CN111912506A - Method and device for determining the load state of a motor vehicle - Google Patents
Method and device for determining the load state of a motor vehicle Download PDFInfo
- Publication number
- CN111912506A CN111912506A CN202010470497.9A CN202010470497A CN111912506A CN 111912506 A CN111912506 A CN 111912506A CN 202010470497 A CN202010470497 A CN 202010470497A CN 111912506 A CN111912506 A CN 111912506A
- Authority
- CN
- China
- Prior art keywords
- data
- determining
- preset
- motor vehicle
- time
- 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
Images
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
- G01G19/02—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing wheeled or rolling bodies, e.g. vehicles
- G01G19/03—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing wheeled or rolling bodies, e.g. vehicles for weighing during motion
-
- 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
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a method and equipment for determining the loading state of a motor vehicle, wherein the method comprises the following steps: acquiring historical operation data of the motor vehicle within a preset time interval, wherein the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data; determining a weight characteristic value sequence of the motor vehicle in operation according to the operation speed data and the engine sound data of different time points; training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model; when the motor vehicle is in a preset running state with zero acceleration, the current load state of the motor vehicle is determined based on the model structure, so that the load state of the motor vehicle is determined flexibly and efficiently without depending on a weighbridge or a high-rigidity load induction sensor.
Description
Technical Field
The present application relates to the field of motor vehicle load detection technologies, and more particularly, to a method and apparatus for determining a load state of a motor vehicle.
Background
For motor vehicles for transporting goods, the load information thereof is very important. For fleet managers, load information can be used to monitor vehicle operation; for traffic management departments, the load information can be used for monitoring whether the motor vehicle is overloaded or not, so that traffic safety loss is avoided. However, great labor and material cost is needed for acquiring the truck load information, and a system or a device for intelligently detecting the truck load is absent in the market.
The traditional motor vehicle load detection needs to drive the loaded motor vehicle to a place with a wagon balance to detect whether overload exists or not, which brings inconvenience to a truck driver and a remote manager. Or need install corresponding load induction sensor, the packing box need press in sensor one end, and the sensor other end presses on the frame, and such detecting system has very high rigidity design requirement to the sensor, and the sensor needs to bear packing box weight, if long-time the use can cause the sensor to damage and make the detection function inefficacy. The sensor is installed, so that the safety detection of the annual inspection of the whole vehicle is not easy to pass; if a sensor which is not easy to damage is selected to be installed, such as a foreign capacitive sensor, one sensor is thousands of yuan, the cost of software and hardware of the whole system is more than ten thousand yuan, the price is high, and the installation design is not flexible.
Therefore, how to more efficiently and conveniently determine the loading state of the motor vehicle is a technical problem to be solved at present.
Disclosure of Invention
Aiming at the technical problems of high cost and complex monitoring process in the prior art when the load state of the motor vehicle is determined, the invention provides a method for determining the load state of the motor vehicle, which comprises the following steps:
acquiring historical operation data of the motor vehicle within a preset time interval, wherein the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data;
determining a weight characteristic value sequence of the motor vehicle in operation according to the operation speed data and the engine sound data of different time points;
training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model;
when the motor vehicle is in a preset running state with zero acceleration, determining the total weight of the motor vehicle based on the model structure, and determining the current load state of the motor vehicle according to the difference value between the total weight and the no-load state of the motor vehicle, wherein the preset running state is that the engine torque is in a first preset range, the running speed is in a second preset range, and the speed deviation is in a third preset range.
Preferably, a preset multiple linear regression model is trained based on the weight characteristic value sequence and the running trajectory data, specifically:
filtering the weight characteristic value sequence based on a first-order difference algorithm and/or a mean filtering algorithm;
determining a final weight characteristic value sequence according to the filtering result;
determining effective operation track data in the operation track data based on a window function;
screening out non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data of which the absolute value of the altitude difference of the motor vehicle in preset time is smaller than a preset distance;
and taking the final weight characteristic value sequence and the non-uphill and downhill data as training data to perform the training.
Preferably, the correlation coefficients of the preset multiple linear regression model are predetermined, the correlation coefficients at least include a loss coefficient of an engine in a transmission process, a blocking coefficient of air resistance to vehicle driving, and an influence factor coefficient, and the training is performed by using the final weight characteristic value sequence and the non-uphill and downhill slope data as training data, specifically:
inputting preset values of the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
determining a prediction error according to a difference between the predicted load state and the actual load data;
determining the model structure based on each preset value when the absolute value of the prediction error is smaller than a preset threshold value;
and when the absolute value of the prediction error is not less than the preset threshold, setting a new preset value of each correlation coefficient, and continuously inputting each new preset value and the training data into the preset multiple linear regression model.
Preferably, the effective trajectory data in the trajectory data is determined based on a window function, and specifically:
determining an abnormal data point in the running track data, wherein the abnormal data point comprises: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp;
extracting the abnormal data points based on the window function and carrying out rejection operation, wherein the rejection operation specifically comprises the operations of merging, andor filling, andor deleting;
determining the effective trajectory data based on the result of the culling operation
Preferably, the weight characteristic value sequence of the motor vehicle during operation is determined according to the operation speed data and the engine sound data at different time points, specifically:
determining a starting time and an ending time of each acceleration of the motor vehicle based on the running speed data;
determining an acceleration time sequence of the motor vehicle according to the starting time and the ending time of each time;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
determining a sound energy time series corresponding to the acceleration time series based on the engine sound data, wherein the time point of the sound energy time series is ahead of the time point of the acceleration time series by a preset time length;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
and determining the weight characteristic value sequence according to the acceleration characteristic value sequence and the sound energy characteristic value sequence.
Accordingly, the invention also proposes a device for determining the loading state of a motor vehicle, said device comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring historical operation data of the motor vehicle within a preset time interval, and the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data;
the first determination module is used for determining a weight characteristic value sequence of the motor vehicle during running according to the running speed data and the engine sound data of different time points;
the training module is used for training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data so as to determine a model structure of the preset multiple linear regression model;
and the second determination module is used for determining the total weight of the motor vehicle based on the model structure when the motor vehicle is in a preset running state with zero acceleration, and determining the current load state of the motor vehicle according to the difference value between the total weight and the no-load state of the motor vehicle, wherein the preset running state is that the engine torque is in a first preset range, the running speed is in a second preset range, and the speed deviation is in a third preset range.
Preferably, the training module is specifically configured to:
filtering the weight characteristic value sequence based on a first-order difference algorithm and/or a mean filtering algorithm;
determining a final weight characteristic value sequence according to the filtering result;
determining effective operation track data in the operation track data based on a window function;
screening out non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data of which the absolute value of the altitude difference of the motor vehicle in preset time is smaller than a preset distance;
and taking the final weight characteristic value sequence and the non-uphill and downhill data as training data to perform the training.
Preferably, the correlation coefficients of the preset multiple linear regression model are predetermined, and the correlation coefficients at least include a loss coefficient of the engine during transmission, a blocking coefficient of air resistance to the driving of the motor vehicle, and an influence factor coefficient, and the training module is further specifically configured to:
inputting preset values of the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
determining a prediction error according to a difference between the predicted load state and the actual load data;
determining the model structure based on each preset value when the absolute value of the prediction error is smaller than a preset threshold value;
and when the absolute value of the prediction error is not less than the preset threshold, setting a new preset value of each correlation coefficient, and continuously inputting each new preset value and the training data into the preset multiple linear regression model.
Preferably, the training module is further specifically configured to:
determining an abnormal data point in the running track data, wherein the abnormal data point comprises: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp;
extracting the abnormal data points based on the window function and carrying out rejection operation, wherein the rejection operation specifically comprises the operations of merging, andor filling, andor deleting;
and determining the effective running track data based on the result of the rejection operation.
Preferably, the first determining module is specifically configured to:
determining a starting time and an ending time of each acceleration of the motor vehicle based on the running speed data;
determining an acceleration time sequence of the motor vehicle according to the starting time and the ending time of each time;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
determining a sound energy time series corresponding to the acceleration time series based on the engine sound data, wherein the time point of the sound energy time series is ahead of the time point of the acceleration time series by a preset time length;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
and determining the weight characteristic value sequence according to the acceleration characteristic value sequence and the sound energy characteristic value sequence.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a method and equipment for determining the loading state of a motor vehicle, wherein the method comprises the following steps: acquiring historical operation data of the motor vehicle within a preset time interval, wherein the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data; determining a weight characteristic value sequence of the motor vehicle in operation according to the operation speed data and the engine sound data of different time points; training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model; when the motor vehicle is in a preset running state with zero acceleration, the current load state of the motor vehicle is determined based on the model structure, so that the load state of the motor vehicle is determined flexibly and efficiently without depending on a weighbridge or a high-rigidity load induction sensor.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating a method for determining a loading state of a vehicle according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart diagram illustrating a method for determining a vehicle loading status according to another embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an apparatus for determining a loading state of a vehicle according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As described in the background art, the cost is high and the monitoring process is complex when the load state of the motor vehicle is determined in the prior art.
To this end, the present application discloses a method of determining a vehicle load state, which determines the vehicle load state without the need for a high stiffness load sensor and a weigh scale, thereby improving the efficiency and flexibility of determining the vehicle load state. As shown in fig. 1, the method comprises the following steps:
step S101, obtaining historical operation data of the motor vehicle in a preset time interval, wherein the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data.
It CAN be understood that the preset time interval is several days or more than ten days, which CAN be adjusted according to actual situations, and in a specific application scenario, historical operation data is obtained from On-Board Diagnostics (OBD) and Global Positioning System (GPS) through a Controller Area Network (CAN) bus. Wherein the engine sound data may be acquired by a microphone.
The OBD is a system capable of monitoring the running state of the automobile at any time and monitoring a plurality of systems and components on the automobile, and the GPS is a positioning system of high-precision radio navigation based on an air satellite, and can provide accurate geographic position, running speed and time information in any place and near-earth space of the world.
S102, determining a weight characteristic value sequence of the motor vehicle during operation according to the operation speed data and the engine sound data of different time points.
In the acceleration process of the motor vehicle, the sound of the engine is correspondingly changed when the acceleration is generated, the acceleration time and the sound energy in the acceleration process of the motor vehicle are different under the condition of different load states, and based on the difference, the weight characteristic value sequence of the motor vehicle in the operation process is determined according to the operation speed data and the engine sound data of different time points.
In order to accurately obtain the weight characteristic value sequence, in a preferred embodiment of the present application, the weight characteristic value sequence when the motor vehicle runs is determined according to the running speed data and the engine sound data at different time points, specifically:
determining a starting time and an ending time of each acceleration of the motor vehicle based on the running speed data;
determining an acceleration time sequence of the motor vehicle according to the starting time and the ending time of each time;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
determining a sound energy time series corresponding to the acceleration time series based on the engine sound data, wherein the time point of the sound energy time series is ahead of the time point of the acceleration time series by a preset time length;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
and determining the weight characteristic value sequence according to the acceleration characteristic value sequence and the sound energy characteristic value sequence.
As described above, the start time and the end time of each acceleration of the motor vehicle are determined according to the operation speed data, and then the acceleration time series of the motor vehicle is determined. For example, if the vehicle speed is greater than 15Km/h, if the acceleration continues to be greater than 0.3m/s for 3s or more, it is determined that the vehicle is in an acceleration state. And determining the acceleration characteristic value sequence according to the average value of two-thirds data in the quartering distance data of each acceleration in the acceleration time sequence. Then, determining a sound energy time sequence corresponding to the acceleration time sequence based on the engine sound data, wherein the time point of the sound energy time sequence is ahead of the time point of the acceleration time sequence by a preset time length because the sound is earlier than the acceleration, a plurality of sound energies are obtained during each acceleration, a sound energy characteristic value sequence is determined according to the average value of two-three-point data in the four-point distance data of each acceleration in the sound energy time sequence, and finally, the weight characteristic value sequence is determined according to the acceleration characteristic value sequence and the sound energy characteristic value sequence. In a specific application scenario of the present application, the weight characteristic value may be determined by dividing the acceleration characteristic value by the sound energy characteristic value, or the weight characteristic value may be determined by dividing the sound energy characteristic value by the acceleration characteristic value.
In addition, the acceleration sequence during each acceleration can be subjected to descending order arrangement, and the second numerical value and the third numerical value are averaged to be used as the acceleration characteristic value of the acceleration; and according to the sound energy sequence during each acceleration, performing descending arrangement on the sound energy sequence, and averaging the second numerical value and the third numerical value to obtain a sound energy characteristic value of the acceleration.
It should be noted that the above solution of the preferred embodiment is only a specific implementation solution proposed in the present application, and other ways of determining the weight characteristic value sequence of the motor vehicle during operation according to the operation speed data and the engine sound data at different time points all belong to the protection scope of the present application.
Step S103, training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model.
The multiple linear regression model is a regression model including two or more independent variables, and prediction or estimation using the multiple linear regression model is more practical and accurate.
In order to ensure reasonable training of the multiple linear regression model, in the preferred embodiment of the present application, a preset multiple linear regression model is trained based on the weight characteristic value sequence and the trajectory data, specifically:
filtering the weight characteristic value sequence based on a first-order difference algorithm and/or a mean filtering algorithm;
determining a final weight characteristic value sequence according to the filtering result;
determining effective operation track data in the operation track data based on a window function;
screening out non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data of which the absolute value of the altitude difference of the motor vehicle in preset time is smaller than a preset distance;
and taking the final weight characteristic value sequence and the non-uphill and downhill data as training data to perform the training.
In particular, the window function is a special type of function in SQL. The input to the window function is a multi-line record and acts on a window, which is a multi-line record defined by an OVER clause. And the window function outputs a result for each line record in the window acted by the window function, and effective operation track data in the operation track data can be determined based on the window function. Because the data of the motor vehicle during ascending and descending is not the data of the motor vehicle under the stable operation condition, and the accuracy of the load state is influenced, the data of non-ascending and non-descending slopes need to be screened from the effective operation track data, wherein the data of the non-ascending and descending slopes is the data that the absolute value of the altitude difference value of the motor vehicle within the preset time is smaller than the preset distance. In addition, the non-uphill and downhill data may also be acquired by two-thirds data of the four-pitch data. And then the final weight characteristic value sequence and the non-uphill and downhill slope data are used as training data to carry out the training.
It should be noted that the above solution of the preferred embodiment is only one specific implementation solution proposed in the present application, and other ways of training a predetermined multiple linear regression model based on the weight characteristic value sequence and the running trajectory data all belong to the protection scope of the present application.
In order to obtain an accurate multiple linear regression model, in a preferred embodiment of the present application, correlation coefficients of the preset multiple linear regression model are predetermined, where the correlation coefficients at least include a loss coefficient of an engine during transmission, a blocking coefficient of air resistance on vehicle driving, and an influence factor coefficient, and the training is performed by using the final weight characteristic value sequence and the non-uphill and downhill data as training data, specifically:
inputting preset values of the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
determining a prediction error according to a difference between the predicted load state and the actual load data;
determining the model structure based on each preset value when the absolute value of the prediction error is smaller than a preset threshold value;
and when the absolute value of the prediction error is not less than the preset threshold, setting a new preset value of each correlation coefficient, and continuously inputting each new preset value and the training data into the preset multiple linear regression model.
Specifically, the correlation coefficients of the multiple linear regression model are predetermined, and the correlation coefficients may be a loss coefficient a of the engine during transmission, a blocking coefficient b of air resistance to vehicle driving, and an influencing factor c, and in a specific application scenario of the present application, the specific formula may be:
and M is the predicted total cargo weight of the motor vehicle, the obtained final weight characteristic value sequence data and the non-uphill and downhill slope data are used as training data, each correlation coefficient can be a preset value, the load of the motor vehicle is predicted and calculated, the calculated result is compared with the actual load, if the error between the obtained result and the actual load is smaller than a preset threshold value, for example 10%, the correlation coefficient is kept to determine a model structure, and if the error between the obtained result and the actual load is larger than the preset threshold value, for example 10%, the training calculation is carried out again.
The person skilled in the art can flexibly set the correlation coefficients of other multiple linear regression models, and set the preset thresholds of other different errors, which does not affect the scope of the present application.
In order to determine accurate effective operation track data, in a preferred embodiment of the present application, effective operation track data in the operation track data is determined based on a window function, specifically:
determining an abnormal data point in the running track data, wherein the abnormal data point comprises: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp;
extracting the abnormal data points based on the window function and carrying out rejection operation, wherein the rejection operation specifically comprises the operations of merging, andor filling, andor deleting;
and determining the effective running track data based on the result of the rejection operation.
Specifically, when the GPS signal strength is low or the engine is turned off/started, the trajectory data may generate abnormal data, which may cause a signal quality problem in the trajectory data. Common data quality problems associated with abnormal data points include the following:
(1) uploading multiple pieces of driving data at the same timestamp
In the embodiment of the invention, when a plurality of pieces of operation track data are uploaded at the same time, the operation track data uploaded at the same time are screened through a window function, and the last operation track data is selected as the uploading operation track data of the current time stamp.
(2) Loss of signal in mileage data or vehicle speed data
In the embodiment of the invention, when signals such as mileage data or vehicle speed data are lost, the lost signals such as mileage data or vehicle speed data are extracted through a window function, and one piece of non-empty running data closest to the lost signals is selected for filling.
(3) Trip signal jump
In the embodiment of the invention, the numerical value of the mileage signal presents an increasing characteristic, and jumping is divided into two conditions, wherein one condition is that the mileage signal jumps out of a normal reasonable range, and the other condition is that the mileage signal jumps to a negative value (the current mileage is less than the previous mileage). The treatment method comprises the following steps: according to the method, the frequency of uploaded data is 1/30 s, the maximum speed limit of a motor vehicle is 100km/h, the trip variable limit value of the mileage traveled at the front moment and the back moment is about 833m, taking the current moment as an example, if the trip range of the current mileage to the last mileage is too large (over 833 m), the process of uploading the mileage is considered to be wrong, and the data at the current moment is directly filtered; and if the jump range is a negative value (the mileage value is reduced), the mileage at the current moment is replaced by averaging the mileage at the previous moment and the mileage at the next moment.
In the embodiment of the invention, conditions for extracting abnormal data points are set through a window function, and the several abnormal data points are subjected to rejection operation, wherein the rejection operation specifically comprises the operations of merging, and/or filling, and/or deleting.
It should be noted that the above solution of the preferred embodiment is only one specific implementation solution proposed in the present application, and other ways of determining valid trajectory data based on the window function all belong to the protection scope of the present application.
And S104, when the motor vehicle is in a preset running state with zero acceleration, determining the total weight of the motor vehicle based on the model structure, and determining the current load state of the motor vehicle according to the difference value between the total weight and the no-load state of the motor vehicle.
Specifically, when the load state is determined through the model structure, the motor vehicle needs to be in a stable driving condition to obtain an accurate result, so that the driving state of the motor vehicle is preset, and the process of determining the load state is performed only when the motor vehicle is in the preset driving state, wherein the preset driving state is that the engine torque is within a first preset range, the running speed is within a second preset range, and the speed deviation is within a third preset range. Through the training in step S103, a model structure with an error value smaller than a preset threshold value can be determined, the weight characteristic value and the driving speed are substituted into the determined model structure, the total weight of the motor vehicle can be calculated by using the model structure, and the current load state of the motor vehicle is obtained by subtracting the empty load state of the motor vehicle from the obtained total weight.
By applying the technical scheme, historical operation data of the motor vehicle in a preset time interval are obtained, wherein the historical operation data at least comprise operation track data, operation speed data, engine sound data and actual load data; determining a weight characteristic value sequence of the motor vehicle in operation according to the operation speed data and the engine sound data of different time points; training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model; when the motor vehicle is in a preset running state with zero acceleration, the current load state of the motor vehicle is determined based on the model structure, so that the load state of the motor vehicle is determined flexibly and efficiently without depending on a weighbridge or a high-rigidity load induction sensor.
To further illustrate the technical idea of the present invention, the technical solution of the present invention will now be described with reference to a specific application scenario, as shown in fig. 2.
Step S201, historical operation data is obtained.
The motor vehicle is provided with an OBD (on-board diagnostics) and a GPS (global positioning system) in advance, and a microphone for acquiring engine sound data is further arranged, so that historical operation data in a preset time interval are acquired, wherein the historical operation data at least comprise operation track data, operation speed data, engine sound data and actual load data.
Step S202, determining a weight characteristic value sequence of the motor vehicle during running according to the running speed data and the engine sound data of different time points.
And carrying out mean value filtering and first-order difference calculation on the running speed data to obtain a time sequence of the acceleration, judging the acceleration state of the motor vehicle according to the value of the acceleration and the duration of the acceleration, and confirming the starting time and the ending time of the acceleration state. According to an embodiment of the present invention, the acceleration state of the motor vehicle is judged according to the vehicle speed, the acceleration and the acceleration duration. For example, if the vehicle speed is greater than 15Km/h, if the acceleration is continuously greater than 0.3m/s for more than 3s, it is determined that the vehicle is in an acceleration state;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
the method comprises the steps that engine sound data can be acquired through a microphone, 400Hz low-pass filtering is conducted on the waveform of the engine sound data, sound source interference except for an engine is filtered, an energy integral value per second is obtained for the filtered sound data, and a sound energy time sequence is obtained, wherein the sound is earlier than acceleration, and the time point position of the sound energy time sequence is 3-5 seconds ahead of the time point position of the acceleration time sequence;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
the weight characteristic value sequence is determined according to the acceleration characteristic value sequence and the sound energy characteristic value sequence, the weight characteristic value can be determined by dividing the acceleration characteristic value by the sound energy characteristic value, the weight characteristic value can also be determined by dividing the sound energy characteristic value by the acceleration characteristic value, and a person skilled in the art can flexibly select a determination mode.
And step S203, processing the weight characteristic value sequence and the running track data.
Extracting abnormal data points in the running track data based on the window function, and determining effective running track data after removing operation, wherein the abnormal data points comprise: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp; the removing operation specifically comprises the operations of merging, andor filling, andor deleting.
Screening non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data that an absolute value of an altitude difference value of the motor vehicle in a preset time is smaller than a preset distance, specifically, real-time atmospheric pressure is obtained by an atmospheric pressure sensor, the altitude at the moment is calculated, the altitude before 3 seconds is subtracted from the current altitude, an absolute value is obtained for the difference value, if the absolute value is smaller than 2m, the state of the motor vehicle at the moment is considered to be in a non-uphill and downhill state, and if not, the state is in the uphill and downhill state. And determining two-thirds data in the corresponding four-quadrant distance in the effective operation track data as non-uphill and downhill data.
And S204, training a multiple linear regression model according to the final weight characteristic value sequence and the non-uphill and downhill data.
And determining the correlation coefficients of the preset multiple linear regression model in advance, wherein the correlation coefficients at least comprise a loss coefficient of an engine in the transmission process, a blocking coefficient of air resistance on the running of the motor vehicle and an influence factor coefficient.
Training a preset multiple linear regression model by using the final weight characteristic value sequence and the non-uphill and downhill slope data as training data, and specifically comprising the following steps of:
step a, inputting preset values of all the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
b, determining a prediction error according to the difference value of the predicted load state and the actual load data;
step c, judging that the absolute value of the prediction error is smaller than a preset threshold, setting the preset threshold to be 10%, if so, executing the step d, and if not, executing the step e;
d, determining the model structure based on each preset value;
and e, setting a new preset value of each correlation coefficient, and executing the step a.
In the embodiment of the present invention, a specific formula of the multiple linear regression model is as follows:
wherein M is the total weight of the motor vehicle, a is the loss coefficient of the engine in the transmission process, TtInstantaneous torque of the motor vehicle, R is the standard radius of the vehicle tyre, maThe characteristic value of the weight, b is a coefficient of resistance of air resistance to the running of the motor vehicle, c is a coefficient of influence factor, and v is the speed of the corresponding time point.
And S205, determining the current load state of the motor vehicle based on the model structure.
And when the torque interval of the engine is +/-100 Nm, the speed interval of the motor vehicle is 40-120 km/h and the speed deviation range is +/-4 km/h, considering the running state of the motor vehicle as a steady-state working condition without acceleration and taking the steady-state working condition as a preset running state.
And (3) bringing the weight characteristic value and the speed data of the motor vehicle in a preset driving state with zero acceleration into a determined multiple linear regression model for calculation to obtain a value which is the current total weight of the motor vehicle, and subtracting the no-load state of the motor vehicle from the obtained current total weight to obtain the current load state of the motor vehicle.
In addition, the load segmentation condition can be preset according to the parking time, for example, the motor vehicle can be reloaded only under the condition of parking for a certain time, and the short parking time can only be that a driver stops for a rest and cannot complete reloading; the load sections of the motor vehicle are divided according to the preset load section conditions, and the preset running state of the motor vehicle is determined in each divided load section, so that the accuracy is improved.
By applying the technical scheme, historical operation data of the motor vehicle in a preset time interval are obtained, wherein the historical operation data at least comprise operation track data, operation speed data, engine sound data and actual load data; determining a weight characteristic value sequence of the motor vehicle in operation according to the operation speed data and the engine sound data of different time points; training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model; when the motor vehicle is in a preset running state with zero acceleration, the current load state of the motor vehicle is determined based on the model structure, so that the load state of the motor vehicle is determined flexibly and efficiently without depending on a weighbridge or a high-rigidity load induction sensor.
In order to achieve the above object, the present invention further provides an apparatus for determining a loading state of a vehicle, as shown in fig. 3, comprising:
an obtaining module 301, configured to obtain historical operation data of the motor vehicle within a preset time interval, where the historical operation data at least includes operation trajectory data, operation speed data, engine sound data, and actual load data;
a first determining module 302, configured to determine a weight characteristic value sequence of the motor vehicle during operation according to the operation speed data and the engine sound data at different time points;
a training module 303, configured to train a preset multiple linear regression model based on the weight characteristic value sequence and the trajectory data to determine a model structure of the preset multiple linear regression model;
a second determining module 304, configured to determine, based on the model structure, a total weight of the motor vehicle when the motor vehicle is in a preset driving state where the acceleration is zero, and determine a current load state of the motor vehicle according to a difference between the total weight and a no-load state of the motor vehicle, where the preset driving state is that an engine torque is within a first preset range, an operating speed is within a second preset range, and a speed deviation is within a third preset range.
In a specific application scenario, the training module 303 is specifically configured to:
filtering the weight characteristic value sequence based on a first-order difference algorithm and/or a mean filtering algorithm;
determining a final weight characteristic value sequence according to the filtering result;
determining effective operation track data in the operation track data based on a window function;
screening out non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data of which the absolute value of the altitude difference of the motor vehicle in preset time is smaller than a preset distance;
and taking the final weight characteristic value sequence and the non-uphill and downhill data as training data to perform the training.
In a specific application scenario, the correlation coefficients of the preset multiple linear regression model are predetermined, where the correlation coefficients at least include a loss coefficient of an engine during transmission, a blocking coefficient of air resistance to vehicle driving, and an influence factor coefficient, and the training module 303 is further specifically configured to:
inputting preset values of the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
determining a prediction error according to a difference between the predicted load state and the actual load data;
determining the model structure based on each preset value when the absolute value of the prediction error is smaller than a preset threshold value;
and when the absolute value of the prediction error is not less than the preset threshold, setting a new preset value of each correlation coefficient, and continuously inputting each new preset value and the training data into the preset multiple linear regression model.
In a specific application scenario, the training module 303 is further specifically configured to:
determining an abnormal data point in the running track data, wherein the abnormal data point comprises: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp;
extracting the abnormal data points based on the window function and carrying out rejection operation, wherein the rejection operation specifically comprises the operations of merging, andor filling, andor deleting;
and determining the effective running track data based on the result of the rejection operation.
In a specific application scenario, the first determining module 302 is specifically configured to:
determining a starting time and an ending time of each acceleration of the motor vehicle based on the running speed data;
determining an acceleration time sequence of the motor vehicle according to the starting time and the ending time of each time;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
determining a sound energy time series corresponding to the acceleration time series based on the engine sound data, wherein the time point of the sound energy time series is ahead of the time point of the acceleration time series by a preset time length;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
and determining the weight characteristic value sequence according to the acceleration characteristic value sequence and the sound energy characteristic value sequence.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention may be implemented by hardware, or by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method according to the implementation scenarios of the present invention.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
Those skilled in the art will appreciate that the modules in the apparatus may be distributed in the apparatus according to the description of the implementation scenario, or may be located in one or more apparatuses different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above-mentioned invention numbers are merely for description and do not represent the merits of the implementation scenarios.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not necessarily depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A method of determining a vehicle load state, the method comprising:
acquiring historical operation data of the motor vehicle within a preset time interval, wherein the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data;
determining a weight characteristic value sequence of the motor vehicle in operation according to the operation speed data and the engine sound data of different time points;
training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data to determine a model structure of the preset multiple linear regression model;
when the motor vehicle is in a preset running state with zero acceleration, determining the total weight of the motor vehicle based on the model structure, and determining the current load state of the motor vehicle according to the difference value between the total weight and the no-load state of the motor vehicle, wherein the preset running state is that the engine torque is in a first preset range, the running speed is in a second preset range, and the speed deviation is in a third preset range.
2. The method of claim 1, wherein a preset multivariate linear regression model is trained based on the sequence of weight eigenvalues and the trajectory data, specifically:
filtering the weight characteristic value sequence based on a first-order difference algorithm and/or a mean filtering algorithm;
determining a final weight characteristic value sequence according to the filtering result;
determining effective operation track data in the operation track data based on a window function;
screening out non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data of which the absolute value of the altitude difference of the motor vehicle in preset time is smaller than a preset distance;
and taking the final weight characteristic value sequence and the non-uphill and downhill data as training data to perform the training.
3. The method according to claim 2, wherein the correlation coefficients of the predetermined multiple linear regression model are predetermined, the correlation coefficients at least include a loss coefficient of an engine during transmission, a blocking coefficient of air resistance to vehicle driving, and an influence factor coefficient, and the training is performed using the final weight characteristic value sequence and the non-uphill and downhill data as training data, specifically:
inputting preset values of the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
determining a prediction error according to a difference between the predicted load state and the actual load data;
determining the model structure based on each preset value when the absolute value of the prediction error is smaller than a preset threshold value;
and when the absolute value of the prediction error is not less than the preset threshold, setting a new preset value of each correlation coefficient, and continuously inputting each new preset value and the training data into the preset multiple linear regression model.
4. The method according to claim 2, wherein the effective trajectory data in the trajectory data is determined based on a window function, specifically:
determining an abnormal data point in the running track data, wherein the abnormal data point comprises: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp;
extracting the abnormal data points based on the window function and carrying out rejection operation, wherein the rejection operation specifically comprises the operations of merging, andor filling, andor deleting;
and determining the effective running track data based on the result of the rejection operation.
5. The method according to claim 1, characterized in that the sequence of weight characteristic values of the motor vehicle during operation is determined from the operating speed data and the engine sound data at different time points, in particular:
determining a starting time and an ending time of each acceleration of the motor vehicle based on the running speed data;
determining an acceleration time sequence of the motor vehicle according to the starting time and the ending time of each time;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
determining a sound energy time series corresponding to the acceleration time series based on the engine sound data, wherein the time point of the sound energy time series is ahead of the time point of the acceleration time series by a preset time length;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
and determining the weight characteristic value sequence according to the acceleration characteristic value sequence and the sound energy characteristic value sequence.
6. An apparatus for determining a vehicle load state, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring historical operation data of the motor vehicle within a preset time interval, and the historical operation data at least comprises operation track data, operation speed data, engine sound data and actual load data;
the first determination module is used for determining a weight characteristic value sequence of the motor vehicle during running according to the running speed data and the engine sound data of different time points;
the training module is used for training a preset multiple linear regression model based on the weight characteristic value sequence and the running track data so as to determine a model structure of the preset multiple linear regression model;
and the second determination module is used for determining the total weight of the motor vehicle based on the model structure when the motor vehicle is in a preset running state with zero acceleration, and determining the current load state of the motor vehicle according to the difference value between the total weight and the no-load state of the motor vehicle, wherein the preset running state is that the engine torque is in a first preset range, the running speed is in a second preset range, and the speed deviation is in a third preset range.
7. The device of claim 6, wherein the training module is specifically configured to:
filtering the weight characteristic value sequence based on a first-order difference algorithm and/or a mean filtering algorithm;
determining a final weight characteristic value sequence according to the filtering result;
determining effective operation track data in the operation track data based on a window function;
screening out non-uphill and downhill data from the effective running track data, wherein the non-uphill and downhill data are data of which the absolute value of the altitude difference of the motor vehicle in preset time is smaller than a preset distance;
and taking the final weight characteristic value sequence and the non-uphill and downhill data as training data to perform the training.
8. The apparatus of claim 7, wherein the correlation coefficients of the predetermined multiple linear regression model are predetermined, and the correlation coefficients at least include a loss coefficient of an engine during transmission, a blocking coefficient of air resistance to vehicle driving, and an influence factor coefficient, and the training module is further specifically configured to:
inputting preset values of the correlation coefficients and the training data into the preset multiple linear regression model to determine a predicted load state;
determining a prediction error according to a difference between the predicted load state and the actual load data;
determining the model structure based on each preset value when the absolute value of the prediction error is smaller than a preset threshold value;
and when the absolute value of the prediction error is not less than the preset threshold, setting a new preset value of each correlation coefficient, and continuously inputting each new preset value and the training data into the preset multiple linear regression model.
9. The device of claim 7, wherein the training module is further specifically configured to:
determining an abnormal data point in the running track data, wherein the abnormal data point comprises: a plurality of data points of the running track data, or data points of the mileage data lost, or data points of the mileage signal jumping exist on the same timestamp;
extracting the abnormal data points based on the window function and carrying out rejection operation, wherein the rejection operation specifically comprises the operations of merging, andor filling, andor deleting;
and determining the effective running track data based on the result of the rejection operation.
10. The device of claim 6, wherein the first determining module is specifically configured to:
determining a starting time and an ending time of each acceleration of the motor vehicle based on the running speed data;
determining an acceleration time sequence of the motor vehicle according to the starting time and the ending time of each time;
determining an acceleration characteristic value sequence according to the average value of two-three-quadrant data in the four-quadrant distance data accelerated every time in the acceleration time sequence;
determining a sound energy time series corresponding to the acceleration time series based on the engine sound data, wherein the time point of the sound energy time series is ahead of the time point of the acceleration time series by a preset time length;
determining a sound energy characteristic value sequence according to the average value of two-three-quadrant data in the acceleration quarter-bit distance data in the sound energy time sequence;
and determining the weight characteristic value sequence according to the acceleration characteristic value sequence and the sound energy characteristic value sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010470497.9A CN111912506A (en) | 2020-05-28 | 2020-05-28 | Method and device for determining the load state of a motor vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010470497.9A CN111912506A (en) | 2020-05-28 | 2020-05-28 | Method and device for determining the load state of a motor vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111912506A true CN111912506A (en) | 2020-11-10 |
Family
ID=73237570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010470497.9A Pending CN111912506A (en) | 2020-05-28 | 2020-05-28 | Method and device for determining the load state of a motor vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111912506A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113173175A (en) * | 2021-06-09 | 2021-07-27 | 一汽解放汽车有限公司 | Vehicle weight determination method and device |
| CN113408591A (en) * | 2021-06-01 | 2021-09-17 | 上海自动化仪表有限公司 | Process trend analysis and prediction method based on intelligent instrument |
| CN113593079A (en) * | 2021-07-30 | 2021-11-02 | 东风商用车有限公司 | Road condition self-adaption method, device, equipment and readable storage medium |
| CN114252005A (en) * | 2021-12-22 | 2022-03-29 | 广东石油化工学院 | Portable swing monitoring method and device for skyscraper building |
| CN114912509A (en) * | 2022-04-06 | 2022-08-16 | 上海擎测机电工程技术有限公司 | Equipment evaluation model establishing method based on equipment historical data and real-time data |
| CN115452421A (en) * | 2022-08-01 | 2022-12-09 | 中国第一汽车股份有限公司 | Test method for rolling radius and load radius of tire |
| CN115790804A (en) * | 2023-02-08 | 2023-03-14 | 福建省智能交通信息工程有限公司 | Dynamic truck scale state monitoring method, medium, equipment and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201685818U (en) * | 2009-12-02 | 2010-12-29 | 上海多为电子科技有限公司 | Automobile intelligent speed monitoring system |
| CN105365665A (en) * | 2014-08-25 | 2016-03-02 | 现代自动车株式会社 | Apparatus for generating virtual engine sound |
| CN105865598A (en) * | 2016-05-04 | 2016-08-17 | 成都皆为科技有限公司 | Dynamic real-time monitoring system and method of car |
| CN205553956U (en) * | 2016-03-11 | 2016-09-07 | 武平泓鑫工业技术开发有限公司 | Control system for electric vehicle |
| CN106228806A (en) * | 2016-07-29 | 2016-12-14 | 北京汇通天下物联科技有限公司 | A kind of method judging vehicle load state based on sound |
| CN110232170A (en) * | 2019-06-18 | 2019-09-13 | 北京蜂云科创信息技术有限公司 | A method of judging vehicle load state |
| CN111121938A (en) * | 2020-01-02 | 2020-05-08 | 深圳市汉德网络科技有限公司 | Method for monitoring vehicle load in real time, terminal equipment and computer readable storage medium |
| CN111177936A (en) * | 2020-01-02 | 2020-05-19 | 深圳市汉德网络科技有限公司 | Method for reducing vehicle load error and computer readable storage medium |
-
2020
- 2020-05-28 CN CN202010470497.9A patent/CN111912506A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201685818U (en) * | 2009-12-02 | 2010-12-29 | 上海多为电子科技有限公司 | Automobile intelligent speed monitoring system |
| CN105365665A (en) * | 2014-08-25 | 2016-03-02 | 现代自动车株式会社 | Apparatus for generating virtual engine sound |
| CN205553956U (en) * | 2016-03-11 | 2016-09-07 | 武平泓鑫工业技术开发有限公司 | Control system for electric vehicle |
| CN105865598A (en) * | 2016-05-04 | 2016-08-17 | 成都皆为科技有限公司 | Dynamic real-time monitoring system and method of car |
| CN106228806A (en) * | 2016-07-29 | 2016-12-14 | 北京汇通天下物联科技有限公司 | A kind of method judging vehicle load state based on sound |
| CN110232170A (en) * | 2019-06-18 | 2019-09-13 | 北京蜂云科创信息技术有限公司 | A method of judging vehicle load state |
| CN111121938A (en) * | 2020-01-02 | 2020-05-08 | 深圳市汉德网络科技有限公司 | Method for monitoring vehicle load in real time, terminal equipment and computer readable storage medium |
| CN111177936A (en) * | 2020-01-02 | 2020-05-19 | 深圳市汉德网络科技有限公司 | Method for reducing vehicle load error and computer readable storage medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408591A (en) * | 2021-06-01 | 2021-09-17 | 上海自动化仪表有限公司 | Process trend analysis and prediction method based on intelligent instrument |
| CN113173175A (en) * | 2021-06-09 | 2021-07-27 | 一汽解放汽车有限公司 | Vehicle weight determination method and device |
| CN113593079A (en) * | 2021-07-30 | 2021-11-02 | 东风商用车有限公司 | Road condition self-adaption method, device, equipment and readable storage medium |
| CN114252005A (en) * | 2021-12-22 | 2022-03-29 | 广东石油化工学院 | Portable swing monitoring method and device for skyscraper building |
| CN114252005B (en) * | 2021-12-22 | 2023-06-13 | 广东石油化工学院 | Portable swing monitoring method and device for skyscraper |
| CN114912509A (en) * | 2022-04-06 | 2022-08-16 | 上海擎测机电工程技术有限公司 | Equipment evaluation model establishing method based on equipment historical data and real-time data |
| CN115452421A (en) * | 2022-08-01 | 2022-12-09 | 中国第一汽车股份有限公司 | Test method for rolling radius and load radius of tire |
| CN115790804A (en) * | 2023-02-08 | 2023-03-14 | 福建省智能交通信息工程有限公司 | Dynamic truck scale state monitoring method, medium, equipment and device |
| CN115790804B (en) * | 2023-02-08 | 2023-04-21 | 福建省智能交通信息工程有限公司 | Dynamic truck scale state monitoring method, medium, equipment and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111912506A (en) | Method and device for determining the load state of a motor vehicle | |
| EP2690423B1 (en) | Vehicle data analysis apparatus, vehicle data analysis method, and defect diagnosis apparatus | |
| CN109767023A (en) | A kind of predictor method and system of vehicle load state | |
| US20130054107A1 (en) | System and method for identifying characteristics of a vehicle | |
| CN106228806B (en) | A method of vehicle load state is judged based on sound | |
| CN106097709A (en) | Driving behavior recognition methods based on intelligent vehicle mounted terminal | |
| US20070136015A1 (en) | Diagnosis apparatus for diagnosing state of equipment | |
| EP3812218A1 (en) | Indication diagnosis device and method | |
| CN110887679A (en) | Rail transit vehicle health management method, device and system | |
| US11274994B2 (en) | Method for determining a parameter of a wheel of an observed railway vehicle and evaluation unit | |
| SE541828C2 (en) | Method and control arrangement for prediction of malfunction of a wheel bearing unit of an axle in a vehicle | |
| CN113129602A (en) | Vehicle state monitoring method and device, storage medium and electronic equipment | |
| CN113673815A (en) | Mine car scheduling method and device based on vehicle data processing | |
| CN115841765A (en) | Vehicle position blind area monitoring method and device, electronic equipment and readable storage medium | |
| EP3891512A1 (en) | System and method for providing an indication of driving performance | |
| JP2017096704A (en) | Weight detection device, weight detection method and weight detection system | |
| CN113112061B (en) | Method and device for predicting fuel consumption of vehicle | |
| CN116499772B (en) | Vehicle braking performance evaluation method and device, electronic equipment and storage medium | |
| US20240109548A1 (en) | Systems and methods for determining an estimated weight of a vehicle | |
| CN117421542B (en) | Method, system and device for calculating sliding speed of aircraft in and out of service area | |
| CN114323706B (en) | Train ATO control fault detection method, device, equipment and medium | |
| US20230116159A1 (en) | Vehicle consumables management system and method | |
| US20240118175A1 (en) | System and method for identifying a tire contact length from radial acceleration signals | |
| CN115985101A (en) | Duration prediction platform and method based on intelligent traffic data analysis | |
| US20230072343A1 (en) | Vehicle occupant monitoring device and method |
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: 20201110 |
|
| RJ01 | Rejection of invention patent application after publication |