CN109816934B - Early warning device and early warning method for preventing driving fatigue - Google Patents
Early warning device and early warning method for preventing driving fatigue Download PDFInfo
- Publication number
- CN109816934B CN109816934B CN201910129442.9A CN201910129442A CN109816934B CN 109816934 B CN109816934 B CN 109816934B CN 201910129442 A CN201910129442 A CN 201910129442A CN 109816934 B CN109816934 B CN 109816934B
- Authority
- CN
- China
- Prior art keywords
- cab
- driver
- early warning
- fatigue
- concentration
- 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.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Abstract
The invention discloses an early warning device for preventing driving fatigue, which comprises: a pressure sensor installed in the driver's seat for detecting the pressure of the driver's seat; a light sensor for detecting the intensity of light within the cab; a somatosensory environment sensor module for detecting temperature, humidity and air pressure in the cab; an air quality detection sensor module for detecting a carbon monoxide concentration, a carbon dioxide concentration, and a PM2.5 concentration in the cab; the information operation processing module is used for receiving detection information of the pressure sensor, the light sensor, the somatosensory environment sensor module and the air quality detection sensor module and judging whether a driver is in a fatigue driving state or not according to the detection information; and the early warning module is electrically connected with the information operation processing module and is used for sending out fatigue driving early warning information. Meanwhile, the invention also discloses an early warning method suitable for the early warning device for preventing driving fatigue.
Description
Technical Field
The invention belongs to the technical field of driving fatigue active safety early warning, and particularly relates to an early warning device and an early warning method for preventing driving fatigue.
Background
The driving fatigue refers to a phenomenon that a driver generates imbalance of physiological functions and psychological functions after continuous driving for a long time, and the driving skill is objectively reduced. The driver drives the vehicle for a long time, and fatigue is likely to occur. Fatigue in driving affects the attention, feel, perception, thinking, judgment, mind, decision, and movement of the driver. The fatigue driving of the driver has important influence on traffic safety. So China prescribes that the driver must not drive continuously for more than four hours.
However, driving fatigue is not only related to driving duration, but also is affected by environmental factors. For example, when a vehicle is driven in hot summer or in an overheated environment in a cab, the temperature is high, the ventilation is poor, a driver is easy to fatigue, the driver is often tired, the sight is gradually blurred, the thinking becomes slow, especially, the driver is easy to sleepy after noon, even the phenomenon that the driver instantaneously loses memory can occur, and traffic accidents can be caused by the driving. Therefore, it is necessary to consider the influence of environmental factors in the early warning of driving fatigue.
Disclosure of Invention
The invention provides a warning device for preventing driving fatigue, which aims to judge whether a driver is in a fatigue driving state according to the pressure of a driver seat and the environment in a vehicle and send out warning when the driver is judged to be in the fatigue driving state.
The invention provides an early warning method for preventing driving fatigue, which has the advantages that whether a driver is in a fatigue driving state is judged according to the continuous driving time of the driver, the light intensity in the driver's cabin, the somatosensory environment in the driver's cabin and the air quality, and the influence of environmental factors is considered in the judging process, so that the reliability of a judging result can be improved.
The invention provides an early warning method for preventing driving fatigue, which has the second purpose of obtaining a somatosensory environment index according to the temperature, the humidity and the air pressure in a cab and obtaining an air quality index according to the concentration of carbon monoxide and the concentration of carbon dioxide PM2.5 in the cab; and the influence of environmental factors on fatigue driving is reasonably and quantitatively controlled, so that the accuracy of a judgment result is further improved.
The technical scheme provided by the invention is as follows:
an early warning device for preventing driving fatigue, comprising:
a pressure sensor installed in the driver's seat for detecting the pressure of the driver's seat;
a light sensor for detecting the intensity of light within the cab;
a somatosensory environment sensor module for detecting temperature, humidity and air pressure in the cab;
an air quality detection sensor module for detecting a carbon monoxide concentration, a carbon dioxide concentration, and a PM2.5 concentration in the cab;
the information operation processing module is used for receiving detection information of the pressure sensor, the light sensor, the somatosensory environment sensor module and the air quality detection sensor module and judging whether a driver is in a fatigue driving state or not according to the detection information;
and the early warning module is electrically connected with the information operation processing module and is used for sending out fatigue driving early warning information.
