Battery swap station health assessment method, electronic device, and computer storage medium

Abstract

The application discloses a battery swap station health degree evaluation method, an electronic device and a computer storage medium. The method comprises the following steps: in response to the start of the current detection cycle, obtaining the energy storage device data information, the battery swap related device data information and the fault maintenance related information of the battery swap station in the last detection cycle; performing feature extraction on the energy storage device data information, the battery swap related device data information and the fault maintenance related information to obtain the battery swap station data features; and inputting the battery swap station data features into a preset evaluation model to obtain the health degree of the battery swap station. At the start of the current detection cycle, the health degree of the battery swap station is obtained according to the energy storage device data information, the battery swap related device data information and the fault maintenance related information of the battery swap station in the last detection cycle. In this way, the fault prediction and preventive maintenance of the equipment are improved, the stable operation of the power system is ensured, the waste of maintenance cost and human resources is reduced, and the user experience and the enterprise operation and maintenance efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery swap stations, in particular to a battery swap station health degree evaluation method, an electronic device and a computer storage medium. BACKGROUND

[0002] At present, as an important infrastructure for new energy vehicle energy supply, battery swap stations have been rapidly developed in recent years. However, although the popularity rate of battery swap stations is continuously increasing, there is still a great development space and improvement demand in the health management, fault prediction and preventive maintenance of the equipment.

[0003] Firstly, the long-term operation and environmental impact of battery swap station equipment inevitably lead to the occurrence of faults. These faults may cause abnormal operation of the power system, power failure and even equipment damage, resulting in serious economic losses and safety risks.

[0004] Secondly, the operation and maintenance cost of battery swap stations is high, and the downtime caused by equipment failure and the reduction of charging and battery swap success rate will directly affect the user experience and the operation efficiency of enterprises. SUMMARY

[0005] The purpose of the present application is to provide a battery swap station health degree evaluation method, an electronic device and a computer storage medium, which aims to ensure the stable operation of the power system, reduce the waste of maintenance cost and human resources, and improve the user experience and the operation and maintenance efficiency of enterprises.

[0006] To achieve the above purpose:

[0007] In a first aspect, the embodiments of the present application provide a battery swap station health degree evaluation method, which comprises:

[0008] In response to the start of the current detection cycle, the energy storage equipment data information, the battery swap related equipment data information and the fault maintenance related information of the battery swap station in the last detection cycle are acquired;

[0009] The energy storage equipment data information, the battery swap related equipment data information and the fault maintenance related information are subjected to feature extraction to obtain battery swap station data features;

[0010] The battery swap station data features are input into a preset evaluation model to obtain the health degree of the battery swap station.

[0011] Optionally, before the response to the start of the current detection cycle, the method further comprises:

[0012] Acquiring historical energy storage equipment data information, historical battery swap related equipment data information and historical fault maintenance related information of multiple detection cycles of the battery swap station;

[0013] Preprocess the historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information;

[0014] Extract features from the preprocessed historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information to obtain historical energy storage device data features, historical battery swap related data features, and historical fault maintenance data features, respectively;

[0015] Obtain the evaluation model according to the historical energy storage device data features, historical battery swap related data features, and historical fault maintenance data features.

[0016] Optionally, the preprocessing of the historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information includes:

[0017] Perform mean smoothing processing on the abnormal values in the historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information, and / or,

[0018] Perform zero value filling processing on the missing values in the historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information, and / or,

[0019] Perform normalization processing on the time series data information in the historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information, and / or,

[0020] Align the historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information according to time.

[0021] Optionally, the obtaining of the evaluation model according to the historical energy storage device data features, historical battery swap related data features, and historical fault maintenance data features includes:

[0022] Respectively obtain weight coefficients corresponding to the historical energy storage device data features, historical battery swap related data features, and historical fault maintenance data features;

[0023] Input the historical energy storage device data features, historical battery swap related data features, historical fault maintenance data features, and the weight coefficients into an untrained model to obtain the evaluation model.

[0024] Optionally, the inputting of the historical energy storage device data features, historical battery swap related data features, historical fault maintenance data features, and the weight coefficients into an untrained model to obtain the evaluation model includes:

[0025] segmenting the historical energy storage device data features, the historical battery swapping related data features and the historical fault maintenance data features according to a preset segmentation ratio to obtain a training data set and a test data set;

[0026] inputting the training data set, the test data set and the weight coefficients into the untrained model to obtain a trained model.

[0027] Optionally, the inputting the training data set, the test data set and the weight coefficients into the untrained model to obtain a trained model comprises:

[0028] inputting the training data set and the weight coefficients into the untrained model to obtain a trained model;

[0029] inputting the test data set and the weight coefficients into the trained model to obtain an evaluation result;

[0030] judging whether the accuracy of the evaluation result is greater than a preset accuracy threshold;

[0031] if yes, determining the trained model as the evaluation model;

[0032] if no, adjusting the weight coefficients corresponding to the historical energy storage device data features, the historical battery swapping related data features and the historical fault maintenance data features according to the evaluation result, and re-executing the inputting the historical energy storage device data features, the historical battery swapping related data features, the historical fault maintenance data features and the weight coefficients into the untrained model.

[0033] Optionally, the energy storage device data information at least includes any one of photovoltaic energy storage device state basic data and compressed air energy storage device state basic data;

[0034] the battery swapping related device data information at least includes any one of battery swapping station software system module state basic data, battery swapping station device state basic data and battery swapping station device integrity basic data;

[0035] the fault maintenance related information at least includes any one of battery swapping station fault and quality evaluation basic data and work order processing situation basic data.

[0036] Optionally, after the inputting the battery swapping station data features into a preset evaluation model to obtain a health degree of the battery swapping station, the method further comprises:

[0037] performing corresponding alarm feedback according to the score interval where the health degree is located.

[0038] In a second aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of the battery swap station health degree evaluation method when executing the computer program.

[0039] In a third aspect, a computer storage medium is provided, which stores a computer program, and the computer program implements the steps of the battery swap station health degree evaluation method when executed by the processor.

[0040] In the present application, at the beginning of the current detection cycle, the health degree of the battery swap station is obtained according to the energy storage device data information, the battery swap related device data information and the fault maintenance related information of the battery swap station in the last detection cycle, so that the fault prediction and preventive maintenance of the equipment are improved, the stable operation of the power system is ensured, the waste of maintenance cost and human resources is reduced, the use experience of users and the operation and maintenance efficiency of enterprises are improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of a battery swap station health degree evaluation method provided by the embodiment of the present application.

[0042] Figure 2 A structural diagram of a battery swap station operation state monitoring system provided by the embodiment of the present application.

[0043] Figure 3 A structural diagram of an electronic device provided by the embodiment of the present application.

[0044] BRIEF DESCRIPTION OF DRAWINGS

[0045] 310, processor; 311, memory; 312, network interface; 313, bus system. DETAILED DESCRIPTION

[0046] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is only exemplary and is not intended to limit the scope, applicability or configuration of the application. Rather, the scope of the application is limited only by the claims. Various changes and modifications can be made in the exemplary embodiments without departing from the scope of the application as defined by the claims. It is therefore intended that this application cover all such changes and modifications provided they come within the scope of the claims.

[0047] It should be noted that, as used in this document, the terms "include," "includes," or "including" are used as the term is used in patent law; i.e., meaning "including but not limited to." As used herein, the term "and / or" means and, or, or a combination thereof. As used herein, the term "if" can be interpreted to mean "when" or "upon" or "in response to determining" or at least the existence of the stated condition. As used herein, the term "plurality" means two or more. As used herein, the term "exemplary" means serving as an example, instance, or illustration. Any implementation of the

[0048] It should be understood that, although terms first, second, third, etc. can be used herein to describe various information, the information should not be limited to these terms. These terms are only used to distinguish one piece of information from another. For example, a first information can also be termed a second information, and, similarly, a second information can also be termed a first information, without departing from the scope of this document. The word "if' as used herein means "when" or "upon" or "in response to the determination" depending upon the context. Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises", "comprising", "includes" and / or "including", when used herein, specify the presence of stated features, steps, operations, elements, components, items, kinds and / or groups but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, items, kinds and / or groups. As used herein, the term "or" is construed as inclusive or, meaning and / or. Hence "A, B, or C" or "A, B, and / or C" means any of the following: A; B; C; A and B; A and C; B and C; A, B, and C. An exception to this definition will occur only when a combination of elements, functions, steps or acts are in some way inherently mutually exclusive.

[0049] It should be understood that although each step in the flowchart in the embodiments of the present application is shown in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the figure can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately executed with at least part of other steps or sub-steps or stages of other steps.

[0050] It should be noted that in this paper, step codes such as S1, S2, etc. are used, the purpose of which is to more clearly and briefly express the corresponding content, and does not constitute a substantial limitation on the order. In specific implementation, a person skilled in the art may first perform S2 and then perform S1, etc., but these should be within the scope of protection of the present application.

[0051] It should be understood that the specific embodiments described herein are merely used to explain the present application and do not limit the present application.

[0052] In the following description, the suffix such as "module", "component" or "unit" used to represent elements is only for the convenience of the description of the present application, and has no specific meaning. Therefore, "module", "component" or "unit" can be used interchangeably.

