CN109552219A - A kind of distributed security monitoring method based on hybrid vehicle - Google Patents
A kind of distributed security monitoring method based on hybrid vehicle Download PDFInfo
- Publication number
- CN109552219A CN109552219A CN201910031796.XA CN201910031796A CN109552219A CN 109552219 A CN109552219 A CN 109552219A CN 201910031796 A CN201910031796 A CN 201910031796A CN 109552219 A CN109552219 A CN 109552219A
- Authority
- CN
- China
- Prior art keywords
- coefficient
- measurement
- battery
- concentration
- hybrid vehicle
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
- B60R16/0231—Circuits relating to the driving or the functioning of the vehicle
- B60R16/0232—Circuits relating to the driving or the functioning of the vehicle for measuring vehicle parameters and indicating critical, abnormal or dangerous conditions
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The distributed security monitoring method based on hybrid vehicle that the invention discloses a kind of, comprising: Step 1: obtaining travel speed V, engine power P, pickup a and the abnormal position point quantity M of automobile by sensor according to the sampling period；Step 2: successively parameter is normalized, the input layer vector x={ x of three layers of BP neural network is determined1,x2,x3,x4}；Wherein, x1For travel speed coefficient, x2For engine power coefficient, x3For acceleration factor, x4For interior abnormal position points coefficient of discharge；Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to middle layer, the middle layer vector y={ y1,y2,…,ym}；M is middle layer node number；Step 4: obtaining output layer vector o={ o1,o2,o3}；o1For control of engine speed signal, o2For battery compartment charge flow rate adjustment signal, o3For alarm system alarm signal, neuron value isWork as o3When being 1, automobile normal running works as o3When being 0, alarm system is alarmed.Real-time monitoring is carried out by the working condition to automobile engine and battery compartment, improves vehicle safety.
Description
Technical field
The distributed security monitoring method based on hybrid vehicle that the present invention relates to a kind of, belongs to automotive field.
Background technique
Hybrid vehicle (Hybrid Vehicle) refers to that vehicle drive system can be operated simultaneously by two or more
The vehicle that single drive system constitutes jointly, the road horsepower of vehicle is according to actual vehicle running state by single drive system
Separately or cooperatively provide.Usually said hybrid vehicle generally refers to oil-electric vehicle (Hybrid
Electric Vehicle, HEV), i.e., using traditional internal combustion engine (diesel engine or gasoline engine) and motor as power source,
Some engines use other alternative fuel, such as compressed natural gas, propane and alcohol fuel etc. by transformation.
As the measure of countries in the world environmental protection is increasingly stringenter, hybrid vehicle is due to its energy conservation, low emission etc.
Feature becomes an emphasis of automotive research and exploitation, and has begun commercialization.
In recent years, with the popularization of hybrid vehicle, the safety of hybrid vehicle receives several high pointes of people
Note, with the popularization and application of hybrid vehicle, causes hybrid vehicle auto-ignition event increasingly to increase, in recent years, China's report
The excessively a lot of new energy buses in road, automobile be on fire, auto-ignition event, causes vehicle to burn the serious consequence of even personnel death, gives
Transport company and the family members of the deceased bring serious injury.
Vehicle spontaneous combustion and vehicle fire event are mainly reflected on energy source of car, including battery, engine, fuel gas
Etc..Hybrid vehicle is provided with enging cabin and High-Voltage Electrical Appliances cabin forms it into closed and narrow sky due to tail portion
Between, when engine operation, under high-temperature high-pressure state, interior road electric wiring and pipeline are easy to appear aging circuit, electric leakage etc.
Problem, or even cause fire gaseous volatilization or is let out in addition, some other artificial or non-artificial carrying fuel gas is ridden
Leakage will lead to burning, or even cause vehicle spontaneous combustion.Meanwhile under engine high-temperature state, it is a large amount of that power-supply battery can discharge place
Flammable and combustion-supporting gas, be on the verge of to burn inside Battery case, such as control not in time, fire or vehicle spontaneous combustion certainly will be brought.
Summary of the invention
The present invention has designed and developed a kind of distributed security monitoring method based on hybrid vehicle, passes through BP nerve net
Network carries out real-time monitoring to the working condition of automobile engine and battery compartment, and early warning is carried out when occurring abnormal, improves automobile
Safety.
