CN109377046A - Overload of vehicle method of discrimination, system and device based on BP neural network - Google Patents
Overload of vehicle method of discrimination, system and device based on BP neural network Download PDFInfo
- Publication number
- CN109377046A CN109377046A CN201811213520.5A CN201811213520A CN109377046A CN 109377046 A CN109377046 A CN 109377046A CN 201811213520 A CN201811213520 A CN 201811213520A CN 109377046 A CN109377046 A CN 109377046A
- Authority
- CN
- China
- Prior art keywords
- overload
- vehicle
- neuron
- layer
- load
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of overload of vehicle method of discrimination based on BP neural network, comprising: step S1 pre-processes overload source data；Step S2 establishes overload model using BP neural network structure；Step S3 will be substituted by pretreated overload source data and be obtained load-carrying predicted value in overload model.Collected Various types of data is carried out data prediction and integration first by the present invention, to obtain the source data of overloading analysis.Then on the basis of distinguishing haulage time and road type, source data is divided by haulage time section and road type (highway, urban express way, city main roads, city secondary road, city ordinary road).It is modeled for every kind of road type using BP neural network in different haulage time sections, obtains the mathematical model between each driving behavior of vehicle and vehicle load, compare the payload ratings of specific vehicle, judge the vehicle with the presence or absence of overloading.
Description
Technical field
The present invention relates to physical field more particularly to measuring technique, especially a kind of vehicle based on BP neural network is super
Carry method of discrimination, system and device.
Background technique
With the gradually development of science and technology, living standards of the people are greatly improved, and communications and transportation is increasingly flourishing, and vehicle constantly increases
More, traffic safety becomes the theme of current road traffic.Wherein, traffic safety problem caused by large-sized truck violation is especially tight
Weight, while overweight road pavement causes serious damage, has also caused numerous great traffic accidents.To check that lorry is super
Again equal unlawful practices, traffic management department would generally set up overweight monitoring point on thoroughfare, due to the when and where of monitoring point
Stationarity, is unable to the overload unlawful practice of effective monitoring lorry, and checking and supervising for traffic department seems passive, cannot control very well
Road traffic processed.Therefore, realize that the real-time monitoring of goods stock has great application value using informationization technology.
Currently, being quantitatively evaluated based on the vehicle drive behavior that mass data is excavated, text temporarily is seen in without correlative study
It offers.How effectively using the GPS data of magnanimity in car networking monitoring system, the overload unlawful practice of goods stock is divided
Potential rule in goods stock spatio-temporal data stream is excavated in analysis, to be road traffic portion using existing goods stock GPS data
The more scientific aid decision of the offers such as door, logistics, insurance business.Before important social economic value and wide application
Scape.
Summary of the invention
In view of the above technical problems, the neural based on BP of above-mentioned technical problem is solved the purpose of the present invention is to provide a kind of
Overload of vehicle method of discrimination, system and the device of network.
In order to solve the above technical problems, the overload of vehicle method of discrimination of the invention based on BP neural network, comprising: step
S1 pre-processes overload source data；
Step S2 establishes overload model using BP neural network structure；
Step S3 will be substituted by pretreated overload source data and be obtained load-carrying predicted value in overload model；
If the ratio of load-carrying predicted value and rated load is greater than 1, overload of vehicle is determined；
If the ratio of load-carrying predicted value and rated load is less than or equal to 1, determine that vehicle does not overload.
Step S1 includes:
Step S1.1 obtains the initial data of vehicle；
Step S1.2 divides initial data according to different road types.
In step S1, initial data includes car operation situation, positioning data of vehicles and vehicle bus data.
Step S2 includes:
Step S2.1 establishes input layer, hidden layer and output layer；Wherein
Input layer has n neuron, and hidden layer has p neuron, and output layer has q neuron；
Input vector x=(x1,x2,...,xn)；Hidden layer input vector hi=(hi1,hi2,...,hin)；Hidden layer is defeated
Outgoing vector ho=(xo1,xo2,...,xop)；Output layer input vector yi=(yi1,yi2,...,yiq)；Output layer output vector
Yo=(yo1,yo2,...,yoq)；Desired output vector do=(d1,d2,...,dq)；
Connection weight between h-th of neuron of i-th of neuron of input layer and hidden layer is Wih, h-th of mind of hidden layer
It is W through the connection weight between member and o-th of neuron of output layerho；
The threshold value of each neuron of hidden layer is bIt is hidden, the threshold value of each neuron of output layer is bOut；
Sample data number: k=1,2 ..., m, activation primitive f (x), error function
Wherein, for k-th of sample, do(k) o-th of neuron of desired output vector, yo are indicatedo(k) output layer output vector is indicated
O-th of neuron；
1. initializing；The random number in a section (- 1,1) is assigned respectively to each connection weight, is set error function e, is given
Devise a stratagem calculates accuracy value ε and maximum study number M；
2. randomly select k-th of input sample and corresponding desired output, wherein the value range of k be k=1,2 ...,
M:
X (k)=(x1(k),x2(k),...,xn(k)),do(k)=(d1(k),d2(k),.....,dn(k))
3. x (k) is substituted into following formula, outputting and inputting for each neuron of each layer is calculated:
4. calculating error function to the partial derivative δ of each neuron of output layero(k)
5. calculating error function to the partial derivative δ of each neuron of hidden layerh(k)；
6. the δ for 4. walking calculating using theo(k) connection weight w is corrected with the output of each neuron of hidden layerho(k), if even
The correction value for connecing weight is Δ who(k), learning rate, that is, step-length η is given；
7. the δ for 5. walking calculating using theh(k) and the input parameters revision connection weight of input layer, if connection weight
The correction value of value is Δ wih(k), learning rate, that is, step-length η is given；
8. calculating global error E
It is greater than the maximum times set when error reaches default precision or learns number, then terminates algorithm；Otherwise, under selection
3. one learning sample and corresponding desired output are walked back to the, learn into next round.
Overload source data at least travel speed, acceleration, hypervelocity degree, revolving speed, instantaneous oil consumption, engine load, start
Machine it is expected revolving speed.
A kind of overload of vehicle judgement system, comprising:
Preprocessing module, for being pre-processed to overload source data；
Modeling module, for establishing overload model with BP neural network structure；
Judgment module will substitute by pretreated overload source data and obtain load-carrying predicted value in overload model；
If the ratio of load-carrying predicted value and rated load is greater than 1, overload of vehicle is determined；
If the ratio of load-carrying predicted value and rated load is less than or equal to 1, determine that vehicle does not overload.
A kind of overload of vehicle discriminating gear, comprising: be stored with the memory of overload of vehicle discriminating program and for running vehicle
Overload discriminating program processor, overload of vehicle discriminating program be arranged for carrying out the overload of vehicle based on BP neural network differentiation
The step of method.
Overload of vehicle discriminating program is stored on computer readable storage medium, overload of vehicle discriminating program is held by processor
Row realizes the step of overload of vehicle method of discrimination based on BP neural network.
The present invention is based on the overload of vehicle method of discrimination of BP neural network firstly, collected Various types of data is carried out data
Pretreatment and integration, to obtain source data (including license plate number, time, longitude, latitude, road, the road class of overloading analysis
Type, speed, acceleration, hypervelocity degree, revolving speed, engine load, engine it is expected revolving speed, instantaneous oil consumption, goods weight).So
Afterwards, on the basis of distinguishing haulage time and road type, source data is pressed into haulage time section (daytime and evening) and five kinds of roads
Road type (highway, urban express way, city main roads, city secondary road, city ordinary road) is divided.
It is modeled for every kind of road type using BP neural network in different haulage time sections, obtains each driving behavior of vehicle
Mathematical model between vehicle load compares the payload ratings of specific vehicle, judges the vehicle with the presence or absence of overloading.
Detailed description of the invention
Fig. 1 is that the present invention is based on the overload of vehicle method of discrimination schematic diagrams of BP neural network.
Specific embodiment
Overload of vehicle method of discrimination, system and the device the present invention is based on BP neural network are made into one with reference to the accompanying drawing
Step is described in detail.
As shown in Figure 1, the present invention is based on the overload of vehicle method of discrimination of BP neural network, comprising:
(1) overload source data prepares process
Initial data is positioning data of vehicles (including license plate number, driving time, longitude, latitude, speed etc.), OBD is acquired
CAN bus data (including the time, speed, revolving speed, engine load, engine it is expected revolving speed, instantaneous oil consumption) and vehicle transport
It seeks situation table (including license plate number, vehicle, service time, loading spot, landing place, goods weight).
Positioning data of vehicles, CAN bus data and car operation situation are passed through into data prediction, obtain overload source data
(including license plate number, the time, longitude, latitude, road, road type, speed, acceleration, hypervelocity degree, revolving speed, instantaneous oil consumption,
Engine load, engine it is expected revolving speed, goods weight).Then, on the basis of distinguishing driving time section and road type,
By overloading analysis source data by five kinds of road types (highway, urban express way, city main roads, city time thoroughfare
Road, city ordinary road) it is divided.Obtain the overload sample data on each road type of each period.
(2) foundation of characteristic index variable
In view of vehicle is under different load conditions, driving behavior should be able to difference.According to available data,
Selectable feature is as follows:
Input feature vector X: speed, acceleration, hypervelocity degree, revolving speed, instantaneous oil consumption, engine load, engine expectation turn
Speed.
Export Y: vehicle load
For the source data that data prediction obtains, on the basis of distinguishing road type, the characteristic index that can be chosen is
Vehicle Speed, acceleration, hypervelocity degree, revolving speed, instantaneous oil consumption, engine load, engine it is expected revolving speed.Wherein road
Type is divided into highway, urban express way, city main roads, city secondary road and city ordinary road.If the time
Number of segment mesh t=2, road type number r=5, the characteristic variable number on every kind of road type are x=7.
(3) overload model is established
Neural network model is the network that many logic units are organized according to different levels, each layer of output variable
It is all next layer of input variable.Using most basic BP neural network structural model, input layer is that the overload in content (2) is special
Variable is levied, only one hidden layer, output layer is vehicle load.Steps are as follows for calculating:
If input layer has n neuron, hidden layer has p neuron, and output layer has q neuron；
Input vector x=(x1,x2,...,xn), i.e., are as follows: speed, acceleration, revolving speed, instantaneous oil consumption, is started at hypervelocity degree
Machine load, engine it is expected revolving speed.Hidden layer input vector hi=(hi1,hi2,...,hin), by input vector x and weight group
Conjunction is calculated, and sees formula (5).Hidden layer output vector ho=(xo1,xo2,...,xop), it is substituted into and is motivated by input vector hi
Function is calculated, and sees formula (5).Output layer input vector yi=(yi1,yi2,...,yiq), by vector hoIt is combined with weight
It is calculated, sees formula (6).Output layer output vector yo=(yo1,yo2,...,yoq), excitation letter is substituted by input vector yi
Number is calculated, and sees formula (6).Desired output vector do=(d1,d2,...,dq), vehicle load number as in sample data
According to；
Connection weight between h-th of neuron of i-th of neuron of input layer and hidden layer is Wih, h-th of mind of hidden layer
It is W through the connection weight between member and o-th of neuron of output layerho；
The threshold value of each neuron of hidden layer is bIt is hidden, the threshold value of each neuron of output layer is bOut；
Sample data number: k=1,2 ..., m, activation primitive f (x), error function
Wherein, for k-th of sample, do(k) o-th of neuron of desired output vector, yo are indicatedo(k) output layer output vector is indicated
O-th of neuron.
1. initializing.The random number in a section (- 1,1) is assigned respectively to each connection weight, is set error function e, is given
Devise a stratagem calculates accuracy value ε and maximum study number M.
2. randomly select k-th of input sample and corresponding desired output, wherein the value range of k be k=1,2 ...,
M:
X (k)=(x1(k),x2(k),...,xn(k)),do(k)=(d1(k),d2(k),.....,dn(k))
3. x (k) is substituted into following formula, outputting and inputting for each neuron of each layer is calculated:
4. calculating error function to the partial derivative δ of each neuron of output layero(k)
5. calculating error function to the partial derivative δ of each neuron of hidden layerh(k)。
6. the δ for 4. walking calculating using theo(k) connection weight w is corrected with the output of each neuron of hidden layerho(k), if even
The correction value for connecing weight is Δ who(k), learning rate, that is, step-length η is given.
7. the δ for 5. walking calculating using theh(k) and the input parameters revision connection weight of input layer, if connection weight
The correction value of value is Δ wih(k), learning rate, that is, step-length η is given.
8. calculating global error E
It is greater than the maximum times set when error reaches default precision or learns number, then terminates algorithm.Otherwise, under selection
3. one learning sample and corresponding desired output are walked back to the, learn into next round.
(4) overload model established according to sample data, calculates vehicle load, load-carrying predicted value is obtained, with volume
Constant load compares, and then suspecting the vehicle beyond one times or more, there are overload behaviors.
The present invention also provides a kind of overload of vehicle judgement systems, comprising:
Preprocessing module, for being pre-processed to overload source data；
Modeling module, for establishing overload model with BP neural network structure；
Judgment module will substitute by pretreated overload source data and obtain load-carrying predicted value in overload model；
If the ratio of load-carrying predicted value and rated load is greater than 1, overload of vehicle is determined；
If the ratio of load-carrying predicted value and rated load is less than or equal to 1, determine that vehicle does not overload.
The present invention also provides a kind of overload of vehicle discriminating gears, comprising: is stored with the storage of overload of vehicle discriminating program
Device and processor for running overload of vehicle discriminating program, overload of vehicle discriminating program are arranged for carrying out based on BP neural network
Overload of vehicle method of discrimination the step of.
The present invention also provides overload of vehicle discriminating program is stored on computer readable storage medium, overload of vehicle differentiates
Program is executed by processor the step of realizing the overload of vehicle method of discrimination based on BP neural network.
The preferred embodiment of the present invention has been described in detail above, but the invention be not limited to it is described
Embodiment, those skilled in the art can also make various equivalent on the premise of not violating the inventive spirit of the present invention
Variation or replacement, these equivalent variation or replacement are all included in the scope defined by the claims of the present application.
Claims (8)
1. a kind of overload of vehicle method of discrimination based on BP neural network, including one to the magnanimity in car networking monitoring system
The process that GPS data is handled, it is characterised in that: include: during described
Step S1 pre-processes overload source data；
Step S2 establishes overload model using BP neural network structure；
Step S3 will be substituted by pretreated overload source data and be obtained load-carrying predicted value in overload model；
The load-carrying predicted value that step S3 is obtained is compared with vehicle rated load, thus judge whether overload of vehicle,
When the ratio of load-carrying predicted value and vehicle rated load is greater than 1, overload of vehicle is determined；
When the ratio of load-carrying predicted value and vehicle rated load is less than or equal to 1, determine that vehicle does not overload.
2. the overload of vehicle method of discrimination according to claim 1 based on BP neural network, which is characterized in that step S1 packet
It includes:
Step S1.1 obtains the initial data of vehicle；
Step S1.2 divides initial data according to road type.
3. the overload of vehicle method of discrimination according to claim 2 based on BP neural network, which is characterized in that step S1
In, initial data includes car operation situation, positioning data of vehicles and vehicle bus data.
4. the overload of vehicle method of discrimination according to claim 1 based on BP neural network, which is characterized in that step S2 packet
It includes:
Step S2.1 establishes input layer, hidden layer and output layer；Wherein
Input layer has n neuron, and hidden layer has p neuron, and output layer has q neuron；
Input vector x=(x1,x2,...,xn)；Hidden layer input vector hi=(hi1,hi2,...,hin)；Hidden layer export to
Measure ho=(xo1,xo2,...,xop)；Output layer input vector yi=(yi1,yi2,...,yiq)；Output layer output vector yo=
(yo1,yo2,...,yoq)；Desired output vector do=(d1,d2,...,dq)；
Connection weight between h-th of neuron of i-th of neuron of input layer and hidden layer is Wih, h-th of neuron of hidden layer
Connection weight between o-th of neuron of output layer is Who；
The threshold value of each neuron of hidden layer is bIt is hidden, the threshold value of each neuron of output layer is bOut；
Sample data number: k=1,2 ..., m, activation primitive f (x), error functionWherein,
For k-th of sample, do(k) o-th of neuron of desired output vector, yo are indicatedo(k) o of output layer output vector is indicated
A neuron；
1. initializing；The random number in a section (- 1,1) is assigned respectively to each connection weight, sets error function e, to devise a stratagem
Calculate accuracy value ε and maximum study number M；
2. randomly selecting k-th of input sample and corresponding desired output, wherein the value range of k is k=1,2 ..., m:
X (k)=(x1(k),x2(k),...,xn(k)),do(k)=(d1(k),d2(k),.....,dn(k))
3. x (k) is substituted into following formula, outputting and inputting for each neuron of each layer is calculated:
4. calculating error function to the partial derivative δ of each neuron of output layero(k)
5. calculating error function to the partial derivative δ of each neuron of hidden layerh(k)；
6. the δ for 4. walking calculating using theo(k) connection weight w is corrected with the output of each neuron of hidden layerho(k), if connection weight
The correction value of value is Δ who(k), learning rate, that is, step-length η is given；
7. the δ for 5. walking calculating using theh(k) and the input parameters revision connection weight of input layer, if connection weight is repaired
Positive value is Δ wih(k), learning rate, that is, step-length η is given；
8. calculating global error E
It is greater than the maximum times set when error reaches default precision or learns number, then terminates algorithm；Otherwise, it chooses next
3. learning sample and corresponding desired output are walked back to the, learn into next round.
5. the overload of vehicle method of discrimination according to claim 1 based on BP neural network, which is characterized in that overload source number
Revolving speed it is expected according at least travel speed, acceleration, hypervelocity degree, revolving speed, instantaneous oil consumption, engine load, engine.
6. a kind of overload of vehicle judgement system characterized by comprising
Preprocessing module, for being pre-processed to overload source data；
Modeling module, for establishing overload model with BP neural network structure；
Judgment module will substitute by pretreated overload source data and obtain load-carrying predicted value in overload model；
If the ratio of load-carrying predicted value and rated load is greater than 1, overload of vehicle is determined；
If the ratio of load-carrying predicted value and rated load is less than or equal to 1, determine that vehicle does not overload.
7. a kind of overload of vehicle discriminating gear characterized by comprising be stored with the memory and use of overload of vehicle discriminating program
In the processor of operation overload of vehicle discriminating program, overload of vehicle discriminating program is arranged for carrying out such as any one of Claims 1 to 5
The step of described overload of vehicle method of discrimination based on BP neural network.
8. a kind of computer readable storage medium, which is characterized in that be stored with overload of vehicle on computer readable storage medium and sentence
Other program, it is as claimed in any one of claims 1 to 5 based on BP nerve net that overload of vehicle discriminating program is executed by processor realization
The step of overload of vehicle method of discrimination of network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811213520.5A CN109377046A (en) | 2018-10-18 | 2018-10-18 | Overload of vehicle method of discrimination, system and device based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811213520.5A CN109377046A (en) | 2018-10-18 | 2018-10-18 | Overload of vehicle method of discrimination, system and device based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109377046A true CN109377046A (en) | 2019-02-22 |
Family
ID=65400215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811213520.5A Pending CN109377046A (en) | 2018-10-18 | 2018-10-18 | Overload of vehicle method of discrimination, system and device based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109377046A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147910A (en) * | 2019-05-24 | 2019-08-20 | 福建工程学院 | A kind of bus car crowding real-time predicting method based on BP neural network |
| CN110406539A (en) * | 2019-07-22 | 2019-11-05 | 杭州鸿泉物联网技术股份有限公司 | A kind of method and device identifying vehicle load state |
| CN111546890A (en) * | 2020-05-19 | 2020-08-18 | 四川万网鑫成信息科技有限公司 | Method for identifying truck overload behavior based on Internet of vehicles terminal |
| CN113421434A (en) * | 2021-06-29 | 2021-09-21 | 福建交科信通科技有限公司 | Overrun overload rate calculation method for road ultra-control off-site law enforcement |
| CN114386892A (en) * | 2021-11-30 | 2022-04-22 | 江铃汽车股份有限公司 | Transportation vehicle load management method, system, storage medium and equipment |
| CN115729189A (en) * | 2022-11-21 | 2023-03-03 | 无锡雪浪数制科技有限公司 | Production control method integrating data model and mechanism model |
| CN116152757A (en) * | 2023-04-18 | 2023-05-23 | 深圳亿维锐创科技股份有限公司 | Weighing data analysis method and related device based on multiple points |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234610A (en) * | 2013-05-14 | 2013-08-07 | 湖南师范大学 | Weighing method applicable to truck scale |
| CN104089690A (en) * | 2014-07-02 | 2014-10-08 | 江苏大学 | Toll station vehicle dynamic weighing estimation method and device |
| CN106095963A (en) * | 2016-06-17 | 2016-11-09 | 上海经达信息科技股份有限公司 | Vehicle drive behavior analysis big data public service platform under the Internet+epoch |
| CN108225502A (en) * | 2017-12-06 | 2018-06-29 | 中南大学 | A kind of truck loads ore quality method of estimation and system |
-
2018
- 2018-10-18 CN CN201811213520.5A patent/CN109377046A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234610A (en) * | 2013-05-14 | 2013-08-07 | 湖南师范大学 | Weighing method applicable to truck scale |
| CN104089690A (en) * | 2014-07-02 | 2014-10-08 | 江苏大学 | Toll station vehicle dynamic weighing estimation method and device |
| CN106095963A (en) * | 2016-06-17 | 2016-11-09 | 上海经达信息科技股份有限公司 | Vehicle drive behavior analysis big data public service platform under the Internet+epoch |
| CN108225502A (en) * | 2017-12-06 | 2018-06-29 | 中南大学 | A kind of truck loads ore quality method of estimation and system |
Non-Patent Citations (1)
| Title |
|---|
| 郝晓娴: "车载动态治超监控系统的研究与设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147910A (en) * | 2019-05-24 | 2019-08-20 | 福建工程学院 | A kind of bus car crowding real-time predicting method based on BP neural network |
| CN110406539A (en) * | 2019-07-22 | 2019-11-05 | 杭州鸿泉物联网技术股份有限公司 | A kind of method and device identifying vehicle load state |
| CN111546890A (en) * | 2020-05-19 | 2020-08-18 | 四川万网鑫成信息科技有限公司 | Method for identifying truck overload behavior based on Internet of vehicles terminal |
| CN113421434A (en) * | 2021-06-29 | 2021-09-21 | 福建交科信通科技有限公司 | Overrun overload rate calculation method for road ultra-control off-site law enforcement |
| CN114386892A (en) * | 2021-11-30 | 2022-04-22 | 江铃汽车股份有限公司 | Transportation vehicle load management method, system, storage medium and equipment |
| CN115729189A (en) * | 2022-11-21 | 2023-03-03 | 无锡雪浪数制科技有限公司 | Production control method integrating data model and mechanism model |
| CN115729189B (en) * | 2022-11-21 | 2024-02-27 | 无锡雪浪数制科技有限公司 | Production control method integrating data model and mechanism model |
| CN116152757A (en) * | 2023-04-18 | 2023-05-23 | 深圳亿维锐创科技股份有限公司 | Weighing data analysis method and related device based on multiple points |
| CN116152757B (en) * | 2023-04-18 | 2023-07-07 | 深圳亿维锐创科技股份有限公司 | Weighing data analysis method and related device based on multiple points |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109377046A (en) | Overload of vehicle method of discrimination, system and device based on BP neural network | |
| Siami-Irdemoosa et al. | Prediction of fuel consumption of mining dump trucks: A neural networks approach | |
| CN113380033B (en) | Urban traffic safety early warning method and system based on man-machine hybrid enhanced intelligence | |
| CN109493566B (en) | Fatigue driving prediction method based on GPS data | |
| Tadić et al. | Assessment of the political city logistics initiatives sustainability | |
| CN106127586A (en) | Vehicle insurance rate aid decision-making system under big data age | |
| CN102289928A (en) | Integrated traffic hub operation situation evaluation method based on FAHP (fuzzy analytic hierarchy process) | |
| CN106095963A (en) | Vehicle drive behavior analysis big data public service platform under the Internet+epoch | |
| CN113988476A (en) | Dynamic assessment prediction method for road transportation safety risk | |
| CN113033840B (en) | Method and device for judging highway maintenance | |
| Yu et al. | Short-term traffic flow prediction based on deep learning network | |
| CN110324336B (en) | Internet of vehicles data situation sensing method and device based on network security | |
| Zhao et al. | Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots | |
| CN113887872A (en) | Traffic risk classification method based on situation assessment technology | |
| CN112929827B (en) | Method, device and medium for monitoring discharge of construction waste | |
| Wang et al. | Causation analysis of crashes and near crashes using naturalistic driving data | |
| Matveev et al. | Intelligent decision support system for transportation emergency response | |
| Shi et al. | Applying a WNN-HMM based driver model in human driver simulation: Method and test | |
| Soofastaei | The application of artificial intelligence to reduce greenhouse gas emissions in the mining industry | |
| Mohanty et al. | Development of crash prediction models by assessing the role of perpetrators and victims: a comparison of ANN & logistic model using historical crash data | |
| CN110610326A (en) | Driving management system based on driving data | |
| Pei et al. | Safety Assessment and Risk Management of Urban Arterial Traffic Flow Based on Artificial Driving and Intelligent Network Connection: An Overview | |
| Mussa et al. | Probabilistic neural networks application for vehicle classification | |
| Bhuiyan et al. | Investigating the impact of access-timing-sizing regulations on urban logistics | |
| CN107169202A (en) | A kind of computational methods kept at a distance safely between traveling vehicle |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190222 |
|
| RJ01 | Rejection of invention patent application after publication |