[0053] Please refer to Figure 1 , Figure 1 A flowchart of a battery swap station health assessment method is shown, the method comprising:

[0054] S10, in response to the start of the current detection cycle, obtaining the energy storage device data information, the battery swap related device data information and the fault maintenance related information of the battery swap station in the last detection cycle. Specifically, through the setting of the detection cycle, on the one hand, the potential problems and faults of the equipment can be found in time, and the continuity of production and operation is ensured. On the other hand, it is helpful to implement preventive maintenance strategy, effectively prolong the service life of the equipment and improve the operation safety of the equipment. In this embodiment, at the beginning of each detection cycle, the battery swap station operation state monitoring system will automatically obtain the energy storage device data information, the battery swap related device data information and the fault maintenance related information of the battery swap station in the last detection cycle.

[0055] Among them, the energy storage device of the battery swap station serves as the power output source for supplying the entire battery swap station. According to the energy storage device data information generated thereby, the abnormal condition of the energy storage device can be found in time, so as to avoid the abnormality of the energy storage device leading to the entire battery swap station unable to operate normally.

[0056] The battery replacement related equipment is an output source for performing a battery replacement process on an electric vehicle. According to battery replacement related equipment data information generated thereby, abnormal conditions of the battery replacement related equipment can be discovered in a timely manner, so that the user cannot normally replace the battery when driving into the battery replacement station for battery replacement due to the abnormality of the battery replacement related equipment, thereby affecting the user's experience.

[0057] The fault maintenance related information is an information source for feeding back whether a fault maintenance condition occurs in each detection cycle of the battery replacement station. By obtaining the fault maintenance related information of the last detection cycle, the fault and maintenance conditions of the battery replacement station can be known, and the fault and maintenance conditions can be quickly investigated in the current detection cycle, which is more targeted and has higher detection efficiency.

[0058] Further, the detection cycle can be set by the operator of the battery replacement station according to actual conditions, such as every minute, every hour, every day, every week, every month, etc., which is not limited herein.

[0059] S20, feature extraction is performed on the energy storage equipment data information, the battery replacement related equipment data information, and the fault maintenance related information to obtain battery replacement station data features. Specifically, in this embodiment, feature extraction is performed on the energy storage equipment data information, the battery replacement related equipment data information, and the fault maintenance related information to obtain battery replacement station data features, which can reduce the influence of noise and abnormal values on the model and improve the robustness of the model and the operation efficiency of the algorithm.

[0060] For example, feature extraction of the energy storage equipment data information can obtain photovoltaic energy storage equipment features, compressed air energy storage equipment features, generator equipment features, and charger equipment features; feature extraction of the battery replacement related equipment data information can obtain battery replacement station key position monitoring features, battery replacement station temperature control features, and battery temperature features; and feature extraction of the fault maintenance related information can obtain fault quality and other features and work order processing condition features.

[0061] S30, the battery replacement station data features are input into a preset evaluation model to obtain the health degree of the battery replacement station. Specifically, in this embodiment, by inputting the battery replacement station data features obtained in step S2 into the preset evaluation model, the current health degree of the battery replacement station can be output. For example, the health degree can be divided into "healthy", "sub-healthy", "deterioration", and "severe deterioration" according to the good and bad grades. The battery replacement station operation state monitoring system can upload the health degree generated each time to the cloud server, and the battery replacement station and the operation and maintenance personnel can also follow up in a timely manner according to the health degree to quickly carry out targeted processing actions and ensure the stable operation of the battery replacement station.

[0062] By executing steps S10-S30, at the beginning of the current detection cycle, the energy storage device data information, the battery swap related equipment data information and the fault maintenance related information of the battery swap station in the last detection cycle are obtained, the health degree of the battery swap station is obtained based on the preset evaluation model, thereby improving the fault prediction and preventive maintenance of the equipment, ensuring the stable operation of the power system, reducing the waste of maintenance cost and human resources, improving the user experience and the operation and maintenance efficiency of the enterprise.

[0063] Optionally, by formulating a complete battery swap station index evaluation system, the index evaluation system can quantitatively evaluate the health status of the battery swap station related equipment and the energy storage equipment, and provide a basis for subsequent maintenance and optimization. In an embodiment, the total amount of battery swap station data features obtained in step S20 is fixed, wherein the evaluation dimension of the battery swap related equipment data information is 40%, the evaluation dimension of the energy storage equipment data information is 20%, the evaluation dimension of the fault maintenance related information is 20%, and the evaluation dimension of the battery swap success rate is 20%.

[0064] Optionally, before step S10, the method further comprises:

[0065] S6, obtaining historical energy storage device data information, historical battery swap related equipment data information and historical fault maintenance related information of the battery swap station in multiple detection cycles. Specifically, in the present embodiment, the multiple detection cycles at least include two detection cycles before the current detection cycle, and can be much more than two detection cycles, which are used as materials for model training, can effectively improve the training degree of the model, and further improve the accuracy of the model.

[0066] S7, preprocessing the historical energy storage device data information, the historical battery swap related equipment data information and the historical fault maintenance related information. Specifically, in the present embodiment, each basic data in the historical energy storage device data information, the historical battery swap related equipment data information and the historical fault maintenance related information is respectively cleaned, processed for missing values and abnormal values, feature selection, feature conversion and other preprocessing methods, so as to ensure the integrity and high quality of the data.

[0067] S8, feature extraction is performed on the preprocessed historical energy storage device data information, historical battery swapping related device data information, and historical fault maintenance related information to obtain historical energy storage device data features, historical battery swapping related data features, and historical fault maintenance data features respectively. Specifically, in this embodiment, similar to step S20, by performing feature extraction on the preprocessed historical energy storage device data information, historical battery swapping related device data information, and historical fault maintenance related information, historical energy storage device data features, historical battery swapping related data features, and historical fault maintenance data features are obtained respectively. This process can reduce the influence of noise and outliers on the model, improve the robustness of the model and the operation efficiency of the algorithm.

[0068] S9, an evaluation model is obtained according to the historical energy storage device data features, historical battery swapping related data features, and historical fault maintenance data features. Specifically, in this embodiment, the historical energy storage device data features, historical battery swapping related data features, and historical fault maintenance data features are used as the training material of the model. After multiple rounds of cyclic training, when the model converges and / or the number of training reaches the preset number threshold, and / or the accuracy of the model generation result reaches the preset accuracy threshold, the trained model is determined as the evaluation model.

[0069] Optionally, the preprocessing of the historical energy storage device data information, historical battery swapping related device data information, and historical fault maintenance related information in step S7 includes:

[0070] The outliers in the historical energy storage device data information, historical battery swapping related device data information, and historical fault maintenance related information are subjected to mean smoothing processing. Specifically, in this embodiment, mean smoothing processing can reduce the influence of random noise, making the data smoother, thereby reducing the influence of outliers on the overall data, so as to maintain the overall trend and pattern of the data. And / or,

[0071] The missing values in the historical energy storage device data information, historical battery swapping related device data information, and historical fault maintenance related information are subjected to zero value filling processing. Specifically, in this embodiment, by zero value filling processing, the integrity of the data set can be maintained, and the deletion of data rows or columns caused by missing values can be avoided, which has the effect of reducing data loss. And / or,

[0072] The time series data information in the historical energy storage device data information, historical battery swapping related device data information, and historical fault maintenance related information is subjected to normalization processing. Specifically, in this embodiment, by normalizing the time series data information, the data features have similar scales, which helps the model better understand the weight of each data feature and improves the stability of the model. And / or,

[0073] The historical energy storage device data information, historical battery swap related device data information, and historical fault maintenance related information are aligned according to time. Specifically, in this embodiment, the data information is aligned according to time, which can reduce noise caused by inconsistent data collection time and improve data quality on the one hand. On the other hand, it can make the model more accurately capture the data jump trend generated by the energy storage device and battery swap related device of the battery swap station, and improve the performance of the model.

[0074] Optionally, the evaluation model is obtained according to the historical energy storage device data features, the historical battery swap related data features, and the historical fault maintenance data features in step S9, comprising:

[0075] S91, respectively obtaining the weight coefficients corresponding to the historical energy storage device data features, the historical battery swap related data features, and the historical fault maintenance data features. Specifically, in this embodiment, the weight coefficients reflect the relative importance of the three groups of values in the evaluation of the health degree of the battery swap station, and the historical energy storage device data features, the historical battery swap related data features, and the historical fault maintenance data features each have a preset weight coefficient. In one embodiment, the weight coefficient corresponding to the historical battery swap related data features > the weight coefficient corresponding to the historical energy storage device data features ≥ the historical fault maintenance data features.

[0076] S92, inputting the historical energy storage device data features, the historical battery swap related data features, the historical fault maintenance data features, and the weight coefficients into an untrained model to obtain an evaluation model. Specifically, in one embodiment, a linear regression prediction model is used as an untrained model (base model), a linear relationship model between the historical energy storage device data features, the historical battery swap related data features, the historical fault maintenance data features, and the weight coefficients as independent variables (explanatory variables), and the health degree as the dependent variable (response variable) is established to achieve the purpose of prediction analysis.

[0077] Optionally, the historical energy storage device data features, the historical battery swap related data features, the historical fault maintenance data features, and the weight coefficients are input into the untrained model to obtain the evaluation model in step S92, comprising:

[0078] S93, randomly segment the historical energy storage device data features, the historical battery swapping related data features, and the historical fault maintenance data features according to a preset segmentation ratio to obtain a training data set and a test data set. Specifically, in this embodiment, the preset segmentation ratio can be 2.5:7.5, 2:8, 3:7, 3.5:6.5, 4:6, etc., which can be adaptively adjusted according to the accuracy of the model generation result, and is not limited herein. By the preset segmentation ratio, the historical energy storage device data features, the historical battery swapping related data features, and the historical fault maintenance data features can be respectively segmented into two parts, the part with a larger proportion of the three groups of data features is aggregated to form a training data set for model training, and the remaining part is aggregated to form a test data set for model testing.

[0079] S94, input the training data set, the test data set, and the weight coefficient into the untrained model to obtain a trained model. Specifically, in this embodiment, based on the above-mentioned embodiments, a linear regression prediction model is taken as an untrained model (base model), the training data set, the test data set, and the weight coefficient are input into the untrained model for training, and then a trained model is obtained.

[0080] Optionally, in the step S94, the inputting of the training data set, the test data set, and the weight coefficient into the untrained model to obtain a trained model comprises:

[0081] S95, input the training data set and the weight coefficient into the untrained model to obtain a trained model. Specifically, in this embodiment, each data in the training data set and the corresponding weight coefficient are input into the untrained model to achieve the purpose of training the model, and then a trained model is obtained.

[0082] S96, input the test data set and the weight coefficient into the trained model to obtain an evaluation result. Specifically, in this embodiment, each data in the test data set and the corresponding weight coefficient are input into the trained model obtained in the step S95 to achieve the purpose of testing the model, and then an evaluation result corresponding to each input is obtained.

[0083] S97, judge whether the accuracy of the evaluation result is greater than a preset accuracy threshold. If yes, the trained model is determined as an evaluation model; if no, the weight coefficient corresponding to the historical energy storage device data features, the historical battery swapping related data features, and the historical fault maintenance data features is adjusted according to the evaluation result, and the step of inputting the historical energy storage device data features, the historical battery swapping related data features, the historical fault maintenance data features, and the weight coefficient into the untrained model is re-executed.

[0084] Specifically, in the present embodiment, the accuracy of the evaluation result output by the trained model will be determined, and when the accuracy of the evaluation result is greater than the accuracy threshold, it is proved that the trained model converges, and it can be determined as the evaluation model used for subsequent evaluation of the health degree of the battery swap station. Otherwise, the weight coefficients corresponding to the historical energy storage device data features, the historical battery swap related data features, and the historical fault maintenance data features need to be readjusted, and then step S92 is re-executed, and the cycle is repeated until the accuracy of the evaluation result output by the trained model is greater than the accuracy threshold in a certain round of training cycle, the training cycle is stopped, and the finally obtained trained model is determined as the evaluation model.

[0085] Optionally, in an embodiment, the evaluation model is obtained by the following steps:

[0086] Step 1, model definition

[0087] y = p0 + p1x1 + p2x2 +... + p p x p

[0088] Wherein:

[0089] y is the target variable.

[0090] x1, x2, …, x p are input features.

[0091] β0, β1, β2, …, β p are model parameters, i.e. weight coefficients.

[0092] Step 2, prepare data

[0093] The photovoltaic device temperature feature, the DC to AC inverter current feature, the energy management device feature, the generator device feature, the thermal energy storage device temperature feature, the battery swap station temperature control feature, the battery swap station water cooling feature, the battery swap station fire water level feature, the battery swap station charger feature, the battery temperature feature, the battery swap station noise feature, the battery swap station key position feature, the battery swap station network feature, and the battery swap station device life feature are subjected to feature engineering processing to generate a feature array: data = {

[0094] 'feature1': [30,40,50,60,70,80,90] # photovoltaic device temperature feature;

[0095] 'feature2': [15,20,25,30,35,40,45] # DC to AC inverter current feature;

[0096] 'feature3': [30,40,50,60,70,80,90] # thermal energy storage device temperature feature;

[0097] 'feature4': [30,40,50,60,70,80,90] # battery swap station temperature control features;

[0098] 'feature5': [30,40,50,60,70,80,90] # battery swap station water cooling features;

[0099] 'feature6': [5,6,7,8,9,10,11] # battery swap station fire water level features;

[0100] 'feature7': [0,1,2,3,-1] # battery swap station charger status features;

[0101] 'feature8': [10,15,20,25,30,35,40] # battery swap station noise features;

[0102] ……}

[0103] 'target': [95,90,86,80,75,70,65] # battery swap station health score.

[0104] Step 3, Split the dataset

[0105] X = df[['feature1', 'feature2', 'feature3', 'feature4', 'feature5', 'feature6', 'feature7', 'feature8']];

[0106] y = df['target'];

[0107] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42);

[0108] Here, the test dataset accounts for 30% of the total dataset, and the training dataset accounts for the remaining 70%. The random_state parameter is used to control the randomness of the dataset split, initializing the random number generator seed to 42.

[0109] Step 4, Create and train a linear regression model

[0110] At this stage, first create a linear regression model, and then use the data in the training dataset to train it.

[0111] model = LinearRegression();

[0112] model.fit(X_train, y_train)。

[0113] Step 5, Model Prediction

[0114] When the untrained model is trained to obtain the trained model, it is used to predict the data in the test dataset to obtain the value of the target variable.

[0115] y_pred = model.predict(X_test)。

[0116] Step 6, Output Health Model Score

[0117] In this step, the coefficients and intercepts of the trained model are output, which describe the relationship between the features and the target variable.

[0118] coefficients = model.coef_;

[0119] intercept = model.intercept_;

[0120] print(f'Coefficients: {coefficients}');

[0121] print(f'Intercept: {intercept}')。

[0122] Step 7, Detect Model Effect Evaluation

[0123] When evaluating the effect of the prediction model, we usually pay attention to the accuracy, stability and practicality of the model. Common evaluation indicators include:

[0124] 1. Accuracy (Accuracy):

[0125] Definition: The proportion of correctly predicted samples to the total number of samples.

[0126] Formula: Accuracy = (TP+TN) / (TP+TN+FP+FN).

[0127] Where, TP (true positive), TN (true negative), FP (false positive), FN (false negative).

[0128] 2. Precision (Precision):

[0129] Definition: The proportion of actual positive samples in the predicted positive samples.

[0130] Formula: Precision = TP / (TP+FP).

[0131] 3. Recall:

[0132] Definition: The proportion of all actual positive samples that are correctly predicted as positive.

[0133] Formula: Recall = TP / (TP+FN).

[0134] In one embodiment, by judging whether any one of the precision, recall and F1 score (precision) meets the preset accuracy threshold, if not, it indicates that the model has not reached the expected performance level and needs further improvement. The model can be retrained by the method performed in the above step S97 to improve the training effect of the model, and finally obtain a battery swap station health evaluation model that can meet the accuracy threshold.

[0135] In another embodiment, the accuracy of the model can also be judged in the following way:

[0136] (1) mse = mean_squared_error(y_test, y_pred);

[0137] Where, the mean squared error (MSE) is used to calculate the mean squared error between the true value (`y_test`) and the predicted value (`y_pred`), which represents the average of the square of the difference between the predicted value and the true value, and can measure the error degree of the predicted value. The smaller the mse, the more accurate the prediction of the model.

[0138] (2) r2 = r2_score(y_test, y_pred);

[0139] Where, R-square value is also called coefficient of determination, which is used to measure the accuracy of the model, which represents how much of the variation in the dependent variable can be explained by the independent variable. The range of R-square value is 0 to 1, the closer to 1, the stronger the explanation ability of the model, the more accurate the prediction.

[0140] (3) print(f'Mean Squared Error: {mse:.2f}');

[0141] print(f'R-squared: {r2:.2f}');

[0142] The two lines of code above correspond to the mean squared error (mse) and R-squared output, respectively. The `:.2f` is a format string that means to round to two decimal places.

[0143] In summary, the two lines of code above calculate and print the mean squared error (mse) and R-squared value of the model, which can intuitively reflect the accuracy and interpretability of the model's predictions.

[0144] Based on the establishment and specific application of the evaluation model described in the above embodiments, the prediction accuracy of the battery swap station site can reach 90%, the recall rate can reach 90%, and the prediction value accuracy can reach 85%. It has been widely used in the health evaluation of the battery swap station laid in reality.

[0145] Optionally, the energy storage device data information at least includes any one of photovoltaic energy storage device state basic data and compressed air energy storage device state basic data. The photovoltaic energy storage device state basic data and the compressed air energy storage device state basic data may, for example, include charging and discharging efficiency, system loss, SOC (State of Charge) consistency, electrical parameters, environmental factors (such as temperature, humidity, weather, wind volume, etc.), energy conversion efficiency, etc., without limitation.

[0146] Further, the battery swap related device data information at least includes any one of battery swap station software system module state basic data, battery swap station device state basic data, and battery swap station device integrity basic data. The battery swap station software system module state basic data may, for example, include positioning system state, battery swap system state, operation and maintenance system state, safety system state, power supply system state, etc., without limitation.

[0147] The battery swap station device state basic data may, for example, include lifting device state, battery swap mechanical arm state, charging cabinet state, battery box state, and transformer state, without limitation.

[0148] The battery swap station device integrity basic data may, for example, include device utilization rate, device inventory, device vacancy rate, power battery failure rate, and power battery replacement success rate, without limitation.

[0149] Further, the fault maintenance related information at least includes any one of battery swap station fault and quality evaluation basic data and work order processing situation basic data. The battery swap station fault and quality evaluation basic data may, for example, include fault records, quality accident records, equipment maintenance records, performance testing and evaluation, equipment replacement or upgrade, and operation and maintenance personnel training records, without limitation.

[0150] The work order processing condition basic data may include, but is not limited to, user reports, shift handover records, safety responsibility records, task management records, defect and processing conditions, fault levels, and reporting management requirements.

[0151] Optionally, after the battery swap station data features are input into the preset evaluation model to obtain the health degree of the battery swap station, the method further includes:

[0152] Corresponding alarm feedback is performed according to the score interval in which the health degree is located. Specifically, in the embodiment, first, a set of quantifiable health degree level table is established, after the health degree of the battery swap station is obtained in the current detection period, the battery swap station operation state monitoring system will automatically perform matching of the score corresponding to the health degree and the health degree level table, and after confirming the score interval in which the health degree is located, perform the alarm feedback corresponding to the score interval.

[0153] In an implementation, in the health degree level table, the health degree can be divided into “healthy”, “sub-healthy”, “deterioration”, and “severe deterioration” according to the good and bad levels, and the score intervals corresponding to the four levels are [90, 95), [80, 90), [60, 80), and [0, 60) respectively, and the alarm feedbacks corresponding to the four score intervals are “APP prompt alarm script”, “initiate work order, manually intervene”, “SMS reminder + APP prompt alarm script + initiate work order”, and “telephone alarm on-duty personnel for emergency treatment, such as going to the scene immediately for inspection and treatment” respectively.

[0154] Please refer to Figure 2 , Figure 2 A structural schematic diagram of a battery swap station operation state monitoring system is shown. Among them, the basic data layer is used to store all data information of the battery swap station, including energy storage device data information, battery swap related equipment data information, and fault maintenance related information. The data processing layer is used to preprocess the data in the basic data layer to ensure the integrity and high quality of the data. The feature layer is used to extract features from the preprocessed data information, and the extracted features include but are not limited to the 20 features shown in Figure 2 The model layer is used to input the data information after feature extraction into the preset evaluation model and output the health degree score. The business layer is used to perform subsequent alarm feedback actions according to the health degree score. In this way, the entire battery swap station operation state monitoring system can collect and analyze the operation data of the battery swap station related equipment and energy storage equipment in real time, discover and handle potential problems in the battery swap station in a timely manner through the fault prediction and preventive maintenance model, and effectively improve the operation stability and reliability of the equipment.

[0155] Based on the same inventive concept as the foregoing embodiments, the embodiments of the present application provide an electronic device, such as Figure 3As shown, the device comprises a processor 310 and a memory 311 storing a computer program; wherein, Figure 3 The processor 310 in the description is not used to refer to the number of processors 310 being one, but is only used to refer to the positional relationship of the processor 310 relative to other devices. In actual application, the number of processors 310 can be one or more; similarly, Figure 3 The memory 311 in the description also has the same meaning, that is, it is only used to refer to the positional relationship of the memory 311 relative to other devices. In actual application, the number of memories 311 can be one or more. When the processor 310 runs the computer program, the method applied to the above device is implemented.

[0156] The device can further comprise at least one network interface 312. Various components in the device are coupled together through a bus system 313. It can be understood that the bus system 313 is used to realize the connection communication between the components. The bus system 313 includes not only a data bus, but also a power supply bus, a control bus and a status signal bus. However, in order to clearly illustrate, various buses are marked as the bus system 313 in the Figure 3 description.

[0157] The memory 311 can be a volatile memory or a nonvolatile memory, and can include both a volatile and a nonvolatile memory. The nonvolatile memory can be a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a ferroelectric random access memory (FRAM), a flash memory, a magnetic memory, an optical memory, or a compact disc read-only memory (CD-ROM). The magnetic memory can be a magnetic disk memory or a magnetic tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of RAM can be used, such as a Static Random Access Memory (SRAM), a Synchronous Static Random Access Memory (SSRAM), a Dynamic Random Access Memory (DRAM), a Synchronous Dynamic Random Access Memory (SDRAM), a Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM), an Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), a Sync Link Dynamic Random Access Memory (SLDRAM), or a Direct Rambus Random Access Memory (DRRAM).The memory 311 described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable type of memory.

[0158] The memory 311 in the embodiments of the present application is configured to store various types of data to support the operation of the device. Examples of the data include: any computer programs for operating on the device, such as an operating system and application programs; contact data; phonebook data; messages; pictures; videos; and the like. The operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs can contain various application programs, such as a Media Player, a Browser, and the like, for implementing various application services. Here, the program for implementing the method of the embodiments of the present application can be contained in the application programs.

[0159] Based on the same inventive concept as the foregoing embodiments, the present embodiment also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer readable storage medium can be a ferromagnetic random access memory (FRAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, a compact disc read-only memory (CD-ROM), or the like. The computer readable storage medium can also be various devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, or the like. The computer program stored in the computer readable storage medium is run by a processor to implement the above method. The specific step flow implemented by the computer program when executed by the processor will be described in the embodiments of the present application shown in the description. Figure 1 The description of the embodiments shown in the foregoing description will not be repeated here.

[0160] Each of the technical features of the above-described embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described, however, as long as the combinations of the technical features do not exist in contradiction, it should be considered that they are within the scope of the present disclosure.

[0161] In this document, the terms "comprise", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0162] The above description is only specific embodiments of the application, but the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the application, which should be covered by the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A method for assessing the health of a battery swapping station, characterized in that, The method includes: In response to the start of this testing cycle, data information on energy storage equipment, battery swapping-related equipment, and fault repair information of the battery swapping station from the previous testing cycle will be obtained. Feature extraction is performed on the data information of the energy storage device, the data information of the battery swapping related equipment, and the data information of the fault maintenance to obtain the data features of the battery swapping station; The data characteristics of the battery swapping station are input into a preset evaluation model to obtain the health status of the battery swapping station; The energy storage device data information includes at least one of the following: basic status data of photovoltaic energy storage device and basic status data of compressed air energy storage device; The battery swapping related equipment data information includes at least one of the following: basic status data of each module of the battery swapping station software system, basic status data of the battery swapping station equipment, and basic integrity data of the battery swapping station equipment. The fault repair information includes at least one of the following: basic data on the fault and quality assessment of the battery swapping station and basic data on the work order processing status.

2. The method according to claim 1, characterized in that, Prior to the start of the current detection cycle, the method further includes: Acquire historical energy storage equipment data, historical battery swapping related equipment data, and historical fault repair information from multiple testing cycles of the battery swapping station; The historical energy storage equipment data, historical battery swapping equipment data, and historical fault repair information are preprocessed. Feature extraction is performed on the preprocessed historical energy storage equipment data, historical battery swapping related equipment data, and historical fault repair related information to obtain the historical energy storage equipment data features, historical battery swapping related data features, and historical fault repair data features, respectively. The evaluation model is obtained based on the characteristics of historical energy storage equipment data, historical battery swapping data, and historical fault repair data.

3. The method according to claim 2, characterized in that, The preprocessing of the historical energy storage device data, historical battery swapping related device data, and historical fault and maintenance related information includes: Outliers in the historical energy storage device data, historical battery swapping equipment data, and historical fault and maintenance information are subjected to mean smoothing, and / or, Missing values ​​in the historical energy storage device data, historical battery swapping related device data, and historical fault maintenance related data are filled with zero values, and / or, The time-series data information in the historical energy storage equipment data information, historical battery swapping related equipment data information, and historical fault maintenance related information information is normalized, and / or, The historical energy storage equipment data, historical battery swapping equipment data, and historical fault repair information are aligned according to time.

4. The method according to claim 2, characterized in that, The step of obtaining the evaluation model based on the historical energy storage device data characteristics, historical battery swapping related data characteristics, and historical fault repair data characteristics includes: Obtain the weighting coefficients corresponding to the historical energy storage device data features, historical battery swapping related data features, and historical fault repair data features, respectively. The historical energy storage device data features, historical battery swapping related data features, historical fault repair data features, and the weighting coefficients are input into the untrained model to obtain the evaluation model.

5. The method according to claim 4, characterized in that, The step of inputting the historical energy storage device data features, historical battery swapping related data features, historical fault repair data features, and the weighting coefficients into the untrained model to obtain the evaluation model includes: The historical energy storage device data features, historical battery swapping related data features, and historical fault maintenance data features are randomly segmented according to a preset segmentation ratio to obtain training datasets and test datasets. The training dataset, the test dataset, and the weight coefficients are input into the untrained model to obtain a trained model.

6. The method according to claim 5, characterized in that, The step of inputting the training dataset, the test dataset, and the weight coefficients into the untrained model to obtain a trained model includes: The training dataset and the weight coefficients are input into the untrained model to obtain a trained model. The test dataset and the weight coefficients are input into the trained model to obtain the evaluation results. Determine whether the accuracy of the evaluation result is greater than a preset accuracy threshold; If so, the trained model is determined as the evaluation model; If not, adjust the weight coefficients corresponding to the historical energy storage device data features, historical battery swapping related data features, and historical fault repair data features according to the evaluation results, and re-execute the step of inputting the historical energy storage device data features, historical battery swapping related data features, historical fault repair data features, and the weight coefficients into the untrained model.

7. The method according to claim 1, characterized in that, After inputting the data features of the battery swapping station into a preset evaluation model to obtain the health status of the battery swapping station, the method further includes: The corresponding alarm feedback is executed based on the score range in which the health status falls.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the battery swapping station health assessment method as described in any one of claims 1 to 7.

9. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of the battery swapping station health assessment method as described in any one of claims 1 to 7.

Images