Another goal of the invention of the invention can quickly determine abnormal position point, further increase the safety of running car
Property, prevent the generation of self-burning of vehicle and fire.
Technical solution provided by the invention are as follows:
A kind of distributed security monitoring method based on hybrid vehicle, comprising:
Step 1: being added according to the sampling period by travel speed V, engine power P, automobile that sensor obtains automobile
Speed a and abnormal position point quantity M；
Step 2: successively parameter is normalized, the input layer vector x={ x of three layers of BP neural network is determined1,x2,
x3,x4}；Wherein, x1For travel speed coefficient, x2For engine power coefficient, x3For acceleration factor, x4For interior abnormal position
Points coefficient of discharge；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to middle layer, the middle layer vector y={ y1,y2,…,ym}；During m is
Interbed node number；
Step 4: obtaining output layer vector o={ o1,o2,o3}；o1For control of engine speed signal, o2For battery compartment into
Throughput adjustment signal, o3For alarm system alarm signal, neuron value isWork as o3When being 1, the normal row of automobile
It sails, works as o3When being 0, alarm system is alarmed.
Preferably, the determination of the abnormal position point includes the following steps:
Step 1, according to the sampling period, pass through sensor and acquire vehicle interior temperature Ti, smokescopeAnd CO concentration CcoiFrom
It is small to being arranged successively greatly, obtain vehicle interior temperature matrix T=[T1, T2, T3... Ti,…TN], smokescope Matrix Cy=[Cy1, Cy2,
Cy3…Cyi…CyN], CO concentration matrix Cco=[Cco1,Cco2,Cco3…Ccoi…CcoN]；
Step 2, normalized after vehicle interior temperature, smokescope and CO concentration are normalized after temperature square
Battle array, smokescope matrix and CO concentration matrix；
Step 3 obtains position correspondingly and temperature, smokescope and CO concentration after normalization, carries out abnormal
Location point determines, determines the empirical equation θ of abnormal position pointiAre as follows:
Wherein, λ is security evaluation coefficient,
Preferably, the empirical equation of the security evaluation coefficient are as follows:
Wherein,For the smokescope measured value of i-th of sensor measurement, CymaxFor smokescope greatest measurement,
For the average value of smokescope in measurement period, CcoiFor the CO concentration measurement of i-th of sensor measurement, CcomaxFor CO concentration
Greatest measurement,For the average value of CO concentration in measurement period, TiFor the vehicle interior temperature measured value of i-th of sensor measurement,
TmaxFor vehicle interior temperature greatest measurement,For vehicle interior temperature average value in measurement period.
Preferably, the formula being normalized in the step 2 are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter V, P, a, N, j=1,2,3,4；XjmaxWith
XjminMaximum value and minimum value in respectively corresponding measurement parameter.
Preferably, the middle layer node number m meets:Wherein, n is input layer
Number, p are output layer node number.
Preferably, the excitation function of the middle layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
Preferably, the empirical equation of the battery compartment charge flow rate are as follows:
Wherein, f is correction coefficient, k1For battery compartment internal drag coefficient, CpFor the specific heat capacity of battery cell, m is battery pack
Quality, TiFor the measurement temperature of battery pack, T0For the initial temperature of battery pack, q is the heat efficiency of battery, and t is the work of battery
Time, kcFor air inlet constriction coefficient, A2Air inlet cross-sectional area, L are the spacing of battery module and battery compartment, and V is battery appearance
Product, V0For battery compartment maximum gas volume, vbFor battery cell volume, PiTo measure pressure, P in battery compartment0It is first in battery compartment
Beginning pressure.
It is of the present invention the utility model has the advantages that the present invention be arranged alarm module, by vehicle interior temperature, smokescope and CO
Concentration carries out Distributed Multi real-time monitoring, can quickly determine abnormal position point, further increase the safety of running car,
The generation of self-burning of vehicle and fire is prevented, while being carried out by working condition of the BP neural network to automobile engine and battery
Real-time monitoring carries out early warning when occurring abnormal, improves the safety of automobile.By CAN bus system to the real-time work of automobile
It is detected as state, is capable of the status information of precise acquisition automobile, realized that vehicle transducing signal is shared, make the peace of running car
Quan Xinggeng high.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of distributed monitoring system of the present invention.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
As shown in Figure 1, the present invention provides a kind of distributed security monitoring method based on hybrid vehicle, distribution peace
Full monitoring system starts with automotive ignition and is opened, and distributed security monitoring system specifically includes: CAN bus telecommunication circuit, master
Control module and multiple CAN networks.
Wherein, CAN bus telecommunication circuit, including at least one CAN controller and CAN transceiver have and receive, send function
Can and message filtering can be completed；
Main control module connects CAN bus telecommunication circuit, can monitor the working condition of system and efficiently control
The operation of system；
Multiple CAN networks connect CAN bus telecommunication circuit, and each network being capable of the corresponding data processing of complete independently
And realize the communication function between CAN bus telecommunication circuit
Wherein, main control module can control one or more completion function debuggings, function control and biography in CAN network
The data of sensor acquire, and can monitor the state of CAN bus telecommunication circuit；
In upper computer control system, the corresponding data sampling and processing of each CAN network complete independently, storage and display
Etc. tasks, network node is " equal party " when data communication, is communicated using point-to-point mode, while each CAN network
Tie point as host computer and CAN bus, wherein main control module can control one or more work in CAN network,
The software realization of CAN bus is mainly made of three parts that receive and transmit of the initialization of SJA1000, data.
Slave computer software utilizes microprocessor to the acquisition function of the data such as driving information, and according to host computer
Control instruction controls engine system, Battery Plant's system and alarm system.It is real by carrying out software implementation to CAN bus agreement
Existing, the data between completion upper and lower machine are shown and control function.,
Lower computer control system mainly realizes two functions: one is acquiring running car data by sensor, and right
Measured value is analyzed and is handled, and transfers to host computer analysis to handle the output of processing result hair to CAN bus in time；The second is
The communication function with CAN bus may be implemented, both can satisfy slave computer data real-time transmission to host computer, also can satisfy reality
When receive the control signal assigned of host computer, realize and slave computer controlled.
As a preference, main control module includes CAN network controller and processor, wherein CAN network controller packet
Include master network operating mode and from network mode of operation；
When being in master network operating mode, the number between main control module and CAN network node is realized by CAN bus
According to communication；
When in from network mode of operation, the data communication between each CAN network is realized by CAN bus.
Wherein, master network operating mode includes: aggressive mode and follower mode；
When have the initiative mode when, main control module send data requesting instructions, and receive returned for data requesting instructions
The data returned, carry out repeat-back after handling the data of return；
When being in follower mode, main control module passively receives data, and carries out after handling received data
Repeat-back.
In the present embodiment, the first CAN network include: engine supervisory system, it is battery management system, speed change system, pre-
Alert system, the second CAN network include: that CO density monitoring system, cockpit temperature monitoring system and smokescope monitor system,
Third CAN network includes: steering system, door control system and braking system.
Due to independently of each other, being between the power battery of hybrid vehicle, enging cabin, High-Voltage Electrical Appliances storehouse and compartment
It is easily installed and is adjusted in monitoring position, realize optimum state monitoring, use nothing between main control module between each CAN network
Line communication modes are installed by distribution, are configured to network address, node between master & slave control module, communication frequency point is matched
It sets, different monitoring networks can be configured to corresponding communication channel.
The distributed security monitoring method based on hybrid vehicle that the present invention also provides a kind of, is realized by CAN network
The covering of distributed locomotive network monitor, and sensing is passed through while the car is driving according to the sampling period by BP neural network
Device carries out Distributed Multi real-time monitoring to vehicle interior temperature, smokescope and CO concentration, can quickly determine abnormal position point,
The safety for further increasing running car prevents the generation of self-burning of vehicle and fire.
Step 1: establishing BP neural network model.
For the BP network architecture that the present invention uses by up of three-layer, first layer is input layer, total n node, corresponding
Indicate n monitoring signals of equipment working state, these signal parameters are provided by data preprocessing module.The second layer is hidden layer,
Total m node is determined in an adaptive way by the training process of network.Third layer is output layer, total p node, by system
Actual needs output in response to determining that.
The mathematical model of the network are as follows:
Input vector: x=(x1,x2,...,xn)T
Middle layer vector: y=(y1,y2,...,ym)T
Output vector: O=(o1,o2,...,op)T
In the present invention, input layer number is n=4, and output layer number of nodes is p=3.Hidden layer number of nodes m is estimated by following formula
It obtains:
4 parameters of input signal respectively indicate are as follows: x1For travel speed coefficient, x2For engine power coefficient, x3To accelerate
Spend coefficient, x4For interior abnormal position points coefficient of discharge
Since the data that sensor obtains belong to different physical quantitys, dimension is different.Therefore, people is inputted in data
Before artificial neural networks, need to turn to data requirement into the number between 0-1.
The travel speed V of automobile, engine power P, pickup a and abnormal position point quantity M are subjected to normalizing
Change processing, formula are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter V, P, a, M, j=1,2,3,4；XjmaxWith
XjminMaximum value and minimum value in respectively corresponding measurement parameter, using S type function, fj(x)=1/ (1+e-x)。
Specifically, after being normalized, obtaining automobile driving speed coefficient x for automobile driving speed V1:
Wherein, VminAnd VmaxThe respectively minimum value and maximum value of automobile driving speed.
Likewise, obtaining engine power coefficient x after engine power P is normalized2；
Wherein, PminAnd PmaxThe respectively minimum value and maximum value of engine power.
Likewise, obtaining pickup coefficient x after pickup a is normalized3；
Wherein, aminAnd amaxThe respectively minimum value and maximum value of pickup.
Likewise, obtaining interior abnormal point numerical coefficient of discharge x after interior abnormal position point quantity M is normalized4
Wherein, MminAnd MmaxRespectively running car when amplitude minimum value and maximum value
Obtain output layer vector o={ o1,o2,o3}；o1For control of engine speed signal, o2For battery compartment charge flow rate tune
Save signal, o3For alarm system alarm signal, neuron value isWork as o3When being 1, automobile normal running works as o3It is 0
When, alarm system is alarmed.
In the present embodiment, the determination of abnormal position point includes the following steps:
Step 1, according to the sampling period, pass through sensor and acquire vehicle interior temperature Ti, smokescopeAnd CO concentration CcoiFrom
It is small to being arranged successively greatly, obtain vehicle interior temperature matrix T=[T1, T2, T3... Ti,…TN], smokescope Matrix Cy=[Cy1, Cy2,
Cy3…Cyi…CyN], CO concentration matrix Cco=[Cco1,Cco2,Cco3…Ccoi…CcoN]；
Step 2, normalized after vehicle interior temperature, smokescope and CO concentration are normalized after temperature square
Battle array, smokescope matrix and CO concentration matrix；
Step 3 obtains position correspondingly and temperature, smokescope and CO concentration after normalization, carries out abnormal
Location point determines, determines the empirical equation θ of abnormal position pointiAre as follows:
Wherein, λ is security evaluation coefficient, empirical equation are as follows:
Interior abnormal position point quantity formula are as follows:
Wherein,For the smokescope measured value of i-th of sensor measurement, CymaxFor smokescope greatest measurement,
For the average value of smokescope in measurement period, CcoiFor the CO concentration measurement of i-th of sensor measurement, CcomaxFor CO concentration
Greatest measurement,For the average value of CO concentration in measurement period, TiFor the vehicle interior temperature measured value of i-th of sensor measurement,
TmaxFor vehicle interior temperature greatest measurement, T is vehicle interior temperature average value in measurement period.
Step 2: carrying out BP neural network training.
The sample of training, and the connection between given input node i and hidden layer node j are obtained according to historical empirical data
Weight Wij, hidden node j and output node layer k between connection weight Wjk, the threshold θ of hidden node jj, output node layer k's
Threshold θk、Wij、Wjk、θj、θkIt is the random number between -1 to 1.
In the training process, W is constantly correctedij、WjkValue, until systematic error be less than or equal to anticipation error when, complete mind
Training process through network.
(1) training method
Each subnet is using individually trained method；When training, first have to provide one group of training sample, each of these sample
This, to forming, when all reality outputs of network and its consistent ideal output, is shown to train by input sample and ideal output
Terminate；Otherwise, by correcting weight, keep the ideal output of network consistent with reality output；
(2) training algorithm
BP network is trained using error back propagation (Backward Propagation) algorithm, and step can be concluded
It is as follows:
Step 1: a selected structurally reasonable network, is arranged the initial value of all Node B thresholds and connection weight.
Step 2: making following calculate to each input sample:
(a) forward calculation: to l layers of j unit
In formula,L layers of j unit information weighted sum when being calculated for n-th,For l layers of j units with it is previous
Connection weight between the unit i of layer (i.e. l-1 layers),For preceding layer (i.e. l-1 layers, number of nodes nl-1) unit i send
Working signal；When i=0, enableFor the threshold value of l layers of j unit.
If the activation primitive of unit j is sigmoid function,
And
If neuron j belongs to the first hidden layer (l=1), have
If neuron j belongs to output layer (l=L), have
(b) retrospectively calculate error:
For output unit
To hidden unit
(c) weight is corrected:
η is learning rate.
Step 3: new sample or a new periodic samples are inputted, and until network convergence, the sample in each period in training
Input sequence is again randomly ordered.
BP algorithm seeks nonlinear function extreme value using gradient descent method, exists and falls into local minimum and convergence rate is slow etc.
Problem.A kind of more efficiently algorithm is Levenberg-Marquardt optimization algorithm, it makes the e-learning time shorter,
Network can be effectively inhibited and sink into local minimum.Its weighed value adjusting rate is selected as
Δ ω=(JTJ+μI)-1JTe；
Wherein, J is error to Jacobi (Jacobian) matrix of weight differential, and I is input vector, and e is error vector,
Variable μ is the scalar adaptively adjusted, for determining that study is completed according to Newton method or gradient method.
In system design, system model is one merely through the network being initialized, and weight needs basis using
The data sample obtained in journey carries out study adjustment, devises the self-learning function of system thus.Specify learning sample and
In the case where quantity, system can carry out self study, to constantly improve network performance；
As shown in table 1, given the value of each node in one group of training sample and training process
Each nodal value of 1 training process of table
Step 3: acquisition sensor operating parameter input neural network obtains automobile normal running signal and the letter that stops in emergency
Number.
Trained artificial neural network is solidificated among chip, hardware circuit is made to have prediction and intelligent decision function
Can, to form Intelligent hardware.
The initial of BP neural network is obtained by the way that above-mentioned parameter is standardized using the collected parameter of sensor simultaneously
Input vectorInitial output vector is obtained by the operation of BP neural network
Step 4: the working condition of monitoring engine speed, battery compartment charge flow rate and alarm system.
According to output layer vectoro1For control of engine speed signal, o2For the adjusting of battery compartment charge flow rate
Signal, o3For alarm system alarm signal, neuron value isWork as o3When being 1, automobile normal running works as o3When being 0,
Alarm system is alarmed.
Wherein, the empirical equation of battery compartment charge flow rate are as follows:
Wherein, f is correction coefficient, k1For battery compartment internal drag coefficient, CpFor the specific heat capacity of battery cell, m is battery pack
Quality, TiFor the measurement temperature of battery pack, T0For the initial temperature of battery pack, q is the heat efficiency of battery, and t is the work of battery
Time, kcFor air inlet constriction coefficient, A2Air inlet cross-sectional area, L are the spacing of battery module and battery compartment, and V is battery appearance
Product, V0For battery compartment maximum gas volume, vbFor battery cell volume, PiTo measure pressure, P in battery compartment0It is first in battery compartment
Beginning pressure
By above-mentioned setting, Distributed Multi real-time monitoring is carried out to vehicle interior temperature, smokescope and CO concentration, it can
It quickly determines abnormal position point, further increases the safety of running car, prevent the generation of self-burning of vehicle and fire.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (7)
1. a kind of distributed security monitoring method based on hybrid vehicle, which is characterized in that in automotive service, be based on BP
Neural network determines the working condition of alarm, specifically comprises the following steps:
Step 1: obtaining travel speed V, engine power P, the pickup a of automobile by sensor according to the sampling period
And abnormal position point quantity M；
Step 2: successively parameter is normalized, the input layer vector x={ x of three layers of BP neural network is determined1,x2,x3,x4}；
Wherein, x1For travel speed coefficient, x2For engine power coefficient, x3For acceleration factor, x4For interior abnormal position point quantity
Coefficient；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to middle layer, the middle layer vector y={ y1,y2,…,ym}；M is middle layer
Node number；
Step 4: obtaining output layer vector o={ o1,o2,o3}；o1For control of engine speed signal, o2For battery compartment inlet air flow
Measure adjustment signal, o3For alarm system alarm signal, neuron value isWork as o3When being 1, automobile normal running works as o3
When being 0, alarm system is alarmed.
2. the distributed security monitoring method according to claim 1 based on hybrid vehicle, which is characterized in that described
The determination of abnormal position point includes the following steps:
Step 1, according to the sampling period, pass through sensor and acquire vehicle interior temperature Ti, smokescope CyiAnd CO concentration CcoiFrom it is small to
It is arranged successively greatly, obtains vehicle interior temperature matrix T=[T1, T2, T3... Ti,…TN], smokescope Matrix Cy=[Cy1, Cy2,Cy3…
Cyi…CyN], CO concentration matrix Cco=[Cco1,Cco2,Cco3…Ccoi…CcoN]；
Step 2, normalized after vehicle interior temperature, smokescope and CO concentration are normalized after temperature matrices, cigarette
Mist concentration matrix and CO concentration matrix；
Step 3 obtains position correspondingly and temperature, smokescope and CO concentration after normalization, carries out abnormal position
Point determines, determines the empirical equation θ of abnormal position pointiAre as follows:
Wherein, λ is security evaluation coefficient,
3. the distributed security monitoring method according to claim 2 based on hybrid vehicle, which is characterized in that described
The empirical equation of security evaluation coefficient are as follows:
Wherein,For the smokescope measured value of i-th of sensor measurement,For smokescope greatest measurement,For
The average value of smokescope, C in measurement periodcoiFor the CO concentration measurement of i-th of sensor measurement,Most for CO concentration
Big measured value,For the average value of CO concentration in measurement period, TiFor the vehicle interior temperature measured value of i-th of sensor measurement,
TmaxFor vehicle interior temperature greatest measurement,For vehicle interior temperature average value in measurement period.
4. the distributed security monitoring method according to claim 3 based on hybrid vehicle, which is characterized in that described
The formula being normalized in step 2 are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter V, P, a, N, j=1,2,3,4；XjmaxAnd XjminPoint
It Wei not maximum value and minimum value in corresponding measurement parameter.
5. the distributed security monitoring method according to claim 4 based on hybrid vehicle, which is characterized in that described
Middle layer node number m meets:Wherein, n is input layer number, and p is output node layer
Number.
6. the distributed security monitoring method according to claim 5 based on hybrid vehicle, which is characterized in that institute
The excitation function for stating middle layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
7. the distributed security monitoring method according to claim 6 based on hybrid vehicle, which is characterized in that described
The empirical equation of battery compartment charge flow rate are as follows:
Wherein, f is correction coefficient, k1For battery compartment internal drag coefficient, CpFor the specific heat capacity of battery cell, m is battery pack matter
Amount, TiFor the measurement temperature of battery pack, T0For the initial temperature of battery pack, q is the heat efficiency of battery, when t is the work of battery
Between, kcFor air inlet constriction coefficient, A2Air inlet cross-sectional area, L are the spacing of battery module and battery compartment, and V is cell volume,
V0For battery compartment maximum gas volume, vbFor battery cell volume, PiTo measure pressure, P in battery compartment0It is initial in battery compartment
Pressure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910031796.XA CN109552219A (en) | 2019-01-14 | 2019-01-14 | A kind of distributed security monitoring method based on hybrid vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910031796.XA CN109552219A (en) | 2019-01-14 | 2019-01-14 | A kind of distributed security monitoring method based on hybrid vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109552219A true CN109552219A (en) | 2019-04-02 |
Family
ID=65872946
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910031796.XA Pending CN109552219A (en) | 2019-01-14 | 2019-01-14 | A kind of distributed security monitoring method based on hybrid vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109552219A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110077341A (en) * | 2019-05-16 | 2019-08-02 | 辽宁工业大学 | A kind of plug-in hybrid-power automobile method for safety monitoring |
| CN110631640A (en) * | 2019-10-29 | 2019-12-31 | 云南师范大学 | Intelligent monitoring system and method for storage tobacco leaf mildew state based on Internet of things |
| CN110733493A (en) * | 2019-11-22 | 2020-01-31 | 辽宁工业大学 | Power distribution method for hybrid electric vehicles |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106043171A (en) * | 2016-07-07 | 2016-10-26 | 辽宁工业大学 | Distributed electric vehicle intelligent in-vehicle network terminal platform and braking control method |
| CN205890794U (en) * | 2016-07-07 | 2017-01-18 | 辽宁工业大学 | On -vehicle network terminal platform of distributing type electric automobile |
| CN207683428U (en) * | 2017-12-06 | 2018-08-03 | 江苏师范大学 | A kind of occupant's security monitoring and warning device |
| CN109000936A (en) * | 2018-07-18 | 2018-12-14 | 辽宁工业大学 | A kind of vehicle fuel fault detection method |
| CN109109787A (en) * | 2018-07-24 | 2019-01-01 | 辽宁工业大学 | A kind of vehicle running fault monitoring method |
-
2019
- 2019-01-14 CN CN201910031796.XA patent/CN109552219A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106043171A (en) * | 2016-07-07 | 2016-10-26 | 辽宁工业大学 | Distributed electric vehicle intelligent in-vehicle network terminal platform and braking control method |
| CN205890794U (en) * | 2016-07-07 | 2017-01-18 | 辽宁工业大学 | On -vehicle network terminal platform of distributing type electric automobile |
| CN207683428U (en) * | 2017-12-06 | 2018-08-03 | 江苏师范大学 | A kind of occupant's security monitoring and warning device |
| CN109000936A (en) * | 2018-07-18 | 2018-12-14 | 辽宁工业大学 | A kind of vehicle fuel fault detection method |
| CN109109787A (en) * | 2018-07-24 | 2019-01-01 | 辽宁工业大学 | A kind of vehicle running fault monitoring method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110077341A (en) * | 2019-05-16 | 2019-08-02 | 辽宁工业大学 | A kind of plug-in hybrid-power automobile method for safety monitoring |
| CN110631640A (en) * | 2019-10-29 | 2019-12-31 | 云南师范大学 | Intelligent monitoring system and method for storage tobacco leaf mildew state based on Internet of things |
| CN110733493A (en) * | 2019-11-22 | 2020-01-31 | 辽宁工业大学 | Power distribution method for hybrid electric vehicles |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Hybrid electric vehicle downshifting strategy based on stochastic dynamic programming during regenerative braking process | |
| Zhou et al. | Knowledge implementation and transfer with an adaptive learning network for real-time power management of the plug-in hybrid vehicle | |
| CN109552219A (en) | A kind of distributed security monitoring method based on hybrid vehicle | |
| CN106295799B (en) | A kind of implementation method of deep learning multilayer neural network | |
| Zhao et al. | A deep reinforcement learning framework for optimizing fuel economy of hybrid electric vehicles | |
| Singh et al. | Fuzzy logic and Elman neural network tuned energy management strategies for a power-split HEVs | |
| Jinquan et al. | Real-time energy management of fuel cell hybrid electric buses: Fuel cell engines friendly intersection speed planning | |
| CN110717218B (en) | Electric drive vehicle distributed power drive system reconstruction control method and vehicle | |
| CN109703548B (en) | Automobile power distribution method based on hybrid power | |
| CN110416644A (en) | A kind of vehicle-mounted lithium-ion-power cell implicit damage monitoring and thermal runaway early warning device and its method for early warning | |
| CN108284752B (en) | Extended range type fuel cell electric automobile power device and control method thereof | |
| CN109552112A (en) | A kind of battery energy storage control method for hybrid vehicle | |
| CN109878499B (en) | Hybrid vehicle power control method | |
| CN107976934B (en) | A kind of oil truck oil and gas leakage speed intelligent early-warning system based on wireless sensor network | |
| CN109300276A (en) | A kind of car inside abnormity early warning method based on Fusion | |
| CN110733493A (en) | Power distribution method for hybrid electric vehicles | |
| CN104680335A (en) | Evaluation method for new energy source automobile | |
| CN110077389B (en) | Energy management method for plug-in hybrid electric vehicle | |
| Ruan et al. | Real‐Time Energy Management Strategy Based on Driver‐Action‐Impact MPC for Series Hybrid Electric Vehicles | |
| CN107472038B (en) | Hybrid electric vehicle energy management method based on HCCI engine | |
| Park et al. | Intelligent energy management and optimization in a hybridized all-terrain vehicle with simple on–off control of the internal combustion engine | |
| Wei | Design of Web based expert system of electronic control engine fault diagnosis | |
| CN109000936A (en) | A kind of vehicle fuel fault detection method | |
| Shuai et al. | Optimal energy management of plug-in hybrid vehicles through exploration-to-exploitation ratio control in ensemble reinforcement learning | |
| CN110077341A (en) | A kind of plug-in hybrid-power automobile method for safety monitoring |
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 |