CN115782595A - Electric bus instantaneous energy consumption estimation method based on energy recovery state - Google Patents
Electric bus instantaneous energy consumption estimation method based on energy recovery state Download PDFInfo
- Publication number
- CN115782595A CN115782595A CN202211558442.9A CN202211558442A CN115782595A CN 115782595 A CN115782595 A CN 115782595A CN 202211558442 A CN202211558442 A CN 202211558442A CN 115782595 A CN115782595 A CN 115782595A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- instantaneous
- electric bus
- energy
- recovery state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 243
- 238000011084 recovery Methods 0.000 title claims abstract description 149
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000001133 acceleration Effects 0.000 claims abstract description 68
- 238000013145 classification model Methods 0.000 claims abstract description 35
- 230000006870 function Effects 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000000809 air pollutant Substances 0.000 description 1
- 231100001243 air pollutant Toxicity 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Abstract
The invention provides an instantaneous energy consumption estimation method of an electric bus based on an energy recovery state, which comprises the steps of obtaining historical data of running states of the electric bus, such as speed, total voltage of a power battery, total current of the power battery and the like, and calculating acceleration and instantaneous energy consumption of the electric bus according to the data; establishing an energy recovery state classification model of the electric bus, taking the instantaneous speed and the acceleration as input variables, taking the energy recovery state as an output variable, performing parameter estimation, and then respectively establishing energy consumption estimation models of an energy consumption state and a recovery state and performing parameter estimation aiming at the state of the bus; according to the instantaneous speed and the acceleration of the vehicle, firstly, the energy recovery state classification model is used for judging the state of the vehicle, and then, according to the state judgment result, the corresponding energy consumption estimation model is used for obtaining the instantaneous energy consumption of the electric bus. The energy consumption estimation method has high energy consumption estimation accuracy, can provide real-time data support for the trip of the user, and is convenient for energy management.
Description
Technical Field
The invention belongs to the technical field of new energy vehicles, and particularly relates to an instantaneous energy consumption estimation method for an electric bus based on an energy recovery state.
Background
With the increasing demand of automobile traveling, the problems of automobile pollutant emission and energy consumption are increasingly highlighted. In order to save energy and reduce road traffic emission, the development of new energy buses is greatly promoted all over the world. Because the proportion of low-speed running in urban roads is large, and vehicles frequently stop running, the ordinary fuel buses are difficult to keep low energy consumption, and because the running efficiency of an engine is low, more air pollutants can be discharged. In contrast, electric buses are more energy efficient on urban roads due to different power sources. However, since the electric bus is limited by the development of battery technology, the driving range is short and the charging time is long, which becomes one of the major obstacles for reducing the overall operating cost. Therefore, the accurate energy consumption estimation is beneficial to the electric bus to carry out energy management, and according to the estimated energy consumption value, the electric bus energy management system can reasonably optimize the use of electric energy, improve the driving mileage of the vehicle and carry out charging planning in advance.
The existing bus energy consumption estimation model mainly comprises a macroscopic model and a microscopic model. In terms of driving strategy and control method, the micro model is superior to the macro model because it can estimate instantaneous energy consumption from second-by-second data, which is suitable for electric bus energy consumption estimation. The microscopic models can be divided into power-based models and data-driven models. The power-based model analyzes energy transfer in the vehicle powertrain system based on vehicle dynamics and establishes a relationship between instantaneous energy consumption and driving behavior through regression. Data-based models exploit a large amount of experimental data to explore the relationship between energy consumption and driving behavior. Although data-driven methods have great advantages in terms of estimation accuracy, most of them 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 considered, so that the method can be practically applied to the energy estimation of the electric bus. However, the electric bus has an energy recovery phenomenon during deceleration, and the traditional power-based model does not consider the situation. Therefore, it is necessary to design a method for determining the recycling status of an electric bus, which is combined with a conventional power-based model to improve the accuracy of energy consumption estimation.
Disclosure of Invention
In order to solve the technical problems, the invention provides an energy recovery state-based instantaneous energy consumption estimation method for an electric bus, and introduces an energy recovery state discrimination method on the basis of a model energy consumption estimation method to realize accurate estimation of instantaneous energy consumption of the electric bus, thereby providing effective technical support for prediction, energy management and optimization of remaining driving mileage.
The invention adopts the following technical scheme:
the method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state comprises the following steps of aiming at a target electric bus to obtain the real-time instantaneous energy consumption of the target electric bus:
step A: acquiring preset driving state data of various types in real time aiming at a target electric bus;
and B: acquiring real-time instantaneous speed and instantaneous acceleration of the target electric bus based on real-time preset various types of running state data of the target electric bus;
and C: judging the energy recovery state of the target electric bus in real time based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus;
step D: and obtaining the real-time instantaneous energy consumption of the target electric bus based on the real-time judged energy recovery state of the target electric bus and by combining the real-time instantaneous speed and the instantaneous acceleration of the target electric bus.
As a preferred technical solution of the present invention, the energy recovery state of the target electric bus includes an energy consumption state and a recovery state.
As a preferred technical solution of the present invention, in the step C, the energy recovery state of the target electric bus is determined in real time by the following scheme:
step C1: acquiring instantaneous speed, instantaneous acceleration and energy recovery states of the target electric bus at all historical moments based on preset various types of historical driving state data of the target electric bus;
and step C2: constructing an energy recovery state classification model which takes the instantaneous speed and the instantaneous acceleration as input and the energy recovery state at the moment as output based on the instantaneous speed, the instantaneous acceleration and the energy recovery state of the target electric bus at each historical moment;
and C3: and judging the energy recovery state of the target electric bus in real time through an energy recovery state classification model based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus.
As a preferred technical solution of the present invention, in the step C2, an energy recovery state classification model is constructed by using a gradient-enhanced algorithm.
As a preferred technical solution of the present invention, in the step D, the real-time instantaneous energy consumption of the target electric bus is obtained through the following scheme:
step D1: acquiring instantaneous speed, instantaneous acceleration, energy recovery state and instantaneous energy consumption of the target electric bus at each historical moment based on preset various types of historical driving state data of the target electric bus;
step D2: constructing an energy consumption estimation model which takes the instantaneous speed, the instantaneous acceleration and the energy recovery state as input and takes the instantaneous energy consumption at the moment as output on the basis of the instantaneous speed, the instantaneous acceleration, the instantaneous energy consumption and the energy recovery state of the target electric bus at each historical moment;
and D3: and obtaining the real-time instantaneous energy consumption of the target electric bus through an energy consumption estimation model based on the real-time distinguished energy recovery state of the target electric bus and by combining the real-time instantaneous speed and the instantaneous acceleration of the target electric bus.
As a preferred technical solution of the present invention, in the step D2, the following steps are specifically executed to construct the energy consumption estimation model:
step D2.1: constructing an energy consumption estimation function by 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 the moment t, v (t) represents the instantaneous speed at the moment t, a (t) represents the instantaneous acceleration at the moment t, and beta 0 、β 1 、β 2 、β 3 、β 4 Uniform meterShowing coefficients;
step D2.2: based on the energy consumption estimation function, combining the instantaneous speed, the instantaneous acceleration and the instantaneous energy consumption of the target electric bus at each historical moment corresponding to different energy recovery states respectively to obtain energy consumption estimation functions corresponding to the different energy recovery states respectively, namely energy consumption estimation models corresponding to the different energy recovery states respectively.
An instantaneous energy consumption estimation system of an electric bus based on an energy recovery state is applied to the instantaneous energy consumption estimation method of the electric bus based on the energy recovery state, and comprises a data acquisition module, an energy consumption estimation establishing module and an energy consumption real-time estimation module, wherein the data acquisition module is used for acquiring and storing real-time preset various types of running state data of a target electric bus; the energy consumption estimation building module builds an energy recovery state classification model and an energy consumption estimation model based on preset various types of historical driving state data stored in the data acquisition module; the energy consumption real-time estimation module is used for acquiring real-time instantaneous energy consumption of the target electric bus by combining preset instantaneous speed and instantaneous acceleration in each type of driving state data on the basis of the energy recovery state classification model and the energy consumption estimation model.
As a preferred technical solution of the present invention, the energy consumption estimation and establishment module includes an energy recovery state classification and establishment unit and an energy consumption estimation and establishment unit, wherein the energy recovery state classification and establishment unit establishes an energy recovery state classification model based on preset various types of historical driving state data stored in the data acquisition module; the energy consumption estimation establishing unit establishes an energy consumption estimation model based on preset historical driving state data of various types 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 respectively corresponding to different energy recovery states.
An instantaneous energy consumption estimation terminal of an electric bus based on an energy recovery state comprises a memory and a processor, wherein the memory and the processor are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the instantaneous energy consumption estimation method of the electric bus based on the energy recovery state.
The invention has the beneficial effects that: the invention provides a pure electric bus instantaneous energy consumption estimation method and system considering energy recovery state classification. Before the energy consumption estimation model is established, an energy recovery state classification model is established, the energy consumption state and the recovery state are distinguished, and then the energy consumption estimation models of the energy consumption state and the recovery state are respectively established. The method considers different characteristics of energy consumption of the electric bus in the energy consumption state and the recovery state, has higher energy consumption estimation precision, and is favorable for scientific energy consumption management.
Drawings
FIG. 1 is a hardware structure of an energy consumption estimation system for an electric bus according to an embodiment of the present invention;
FIG. 2 is a framework of an energy consumption estimation algorithm considering energy consumption state discrimination in an embodiment of the present invention;
FIG. 3 is a comparison graph of energy consumption estimates for models with and without classification in an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are presented to enable one of ordinary skill in the art to more fully understand the present invention and are not intended to limit the invention in any way.
Fig. 1 shows a hardware structure of an electric bus energy consumption estimation system according to an embodiment of the present invention, wherein a power system of the electric bus in the embodiment includes a motor, a Motor Control System (MCS), a Battery Management System (BMS), and a speed reducer. In order to realize the energy consumption prediction function, a GPS navigation system is arranged on the vehicle to acquire speed information, perform data acquisition, storage, cleaning, format alignment and the like on the speed information, and convert the data into data identified by an Energy Management System (EMS). In this example, the energy consumption estimation is performed in an energy management system, which is used 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 the MCS through the CAN bus to coordinate and optimize the energy usage of the electric bus.
The method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state comprises the following steps of executing the following steps aiming at a target electric bus to obtain the real-time instantaneous energy consumption of the target electric bus:
step A: and aiming at the target electric bus, preset driving state data of each type are acquired in real time.
The method comprises the steps that an on-board diagnostic system (OBD) is utilized to obtain the electric bus to obtain preset various types of running state data in real time, and the preset various types of running state data comprise data such as vehicle speed, total voltage of a power battery, total current of the power battery and the like. On the basis, the data can be further processed, and the second-by-second acceleration, namely the instantaneous acceleration, can be calculated.
And B: and acquiring real-time instantaneous speed and instantaneous acceleration of the target electric bus based on the real-time preset driving state data of each type of the target electric bus.
And C: judging the energy recovery state of the target electric bus in real time based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus; in this embodiment, the energy recovery state of the target electric bus includes an energy consumption state and a recovery state.
In the step C, the energy recovery state of the target electric bus is judged in real time through the following scheme:
step C1: and acquiring the instantaneous speed, the instantaneous acceleration and the energy recovery state of the target electric bus at each historical moment based on the preset various types of historical driving state data of the target electric bus.
And step C2: based on the instantaneous speed, the instantaneous acceleration and the energy recovery state of the target electric bus at each historical moment, an energy recovery state classification model which takes the instantaneous speed and the instantaneous acceleration as input and the energy recovery state at the moment as output is constructed. And constructing an energy recovery state classification model by adopting an extreme gradient lifting algorithm.
And C3: and judging the energy recovery state of the target electric bus in real time through an energy recovery state classification model based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus.
Pure electric bus is different from traditional fuel vehicle, has the energy recuperation state. When the vehicle is in a power-consuming state, energy flows from the battery to the engine, and when the vehicle is decelerating, there is a possibility that energy is recovered and energy flows from the engine to the battery, but this does not necessarily occur. Therefore, a classification model needs to be established to identify the energy consumption state during deceleration. An energy state classification model is established by utilizing an extreme gradient boost algorithm (XGboost), the speed and the acceleration are used as input variables, the energy consumption states (the energy consumption state and the recovery state) are used as output variables, and the model is trained to obtain a final classification model.
There are many mature classification algorithms, such as Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), naive bayes method, logistic model, decision tree method, etc. Through comparative research, the XGboost algorithm is finally adopted to establish the classification model. Because the energy recovery state of the electric bus is closely related to the speed and the acceleration, the speed and the acceleration are used as input variables, and the energy consumption state (the energy consumption state and the recovery state) of the vehicle is used as an output variable.
The XGboost algorithm of the energy recovery state classification model mainly comprises the following steps:
step 1, initializing a predicted value of each sample.
Step 2, defining a loss function
Wherein t represents a regression tree number, y i Is a sample label, f t (x i ) Representing a strong learner, C being a constant, Ω (f) t ) Is a term of regularization that is,
wherein T is t Number of leaf nodes, w j For j leaf node weights, γ and λ are pre-set hyper-parameters.
And 3, calculating the derivative of the loss function for each sample predicted value.
And 4, establishing a new decision tree according to the derivative information.
And 5, predicting the sample value by using the new decision tree and accumulating the sample value to the original value. And (5) obtaining the final XGboost decision tree through iteration steps 3-5 for n times or meeting a stopping condition. And further obtaining an energy recovery state classification model.
In this embodiment, the trained XGBoost model is used to classify the energy consumption states of the electric bus, and the classification accuracy of the test set in this embodiment is 71.74%, where the classification accuracy of the recovery state reaches 88.06%.
Step D: and obtaining the real-time instantaneous energy consumption of the target electric bus based on the real-time judged energy recovery state of the target electric bus and by combining the real-time instantaneous speed and the instantaneous acceleration of the target electric bus.
The electric bus parameter information in this embodiment is shown in table 1.
TABLE 1
| Parameter(s) | Numerical value |
| Number of seats | 32 |
| Quality of | 13450kg |
| Size of | 11990mm×2550mm×3135mm |
| Maximum speed | 69km/h |
| Maximum mileage | 420km |
| Maximum output power | 200kw |
| Maximum torque | 2800Nm |
| Maximum engine speed | 3000r/min |
| Capacity of battery | 233.8kwh |
In the step D, the real-time instantaneous energy consumption of the target electric bus is obtained through the following scheme:
step D1: and acquiring the instantaneous speed, the instantaneous acceleration, the energy recovery state and the instantaneous energy consumption of the target electric bus at each historical moment based on the preset historical driving state data of each type of the target electric bus. The method comprises the steps that an on-board diagnostic system (OBD) is utilized to obtain the electric bus to obtain preset various types of running state data in real time, and the preset various types of running state data comprise data such as vehicle speed, total voltage of a power battery, total current of the power battery and the like. On the basis, the data can be further processed, the second-by-second acceleration, namely the instantaneous acceleration, the total power of the power battery is obtained through calculation, and the second-by-second power of the power battery can be regarded as the second-by-second energy consumption, namely the instantaneous energy consumption.
Step D2: based on the instantaneous speed, the instantaneous acceleration, the instantaneous energy consumption and the energy recovery state of the target electric bus at each historical moment, an energy consumption estimation model which takes the instantaneous speed, the instantaneous acceleration and the energy recovery state as input and takes the instantaneous energy consumption at the moment as output is constructed.
In the step D2, the following steps are specifically executed to construct an energy consumption estimation model:
step D2.1: constructing an energy consumption estimation function by 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 the moment t, v (t) represents the instantaneous speed at the moment t, a (t) represents the instantaneous acceleration at the moment t, and beta 0 、β 1 、β 2 、β 3 、β 4 Both represent coefficients.
Step D2.2: based on the energy consumption estimation function, combining the instantaneous speed, the instantaneous acceleration and the instantaneous energy consumption of the target electric bus at each historical moment corresponding to different energy recovery states respectively to obtain energy consumption estimation functions corresponding to the different energy recovery states respectively, namely energy consumption estimation models corresponding to the different energy recovery states respectively. The method specifically comprises the following steps: based on the energy consumption estimation function, parameters in the energy consumption estimation function are calibrated through the instantaneous speed, the instantaneous acceleration and the instantaneous energy consumption of the target electric bus at each historical moment respectively corresponding to the energy consumption state and the recovery state, so that energy consumption estimation models respectively corresponding to the energy recovery state of the target electric bus in the energy consumption state and the recovery state are obtained, and the two energy consumption estimation models are different based on the coefficients of the energy consumption estimation functions.
Aiming at two energy consumption recovery states, energy consumption estimation models of the energy consumption state and the recovery state are respectively established based on an energy consumption estimation function, namely, the energy consumption estimation function is used as a model, and then parameter estimation is carried out based on historical data, so that energy consumption estimation models corresponding to the energy consumption state and the recovery state respectively are obtained. The method comprises the steps of utilizing a power-based comprehensive electric automobile energy consumption model (CPEM), considering vehicle dynamics characteristics, and predicting the energy consumption of a vehicle by inputting driving parameters such as speed and acceleration and vehicle and external environment parameters such as vehicle size, air density and resistance coefficient.
The method specifically comprises the following steps: step a: wheel power is calculated. The power of the wheels is estimated by inputting driving parameters such as speed and acceleration, and vehicle and external environment parameters such as vehicle size, air density and resistance coefficient, taking into account the vehicle dynamics:
wherein m is the vehicle mass (kg), a (t) is the acceleration (m/s) of the vehicle at time t 2 ) V (t) is the speed of the vehicle at time t (m/s), g is the local gravitational acceleration, θ is the road gradient, C r ,c 1 ,c 2 Is the coefficient of rolling resistance, ρ Air Is the air density (kg/m) 3 )，A f Is the front area of the vehicle, C D Is the aerodynamic drag coefficient of the vehicle.
Step b: the battery power is calculated. Taking into account motor efficiency, driveline efficiency and other energy losses, battery power P Battery And the wheel power P Wheels There are the following relationships between:
P Wheels (t)＝P Battery (t)·η
wherein η is a reduction coefficient of the battery power converted into the wheel power. Therefore, the battery power can be calculated through the wheel power, and the energy consumption of the battery is obtained:
step c: further, battery power consumption can be translated into functions related to 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 derived, the final battery energy consumption can be converted into a multiple regression function related to the speed and the acceleration, as shown in step D2.1, and used as a corresponding target under different energy consumption states according to various historical momentsThe instantaneous speed, the instantaneous acceleration and the instantaneous energy consumption of the electric bus carry out parameter calibration on the model, and a model coefficient is obtained through multiple linear regression, wherein beta is 0 ，β 1 ，β 2 ，β 3 ，β 4 Both represent coefficients. The energy consumption estimation function is used as a current energy consumption calculation model and is converted into a multiple linear regression model, so that the model can be subjected to parameter calibration only by utilizing historical vehicle data, namely the model is subjected to parameter calibration according to two target electric bus energy recovery states of an energy consumption state and a recovery state, and on the basis of the energy consumption estimation function and in combination with the instantaneous speed, the instantaneous acceleration and the instantaneous energy consumption of the corresponding target electric bus in different energy consumption states at different historical moments, each coefficient beta in the energy consumption estimation function in the different energy consumption states is obtained respectively 0 ，β 1 ，β 2 ，β 3 ，β 4 And further acquiring energy consumption estimation models corresponding to the two energy recovery states respectively, wherein the two energy consumption estimation models are different based on the coefficient of the energy consumption estimation function. In this embodiment, the model fitting parameters and goodness of fit R 2 As shown in table 2 for calibration parameters of the energy consumption calculation submodel. The goodness of fit in the energy consumption state and the recovery state is 0.8043 and 0.8097 respectively, so that the good fitting effect of the model can be found.
TABLE 2
| Coefficient (variable) | State of energy consumption | Recovery state |
| 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 |
And D3: and obtaining the real-time instantaneous energy consumption of the target electric bus through an energy consumption estimation model based on the real-time distinguished energy recovery state of the target electric bus and by combining the real-time instantaneous speed and the instantaneous acceleration of the target electric bus. Specifically, the instantaneous speed and the acceleration of the vehicle are obtained according to the GPS navigation system, firstly, an energy recovery state classification model is used for judging whether the vehicle is subjected to energy recovery, and then, a corresponding energy consumption estimation model is used for carrying out instantaneous energy consumption estimation according to a state judgment result.
Further, as shown in fig. 2, an energy consumption estimation algorithm framework considering energy consumption state discrimination in the embodiment of the present invention mainly includes three layers: the system comprises an information acquisition layer, a parameter estimation layer and a core calculation layer.
On the information acquisition layer, historical information of the running state of the electric bus, which mainly comprises speed, total voltage of the power battery and total current of the power battery, is acquired by using the OBD.
And on a parameter estimation layer, calculating the acceleration and instantaneous energy consumption of the vehicle by using the acquired data such as the vehicle speed, the total voltage of the power battery, the total current of the power battery and the like. Establishing an energy recovery state classification model of the electric bus, taking the second-by-second (instantaneous) speed and the acceleration as input variables, taking the energy recovery state as an output variable, carrying out parameter estimation, and then respectively establishing energy consumption estimation models of an energy consumption state and a recovery state and carrying out parameter estimation.
In the core calculation layer, the instantaneous speed and the acceleration of the vehicle are obtained according to the GPS navigation system, firstly, an energy recovery state classification model is used for judging whether the vehicle carries out energy recovery, and then, the corresponding energy consumption estimation model is used for carrying out instantaneous energy consumption estimation according to the state judgment result.
An instantaneous energy consumption estimation system of an electric bus based on an energy recovery state is applied to the instantaneous energy consumption estimation method of the electric bus based on the energy recovery state, and comprises a data acquisition module, an energy consumption estimation establishment module and an energy consumption real-time estimation module, wherein the data acquisition module is used for acquiring and storing real-time preset various types of running state data of a target electric bus, specifically, an on-board diagnostic system (OBD) is used for acquiring monitoring data of the electric bus and acquiring historical running data of a detected vehicle, and the historical running data mainly comprises speed, total current of a power battery and total voltage of the power battery; the energy consumption estimation building module builds an energy recovery state classification model and an energy consumption estimation model based on preset various types of historical driving state data stored in the data acquisition module; the energy consumption real-time estimation module is based on the energy recovery state classification model and the energy consumption estimation model, and combines instantaneous speed and instantaneous acceleration in each type of driving state data preset in real time, namely, the GPS is utilized to obtain the real-time speed and acceleration, so that the real-time instantaneous energy consumption of the target electric bus is obtained.
The energy consumption estimation building module comprises an energy recovery state classification building unit and an energy consumption estimation building unit, wherein the energy recovery state classification building unit builds an energy recovery state classification model based on preset various types of historical driving state data stored in the data acquisition module; the energy consumption estimation establishing unit establishes 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 models comprise energy consumption estimation models corresponding to different energy recovery states respectively, namely the energy consumption estimation models corresponding to the energy consumption states and the energy recovery states respectively, and the energy consumption estimation models corresponding to the energy consumption states and the energy recovery states respectively.
An instantaneous energy consumption estimation terminal of an electric bus based on an energy recovery state comprises a memory and a processor, wherein the memory and the processor are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the instantaneous energy consumption estimation method of the electric bus based on the energy recovery state.
The energy recovery state classification model and the energy consumption estimation model are integrated to obtain the energy consumption estimation module of the electric bus. Firstly, energy consumption state classification is carried out by utilizing the collected speed and acceleration data, whether the vehicle is in an energy consumption state or a recovery state is judged, and then the energy consumption calculation sub-model in the corresponding state is utilized to estimate the current battery power consumption or recovery amount within 1 second, namely instantaneous energy consumption.
In order to illustrate the superiority of the energy consumption estimation model after adding the state classification model, the invention also establishes the energy consumption estimation model without classification as comparison. The energy consumption estimation results of the classified and unclassified electric buses are obtained by training the data in the embodiment and then estimating the energy consumption by using the test set, and are shown in fig. 3. As can be seen from fig. 3, the classified and unclassified energy consumption models have better estimation effects on the energy consumption state, i.e., the energy outflow state, but the classified energy consumption estimation model is significantly better than the unclassified energy consumption estimation model in the energy recovery state.
The energy consumption estimation errors for both models are shown in table 3 with and without classification model energy consumption estimation errors. The embodiment adopts three error types of MSE, RMSE and MAE to illustrate the estimation error of the model. Compared with the errors of the two models, the three errors of the energy consumption estimation model with the energy state division are obviously lower than those of the energy consumption estimation model without the state division, and the instantaneous energy consumption estimation method of the electric bus considering the energy recovery state discrimination, which is provided by the invention, has better energy consumption estimation effect and greater superiority and can accurately estimate the energy consumption of the electric bus.
TABLE 3
| Type of error | With classification models | Classification-free model |
| MSE | 2.94×10 -6 | 5.61×10 -6 |
| RMSE | 0.00171 | 0.00237 |
| MAE | 0.00112 | 0.00135 |
The invention designs a pure electric bus instantaneous energy consumption estimation method and system considering energy recovery state classification, establishes a pure electric bus instantaneous energy consumption estimation model based on real vehicle driving data, and outputs instantaneous energy consumption of a vehicle at the current moment by taking real-time speed and acceleration as input variables. Before the energy consumption estimation model is established, an energy recovery state classification model is established, the energy consumption state and the recovery state are distinguished, and then the energy consumption estimation models of the energy consumption state and the recovery state are respectively established. The method considers different characteristics of energy consumption of the electric bus in the energy consumption state and the recovery state, has higher energy consumption estimation precision, and is beneficial to scientific energy consumption management.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing detailed description, or equivalent changes may be made in some of the features of the embodiments described above. All equivalent structures made by using the contents of the specification and the attached drawings of the invention can be directly or indirectly applied to other related technical fields, and are also within the protection scope of the patent of the invention.
Claims (10)
1. An electric bus instantaneous energy consumption estimation method based on an energy recovery state is characterized in that: aiming at the target electric bus, the following steps are executed to obtain the real-time instantaneous energy consumption of the target electric bus:
step A: acquiring preset driving state data of various types in real time aiming at a target electric bus;
and B: acquiring real-time instantaneous speed and instantaneous acceleration of the target electric bus based on real-time preset various types of running state data of the target electric bus;
and C: judging the energy recovery state of the target electric bus in real time based on the real-time instantaneous speed and the instantaneous acceleration of the target electric bus;
step D: and obtaining the real-time instantaneous energy consumption of the target electric bus based on the real-time judged energy recovery state of the target electric bus and by combining the real-time instantaneous speed and instantaneous acceleration of the target electric bus.
2. The method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state as claimed in claim 1, wherein: the target electric bus energy recovery state comprises an energy consumption state and a recovery state.
3. The method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state as claimed in claim 1, wherein: in the step C, the energy recovery state of the target electric bus is judged in real time through the following scheme:
step C1: acquiring instantaneous speed, instantaneous acceleration and energy recovery states of the target electric bus at all historical moments based on preset various types of historical driving state data of the target electric bus;
and C2: constructing an energy recovery state classification model which takes the instantaneous speed and the instantaneous acceleration as input and takes the energy recovery state at the moment as output based on the instantaneous speed, the instantaneous acceleration and the energy recovery state of the target electric bus at each historical moment;
and C3: and judging the energy recovery state of the target electric bus in real time through an energy recovery state classification model based on the real-time instantaneous speed and instantaneous acceleration of the target electric bus.
4. The method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state as claimed in claim 3, wherein: and in the step C2, an energy recovery state classification model is constructed by adopting a gradient lifting algorithm.
5. The method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state as claimed in claim 1, wherein: in the step D, the real-time instantaneous energy consumption of the target electric bus is obtained through the following scheme:
step D1: acquiring instantaneous speed, instantaneous acceleration, energy recovery state and instantaneous energy consumption of the target electric bus at each historical moment based on preset various types of historical driving state data of the target electric bus;
step D2: constructing an energy consumption estimation model which takes the instantaneous speed, the instantaneous acceleration and the energy recovery state as input and takes the instantaneous energy consumption at the moment as output on the basis of the instantaneous speed, the instantaneous acceleration, the instantaneous energy consumption and the energy recovery state of the target electric bus at each historical moment;
and D3: and obtaining the real-time instantaneous energy consumption of the target electric bus through an energy consumption estimation model based on the real-time distinguished energy recovery state of the target electric bus and by combining the real-time instantaneous speed and the instantaneous acceleration of the target electric bus.
6. The method for estimating the instantaneous energy consumption of the electric bus based on the energy recovery state as claimed in claim 5, wherein: in the step D2, the following steps are specifically executed to construct an energy consumption estimation model:
step D2.1: constructing an energy consumption estimation function by 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 the moment t, v (t) represents the instantaneous speed at the moment t, a (t) represents the instantaneous acceleration at the moment t, and beta 0 、β 1 、β 2 、β 3 、β 4 All represent coefficients;
step D2.2: based on the energy consumption estimation function, combining the instantaneous speed, the instantaneous acceleration and the instantaneous energy consumption of the target electric bus at each historical moment corresponding to different energy recovery states respectively to obtain energy consumption estimation functions corresponding to the different energy recovery states respectively, namely energy consumption estimation models corresponding to the different energy recovery states respectively.
7. An electric bus instantaneous energy consumption estimation system based on an energy recovery state is applied to the electric bus instantaneous energy consumption estimation method based on the energy recovery state, which is characterized in that: the energy consumption real-time estimation method comprises a data acquisition module, an energy consumption estimation establishing module and an energy consumption real-time estimation module, wherein the data acquisition module is used for acquiring and storing real-time preset driving state data of various types of target electric buses; the energy consumption estimation building module builds an energy recovery state classification model and an energy consumption estimation model based on preset various types of historical driving state data stored in the data acquisition module; the energy consumption real-time estimation module is used for acquiring real-time instantaneous energy consumption of the target electric bus by combining preset instantaneous speed and instantaneous acceleration in each type of driving state data on the basis of the energy recovery state classification model and the energy consumption estimation model.
8. The system according to claim 7, wherein the energy recovery state-based instantaneous energy consumption estimation system for the electric bus comprises: the energy consumption estimation building module comprises an energy recovery state classification building unit and an energy consumption estimation building unit, wherein the energy recovery state classification building unit builds an energy recovery state classification model based on preset various types of historical driving state data stored in the data acquisition module; the energy consumption estimation establishing unit establishes an energy consumption estimation model based on preset historical driving state data of various types stored in the data acquisition module.
9. The system for estimating instantaneous energy consumption of electric buses according to the energy recovery state as claimed in claim 7, characterized in that: the energy consumption estimation models comprise energy consumption estimation models respectively corresponding to different energy recovery states.
10. The utility model provides an electric bus instantaneous energy consumption estimation terminal based on energy recuperation state which characterized in that: the energy recovery state-based instantaneous energy consumption estimation method for the electric buses comprises a memory and a processor, wherein the memory and the processor are connected with each other in a communication mode, computer instructions are stored in the memory, and the processor executes the computer instructions so as to execute the energy recovery state-based instantaneous energy consumption estimation method for the electric buses according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211558442.9A CN115782595B (en) | 2022-12-06 | 2022-12-06 | Electric bus instantaneous energy consumption estimation method based on energy recovery state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211558442.9A CN115782595B (en) | 2022-12-06 | 2022-12-06 | Electric bus instantaneous energy consumption estimation method based on energy recovery state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115782595A true CN115782595A (en) | 2023-03-14 |
| CN115782595B CN115782595B (en) | 2024-04-02 |
Family
ID=85418825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211558442.9A Active CN115782595B (en) | 2022-12-06 | 2022-12-06 | Electric bus instantaneous energy consumption estimation method based on energy recovery state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115782595B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868787A (en) * | 2016-03-31 | 2016-08-17 | 江苏大学 | Electric car driving range evaluation method based on working condition identification and fuzzy energy consumption |
| CN109558988A (en) * | 2018-12-13 | 2019-04-02 | 北京理工新源信息科技有限公司 | A kind of electric car energy consumption prediction technique and system based on big data fusion |
| CN109733248A (en) * | 2019-01-09 | 2019-05-10 | 吉林大学 | Pure electric automobile remaining mileage model prediction method based on routing information |
| CN109752590A (en) * | 2019-01-28 | 2019-05-14 | 北京航空航天大学 | A kind of Electric Transit energy consumption estimation method based on data-driven |
| CN110610260A (en) * | 2019-08-21 | 2019-12-24 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
| CN113485102A (en) * | 2021-06-22 | 2021-10-08 | 西安法士特汽车传动有限公司 | Method for identifying vehicle running condition based on long-term and short-term memory neural network |
| CN114595513A (en) * | 2022-02-24 | 2022-06-07 | 智己汽车科技有限公司 | Electric drive system energy consumption simulation calculation method and device, vehicle and storage medium |
-
2022
- 2022-12-06 CN CN202211558442.9A patent/CN115782595B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868787A (en) * | 2016-03-31 | 2016-08-17 | 江苏大学 | Electric car driving range evaluation method based on working condition identification and fuzzy energy consumption |
| CN109558988A (en) * | 2018-12-13 | 2019-04-02 | 北京理工新源信息科技有限公司 | A kind of electric car energy consumption prediction technique and system based on big data fusion |
| CN109733248A (en) * | 2019-01-09 | 2019-05-10 | 吉林大学 | Pure electric automobile remaining mileage model prediction method based on routing information |
| CN109752590A (en) * | 2019-01-28 | 2019-05-14 | 北京航空航天大学 | A kind of Electric Transit energy consumption estimation method based on data-driven |
| CN110610260A (en) * | 2019-08-21 | 2019-12-24 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
| CN113485102A (en) * | 2021-06-22 | 2021-10-08 | 西安法士特汽车传动有限公司 | Method for identifying vehicle running condition based on long-term and short-term memory neural network |
| CN114595513A (en) * | 2022-02-24 | 2022-06-07 | 智己汽车科技有限公司 | Electric drive system energy consumption simulation calculation method and device, vehicle and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| SIRUI NAN等: "From driving behavior to energy consumption_ A novel method to predict the energy consumption of electric bus", ENERGY * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115782595B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | Intelligent energy management strategy based on hierarchical approximate global optimization for plug-in fuel cell hybrid electric vehicles | |
| CN110775065B (en) | Hybrid electric vehicle battery life prediction method based on working condition recognition | |
| Tian et al. | An adaptive ECMS with driving style recognition for energy optimization of parallel hybrid electric buses | |
| Zhao et al. | Energy management strategies for fuel cell hybrid electric vehicles: Classification, comparison, and outlook | |
| CN107688343B (en) | Energy control method of hybrid power vehicle | |
| Shi et al. | Pontryagin’s minimum principle based fuzzy adaptive energy management for hybrid electric vehicle using real-time traffic information | |
| Zhang et al. | A deep reinforcement learning-based energy management framework with lagrangian relaxation for plug-in hybrid electric vehicle | |
| CN110991757A (en) | Comprehensive prediction energy management method for hybrid electric vehicle | |
| Wei et al. | Comparison of architecture and adaptive energy management strategy for plug-in hybrid electric logistics vehicle | |
| CN112327168A (en) | XGboost-based electric vehicle battery consumption prediction method | |
| CN113479186B (en) | Energy management strategy optimization method for hybrid electric vehicle | |
| Wei et al. | Online estimation of driving range for battery electric vehicles based on SOC-segmented actual driving cycle | |
| CN109693545A (en) | The evaluation method and device of a kind of battery remaining power, vehicle remaining mileage | |
| Jia et al. | Health-aware energy management strategy for fuel cell hybrid bus considering air-conditioning control based on TD3 algorithm | |
| Chen et al. | Power reserve predictive control strategy for hybrid electric vehicle using recognition-based long short-term memory network | |
| Jinquan et al. | Driving information process system-based real-time energy management for the fuel cell bus to minimize fuel cell engine aging and energy consumption | |
| Ye et al. | Application of a new type of lithium‑sulfur battery and reinforcement learning in plug-in hybrid electric vehicle energy management | |
| CN113815437B (en) | Predictive energy management method for fuel cell hybrid electric vehicle | |
| Li et al. | Energy sources durability energy management for fuel cell hybrid electric bus based on deep reinforcement learning considering future terrain information | |
| Hou et al. | Real-time energy management strategy of a fuel cell electric vehicle with global optimal learning | |
| Zhang et al. | Deep Reinforcement Learning based Multi-Objective Energy Management Strategy for a Plug-in Hybrid Electric Bus Considering Driving Style Recognition | |
| Chen et al. | On the relationship between energy consumption and driving behavior of electric vehicles based on statistical features | |
| Golchoubian et al. | Stochastic nonlinear model predictive control of battery-supercapacitor hybrid energy storage systems in electric vehicles | |
| Mei et al. | Remaining driving range prediction for electric vehicles: Key challenges and outlook | |
| Gao et al. | Control strategy for PHEB based on actual driving cycle with driving style characteristic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |