CN116481626B - Vehicle-mounted weighing self-adaptive high-precision calibration method and system - Google Patents
Vehicle-mounted weighing self-adaptive high-precision calibration method and system Download PDFInfo
- Publication number
- CN116481626B CN116481626B CN202310770603.9A CN202310770603A CN116481626B CN 116481626 B CN116481626 B CN 116481626B CN 202310770603 A CN202310770603 A CN 202310770603A CN 116481626 B CN116481626 B CN 116481626B
- Authority
- CN
- China
- Prior art keywords
- weighing
- area
- point
- vehicle
- mapping relation
- 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
- 238000005303 weighing Methods 0.000 title claims abstract description 185
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013507 mapping Methods 0.000 claims abstract description 135
- 238000001514 detection method Methods 0.000 claims description 55
- 238000009434 installation Methods 0.000 claims description 27
- 238000012790 confirmation Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000005856 abnormality Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract 1
- 239000002245 particle Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005452 bending Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G23/00—Auxiliary devices for weighing apparatus
- G01G23/01—Testing or calibrating of weighing apparatus
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the technical field of vehicle-mounted weighing, in particular to a vehicle-mounted weighing self-adaptive high-precision calibration method and system. Aiming at the defects of inaccurate and incomplete existing calibration methods, the adopted technical scheme comprises the following steps: collecting an original output value of a weighing sensor; further, inputting the original output value of the weighing sensor into a loading state identification model; furthermore, a data set for optimizing training and a plurality of groups of mapping relations are input into a mapping relation optimizing model; further, outputting an optimal mapping relation; furthermore, the optimal mapping relation is started; further, judging whether to recalibrate the mapping relation; finally, if the mapping relation is recalibrated, the step of collecting the original output value of the weighing sensor is skipped. By the method, different mapping relations can be selected in a self-adaptive mode for different vehicles, the optimal mapping relation is automatically searched, calibration efficiency is improved, weighing cost is reduced, weighing precision is improved, and flow direction management and control work efficiency is improved.
Description
Technical Field
The invention relates to the technical field of vehicle-mounted weighing, in particular to a vehicle-mounted weighing self-adaptive high-precision calibration method and system.
Background
And the vehicle-mounted weighing technology is used for detecting the cargo carrying capacity of the vehicle so as to monitor logistics. There are many dynamic weighing schemes for vehicles, in which only a multiple linear regression equation is used to calibrate the weighing sensor, but in practical applications, only the multiple linear regression equation has the following disadvantages:
1. the complexity of the vehicle state is ignored. In the process of parking and loading the vehicle, the vehicle is often influenced by surrounding environments (such as parking in a pothole, a slope and the like), so that uneven stress of the weighing sensor is caused, and then nonlinear change of the weighing sensor is caused;
2. uncertainty in the shipment process is ignored. Because the goods such as the dregs, the bagged cement and the like are easily influenced by human factors in the process of loading, the unbalanced loading condition occurs;
the diversity of load cell installations is neglected. Different vehicle types, different installation positions and even different installation methods can influence the signal performance of the weighing sensor, and the single unified multiple regression linear relation cannot truly reflect the specificity of the real loading weight of each vehicle.
Disclosure of Invention
The invention mainly aims to provide a vehicle-mounted weighing self-adaptive high-precision calibration method and system.
In order to achieve the above purpose, the invention provides a vehicle-mounted weighing self-adaptive high-precision calibration method, which comprises the following steps:
collecting an original output value of a weighing sensor; only two groups of weighing sensors are arranged on the vehicle, one group of weighing sensors is arranged on a front axle of the vehicle, the other group of weighing sensors is arranged on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle;
inputting the original output value of the weighing sensor into a pre-trained cargo state identification model;
if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, and the output of the data set for optimizing training is the weighing difference value of a wagon balance, wherein the original output difference value of the weighing sensor is the output change value from the current start of loading to the current end of loading, the weighing difference value of the wagon balance is the weighing change value from the current start of loading to the current end of loading, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations;
outputting an optimal mapping relation based on the mapping relation optimizing model;
starting an optimal mapping relation to output a weighing difference value in the loading process of the weighing sensor;
according to a preset mapping relation recalibration rule, judging whether to recalibrate the mapping relation;
and if the mapping relation is recalibrated, skipping to execute the step of collecting the original output value of the weighing sensor until the optimal mapping relation is started.
The invention also provides a vehicle-mounted weighing self-adaptive high-precision calibration system, which comprises: the system comprises a memory, a processor, two groups of weighing sensors and a wagon balance; the memory, the wagon balance and the two groups of weighing sensors are electrically connected with the processor;
the memory stores instructions, and the processor is configured to execute the instructions of the memory to implement the following functions:
collecting an original output value of the weighing sensor; only two groups of weighing sensors are arranged on the vehicle, one group of weighing sensors is arranged on a front axle of the vehicle, the other group of weighing sensors is arranged on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle;
inputting the original output value of the weighing sensor into a pre-trained cargo state identification model;
if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, and the output of the data set for optimizing training is the weighing difference value of a wagon balance, wherein the original output difference value of the weighing sensor is the output change value from the current start of loading to the current end of loading, the weighing difference value of the wagon balance is the weighing change value from the current start of loading to the current end of loading, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations;
outputting an optimal mapping relation based on the mapping relation optimizing model;
starting an optimal mapping relation to output a weighing difference value in the loading process of the weighing sensor;
according to a preset mapping relation recalibration rule, judging whether to recalibrate the mapping relation;
and if the mapping relation is recalibrated, skipping to execute the step of collecting the original output value of the weighing sensor until the optimal mapping relation is started.
According to the high-precision calibration method provided by the invention, the original output value of the weighing sensor is acquired; only two groups of weighing sensors are arranged on the vehicle, one group of weighing sensors is arranged on a front axle of the vehicle, the other group of weighing sensors is arranged on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle; further, inputting the original output value of the weighing sensor into a pre-trained cargo state identification model; if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, the weighing difference value of the wagon balance is output change value from the current loading to the current ending, the weighing difference value of the wagon balance is the weighing change value from the current loading to the current ending, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations; further, outputting an optimal mapping relation based on the mapping relation optimizing model; furthermore, an optimal mapping relation is started for the weighing sensor to output a weighing difference value in the loading process; further, whether the mapping relation is recalibrated or not is judged according to a preset mapping relation recalibration rule; finally, if the mapping relation is recalibrated, the step of collecting the original output value of the weighing sensor is skipped until the optimal mapping relation is started. According to the method, different mapping relations can be selected in a self-adaptive mode for different vehicles, the actual loading situation is reflected better, the optimal mapping relation is automatically found through the mapping relation optimizing model, the calibration efficiency is improved, in addition, the weighing sensors are arranged at key positions, the weighing cost is reduced, the weighing precision can be improved, and the flow direction management and control working efficiency is improved.
Drawings
FIG. 1 is a flow chart of a vehicle-mounted weighing self-adaptive high-precision calibration method provided by an embodiment of the invention;
FIG. 2 is a schematic diagram illustrating the installation of two sets of weighing sensors in a vehicle-mounted weighing adaptive high-precision calibration method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the use of a first region in a vehicle-mounted weighing adaptive high-precision calibration method according to an embodiment of the present invention;
FIG. 4 is a flowchart of optimizing a mapping relation optimizing model in a vehicle-mounted weighing self-adaptive high-precision calibration method provided by the embodiment of the invention;
FIG. 5 is a schematic diagram of the structural components of a vehicle-mounted weighing self-adaptive high-precision calibration system according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the invention provides a vehicle-mounted weighing self-adaptive high-precision calibration method, wherein fig. 1 is an overall flow chart, fig. 2 is an installation schematic diagram of two groups of weighing sensors, fig. 3 is a use schematic diagram of a first area, and fig. 4 is an optimizing flow chart of a mapping relation optimizing model, as shown in fig. 1, and the method comprises the following steps:
step S1, acquiring an original output value of a weighing sensor; only two groups of weighing sensors are installed on the vehicle, one group of weighing sensors is installed on a front axle of the vehicle, the other group of weighing sensors is installed on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle.
In this step, unlike the prior art, only two sets of weighing sensors are installed, so that the device cost can be reduced, the installation time can be saved, and the load change of the carriage can be well perceived by symmetrical distribution.
In this step, preferably, the two sets of load cells are mounted on the front axle furthest from the head of the vehicle and on the rear axle closest to the head of the vehicle, respectively; compared with other front axles, the mounting space of the front axle furthest from the vehicle head is most sufficient, so that the mounting difficulty of the weighing sensor can be reduced; compared with other rear axles, the mounting space of the rear axle closest to the vehicle head is most sufficient, and the mounting difficulty of the weighing sensor can be reduced.
Before this step, the method further comprises: collecting a data set for cargo identification training, and inputting the data set for cargo identification training into an artificial neural network for training to obtain a cargo state identification model; the data set for loading identification training comprises an original output value from the current loading of each group of weighing sensors to the current loading of the weighing sensors, and a loading starting point and a loading ending point which are manually calibrated in the original output value. Wherein, optionally, the data for the cargo identification training is established for a sliding window of 10 seconds.
Before this step, the method further comprises:
acquiring a first front axle image and a first rear axle image according to a preset image acquisition requirement; the front axle in the first front axle image is to be provided with a weighing sensor, the rear axle in the first rear axle image is to be provided with a weighing sensor, and the image acquisition requirements comprise: the front axle in the first front axle image has the same size as the front axle in the pre-stored second front axle image; the central area of the first rear axle image is a black rear axle, the other areas are white areas without patterns, and the rear axle in the first rear axle image is the same as the rear axle in the pre-stored second rear axle image in size;
superimposing the second front axle image on the first front axle image and the second rear axle image on the first rear axle image; the front axle in the second front axle image is a new axle, and the front axle in the second front axle image is a white front axle, and the rest areas are transparent areas; the middle area of the second rear axle image is a white rear axle, the rest areas are transparent areas, and the rear axle in the second front axle image is a new axle;
detecting whether black pixel points exist in a first area of the first front axle image or not, and detecting whether black pixel points exist in a second area of the first rear axle image or not; wherein the first region and the second region are defined in advance; the front axle comprises a first transverse axle, a first left connecting disc and a first right connecting disc which are respectively fixed at two ends of the first transverse axle, wherein the joint surface of the first transverse axle and the first left connecting disc comprises a first left lowest point, the joint surface of the first transverse axle and the first right connecting disc comprises a first right lowest point, a first area is arched, the left end point of the first area is overlapped with the first left lowest point, the right end point of the first area is overlapped with the first right lowest point, and the height of the first area is a first preset value; the rear axle comprises a second transverse axle, a second left connecting disc and a second right connecting disc which are respectively fixed at two ends of the second transverse axle, the joint surface of the second transverse axle and the second left connecting disc comprises a second left lowest point, the joint surface of the second transverse axle and the second right connecting disc comprises a second right lowest point, a second area is arched, the left end point of the second area coincides with the second left lowest point, the right end point of the second area coincides with the second right lowest point, and the height of the second area is a second preset value;
and confirming the optimal mounting positions of the two groups of weighing sensors according to the detection result of the black pixel points and a preset optimal mounting position confirmation rule.
The bending part of the axle can be highlighted in an image superposition mode, so that the pixel point detection is more convenient. Furthermore, only the first area and the second area which are defined in advance are detected, so that the detection of an invalid area can be avoided, and the detection efficiency is improved.
wherein ,
the optimal installation position confirmation rule comprises a first sub-rule and a second sub-rule; the first sub-rule is used for confirming a first optimal installation position, wherein the first optimal installation position is the position of the weighing sensor to be installed at first in the transverse direction, and the second sub-rule is used for confirming a second optimal installation position, and the second optimal installation position is the position of the weighing sensor to be installed at last in the transverse direction;
the first sub-rule includes:
if only the first area of the first front axle image has black pixel points, determining the position information of a first datum point in the first area, wherein the first datum point is the black pixel point at the lowest point in the first area, and the position information of the first datum point comprises a first transverse distance from the left end point of the first area and a second transverse distance from the right end point of the first area; setting a first position corresponding to the first datum point as a first optimal installation position, wherein if the first transverse distance is equal to the second transverse distance or the first transverse distance is larger than the second transverse distance, the first position is positioned on a left half shaft of the front axle, a third transverse distance between a left end point of the first area and the first position falls within a preset first numerical range, and the transverse distance between the first position and the first datum point is maximum; if the first transverse distance is smaller than the second transverse distance, the first position is positioned on the right half axle of the front axle, the fourth transverse distance between the right end point of the first area and the first position falls within a first numerical range, and the transverse distance between the first position and the first datum point is the largest;
if only the second area of the first rear axle image has black pixel points, determining the position information of a second datum point in the second area, wherein the second datum point is the black pixel point at the lowest point in the second area, and the position information of the second datum point comprises a fifth transverse distance from the left end point of the second area and a sixth transverse distance from the right end point of the second area; setting a second position corresponding to the second datum point as a first optimal installation position, wherein if the fifth transverse distance is equal to or greater than the sixth transverse distance, the second position is positioned on a left half shaft of the rear axle, a seventh transverse distance between a left end point of the second area and the second position falls within a preset second numerical range, and the transverse distance between the second position and the second datum point is maximum; if the fifth transverse distance is smaller than the sixth transverse distance, the second position is positioned on the right half axle of the rear axle, the eighth transverse distance between the right end point of the second area and the second position falls in a second numerical range, and the transverse distance between the second position and the second reference point is the largest;
if the first area of the first front axle image and the second area of the first rear axle image are not provided with black pixel points, setting a third position as a first optimal installation position, wherein the third position is positioned on a left half shaft of a first transverse shaft of the front axle, and a ninth transverse distance between the first left connecting disc and the third position falls at the middle point of a first numerical range;
if the first area of the first front axle image and the second area of the first rear axle image are provided with black pixel points, determining the position of a first datum point and the position of a second datum point; if the first datum point is lower than the second datum point, setting a first position corresponding to the first datum point as a first optimal installation position, if the second datum point is lower than the first datum point, setting a second position corresponding to the second datum point as the first optimal installation position, and if the first datum point is equal to the second datum point in height, setting the first position corresponding to the first datum point as the first optimal installation position.
Through black pixel point detection, the bending deformation degree of which axletree is bigger can be known to can compromise this axle condition when designing the mounted position, avoid direct mount in this bending deformation position, can not aggravate the bending deformation of this axletree, guarantee the accuracy of follow-up weighing detection again.
In order to further improve the detection efficiency, among them, preferably,
detecting whether a black pixel point with an inflection point exists in the first rough detection area; the detection sequence is that the first upper fine detection area A1, the first coarse detection area A2 and the first lower fine detection area A3 are respectively positioned in the upper, middle and lower areas of the first area, wherein the detection sequence is that the first middle and the rear are diffused towards the two sides;
if the black pixel point is the inflection point, the detection of the black pixel point is finished;
if the black pixel points which are not inflection points exist, and the black pixel points in the first coarse detection area A2 are arranged in an inverted cone shape, detecting the first fine detection area A3 until the black pixel points which are inflection points are detected, wherein the detection sequence is an area pointed by the inverted cone arrangement firstly and an area pointed by the non-inverted cone arrangement later;
if no black pixel point exists, detecting the first upper fine detection area A1 until the black pixel point which is an inflection point is detected;
the step of detecting whether a black pixel exists in the second area of the first rear axle image comprises the following steps:
detecting whether a black pixel point with an inflection point exists in the second coarse detection area; the detection sequence is that the first middle and the second sides are diffused, the second area consists of a second upper fine detection area, a second coarse detection area and a second lower fine detection area, and the second upper fine detection area, the second coarse detection area and the second lower fine detection area are respectively positioned in the upper, middle and lower areas of the second area;
if the black pixel point is the inflection point, the detection of the black pixel point is finished;
if the black pixel points which are not inflection points exist, and the black pixel points in the second coarse detection area are arranged in an inverted cone shape, detecting the second lower fine detection area until the black pixel points which are inflection points are detected, wherein the detection sequence is an area pointed by the inverted cone arrangement firstly and an area pointed by the non-inverted cone arrangement later;
and if the black pixel point does not exist, detecting the second upper fine detection area until the black pixel point serving as the inflection point is detected.
The area pointed by the inverted cone arrangement can be a circular area, and the radius of the area is preset.
And S2, inputting the original output value of the weighing sensor into a pre-trained cargo state identification model.
Step S3, if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, the weighing difference value of the wagon balance is output change value from the current loading to the current loading, the weighing difference value of the wagon balance is the weighing change value from the current loading to the current loading, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations.
In the step, three groups of mapping relations to be optimized are provided, and the three groups of mapping relations are sequentially:
；
；
；
wherein ,ifor the sequencing of the load cells,for the original output difference of the first load cell,/->For the original output difference of the second load cell,/->Is the firstiRaw output difference of individual load cells, < +.>For the weighing difference of the weighing cell, +.>~/>Is a parameter to be optimized.
And S4, outputting an optimal mapping relation based on the mapping relation optimizing model.
In the step, the mapping relation optimizing model is a Particle Swarm Optimization (PSO), three groups of mapping relations are independently iterated and operated for multiple times (such as 100 times), the results obtained by the multiple times of operation are counted with optimal values and worst values, and the optimal mapping relation is confirmed by comparing the counted results. The specific flow of the particle swarm algorithm comprises the following steps: starting, initializing a particle swarm, calculating the fitness value of each particle, updating the particle speed position according to an updating formula, updating an individual extremum and a group extremum according to the fitness value, judging whether the maximum iteration number is reached, if not, jumping to the step of calculating the fitness value of each particle, and if so, ending.
And S5, starting an optimal mapping relation for the weighing sensor to output a weighing difference value in the loading process.
And S6, judging whether to recalibrate the mapping relation according to a preset mapping relation recalibration rule.
When only considering the time factor, the early calibration or the late calibration is easy to be caused, and when the actual loss of the vehicle is considered (such as shaking the carriage when the road surface jolts and shakes the carriage when the vehicle is loaded, and shaking the carriage when the vehicle is braked suddenly), the calibration can be more in line with the actual demand, so in the step, the mapping relation recalibration rule comprises:
calculating the current characteristic disturbance value of the vehicle according to the vehicle cabin jitter value and a preset characteristic disturbance value calculation rule; if the vehicle cabin jitter value falls in a third numerical range, the characteristic disturbance value is the product of the jitter duration time and a third preset value, and the unit of the jitter duration time is hours; if the vehicle cabin jitter value falls in the fourth numerical range, the characteristic disturbance value is the product of the jitter duration and a fourth preset value; if the vehicle cabin jitter value falls in a fifth numerical range, the characteristic disturbance value is the product of the jitter duration and a fifth preset value; the values of the third numerical range are smaller than the minimum value of the fourth numerical range, the values of the fourth numerical range are smaller than the minimum value of the fifth numerical range, the third preset value is smaller than the fourth preset value, the fourth preset value is smaller than the fifth preset value, and all the third preset value to the fifth preset value are positive numbers;
judging whether the current characteristic disturbance value of the vehicle is larger than a sixth preset value or not;
and if the mapping relation is larger than the sixth preset value, recalibrating the mapping relation.
In this step, the mapping relationship recalibration rule may also be:
when the starting time length reaches a seventh preset value, recalibrating the mapping relation, wherein the starting time length is the use time length of the optimal mapping relation output by the mapping relation optimizing model for the last time;
or ,
detecting that the weighing sensor is abnormal, and recalibrating the mapping relation after eliminating the abnormal weighing sensor.
Wherein load cell anomalies include, but are not limited to, hardware damage, data skip.
And S7, if the mapping relation is recalibrated, skipping to execute the step of collecting the original output value of the weighing sensor until the optimal mapping relation is started.
According to the high-precision calibration method provided by the embodiment, the original output value of the weighing sensor is collected; only two groups of weighing sensors are arranged on the vehicle, one group of weighing sensors is arranged on a front axle of the vehicle, the other group of weighing sensors is arranged on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle; further, inputting the original output value of the weighing sensor into a pre-trained cargo state identification model; if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, the weighing difference value of the wagon balance is output change value from the current loading to the current ending, the weighing difference value of the wagon balance is the weighing change value from the current loading to the current ending, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations; further, outputting an optimal mapping relation based on the mapping relation optimizing model; furthermore, an optimal mapping relation is started for the weighing sensor to output a weighing difference value in the loading process; further, whether the mapping relation is recalibrated or not is judged according to a preset mapping relation recalibration rule; finally, if the mapping relation is recalibrated, the step of collecting the original output value of the weighing sensor is skipped until the optimal mapping relation is started. According to the method, different mapping relations can be selected in a self-adaptive mode for different vehicles, the actual loading situation is reflected better, the optimal mapping relation is automatically found through the mapping relation optimizing model, the calibration efficiency is improved, in addition, the weighing sensors are arranged at key positions, the weighing cost is reduced, the weighing precision can be improved, and the flow direction management and control working efficiency is improved.
The embodiment of the invention also provides a vehicle-mounted weighing self-adaptive high-precision calibration system, as shown in fig. 5, comprising: a memory 10, a processor 11, two groups of weighing sensors 12 and a wagon balance 13; the memory 10, the wagon balance 13 and the two groups of weighing sensors 12 are electrically connected with the processor 11;
the memory 10 stores instructions and the processor 11 is configured to execute the instructions of the memory to perform the following functions:
collecting an original output value of the weighing sensor 12; wherein, only two groups of weighing sensors 12 are arranged on the vehicle, one group of weighing sensors 12 is arranged on the front axle of the vehicle, the other group of weighing sensors 12 is arranged on the rear axle of the vehicle, and the two groups of weighing sensors 12 are symmetrically distributed, and the symmetry plane coincides with the central symmetry plane of the vehicle;
inputting the original output value of the load cell 12 into a pre-trained loading state identification model;
if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, the weighing difference value of the wagon balance is output change value from the current loading to the current loading, the weighing difference value of the wagon balance 13 is the weighing change value from the current loading to the current loading, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations;
outputting an optimal mapping relation based on the mapping relation optimizing model;
starting the optimal mapping relation to enable the weighing sensor 12 to output a weighing difference value in the loading process;
according to a preset mapping relation recalibration rule, judging whether to recalibrate the mapping relation;
if the mapping is recalibrated, the step of collecting the original output value of the load cell 12 is skipped until the optimal mapping is enabled.
In this embodiment, for specific implementation of each device in the above system embodiment, please refer to the description in the above method embodiment, and no further description is given here.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. The vehicle-mounted weighing self-adaptive high-precision calibration method is characterized by comprising the following steps of:
collecting an original output value of a weighing sensor; only two groups of weighing sensors are arranged on the vehicle, one group of weighing sensors is arranged on a front axle of the vehicle, the other group of weighing sensors is arranged on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle;
inputting the original output value of the weighing sensor into a pre-trained cargo state identification model;
if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, and the output of the data set for optimizing training is the weighing difference value of a wagon balance, wherein the original output difference value of the weighing sensor is the output change value from the current start of loading to the current end of loading, the weighing difference value of the wagon balance is the weighing change value from the current start of loading to the current end of loading, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations;
outputting an optimal mapping relation based on the mapping relation optimizing model;
starting an optimal mapping relation to output a weighing difference value in the loading process of the weighing sensor;
according to a preset mapping relation recalibration rule, judging whether to recalibrate the mapping relation;
and if the mapping relation is recalibrated, skipping to execute the step of collecting the original output value of the weighing sensor until the optimal mapping relation is started.
2. The vehicle-mounted weighing self-adaptive high-precision calibration method according to claim 1, wherein three groups of mapping relations to be optimized are provided, and the three groups of mapping relations are as follows:
；
；
；
wherein ,ifor the sequencing of the load cells,for the original output difference of the first of said load cells,/>For the original output difference of the second of said load cells, < >>Is the firstiThe raw output differences of each of the load cells,for the weighing difference of the weighing cell, < >>~/>Is a parameter to be optimized.
3. The method for adaptively calibrating vehicle-mounted weighing according to claim 1, wherein before the step of collecting the original output value of the weighing sensor, the method further comprises:
acquiring a first front axle image and a first rear axle image according to a preset image acquisition requirement; the front axle in the first front axle image is to be provided with the weighing sensor, the rear axle in the first rear axle image is to be provided with the weighing sensor, and the image acquisition requirements comprise: the front axle in the first front axle image has the same size as the front axle in the pre-stored second front axle image; the central area of the first rear axle image is a black rear axle, the other areas are white areas without patterns, and the rear axle in the first rear axle image is the same as the rear axle in the pre-stored second rear axle image in size;
superimposing the second front axle image on the first front axle image and the second rear axle image on the first rear axle image; the front axle in the second front axle image is a new axle, and the front axle in the second front axle image is a white front axle, and the rest areas are transparent areas; the middle area of the second rear axle image is a white rear axle, the rest areas are transparent areas, and the rear axle in the second front axle image is a new axle;
detecting whether black pixel points exist in a first area of the first front axle image or not, and detecting whether black pixel points exist in a second area of the first rear axle image or not; wherein the first region and the second region are defined in advance; the front axle comprises a first transverse axle, a first left connecting disc and a first right connecting disc which are respectively fixed at two ends of the first transverse axle, wherein the joint surface of the first transverse axle and the first left connecting disc comprises a first left lowest point, the joint surface of the first transverse axle and the first right connecting disc comprises a first right lowest point, a first area is arched, the left end point of the first area is overlapped with the first left lowest point, the right end point of the first area is overlapped with the first right lowest point, and the height of the first area is a first preset value; the rear axle comprises a second transverse axle, a second left connecting disc and a second right connecting disc which are respectively fixed at two ends of the second transverse axle, the joint surface of the second transverse axle and the second left connecting disc comprises a second left lowest point, the joint surface of the second transverse axle and the second right connecting disc comprises a second right lowest point, a second area is arched, the left end point of the second area coincides with the second left lowest point, the right end point of the second area coincides with the second right lowest point, and the height of the second area is a second preset value;
and confirming the optimal mounting positions of the two groups of weighing sensors according to the detection result of the black pixel points and a preset optimal mounting position confirmation rule.
4. A vehicle-mounted weighing self-adaptive high-precision calibration method according to claim 3, wherein the optimal mounting position confirmation rule comprises a first sub-rule and a second sub-rule; the first sub-rule is used for confirming a first optimal installation position, wherein the first optimal installation position is the position of the weighing sensor to be installed at first in the transverse direction, and the second sub-rule is used for confirming a second optimal installation position, and the second optimal installation position is the position of the weighing sensor to be installed at last in the transverse direction;
the first sub-rule includes:
if only the first area of the first front axle image has black pixel points, determining the position information of a first datum point in the first area, wherein the first datum point is the black pixel point at the lowest point in the first area, and the position information of the first datum point comprises a first transverse distance from the left end point of the first area and a second transverse distance from the right end point of the first area; setting a first position corresponding to the first datum point as a first optimal installation position, wherein if the first transverse distance is equal to the second transverse distance or the first transverse distance is larger than the second transverse distance, the first position is positioned on a left half shaft of the front axle, a third transverse distance between a left end point of the first area and the first position falls within a preset first numerical range, and the transverse distance between the first position and the first datum point is maximum; if the first transverse distance is smaller than the second transverse distance, the first position is positioned on the right half axle of the front axle, the fourth transverse distance between the right end point of the first area and the first position falls within a first numerical range, and the transverse distance between the first position and the first datum point is the largest;
if only the second area of the first rear axle image has black pixel points, determining the position information of a second datum point in the second area, wherein the second datum point is the black pixel point at the lowest point in the second area, and the position information of the second datum point comprises a fifth transverse distance from the left end point of the second area and a sixth transverse distance from the right end point of the second area; setting a second position corresponding to the second datum point as a first optimal installation position, wherein if the fifth transverse distance is equal to or greater than the sixth transverse distance, the second position is positioned on a left half shaft of the rear axle, a seventh transverse distance between a left end point of the second area and the second position falls within a preset second numerical range, and the transverse distance between the second position and the second datum point is maximum; if the fifth transverse distance is smaller than the sixth transverse distance, the second position is positioned on the right half axle of the rear axle, the eighth transverse distance between the right end point of the second area and the second position falls in a second numerical range, and the transverse distance between the second position and the second reference point is the largest;
if the first area of the first front axle image and the second area of the first rear axle image are not provided with black pixel points, setting a third position as a first optimal installation position, wherein the third position is positioned on a left half shaft of a first transverse shaft of the front axle, and a ninth transverse distance between the first left connecting disc and the third position falls at the middle point of a first numerical range;
if the first area of the first front axle image and the second area of the first rear axle image are provided with black pixel points, determining the position of a first datum point and the position of a second datum point; if the first datum point is lower than the second datum point, setting a first position corresponding to the first datum point as a first optimal installation position, if the second datum point is lower than the first datum point, setting a second position corresponding to the second datum point as the first optimal installation position, and if the first datum point is equal to the second datum point in height, setting the first position corresponding to the first datum point as the first optimal installation position.
5. A vehicle-mounted weighing self-adaptive high-precision calibration method according to claim 3, wherein the step of detecting whether black pixels exist in the first area of the first front axle image comprises the following steps:
detecting whether a black pixel point with an inflection point exists in the first rough detection area; the detection sequence is that the first upper fine detection area, the first coarse detection area and the first lower fine detection area are respectively positioned in the upper, middle and lower areas of the first area;
if the black pixel point is the inflection point, the detection of the black pixel point is finished;
if the black pixel points which are not inflection points exist, and the black pixel points in the first coarse detection area are arranged in an inverted cone shape, detecting the first fine detection area until the black pixel points which are inflection points are detected, wherein the detection sequence is an area pointed by the inverted cone arrangement firstly and an area pointed by the non-inverted cone arrangement later;
if the black pixel point does not exist, detecting the first upper fine detection area until the black pixel point serving as an inflection point is detected;
the step of detecting whether a black pixel exists in the second area of the first rear axle image comprises the following steps:
detecting whether a black pixel point with an inflection point exists in the second coarse detection area; the detection sequence is that the first middle and the second sides are diffused, the second area consists of a second upper fine detection area, a second coarse detection area and a second lower fine detection area, and the second upper fine detection area, the second coarse detection area and the second lower fine detection area are respectively positioned in the upper, middle and lower areas of the second area;
if the black pixel point is the inflection point, the detection of the black pixel point is finished;
if the black pixel points which are not inflection points exist, and the black pixel points in the second coarse detection area are arranged in an inverted cone shape, detecting the second lower fine detection area until the black pixel points which are inflection points are detected, wherein the detection sequence is an area pointed by the inverted cone arrangement firstly and an area pointed by the non-inverted cone arrangement later;
and if the black pixel point does not exist, detecting the second upper fine detection area until the black pixel point serving as the inflection point is detected.
6. The vehicle-mounted weighing self-adaptive high-precision calibration method according to claim 1, wherein the mapping relation recalibration rule comprises:
calculating the current characteristic disturbance value of the vehicle according to the vehicle cabin jitter value and a preset characteristic disturbance value calculation rule; if the vehicle cabin jitter value falls in a third numerical range, the characteristic disturbance value is the product of the jitter duration time and a third preset value, and the unit of the jitter duration time is hours; if the vehicle cabin jitter value falls in the fourth numerical range, the characteristic disturbance value is the product of the jitter duration and a fourth preset value; if the vehicle cabin jitter value falls in a fifth numerical range, the characteristic disturbance value is the product of the jitter duration and a fifth preset value; the values of the third numerical range are smaller than the minimum value of the fourth numerical range, the values of the fourth numerical range are smaller than the minimum value of the fifth numerical range, the third preset value is smaller than the fourth preset value, the fourth preset value is smaller than the fifth preset value, and all the third preset value to the fifth preset value are positive numbers;
judging whether the current characteristic disturbance value of the vehicle is larger than a sixth preset value or not;
and if the mapping relation is larger than the sixth preset value, recalibrating the mapping relation.
7. The vehicle-mounted weighing self-adaptive high-precision calibration method according to claim 1, wherein the mapping relation recalibration rule comprises:
when the starting time length reaches a seventh preset value, recalibrating the mapping relation, wherein the starting time length is the use time length of the optimal mapping relation output by the mapping relation optimizing model for the last time;
or ,
detecting that the weighing sensor is abnormal, and recalibrating the mapping relation after eliminating the weighing sensor with the abnormality.
8. The method for calibrating the vehicle-mounted weighing self-adaption high precision according to claim 1, wherein the two groups of weighing sensors are respectively arranged on a front axle farthest from the head of the vehicle and a rear axle nearest to the head of the vehicle.
9. The method for adaptively calibrating vehicle-mounted weighing according to claim 1, wherein before the step of collecting the original output value of the weighing sensor, the method further comprises:
collecting a data set for cargo identification training, and inputting the data set for cargo identification training into an artificial neural network for training to obtain a cargo state identification model; the data set for loading identification training comprises original output values from the current loading of the weighing sensor to the current loading of the weighing sensor, and loading starting points and loading ending points which are manually calibrated in the original output values.
10. The utility model provides a vehicle-mounted self-adaptation's high accuracy calibration system, its characterized in that includes: the system comprises a memory, a processor, two groups of weighing sensors and a wagon balance; the memory, the wagon balance and the two groups of weighing sensors are electrically connected with the processor;
the memory stores instructions, and the processor is configured to execute the instructions of the memory to implement the following functions:
collecting an original output value of the weighing sensor; only two groups of weighing sensors are arranged on the vehicle, one group of weighing sensors is arranged on a front axle of the vehicle, the other group of weighing sensors is arranged on a rear axle of the vehicle, and the two groups of weighing sensors are symmetrically distributed and the symmetrical plane coincides with the central symmetrical plane of the vehicle;
inputting the original output value of the weighing sensor into a pre-trained cargo state identification model;
if the output result of the stock state identification model is in the stock state, inputting a data set for optimizing training and a plurality of groups of mapping relations to be optimized into a mapping relation optimizing model; the input of the data set for optimizing training is the original output difference value of the weighing sensor, and the output of the data set for optimizing training is the weighing difference value of a wagon balance, wherein the original output difference value of the weighing sensor is the output change value from the current start of loading to the current end of loading, the weighing difference value of the wagon balance is the weighing change value from the current start of loading to the current end of loading, and the plurality of groups of mapping relations comprise linear mapping relations and nonlinear mapping relations;
outputting an optimal mapping relation based on the mapping relation optimizing model;
starting an optimal mapping relation to output a weighing difference value in the loading process of the weighing sensor;
according to a preset mapping relation recalibration rule, judging whether to recalibrate the mapping relation;
and if the mapping relation is recalibrated, skipping to execute the step of collecting the original output value of the weighing sensor until the optimal mapping relation is started.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310770603.9A CN116481626B (en) | 2023-06-28 | 2023-06-28 | Vehicle-mounted weighing self-adaptive high-precision calibration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310770603.9A CN116481626B (en) | 2023-06-28 | 2023-06-28 | Vehicle-mounted weighing self-adaptive high-precision calibration method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116481626A CN116481626A (en) | 2023-07-25 |
| CN116481626B true CN116481626B (en) | 2023-08-29 |
Family
ID=87219974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310770603.9A Active CN116481626B (en) | 2023-06-28 | 2023-06-28 | Vehicle-mounted weighing self-adaptive high-precision calibration method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116481626B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5970435A (en) * | 1996-03-22 | 1999-10-19 | Yazaki Corporation | Automatic load measuring device |
| CN102506983A (en) * | 2011-10-31 | 2012-06-20 | 湖南师范大学 | Weighing error automatic compensation method of vehicle scale |
| CN103234610A (en) * | 2013-05-14 | 2013-08-07 | 湖南师范大学 | Weighing method applicable to truck scale |
| FR3055964A1 (en) * | 2016-09-14 | 2018-03-16 | Patrick Petit | DEVICE AND METHOD FOR LOADING LOADED VEHICLE |
| WO2020024873A1 (en) * | 2018-07-30 | 2020-02-06 | 白杨 | Weighing-based goods quantity calculation method |
| CN111089643A (en) * | 2020-01-02 | 2020-05-01 | 深圳市汉德网络科技有限公司 | Dynamic vehicle-mounted weighing method and system |
| CN111121939A (en) * | 2020-01-02 | 2020-05-08 | 深圳市汉德网络科技有限公司 | High-precision vehicle-mounted area weighing method |
| CN111157092A (en) * | 2020-01-02 | 2020-05-15 | 深圳市汉德网络科技有限公司 | Vehicle-mounted weighing automatic calibration method and computer readable storage medium |
| KR102165337B1 (en) * | 2020-03-10 | 2020-10-13 | 주식회사 오토비젼 | Apparatus and Method for Measuring Load Weight of Axises of a Car |
| WO2021018160A1 (en) * | 2019-07-31 | 2021-02-04 | Mettler-Toledo (Changzhou) Measurement Technology Ltd. | Hysteresis compensation method for a weighing device |
| WO2021081604A1 (en) * | 2019-10-31 | 2021-05-06 | Commonwealth Scientific And Industrial Research Organisation | Vehicle weighing system |
| CN112834013A (en) * | 2021-02-04 | 2021-05-25 | 支付宝(杭州)信息技术有限公司 | Weighing sensor unbalance loading error calibration method and system, goods shelf and article monitoring method |
| CN112985570A (en) * | 2021-02-04 | 2021-06-18 | 支付宝(杭州)信息技术有限公司 | Calibration method and system for sensor of weighing shelf |
| WO2021131091A1 (en) * | 2019-12-25 | 2021-07-01 | 新明和工業株式会社 | Computer program, estimation device, method for generating training model, and system for estimating load weight of specially-equipped vehicle |
| CN113091866A (en) * | 2021-04-06 | 2021-07-09 | 深圳市汉德网络科技有限公司 | Method and device for measuring load mass of automobile in real time |
| CN114414023A (en) * | 2021-12-30 | 2022-04-29 | 北京万集科技股份有限公司 | Sensor abnormality diagnosis method and device, and storage medium |
| CN115371790A (en) * | 2022-09-07 | 2022-11-22 | 中国兵器科学研究院宁波分院 | Sensor calibration and weighing method of vehicle dynamic weighing system |
| CN116124270A (en) * | 2023-04-18 | 2023-05-16 | 深圳亿维锐创科技股份有限公司 | Automatic intelligent calibration method for dynamic truck scale |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7783450B2 (en) * | 2007-11-14 | 2010-08-24 | Ut-Battelle, Llc | Method and system for reducing errors in vehicle weighing systems |
| JP6704375B2 (en) * | 2017-07-13 | 2020-06-03 | 日立建機株式会社 | Load compensation system |
-
2023
- 2023-06-28 CN CN202310770603.9A patent/CN116481626B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5970435A (en) * | 1996-03-22 | 1999-10-19 | Yazaki Corporation | Automatic load measuring device |
| CN102506983A (en) * | 2011-10-31 | 2012-06-20 | 湖南师范大学 | Weighing error automatic compensation method of vehicle scale |
| CN103234610A (en) * | 2013-05-14 | 2013-08-07 | 湖南师范大学 | Weighing method applicable to truck scale |
| FR3055964A1 (en) * | 2016-09-14 | 2018-03-16 | Patrick Petit | DEVICE AND METHOD FOR LOADING LOADED VEHICLE |
| WO2020024873A1 (en) * | 2018-07-30 | 2020-02-06 | 白杨 | Weighing-based goods quantity calculation method |
| WO2021018160A1 (en) * | 2019-07-31 | 2021-02-04 | Mettler-Toledo (Changzhou) Measurement Technology Ltd. | Hysteresis compensation method for a weighing device |
| WO2021081604A1 (en) * | 2019-10-31 | 2021-05-06 | Commonwealth Scientific And Industrial Research Organisation | Vehicle weighing system |
| WO2021131091A1 (en) * | 2019-12-25 | 2021-07-01 | 新明和工業株式会社 | Computer program, estimation device, method for generating training model, and system for estimating load weight of specially-equipped vehicle |
| CN111089643A (en) * | 2020-01-02 | 2020-05-01 | 深圳市汉德网络科技有限公司 | Dynamic vehicle-mounted weighing method and system |
| CN111121939A (en) * | 2020-01-02 | 2020-05-08 | 深圳市汉德网络科技有限公司 | High-precision vehicle-mounted area weighing method |
| CN111157092A (en) * | 2020-01-02 | 2020-05-15 | 深圳市汉德网络科技有限公司 | Vehicle-mounted weighing automatic calibration method and computer readable storage medium |
| KR102165337B1 (en) * | 2020-03-10 | 2020-10-13 | 주식회사 오토비젼 | Apparatus and Method for Measuring Load Weight of Axises of a Car |
| CN112985570A (en) * | 2021-02-04 | 2021-06-18 | 支付宝(杭州)信息技术有限公司 | Calibration method and system for sensor of weighing shelf |
| CN112834013A (en) * | 2021-02-04 | 2021-05-25 | 支付宝(杭州)信息技术有限公司 | Weighing sensor unbalance loading error calibration method and system, goods shelf and article monitoring method |
| CN113091866A (en) * | 2021-04-06 | 2021-07-09 | 深圳市汉德网络科技有限公司 | Method and device for measuring load mass of automobile in real time |
| CN114414023A (en) * | 2021-12-30 | 2022-04-29 | 北京万集科技股份有限公司 | Sensor abnormality diagnosis method and device, and storage medium |
| CN115371790A (en) * | 2022-09-07 | 2022-11-22 | 中国兵器科学研究院宁波分院 | Sensor calibration and weighing method of vehicle dynamic weighing system |
| CN116124270A (en) * | 2023-04-18 | 2023-05-16 | 深圳亿维锐创科技股份有限公司 | Automatic intelligent calibration method for dynamic truck scale |
Non-Patent Citations (1)
| Title |
|---|
| 某轻型物流车的实时车载称重系统方案;于法祥，苗少光;客车技术与研究(第第5期期);第32-36页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116481626A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180012494A1 (en) | Method for Providing Obstacle Maps for Vehicles | |
| CN113450353B (en) | Method and device for optimizing precision of leaf area index | |
| EP1994380A1 (en) | A system for determining a vehicle load | |
| CN111522469B (en) | Touch capacitance data adjusting method and device, electronic equipment and storage medium | |
| CN116481626B (en) | Vehicle-mounted weighing self-adaptive high-precision calibration method and system | |
| US10486711B2 (en) | Integrated body control and weight sensing system | |
| US20210095995A1 (en) | Inertial sensor and computer-implemented method for self-calibration of an inertial sensor | |
| CN113389115A (en) | Vehicle characteristic and road surface flatness detection method, device, equipment and storage medium | |
| CN107491577B (en) | Body-in-white design method and device | |
| CN112319490B (en) | Method for estimating mass center slip angle of automobile, computer equipment and storage medium | |
| US7292951B2 (en) | Systems for compensating for creep and hysteresis in a load cell | |
| JP4269296B2 (en) | Vehicle headlight optical axis direction adjusting device | |
| CN113361079A (en) | Road surface flatness detection method, device, equipment and storage medium | |
| CN115902843A (en) | Multi-laser-radar calibration method and device and electronic equipment | |
| CN110979218B (en) | Automobile parameter adjusting method and electronic equipment | |
| WO2018158971A1 (en) | Calibration device and calibration method | |
| CN115953111B (en) | Verification method, system, terminal and storage medium for order picking | |
| CN115847392B (en) | Force sensor no-load reading compensation method, device and storage medium | |
| CN116907620A (en) | System and method for calibrating an on-board weight sensor | |
| CN116908779A (en) | Method, device, equipment and storage medium for determining position of vehicle sensor | |
| CN115046617B (en) | Vehicle load measuring method, controller, storage medium and automobile | |
| CN114655131B (en) | Vehicle-mounted sensing sensor adjustment method, device, equipment and readable storage medium | |
| CN115046617A (en) | Vehicle load measuring method, controller, storage medium and automobile | |
| CN116720045A (en) | Abnormal unloading behavior identification method and device for transport vehicle and transport vehicle | |
| JP7208888B2 (en) | Computer program, estimation device, and learning model generation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |