Method and device for determining ash deposition state of charging module and electronic equipment

Abstract

The invention discloses a method and device for determining the dust deposition state of a charging module and electronic equipment. The method comprises the following steps: acquiring current temperature data and current electricity data of a target charging module at a target acquisition point, and acquiring a current fan rotating speed of a fan included in the target charging module; determining the power conversion efficiency of the target charging module based on the current electric data; based on the current temperature data, the power conversion efficiency and the current fan rotating speed, a target dust deposition state prediction model is adopted, the dust deposition state of the target charging module is obtained, the target dust deposition state prediction model is used for determining the dust deposition state of the target charging module, and the dust deposition state is used for indicating the dust deposition degree of the target charging module. The technical problem of low accuracy of the ash deposition state determination result of the charging module of the charging pile in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of power systems, and more specifically, to a method, device, and electronic device for determining the dust accumulation state of a charging module. Background Art

[0002] The charging process of electric vehicles presents safety risks, including the risk of spontaneous combustion and low operational and maintenance efficiency. Charging piles serve as the connection point between electric vehicles and the power grid, and their reliable operation directly impacts the efficient use of electric vehicles and the safety of the power grid. Dust accumulation in charging piles not only increases power loss in the charging module but also makes heat dissipation difficult for many components within the module, leading to higher operating temperatures. Because the losses of power devices like MOSFETs are positively correlated with temperature, dust accumulation increases power loss, resulting in lower output voltage, increased harmonics, and reduced conversion efficiency. Therefore, to ensure safe charging of electric vehicles and improve conversion efficiency, accurately predicting the dust accumulation status of charging modules is a pressing issue.

[0003] Related technologies use sensors to collect data such as temperature, pressure, and current from the charging module, and then use data analysis to determine the module's dust accumulation status. However, this analysis is simple and only considers the linear relationship between single parameters, failing to fully reflect the module's performance. Furthermore, the dust accumulation status determination criteria are single and cannot be combined with the module's current state, resulting in significant errors in the dust accumulation status determination results. Consequently, related technologies suffer from the technical problem of low accuracy in determining the dust accumulation status of charging pile modules.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, and electronic device for determining the dust accumulation status of a charging module, so as to at least solve the technical problem in the related art of low accuracy of the dust accumulation status determination result of the charging module of a charging pile.

[0006] According to one aspect of an embodiment of the present application, a method for determining the dust accumulation state of a charging module is provided, including: collecting current temperature data, current electrical data, and current fan speed of a fan included in the target charging module at a target collection point; determining the power conversion efficiency of the target charging module based on the current electrical data; and obtaining the dust accumulation state of the target charging module using a target dust accumulation state prediction model based on the current temperature data, the power conversion efficiency, and the current fan speed, wherein the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module, and the dust accumulation state is used to indicate the degree of dust accumulation of the target charging module.

[0007] According to another aspect of an embodiment of the present application, a device for determining the dust accumulation status of a charging module is provided, including: a data acquisition module for acquiring current temperature data of a target charging module at a target acquisition point, current electrical data, and a current fan speed of a fan included in the target charging module; a power conversion efficiency determination module for determining the power conversion efficiency of the target charging module based on the current electrical data; a dust accumulation status determination module for obtaining the dust accumulation status of the target charging module by using a target dust accumulation status prediction model based on the current temperature data, the power conversion efficiency, and the current fan speed, wherein the target dust accumulation status prediction model is used to determine the dust accumulation status of the target charging module, and the dust accumulation status is used to indicate the degree of dust accumulation of the target charging module.

[0008] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, which stores a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor in any one of the methods for determining the dust accumulation state of a charging module.

[0009] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the methods for determining the dust accumulation status of a charging module.

[0010] In an embodiment of the present application, the current temperature data, current electrical data, and current fan speed of the fan included in the target charging module are collected at the target collection point; the power conversion efficiency of the target charging module is determined based on the current electrical data; and the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module based on the current temperature data, power conversion efficiency, and current fan speed, and the dust accumulation state of the target charging module is obtained, wherein the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module, and the dust accumulation state is used to indicate the degree of dust accumulation in the target charging module. The purpose of determining the dust accumulation state of the charging module by collecting temperature data, electrical data, and fan speed in real time and using the target dust accumulation state prediction model is achieved, and the technical effect of improving the accuracy of the dust accumulation state determination result for the charging module of the charging pile is achieved, thereby solving the technical problem of low accuracy of the dust accumulation state determination result for the charging module of the charging pile existing in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0012] Figure 1is a flow chart of an optional determination method of the dusting state of the charging module according to the embodiment of the application;

[0013] Figure 2 is an optional feature quantity importance diagram according to the embodiment of the application;

[0014] Figure 3 is an optional dusting state prediction result diagram according to the embodiment of the application;

[0015] Figure 4 is a schematic diagram of an optional determination device of the dusting state of the charging module according to the embodiment of the application. DETAILED DESCRIPTION

[0016] In order to enable persons skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should be within the protection scope of the present application.

[0017] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product or device.

[0018] For ease of description, the following describes some nouns or terms related to the embodiments of the present application:

[0019] MOSFET (Metal-Oxide-Semiconductor Field-Effect Transistor, Metal-Oxide-Semiconductor Field-Effect Transistor) is a semiconductor device widely used in electronic circuit design, which has high input impedance, low power consumption, and is easy to be integrated on a large scale.

[0020] According to an embodiment of the present application, a method embodiment of a method for determining the dust accumulation status of a charging module is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0021] Figure 1 This is a flow chart of an optional method for determining the dust accumulation state of a charging module provided in an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0022] Step S102, collecting current temperature data and current electrical data of the target charging module at the target collection point, as well as the current fan speed of the fan included in the target charging module;

[0023] It is understood that the current temperature data and current power data of the target charging module at the target collection point, as well as the current fan speed of the fan included in the target charging module, are collected. By collecting multi-dimensional data from the charging module, the dust accumulation status of the charging module can be evaluated from multiple dimensions, avoiding the one-sidedness caused by evaluating the dust accumulation status based on single-dimensional data and improving the accuracy of the dust accumulation status determination result.

[0024] Optionally, the current temperature data can be collected by deploying temperature sensors at the target collection points of the target charging module. The above-mentioned target collection points can be multiple key locations of the target charging module, such as the surface of the power conversion circuit, MOSFET and other power devices, heat sinks, internal air circulation paths and other locations. By collecting the temperature data of the target collection points, the operating temperature and heat dissipation efficiency of the charging module can be reflected. The above-mentioned electrical data at least includes the input current, input voltage, output current and output voltage of the target charging module. By collecting electrical data, the impact of dust accumulation on the charging efficiency and power conversion of the charging module can be evaluated. The above-mentioned current fan speed at least includes the left fan speed and the right fan speed of the target charging module. By collecting the fan speed, the impact of dust accumulation on fan performance can be evaluated to determine whether dust accumulation causes fan blockage, thereby reducing the fan's heat dissipation efficiency.

[0025] Optionally, dust deposition can affect the charging module's conversion efficiency (i.e., power conversion efficiency, which is determined based on the charging module's electrical data), internal temperature, fan speed, and other parameters. These parameters are coupled to each other, and a single characteristic quantity cannot fully characterize the charging module's dust accumulation status. Therefore, a matrix consisting of the charging module's conversion efficiency at different output voltage levels, temperature data collected at multiple target collection points (i.e., the temperatures at collection points 1 to 5 and 8), and the left and right fan speeds can be used as a characteristic quantity to characterize the charging module's dust accumulation status. These characteristic quantities are shown in Table 1.

[0026] Table 1 Characteristic quantity of charging module

[0027]

[0028] Optionally, the number of fans in the charging module is not fixed, but varies according to the design, power level and heat dissipation requirements of the module. Generally, to ensure stable operation of power electronic devices and prevent overheating, the charging module will be equipped with at least one fan for forced air cooling. However, in high-power charging modules or situations requiring high-efficiency heat dissipation, multiple fans can be integrated, and the number and layout of the fans are usually determined by factors such as the power output of the charging module, the working environment (such as temperature, humidity), etc. Therefore, the charging module can be built-in with a pair of fans (left fan and right fan) respectively located on both sides of the charging module to form air convection and improve heat dissipation effect. At the same time, for high-power charging modules, more fans can be built-in and distributed in different areas of the module, such as the top, bottom, side, etc., to meet higher heat dissipation requirements.

[0029] In an optional embodiment, collecting the current temperature data of the target charging module at the target collection point comprises: obtaining historical temperature data corresponding to a plurality of collection points respectively; performing standardization processing on the historical temperature data corresponding to the plurality of collection points respectively to obtain standard temperature data corresponding to the plurality of collection points respectively; and determining the target collection point from the plurality of collection points based on the standard temperature data corresponding to the plurality of collection points respectively by using principal component analysis.

[0030] It can be understood that, in order to obtain temperature data capable of representing the temperature state of the target charging module, it is necessary to determine the target collection point from a plurality of collection points included in the target charging module. The principal component analysis method can be used to determine the target collection point. First, the obtained historical temperature data of the target charging module at a plurality of collection points respectively is standardized to eliminate the dimensional difference and numerical range difference between the historical temperature data of different collection points, and standard temperature data corresponding to the plurality of collection points respectively is obtained. Based on the standard temperature data corresponding to the plurality of collection points respectively, the target collection point is determined from the plurality of collection points by using principal component analysis. By using the principal component analysis method to determine the target collection point, key temperature data can be identified from a large amount of temperature data, redundant data processing is reduced, and the efficiency of the dust accumulation state prediction and the accuracy of the prediction result are improved.

[0031] Optionally, the data can be standardized by using standard score (Z-Score) normalization, minimum-maximum normalization and decimal scaling normalization.

[0032] Step S104, determining the power conversion efficiency of the target charging module based on the current electrical data;

[0033] It is understood that the power conversion efficiency of the target charging module is determined based on the collected current electrical data of the target charging module, such as input current, input voltage, output current, and output voltage. Determining the power conversion efficiency can provide a quantitative indicator of charging module performance, which can help provide early warning of charging module failures based on the power conversion efficiency determination, prevent further failures, and improve the reliability and safety of the charging pile.

[0034] In an optional embodiment, the power conversion efficiency of the target charging module is determined based on the current electrical data, including: determining the input power of the target charging module based on the input voltage and input current of the target charging module included in the current electrical data; determining the output power of the target charging module based on the output voltage and output current of the target charging module included in the current electrical data; and determining the power conversion efficiency based on the input power and the output power.

[0035] As can be understood, the input power of the target charging module is determined based on the input voltage and input current included in the electrical data; the output power of the target charging module is determined based on the output voltage and output current included in the electrical data. The power conversion efficiency of the target charging module is determined based on the ratio of output power to input power. Power conversion efficiency is a key indicator of charging module performance. By monitoring the output and input power in real time, the conversion efficiency of the charging module can be accurately assessed, thereby determining its operating status and performance level, and providing quantitative data support for the assessment of dust accumulation.

[0036] Step S106, based on the current temperature data, power conversion efficiency, and current fan speed, the target dust accumulation state prediction model is used to obtain the dust accumulation state of the target charging module, wherein the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module, and the dust accumulation state is used to indicate the degree of dust accumulation of the target charging module.

[0037] It can be understood that by inputting the current temperature data, power conversion efficiency, and current fan speed of the target charging module into a predetermined target dust accumulation state prediction model for predicting the dust accumulation state of the target charging module, the dust accumulation state of the target charging module can be obtained, and the dust accumulation degree of the target charging module can be determined based on the dust accumulation state. Through the above method, the dust accumulation state of the target charging module can be predicted in real time, eliminating the need for operation and maintenance personnel to manually check or rely on regular maintenance plans, thereby improving the efficiency and response speed of dust accumulation management.

[0038] In an optional embodiment, before obtaining the dust accumulation state of the target charging module by using a target dust accumulation state prediction model based on current temperature data, power conversion efficiency, and current fan speed, the method further includes: obtaining an initial training data set and an initial test data set of the target charging module, wherein the initial training data set includes historical temperature data, historical electricity data, and historical fan speed of the target collection point collected during the first historical sampling period, and the initial test data set includes historical temperature data, historical electricity data, and historical fan speed of the target collection point collected during the second historical sampling period; preprocessing the initial training data set and the initial test data set to obtain a target training data set and a target test data set; training a predetermined initial dust accumulation state prediction model based on the target training data set to obtain a trained dust accumulation state prediction model; and testing the trained dust accumulation state prediction model based on the target test data set to obtain a target dust accumulation state prediction model.

[0039] It can be understood that during the first historical sampling period, the historical temperature data, historical electricity data and historical fan speed of the target charging module at the target collection point are collected to form an initial training data set; during the second historical sampling period, the historical temperature data, historical electricity data and historical fan speed of the target charging module at the target collection point are collected to form an initial test data set. The data in the above initial training data set and the initial test data set are preprocessed to obtain the target training data set and the target test data set. Using the data in the target training data set, the predetermined initial dust accumulation state prediction model is trained, and the model parameters are optimized through continuous iteration so that it can learn the correlation between the dust accumulation state and the temperature, electricity data and fan speed from the input data to obtain the trained dust accumulation state prediction model; then the data in the target test data set is used to test the trained dust accumulation state prediction model to obtain the target dust accumulation state prediction model. The above data preprocessing and model training process ensures that the model (i.e., the target dust accumulation state prediction model) can learn the characteristics of the dust accumulation state from high-quality, multi-dimensional data, thereby improving the accuracy of the model prediction results and the generalization ability of unknown data.

[0040] Optionally, the above-mentioned preprocessing may include but is not limited to data cleaning (for removing outliers and missing values), data standardization (for ensuring that data of different dimensions and ranges are comparable during the model training process), feature engineering (for converting temperature data, electrical data and fan speed into a format recognizable by the model), etc., to obtain the target training data set and the target test data set, thereby improving the training efficiency of the model and the accuracy of the prediction results.

[0041] Optionally, a random forest model, a support vector machine model, and an XGBoost (eXtreme Gradient Boosting) model can be used as the initial soot accumulation state prediction model. The random forest model can improve the stability of the model through an ensemble learning method, reduce the risk of overfitting, and be suitable for classification tasks when there is a certain degree of correlation between feature quantities, and the data set contains a certain amount of noise or abnormal values. The support vector machine model can well solve the classification problem through the kernel trick, can process small sample data, has a good solution strategy for nonlinear problems, and has good generalization ability, and is suitable for scenarios where the sample size is relatively small compared to the number of features, and there is a nonlinear relationship between data, i.e., the relationship between the feature quantity and the soot accumulation state is complex. The XGBoost model is excellent in handling large amounts of data and features, and can handle class imbalance problems. The XGBoost model has fast training speed and high prediction accuracy, can handle large or small sample data, automatically sorts the importance of features, and is easy to parallel operation, suitable for classification and regression tasks, especially in the case of moderate data volume and complex nonlinear relationships between features.

[0042] In an optional embodiment, the initial training data set and the initial test data set are preprocessed to obtain a target training data set and a target test data set, including: determining a first weight of historical temperature data included in the initial training data set, a second weight of historical electric data included in the initial training data set, and a third weight of historical fan speed included in the initial training data set; preprocessing the historical temperature data included in the initial training data set using the first weight to obtain target temperature data; preprocessing the historical electric data included in the initial training data set using the second weight to obtain target electric data; preprocessing the historical fan speed included in the initial training data set using the third weight to obtain target fan speed; determining the target training data set based on the target temperature data, the target electric data, and the target fan speed; and obtaining the target test data set in the same manner as the target training data set.

[0043] It can be understood that, in order to preprocess the initial training data set and the initial test data set, first, the first weight of the historical temperature data, the second weight of the historical electric data, and the third weight of the historical fan rotating speed are obtained. In order to ensure the quality and consistency of the data, the historical temperature data is weighted using the first weight to obtain target electric data. Similarly, the historical electric data is weighted using the second weight to obtain target electric data, and the historical fan rotating speed is weighted using the third weight to obtain target fan rotating speed. The above-mentioned target temperature data, target electric data, and target fan rotating speed constitute a target training data set. Similarly, the target test data set is obtained in the same way as the target training data set. By weighting and preprocessing the data, the model can pay more attention to the features that are more critical to the prediction of the dust accumulation state during training, thereby improving the training efficiency. At the same time, it can reduce the excessive dependence of the model on certain features during training, while ignoring other important information, thereby reducing the risk of overfitting.

[0044] In an optional embodiment, determining the first weight of the historical temperature data included in the initial training data set, the second weight of the historical electric data included in the initial training data set, and the third weight of the historical fan rotating speed included in the initial training data set comprises: determining the subjective weight and the objective weight of the historical temperature data included in the initial training data set; determining the first weight based on the subjective weight and the objective weight; and obtaining the second weight and the third weight in the same way as the first weight.

[0045] It can be understood that the subjective weight and the objective weight of the historical temperature data are determined, and the first weight of the historical temperature data is determined according to the subjective weight and the objective weight of the historical temperature data; similarly, the subjective weight and the objective weight of the historical electric data are determined, and the second weight of the historical electric data is determined according to the subjective weight and the objective weight of the historical electric data; the subjective weight and the objective weight of the historical fan rotating speed are determined, and the third weight of the historical fan rotating speed is determined according to the subjective weight and the objective weight of the historical fan rotating speed. By giving appropriate weights to different types of data, the model can better capture the key factors affecting the dust accumulation state evaluation, avoid excessive attention to insignificant features, and thus improve the accuracy and stability of the prediction.

[0046] Optionally, the subjective weights of the characteristic quantities such as historical temperature data can be determined by expert scoring method and analytic hierarchy process method, etc. The expert scoring method refers to inviting experts in the field to score the importance of each characteristic quantity according to their professional knowledge and experience, and then determining the subjective weight of the characteristic quantity. This method can directly utilize the experience and professional knowledge of industry experts, but it is highly subjective, and the scores of experts may differ and be influenced by personal bias. The analytic hierarchy process method determines the relative importance of characteristic quantities by pairwise comparison. This method provides a systematic way to handle subjective judgments and can quantify the relative importance between characteristics, but the calculation process is relatively complex, and the rationality of expert scoring has a greater impact on the results.

[0047] Optionally, the objective weights of the characteristic quantities such as historical temperature data can be determined by objective evaluation methods such as Criteria Importance Through Intercriteria Correlation (CRITIC) and entropy weight method. The CRITIC method considers the correlation between characteristic quantities and the variability of the values of characteristic quantities to determine the objective weights of the characteristic quantities. It is suitable for handling multi-feature decision-making problems where characteristic quantities may be related to each other, and the importance of characteristic quantities varies with the dispersion of the values of characteristic quantities. The entropy weight method is a weight determination method based on the principle of information entropy, which is used to measure the uncertainty or information amount of the values of characteristic quantities. The smaller the information entropy, the higher the certainty of the information provided by the characteristic quantity, and the greater its weight should be.

[0048] Optionally, the first weight can be determined by methods such as fuzzy comprehensive evaluation method, weighted index method, and weighted average method, according to the subjective weight and objective weight of the historical temperature data. The fuzzy comprehensive evaluation method refers to using fuzzy set theory and fuzzy mathematical methods to consider the uncertainty of subjective and objective weights, and then determining the first weight by comprehensive evaluation of characteristic weights. The weighted index method refers to strengthening or attenuating the subjective weight and objective weight by an exponential function, and then combining them by weighting to obtain the first weight. The weighted average method refers to weighting and summing the subjective weight and objective weight by a certain proportion to obtain the first weight. The choice of which method to combine the subjective and objective weights depends on specific application scenarios, data quality and complexity, expert knowledge level and availability, etc. When evaluating the dust accumulation state of the charging module, if expert resources are abundant and have sufficient industry experience, the analytic hierarchy process method can be considered first; while for limited data or to handle the uncertainty of weight information, the fuzzy comprehensive evaluation method or weighted index method can be considered first.

[0049] In an optional embodiment, the method further comprises: based on the verification data set, obtaining a predicted dust deposition state of the target charging module by using the target dust deposition state prediction model; based on the predicted dust deposition state and the actual dust deposition state of the target charging module, determining a prediction error of the target dust deposition state prediction model; based on the prediction error and a predetermined error threshold, correcting the target dust deposition state prediction model to obtain a corrected dust deposition state prediction model.

[0050] It can be understood that the verification data set of the target charging module includes temperature data, electrical data and fan speed. The data in the above verification data set is input into the target dust deposition state prediction model to obtain a predicted dust deposition state of the target charging module. The predicted dust deposition state is compared with the actual dust deposition state of the target charging module to calculate the prediction error of the target dust deposition state prediction model. According to the prediction error and the predetermined error threshold, the target dust deposition state prediction model is corrected to obtain a corrected dust deposition state prediction model. Through model correction, the prediction accuracy of the model for the dust deposition state of the charging module can be significantly improved, ensuring that the model can more accurately reflect the actual situation of the dust deposition state and reduce the prediction error.

[0051] Optionally, the prediction error and the error threshold are compared in size. If the prediction error is less than the error threshold, it indicates that the prediction ability of the target dust deposition state prediction model is good and no correction is needed. If the prediction error is greater than or equal to the error threshold, it indicates that the prediction ability of the target dust deposition state prediction model is poor and needs to be corrected. The correction process can be as follows: (1) according to the prediction error, the hyperparameters of the model are optimized, such as learning rate, regularization strength, maximum depth of tree, etc., to improve the generalization ability of the model; (2) according to the prediction error, it is analyzed which features have a greater impact on the prediction results of the model, and according to the analysis results, the features are added or deleted, or the existing features are transformed, to improve the accuracy of the model prediction; (3) if the model shows signs of overfitting, the diversity of training data can be increased and the robustness of the model can be improved by data enhancement techniques such as introducing noise and data augmentation. For the corrected target dust deposition state prediction model, the prediction error is determined again using the verification data set, and the prediction error and the error threshold are compared. If the prediction error is greater than or equal to the error threshold, the model is continuously corrected until the prediction error is less than the error threshold. If the prediction error is less than the error threshold, the corrected target dust deposition state prediction model is used as the above corrected dust deposition state prediction model.

[0052] Optionally, the absolute error, mean square error, precision, recall, etc. can be used as the above prediction error. The absolute error refers to the absolute value of the difference between the predicted value (i.e. the predicted dust accumulation state) and the true value (i.e. the actual dust accumulation state). The absolute error is intuitive and easy to understand, and is not affected by the size of the predicted value. However, it does not distinguish between the size of the error, and a larger error has the same impact on the overall error as a smaller error. Therefore, it is suitable for regression tasks, especially in scenarios where all errors are treated equally. The mean square error is the average of the square of the difference between the predicted value and the true value. The mean square error is very sensitive to outliers, so it is suitable when the size of the prediction error needs to be significantly distinguished. The precision is the proportion of the number of samples correctly classified by the model to the total number of samples. The precision is intuitive and easy to understand, and performs well for cases where the classification distribution is relatively uniform. Therefore, it is suitable for classification tasks, especially when the classification distribution is relatively balanced. The recall is the ability of the model to correctly identify samples of a certain class. In particular, in cases where a certain event (such as a severe situation with 30g of dust accumulation) is of interest, the recall emphasizes the ability of the model to identify a specific class. Therefore, it is suitable for classification tasks, especially when the identification of a certain class is particularly important.

[0053] Through the above steps S102 to S106, the purpose of determining the dust accumulation state of the charging module by collecting temperature data, electrical data and fan speed in real time, and using the target dust accumulation state prediction model can be achieved. The technical effect of improving the accuracy of the determination result of the dust accumulation state of the charging module of the charging pile is realized, and the technical problem of low accuracy of the determination result of the dust accumulation state of the charging module of the charging pile in the related art is solved.

[0054] Based on the above embodiments and optional embodiments, the present application proposes an optional implementation of a method for determining the dust accumulation state of a charging module, which comprises:

[0055] Step S1, selecting a feature quantity representing the dust accumulation state of the charging module.

[0056] Dust deposition will affect the conversion efficiency (i.e. power conversion efficiency, which is determined according to the electrical data of the charging module), internal temperature, fan speed and other parameters of the charging module, and these parameters are mutually coupled, and a single feature quantity cannot fully represent the dust accumulation state of the charging module. Therefore, the conversion efficiency at different output voltage levels of the charging module, the temperature data collected at multiple target collection points (i.e. collection points 1-5 and collection point 8), and the left and right fan speed combination matrix are selected as the feature quantity representing the dust accumulation state of the charging module. The above feature quantity is shown in Table 1.

[0057] Step S2, XGBoost model-based charging module dust accumulation state evaluation.

[0058] The dust accumulation state evaluation of the charging module is a typical classification problem, and the various feature quantities are coupled with each other, and the importance is not easy to evaluate. Compared with other models, firstly, the XGBoost model has fast training speed and high prediction accuracy, and can process large sample or small sample data; secondly, the XGBoost model does not need to perform feature selection, and after training, the importance of the features is automatically given; finally, the XGBoost model is easy to perform parallel operation, further improving the training speed. Therefore, in the optional implementation manner, the XGBoost model is used as the target dust accumulation state prediction model to evaluate the dust accumulation state of the charging module.

[0059] When the XGBoost model is used as the target dust accumulation state prediction model, the verification scale is set to 0.2, that is, 48 groups of feature data and their label items accounting for 80% of the total data set are randomly extracted as the training data set; the remaining 12 groups of feature data and their label items accounting for 20% of the total data set are used as the test data set. Table 2 shows a test data set of an optional target dust accumulation state prediction model provided by the application, and the test set data items and label items are shown in Table 2.

[0060] Table 2 Test data set of target dust accumulation state prediction model

[0061]

[0062]

[0063] In Table 2, the 12 groups of feature data are in turn dust accumulation state 10g output voltage 455V (label item 1), dust accumulation state 0g output voltage 365V (label item 0), dust accumulation state 10g output voltage 290V (label item 1), dust accumulation state 20g output voltage 305V (label item 2), dust accumulation state 10g output voltage 395V (label item 1), dust accumulation state 20g output voltage 440V (label item 2), dust accumulation state 10g output voltage 410V (label item 1), dust accumulation state 0g output voltage 410V (label item 0), dust accumulation state 20g output voltage 380V (label item 2), dust accumulation state 10g output voltage 425V (label item 1), dust accumulation state 0g output voltage 425V (label item 0), and dust accumulation state 20g output voltage 395V (label item 2).

[0064] Figure 2is an optional feature importance diagram provided by an embodiment of the present application, the horizontal axis is the importance score of the feature, and the vertical axis is the feature. When using the XGBoost model as the target dust accumulation state prediction model, the importance of the feature is automatically given after training the model using the training data set. Therefore, the importance of the above-mentioned plurality of feature quantities (i.e. the influence degree of the feature quantity on the prediction result of the model) can be obtained when training the XGBoost model using the above-mentioned training data set. As shown in Figure 2 , among the above-mentioned plurality of feature quantities, the temperature of the collection points 2-5 and 8 has the greatest influence on the dust accumulation state prediction result, and the output voltage value representing the operating condition has the smallest influence on the dust accumulation state prediction result.

[0065] Figure 3 is an optional dust accumulation state prediction result diagram provided by an embodiment of the present application, as shown in Figure 3 , the horizontal axis is the serial number of the data, and the vertical axis is the label item. Using 12 sets of feature data in the test data set, 12 dust accumulation state prediction results (i.e. predicted values) are obtained. Among the corresponding label items of the actual values, 11 sets of label items are consistent, and only when the dust accumulation state 10g output voltage is 455V, the actual value corresponding label item 1 is predicted as label item 2, and the overall accuracy is 91.67%. Although the number of data in the above-mentioned training data set is small, the dust accumulation state prediction result based on the XGBoost model still has a high accuracy. When the data set dimension is higher or the number is larger, a better prediction accuracy can be obtained. Therefore, the prediction model based on XGBoost can effectively realize the recognition and evaluation of the dust accumulation state of the charging module.

[0066] The above-mentioned optional implementation at least realizes the following effects: by collecting multi-dimensional data of the charging module, the dust accumulation state of the charging module can be evaluated from multiple dimensions, avoiding the one-sidedness caused by evaluating the dust accumulation state based on single-dimensional data, and improving the accuracy of the dust accumulation state determination result; by training the multi-dimensional features using the XGBoost model, the dust accumulation state of the charging module can be accurately evaluated, potential failures caused by dust accumulation can be prevented, and operation and maintenance costs and charging risks can be reduced.

[0067] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0068] In the embodiment, a dusting state determination apparatus of a charging module is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" "apparatus" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation of hardware, or a combination of software and hardware, is also possible and contemplated.

[0069] According to the embodiments of the present application, an apparatus embodiment for implementing a dusting state determination method of a charging module is also provided, Figure 4 is a schematic diagram of a dusting state determination apparatus of a charging module according to an embodiment of the present application, as Figure 4 shown, the dusting state determination apparatus of the charging module includes a data acquisition module 402, a power conversion efficiency determination module 404, a dusting state determination module 406, which will be described below.

[0070] The data acquisition module 402 is configured to acquire current temperature data, current electrical data of the target charging module at a target acquisition point, and a current fan speed of a fan included in the target charging module;

[0071] The power conversion efficiency determination module 404 is connected with the data acquisition module 402, and is configured to determine the power conversion efficiency of the target charging module based on the current electrical data;

[0072] The dusting state determination module 406 is connected with the power conversion efficiency determination module 404, and is configured to obtain the dusting state of the target charging module based on the current temperature data, the power conversion efficiency, and the current fan speed, by using a target dusting state prediction model, wherein the target dusting state prediction model is used to determine the dusting state of the target charging module, and the dusting state is used to indicate the dusting degree of the target charging module.

[0073] The dusting state determination device of the charging module provided in the embodiment comprises a data acquisition module 402, a power conversion efficiency determination module 404, and a dusting state determination module 406. The data acquisition module 402 is configured to acquire current temperature data, current electric data, and current fan speed of a fan included in the target charging module at a target acquisition point. The power conversion efficiency determination module 404 is connected to the data acquisition module 402 and configured to determine the power conversion efficiency of the target charging module based on the current electric data. The dusting state determination module 406 is connected to the power conversion efficiency determination module 404 and configured to obtain the dusting state of the target charging module by using a target dusting state prediction model based on the current temperature data, the power conversion efficiency, and the current fan speed. The target dusting state prediction model is used to determine the dusting state of the target charging module, and the dusting state is used to indicate the dusting degree of the target charging module. The purpose of determining the dusting state of the charging module by acquiring the temperature data, the electric data, and the fan speed in real time and using the target dusting state prediction model is achieved, and the technical effect of improving the accuracy of the dusting state determination result of the charging module of the charging pile is achieved, thereby solving the technical problem of low accuracy of the dusting state determination result of the charging module of the charging pile in the related art.

[0074] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, the modules can be located in the same processor or in different processors in any combination.

[0075] It should be noted that the data acquisition module 402, the power conversion efficiency determination module 404, and the dusting state determination module 406 correspond to steps S102 to S106 in the embodiment, and have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in the above embodiment. It should be noted that the modules as part of the device can run in a computer terminal.

[0076] It should be noted that the optional or preferred embodiments of the present embodiment can refer to the related description in the embodiment, which will not be repeated here.

[0077] The dusting state determination device of the charging module can further comprise a processor and a memory. The data acquisition module 402, the power conversion efficiency determination module 404, and the dusting state determination module 406 are stored in the memory as program units, and the processor executes the above program units stored in the memory to realize the corresponding functions.

[0078] The processor includes a core, and the core retrieves corresponding program units in the memory. The core can be set as one or more. The memory can include a non-permanent memory in a computer readable medium, a random access memory (RAM), and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory includes at least one memory chip.

[0079] Embodiments of the present application provide a non-volatile storage medium, which stores a program. The program is executed by a processor to implement a method for determining a dust accumulation state of a charging module.

[0080] Embodiments of the present application provide an electronic device, which includes a processor, a memory, and a program stored in the memory and executable in the processor. When the processor executes the program, the following steps are implemented: collecting current temperature data of a target charging module at a target collection point, current electric data, and a current fan speed of a fan included in the target charging module; determining a power conversion efficiency of the target charging module based on the current electric data; and obtaining a dust accumulation state of the target charging module by using a target dust accumulation state prediction model based on the current temperature data, the power conversion efficiency, and the current fan speed, wherein the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module, and the dust accumulation state is used to indicate a dust accumulation degree of the target charging module. The device in the present document can be a server, a PC, or the like.

[0081] The present application also provides a computer program product, which, when executed in a data processing device, is adapted to execute a program that is initialized with the following method steps: collecting current temperature data of a target charging module at a target collection point, current electric data, and a current fan speed of a fan included in the target charging module; determining a power conversion efficiency of the target charging module based on the current electric data; and obtaining a dust accumulation state of the target charging module by using a target dust accumulation state prediction model based on the current temperature data, the power conversion efficiency, and the current fan speed, wherein the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module, and the dust accumulation state is used to indicate a dust accumulation degree of the target charging module.

[0082] Those skilled in the art should understand that embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0083] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0084] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0085] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0086] In one typical configuration, the computing device includes one or more processors (CPU's), input / output interfaces, network interfaces, and memory.

[0087] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer-readable media.

[0088] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0089] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but also other elements not explicitly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0090] Those skilled in the art will appreciate that embodiments of the present application can be provided as a method, system or computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0091] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for determining the dust accumulation state of a charging module, characterized in that: include: Collecting current temperature data and current electrical data of a target charging module at a target collection point, as well as a current fan speed of a fan included in the target charging module; determining a power conversion efficiency of the target charging module based on the current power data; Based on the current temperature data, the power conversion efficiency, and the current fan speed, a target dust accumulation state prediction model is used to obtain the dust accumulation state of the target charging module, wherein the target dust accumulation state prediction model is used to determine the dust accumulation state of the target charging module, and the dust accumulation state is used to indicate the degree of dust accumulation of the target charging module.

2. The method according to claim 1, characterized in that The collecting of current temperature data of the target charging module at the target collection point includes: Obtain historical temperature data corresponding to multiple collection points; Standardizing the historical temperature data corresponding to the plurality of collection points to obtain standard temperature data corresponding to the plurality of collection points; Based on the standard temperature data respectively corresponding to the multiple collection points, the target collection point is determined from the multiple collection points using a principal component analysis method.

3. The method according to claim 1, characterized in that The determining, based on the current power data, the power conversion efficiency of the target charging module includes: determining the input power of the target charging module based on the input voltage and input current of the target charging module included in the current electrical data; determining the output power of the target charging module based on the output voltage and output current of the target charging module included in the current electrical data; The power conversion efficiency is determined based on the input power and the output power.

4. The method according to claim 1, wherein Before obtaining the dust accumulation state of the target charging module by using a target dust accumulation state prediction model based on the current temperature data, the power conversion efficiency, and the current fan speed, the method further includes: Obtaining an initial training data set and an initial test data set for the target charging module, wherein the initial training data set includes historical temperature data, historical electrical data, and historical fan speed of the target collection point collected during a first historical sampling period, and the initial test data set includes historical temperature data, historical electrical data, and historical fan speed of the target collection point collected during a second historical sampling period; Preprocessing the initial training data set and the initial test data set to obtain a target training data set and a target test data set; Based on the target training data set, a predetermined initial dust accumulation state prediction model is trained to obtain a trained dust accumulation state prediction model; The trained dust accumulation state prediction model is tested based on the target test data set to obtain the target dust accumulation state prediction model.

5. The method according to claim 4, characterized in that The preprocessing of the initial training data set and the initial test data set to obtain a target training data set and a target test data set includes: determining a first weight of the historical temperature data included in the initial training data set, a second weight of the historical electricity data included in the initial training data set, and a third weight of the historical fan speed included in the initial training data set; Preprocessing the historical temperature data included in the initial training data set using the first weight to obtain target temperature data; Preprocessing the historical electrical data included in the initial training data set using the second weight to obtain target electrical data; Preprocessing the historical fan speeds included in the initial training data set using the third weight to obtain a target fan speed; determining the target training data set based on the target temperature data, the target electrical data, and the target fan speed; The target test data set is obtained in the same manner as the target training data set.

6. The method according to claim 5, characterized in that Determining a first weight of the historical temperature data included in the initial training data set, a second weight of the historical electricity data included in the initial training data set, and a third weight of the historical fan speed included in the initial training data set includes: Determining subjective weights and objective weights of historical temperature data included in the initial training data set; determining the first weight based on the subjective weight and the objective weight; The second weight and the third weight are obtained in the same manner as the first weight.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Based on the validation data set, using the target dust accumulation state prediction model, obtaining a predicted dust accumulation state of the target charging module; determining a prediction error of the target dust accumulation state prediction model based on the predicted dust accumulation state and the actual dust accumulation state of the target charging module; Based on the prediction error and a predetermined error threshold, the target dust accumulation state prediction model is corrected to obtain a corrected dust accumulation state prediction model.

8. A device for determining dust accumulation status of a charging module, characterized in that: include: a data acquisition module, configured to acquire current temperature data and current electrical data of a target charging module at a target acquisition point, and a current fan speed of a fan included in the target charging module; a power conversion efficiency determination module, configured to determine the power conversion efficiency of the target charging module based on the current power data; The dust accumulation status determination module is used to obtain the dust accumulation status of the target charging module based on the current temperature data, the power conversion efficiency, and the current fan speed using a target dust accumulation status prediction model, wherein the target dust accumulation status prediction model is used to determine the dust accumulation status of the target charging module, and the dust accumulation status is used to indicate the degree of dust accumulation of the target charging module.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executed by the method for determining the dust accumulation state of a charging module according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the dust accumulation status of a charging module as described in any one of claims 1 to 7.

Images