CN115782595B - A method for estimating instantaneous energy consumption of electric buses based on energy recovery status - Google Patents

Abstract

The present invention provides a method for estimating the instantaneous energy consumption of an electric bus based on the energy recovery state. It uses the historical data of the driving state such as the speed of the electric bus, the total voltage of the power battery, the total current of the power battery, etc. to calculate the vehicle acceleration, Instantaneous energy consumption; establish a classification model of energy recovery states of electric buses, using instantaneous speed and acceleration as input variables, and energy recovery state as output variables, to estimate parameters, and then establish energy consumption states and recovery states based on vehicle states. Consumption estimation model and parameter estimation are carried out; according to the instantaneous speed and acceleration of the vehicle, the energy recovery state classification model is first used to judge the vehicle status, and then the corresponding energy consumption estimation model is used according to the status judgment result to obtain the instantaneous energy consumption of the electric bus. The invention has high energy consumption estimation accuracy, can provide real-time data support for users' travel, and facilitates energy management.

Description

A method for estimating instantaneous energy consumption of electric buses based on energy recovery status

Technical Field

The invention belongs to the technical field of new energy vehicles, and specifically relates to a method for estimating instantaneous energy consumption of electric buses based on energy recovery status.

Background technique

As the demand for automobile travel continues to grow, the problems of automobile pollutant emissions and energy consumption have become increasingly prominent. In order to save energy and reduce road traffic emissions, the world has vigorously promoted the development of new energy buses. Due to the large proportion of low-speed driving on urban roads and frequent vehicle stops, it is difficult for ordinary fuel buses to maintain low energy consumption because the engine operating efficiency is low and more air pollutant emissions are produced. In contrast, electric buses are more energy efficient on urban roads due to different power sources. However, due to limitations in the development of battery technology, electric buses have a shorter driving range and longer charging times, which has become one of the main obstacles to reducing overall operating costs. Therefore, accurate energy consumption estimation helps electric buses perform energy management. Based on the estimated energy consumption value, the electric bus energy management system can reasonably optimize the use of electric energy, increase the vehicle's driving range, and plan charging in advance.

Existing bus energy consumption estimation models mainly include macro models and micro models. In terms of driving strategies and control methods, microscopic models are superior to macroscopic models because they are able to estimate instantaneous energy consumption based on second-by-second data, which is suitable for electric bus energy consumption estimation. Microscopic models can be divided into power-based models and data-driven models. The power-based model analyzes the energy transfer in the vehicle power system according to the vehicle dynamics characteristics, and establishes the relationship between instantaneous energy consumption and driving behavior through regression. Data-based models utilize large amounts of experimental data to explore the relationship between energy consumption and driving behavior. Although data-driven methods have great advantages in estimation accuracy, most methods are poorly interpretable and require large amounts of data, some of which are difficult to obtain in real life, especially for buses. The power-based model modeling process is relatively simple, the model coefficient calibration is easier, and the dynamic characteristics of the vehicle are taken into account, so it can be practically applied to electric bus energy estimation. However, there is energy recovery phenomenon when electric buses decelerate, and traditional power-based models do not consider this situation. Therefore, it is necessary to design a recycling state discrimination method for electric buses and combine it with traditional power-based models to improve the accuracy of energy consumption estimation.

Contents of the invention

In order to solve the above technical problems, the present invention proposes a method for estimating instantaneous energy consumption of electric buses based on energy recovery state. Based on the model energy consumption estimation method, an energy recovery state discrimination method is introduced to realize the estimation of electric buses. Accurate estimation of vehicle instantaneous energy consumption, thereby providing effective technical support for remaining mileage prediction, energy management and optimization.

The present invention adopts the following technical solutions:

A method for estimating instantaneous energy consumption of electric buses based on energy recovery status. For the target electric bus, perform the following steps to obtain the real-time instantaneous energy consumption of the target electric bus:

Step A: For the target electric bus, obtain preset driving status data of various types in real time;

Step B: Based on the real-time preset driving status data of various types of the target electric bus, obtain the real-time instantaneous speed and instantaneous acceleration of the target electric bus;

Step C: Based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus, determine the energy recovery status of the target electric bus in real time;

Step D: Based on the real-time determination of the energy recovery status of the target electric bus and combined with the real-time instantaneous speed and instantaneous acceleration of the target electric bus, the real-time instantaneous energy consumption of the target electric bus is obtained.

As a preferred technical solution of the present invention, the target electric bus energy recovery state includes energy consumption state and recovery state.

As a preferred technical solution of the present invention, in step C, the energy recovery state of the target electric bus is determined in real time by the following scheme:

Step C1: based on preset historical driving status data of each type of the target electric bus, the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment are obtained;

Step C2: Based on the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment, construct an energy recovery status classification model that uses instantaneous speed and instantaneous acceleration as inputs and uses the energy recovery status at that moment as output;

Step C3: Based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus, the energy recovery status of the target electric bus is determined in real time through the energy recovery status classification model.

As a preferred technical solution of the present invention, in step C2, an extreme gradient boosting algorithm is used to construct an energy recovery state classification model.

As a preferred technical solution of the present invention, in step D, the real-time instantaneous energy consumption of the target electric bus is obtained by the following scheme:

Step D1: Based on the preset various types of historical driving status data of the target electric bus, obtain the instantaneous speed, instantaneous acceleration, energy recovery status, and instantaneous energy consumption of the target electric bus at each historical moment;

Step D2: Based on the instantaneous speed, instantaneous acceleration, instantaneous energy consumption, and energy recovery status of the target electric bus at each historical moment, construct a model that takes the instantaneous speed, instantaneous acceleration, and energy recovery status as inputs and uses the instantaneous energy consumption at that moment as the output. energy consumption estimation model;

Step D3: Based on the real-time determination of the energy recovery status of the target electric bus, combined with the real-time instantaneous speed and instantaneous acceleration of the target electric bus, and through the energy consumption estimation model, obtain the real-time instantaneous energy consumption of the target electric bus.

As a preferred technical solution of the present invention, in step D2, the following steps are specifically performed to construct an energy consumption estimation model:

Step D2.1: Construct the energy consumption estimation function through the following formula:

E(t)＝β ₀ +β ₁ v(t)+β ₂ v ² (t)+β ₃ v ³ (t)+β ₄ a(t)v(t)

Among them, E(t) represents the instantaneous energy consumption at time t, v(t) represents the instantaneous speed at time t, a(t) represents the instantaneous acceleration at time t, β ₀ , β ₁ , β ₂ , β ₃ , β ₄ Both represent coefficients;

Step D2.2: Based on the energy consumption estimation function, combined with the instantaneous speed, instantaneous acceleration, and instantaneous energy consumption of the target electric bus at each historical moment corresponding to different energy recovery states, obtain the energy consumption estimation function corresponding to different energy recovery states. , that is, the energy consumption estimation model corresponding to different energy recovery states.

A system for estimating instantaneous energy consumption of an electric bus based on energy recovery status is applied to a method for estimating instantaneous energy consumption of an electric bus based on energy recovery status, comprising a data acquisition module, an energy consumption estimation establishment module, and an energy consumption real-time estimation module. The data acquisition module is used to acquire and store preset various types of driving status data of a target electric bus in real time; the energy consumption estimation establishment module establishes an energy recovery status classification model and an energy consumption estimation model based on preset various types of historical driving status data stored in the data acquisition module; the energy consumption real-time estimation module obtains the real-time instantaneous energy consumption of the target electric bus based on the energy recovery status classification model and the energy consumption estimation model, combined with the instantaneous speed and instantaneous acceleration in the real-time preset various types of driving status data.

As a preferred technical solution of the present invention, the energy consumption estimation establishment module includes an energy recovery status classification establishment unit and an energy consumption estimation establishment unit. The energy recovery status classification establishment unit is based on the preset various types of historical driving stored in the data acquisition module. status data to establish an energy recovery status classification model; the energy consumption estimation establishment unit establishes an energy consumption estimation model based on various types of preset historical driving status data stored in the data acquisition module.

As a preferred technical solution of the present invention, the energy consumption estimation model includes energy consumption estimation models corresponding to different energy recovery states.

An instantaneous energy consumption estimation terminal for electric buses based on energy recovery status, including a memory and a processor. The memory and the processor are connected to each other. Computer instructions are stored in the memory. The processor passes The computer instructions are executed to execute the instantaneous energy consumption estimation method of an electric bus based on the energy recovery state.

The beneficial effects of the present invention are: the present invention provides a pure electric bus instantaneous energy consumption estimation method and system that considers energy recovery state classification, and establishes a pure electric bus instantaneous energy consumption estimation model based on actual vehicle driving data to achieve real-time Speed and acceleration are used as input variables to output the instantaneous energy consumption of the vehicle at the current moment. Before establishing the energy consumption estimation model, establish an energy recovery state classification model to distinguish the energy consumption state and recovery state, and then establish energy consumption estimation models for the energy consumption state and recovery state respectively. This method takes into account the different characteristics of energy consumption of electric buses in energy consumption state and recovery state, has high energy consumption estimation accuracy, and is conducive to scientific energy consumption management.

Description of drawings

Figure 1 shows the hardware structure of the electric bus energy consumption estimation system in the embodiment of the present invention;

Figure 2 is an energy consumption estimation algorithm framework that considers energy consumption status discrimination in the embodiment of the present invention;

FIG. 3 is a comparison diagram of energy consumption estimation with and without classification models in an embodiment of the present invention.

Detailed ways

The present invention will be further described below in conjunction with the accompanying drawings. The following examples can enable those skilled in the art to understand the present invention more comprehensively, but do not limit the present invention in any way.

As shown in Figure 1, the hardware structure of the electric bus energy consumption estimation system in the embodiment of the present invention is shown. The electric bus power system in this embodiment is composed of a motor, a motor control system (MCS), a battery, a battery management system (BMS) and a reducer. In order to realize the energy consumption prediction function, a GPS navigation system is installed on the vehicle to obtain speed information, and perform data collection, storage, cleaning and format alignment, etc., to convert the data into data recognized by the energy management system (EMS). In this example, energy consumption estimation is carried out in the energy management system, and the role of the system is to estimate the energy consumption of the electric bus to realize the energy management of the electric bus. The EMS communicates with the BMS and MCS through the CAN bus to coordinate and optimize the energy use of the electric bus.

A method for estimating instantaneous energy consumption of electric buses based on energy recovery status. For the target electric bus, perform the following steps to obtain the real-time instantaneous energy consumption of the target electric bus:

Step A: For the target electric bus, obtain preset driving status data of various types in real time.

The on-board diagnostic system (OBD) is used to obtain real-time preset driving status data of various types of electric buses. The preset driving status data of various types include vehicle speed, total power battery voltage, total power battery current and other data. On this basis, the data can be further processed to calculate the second-by-second acceleration, that is, the instantaneous acceleration.

Step B: Based on the preset real-time data of various types of driving states of the target electric bus, the real-time instantaneous speed and instantaneous acceleration of the target electric bus are obtained.

Step C: Based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus, determine the energy recovery state of the target electric bus in real time; in this embodiment, the energy recovery state of the target electric bus includes an energy consumption state and a recovery state.

In step C, the energy recovery status of the target electric bus is determined in real time through the following solution:

Step C1: Based on the preset various types of historical driving status data of the target electric bus, obtain the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment.

Step C2: Based on the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment, construct an energy recovery status classification model that takes instantaneous speed and instantaneous acceleration as input and uses the energy recovery status at that moment as output. An extreme gradient boosting algorithm is used to construct an energy recovery state classification model.

Step C3: Based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus, the energy recovery status of the target electric bus is determined in real time through the energy recovery status classification model.

Pure electric buses are different from traditional fuel vehicles in that they have an energy recovery state. When the vehicle is in an energy-consuming state, energy flows from the battery to the engine. When the vehicle decelerates, energy recovery may occur and energy flows from the engine to the battery, but this does not necessarily happen. Therefore, it is first necessary to establish a classification model to identify the energy consumption status during deceleration. The extreme gradient boosting algorithm (XGBoost) is used to establish an energy state classification model, using speed and acceleration as input variables and energy consumption state (energy consumption state and recycling state) as output variables. The model is trained to obtain the final classification model.

There are currently many mature classification algorithms, such as support vector machine (SVM), eXtremeGradient Boosting (XGBoost), naive Bayes method, logistic model, decision tree method, etc. After comparative research, the present invention finally uses the XGBoost algorithm to establish a classification model. Since the energy recovery state of electric buses is closely related to speed and acceleration, the present invention uses speed and acceleration as input variables, and the vehicle energy consumption state (energy consumption state and recovery state) as output variables.

The XGBoost algorithm steps of the energy recovery state classification model mainly include the following steps:

Step 1. Initialize the predicted value of each sample.

Step 2. Define the loss function where t represents the regression tree number, y _i is the sample label, f _t ( _xi ) represents the strong learner, C is a constant, and Ω(f _t ) is the regularization term, Among them, T _t is the number of leaf nodes, w _j is the weight of j leaf node, and γ and λ are preset hyperparameters.

Step 3. Calculate the derivative of the loss function for each sample predicted value.

Step 4. Build a new decision tree based on the derivative information.

Step 5. Use the new decision tree to predict the sample value and add it to the original value. The final XGBoost decision tree can be obtained by iterating steps 3-5 n times or when the stop condition is met. Then the energy recovery state classification model is obtained.

In this embodiment, the trained XGBoost model can be used to classify the energy consumption status of electric buses. In this embodiment, the classification accuracy of the test set is 71.74%, of which the classification accuracy for recycling status reaches 88.06%.

Step D: Based on the real-time determined energy recovery state of the target electric bus, combined with the real-time instantaneous speed and instantaneous acceleration of the target electric bus, the real-time instantaneous energy consumption of the target electric bus is obtained.

The electric bus parameter information in this embodiment is shown in Table 1 Vehicle parameter information.

Table 1

parameter numerical value number of seats 32 quality 13450kg size 11990mm×2550mm×3135mm Maximum speed 69km/h Maximum mileage 420km Maximum output power 200kw Maximum torque 2800Nm engine maximum speed 3000r/min battery capacity 233.8kwh

In step D, the real-time instantaneous energy consumption of the target electric bus is obtained through the following scheme:

Step D1: Based on the preset historical driving state data of the target electric bus, the instantaneous speed, instantaneous acceleration, energy recovery state, and instantaneous energy consumption of the target electric bus at each historical moment are obtained. The on-board diagnostic system (OBD) is used to obtain the preset driving state data of the electric bus in real time. The preset driving state data of each type includes vehicle speed, total voltage of the power battery, total current of the power battery, and other data. On this basis, the data can be further processed to calculate the acceleration per second, that is, the instantaneous acceleration, and the total power of the power battery. The power of the power battery per second can be regarded as the energy consumption per second, that is, the instantaneous energy consumption.

Step D2: Based on the instantaneous speed, instantaneous acceleration, instantaneous energy consumption, and energy recovery status of the target electric bus at each historical moment, an energy consumption estimation model is constructed with the instantaneous speed, instantaneous acceleration, and energy recovery status as input and the instantaneous energy consumption at that moment as output.

In step D2, the following steps are specifically performed to build an energy consumption estimation model:

Step D2.1: Construct the energy consumption estimation function through the following formula:

E(t)＝β ₀ +β ₁ v(t)+β ₂ v ² (t)+β ₃ v ³ (t)+β ₄ a(t)v(t)

Wherein, E(t) represents the instantaneous energy consumption at time t, v(t) represents the instantaneous velocity at time t, a(t) represents the instantaneous acceleration at time t, and β ₀ , β ₁ , β ₂ , β ₃ , and β ₄ all represent coefficients.

Step D2.2: Based on the energy consumption estimation function, combined with the instantaneous speed, instantaneous acceleration, and instantaneous energy consumption of the target electric bus at each historical moment corresponding to different energy recovery states, obtain the energy consumption estimation functions corresponding to different energy recovery states, that is, the energy consumption estimation models corresponding to different energy recovery states. Specifically: Based on the energy consumption estimation function, the parameters in the energy consumption estimation function are calibrated by the instantaneous speed, instantaneous acceleration, and instantaneous energy consumption of the target electric bus at each historical moment corresponding to the energy consumption state and the recovery state, and then the energy consumption estimation models corresponding to the energy recovery states of the two target electric buses, the energy consumption state and the recovery state, are obtained. The two energy consumption estimation models are based on different coefficients of the energy consumption estimation function.

For the two energy recovery states, based on the energy consumption estimation function, an energy consumption estimation model for the energy consumption state and the recovery state is established respectively. That is, based on the energy consumption estimation function as a model, parameter estimation is then performed based on historical data to obtain the energy consumption state. Energy consumption estimation models corresponding to the recycling status. The power-based Comprehensive Electric Vehicle Energy Consumption Model (CPEM) is used to consider the vehicle dynamics characteristics and conduct vehicle energy consumption by inputting driving parameters such as speed and acceleration, as well as vehicle and external environment parameters such as vehicle size, air density, and drag coefficient. predict.

Specifically: Step a: Calculate wheel power. Considering the vehicle dynamics, the wheel power is estimated by inputting driving parameters such as speed and acceleration and vehicle and external environment parameters such as vehicle size, air density, and drag coefficient:

Among them, m is the mass of the vehicle (kg), a(t) is the acceleration of the vehicle at time t (m/s ² ), v(t) is the speed of the vehicle at time t (m/s), and g is the local gravity Acceleration, θ is the road gradient, C _r , c ₁ , c ₂ are the rolling resistance coefficients, ρ _Air is the air density (kg/m ³ ), A _f is the front area of the vehicle, C _D is the aerodynamic resistance of the vehicle coefficient.

Step b: Calculate battery power. Taking into account motor efficiency, driveline efficiency, and other energy losses, the following relationship exists between battery power P _Battery and wheel power P _Wheels :

P _Wheels (t) = P _Battery (t)·η

Among them, eta is the reduction coefficient for converting battery power into wheel power. Therefore, the battery power can be calculated from the wheel power, and then the battery energy consumption can be obtained:

Step c: Then, the battery energy consumption can be converted into a function of speed and acceleration:

E(t)＝β ₀ +β ₁ v(t)+β ₂ v ² (t)+β ₃ v ³ (t)+β ₄ a(t)v(t)

Furthermore, after the model is deduced, the final battery energy consumption can be converted into a multiple regression function about speed and acceleration, as shown in the formula in step D2.1, as the target electric bus corresponding to different energy consumption states at each historical moment. The parameters of the model are calibrated using the instantaneous speed, instantaneous acceleration, and instantaneous energy consumption, and the model coefficients are obtained through multiple linear regression, where β ₀ , β ₁ , β ₂ , β ₃ , and β ₄ all represent coefficients. That is, the energy consumption estimation function is converted into a multiple linear regression model as the current energy consumption calculation model. Therefore, only historical vehicle data can be used to calibrate the parameters of the model, that is, for the two target electric bus energy recovery states: energy consumption state and recovery state. , based on the energy consumption estimation function, the parameters of the model are calibrated based on the instantaneous speed, instantaneous acceleration, and instantaneous energy consumption of the target electric bus corresponding to different energy consumption states at each historical moment, and the energy consumption estimates under different energy consumption states are obtained. Each coefficient β ₀ , β ₁ , β ₂ , β ₃ , β ₄ in the function is used to obtain energy consumption estimation models corresponding to the two energy recovery states. The two energy consumption estimation models are based on different coefficients of the energy consumption estimation function. In this embodiment, the model fitting parameters and the fitting goodness R ² are as shown in Table 2 Calibration parameters of the energy consumption calculation submodel. The goodness of fit in the energy consumption state and recovery state are 0.8043 and 0.8097 respectively, which shows that the model has a good fitting effect.

Table 2

coefficient(variable) Energy consumption status Recycling status β ₀ (intercept) 1.84× ^10-5 1.47× ^10-3 β ₁ (v(t)) 6.29× ^10-4 -1.39×10 ^-3 β ₂ (v ² (t)) -2.00×10 ^-6 1.93×10 ^-4 β ₃ (v ³ (t)) -1.74×10 ^-6 -5.24×10 ^-6 β ₄ (a(t)v(t)) 7.58× ^10-4 9.37× ^10-4 R ² 0.8043 0.8097

Step D3: Based on the real-time determination of the energy recovery status of the target electric bus, combined with the real-time instantaneous speed and instantaneous acceleration of the target electric bus, and through the energy consumption estimation model, obtain the real-time instantaneous energy consumption of the target electric bus. Specifically, the instantaneous speed and acceleration of the vehicle are obtained from the GPS navigation system. First, the energy recovery state classification model is used to determine whether the vehicle is recovering energy, and then the corresponding energy consumption estimation model is used to estimate instantaneous energy consumption based on the state judgment results.

Furthermore, Figure 2 shows the energy consumption estimation algorithm framework considering energy consumption status discrimination in the embodiment of the present invention, which mainly includes three levels: information acquisition layer, parameter estimation layer and core calculation layer.

In the information acquisition layer, OBD is used to obtain the historical information of the electric bus's driving status, which mainly includes speed, total power battery voltage and total power battery current.

In the parameter estimation layer, the vehicle acceleration and instantaneous energy consumption are calculated using the obtained vehicle speed, total power battery voltage, total power battery current and other data. Establish an energy recovery state classification model for electric buses. Second-by-second (instantaneous) speed and acceleration are used as input variables, and the energy recovery state is used as an output variable. Parameter estimation is performed, and then energy consumption estimation models for energy consumption state and recovery state are established respectively. Perform parameter estimation.

At the core computing layer, the vehicle's instantaneous speed and acceleration are obtained based on the GPS navigation system. First, the energy recovery state classification model is used to determine whether the vehicle is recovering energy, and then the corresponding energy consumption estimation model is used to estimate instantaneous energy consumption based on the state judgment results.

An instantaneous energy consumption estimation system for electric buses based on energy recovery status, applied to the instantaneous energy consumption estimation method for electric buses based on energy recovery status, including a data acquisition module, an energy consumption estimation establishment module, and a real-time energy consumption Estimation module, the data acquisition module is used to obtain and store the real-time preset various types of driving status data of the target electric bus. Specifically, it uses the on-board diagnostic system (OBD) to collect the monitoring data of the electric bus and obtain the vehicle under test. Historical operating data mainly includes speed, total power battery current and total power battery voltage; the energy consumption estimation establishment module establishes an energy recovery status classification model and an energy consumption estimation model based on the preset various types of historical driving status data stored in the data acquisition module. ;The real-time energy consumption estimation module is based on the energy recovery state classification model and energy consumption estimation model, combined with the real-time preset instantaneous speed and instantaneous acceleration in various types of driving status data, that is, using GPS to obtain real-time speed and acceleration, and obtain the real-time target electric bus instantaneous energy consumption.

The energy consumption estimation establishment module includes an energy recovery status classification establishment unit and an energy consumption estimation establishment unit. The energy recovery status classification establishment unit establishes an energy recovery status classification model based on preset various types of historical driving status data stored in the data acquisition module; The energy consumption estimation establishment unit establishes an energy consumption estimation model based on preset various types of historical driving status data stored in the data acquisition module.

The energy consumption estimation model includes energy consumption estimation models corresponding to different energy recovery states, that is, the energy consumption state and the recovery state correspond to an energy consumption estimation model of the energy consumption state and an energy consumption estimation model of the recovery state, respectively.

A terminal for estimating instantaneous energy consumption of an electric bus based on energy recovery status comprises a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method for estimating instantaneous energy consumption of an electric bus based on energy recovery status.

This embodiment integrates the energy recovery state classification model and the energy consumption estimation model to obtain the electric bus energy consumption estimation module. First, the collected speed and acceleration data are used to classify the energy consumption status to determine whether the vehicle is in an energy consumption state or a recovery state. Then, the energy consumption calculation sub-model of the corresponding state is used to estimate the battery power consumption or recovery amount within the current 1 second, that is, the instantaneous energy consumption.

In order to illustrate the superiority of the energy consumption estimation model after adding the state classification model, the present invention also establishes an unclassified energy consumption estimation model for comparison. The data in the embodiment are used for training, and then the test set is used for energy consumption estimation. The energy consumption estimation results of classified and unclassified electric buses are obtained, as shown in Figure 3. As can be seen from Figure 3, both the classified and unclassified models have better estimation results for the energy consumption state, that is, the energy outflow state. However, for the energy recovery state, the classified energy consumption estimation model is significantly better than the unclassified energy consumption estimation model. Consumption estimation model.

The energy consumption estimation errors of the two models are shown in Table 3. The energy consumption estimation errors of the classified and unclassified models. This embodiment uses three error types: MSE, RMSE and MAE to illustrate the estimation error of the model. Comparing the errors of the two models, it can be found that the three errors of the energy consumption estimation model with energy state division are significantly lower than the energy consumption estimation model without state division. This illustrates the electric power consumption estimation model considering energy recovery state discrimination proposed by the present invention. The bus instantaneous energy consumption estimation method has good energy consumption estimation effect and great advantages, and can accurately estimate the energy consumption of electric buses.

table 3

Error type There is a classification model No classification model MSE 2.94× ^10-6 5.61×10 ^-6 RMSE 0.00171 0.00237 MAE 0.00112 0.00135

The present invention designs a pure electric bus instantaneous energy consumption estimation method and system that considers energy recovery status classification. It establishes a pure electric bus instantaneous energy consumption estimation model based on actual vehicle driving data, using real-time speed and acceleration as input variables. Output the instantaneous energy consumption of the vehicle at the current moment. Before establishing the energy consumption estimation model, establish an energy recovery state classification model to distinguish the energy consumption state and recovery state, and then establish energy consumption estimation models for the energy consumption state and recovery state respectively. This method takes into account the different characteristics of energy consumption of electric buses in energy consumption state and recovery state, has high energy consumption estimation accuracy, and is conducive to scientific energy consumption management.

The above are only preferred embodiments of the present invention, but do not limit the patent scope of the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still make various modifications to the foregoing aspects. Modify the technical solutions described in the specific embodiments, or make equivalent replacements for some of the technical features. Any equivalent structures made using the contents of the description and drawings of the present invention and used directly or indirectly in other related technical fields shall likewise fall within the scope of patent protection of the present invention.

Claims (8)

1. A method for estimating instantaneous energy consumption of electric buses based on energy recovery state, which is characterized in that: for the target electric bus, perform the following steps to obtain the real-time instantaneous energy consumption of the target electric bus: Step A: For the target electric bus, obtain preset driving status data of various types in real time; Step B: Based on the real-time preset various types of driving status data of the target electric bus, obtain the real-time instantaneous speed and instantaneous acceleration of the target electric bus; Step C: Based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus, the energy recovery status of the target electric bus is determined in real time; in step C, the energy recovery status of the target electric bus is determined in real time through the following solution: Step C1: Based on the preset historical driving status data of various types of the target electric bus, obtain the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment; Step C2: Based on the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment, construct an energy recovery status classification model that uses instantaneous speed and instantaneous acceleration as inputs and uses the energy recovery status at that moment as output; Step C3: Based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus, determine the energy recovery status of the target electric bus in real time through the energy recovery status classification model; Step D: Based on the real-time determined energy recovery state of the target electric bus, combined with the real-time instantaneous speed and instantaneous acceleration of the target electric bus, the real-time instantaneous energy consumption of the target electric bus is obtained. 2. According to claim 1, a method for estimating instantaneous energy consumption of an electric bus based on energy recovery status is characterized in that the energy recovery status of the target electric bus includes energy consumption status and recovery status. 3. According to the method for estimating instantaneous energy consumption of an electric bus based on energy recovery status in claim 1, it is characterized in that: in the step C2, an extreme gradient boosting algorithm is used to construct an energy recovery status classification model. 4. A method for estimating instantaneous energy consumption of electric buses based on energy recovery status according to claim 1, characterized in that: in step D, the real-time instantaneous energy consumption of the target electric bus is obtained through the following scheme: Step D1: Based on the preset various types of historical driving status data of the target electric bus, obtain the instantaneous speed, instantaneous acceleration, energy recovery status, and instantaneous energy consumption of the target electric bus at each historical moment; Step D2: Based on the instantaneous speed, instantaneous acceleration, instantaneous energy consumption, and energy recovery status of the target electric bus at each historical moment, construct a model that takes the instantaneous speed, instantaneous acceleration, and energy recovery status as inputs and uses the instantaneous energy consumption at that moment as the output. energy consumption estimation model; Step D3: Based on the real-time determination of the energy recovery status of the target electric bus, combined with the real-time instantaneous speed and instantaneous acceleration of the target electric bus, and through the energy consumption estimation model, obtain the real-time instantaneous energy consumption of the target electric bus. 5. The method for estimating instantaneous energy consumption of an electric bus based on energy recovery state according to claim 4 is characterized in that: in the step D2, the following steps are specifically performed to construct an energy consumption estimation model: Step D2.1: Construct the energy consumption estimation function through the following formula: E(t)＝β ₀ +β ₁ v(t)+β ₂ v ² (t)+β ₃ v ³ (t)+β ₄ a(t)v(t) Among them, E(t) represents the instantaneous energy consumption at time t, v(t) represents the instantaneous speed at time t, a(t) represents the instantaneous acceleration at time t, β ₀ , β ₁ , β ₂ , β ₃ , β ₄ Both represent coefficients; Step D2.2: Based on the energy consumption estimation function, combined with the instantaneous speed, instantaneous acceleration, and instantaneous energy consumption of the target electric bus at each historical moment corresponding to different energy recovery states, obtain the energy consumption estimation function corresponding to different energy recovery states. , that is, the energy consumption estimation model corresponding to different energy recovery states. 6. A system for estimating instantaneous energy consumption of electric buses based on energy recovery state, applied to the method of estimating instantaneous energy consumption of electric buses based on energy recovery state according to any one of claims 1-5, characterized by: Including data acquisition module, energy consumption estimation establishment module, energy consumption real-time estimation module, The data acquisition module is used to acquire real-time preset various types of driving status data of the target electric bus and store it; The energy consumption estimation establishment module establishes an energy recovery state classification model and an energy consumption estimation model based on preset historical driving state data of various types stored in the data acquisition module; the energy consumption estimation establishment module includes an energy recovery state classification establishment unit and an energy consumption estimation establishment unit; The real-time energy consumption estimation module is based on the energy recovery state classification model and energy consumption estimation model, combined with the instantaneous speed and instantaneous acceleration in the real-time preset various types of driving status data, to obtain the real-time instantaneous energy consumption of the target electric bus; Among them, the energy recovery status classification establishment unit establishes an energy recovery status classification model based on the preset various types of historical driving status data stored in the data acquisition module; the energy recovery status classification establishment unit is configured to perform the following actions: based on the preset prediction of the target electric bus Assume various types of historical driving status data to obtain the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment; then based on the instantaneous speed, instantaneous acceleration, and energy recovery status of the target electric bus at each historical moment, construct An energy recovery state classification model that takes instantaneous speed and instantaneous acceleration as input and uses the energy recovery state at that moment as output; The energy consumption estimation establishment unit establishes an energy consumption estimation model based on various types of preset historical driving status data stored in the data acquisition module; the energy consumption estimation establishment unit is configured to perform the following actions: based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus , through the energy recovery state classification model, the energy recovery state of the target electric bus is determined in real time. 7. An instantaneous energy consumption estimation system for electric buses based on energy recovery states according to claim 6, characterized in that: the energy consumption estimation model includes energy consumption estimation models corresponding to different energy recovery states. 8. An instantaneous energy consumption estimation terminal for electric buses based on energy recovery status, characterized by: including a memory and a processor, the memory and the processor are connected to each other, and computer instructions are stored in the memory , the processor executes the computer instructions to execute the instantaneous energy consumption estimation method of an electric bus based on the energy recovery state described in any one of claims 1-5.