Power consumption calculation method and device

Abstract

The invention provides a power consumption calculation method and device. The method comprises the steps that the charging electric quantity and the current remaining electric quantity of a target vehicle are acquired; according to the law of conservation of energy, calculating effective discharge electric quantity corresponding to the charge electric quantity; calibrating the residual electric quantity according to the effective discharge electric quantity; and calculating power consumption information of the target vehicle according to the calibrated residual electric quantity.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method and device for calculating power consumption. Background Art

[0002] As the market penetration rate of new energy vehicles continues to increase, users are paying more and more attention to the power consumption of new energy vehicles.

[0003] In actual vehicle use, people have found that the power consumption information disclosed by manufacturers is often inaccurate. This is because manufacturers calculate vehicle power consumption by simulating daily travel situations under ideal conditions, resulting in ideal vehicle power consumption information. However, real-world vehicle usage is not ideal, resulting in a mismatch between user-perceived power consumption and manufacturer-disclosed power consumption. Summary of the Invention

[0004] In view of this, one or more embodiments of the present application provide a power consumption calculation method and device, an electronic device, and a storage medium to solve the problems existing in the related art.

[0005] To achieve the above objectives, one or more embodiments of the present application provide the following technical solutions:

[0006] According to a first aspect of an embodiment of the present application, a method for calculating power consumption is provided, the method comprising:

[0007] Obtain the target vehicle's charging capacity and current remaining capacity;

[0008] According to the law of conservation of energy, calculating the effective discharge power corresponding to the charging power;

[0009] calibrating the remaining power according to the effective discharge power;

[0010] The power consumption information of the target vehicle is calculated based on the calibrated remaining power.

[0011] Optionally, calculating the power consumption information of the target vehicle based on the calibrated remaining power includes:

[0012] The remaining mileage of the target vehicle is calculated based on the calibrated remaining power and the average power consumption of the target vehicle.

[0013] Optionally, calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes:

[0014] The effective discharge power is obtained by subtracting the power transmission loss of the target vehicle from the charging power of the target vehicle.

[0015] Optionally, calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes:

[0016] Obtaining the battery health of the target vehicle, and determining the product of the charged power of the target vehicle and the battery health as the effective charged power of the target vehicle;

[0017] The effective charging power of the target vehicle is subtracted from the power transmission loss of the target vehicle to obtain the effective discharging power.

[0018] Optionally, calibrating the remaining power according to the effective discharged power includes:

[0019] Based on a power calibration formula, the remaining power is calibrated on the basis of the effective discharge power to obtain a calibrated remaining power; wherein the power calibration formula includes:

[0020]

[0021] Among them, SOC is the remaining power after calibration, Q f is the effective discharge capacity, SOH is the battery health, I is the discharge current, and t is the discharge time.

[0022] Optionally, the method further includes:

[0023] Determining a usage scenario corresponding to the target vehicle, and obtaining a scenario coefficient of the same vehicle type as the target vehicle in the usage scenario;

[0024] Performing power consumption calibration on the average power consumption of the target vehicle using the scenario coefficient to obtain calibrated power consumption;

[0025] The calculating the remaining mileage of the vehicle according to the calibrated remaining power and the average power consumption of the target vehicle includes:

[0026] The remaining mileage of the vehicle is calculated based on the calibrated remaining power and the calibrated average power consumption.

[0027] Optionally, obtaining a scenario coefficient of the same vehicle model as the target vehicle in the usage scenario includes:

[0028] Obtain a database of power consumption of vehicles of the same model as the target vehicle and calculate the average power consumption of the same model under the same usage scenario;

[0029] The ratio of the actual average power consumption of the target vehicle to the average power consumption of the same vehicle type is calculated, and the ratio is used as the scenario coefficient.

[0030] Optionally, calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes:

[0031] The charging power is input into a pre-trained prediction model, and the prediction model calculates the effective discharge power corresponding to the charging power according to the law of conservation of energy.

[0032] Optionally, the method further includes:

[0033] In response to the power consumption viewing operation, the power transmission loss and / or the effective discharge power is visually displayed.

[0034] Optionally, the method further includes:

[0035] In response to the power transmission loss reaching a threshold, an alarm message of battery health or charging pile compatibility is triggered.

[0036] Optionally, the warning information includes at least one of the following:

[0037] Visual display of power transmission loss;

[0038] The power transmission loss includes charging power loss, discharging power loss and / or AC-DC conversion loss, which is visually displayed.

[0039] According to a second aspect of an embodiment of the present application, a power consumption calculation device is provided, the device comprising:

[0040] An acquisition unit, which acquires the charging power, current remaining power and average power consumption of the target vehicle;

[0041] The conversion unit calculates the effective discharge power corresponding to the charged power according to the law of conservation of energy;

[0042] The calibration unit calibrates the remaining power calculation unit according to the effective discharged power, and calculates the power consumption information of the target vehicle according to the calibrated remaining power.

[0043] According to a third aspect of an embodiment of the present application, there is provided an electronic device, comprising a communication interface, a processor, a memory, and a bus, wherein the communication interface, the processor, and the memory are interconnected via the bus;

[0044] The memory stores machine-readable instructions, and the processor executes the above method by calling the machine-readable instructions.

[0045] According to a fourth aspect of an embodiment of the present application, a machine-readable storage medium is provided, wherein the machine-readable storage medium stores machine-readable instructions, and when the machine-readable instructions are called and executed by a processor, the above method is implemented.

[0046] The technical solutions provided by the embodiments of the present application may have the following beneficial effects:

[0047] The effective discharge capacity is calculated according to the law of conservation of energy, and the remaining capacity is calibrated to obtain the accurate remaining capacity of the target vehicle. The calibrated remaining capacity is then analyzed to calculate the accurate power consumption information of the target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flowchart of a method for calculating power consumption provided by an exemplary embodiment of the present application;

[0049] Figure 2 A schematic diagram of various stages of prediction model training provided by an exemplary embodiment of the present application;

[0050] Figure 3 A schematic diagram of the relationship between SOC and discharge provided by an exemplary embodiment of the present application;

[0051] Figure 4 A schematic diagram of iterative updating of a prediction model provided by an exemplary embodiment of the present application;

[0052] Figure 5 A schematic structural diagram of an electronic device in which a power consumption calculation device is provided according to an exemplary embodiment of the present application;

[0053] Figure 6 A block diagram of a power consumption calculation device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numbers in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible implementations consistent with one or more embodiments of the present application. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of one or more embodiments of the present application, as detailed in the appended claims.

[0055] It should be noted that in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this application. In some other embodiments, the method may include more or fewer steps than those described in this application. In addition, a single step described in this application may be broken down into multiple steps for description in other embodiments; and multiple steps described in this application may be combined into a single step for description in other embodiments.

[0056] As mentioned above, the power consumption information displayed by existing vehicles does not match the actual power consumption information of the vehicles, which in turn causes users to distrust the power consumption of the vehicles, and even worse, affects the brand image of the models and car companies.

[0057] Therefore, it is necessary to provide a solution that can accurately calculate and trustworthy vehicle power consumption, so as to provide accurate vehicle power consumption information to driving users.

[0058] See below Figure 1 , Figure 1 This is a flow chart of a method for calculating power consumption provided by an exemplary embodiment of the present application. Figure 1 As shown, the method may include the following steps:

[0059] Step 110: Obtain the charging power and current remaining power of the target vehicle.

[0060] Step 120, calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy;

[0061] Step 130, calibrating the remaining power according to the effective discharge power;

[0062] Step 140 : Calculate the power consumption information of the target vehicle based on the calibrated remaining power.

[0063] In the present application, the charging capacity may refer to the rated capacity of the battery, that is, the amount of electricity required to charge the battery from 0% to 100%; under ideal conditions, the charging capacity of the battery can be 100% converted into discharging capacity.

[0064] However, in actual use, it is often difficult to achieve the ideal state due to many restrictions, and it is also impossible to convert 100% of the battery's charging capacity into discharging capacity.

[0065] Since the discharged power is not equal to the charged power, there is uncertainty in the remaining power available for vehicle driving. Therefore, it is impossible to accurately predict the remaining mileage based on the uncertain remaining power.

[0066] Based on this, this application constructs the charging power Q according to the principle of energy conservation. c and effective discharge capacity Q f The dynamic conversion rate algorithm based on the relationship between them is used to calculate the accurate effective discharge capacity.

[0067] In an exemplary embodiment, the calculation of the effective discharge power corresponding to the charge power according to the law of conservation of energy may include:

[0068] The effective discharge power is obtained by subtracting the power transmission loss of the target vehicle from the charging power of the target vehicle.

[0069] In this application, taking into account the fact that in actual applications, batteries generally suffer from power transmission losses during the charging and discharging process, which results in the inability to convert 100% of the charging power into the discharging power, the power transmission losses are introduced into the dynamic conversion rate algorithm of energy conservation to realize the calculation of the effective discharge power.

[0070] For example, the energy conservation law may refer to the dynamic conversion rate algorithm shown in the following formula 1:

[0071] Q c =Q s +Q f Formula 1

[0072] Among them, Q c is the charging capacity Q c , Q f is the effective discharge capacity, Q s It is the power transmission loss;

[0073] It is understandable that the power transmission loss may include power loss during the charging process, power loss during the discharging process, power loss during DC / AC conversion, etc.

[0074] In another exemplary embodiment, the calculation of the effective discharge power corresponding to the charge power according to the law of conservation of energy may include:

[0075] Obtaining the battery health of the target vehicle, and determining the product of the charged power of the target vehicle and the battery health as the effective charged power of the target vehicle;

[0076] The effective charging power of the target vehicle is subtracted from the power transmission loss of the target vehicle to obtain the effective discharging power.

[0077] In this application, it is also taken into consideration that in actual use, as the number of battery charge and discharge times increases, the battery will usually have a certain performance degradation, so that the battery's charging power cannot be fully converted into discharge power. Therefore, the factors affecting power transmission loss and battery performance degradation are also introduced into the dynamic conversion rate algorithm of energy conservation to realize the calculation of effective discharge power.

[0078] For example, the battery performance degradation can be quantified using SOH (State of Health), which reflects the battery capacity degradation. Accordingly, the dynamic conversion rate algorithm of energy conservation can refer to the following formula 2:

[0079] Q c *SOH=Q s +Q f Formula 2

[0080] Among them, Q c is the charging capacity Q c , SOH is the battery health, Q f is the effective discharge capacity, Q s It is the power transmission loss.

[0081] It is understandable that the power transmission loss may include power loss during the charging process, power loss during the discharging process, power loss during DC / AC conversion, etc.

[0082] It should be noted that in any of the above dynamic conversion rate algorithms, the effective discharge capacity can usually reflect the vehicle's range, which can be expressed as Q s =H*L; where H is the power consumption and L is the cruising range.

[0083] However, the effective discharge capacity is not the remaining capacity, so the power consumption information of the target vehicle cannot be directly calculated based on the effective discharge capacity, and the remaining capacity of the target vehicle does not take into account the battery performance degradation, power transmission damage, etc. described in the above embodiment.

[0084] Based on this, the present application also proposes a process of calibrating the current remaining power of the target vehicle based on the above-mentioned effective discharge power, namely the above-mentioned step 130.

[0085] In an exemplary embodiment, step 130 of calibrating the remaining power according to the effective discharge power may include:

[0086] Based on the power calibration formula, the remaining power is calibrated on the basis of the effective discharge power to obtain the calibrated remaining power; wherein the power calibration is shown in the following formula 3:

[0087]

[0088] Among them, SOC (State of Charge) is the remaining power after calibration, Q f is the effective discharge capacity, SOH is the battery health, I is the discharge current, and t is the discharge time.

[0089] In this embodiment, by introducing the battery health and combining the real-time current I and time t, the SOC estimation value can be dynamically corrected to avoid the error caused by the traditional linear calculation of the remaining power.

[0090] In an exemplary embodiment, calculating the power consumption information of the target vehicle based on the calibrated remaining power may include:

[0091] The consumed power of the target vehicle is determined based on the calibrated remaining power; wherein the consumed power may include power used for vehicle driving, power used by vehicle electronic equipment (such as air conditioning), power transmission loss, battery capacity attenuation, etc.

[0092] Through this embodiment, the actual power consumed by the vehicle can be accurately analyzed using the calibrated remaining power, and the power consumption details of the consumed power can be further provided, thereby avoiding the user's misunderstanding that all the vehicle power consumption is used for vehicle driving. The feasibility of power consumption information can be improved based on the power consumption details.

[0093] In an exemplary embodiment, calculating the power consumption information of the target vehicle based on the calibrated remaining power may include:

[0094] The remaining mileage of the target vehicle is calculated based on the calibrated remaining power and the average power consumption of the target vehicle.

[0095] In related technologies, vehicles can usually display the remaining mileage, but the actual mileage is usually less than the remaining mileage. This is because the existing power consumption analysis refers to the remaining battery power (i.e. the remaining power before calibration) when calculating the remaining mileage of the vehicle, and then performs a linear calculation based on the remaining power. However, in actual vehicle use, not all of the remaining battery power is used to power the vehicle, resulting in the actual mileage being less than the displayed remaining mileage, which makes users generally skeptical about the remaining mileage displayed by the vehicle, exacerbating "mileage anxiety" and affecting driving experience and travel confidence.

[0096] Through the embodiments provided in the present application, the effective discharge power is calculated according to the dynamic conversion rate algorithm of the law of conservation of energy, and the remaining power is calibrated to obtain the remaining power for powering the target vehicle. Since the calibrated remaining power can be fully used for vehicle driving, the remaining mileage of the vehicle can be accurately calculated based on the calibrated remaining power and the average power consumption.

[0097] In an exemplary embodiment, the method further includes:

[0098] Determining a usage scenario corresponding to the target vehicle, and obtaining a scenario coefficient of the same vehicle type as the target vehicle in the usage scenario;

[0099] Performing power consumption calibration on the average power consumption of the target vehicle using the scenario coefficient to obtain calibrated power consumption;

[0100] Accordingly, the calculation of the remaining mileage of the vehicle based on the calibrated remaining power and the average power consumption of the target vehicle may include:

[0101] The remaining mileage of the vehicle is calculated based on the calibrated remaining power and the calibrated average power consumption.

[0102] In this application, taking into account the different levels of electricity consumption in different usage scenarios, for example, the usage scenario of refrigerated trucks in freight business requires more electricity consumption because the refrigeration in the refrigerated trucks themselves consumes a lot of electricity. Therefore, the scenario coefficient under the usage scenario of the target vehicle is introduced to calibrate the average power consumption of the target vehicle.

[0103] Exemplarily, the calculation of the remaining mileage of the vehicle based on the calibrated remaining power and the calibrated average power consumption can be achieved by the following formula 4:

[0104]

[0105] Among them, L s Indicates the remaining mileage, H represents the average power consumption, and η is the scenario coefficient. It can indicate the power consumption after calibration.

[0106] Through the above embodiments, based on the scenario coefficient, it is possible to predict the remaining mileage that is more in line with the actual usage scenario.

[0107] In an exemplary embodiment, the scene coefficient is calculated in the following manner:

[0108] Obtain a database of power consumption of vehicles of the same model as the target vehicle and calculate the average power consumption of the same model under the same usage scenario;

[0109] The ratio of the actual average power consumption of the target vehicle to the average power consumption of the same vehicle type is calculated, and the ratio is used as the scenario coefficient.

[0110] In this embodiment, by comparing the average power consumption of the target vehicle with similar vehicles, the scenario coefficient is dynamically adjusted to eliminate the data deviation of a single vehicle.

[0111] In an exemplary embodiment, calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes:

[0112] The charging power is input into a pre-trained prediction model, and the prediction model calculates the effective discharge power corresponding to the charging power according to the law of conservation of energy.

[0113] In this application, by using machine learning technology to pre-train a prediction model that can quickly calculate the effective discharge power, computing efficiency can be improved and response time can be reduced.

[0114] The following further introduces the relevant content of the preset model.

[0115] The prediction model can be obtained by Figure 2 The various stages shown may include, for example, [data preparation], [feature engineering], [data labeling], [model training and tuning], [model evaluation], and [model iteration] stages, with gradual training and improvement.

[0116] [Data preparation]

[0117] The prediction model design can provide data files that comply with relevant technical standards (such as those based on GB / T 32960-3 full life cycle vehicles). The file format of the data files may include but is not limited to .parquet files, .csv files, or .json files.

[0118] The data file contains at least some or all of the following data fields, which can be used in the subsequent [feature engineering] stage:

[0119] Time and date, maximum temperature probe value, minimum temperature probe value, temperature values ​​detected by each temperature probe, maximum single cell voltage value, minimum single cell voltage value, voltage value of each single cell, vehicle status, charging status, operating mode, speed, mileage, total power battery voltage, total power battery current, power battery SoC, longitude, latitude.

[0120] In addition, the vehicle's operating area, season, weather and other data can be obtained based on the latitude and longitude information in the map data; and the vehicle charging order information such as charging power, charging time and other data can be obtained based on the data of the charging pile to which the vehicle is connected.

[0121] The acquired raw data can be cleaned. The purpose of data cleaning is to ensure the quality and accuracy of the raw data. Through data cleaning, invalid data, inconsistent data formats, data errors, missing data and other abnormal data in the raw data can be resolved, making the cleaned data more suitable for subsequent data analysis, processing and application.

[0122] For example, for data cleaning of a prediction model, the following cleaning rules can be used to ensure data continuity and availability:

[0123] Delete rows whose dates exceed the specified value;

[0124] Delete the invalid rows where both the maximum and minimum temperature probe values ​​are 215;

[0125] Delete the invalid rows where both the highest and lowest single cell voltage values ​​are 65.535;

[0126] Delete invalid rows in the single cell list where 1 / 3 of the values ​​exceed 65.535;

[0127] Delete invalid values ​​in latitude and longitude, battery, power level, voltage, and speed.

[0128] In addition, data cleaning can be performed by verifying the data in groups A and B. For example, the power and time information of charging orders can be cleaned based on the vehicle status and charging status, and the charging rules of both parties can be accurately matched (charging start / end time range is within 5 minutes). This verifies whether the vehicle status message and charging data are abnormal, and cleans the abnormal data.

[0129] [Feature Engineering]

[0130] In machine learning tasks, feature engineering is used to transform raw data into more meaningful features that are more suitable for machine learning algorithms, such as determining model input, model output, and other features.

[0131] During actual battery use, side reactions and irreversible loss of active materials occur, such as active material dissolution, electrolyte decomposition, and lithium metal deposition, leading to irreversible degradation of battery capacity. Vehicle-side battery applications can be reflected in driving and charging data. Analyzing the driving and charging habits of different vehicles can extract effective features. Extracting effective features from raw data related to mileage, calendar, current, state of charge, and temperature can also be used to reflect battery degradation.

[0132] The vehicle's Battery Management System (BMS) typically uploads vehicle-side data to the cloud, where mileage represents the vehicle's operating conditions and, to a certain extent, the battery's usage. The time and date can be used to calculate calendar life, and the difference between the current time and the initial time represents the battery's calendar decay. Similarly, by analyzing charging data, the number of battery charges can be calculated based on changes in the charging state, and the integral of the charging current and time can also represent the battery's cumulative charging capacity. Therefore, relevant charging characteristics can be extracted based on the charging state, total power battery current, power battery SOC, and vehicle status.

[0133] The following examples illustrate some of the features determined through feature engineering:

[0134] Mileage feature. The unit is kilometers (km). The vehicle-side mileage is used as the characteristic value of the mileage feature.

[0135] Calendar decay feature. Measured in days. The current time minus the initial date is used as the calendar decay feature value.

[0136] Average daily driving distance feature. The unit is kilometers per day (km / day), using mileage / calendar as the feature value of average daily driving distance;

[0137] Cumulative charging times feature. The unit is times. The number of parking charges is calculated based on the change of the charging status field.

[0138] Average charge start SOC characteristic. By recording the SOC at the start of each charge, the average charge start SOC is calculated.

[0139] Average end-of-charge SOC characteristics. By recording the SOC at the end of each charge, the average end-of-charge SOC is calculated.

[0140] Charging capacity characteristics. The unit is ampere-hour (Ah). The product of charging current and time is used as the characteristic value.

[0141] Charging times per 1000km. The unit is times. The characteristic value is calculated as: cumulative charging times / mileage / 1000.

[0142] Average charging current characteristics. The charging current is calculated as the characteristic value.

[0143] It can be understood that the features shown above are only examples, and in actual applications, other features can be flexibly determined according to actual needs.

[0144] [data label]

[0145] Based on the aforementioned raw data such as SOC, voltage, battery cumulative charging energy, battery charging state, battery real-time current, vehicle speed, ampere-hours, etc., the relationship between SOC and discharge can be optimized using the following formula 5:

[0146]

[0147] Where η coulomb is the coulomb efficiency (used to characterize the difference in charge and discharge efficiency).

[0148] The SOC before and after optimization by formula 5 can be Figure 3 As shown in FIG, the optimized SOC curve is smoother, which can better establish the mapping relationship between SOC and discharge.

[0149] [Model training and tuning]

[0150] First, let’s introduce model training:

[0151] The data processed through the above stages can be used as a training set, which is input into the prediction model for training.

[0152] The prediction model can be a hybrid model of a multilayer perceptron (MLP) and a support vector regression (SVR). The MLP model and the SVR model are described below:

[0153] [MLP model]

[0154] MLP is a feedforward neural network consisting of multiple neurons (or nodes), usually including an input layer, a hidden layer, and an output layer.

[0155] When instantiating the MLP model, you can set the parameters corresponding to the MLP model. The parameters may include:

[0156] hidden_layer_sizes: Used to set the number of hidden layers and the number of neurons in the hidden layer within the MLP model. The number of hidden layers and the number of neurons in each layer can be changed by setting different integers or tuples.

[0157] Activation: Used to set the activation function of the MLP model. By introducing an activation function, the transmission between hidden layers can achieve nonlinear combination, making the neural network suitable for solving nonlinear problems. Exemplary activation functions include identity activation function, logistic activation function, tanh activation function, ReLU activation function, etc.

[0158] Solver: Used to set the weight optimizer of the MLP model. Exemplary weight optimizers include lbfgs optimizer, sgd optimizer, adam optimizer, etc.

[0159] alpha: Used to set the L2 regularization parameter in the MLP model. Alpha can be used to control the complexity of the model. Specifically, by limiting the size of the weights, it can prevent the model from overfitting, thereby improving the model's generalization ability.

[0160] learning_rate: Sets the learning rate in the MLP model. The learning rate controls the speed and stability of weight updates, determining the magnitude of weight updates at each iteration. Excessively large learning rates can make it difficult for the model to converge, while excessively small ones can lead to slow convergence.

[0161] max_iter: Sets the number of iterations in the MLP model. Model training terminates when this number of iterations is reached. Each iteration includes forward propagation, loss function calculation, backpropagation, and weight updates.

[0162] random_state: used to set the random seed.

[0163] [SVR model]

[0164] The SVR model is a regression model. It's typically used to solve regression problems—predicting continuous values—rather than classification problems. The core concept of SVR is similar to that of SVM, but in regression tasks, its goal is to find a regression function that is as smooth as possible to accurately predict the output.

[0165] Similar to the MLP model, when instantiating the SVR model, you also need to set the parameters corresponding to the SVR model. The parameters may include:

[0166] Kernel: This parameter is used to specify the kernel function. Common kernel function parameters include linear (linear kernel), poly (polynomial kernel), rbf (radial basis function kernel), etc.

[0167] C: represents the regularization parameter. The C parameter is used to control the degree of penalty for error. The default value is 1.0.

[0168] Epsilon: used to set the width of the ε-insensitive interval, which is used to define the range of acceptable error. Predictions within the ε range of the training sample are considered accurate.

[0169] gamma: kernel coefficient, if set to 'scale', the value of γ will be scaled by the inverse of the number of features. If set to 'auto', the value of γ will be scaled by the size of the dataset.

[0170] degree: The order of the polynomial kernel (polynomial kernel is valid).

[0171] tol: Algorithm tolerance parameter. If the change in model parameters is less than this value, it is considered to have reached convergence.

[0172] After instantiating the MLP model and the SVR model, the aforementioned training set can be used to train the model, and the model parameters can be tuned during the model training process.

[0173] Typically, different combinations of parameters will affect the actual performance of the model. Since there are a large number of hyperparameter combinations, the embodiment of the present application can automatically complete hyperparameter optimization using grid search and cross-validation methods. Wherein, the grid search method needs to list the debugged hyperparameters in advance, and then try all possible hyperparameter combinations to find the optimal hyperparameters. The cross-validation can divide the training set into multiple subsets, perform training tests on different subsets, and evaluate the performance of the model under the current hyperparameter combination. The final output has the hyperparameter combination with the best performance and the corresponding performance evaluation results.

[0174] It should be noted that due to the large differences in the actual usage environment of vehicles, when training the prediction model, the corresponding prediction model can be trained separately according to environmental conditions such as road conditions in different regions (provinces, cities and districts), different seasons (temperatures), different vehicle conditions, and different models.

[0175] This allows predictions to be made for a target vehicle by matching the corresponding prediction model to the target vehicle's environmental conditions, further improving the accuracy of power consumption calculations.

[0176] [Model Evaluation]

[0177] After the prediction model constructed by the MLP model and the SVR model is trained, the model performance can be evaluated according to some preset evaluation indicators.

[0178] Since the prediction model belongs to the regression prediction model, the following evaluation indicators can be considered:

[0179] MAE (mean absolute error) represents the average deviation between the predicted value and the true value, reflecting the actual situation of the predicted value error.

[0180] The calculation formula of MAE value is as follows:

[0181]

[0182] Among them, m represents the number of training samples in the training set, y i represents the predicted value of the i-th training sample, Represents the true value of the i-th training sample.

[0183] MSE (mean square error) represents the average of the sum of the squares of the differences between each data point and the true value. The smaller the MSE value, the better the accuracy of the prediction model.

[0184] The calculation formula of MSE value is as follows:

[0185]

[0186] R2 (coefficient of determination), the coefficient of determination characterizes the effect of fitting through the change of data. The closer it is to 1, the better the model prediction effect.

[0187] The formula for calculating the R2 value is as follows:

[0188]

[0189] [Model iteration]

[0190] This application can use incremental iterative learning to update the trained prediction model by introducing new data. In incremental learning, the new data can be used to partially train the model, improving the accuracy and generalization ability of the model.

[0191] Please refer to the following Figure 4 The flowchart of iterative training is shown in Figure 2. Figure 4 As shown, the trained prediction model is exported as a .pkl file for saving. When a new training data set needs to be expanded, the .pkl file is loaded into the training environment, incremental learning is performed through partial_fit, and the trained prediction model is exported as a .pkl file, and the onnx model required for deployment is exported.

[0192] In an exemplary embodiment, the method further includes:

[0193] In response to the power consumption viewing operation, the power transmission loss and / or the effective discharge power is visually displayed.

[0194] In this embodiment of the present application, users can view in real time the power transmission loss within the charging power, the effective discharge power actually used to drive the vehicle, or the ratio of power transmission loss to effective discharge power. This visualized power consumption detail enhances the user's understanding of vehicle power consumption, thereby helping the user make reasonable charging plans and itinerary arrangements for travel.

[0195] In an exemplary embodiment, the method further includes:

[0196] In response to the power transmission loss reaching a threshold, an alarm message of battery health or charging pile compatibility is triggered.

[0197] In an embodiment of the present application, if the power transmission loss of a certain charge reaches a threshold, the threshold can be an artificially set empirical value, for example, a preset proportion (10%) of the battery rated capacity, that is, when the power transmission loss reaches 10% of the battery rated capacity, an alarm message can be triggered.

[0198] For example, the threshold can be set based on the average power transmission loss of similar models. For example, it can be set to increase the average power transmission loss by 15%. In other words, when the power transmission loss of the target vehicle exceeds the average power transmission loss of similar models by 15%, an alarm message can be triggered. In this way, by comparing the average power transmission loss of similar models, it can be determined whether the power transmission loss of the target vehicle is abnormal.

[0199] It is understandable that the threshold value can be flexibly configured according to actual needs. By setting a reasonable threshold value, battery health problems or charging pile compatibility problems can be discovered in a timely manner.

[0200] In an exemplary embodiment, the warning information may include at least one of the following:

[0201] Visual display of power transmission loss;

[0202] The power transmission loss includes charging power loss, discharging power loss and / or AC-DC conversion loss, which is visually displayed.

[0203] By visually displaying alarm information, users can be informed of the cause of an anomaly, such as excessive power transmission loss, or whether the cause is excessive charging loss, discharging loss, or DC conversion loss. This alarm information also facilitates rapid locating of the cause of the fault and developing a corrective action plan during subsequent repairs, significantly improving after-sales service efficiency.

[0204] In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

[0205] Figure 5 This is a schematic structural diagram of an electronic device provided by an exemplary embodiment. Figure 5 At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course may also include hardware required for other services. One or more embodiments of the present application can be implemented based on software, such as the processor reading the corresponding computer program from the non-volatile memory into the memory and then running it. Of course, in addition to software implementation, one or more embodiments of the present application do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0206] Please refer to Figure 6 In a software embodiment, a power consumption calculation device is provided, the device comprising:

[0207] An acquisition unit 610 acquires the charging power and current remaining power of the target vehicle;

[0208] The conversion unit 620 calculates the effective discharge power corresponding to the charging power according to the law of conservation of energy;

[0209] A calibration unit 630 calibrates the remaining power according to the effective discharge power;

[0210] The calculation unit 640 calculates the power consumption information of the target vehicle according to the calibrated remaining power.

[0211] Optionally, the calculation unit 640 includes:

[0212] The mileage calculation subunit calculates the remaining mileage of the target vehicle according to the calibrated remaining power and the average power consumption of the target vehicle.

[0213] Optionally, the conversion unit 620 is further configured to subtract the power transmission loss of the target vehicle from the charging power of the target vehicle to obtain the effective discharge power.

[0214] Optionally, the conversion unit 620 is further used to obtain the battery health of the target vehicle, and determine the product of the charging power of the target vehicle and the battery health as the effective charging power of the target vehicle; subtract the power transmission loss of the target vehicle from the effective charging power of the target vehicle to obtain the effective discharge power.

[0215] Optionally, the calibration unit 630 is further configured to calibrate the remaining power based on the effective discharge power based on a power calibration formula to obtain a calibrated remaining power; wherein the power calibration formula includes:

[0216]

[0217] Among them, SOC is the remaining power after calibration, Q f is the effective discharge capacity, SOH is the battery health, I is the discharge current, and t is the discharge time.

[0218] Optionally, the device further includes:

[0219] A coefficient calculation subunit determines a usage scenario corresponding to the target vehicle and obtains a scenario coefficient of the same vehicle type as the target vehicle in the usage scenario;

[0220] a power consumption calibration subunit, which uses the scenario coefficient to calibrate the average power consumption of the target vehicle to obtain a calibrated power consumption;

[0221] The calculation unit 640 is further configured to calculate the remaining mileage of the vehicle based on the calibrated remaining power and the calibrated average power consumption.

[0222] Optionally, the coefficient calculation subunit obtains a power consumption database of the same model as the target vehicle, and counts the average power consumption of the same model under the same usage scenario; calculates the ratio of the actual average power consumption of the target vehicle to the average power consumption of the same model, and uses the ratio as the scenario coefficient.

[0223] Optionally, the conversion unit 620 is further configured to input the charging power into a pre-trained prediction model, and the prediction model calculates the effective discharge power corresponding to the charging power according to the law of conservation of energy.

[0224] Optionally, the device further includes:

[0225] The display unit visually displays the power transmission loss and / or effective discharge power in response to the power consumption viewing operation.

[0226] Optionally, the device further includes:

[0227] The alarm unit triggers an alarm message of battery health or charging pile compatibility in response to the power transmission loss reaching a threshold.

[0228] Optionally, the warning information includes at least one of the following:

[0229] Visual display of power transmission loss;

[0230] The power transmission loss includes charging power loss, discharging power loss and / or AC-DC conversion loss, which is visually displayed.

[0231] The implementation process of the functions and effects of each module in the above-mentioned device is specifically detailed in the implementation process of the corresponding steps in the above-mentioned power consumption calculation method. For relevant matters, please refer to the partial description of the method implementation method, which will not be repeated here.

[0232] The device implementation methods described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the units or modules may be selected according to actual needs to achieve the purpose of the present application. Those of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0233] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email transceiver, game console, tablet computer, wearable device, or any combination of these devices.

[0234] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0235] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0236] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information using any method or technology. 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0237] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0238] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0239] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the", and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0240] It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of the present application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0241] The above description is merely a preferred embodiment of one or more embodiments of the present application and is not intended to limit one or more embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application shall be included in the scope of protection of one or more embodiments of the present application.

Claims

1. A method for calculating power consumption, characterized in that: The method comprises: Obtain the target vehicle's charging capacity and current remaining capacity; According to the law of conservation of energy, calculating the effective discharge power corresponding to the charging power; calibrating the remaining power according to the effective discharge power; The power consumption information of the target vehicle is calculated based on the calibrated remaining power.

2. The method according to claim 1, wherein: The calculating the power consumption information of the target vehicle according to the calibrated remaining power includes: The remaining mileage of the target vehicle is calculated based on the calibrated remaining power and the average power consumption of the target vehicle.

3. The method according to claim 1, characterized in that Calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes: The effective discharge power is obtained by subtracting the power transmission loss of the target vehicle from the charging power of the target vehicle.

4. The method according to claim 1, wherein Calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes: Obtaining the battery health of the target vehicle, and determining the product of the charged power of the target vehicle and the battery health as the effective charged power of the target vehicle; The effective charging power of the target vehicle is subtracted from the power transmission loss of the target vehicle to obtain the effective discharging power.

5. The method according to claim 4, characterized in that The calibrating the remaining power according to the effective discharge power includes: Based on a power calibration formula, the remaining power is calibrated on the basis of the effective discharge power to obtain a calibrated remaining power; wherein the power calibration formula includes: Among them, SOC is the remaining power after calibration, Q f is the effective discharge capacity, SOH is the battery health, I is the discharge current, and t is the discharge time.

6. The method according to claim 2, characterized in that The method further comprises: Determining a usage scenario corresponding to the target vehicle, and obtaining a scenario coefficient of the same vehicle type as the target vehicle in the usage scenario; Performing power consumption calibration on the average power consumption of the target vehicle using the scenario coefficient to obtain calibrated power consumption; The calculating the remaining mileage of the vehicle according to the calibrated remaining power and the average power consumption of the target vehicle includes: The remaining mileage of the vehicle is calculated based on the calibrated remaining power and the calibrated average power consumption.

7. The method according to claim 6, characterized in that The obtaining of the scenario coefficient of the same vehicle model as the target vehicle in the usage scenario includes: Obtain a database of power consumption of vehicles of the same model as the target vehicle and calculate the average power consumption of the same model under the same usage scenario; The ratio of the actual average power consumption of the target vehicle to the average power consumption of the same vehicle type is calculated, and the ratio is used as the scenario coefficient.

8. The method according to claim 1, characterized in that Calculating the effective discharge power corresponding to the charged power according to the law of conservation of energy includes: The charging power is input into a pre-trained prediction model, and the prediction model calculates the effective discharge power corresponding to the charging power according to the law of conservation of energy.

9. The method according to claim 3 or 4, characterized in that The method further comprises: In response to the power consumption viewing operation, the power transmission loss and / or the effective discharge power is visually displayed.

10. The method according to claim 3 or 4, characterized in that The method further comprises: In response to the power transmission loss reaching a threshold, an alarm message of battery health or charging pile compatibility is triggered.

11. The method according to claim 10, characterized in that The warning information includes at least one of the following: Visual display of power transmission loss; The power transmission loss includes charging power loss, discharging power loss and / or AC-DC conversion loss, which is visually displayed.

12. A power consumption calculation device, characterized in that: The device comprises: An acquisition unit obtains the charging power and current remaining power of the target vehicle; The conversion unit calculates the effective discharge power corresponding to the charged power according to the law of conservation of energy; The calibration unit calibrates the remaining power calculation unit according to the effective discharged power, and calculates the power consumption information of the target vehicle according to the calibrated remaining power.

13. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 9 by running the executable instructions.

14. A machine-readable storage medium, characterized in that Machine-readable instructions are stored thereon, and when the instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images