CN110733493A - A power distribution method for a hybrid electric vehicle - Google Patents

Abstract

The invention discloses a power distribution method of hybrid electric vehicles, which comprises the steps of monitoring the driving speed v and the acceleration a of the hybrid electric vehicle and the SOCS of an energy storage battery after the vehicle is driven_socMonitoring the running environment information of the hybrid electric vehicle, calculating the environmental influence factor α in the running process of the vehicle, and calculating the running speed v and the acceleration a of the hybrid electric vehicle and the SOC value S of the energy storage battery_socAnd an environmental impact factor α, controlling the mixing actionThe working states of the engine and the motor of the electric automobile are changed. The method can control the working states of the engine and the motor of the hybrid electric vehicle according to the driving environment and the state of the vehicle, so that the total energy consumption is minimum.

Description

A power distribution method for a hybrid electric vehicle

technical field

The invention relates to a power distribution method for a hybrid electric vehicle, belonging to the field of vehicle dynamics.

Background technique

The 100-year history of the vigorous development of the automobile industry records the glorious course of the rapid development of human civilization. However, the continuous increase in the number of automobiles has not only contributed to the rapid development of the world economy and provided convenience to people, but also pushed the energy and environmental problems to an increasingly serious problem. situation.

The energy consumed by traditional automobiles depends almost entirely on petroleum products. According to the estimated total world petroleum reserves, the world's petroleum resources can only be used by human beings for 40-50 years. Gradually scarcity, the gradual reduction of production, and the gradual increase in the cost of exploitation, the actual useful life of oil resources will be shorter. At the same time, along with the problem of oil consumption by automobiles, environmental problems cannot be ignored. At present, 42% of air pollution comes from transportation.

In order to solve energy and environmental problems, governments around the world and large automobile companies are developing new clean and energy-saving vehicles to alleviate environmental and energy problems.

A hybrid vehicle refers to a vehicle in which the vehicle drive system is composed of two or more single drive systems that can operate simultaneously. The driving power of the vehicle is provided by the single drive system alone or jointly according to the actual vehicle driving state.

The so-called hybrid vehicle generally refers to a gasoline-electric hybrid vehicle, that is, a traditional internal combustion engine and an electric motor are used as the power source, and some engines are modified to use other alternative fuels. With the stricter and stricter environmental protection measures all over the world, hybrid vehicles are more and more valued and welcomed by people due to their energy-saving, low-emission and other characteristics.

SUMMARY OF THE INVENTION

The invention designs and develops a power distribution method for a hybrid electric vehicle, which can control the working states of the engine and the electric motor of the hybrid electric vehicle according to the driving environment and state of the vehicle, so as to minimize the total energy consumption.

The technical scheme provided by the present invention is:

A power distribution method for a hybrid electric vehicle, comprising:

After the vehicle is running, monitor the driving speed v, acceleration a, and SOCS _soc of the energy storage battery of the hybrid electric vehicle;

Monitor the environmental information of the hybrid electric vehicle and calculate the environmental impact factor α during the driving process of the vehicle;

According to the driving speed v of the hybrid electric vehicle, the acceleration a, the SOC value S _soc of the energy storage battery and the environmental influence factor α, the working state of the engine and the electric motor of the hybrid electric vehicle is controlled.

Preferably, the environmental information includes: environmental temperature T, environmental humidity RH, road gradient δ, and wind speed κ.

Preferably, the controlling the working state of the engine and the electric motor of the hybrid electric vehicle includes:

Step 1: According to the sampling period, obtain the driving speed v, acceleration a of the hybrid electric vehicle, the SOC value S _soc of the energy storage battery, and the environmental impact factor α;

Step 2: Normalize the acquired parameters in turn, and determine the input layer vector of the three-layer BP neural network as, x={x ₁ , x ₂ , x ₃ , x ₄ , x ₅ }; wherein, x ₁ is the car The driving speed coefficient of , x ₂ is the acceleration coefficient of the car, x ₃ is the SOC value coefficient of the energy storage battery, and x ₄ is the environmental impact factor coefficient;

Step 3: The input layer vector is mapped to the middle layer, and the middle layer vector y={y ₁ , y ₂ , ..., y _m }; m is the number of nodes in the middle layer;

Step 4. Obtain the output layer vector o={o ₁ , o ₂ }, where o ₁ is the engine adjustment coefficient, and o ₂ is the motor adjustment coefficient;

Step 5: Input the output layer vector into the fuzzy controller, obtain the output vector group representing the adjustment category, and output it as the adjustment answer.

Preferably, the working process of the fuzzy controller includes:

Comparing the engine adjustment coefficient with a preset engine adjustment coefficient to obtain an engine adjustment deviation signal, and comparing the motor adjustment coefficient with the preset motor adjustment coefficient to obtain an electric motor adjustment deviation signal;

The engine adjustment deviation signal is obtained through differential calculation to obtain the engine adjustment change rate signal, and the motor adjustment deviation signal is obtained through differential calculation to obtain the motor adjustment change rate signal;

The engine regulation change rate signal and the motor regulation change rate signal are both amplified and input to the fuzzy controller, and the regulation level is output.

Preferably, the empirical formula of the air intake flow rate of the battery compartment of the energy storage battery satisfies:

Among them, q ₀ is the set reference value of the intake air flow of the battery compartment, k _c is the shrinkage coefficient, k ₁ is the resistance coefficient inside the battery compartment, V ₁ is the volume of the battery cell, and _VC is the total volume of the battery compartment, Pi is the working pressure _{in the battery compartment, and P 0 is} the initial pressure in the battery compartment.

Preferably, the empirical formula of the environmental impact factor satisfies:

为设定的环境温度基准值，δ为路面坡度，δ₀为设定的路面坡度基准值，κ为风速，κ₀为设定的风速基准值。Among them, T is the ambient temperature, T ₀ is the set ambient temperature reference value, RH is the ambient humidity,

is the set ambient temperature reference value, δ is the road gradient, δ ₀ is the set road gradient reference value, κ is the wind speed, and κ ₀ is the set wind speed reference value.

Preferably, the formula for normalization in the second step is:

Among them, x _j is the parameter in the input layer vector, X _j is the measurement parameter v, a, S _soc and α, respectively, j=1, 2, 3, 4; X _jmax and X _jmin are the maximum of the corresponding measurement parameters, respectively value and minimum value.

其中，n为输入层节点个数，p为输出层节点个数。Preferably, the number m of the intermediate layer nodes satisfies:

Among them, n is the number of nodes in the input layer, and p is the number of nodes in the output layer.

The beneficial effects of the present invention: the present invention can monitor the hybrid electric vehicle in real time during the driving process, control the working state of the electric motor and the engine of the hybrid electric vehicle according to the driving condition of the hybrid electric vehicle, and realize the power of the hybrid electric vehicle. Distribution and energy recovery to improve energy utilization.

During the driving process of the hybrid vehicle, by controlling the air intake flow of the battery compartment of the energy storage battery, the power mode of the hybrid vehicle is controlled, the damage to the energy storage battery is reduced, and the energy distribution in different modes is realized.

Through the BP neural network and fuzzy control, the working state of the electric motor and the engine of the hybrid electric vehicle is controlled and adjusted, so as to realize the energy recovery of the hybrid electric vehicle and improve the utilization rate of the energy of the hybrid electric vehicle.

Detailed ways

The present invention will be further described in detail below, so that those skilled in the art can implement it with reference to the description.

The invention provides a power distribution method for a hybrid electric vehicle, which can monitor the running process of the hybrid electric vehicle in real time, and control the working states of the electric motor and the engine of the hybrid electric vehicle according to the driving condition of the hybrid electric vehicle, so as to realize the hybrid electric vehicle. Power distribution and energy recovery of electric vehicles to improve energy utilization.

The power distribution method for a hybrid electric vehicle provided by the present invention is used in a parallel hybrid electric vehicle, and its power system consists of an engine (an internal combustion engine) and an electric motor (powered by an energy storage battery). The measurement parameters of the present invention are acquired through the CAN bus, and specifically include:

After the vehicle is running, monitor the driving speed v, acceleration a, and SOCS _soc of the energy storage battery of the hybrid electric vehicle;

Monitor the environmental information of the hybrid electric vehicle and calculate the environmental impact factor α during the driving process of the vehicle;

Among them, the empirical formula of environmental impact factor satisfies:

In the formula, T is the ambient temperature, the unit is °C, _T0 is the set ambient temperature reference value, the unit is °C, RH is the ambient humidity, the unit is %, is the set ambient temperature reference value, the unit is %, δ is the road slope, the unit is %, δ ₀ is the set road gradient reference value, the unit is %, κ is the wind speed, the unit is m/s, κ ₀ is The set wind speed reference value, the unit is m/s.

According to the driving speed v of the hybrid electric vehicle, the acceleration a, the SOC value S _soc of the energy storage battery and the environmental influence factor α, the working state of the engine and the electric motor of the hybrid electric vehicle is controlled.

Among them, the empirical formula of the air intake flow of the battery compartment of the energy storage battery satisfies:

In the formula, q ₀ is the set reference value of the intake air flow rate of the battery compartment, the unit is m ³ /h, k _c is the shrinkage coefficient, k ₁ is the resistance coefficient inside the battery compartment, and V ₁ is the volume of the battery cell, the unit is is m ³ , _VC is the total volume of the battery compartment, the unit is m ³ , Pi is the working pressure in the battery compartment, the unit is Pa, and P ₀ is the initial pressure _in the battery compartment, the unit is Pa.

The working state of the engine and motor of the hybrid electric vehicle is controlled through the BP neural network, including:

Step 1: Establish a BP neural network model.

The BP network architecture adopted by the present invention consists of three layers, the first layer is the input layer, with n nodes in total, corresponding to n monitoring signals representing the working state of the equipment, and these signal parameters are given by the data preprocessing module. The second layer is the hidden layer, with a total of m nodes, which is determined in an adaptive manner by the training process of the network. The third layer is the output layer, with a total of p nodes, which is determined by the response that the system actually needs to output.

The mathematical model of the network is:

Input vector: x=(x ₁ ,x ₂ ,...,x _n ) ^T

Intermediate layer vector: y=(y ₁ , y ₂ ,...,y _m ) ^T

Output vector: O=(o ₁ ,o ₂ ,...,o _p ) ^T

In the present invention, the number of nodes in the input layer is n=4, and the number of nodes in the output layer is p=2. The number of hidden layer nodes m is estimated by the following formula:

The four parameters of the input signal are respectively expressed as: x1 is the driving speed coefficient _of the car, _x2 is the acceleration coefficient of the car, _x3 is the SOC value coefficient of the energy storage battery, and _x4 is the environmental impact factor coefficient;

The driving speed v, acceleration a of the electric vehicle, the SOC value S _soc of the energy storage battery, and the environmental impact factor α are normalized, and the formula is

Among them, x _j is the parameter in the input layer vector, X _j is the measurement parameter v, a, S _soc , α, j=1, 2, 3, 4; X _jmax and X _jmin are the maximum values of the corresponding measurement parameters, respectively Value and minimum value, using sigmoid function, f _j (x)=1/(1+e ^-x ).

The two parameters of the output signal are respectively expressed as: o={o ₁ , o ₂ }, o ₁ is the adjustment coefficient of the engine, and o ₂ is the adjustment coefficient of the motor.

Step 2. Perform BP neural network training

After the BP neural network node model is established, the BP neural network can be trained. The training samples are obtained according to the historical experience data, and given the connection weight W _ij between the input node i and the hidden layer node j, the connection weight W _jk between the hidden layer node j and the output layer node k, the hidden layer The threshold θ _j of node j and the threshold θ _k , W _ij , W _jk , θ _j , and θ _k of node k of the output layer are all random numbers between -1 and 1.

During the training process, the values of W _ij and W _jk are continuously corrected until the system error is less than or equal to the expected error, and the training process of the neural network is completed.

training method

Each sub-network adopts a separate training method; during training, a set of training samples must be provided first, each of which consists of an input sample and an ideal output pair. When all the actual outputs of the network are consistent with their ideal outputs, the training is over; Otherwise, correct the weights to make the ideal output of the network consistent with the actual output; the input samples during training of each sub-network are shown in Table 1:

Table 1

When designing the system, the system model is a network that has only been initialized, and the weights need to be learned and adjusted according to the data samples obtained during use. For this reason, the self-learning function of the system is designed. In the case of specifying the learning samples and the number, the system can perform self-learning to continuously improve the network performance. The output samples after training of each subnet are shown in Table 2:

Table 2

Step 3: Collect and transmit the operating parameters of each unit and input them into the neural network to obtain the output power regulation of the motor and the output signal of the power converter.

The trained artificial neural network is solidified in the chip, so that the hardware circuit has the functions of prediction and intelligent decision-making, thus forming intelligent hardware.

通过BP神经网络的运算得到初始输出向量 At the same time, the parameters collected by the sensor are used, and the initial input vector of the BP neural network is obtained by normalizing the above parameters.

The initial output vector is obtained through the operation of the BP neural network

According to the environmental influence factor in the i-th cycle, the SOC lower limit value of the energy storage battery, and the sampling signal of the output power of the energy storage battery, determine the working state of the motor and the power converter in the i+1-th cycle, and get The output layer vector of is input into the fuzzy controller;

比较得到发动机调节偏差信号，将电动机调节系数o₂与预设的电动机调节系数

比较得到电动机调节偏差信号；Compare the engine adjustment factor o ₁ with the preset engine adjustment factor

Compare the engine adjustment deviation signal, and compare the motor adjustment coefficient o ₂ with the preset motor adjustment coefficient

Comparing to get the motor regulation deviation signal;

The engine adjustment deviation signal is obtained through differential calculation to obtain the engine adjustment change rate signal e ₁ , and the motor adjustment deviation signal is obtained through differential calculation to obtain the motor adjustment change rate signal e ₂ ;

The engine regulation change rate signal e ₁ and the motor regulation change rate signal e ₂ are both amplified and input into the fuzzy controller, and the output regulation level I={I ₀ , I ₁ , I ₂ , I ₃ }, where I ₀ For normal operation, I ₁ is the primary regulation, I ₂ is the secondary regulation, and I ₃ is the alarm signal.

Among them, the actual variation ranges of e ₁ and e ₂ are [-1,1], [-1,1] respectively; the discrete universes are {-6, -5, -4, -3, -2, -1 , 0, 1, 2, 3, 4, 5, 6}, the discrete universe of I is {0, 1, 2, 3}, then the quantization factor, then k ₁ =6/1, k ₂ =6/1 ;

Define fuzzy subsets and membership functions:

Divide the engine regulation change rate signal into 7 fuzzy states: PB (positive large), PM (positive middle), PS (positive small), ZR (zero), NS (negative small), NM (negative medium), NB (negative large) ), and combined with experience, the membership function table of the air-conditioning regulation change rate signal e ₁ is obtained, as shown in Table 3:

table 3

e₁ -6 -5 -4 -3 -2 -1 0 +1 +2 +3 +4 +5 +6 PB 0 0 0 0 0 0 0 0 0 0 0.4 0.8 1.0 PM 0 0 0 0 0 0 0 0 0.2 0.7 1.0 0.5 0.1 PS 0 0 0 0 0 0 0 0.4 1.0 0.8 0.7 0 0 ZR 0 0 0 0 0.2 0.7 1.0 0 0 0 0 0 0 NB 0 0 0.3 0.6 1.0 0.8 0.5 0 0 0 0 0 0 NM 0.2 0.4 1.0 0.6 0.1 0 0 0 0 0 0 0 0 NS 1.0 0.6 0.4 0.2 0 0 0 0.2 0 0 0 0 0

Divide the engine regulation change rate signal into 7 fuzzy states: PB (positive large), PM (positive middle), PS (positive small), ZR (zero), NS (negative small), NM (negative medium), NB (negative large) ), and combined with experience, the membership function table of the air-conditioning regulation change rate signal e ₁ is obtained, as shown in Table 4:

Table 4

e₂ -6 -5 -4 -3 -2 -1 0 +1 +2 +3 +4 +5 +6 PB 0 0 0 0 0 0 0 0 0 0 0.4 0.8 1.0 PM 0 0 0 0 0 0 0 0 0.2 0.7 1.0 0.5 0.1 PS 0 0 0 0 0 0 0 0.4 1.0 0.8 0.7 0 0 ZR 0 0 0 0 0.2 0.7 1.0 0 0 0 0 0 0 NB 0 0 0.3 0.6 1.0 0.8 0.5 0 0 0 0 0 0 NM 0.2 0.4 1.0 0.6 0.1 0 0 0 0 0 0 0 0 NS 1.0 0.6 0.4 0.2 0 0 0 0.2 0 0 0 0 0

The fuzzy inference process must perform complex matrix operations, the amount of calculation is very large, and it is difficult to implement the inference online to meet the real-time requirements of the control system. Experience can summarize the preliminary control rules of the fuzzy controller. The fuzzy controller defuzzifies the output signal according to the obtained fuzzy value, and obtains the fault level I, and obtains the fuzzy control look-up table. Since the universe of discourse is discrete, the fuzzy control rules and can be expressed as a fuzzy matrix, using single-point fuzzification, the I control rules are shown in Table 5.

Through the BP neural network and fuzzy control, the working state of the electric motor and the engine of the hybrid electric vehicle is controlled and adjusted, so as to realize the energy recovery of the hybrid electric vehicle and improve the utilization rate of the energy of the hybrid electric vehicle.

Although the embodiment of the present invention has been disclosed as above, it is not limited to the application listed in the description and the embodiment, and it can be applied to various fields suitable for the present invention. For those skilled in the art, it can be easily Therefore, the invention is not limited to the specific details and embodiments shown and described herein without departing from the general concept defined by the appended claims and the scope of equivalents.

Claims (8)

1, A power distribution method for a hybrid electric vehicle, comprising:

after the vehicle runs, the running speed v and the acceleration a of the hybrid electric vehicle and the SOC value S of the energy storage battery are monitored_soc；

Monitoring running environment information of the hybrid electric vehicle, and calculating an environment influence factor α in the running process of the vehicle;

according to the running speed v and the acceleration a of the hybrid electric vehicle and the SOC value S of the energy storage battery_socAnd environmental impact factor α, controlling the engine and motor of a hybrid electric vehicleAnd (5) working state.

2. The power distribution method of a hybrid electric vehicle according to claim 1, wherein the environmental information includes: ambient temperature T, ambient humidity RH, road slope δ, wind speed κ.

3. The power distribution method of a hybrid electric vehicle according to claim 2, wherein the controlling the operating states of the engine and the motor of the hybrid electric vehicle includes:

step , acquiring the running speed v and the acceleration a of the hybrid electric vehicle and the SOC value S of the energy storage battery according to the sampling period_socAnd an environmental impact factor α;

step two, the obtained parameters are classified into in sequence, and the input layer vector of the three-layer BP neural network is determined to be x ═ x₁,x₂,x₃,x₄,x₅}; wherein x is₁Is the running speed coefficient, x, of the motor vehicle₂Is the acceleration coefficient, x, of the vehicle₃For the SOC value coefficient, x, of the energy storage battery₄Is an environmental impact factor coefficient;

step three, the input layer vector is mapped to a middle layer, and the middle layer vector y is { y ═ y₁,y₂,…,y_m}; m is the number of intermediate layer nodes;

step four, obtaining an output layer vector o ═ o₁,o₂}，o₁For engine adjustment factor, o₂Adjusting the coefficient for the motor;

and step five, inputting the output layer vector into the fuzzy controller to obtain an output vector group representing the adjustment type, and outputting the output vector group as an adjustment answer.

4. The power distribution method of a hybrid electric vehicle according to claim 3, wherein the operation process of the fuzzy controller comprises:

comparing the engine regulating coefficient with a preset engine regulating coefficient to obtain an engine regulating deviation signal, and comparing the motor regulating coefficient with a preset motor regulating coefficient to obtain a motor regulating deviation signal;

carrying out differential calculation on the engine regulation deviation signal to obtain an engine regulation change rate signal, and carrying out differential calculation on the motor regulation deviation signal to obtain a motor regulation change rate signal;

the engine regulation change rate signal and the motor regulation change rate signal are amplified and then input into a fuzzy controller, and the regulation grade is output.

5. The power distribution method of a hybrid electric vehicle according to claim 4, wherein an empirical formula of a battery compartment intake air flow rate of the energy storage battery satisfies:

wherein q is₀Is a reference value, k, of the set battery compartment intake air flow_cIs the coefficient of contraction, k₁Is the coefficient of resistance, V, inside the battery compartment₁Is the cell volume, V_CIs the total volume of the battery compartment, P_iIs the working pressure in the battery compartment, P₀Is the initial pressure within the battery compartment.

6. The power distribution method of a hybrid electric vehicle according to claim 5, wherein the empirical formula of the environmental impact factor satisfies:

wherein T is the ambient temperature, T₀RH is the environmental humidity for the set environmental temperature reference value,

for a set reference value of ambient temperature, δ is the road gradient, δ₀For a set road slope referenceValue, κ wind speed, κ₀Is the set wind speed reference value.

7. The method of distributing power of a hybrid electric vehicle according to claim 6, wherein the formula classified into in the second step is:

wherein x is_jFor parameters in the input layer vector, X_jRespectively as measurement parameters v, a and S_socAnd α, j ═ 1,2,3,4, X_jmaxAnd X_jminRespectively, a maximum value and a minimum value in the corresponding measured parameter.

8. The power distribution method of a hybrid electric vehicle according to claim 7, wherein the number m of intermediate nodes satisfies:

wherein n is the number of nodes of the input layer, and p is the number of nodes of the output layer.