CN113340392B - Vehicle load detection method and device based on acceleration sensor - Google Patents
Vehicle load detection method and device based on acceleration sensor Download PDFInfo
- Publication number
- CN113340392B CN113340392B CN202110834201.1A CN202110834201A CN113340392B CN 113340392 B CN113340392 B CN 113340392B CN 202110834201 A CN202110834201 A CN 202110834201A CN 113340392 B CN113340392 B CN 113340392B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- acceleration
- database
- running
- data
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/08—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for incorporation in vehicles
- G01G19/086—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for incorporation in vehicles wherein the vehicle mass is dynamically estimated
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a vehicle load detection method and device based on an acceleration sensor, wherein the vehicle load detection method based on the acceleration sensor comprises the following steps: establishing a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle; establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model; and detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle. According to the invention, real-time weight measurement can be realized in the running process of the vehicle, so that the high-speed passing efficiency can be improved on one hand; on the other hand, by installing the vibration sensor on the vehicle, weight estimation can be carried out in different areas based on the same equipment, errors caused by different weight measurement equipment are avoided, and unified supervision of the vehicle weight is facilitated for related departments.
Description
Technical Field
The invention relates to the technical field of application of vehicle-mounted sensors and traffic information processing, in particular to a vehicle load detection method and device based on an acceleration sensor.
Background
Aiming at the vehicle load detection technology, in the prior art, weighing equipment is arranged at a toll gate of a highway junction and part of highway entrances, so that the load condition of a truck on a highway is monitored, the highway surface is maintained, and the accident risk of a large truck is reduced. The method for weighing the vehicle by the weighing equipment arranged at the expressway requires that the vehicle is in a static state to obtain a relatively accurate weighing result, and on one hand, the weighing method has great influence on the vehicle passing efficiency of the expressway; in addition, because weighing equipment errors of different high-speed intersections are different, the problem of different bayonet weighing results exists, and effective supervision of the vehicle load is not facilitated; on the other hand, with the innovation of toll road system and the implementation of highway ETC, the weighing system of the toll station at the expressway is about to be banned, so that an efficient and relatively accurate method for estimating the weight of the vehicle is needed to be found so as to realize effective supervision on the load condition of the vehicle.
In recent years, with the rapid development of the concept of intelligent transportation, researchers have begun to fully mine the use of vehicle-mounted sensors, collect data by the sensors, and implement various driving assistance applications by carrying algorithms on vehicles.
The main methods of weighing vehicles, which are currently realized by mounting sensors on the vehicles, include a laminated spring deformation measurement method and a tire pressure variation measurement method. According to the load measuring method based on deformation of the laminated spring of the automobile, the deformation quantity of the spring is detected by arranging ultrasonic sensors at the centers of the front axle and the rear axle of the automobile, and the load of the automobile is indirectly calculated by means of a mechanical model; according to the load measuring method based on the tire pressure, the deformation of the automobile tire is detected by installing a temperature sensor and a pressure sensor in the tire, so that the load of the automobile is calculated. Both methods can acquire the load of the vehicle, but have the common problems of high requirements on the installation position of equipment, high installation difficulty and high weight measurement cost. The ultrasonic sensor needs to be provided with equipment at the center of a front axle and a rear axle of the vehicle at the same time, and the ultrasonic sensor needs to be calibrated manually; the tire pressure-based weight measurement method requires the installation of sensors in the tires of the vehicle, and is difficult to maintain in the later period. These all present a significant impediment to the promotion of such weight measurement methods. In addition, the two measuring methods are greatly affected by temperature, the propagation speed of ultrasonic waves and the deformation of the tire are sensitive to the environmental temperature, so that the calculation for measuring the load of the automobile is more complex, and the accuracy is greatly reduced.
Disclosure of Invention
Aiming at the problems in the prior art, the vehicle load detection method and device based on the acceleration sensor can realize real-time weight measurement in the running process of the vehicle, and can improve the high-speed passing efficiency on one hand; on the other hand, by installing the vibration sensor on the vehicle, weight estimation can be carried out in different areas based on the same equipment, errors caused by different weight measurement equipment are avoided, and unified supervision of the vehicle weight is facilitated for related departments.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the present invention provides a vehicle load detection method based on an acceleration sensor, including:
establishing a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle;
establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
and detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle.
In an embodiment, the building a type database, a driving state database and an acceleration model of the vehicle according to the GPS positioning data and the three-dimensional acceleration data of the vehicle includes:
Calculating the running speed of the vehicle according to the GPS positioning data and the corresponding time stamp thereof;
respectively determining the vehicle advancing direction, the vehicle transverse direction and the acceleration change rate in the gravity direction according to the running speed and a preset vehicle-mounted acceleration sensor;
and based on the model data of the vehicle, utilizing the acceleration change rate to represent the vibration condition of the vehicle so as to establish the type database and the running state database.
In an embodiment, the establishing a parameter database of vehicles with different types and different running states according to the type database, the running state database and the acceleration model includes:
extracting the driving state characteristics of the vehicle according to the driving state database in a time window mode;
and establishing the parameter database according to the driving state characteristics and the acceleration model.
In one embodiment, the detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle includes:
collecting running data of the target vehicle in real time;
comparing the driving data in the type database, the driving state database and the parameter database to determine the parameters corresponding to the target vehicle;
And detecting the load of the target vehicle in real time according to the parameters.
In a second aspect, the present invention provides a vehicle load detection device based on an acceleration sensor, including:
the model building module is used for building a type database, a driving state database and an acceleration model of the vehicle according to the GPS positioning data and the three-dimensional acceleration data of the vehicle;
the parameter library establishing module is used for establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
and the load detection module is used for detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle.
In one embodiment, the model building module includes:
a running speed calculation unit for calculating the running speed of the vehicle according to the GPS positioning data and the corresponding time stamp thereof;
the change rate establishing unit is used for respectively determining the acceleration change rates in the vehicle advancing direction, the vehicle transverse direction and the gravity direction according to the running speed and a preset vehicle-mounted acceleration sensor;
and the database establishing unit is used for utilizing the acceleration change rate to represent the vibration condition of the vehicle based on the model data of the vehicle so as to establish the type database and the driving state database.
In one embodiment, the parameter library building module includes:
the feature extraction unit is used for extracting the running state features of the vehicle according to the running state database in a time window mode;
and the parameter database establishing unit is used for establishing the parameter database according to the driving state characteristics and the acceleration model.
In one embodiment, the load detection module includes:
the driving data acquisition unit is used for acquiring driving data of the target vehicle in real time;
the parameter determining unit is used for comparing the driving data in the type database, the driving state database and the parameter database to determine the parameters corresponding to the target vehicle;
and the load detection unit is used for detecting the load of the target vehicle in real time according to the parameters.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of a vehicle load detection method based on an acceleration sensor when the program is executed by the processor.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a vehicle load detection method based on an acceleration sensor.
As can be seen from the above description, the vehicle load detection method and device based on the acceleration sensor according to the embodiments of the present invention first establishes a type database, a driving state database and an acceleration model of a vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle; then, establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model; and finally, detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle. According to the invention, real-time weight measurement can be realized in the running process of the vehicle, and the high-speed passing efficiency is improved; the vibration sensor is arranged on the vehicle, and weight estimation is carried out on the basis of the same equipment in different areas, so that errors caused by different weight measurement equipment are avoided, and unified supervision of the vehicle weight is facilitated for related departments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a vehicle load detection method based on an acceleration sensor in an embodiment of the invention;
FIG. 2 is a schematic diagram of the actuation of truck NKR552/555 in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of step 100 in an embodiment of the invention;
FIG. 4 is a schematic flow chart of spectral clustering on vehicle sample data in an embodiment of the invention;
FIG. 5 is a flow chart of step 200 in an embodiment of the invention;
FIG. 6 is a flow chart of step 300 in an embodiment of the invention;
FIG. 7 is a flow chart of a method for detecting load of a vehicle based on an acceleration sensor in an embodiment of the invention;
FIG. 8 is a frame diagram of data collection and storage and construction of a vehicle type library and a model parameter library in a specific application example of the present invention;
FIG. 9 is a flowchart of constructing a model parameter library based on pre-experimental data for different driving states of a vehicle in a specific application example of the present invention;
FIG. 10 is a flowchart of a load estimation process based on data recorded during a certain trip of a vehicle after a vehicle type database and a parameter set database are established
Fig. 11 is a graph showing a comparison between an actual weight of a vehicle and an estimated result when a sliding window size t=15 minutes in an embodiment of the present invention;
Fig. 12 is a block diagram showing a structure of a vehicle load detection device based on an acceleration sensor in the embodiment of the present invention;
FIG. 13 is a schematic diagram of a model building block 10 according to an embodiment of the invention;
FIG. 14 is a schematic diagram of the structure of the parameter library creating module 20 in the embodiment of the present invention;
fig. 15 is a schematic structural diagram of a load detection module 30 in a specific application example of the present invention;
fig. 16 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
An embodiment of the present invention provides a specific implementation manner of a vehicle load detection method based on an acceleration sensor, referring to fig. 1, the method specifically includes the following steps:
Step 100: and establishing a type database, a driving state database and an acceleration model of the vehicle according to the GPS positioning data and the three-dimensional acceleration data of the vehicle.
Specifically, based on GPS positioning data and vehicle three-dimensional acceleration information acquired by an acceleration sensor, classification of different types of vehicles is realized, and classification is further carried out according to the running state of the vehicles.
And constructing an acceleration model based on the running state of the vehicle and the position information of the vehicle. The automobile is subjected to the combined action of traction force and resistance in normal forward running, and the combined action is expressed as:
F t -f resistance resistor ＝ma x (1)
Wherein F is t For driving the car, f Resistance resistor Is used in the running process of the automobileResistance to rolling force F f Air resistance F w Slope resistance F g Etc.
Driving force F of automobile t With respect to the gear G, vehicle model M and speed of the vehicle, reference is made to fig. 2, which shows a vehicle drive diagram showing the relationship between vehicle drive force and vehicle gear and speed for a certain model of truck.
Considering the sensor acquisition errors and correction factors, there are:
wherein C is a constant, and the vehicle speed, the vehicle acceleration error and the like acquired by the GPS positioning device and the acceleration sensor are corrected.
In practical application, vehicle data in normal progress is screened out firstly based on acceleration in the y direction, and then the vehicle weight is estimated further based on the model.
Step 200: and establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model.
It will be appreciated that these parameters refer to solving unknowns in the formula, i.e., the magnitude of C, which is Ft (vehicle driving force) for different types of vehicles at different speeds and accelerations. In the implementation of step 200, a model parameter database is specifically built for vehicles of different types and different driving states through a plurality of pre-experiments. In a pre-experiment, the model, the running state, the environmental characteristics and the corresponding total weight of the vehicle are recorded, the vehicle is classified according to the spectral clustering according to the method of the first part, a model is built, data are divided according to the running environment and the state of the vehicle in each class, model parameters are solved, and a built parameter database is stored in a cloud.
Step 300: and detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle.
Specifically, characteristics such as a vehicle vibration mode, a vehicle model and the like are extracted from vehicle data in real time, and are compared with a model type database, a driving state database and vehicles in an acceleration model, and parameters are selected from a model library in combination with vehicle speed, acceleration in the x direction of the vehicle, altitude change and the like; setting a time sliding window threshold T, intercepting the data of the current time and T time units before the current time at each time point, and estimating the weight of the vehicle in real time based on the selected parameters; the weight of the vehicle over a journey is determined comprehensively from real-time estimation results.
As can be seen from the above description, the vehicle load detection method based on the acceleration sensor provided by the embodiment of the invention firstly uses the triaxial acceleration sensor and the GPS positioning device to collect acceleration information, speed and position information in a large number of vehicle driving processes, constructs a vehicle information database, classifies vehicles according to vehicle models, driving environments and the like based on a spectral clustering method, respectively constructs model parameter libraries for different types, selects different parameters based on driving states of the vehicles, measures vehicle weights in real time based on data acquired in the driving processes, and realizes vehicle load supervision.
The innovation points of the invention include: 1) The traditional vehicle load detection method based on the acceleration sensor is often combined with other sensors for detecting the deformation of the vehicle, so that small difficulties are brought to the installation and popularization of detection equipment. 2) The traditional vehicle load detection method based on the sensor has larger error and cannot carry out high-distinction load detection, and the method provided by the invention can almost reach estimation error within 10%. 3) The method provided by the invention can realize real-time weight measurement in the running process of the vehicle and improve the high-speed passing efficiency; the vibration sensor is arranged on the vehicle, and weight estimation is carried out on the basis of the same equipment in different areas, so that errors caused by different weight measurement equipment are avoided, and unified supervision of the vehicle weight is facilitated for related departments.
In one embodiment, referring to fig. 3, step 100 specifically includes:
step 101: calculating the running speed of the vehicle according to the GPS positioning data and the corresponding time stamp thereof;
based on GPS positioning data and vehicle three-dimensional acceleration information acquired by an acceleration sensor, classification of different types of vehicles is realized, and classification is further carried out according to the running state of the vehicles. And acquiring the longitude and latitude position of the vehicle according to the GPS positioning device of the vehicle, and calculating the running speed v of the vehicle by combining the time stamp of the position.
Step 102: respectively determining the vehicle advancing direction, the vehicle transverse direction and the acceleration change rate in the gravity direction according to the running speed and a preset vehicle-mounted acceleration sensor;
based on step 101, vehicle forward direction acceleration a is acquired based on an in-vehicle acceleration sensor x Transverse direction a of vehicle body y Direction of gravity a z And time stamp, calculate the rate of change of acceleration of three directions, record as a respectively x ′、a y ′、a z ′；
Step 103: and based on the model data of the vehicle, utilizing the acceleration change rate to represent the vibration condition of the vehicle so as to establish the type database and the running state database.
Specifically, vehicles of different models are tracked, and a database of related data in the running process of the vehicles is built. Because the vibration frequencies and the like of the vehicles in different types and load states have larger differences when the vehicles run, the running states of the vehicles, the environments where the vehicles are located and the vibration conditions of the vehicles in the running process of the vehicles are taken as characteristics, the classification of the vehicles in different types and the running states is realized based on a spectral clustering method, and the classification types comprise the following steps: and parameters are respectively set according to classification results, such as a medium-sized truck which runs straight at a high speed on a slow slope, a small-sized truck which turns left at a low speed on a slow slope, and the like.
Referring to FIG. 4, further, the input of spectral clustering includes a sample dataset, clustered dimension k 2 Sample set d= { x 1 ,x 2 ,…,x n Consists of sample data sets of different vehicles. A piece of vehicle sample data x i (i=1, 2, …, n) includes vehicle id, vehicleVehicle model X, speed (v x ,v y ,v z ) Speed (a) x ,a y ,a z ) Acceleration (a' x ,a′ y ,a′ z ) Longitude, latitude, altitude (long, lat, ele), etc. And setting the dimension after clustering as k, wherein k can be determined according to inflection points among types after the specific data sets are classified. The result of spectral clustering is a cluster division result C= { C of the sample 1 ,c 2 ,…,c k }。
The spectrum clustering process comprises the following steps: constructing a similarity matrix S according to a sample set D of vehicle driving data; constructing an adjacent matrix W according to the similarity matrix S, wherein the construction degree matrix d is a diagonal matrix; calculating a Laplace matrix L of the data set; based on the degree matrix d, constructing a standardized Laplace matrix d -1/2 Ld -1/2 The method comprises the steps of carrying out a first treatment on the surface of the Setting dimension k of matrix after dimension reduction 1 Calculate d -1/2 Ld -1/2 Minimum k 1 The feature vectors f corresponding to the feature values respectively; the matrix composed of the corresponding characteristic vectors f is standardized according to the rows, and finally n multiplied by k is composed 1 A feature matrix F of the dimension; let n rows in F be k 1 N samples of the dimension are clustered by using an input clustering method, and the clustering dimension is k; obtaining a cluster division result C= { C of the vehicle type and the running state 1 ,c 2 ,…,c k Each of which represents a running state of a certain model vehicle.
In one embodiment, referring to fig. 5, step 200 specifically includes:
step 201: extracting the driving state characteristics of the vehicle according to the driving state database in a time window mode;
step 202: and establishing the parameter database according to the driving state characteristics and the acceleration model.
In step 201 and step 202, the travel is divided by time, and the average speed, acceleration, change rate of acceleration, altitude change, and the like of each travel are used as features to further classify the running state of the vehicle and extract the relevant features. Then, the relevant characteristic value of each stroke is input into a model, the recorded actual weight of the vehicle is taken as a true value, and the model is obtained by solvingSets of unknown parameter solutions in the pattern (F t (y)，And finally, filtering out unreasonable parameter solutions according to the actual meaning of the parameters, and storing the average value of all reasonable parameter groups of a certain type of vehicle in a running state as an effective model parameter into a model parameter library to form a parameter database.
In one embodiment, referring to fig. 6, step 300 specifically includes:
step 301: collecting running data of the target vehicle in real time;
Step 302: comparing the driving data in the type database, the driving state database and the parameter database to determine the parameters corresponding to the target vehicle;
step 303: and detecting the load of the target vehicle in real time according to the parameters.
In steps 301 to 303, data of speed, acceleration, position and altitude in the running process of the vehicle are recorded in real time by installing a GPS positioning device, an acceleration sensor and communication equipment on the vehicle; screening vehicle data records in a normal straight running state according to the acceleration of the vehicle in the y direction, and screening data in a specific range according to the vehicle speed; extracting characteristics such as vehicle vibration modes, vehicle models and the like from vehicle data in real time, comparing the characteristics with vehicles in a model library, and selecting parameters from the model library by combining vehicle speed, acceleration in the x direction of the vehicle, altitude change and the like; setting a time sliding window threshold T, intercepting the data of the current time and T time units before the current time at each time point, and estimating the weight of the vehicle in real time based on the selected parameters; the weight of the vehicle over a journey is determined comprehensively from real-time estimation results. Based on the load estimation result and the type of the vehicle divided by the first part, the load conditions of the vehicle are classified, the load comprises various conditions such as no-load, normal load, overload, serious overload and the like, if the load is overload or serious overload, an early warning is sent to a data center, and a driver and related departments are contacted through the data center, so that the purpose of effective supervision is achieved.
As can be seen from the above description, the vehicle load detection method based on the acceleration sensor provided by the embodiment of the invention mainly includes four parts, wherein the first part is to construct a vehicle classification library, and based on basic information such as vehicle types, GPS positioning data and vehicle three-dimensional acceleration information acquired by the acceleration sensor, classification of different types of vehicles is realized; the second part is to construct acceleration models for different types of vehicles according to the running state of the vehicles, the environment of the vehicles and the like; the third part is used for respectively establishing a model parameter database for different types of vehicles, and during the weight estimation, firstly realizing the classification of the current vehicles according to the method of the first part in each section of journey, judging the running state of the vehicles according to the types, the driving states and the environments of the vehicles, and selecting proper parameters from the model parameter database; and a fourth part, setting a time sliding window, realizing the weight estimation by using data acquired in one section of travel of the vehicle in real time, and giving the load state of the vehicle according to the detection result of the load of the vehicle, wherein the load state comprises various different conditions such as no-load, normal load, overload, serious overload and the like, and giving warning for the overload and the serious overload.
To further explain the present embodiment, the present invention provides a specific application example of the vehicle load detection method based on the acceleration sensor, which specifically includes the following, see fig. 7.
S1: and constructing a vehicle type database and a model parameter library.
Referring to fig. 8, step S1 further includes: the vehicle-mounted GPS positioning device is used for acquiring the position data of the vehicle, the three-axis acceleration sensor is used for acquiring the acceleration of the vehicle in three directions, and the corresponding data acquisition time is recorded. The in-vehicle apparatus calculates a real-time vehicle speed v based on the time stamp and the position data, and calculates a real-time vehicle speed v based on the time stamp and the vehicle acceleration a x 、a y 、a z Calculating acceleration a of vehicle acceleration x ′、a y ′、a z And', storing the data as basic information records of the vehicle and sending the basic information records to the cloud. Based on the basic model information of the vehicle and the vibration condition of the vehicle recorded by the acceleration sensor, the classification of the vehicle is realized by adopting a spectral clustering mode, and a vehicle type database is established. General purpose medicineAnd after a large number of pre-experiments, the recorded information such as the basic running state, running environment, actual total weight of the vehicle and the like of the vehicle are classified according to the type and running state of the vehicle, a model is built for each type, parameters are solved, and a model parameter library of different types is built.
S2: and constructing a vehicle model parameter library under different driving states.
Referring to fig. 9, step S2 further includes:
step S201: the vehicle-mounted GPS positioning and acceleration sensor is used for acquiring data of the running state and the running environment of the vehicle as characteristics, and weighing equipment such as a wagon balance is used for acquiring the total weight of the vehicle as a true value to be used as a pre-experiment data set.
Step S202: and (3) carrying out basic pretreatment on the data set, and screening out abnormal data.
Step S203: and classifying the vehicle types by using a spectral clustering method.
Step S204, dividing the strokes according to time, taking the average speed, the acceleration, the change rate of the acceleration, the change of the altitude and the like of each stroke as characteristics, further classifying the running state of the vehicle, and extracting related characteristics.
Step S205: inputting the related characteristic values of each stroke into a model, taking the recorded actual weight of the vehicle as a true value, and solving to obtain a plurality of groups of unknown parameter solutions in the model
Step 206: according to the actual meaning of the parameters, unreasonable parameter solutions are filtered, and the average value of all reasonable parameter sets of a certain type of vehicle in a running state is used as an effective model parameter and is stored in a model parameter library.
S3: and estimating the load of the target vehicle corresponding to the journey record according to the journey record of the target vehicle.
Referring to fig. 10, step S3 further includes:
step S301: cloud acquires acceleration a of vehicle in three directions x ，a y ，a z Vehicle speed v x Vehicle position, altitude becomeChemical, basic information, etc.
Step S302: and according to the basic information of the vehicle, matching the basic information of the vehicle with the data related to the vehicle stored in the vehicle type library, and confirming the type of the current vehicle.
Step S303: screening data a y Data close to 0 confirms that the vehicle is in a normal straight-going, non-turning state.
Step S304: a time window threshold T is set and characteristics of the vehicle at a certain moment are obtained from the data of the vehicle at the moment and within the previous T time units. The average value of the speed, acceleration, and the like of the vehicle in T time units before the time is used as the running state characteristic, and the position, altitude change, and the like of the vehicle are used as the running environment characteristic.
Step S305: and selecting matched parameters from the model parameter library to solve the estimated weight based on the acquired vehicle driving characteristics.
Step S306: the weight of the vehicle in a certain journey is finally determined by the average value of the effective estimated weight in the whole journey.
Fig. 11 and table 1 show the results of a test on vehicle weight and on full range travel in real time. In this experiment, four sections of data of different load strokes of a certain truck are obtained, part of the data is used as pre-experiment data, model parameters are solved based on the pre-experiment data, and then, for other data, T=15min is used as a sliding window size, proper y-direction acceleration threshold is set for screening data of a vehicle straight-running state, errors of four sections of stroke estimation results and true values are shown in table 1 (the true value weight and the estimation result of a medium truck are divided according to strokes), and estimated weight and actual weight at each moment are shown in fig. 11.
TABLE 1
| Travel distance | True value (kg) | Estimation value (kg) | Error of |
| 1 | 17800 | 18033.58 | 1.31％ |
| 2 | 11840 | 12809.02 | 8.18％ |
| 3 | 17500 | 17071.68 | 2.45％ |
| 4 | 11780 | 12495.93 | 6.08％ |
As can be seen from the above description, the vehicle load detection method based on the acceleration sensor provided by the embodiment of the present application firstly establishes a type database, a driving state database and an acceleration model of a vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle; then, establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model; and finally, detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle. According to the application, real-time weight measurement can be realized in the running process of the vehicle, and the high-speed passing efficiency is improved; the vibration sensor is arranged on the vehicle, and weight estimation is carried out on the basis of the same equipment in different areas, so that errors caused by different weight measurement equipment are avoided, and unified supervision of the vehicle weight is facilitated for related departments.
Based on the same inventive concept, the embodiment of the present application also provides a vehicle load detection device based on an acceleration sensor, which can be used to implement the method described in the above embodiment, such as the following embodiment. The principle of solving the problem of the vehicle load detection device based on the acceleration sensor is similar to that of the vehicle load detection method based on the acceleration sensor, so that the implementation of the vehicle load detection device based on the acceleration sensor can be implemented by referring to the vehicle load detection method based on the acceleration sensor, and repeated parts are omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
An embodiment of the present invention provides a specific embodiment of an acceleration sensor-based vehicle load detection apparatus capable of implementing an acceleration sensor-based vehicle load detection method, referring to fig. 12, the acceleration sensor-based vehicle load detection apparatus specifically includes:
the model building module 10 is used for building a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle;
the parameter library establishing module 20 is configured to establish parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
and the load detection module 30 is used for detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle.
In one embodiment, referring to fig. 13, the modeling module 10 includes:
a running speed calculating unit 101, configured to calculate a running speed of the vehicle according to the GPS positioning data and the corresponding timestamp thereof;
a change rate establishing unit 102, configured to determine acceleration change rates in a vehicle forward direction, a vehicle lateral direction, and a gravity direction according to the running speed and a preset vehicle-mounted acceleration sensor, respectively;
A database creation unit 103 for characterizing the vibration condition of the vehicle using the acceleration change rate based on the model data of the vehicle to create the type database and the running state database.
In one embodiment, referring to fig. 14, the parameter library creating module 20 includes:
a feature extraction unit 201, configured to extract a driving state feature of the vehicle according to the driving state database in a time window manner;
and a parameter database establishing unit 202, configured to establish the parameter database according to the driving state feature and the acceleration model.
In one embodiment, referring to fig. 15, the load detection module 30 includes:
a driving data acquisition unit 301, configured to acquire driving data of the target vehicle in real time;
a parameter determining unit 302, configured to compare the driving data in the type database, the driving state database, and the parameter database, so as to determine a parameter corresponding to the target vehicle;
and the load detection unit 303 is used for detecting the load of the target vehicle in real time according to the parameters.
As can be seen from the above description, the vehicle load detection device based on the acceleration sensor according to the embodiments of the present invention first establishes a type database, a driving state database and an acceleration model of a vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle; then, establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model; and finally, detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle. According to the invention, real-time weight measurement can be realized in the running process of the vehicle, and the high-speed passing efficiency is improved; the vibration sensor is arranged on the vehicle, and weight estimation is carried out on the basis of the same equipment in different areas, so that errors caused by different weight measurement equipment are avoided, and unified supervision of the vehicle weight is facilitated for related departments.
The embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all the steps in the vehicle load detection method based on an acceleration sensor in the foregoing embodiment, and referring to fig. 16, the electronic device specifically includes the following contents:
a processor 1201, a memory 1202, a communication interface (Communications Interface) 1203, and a bus 1204;
wherein the processor 1201, the memory 1202 and the communication interface 1203 perform communication with each other through the bus 1204; the communication interface 1203 is used to implement information transmission between related devices such as server-side devices, sensors, and client devices.
The processor 1201 is configured to invoke a computer program in the memory 1202, and when the processor executes the computer program, the processor implements all the steps in the acceleration sensor-based vehicle load detection method in the above embodiment, for example, when the processor executes the computer program, the processor implements the following steps:
step 100: establishing a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle;
step 200: establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
Step 300: and detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle.
The embodiment of the present application also provides a computer-readable storage medium capable of realizing all the steps in the acceleration sensor-based vehicle load detection method in the above embodiment, on which a computer program is stored, which when executed by a processor realizes all the steps in the acceleration sensor-based vehicle load detection method in the above embodiment, for example, the processor realizes the following steps when executing the computer program:
step 100: establishing a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle;
step 200: establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
step 300: and detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a hardware+program class embodiment, the description is relatively simple, as it is substantially similar to the method embodiment, as relevant see the partial description of the method embodiment.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A vehicle load detection method based on an acceleration sensor, characterized by comprising:
establishing a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle;
establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle;
the building of a type database, a driving state database and an acceleration model of the vehicle according to GPS positioning data and three-dimensional acceleration data of the vehicle comprises the following steps:
based on GPS positioning data and vehicle three-dimensional acceleration information acquired by an acceleration sensor, different types of vehicles are classified, and the vehicles are further classified according to the running states of the vehicles;
constructing an acceleration model based on the running state of the vehicle and the position information of the vehicle; the automobile is subjected to the combined action of traction force and resistance in normal forward running, and the combined action is expressed as:
F t -f resistance resistor ＝ma x (1)
Wherein F is t For driving the car, f Resistance resistor For the resistance applied during the running of the automobile, the resistance applied during the running of the automobile comprises rolling resistance F f Air resistance F w Slope resistance;
driving force F of automobile t Regarding the gear G, the vehicle model M and the vehicle speed of the automobile, the relation between the driving force of the truck and the gear and the vehicle speed of the automobile in a certain model is shown in the formula (2)
Considering the sensor acquisition errors and correction factors, there are:
c is a constant, the vehicle speed and the vehicle acceleration errors acquired by the GPS positioning device and the acceleration sensor are corrected, further, vehicle data in normal progress are screened out firstly based on acceleration in the y direction, and further, the vehicle weight is estimated based on a formula (1) and a formula (2).
2. The vehicle load detection method according to claim 1, wherein the building of a type database, a running state database, and an acceleration model of the vehicle from the GPS positioning data and the three-dimensional acceleration data of the vehicle includes:
calculating the running speed of the vehicle according to the GPS positioning data and the corresponding time stamp thereof;
respectively determining the vehicle advancing direction, the vehicle transverse direction and the acceleration change rate in the gravity direction according to the running speed and a preset vehicle-mounted acceleration sensor;
and based on the model data of the vehicle, utilizing the acceleration change rate to represent the vibration condition of the vehicle so as to establish the type database and the running state database.
3. The vehicle load detection method according to claim 1, wherein the building of the parameter database of the vehicles of different types and different running states from the type database, the running state database, and the acceleration model includes:
extracting the driving state characteristics of the vehicle according to the driving state database in a time window mode;
and establishing the parameter database according to the driving state characteristics and the acceleration model.
4. The vehicle load detection method according to claim 1, wherein the detecting the load of the target vehicle based on the parameter database and the running data of the target vehicle includes:
collecting running data of the target vehicle in real time;
comparing the driving data in the type database, the driving state database and the parameter database to determine the parameters corresponding to the target vehicle;
and detecting the load of the target vehicle in real time according to the parameters.
5. A vehicle load detection device based on an acceleration sensor, characterized by comprising:
the model building module is used for building a type database, a driving state database and an acceleration model of the vehicle according to the GPS positioning data and the three-dimensional acceleration data of the vehicle;
The parameter library establishing module is used for establishing parameter databases of vehicles in different types and different running states according to the type database, the running state database and the acceleration model;
the load detection module is used for detecting the load of the target vehicle according to the parameter database and the running data of the target vehicle;
the model building module is specifically configured to build a type database, a driving state database and an acceleration model of the vehicle according to the GPS positioning data and the three-dimensional acceleration data of the vehicle, and includes:
based on GPS positioning data and vehicle three-dimensional acceleration information acquired by an acceleration sensor, different types of vehicles are classified, and the vehicles are further classified according to the running states of the vehicles;
constructing an acceleration model based on the running state of the vehicle and the position information of the vehicle; the automobile is subjected to the combined action of traction force and resistance in normal forward running, and the combined action is expressed as:
F t -f resistance resistor ＝ma x (1)
Wherein F is t For driving the car, f Resistance resistor For the resistance applied during the running of the automobile, the resistance applied during the running of the automobile comprises rolling resistance F f Air resistance F w Slope resistance;
driving force F of automobile t Regarding the gear G, the vehicle model M and the vehicle speed of the automobile, the relation between the driving force of the truck and the gear and the vehicle speed of the automobile in a certain model is shown in the formula (2)
Considering the sensor acquisition errors and correction factors, there are:
c is a constant, the vehicle speed and the vehicle acceleration errors acquired by the GPS positioning device and the acceleration sensor are corrected, further, vehicle data in normal progress are screened out firstly based on acceleration in the y direction, and further, the vehicle weight is estimated based on a formula (1) and a formula (2).
6. The vehicle load detection apparatus according to claim 5, wherein the model building module includes:
a running speed calculation unit for calculating the running speed of the vehicle according to the GPS positioning data and the corresponding time stamp thereof;
the change rate establishing unit is used for respectively determining the acceleration change rates in the vehicle advancing direction, the vehicle transverse direction and the gravity direction according to the running speed and a preset vehicle-mounted acceleration sensor;
and the database establishing unit is used for utilizing the acceleration change rate to represent the vibration condition of the vehicle based on the model data of the vehicle so as to establish the type database and the driving state database.
7. The vehicle load detection apparatus according to claim 5, wherein the parameter library creation module includes:
the feature extraction unit is used for extracting the running state features of the vehicle according to the running state database in a time window mode;
And the parameter database establishing unit is used for establishing the parameter database according to the driving state characteristics and the acceleration model.
8. The vehicle load detection apparatus of claim 5, wherein the load detection module comprises:
the driving data acquisition unit is used for acquiring driving data of the target vehicle in real time;
the parameter determining unit is used for comparing the driving data in the type database, the driving state database and the parameter database so as to determine the parameters corresponding to the target vehicle;
and the load detection unit is used for detecting the load of the target vehicle in real time according to the parameters.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, characterized in that the processor implements the steps of the acceleration sensor based vehicle load detection method according to any one of claims 1 to 4 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the acceleration sensor-based vehicle load detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834201.1A CN113340392B (en) | 2021-07-21 | 2021-07-21 | Vehicle load detection method and device based on acceleration sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110834201.1A CN113340392B (en) | 2021-07-21 | 2021-07-21 | Vehicle load detection method and device based on acceleration sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113340392A CN113340392A (en) | 2021-09-03 |
| CN113340392B true CN113340392B (en) | 2023-08-18 |
Family
ID=77480280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110834201.1A Active CN113340392B (en) | 2021-07-21 | 2021-07-21 | Vehicle load detection method and device based on acceleration sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113340392B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114724378B (en) * | 2022-06-02 | 2022-10-18 | 瞳见科技有限公司 | Vehicle tracking statistical system and method based on deep learning |
| CN117571107B (en) * | 2024-01-15 | 2024-03-15 | 山西富衡达自动化设备有限公司 | Intelligent unattended wagon balance anomaly monitoring system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010243305A (en) * | 2009-04-06 | 2010-10-28 | Yazaki Corp | Load weight estimation device |
| CN102901550A (en) * | 2012-11-15 | 2013-01-30 | 陕西电器研究所 | Method for implementing vehicle-mounted dynamic weighing |
| CN105675101A (en) * | 2016-03-10 | 2016-06-15 | 赛度科技（北京）有限责任公司 | OBD-based vehicle quality dynamic measuring device and measuring method |
| CN106529111A (en) * | 2015-09-14 | 2017-03-22 | 北汽福田汽车股份有限公司 | Method and system for detecting total vehicle weight and vehicle |
| CN108896149A (en) * | 2018-03-26 | 2018-11-27 | 北汽福田汽车股份有限公司 | Vehicle weighing method and vehicle |
| CN110702195A (en) * | 2019-09-24 | 2020-01-17 | 北京化工大学 | Method and device for monitoring running state of load-carrying vehicle |
| CN111833604A (en) * | 2020-07-10 | 2020-10-27 | 北京交通大学 | Vehicle load state identification method and device based on driving behavior feature extraction |
-
2021
- 2021-07-21 CN CN202110834201.1A patent/CN113340392B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010243305A (en) * | 2009-04-06 | 2010-10-28 | Yazaki Corp | Load weight estimation device |
| CN102901550A (en) * | 2012-11-15 | 2013-01-30 | 陕西电器研究所 | Method for implementing vehicle-mounted dynamic weighing |
| CN106529111A (en) * | 2015-09-14 | 2017-03-22 | 北汽福田汽车股份有限公司 | Method and system for detecting total vehicle weight and vehicle |
| CN105675101A (en) * | 2016-03-10 | 2016-06-15 | 赛度科技（北京）有限责任公司 | OBD-based vehicle quality dynamic measuring device and measuring method |
| CN108896149A (en) * | 2018-03-26 | 2018-11-27 | 北汽福田汽车股份有限公司 | Vehicle weighing method and vehicle |
| CN110702195A (en) * | 2019-09-24 | 2020-01-17 | 北京化工大学 | Method and device for monitoring running state of load-carrying vehicle |
| CN111833604A (en) * | 2020-07-10 | 2020-10-27 | 北京交通大学 | Vehicle load state identification method and device based on driving behavior feature extraction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113340392A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104164829B (en) | Detection method of road-surface evenness and intelligent information of road surface real-time monitoring system based on mobile terminal | |
| EP4261051A2 (en) | System and method for vehicle tire performance modeling and feedback | |
| CN113340392B (en) | Vehicle load detection method and device based on acceleration sensor | |
| CN101044386B (en) | Tire wear analysis method | |
| CN104540717A (en) | Method and device for determining state of road surface | |
| CN111833604B (en) | Vehicle load state identification method and device based on driving behavior feature extraction | |
| CN109668610A (en) | The system of vehicle dynamically weighting method and its use based on neural net regression | |
| CN110702195B (en) | Method and device for monitoring running state of load-carrying vehicle | |
| CN107458380A (en) | A kind of road grade real-time estimation method being applied under comprehensive driving cycles | |
| CN103471865A (en) | Train suspension system failure isolation method based on LDA method | |
| CN113183973A (en) | Tire pressure monitoring and road surface information intelligent sensing platform and method based on CAN network | |
| CN109186528A (en) | A kind of theoretical method determining international roughness index based on the acceleration that mobile phone measures | |
| CN109131336A (en) | Obtain the method and system of coefficient of road adhesion | |
| CN102519577B (en) | Method and system for identifying road surface in a road | |
| Kirushnath et al. | Weigh-in-motion using machine learning and telematics | |
| CN108228994B (en) | Stress calculation method for vehicle and working device under random excitation of off-road | |
| US11525728B1 (en) | Systems and methods for determining an estimated weight of a vehicle | |
| Hamad et al. | A new approach for varied speed weigh-in-motion vehicle based on smartphone inertial sensors | |
| Altmann et al. | Identification of Damaging Road Events Using Pseudo Damage Density | |
| Ren et al. | An SVM based algorithm for road disease detection using accelerometer | |
| EP4187215B1 (en) | Systems and methods for determining an estimated weight of a vehicle | |
| EP4350305A1 (en) | Systems and methods for determining an estimated weight of a vehicle | |
| US20220219680A1 (en) | Information processing device, information processing method, and non-transitory computer-readable medium storing information processing program | |
| CN113112061B (en) | Method and device for predicting fuel consumption of vehicle | |
| EP4187214B1 (en) | Systems and methods for determining an estimated weight of a 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |