feature sequences to be used are input into the preset prediction model. Since the selected feature sequences to be used are all feature sequences with good trends, the results determined based on feature sequences with good trends will be more accurate and have stronger reference value. That is, the prediction results obtained based on the above-mentioned feature sequences to be used will be more accurate. 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 electrical life of low-voltage electrical appliances according to an embodiment of this application;

[0050] Figure 2 This is a partial structural diagram of a voltage signal acquisition device according to an embodiment of this application;

[0051] Figure 3 A flowchart illustrating a method for predicting the electrical life of low-voltage electrical appliances according to another embodiment of this application;

[0052] Figure 4 A flowchart illustrating a method for predicting the electrical life of low-voltage electrical appliances according to another embodiment of this application;

[0053] Figure 5 This is a schematic diagram of the structure of a low-voltage electrical life prediction device provided in an embodiment of this application;

[0054] Figure 6 This is a schematic diagram of the structure of a low-voltage electrical life prediction device provided in another embodiment of this application;

[0055] Figure 7 This is a schematic diagram of the structure of a low-voltage electrical life prediction device provided in an embodiment of this application. Detailed Implementation

[0056] 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 some embodiments of this application, but not all embodiments.

[0057] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the 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.

[0058] Furthermore, the flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed in order or performed simultaneously. Moreover, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0059] The following explanation, using several specific application examples, illustrates the method for predicting the electrical life of low-voltage electrical appliances provided in this application. Figure 1 This is a flowchart illustrating a method for predicting the electrical life of low-voltage electrical appliances according to an embodiment of this application. This method can be applied to low-voltage electrical appliances, such as intelligent low-voltage electrical appliances, like low-voltage circuit breakers and low-voltage switches, and is not limited to any particular type.

[0060] like Figure 1 As shown, the method includes:

[0061] S101: Based on the electrical data during the opening and closing process of the low-voltage electrical appliance to be tested, obtain the characteristic sequence corresponding to the low-voltage electrical appliance to be tested.

[0062] The feature sequence includes at least one electrical lifetime feature.

[0063] In embodiments of this application, electrical data may include, for example, voltage data and current data. The voltage data may be acquired, for example, by a voltage signal processing module. The voltage signal processing module is connected to the test terminal of the low-voltage electrical appliance under test through a controlled contact, thereby enabling online acquisition of the voltage data of the low-voltage electrical appliance under test through the voltage signal processing module.

[0064] Figure 2 This is a partial structural diagram of a voltage signal acquisition device according to an embodiment of this application, as shown below. Figure 2As shown, the voltage signal acquisition device includes two controlled contacts and a voltage signal processing module. Each controlled contact is connected to the low-voltage electrical appliance under test at one end and to the voltage signal processing module at the other end, thereby enabling the voltage signal processing module to measure the actual contact voltage data of the low-voltage electrical appliance under test online, providing actual data for subsequent life prediction.

[0065] The current data can be acquired, for example, through a current module. The current module can take the form of: an open-type current transformer and its signal processing and amplification circuit; or a Rogowski hollow current transformer and its signal processing and amplification circuit; or a flexible current transformer and its signal processing and amplification circuit. It should be understood that the above embodiments are only illustrative examples, and the specific form of the current module can be flexibly adjusted according to the user's needs, and is not limited to the forms given in the above embodiments.

[0066] That is, after obtaining the voltage and current data generated when the low-voltage electrical appliance under test is switched on and off, feature extraction can be performed on the voltage and current data to extract at least one electrical lifetime feature corresponding to the low-voltage electrical appliance under test, and generate a feature sequence corresponding to the electrical lifetime feature; wherein, one electrical lifetime feature corresponds to one feature sequence.

[0067] In some possible embodiments, electrical lifetime characteristics may include, but are not limited to: contact voltage characteristics, contact current characteristics, contact resistance characteristics, arcing time characteristics, low-energy arcing ratio characteristics, high-energy arcing ratio characteristics, high and low energy arcing probability characteristics, time-frequency domain characteristics, etc.

[0068] Furthermore, in the embodiments of this application, through multiple experiments on electrical lifetime characteristics and analysis of the voltage and current waveform data recorded in the experiments, waveforms with different arcing energies are distinguished by a classification algorithm. Statistical analysis reveals that the proportion of low-arcing-energy waveforms in different stages of the electrical lifetime cycle exhibits a trend, meaning that the low-energy arcing proportion characteristic can be used as a feature for electrical lifetime prediction; similarly, the high-energy arcing proportion characteristic can also be used as a feature for electrical lifetime prediction.

[0069] One method for determining arc energy is, for example, to determine the arc time period after collecting voltage and current data, obtain the power based on the voltage and current data within the arc time period, and integrate the power to obtain the arc energy data. A preset energy threshold can be set, and based on the arc energy data and the preset energy threshold, it can be distinguished whether each arc energy belongs to high-energy arc or low-energy arc. For example, a high-energy arc threshold and a low-energy arc threshold can be set; arc data greater than or equal to the high-energy arc threshold is considered high-energy arc, and arc data less than or equal to the low-energy arc threshold is considered low-energy arc. It should be understood that the above methods for distinguishing between high-energy and low-energy arcs are merely illustrative examples, and the specific methods can be flexibly adjusted according to user needs, and are not limited to those given in the above embodiments.

[0070] The proportion of low-energy arc waveforms is the ratio of the number of low-energy arc waveforms to the sum of the number of low-energy arc waveforms and other arc waveforms: Proportion of low-energy arc waveforms = Number of low-energy arc waveforms / (Number of low-energy arc waveforms + Number of other arc waveforms). Experiments revealed that, with increasing number of operations, the proportion of low-energy arc waveforms exhibits a trend within the same number of operations. Similarly, the proportion of high-energy arc waveforms also shows a trend.

[0071] S102: Determine the trend sequence corresponding to each characteristic sequence based on each electrical lifetime characteristic.

[0072] Since features with better trend characteristics can better reflect changes in electrical lifetime, it is necessary to obtain the trend sequence corresponding to each feature sequence before obtaining the features to be used. This will allow for subsequent screening of each feature sequence based on the quality of the trend, thereby improving the accuracy of subsequent electrical lifetime prediction.

[0073] S103: Based on the similarity between the trend sequence and the corresponding feature sequence, analyze and obtain the feature sequence to be used.

[0074] It should be noted that the aforementioned degree of proximity can be represented by different parameters such as distance and approximation, depending on different algorithms or methods.

[0075] In some possible embodiments, for example, a similarity analysis algorithm can be used to determine the degree of proximity between the trend sequence and the corresponding feature sequence; or a Dynamic Time Warping (DTW) algorithm can be used to determine the degree of proximity between the trend sequence and the corresponding feature sequence; or algorithms such as cosine similarity, Euclidean distance, Hamming distance, Mahalanobis distance, and Chebyshev distance can also be used to determine the degree of proximity between the trend sequence and the corresponding feature sequence. It should be understood that the above embodiments are only illustrative examples, and the specific algorithm for determining the degree of proximity can be flexibly adjusted according to user needs, and is not limited to the embodiments given above.

[0076] In one embodiment of this application, the DTW method can be used, for example, to compare the similarity between two time series. DTW finds the correct corresponding points between two series and then measures the shortest distance between the two series based on the Euclidean distance between each point. Compared with the correlation coefficient, it can solve the problem of graph translation. Therefore, this application uses the determination of the closeness between the trend series and the corresponding feature series by the DTW algorithm as an example for illustration. Specifically, the method of obtaining the feature series to be used can be, for example, as follows: determine the distance between each trend series and the corresponding feature series based on the trend series and the corresponding feature series; determine the feature series whose distance is less than or equal to a preset threshold as the feature series to be used.

[0077] In some possible embodiments, after determining the distance between each trend sequence and the corresponding feature sequence, the feature sequences can be sorted from smallest to largest distance according to the distance, and a preset number of the top-ranked feature sequences can be obtained as the feature sequences to be used, and the feature sequences with smaller distances to the trend sequences can be obtained as the feature sequences to be used. It should be understood that the above embodiments are only illustrative examples, and the specific method of determining the feature sequences to be used can be flexibly adjusted according to user needs, and is not limited to the above embodiments.

[0078] S104: Based on the feature sequence to be used and the preset prediction model, obtain the electrical life of the low-voltage electrical appliance to be detected.

[0079] The preset prediction model is obtained by training the feature sequence corresponding to the sample electrical data. The preset prediction model can be, for example, an LSTM (Long Short-Term Memory) network. The sample electrical data includes sample feature data and label data. The label data is the actual value of the electrical lifetime corresponding to the current feature data. The prediction model is continuously optimized based on the sample feature data and label data until the model converges.

[0080] The low-voltage electrical life prediction method provided in this application, before predicting the electrical life based on the feature sequences in the preset model, filters the feature sequences according to the trend sequences corresponding to each feature sequence, and only inputs the feature sequences to be used into the preset prediction model. Since the selected feature sequences to be used are all feature sequences with good trends, the results determined based on feature sequences with good trends will be more accurate and have stronger reference value; that is, the prediction results obtained based on the above-mentioned feature sequences to be used will be more accurate.

[0081] Optionally, based on the above embodiments, this application embodiment may also provide a method for predicting the electrical life of low-voltage electrical appliances. The implementation process of determining the trend sequence corresponding to the feature sequence in the above method is illustrated below with reference to the accompanying drawings.

[0082] Figure 3 A flowchart illustrating a method for predicting the electrical life of low-voltage electrical appliances, as provided in another embodiment of this application, is shown below. Figure 3 As shown, S102 may include:

[0083] S105: Obtain the maximum value, minimum value, and sequence length of the electrical lifetime feature in each feature sequence.

[0084] For example, all electrical lifetime features in the acquired feature sequence are identified. For instance, taking the currently acquired sequence feature as a contact voltage feature sequence as an example, all contact voltage data in the current feature sequence are acquired, the number of all data is determined to be the sequence length n corresponding to the current feature sequence, and among all contact voltage data, the data with the largest value is determined to be the maximum value max in the current sequence feature, and the data with the smallest value is determined to be the minimum value min in the current sequence feature.

[0085] S106: Determine the differences between features in the trend sequence based on the maximum value, minimum value, and sequence length.

[0086] Taking the example given in the above embodiment as an example, if the number of data (i.e. the length of the feature sequence) of all data in the current feature sequence is n, the maximum value is max, and the minimum value is min, then the difference is (max-min) / n.

[0087] S107: Based on the maximum value, minimum value, and the difference between each feature, determine the generated arithmetic progression sequence as the trend sequence corresponding to the feature sequence.

[0088] In some possible embodiments, a feature sequence may correspond to two trend sequences, namely: an arithmetic descending sequence with an initial value of max and a difference of (max-min) / n; and an arithmetic ascending sequence with an initial value of min and a difference of (max-min) / n. It should be understood that the above embodiments are only illustrative examples. A trend sequence with the same trend as the feature sequence can also be generated based on the trend of the feature sequence. For example, if the trend of the feature sequence is an ascending sequence, only a trend sequence with an ascending trend can be generated; or if the trend is a descending sequence, only a trend sequence with a descending trend can be generated. The specific number of trend sequences generated can be flexibly adjusted according to user needs and is not limited to the above embodiments.

[0089] Taking the example of one feature sequence corresponding to two trend sequences, after determining the two trend sequences corresponding to the feature sequence, the distance between the feature sequence and the two trend sequences is calculated respectively. The minimum distance between the two trend sequences is obtained, and the reciprocal of the minimum distance is used as the basis for judging the trend of the feature sequence.

[0090] When determining the feature sequences to be used, for example, the feature sequences with smaller values ​​corresponding to the trend discrimination criteria can be selected as the feature sequences to be used, based on the trend discrimination criteria of each feature sequence.

[0091] For example, in some other possible embodiments, since the numerical fluctuation range of each feature sequence is different, some feature sequences may have a larger fluctuation range, such as fluctuating between 40 and 200, while some feature sequences may have a smaller fluctuation range, such as fluctuating between 0 and 1. Therefore, in order to ensure the accuracy of the trend discrimination criteria, before determining the trend sequence corresponding to each feature sequence, for example, each feature sequence can be normalized first. This can normalize multiple feature sequences of the current low-voltage electrical appliance to be detected into feature sequences that fluctuate within the same range, thus ensuring the accuracy of the subsequent determination of the trend sequence and the accuracy of the subsequently obtained trend discrimination criteria.

[0092] Optionally, based on the above embodiments, this application embodiment may also provide a method for predicting the electrical life of low-voltage electrical appliances. The implementation process of the above method will be illustrated below with reference to the accompanying drawings. Figure 4 A flowchart illustrating a method for predicting the electrical life of low-voltage electrical appliances, as provided in another embodiment of this application, is shown below. Figure 4 As shown, before S104, the method may further include:

[0093] S108: If there are multiple feature sequences to be used, then the feature sequences to be used are dimensionality reduced according to the dimensions of the multiple feature sequences to be used.

[0094] The dimension of the feature sequence to be used is determined by the number of feature sequences to be used. For example, if there are 5 feature sequences to be used, the dimension of the current feature sequence to be used is 5; if there are 10 feature sequences to be used, the dimension of the current feature sequence to be used is 10.

[0095] In some possible embodiments, the dimensionality reduction process can be, for example, by transforming the coordinate axes of multiple feature sequences to be used, and obtaining the coordinate information of each feature point on the transformed coordinate axis on the preset coordinate axis as the coordinate information after dimensionality reduction.

[0096] For example, in the embodiments of this application, principal component analysis (PCA) can be used to reduce the dimensionality of the feature sequence to be used, that is, to select the factor with the greatest impact on electrical lifetime in the feature sequence to be used by reducing the dimensionality.

[0097] Principal Component Analysis (PCA) uses linear algebra to reduce the dimensionality of data, transforming multiple variables into a few unrelated variables that contain the main information of the vector, thus simplifying the process. For example, given an m-dimensional eigenvector, PCA reduces its dimensionality to n dimensions, where m > n.

[0098] Correspondingly, S104 may include:

[0099] S109: Based on the dimension-reduced feature sequence to be used and the preset prediction model, obtain the electrical lifetime of the low-voltage electrical appliance to be detected.

[0100] In other possible embodiments, the electrical lifetime characteristics may also include, for example, high and low energy arc occurrence probability characteristics derived from low energy arc ratio characteristics or high energy arc ratio characteristics.

[0101] The probability characteristics of high and low energy arcing are determined based on the number of times low-energy and high-energy arcing occur during the opening and closing of the low-voltage electrical appliance under test, so as to indicate the probability of high-energy or low-energy arcing occurring as the number of operations increases.

[0102] The low-voltage electrical appliance life prediction method provided in this application involves collecting voltage and current data, extracting at least one feature parameter from the voltage and current data, and obtaining the feature sequence corresponding to each feature parameter. Then, trend analysis is performed on the collected feature sequence to analyze the trend of each feature. Based on the trend of each feature sequence, a feature sequence to be used is selected. Before inputting the features into the preset prediction model, the feature sequence to be used is dimensionality reduced to determine the feature sequence that plays a major role in predicting electrical life. This feature sequence is then used as the input feature of the preset prediction model. The input features are processed according to the preset prediction model to obtain the output result, which is the electrical life of the low-voltage electrical appliance to be detected.

[0103] The low-voltage electrical life prediction device provided in this application will be explained below with reference to the accompanying drawings. This low-voltage electrical life prediction device can perform the above-described... Figures 1-4 The specific implementation and beneficial effects of any method for predicting the electrical life of low-voltage electrical appliances are as described above, and will not be repeated below.

[0104] Figure 5 This is a schematic diagram of the structure of a low-voltage electrical life prediction device provided in an embodiment of this application, as shown below. Figure 5 As shown, the device includes: an acquisition module 201 and a determination module 202, wherein:

[0105] The acquisition module 201 is used to acquire the feature sequence corresponding to the low-voltage electrical appliance under test based on the electrical data during the opening and closing process of the low-voltage electrical appliance under test. The feature sequence includes at least one electrical lifetime feature.

[0106] The determination module 202 is used to determine the trend sequence corresponding to each feature sequence based on each electrical lifetime characteristic;

[0107] The acquisition module 201 is specifically used to analyze and acquire the feature sequence to be used based on the similarity between the trend sequence and the corresponding feature sequence; and to acquire the electrical lifetime of the low-voltage electrical appliance to be detected based on the feature sequence to be used and the preset prediction model, wherein the preset prediction model is acquired by training the feature sequence corresponding to the sample electrical data.

[0108] Optionally, the determining module 202 is specifically used to determine the distance between each trend sequence and its corresponding feature sequence based on the trend sequence and the corresponding feature sequence; and to determine the feature sequence whose distance is less than or equal to a preset threshold as the feature sequence to be used.

[0109] Optionally, the acquisition module 201 is specifically used to acquire the maximum value, minimum value and sequence length of the electrical lifetime feature in each feature sequence;

[0110] The determination module 202 is specifically used to determine the difference between each feature in the trend sequence based on the maximum value, minimum value and sequence length; and to determine the generated arithmetic progression sequence as the trend sequence corresponding to the feature sequence based on the maximum value, minimum value and the difference between each feature.

[0111] Optionally, based on the above embodiments, this application embodiment may also provide a low-voltage electrical life prediction device, as described below with reference to the accompanying drawings. Figure 5 The implementation process of the given device is illustrated with examples. Figure 6 This is a schematic diagram of the structure of a low-voltage electrical life prediction device provided in another embodiment of this application, as shown below. Figure 6 As shown, the device further includes: a processing module 203, used to perform dimensionality reduction processing on the feature sequences to be used according to the dimensions of the multiple feature sequences to be used if there are multiple feature sequences to be used; wherein, the dimensions of the feature sequences to be used are determined according to the number of feature sequences to be used;

[0112] The acquisition module 201 is specifically used to obtain the electrical lifetime of the low-voltage electrical appliance to be detected based on the dimension-reduced feature sequence to be used and the preset prediction model.

[0113] like Figure 6 As shown, the device also includes a transformation module 204, which is used to transform the coordinate axes of multiple feature sequences to be used, and obtain the coordinate information of each feature point on the transformed coordinate axis on the preset coordinate axis as the coordinate information after dimensionality reduction.

[0114] Optionally, the electrical lifetime characteristics include one or more of the following: contact voltage characteristics, contact current characteristics, contact resistance characteristics, arcing time characteristics, low-energy arcing ratio characteristics, high-energy arcing ratio characteristics, high and low energy arcing probability characteristics, and time-frequency domain characteristics.

[0115] Optionally, the probability characteristics of high and low energy arcing are determined based on the number of occurrences of low-energy and high-energy arcing during the opening and closing of the low-voltage electrical appliance under test, so as to indicate the probability of occurrence of high-energy or low-energy arcing as the number of operations increases.

[0116] like Figure 6 As shown, the device also includes: an extraction module 205, wherein:

[0117] The acquisition module 201 is specifically used to acquire the voltage and current data generated when the low-voltage electrical appliance under test is opened and closed;

[0118] Extraction module 205 is used to extract at least one electrical lifetime feature and generate a feature sequence based on voltage and current data.

[0119] 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.

[0120] 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).

[0121] Figure 7 This is a schematic diagram of the structure of a low-voltage electrical life prediction device provided in an embodiment of this application. The low-voltage electrical life prediction device can be integrated into a terminal device or a chip of a terminal device.

[0122] like Figure 7 As shown, the low-voltage electrical life prediction device includes: a processor 501, a storage medium 502, and a bus 503.

[0123] Processor 501 is used to store programs, and processor 501 calls the programs stored in storage medium 502 to execute the above-mentioned programs. Figures 1-4 The corresponding method implementation is similar in both implementation and technical effect, and will not be described in detail here.

[0124] Optionally, this application also provides a program product, such as a storage medium storing a computer program, including a program that executes the embodiments corresponding to the above-described methods when run by a processor.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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 described in 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.

Claims

1. A low voltage electrical apparatus electrical life prediction method, characterized in that, The method comprises: According to the electrical data in the opening and closing process of the low-voltage electrical apparatus to be detected, the characteristic sequence corresponding to the low-voltage electrical apparatus to be detected is obtained, and the characteristic sequence comprises at least one electrical life characteristic; According to each electrical life characteristic, a trend sequence corresponding to each characteristic sequence is determined; wherein the trend sequence is used for screening the characteristic sequence; According to the trend sequence and the proximity of the corresponding characteristic sequence, a to-be-used characteristic sequence is analyzed and obtained; According to the to-be-used characteristic sequence and a preset prediction model, the electrical life corresponding to the low-voltage electrical apparatus to be detected is obtained, wherein the preset prediction model is obtained by training a characteristic sequence corresponding to sample electrical data; According to each electrical life characteristic, a trend sequence corresponding to each characteristic sequence is determined; wherein the trend sequence is used for screening the characteristic sequence; The maximum value, the minimum value and the sequence length of the electrical life characteristic in each characteristic sequence are obtained; According to the maximum value, the minimum value and the sequence length, the difference between each characteristic in the trend sequence is determined; According to the maximum value, the minimum value and the difference between each characteristic, an arithmetic progression sequence generated is determined as the trend sequence corresponding to the characteristic sequence.

2. The method of claim 1, wherein, According to the trend sequence and the proximity of the corresponding characteristic sequence, a to-be-used characteristic sequence is analyzed and obtained, comprising: According to the trend sequence and the corresponding characteristic sequence, the distance between each trend sequence and the corresponding characteristic sequence is determined; The characteristic sequence with a distance less than or equal to a preset threshold is determined as the to-be-used characteristic sequence.

3. The method of claim 1, wherein, Before the electrical life corresponding to the low-voltage electrical apparatus to be detected is obtained according to the to-be-used characteristic sequence and the preset prediction model, the method further comprises: If the to-be-used characteristic sequence comprises a plurality of to-be-used characteristic sequences, dimension reduction processing is performed on the to-be-used characteristic sequence according to the dimension of the plurality of to-be-used characteristic sequences; wherein the dimension of the to-be-used characteristic sequence is determined according to the number of to-be-used characteristic sequences; According to the to-be-used characteristic sequence and the preset prediction model, the electrical life corresponding to the low-voltage electrical apparatus to be detected is obtained, comprising: According to the to-be-used characteristic sequence after dimension reduction and the preset prediction model, the electrical life corresponding to the low-voltage electrical apparatus to be detected is obtained.

4. The method of claim 3, wherein, According to the dimension of the plurality of to-be-used characteristic sequences, the dimension reduction processing is performed on the to-be-used characteristic sequence, comprising: The coordinate axes of the plurality of to-be-used characteristic sequences are transformed, and the coordinate information of each characteristic point on the preset coordinate axis after transformation is obtained as the coordinate information after dimension reduction.

5. The method of claim 1, wherein, The electrical life characteristic comprises one or more of the following: contact voltage characteristic, contact current characteristic, contact resistance characteristic, arcing time characteristic, low-energy arcing proportion characteristic, high-energy arcing proportion characteristic, high and low energy arcing probability characteristic, time-frequency domain characteristic.

6. The method of claim 5, wherein, The high and low energy arcing probability characteristic is determined according to the number of low-energy arcing and high-energy arcing in the opening and closing process of the low-voltage electrical apparatus to be detected, to indicate the occurrence probability of high-energy arcing or low-energy arcing corresponding to the number of operations.

7. The method of claim 1, wherein, According to the electrical data in the opening and closing process of the low-voltage electrical apparatus to be detected, the characteristic sequence corresponding to the low-voltage electrical apparatus to be detected is obtained, comprising: Obtain voltage and current data generated by the low-voltage electrical apparatus during opening and closing; According to the voltage and current data, at least one electrical life characteristic is extracted and a characteristic sequence is generated.

8. A low voltage electrical apparatus electrical life prediction device, characterized by, The device comprises an obtaining module and a determining module, wherein: The obtaining module is configured to obtain a characteristic sequence corresponding to the low-voltage electrical apparatus according to electrical data during opening and closing of the low-voltage electrical apparatus, the characteristic sequence comprising at least one electrical life characteristic; The determining module is configured to determine a trend sequence corresponding to each characteristic sequence according to each electrical life characteristic, wherein the trend sequence is used to screen the characteristic sequence; The obtaining module is specifically configured to analyze and obtain a to-be-used characteristic sequence according to the trend sequence and the proximity of the corresponding characteristic sequence, and obtain the electrical life of the low-voltage electrical apparatus according to the to-be-used characteristic sequence and a preset prediction model, wherein the preset prediction model is obtained by training a characteristic sequence corresponding to sample electrical data; The determining module is specifically configured to obtain a maximum value, a minimum value, and a sequence length of the electrical life characteristic in each characteristic sequence, determine a difference between each characteristic in the trend sequence according to the maximum value, the minimum value, and the sequence length, and determine that an arithmetic progression sequence generated according to the maximum value, the minimum value, and the difference between each characteristic is the trend sequence corresponding to the characteristic sequence.

9. A low voltage electrical apparatus electrical life prediction device, characterized by, The device comprises a processor, a storage medium, and a bus, the storage medium stores machine-readable instructions executable by the processor, when the low-voltage electrical apparatus electrical life prediction device is running, the processor communicates with the storage medium through the bus, the processor executes the machine-readable instructions to execute the method of any one of claims 1-7.

10. A storage medium, characterized by The storage medium stores a computer program, and the computer program is executed by the processor to execute the method of any one of claims 1-7.

Images