Preferably, the pressure sensor has a plurality of pressure measurement points, and the plurality of pressure measurement points are disposed in a dispersed manner in the driver seat.
A warning method for preventing driving fatigue comprises the following steps:
step one, obtaining continuous driving time T of a driver through a pressure sensor, obtaining light intensity I in the driver's cabin through a light sensor, obtaining temperature T, humidity RH and air pressure P in the driver's cabin through a somatosensory environment sensor module, and obtaining carbon monoxide concentration C in the driver's cabin through an air quality detection sensor module CO Concentration of carbon dioxideAnd PM2.5 concentration C PM ；
Step two, obtaining a somatosensory environment index I in the cab according to the temperature T, the humidity RH and the air pressure P in the cab S According to the concentration C of carbon monoxide in the cab CO Concentration of carbon dioxideAnd PM2.5 concentration C PM Obtaining the air quality index I in the cab A ；
Step three, according to the continuous driving time t, the light intensity I in the cab and the somatosensory environment index I in the cab S Air quality index I in cab A Judging whether the driver is in a fatigue driving state, and sending out early warning information when the driver is in the fatigue driving state.
Preferably, in the second step, the somatosensory environment index is:
wherein a is 1 ＝0.4～0.5、a 2 ＝0.2～0.3、a 3 =0.2 to 0.3, and a 1 +a 2 +a 3 =1; t is the temperature in the cab, T 0 Is a set standard temperature; RH is humidity in the cab, RH 0 Is the set standard humidity; p is the air pressure in the cab, P 0 Is at standard atmospheric pressure.
Preferably, in the second step, the air quality index in the cab is:
wherein b is 1 ＝0.4～0.6、b 2 ＝0.2～0.3、b 3 =0.3 to 0.5, and b 1 +b 2 +b 3 ＝1；C CO For carbon monoxide concentration in the cab, C CO-0 Is the set standard carbon monoxide concentration;for the concentration of carbon dioxide in the cab,is the set standard carbon dioxide concentration; c (C) PM For PM2.5 concentration in the cab, C PM-0 Is the set standard PM2.5 concentration.
Preferably, in the first step, after the early warning device is started, when the pressure detected by more than 50% of detection points in the pressure sensor is greater than the set pressure, timing is started; when the interval time of the two times of timing is within the set time interval, accumulating timing; the twice timing time exceeds the set time interval and is re-timed.
Preferably, the set pressure is 2000Pa; the set time interval is 10min.
Preferably, in the third step, the step of judging whether the driver is in the fatigue driving state by using the BP neural network includes the following steps:
step 1, obtaining continuous driving time t, light intensity I in a driving cab and somatosensory environment index I in the driving cab according to a sampling period S Air quality index I in cab A ；
Step 2, normalizing the continuous driving time t and the light intensity I in the cab, and determining an input layer vector x= { x of the three-layer BP neural network 1 ,x 2 ,x 3 ,x 4 -a }; wherein x is 1 For continuous driving time coefficient, x 2 Is the light intensity coefficient, x 3 Is the somatosensory environment index I in the cab S 、x 4 For air quality index I in the cab A ；
Step 3, mapping the input layer vector to an intermediate layer, wherein the intermediate layer vector y= { y 1 ,y 2 ,…,y m -a }; m is the number of intermediate layer nodes;
step 4, obtaining an output layer vector o= { o 1 ,o 2 }；o 1 For fatigue driving coefficient o of driver 2 For emergency shutdown signals, the output layer neuron value isk is the output layer neuron sequence number, k= {1,2}; wherein, when o 1 When 1, the driver is in fatigue driving state, when o 1 When the vehicle is 0, the driver is in a non-fatigue driving state; when o 2 When the value is 1, the alarm device works normally, when o 2 When the value is 0, the alarm device works abnormally and stops working.
Preferably, in the step 2, the formula for normalizing the continuous driving time t and the intensity of light I in the cab is:
wherein x is j To input parameters in layer vectors, X j The detection parameters t, I, j=1, 2 respectively; x is X jmax And X jmin Respectively, the maximum value and the minimum value in the corresponding detection parameters.
Preferably, the number of the intermediate layer nodes is 3.
The beneficial effects of the invention are as follows:
(1) The early warning device for preventing driving fatigue provided by the invention can judge whether the driver is in a fatigue driving state according to the seat pressure of the driver and the environment in the vehicle, and send out early warning when the driver is judged to be in the fatigue driving state.
(2) According to the early warning method for preventing driving fatigue, whether the driver is in a fatigue driving state is judged according to the continuous driving time of the driver, the light intensity in the driver cab, the somatosensory environment in the driver cab and the air quality, and the influence of environmental factors is considered in the judging process, so that the reliability of a judging result is improved.
(3) According to the early warning method for preventing driving fatigue, the somatosensory environment index is obtained according to the temperature, the humidity and the air pressure in the cab, and the air quality index is obtained according to the concentration of carbon monoxide and the concentration of carbon dioxide PM2.5 in the cab; and the influence of environmental factors is reasonably and quantitatively controlled, so that the accuracy of a judgment result is further improved.
(4) According to the early warning method for preventing driving fatigue, the BP neural network is adopted to judge whether the driver is in a fatigue state, so that the judging efficiency can be improved, and the early warning device alarms when the early warning device is abnormal.
Drawings
Fig. 1 is a schematic view of a pressure sensor according to the present invention.
Fig. 2 is a schematic diagram of a warning method for preventing driving fatigue according to the present invention.
Detailed Description
The present invention is described in further detail below with reference to the drawings to enable those skilled in the art to practice the invention by referring to the description.
The invention provides an early warning device for preventing driving fatigue, which comprises a pressure sensor, a control unit and a control unit, wherein the pressure sensor is arranged in a driver seat and is used for detecting the pressure of the driver seat; the light sensor is arranged at the vehicle ceiling corresponding to the driver seat and is used for detecting the light intensity in the driver cab; a somatosensory environment sensor module mounted on top of the driver's seat or at other suitable location within the driver's cabin for detecting temperature, humidity and air pressure within the cabin; an air quality detection sensor module mounted proximate to the light sensor for detecting carbon monoxide concentration, carbon dioxide concentration and PM2.5 concentration within the cab; the information operation processing module is electrically connected with the pressure sensor, the light sensor, the body sensing environment sensor module and the air quality detection sensor module, receives detection information of the pressure sensor, the light sensor, the body sensing environment sensor module and the air quality detection sensor module, and judges whether a driver is in a fatigue driving state or not according to the detection information; and the early warning module is electrically connected with the information operation processing module and is used for sending out fatigue driving early warning information. The early warning module adopts a voice early warning mode to remind a driver.
As shown in fig. 1, the pressure sensor has a plurality of pressure measurement points 110, which are disposed in the driver's seat in a dispersed manner, and transmits the detected pressure to the information operation processing module through a data transmission line 120.
The early warning device for preventing driving fatigue is provided with an early warning terminal, the early warning terminal is arranged in a cab, and the information operation processing module and the early warning module are arranged in the early warning terminal; and a lithium battery is arranged in the early warning terminal and used as a power supply. The early warning terminal is provided with a switch, and a driver turns on and off the early warning terminal through the switch.
As shown in fig. 2, the invention further provides a warning method for preventing driving fatigue, which comprises the following steps:
step one, acquiring continuous driving time t of a driver through a pressure sensor, acquiring light intensity I in the driver's cabin through a light sensor, and acquiring the light intensity I in the driver's cabin through a somatosensory environment sensor moduleTemperature T, humidity RH and barometric pressure P, and the carbon monoxide concentration C in the cab is obtained by means of an air quality detection sensor module CO Concentration of carbon dioxideAnd PM2.5 concentration C PM ；
Step two, obtaining a somatosensory environment index I in the cab according to the temperature T, the humidity RH and the air pressure P in the cab S According to the concentration C of carbon monoxide in the cab CO Concentration of carbon dioxideAnd PM2.5 concentration C PM Obtaining the air quality index I in the cab A ；
Step three, according to the continuous driving time t, the light intensity I in the cab and the somatosensory environment index I in the cab S Air quality index I in cab A Judging whether the driver is in a fatigue driving state, and sending out early warning information when the driver is in the fatigue driving state.
In this embodiment, in the second step, the somatosensory environment index is empirically set as follows:
wherein a is 1 ＝0.4～0.5、a 2 ＝0.2～0.3、a 3 =0.2 to 0.3, and a 1 +a 2 +a 3 =1; t is the temperature in the cab, T 0 T is the set standard temperature 0 =25 ℃; RH is humidity in the cab, RH 0 For a set standard humidity, RH 0 =50; p is the air pressure in the cab, P 0 Is at standard atmospheric pressure.
Wherein, the value range of the temperature T is set to be [ -50,50 according to experience]The unit is DEG; setting the range of humidity RH to be [0,100 ]]Setting the value range of the air pressure P as [86,106 ]]The unit is kPa. Somatosensory feelEnvironmental index I S The value range of (2) is 0-1, and the somatosensory environment index I is that S The higher the driver is, the easier the driver enters a fatigue state. If the detected temperature T, humidity RH and air pressure P exceed the value range, the early warning device directly reminds which parameter is higher or lower than the early warning range through voice.
In another embodiment, in the second step, the air quality index is empirically set to be:
wherein b is 1 ＝0.4～0.6、b 2 ＝0.2～0.3、b 3 =0.3 to 0.5, and b 1 +b 2 +b 3 ＝1；C CO For carbon monoxide concentration in the cab, C CO-0 For the set standard carbon monoxide concentration, C CO-0 ＝5ppm；For the concentration of carbon dioxide in the cab>For a set standard carbon dioxide concentration, +.>C PM For PM2.5 concentration in the cab, C PM-0 For the set standard PM2.5 concentration, C PM-0 ＝35ppm。
Wherein the carbon monoxide concentration C is empirically set CO The value range of (2) is [5,40 ]]The unit is ppm; setting the concentration of carbon dioxideThe value range of (2) is [500,1000 ]]The unit is ppm; setting PM2.5 concentration C PM The value range of (5) is [35,250 ]]In ppm. Air quality index I A The value range of (2) is 0-1, and the somatosensory environment index I is that A The higher the driver is, the easier the driver gets intoFatigue state. If the detected concentration of carbon monoxide C CO Carbon dioxide concentration->PM2.5 concentration exceeds the value range, and the early warning device directly reminds which parameter is higher or lower than the early warning range through voice.
In another embodiment, in the first step, after the early warning device is started, when the pressure detected by more than 50% of detection points in the pressure sensor is greater than the set pressure, timing is started; when the interval time of the two times of timing is within the set time interval, accumulating timing; the twice timing time exceeds the set time interval and is re-timed. Wherein the set pressure is 2000Pa; the set time interval is 10min. For example, 8 measuring points of the pressure sensor exist, and when the pressure of more than 4 measuring points exists at the pressure sensor or the pressure of more than 2000Pa, the operation processing module judges that a person exists on the driver seat and starts timing; if the middle timing is interrupted, accumulating timing when the interval time of the two times of timing is within 10 min; the interval time exceeds 10 minutes to reckon.
In another embodiment, in the third step, the step of using the BP neural network to determine whether the driver is in the fatigue driving state includes the following steps:
and step 1, establishing a BP neural network model.
The BP network system structure adopted by the invention is composed of three layers, the first layer is an input layer, n nodes are used as the first layer, n monitoring signals representing the working state of equipment are corresponding to the first layer, and the parameters of the signals are given by a data preprocessing module. The second layer is a hidden layer, and m nodes are determined in an adaptive manner by the training process of the network. The third layer is an output layer, and p nodes are totally determined by the response which is actually required to be output by the system.
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 input layer nodes is n=4, and the number of output layer nodes is p=2. The number of hidden layer nodes m is estimated by:
the 4 parameters of the input signal are respectively expressed as: x is x 1 For continuous driving time coefficient, x 2 Is the intensity coefficient of the light in the cab, x 3 Is the somatosensory environment index I in the cab S 、x 4 For air quality index I in the cab A 。
Since the data acquired by the sensor belong to different physical quantities, the dimensions are different. Therefore, the data needs to be normalized to a number between 0 and 1 before the data is input into the artificial neural network.
Specifically, the continuous driving time t is normalized to obtain the continuous driving time coefficient x 1 ：
Wherein t is min And t max Respectively, the shortest continuous driving time and the longest continuous driving time are set.
Similarly, the light intensity I in the cab is normalized to obtain the light intensity coefficient x in the cab 2 ：
Wherein I is min And I max Respectively, the minimum light intensity in the cab and the maximum light intensity in the vehicle.
Due to somatosensory environmental index I S And air quality index I in the cab A The value ranges of the (a) are 0-1, and normalization is not needed, namely:
x 3 ＝I S ；
x 4 ＝I A ；
the 2 parameters of the output signal are expressed as: output layer vector o= { o 1 ,o 2 }；o 1 For fatigue driving coefficient o of driver 2 For emergency shutdown signals, the output layer neuron value isk is the output layer neuron sequence number, k= {1,2}; wherein, when o 1 When 1, the driver is in fatigue driving state, when o 1 When the vehicle is 0, the driver is in a non-fatigue driving state; when o 2 When the value is 1, the alarm device works normally, when o 2 When the value is 0, the alarm device works abnormally and stops working.
And step 2, training the BP neural network.
After the BP neural network node model is established, the BP neural network can be trained. Obtaining training samples according to historical experience data of products, and giving a connection weight w between an input node i and an hidden layer node j ij Connection weight w between hidden layer node j and output layer node k jk Threshold θ of hidden node j j The threshold value theta of the output layer node k k 、w ij 、w jk 、θ j 、θ k Are random numbers between-1 and 1.
In the training process, continuously correcting w ij And w jk And (3) completing the training process of the neural network until the systematic error is less than or equal to the expected error.
(1) Training method
Each sub-network adopts a method of independent training; during training, a group of training samples are provided, wherein each sample consists of an input sample and an ideal output pair, and when all actual outputs of the network are consistent with the ideal outputs, the training is finished; otherwise, the ideal output of the network is consistent with the actual output through correcting the weight;
(2) Training algorithm
The BP network adopts an error back propagation (Backward Propagation) algorithm for training, and the steps can be summarized as follows:
the first step: a network with reasonable structure is selected, and initial values of all node thresholds and connection weights are set.
And a second step of: the following calculations are made for each input sample:
(a) Forward calculation: j units to layer l
In the method, in the process of the invention,for the weighted sum of j unit information of layer l in the nth calculation,/>Is the connection weight between the j cell of layer l and the cell i of the previous layer (i.e. layer l-1,)>For the previous layer (i.e., layer l-1, node number n l-1 ) The working signal sent by the unit i; when i=0, let ∈ ->The threshold for j cells of layer i.
If the activation function of element j is a sigmoid function
And is also provided with
If neuron j belongs to the first hidden layer (l=1), then there is
If neuron j belongs to the output layer (l=l), then there is
And e j (n)＝x j (n)-o j (n)；
(b) Reverse calculation error:
for output units
To hidden unit
(c) Correcting the weight value:
η is the learning rate.
And a third step of: new samples or new period samples are input until the network converges, and the input sequence of the samples in each period is rearranged during training.
The BP algorithm adopts a gradient descent method to solve the extreme value of the nonlinear function, and has the problems of local minimum sinking, low convergence speed and the like. One of the more efficient algorithms is the Levenberg-Marquardt optimization algorithm, which allows for shorter network learning times and can effectively suppress network collapse to a local minimum. The weight adjustment rate is selected as
Δω＝(J T J+μI) -1 J T e；
Wherein J is a Jacobian (Jacobian) matrix of error versus weight differentiation, I is an input vector, e is an error vector, and the variable μ is an adaptively adjusted scalar used to determine whether learning is done according to Newton's method or gradient method.
When designing the system, the system model is a network which is only initialized, the weight is required to be learned and adjusted according to the data sample obtained in the using process, and the self-learning function of the system is designed for the system model. Under the condition that the learning samples and the number are specified, the system can perform self-learning to continuously perfect the network performance;
as shown in table 1, a set of training samples and the values of the nodes during training are given.
Table 1 training process node values
And step 3, acquiring operation parameters of the sensor, inputting the operation parameters into a neural network to obtain a fatigue coefficient of the driver and an emergency stop monitoring system.
And solidifying the trained artificial neural network in a chip to enable the hardware circuit to have the functions of prediction and intelligent decision making, thereby forming intelligent hardware.
Simultaneously, parameters acquired by the sensor are used for normalizing the parameters to obtain an initial input vector of the BP neural networkObtaining an initial output vector by the operation of the BP neural network>
And 4, monitoring fatigue conditions of the driver so as to monitor the emergency shutdown of the system.
According to the output layer neuron value o= { o 1 ,o 2 }；o 1 For fatigue driving coefficient o of driver 2 For emergency shutdown signals, the output layer neuron value isk is the output layer neuron sequence number, k= {1,2}; wherein, when o 1 When 1, the driver is in fatigue driving state, when o 1 When the vehicle is 0, the driver is in a non-fatigue driving state; when o 2 When the value is 1, the alarm device works normally, when o 2 When the value is 0, the alarm device works abnormally and stops working.
Through the arrangement, the continuous driving time t, the light intensity I in the cab and the somatosensory environment index I in the cab are obtained according to the sampling period S Air quality index I in cab A The method comprises the steps of carrying out a first treatment on the surface of the And (3) adopting a BP neural network algorithm to monitor the alarm condition of the monitoring system in real time. When the driver is in the fatigue driving state, sending out early warning to remind the driver; when the monitoring system is abnormal, the emergency stop is performed.
According to the early warning method for preventing driving fatigue, whether the driver is in a fatigue driving state is judged according to the continuous driving time of the driver, the light intensity in the driver cab, the somatosensory environment in the driver cab and the air quality, and the influence of environmental factors is considered in the judging process, so that the reliability of a judging result is improved. According to the invention, the somatosensory environment index is obtained according to the temperature, humidity and air pressure in the cab, and the air quality index is obtained according to the carbon monoxide concentration and the carbon dioxide concentration PM2.5 concentration in the cab; and the influence of environmental factors is reasonably and quantitatively controlled, so that the accuracy of a judgment result is further improved.
The invention adopts the BP neural network to judge whether the driver is in a fatigue state, can improve the judging efficiency, and gives an alarm when the early warning device is abnormal.
Although embodiments of the present invention have been disclosed above, it is not limited to the details and embodiments shown and described, it is well suited to various fields of use for which the invention would be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the specific details and illustrations shown and described herein, without departing from the general concepts defined in the claims and their equivalents.
Claims (7)
1. The utility model provides a prevent driving fatigue's early warning method which characterized in that, the early warning device of preventing driving fatigue who uses includes:
a pressure sensor installed in the driver's seat for detecting the pressure of the driver's seat;
a light sensor for detecting the intensity of light within the cab;
a somatosensory environment sensor module for detecting temperature, humidity and air pressure in the cab;
an air quality detection sensor module for detecting a carbon monoxide concentration, a carbon dioxide concentration, and a PM2.5 concentration in the cab;
the information operation processing module is used for receiving detection information of the pressure sensor, the light sensor, the somatosensory environment sensor module and the air quality detection sensor module and judging whether a driver is in a fatigue driving state or not according to the detection information;
the early warning module is electrically connected with the information operation processing module and is used for sending out fatigue driving early warning information;
the early warning method comprises the following steps:
step one, obtaining continuous driving time T of a driver through a pressure sensor, obtaining light intensity I in the driver's cabin through a light sensor, obtaining temperature T, humidity RH and air pressure P in the driver's cabin through a somatosensory environment sensor module, and obtaining carbon monoxide concentration C in the driver's cabin through an air quality detection sensor module CO Concentration of carbon dioxideAnd PM2.5 concentration C PM ；
Step two, obtaining a somatosensory environment index I in the cab according to the temperature T, the humidity RH and the air pressure P in the cab S According to the concentration C of carbon monoxide in the cab CO Concentration of carbon dioxideAnd PM2.5 concentration C PM Obtaining the air quality index I in the cab A ；
The somatosensory environment index is as follows:
wherein a is 1 ＝0.4～0.5、a 2 ＝0.2～0.3、a 3 =0.2 to 0.3, and a 1 +a 2 +a 3 =1; t is the temperature in the cab, T 0 Is a set standard temperature; RH is humidity in the cab, RH 0 Is the set standard humidity; p is the air pressure in the cab, P 0 Is at standard atmospheric pressure;
the air quality index in the cab is as follows:
wherein b is 1 ＝0.4～0.6、b 2 ＝0.2～0.3、b 3 =0.3 to 0.5, and b 1 +b 2 +b 3 ＝1；C CO For carbon monoxide concentration in the cab, C CO-0 Is the set standard carbon monoxide concentration;for the carbon dioxide concentration in the cab,/-, is->Is the set standard carbon dioxide concentration; c (C) PM For PM2.5 concentration in the cab, C PM-0 Is the set standard PM2.5 concentration;
step three,According to the continuous driving time t, the light intensity I in the cab and the somatosensory environment index I in the cab S Air quality index I in cab A Judging whether the driver is in a fatigue driving state, and sending out early warning information when the driver is in the fatigue driving state.
2. The method for early warning against driving fatigue according to claim 1, wherein the pressure sensor has a plurality of pressure measurement points, and the plurality of pressure measurement points are disposed in a dispersed manner in the driver's seat.
3. The method for early warning against driving fatigue according to claim 2, wherein in the first step, after the early warning device is started, the timing is started when the pressure detected by more than 50% of the detection points in the pressure sensor is greater than the set pressure; when the interval time of the two times of timing is within the set time interval, accumulating timing; the twice timing time exceeds the set time interval and is re-timed.
4. The early warning method for preventing driving fatigue according to claim 3, wherein the set pressure is 2000Pa; the set time interval is 10min.
5. The method for preventing driving fatigue according to claim 4, wherein in the third step, the BP neural network is used to determine whether the driver is in a fatigue driving state, comprising the steps of:
step 1, obtaining continuous driving time t, light intensity I in a driving cab and somatosensory environment index I in the driving cab according to a sampling period S Air quality index I in cab A ；
Step 2, normalizing the continuous driving time t and the light intensity I in the cab, and determining an input layer vector x= { x of the three-layer BP neural network 1 ,x 2 ,x 3 ,x 4 -a }; wherein x is 1 For continuous driving time coefficient, x 2 Is the light intensity systemNumber, x 3 Is the somatosensory environment index I in the cab S 、x 4 For air quality index I in the cab A ；
Step 3, mapping the input layer vector to an intermediate layer, wherein the intermediate layer vector y= { y 1 ,y 2 ,…,y m -a }; m is the number of intermediate layer nodes;
step 4, obtaining an output layer vector o= { o 1 ,o 2 }；o 1 For fatigue driving coefficient o of driver 2 For emergency shutdown signals, the output layer neuron value isk is the output layer neuron sequence number, k= {1,2}; wherein, when o 1 When 1, the driver is in fatigue driving state, when o 1 When the vehicle is 0, the driver is in a non-fatigue driving state; when o 2 When the value is 1, the alarm device works normally, when o 2 When the value is 0, the alarm device works abnormally and stops working.
6. The method for early warning against driving fatigue according to claim 5, wherein in the step 2, the formula for normalizing the continuous driving time t and the intensity of light I in the cab is:
wherein x is j To input parameters in layer vectors, X j The detection parameters t and I, j=1, 2, respectively; x is X jmax And X jmin Respectively, the maximum value and the minimum value in the corresponding detection parameters.
7. The early warning method for preventing driving fatigue according to claim 6, wherein the number of intermediate layer nodes is 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910129442.9A CN109816934B (en) | 2019-02-21 | 2019-02-21 | Early warning device and early warning method for preventing driving fatigue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910129442.9A CN109816934B (en) | 2019-02-21 | 2019-02-21 | Early warning device and early warning method for preventing driving fatigue |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109816934A CN109816934A (en) | 2019-05-28 |
| CN109816934B true CN109816934B (en) | 2023-09-08 |
Family
ID=66607049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910129442.9A Active CN109816934B (en) | 2019-02-21 | 2019-02-21 | Early warning device and early warning method for preventing driving fatigue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816934B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113223270B (en) * | 2021-04-26 | 2023-02-28 | 西安建筑科技大学 | Fatigue driving monitoring, reminding and early warning method and system based on computer vision technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714660A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic |
| CN106652355A (en) * | 2016-12-22 | 2017-05-10 | 吴中区穹窿山倪源交通器材经营部 | Fatigue driving detection system |
| CN106652356A (en) * | 2016-12-22 | 2017-05-10 | 深圳市元征科技股份有限公司 | Driver fatigue determining method and device |
| CN107199845A (en) * | 2017-06-12 | 2017-09-26 | 吉林大学 | One kind drives indoor environment active control system and its control method |
| JP2017188127A (en) * | 2017-05-15 | 2017-10-12 | みこらった株式会社 | Automatic driving vehicle |
| CN107599783A (en) * | 2017-09-28 | 2018-01-19 | 吉林大学 | A kind of environment inside car management system and its control method |
| CN107914637A (en) * | 2017-11-23 | 2018-04-17 | 广东菲柯特电子科技有限公司 | Burglar alarm for long-time driving reminding |
| CN109147279A (en) * | 2018-10-19 | 2019-01-04 | 燕山大学 | A kind of driver tired driving monitoring and pre-alarming method and system based on car networking |
-
2019
- 2019-02-21 CN CN201910129442.9A patent/CN109816934B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714660A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic |
| CN106652355A (en) * | 2016-12-22 | 2017-05-10 | 吴中区穹窿山倪源交通器材经营部 | Fatigue driving detection system |
| CN106652356A (en) * | 2016-12-22 | 2017-05-10 | 深圳市元征科技股份有限公司 | Driver fatigue determining method and device |
| JP2017188127A (en) * | 2017-05-15 | 2017-10-12 | みこらった株式会社 | Automatic driving vehicle |
| CN107199845A (en) * | 2017-06-12 | 2017-09-26 | 吉林大学 | One kind drives indoor environment active control system and its control method |
| CN107599783A (en) * | 2017-09-28 | 2018-01-19 | 吉林大学 | A kind of environment inside car management system and its control method |
| CN107914637A (en) * | 2017-11-23 | 2018-04-17 | 广东菲柯特电子科技有限公司 | Burglar alarm for long-time driving reminding |
| CN109147279A (en) * | 2018-10-19 | 2019-01-04 | 燕山大学 | A kind of driver tired driving monitoring and pre-alarming method and system based on car networking |
Non-Patent Citations (1)
| Title |
|---|
| 熊群芳等.基于深度学习的疲劳驾驶状态检测方法.《控制与信息技术》.2018,(第第6期期),第91-95页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109816934A (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108335457B (en) | Driving safety monitoring method based on driving hand ring | |
| CN103978977B (en) | Vehicle monitoring system based on human body communication and method | |
| CN108545082B (en) | A kind of automobile lane change method for early warning | |
| CN109147279B (en) | Driver fatigue driving monitoring and early warning method and system based on Internet of vehicles | |
| CN108172288A (en) | Medical Devices intelligent control method, device and computer readable storage medium | |
| CN108556591A (en) | Interior air index adjusts Active Service System and method under car networking environment | |
| CN107117027A (en) | Vehicular intelligent control method and system based on fatigue monitoring | |
| CN109816934B (en) | Early warning device and early warning method for preventing driving fatigue | |
| CN108460957A (en) | A kind of the elder's health group monitoring warning system and method | |
| CN109300276A (en) | A kind of car inside abnormity early warning method based on Fusion | |
| CN110464315A (en) | It is a kind of merge multisensor the elderly fall down prediction technique and device | |
| CN110682903B (en) | Safety overtaking early warning system and method based on visual perception | |
| CN109886439B (en) | Remote diagnosis system and method for electric control vehicle | |
| CN110606034B (en) | Control method of intelligent cloud seat system | |
| CN109846459A (en) | A kind of fatigue driving state monitoring method | |
| US11263884B2 (en) | Early warning forecasting life-threatening temperature method and system | |
| CN108682120A (en) | A kind of vehicle fatigue early warning device and method | |
| CN109572692A (en) | A kind of electric-controlled vehicle Anti-knocking system and its control method | |
| CN111814976B (en) | Air conditioning system sensor fault error relearning method and system | |
| CN110154893A (en) | A kind of vehicle security drive method for early warning based on driver characteristics | |
| CN107170190A (en) | A kind of dangerous driving warning system | |
| CN113085555B (en) | Warning method for battery pack after thermal runaway | |
| CN206096872U (en) | Power generating equipment intelligence monitoring device | |
| CN112660957B (en) | Early warning method and early warning system for elevator operation risk | |
| CN105424224B (en) | A kind of disconnecting switch state monitoring method and device |
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 |