CN113954850B - Wheel center load estimation method and system based on edge calculation and soft measurement - Google Patents
Wheel center load estimation method and system based on edge calculation and soft measurement Download PDFInfo
- Publication number
- CN113954850B CN113954850B CN202111423214.6A CN202111423214A CN113954850B CN 113954850 B CN113954850 B CN 113954850B CN 202111423214 A CN202111423214 A CN 202111423214A CN 113954850 B CN113954850 B CN 113954850B
- Authority
- CN
- China
- Prior art keywords
- wheel center
- model
- edge
- displacement
- center load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004364 calculation method Methods 0.000 title claims abstract description 19
- 238000005259 measurement Methods 0.000 title claims abstract description 16
- 230000001133 acceleration Effects 0.000 claims abstract description 54
- 238000006073 displacement reaction Methods 0.000 claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000004891 communication Methods 0.000 claims description 16
- 239000000725 suspension Substances 0.000 claims description 7
- 241000475481 Nebula Species 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims 1
- 238000009434 installation Methods 0.000 abstract 1
- 238000013499 data model Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000011900 installation process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/12—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to parameters of the vehicle itself, e.g. tyre models
- B60W40/13—Load or weight
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/12—Lateral speed
- B60W2520/125—Lateral acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Vehicle Body Suspensions (AREA)
Abstract
The invention relates to a wheel center load estimation method and a wheel center load estimation system based on edge calculation and soft measurement, wherein a plurality of models from data of acceleration and displacement sensors to wheel center load data are obtained by training from data of collected sensors under a plurality of road conditions through lines; secondly, determining the road condition of the current vehicle according to sensor data such as acceleration and displacement acquired on line, and inputting the sensor data of the acceleration and the displacement into a model corresponding to the road condition, so as to obtain the wheel center load of the vehicle in the driving process in real time; compared with the installation of a six-component tire sensor, the method has the advantages of being convenient to install, simple, mature in theory, wide in applicable vehicle type range, capable of supporting batch model deployment and management and the like while the wheel center load with high precision can be obtained in real time.
Description
Technical Field
The invention relates to the field of automobiles, in particular to a wheel center load estimation method and system based on edge calculation and soft measurement.
Background
During the running of the vehicle on the road surface, the wheel center of the tire generates six-freedom-degree load comprising three flat driving forces and three rotating moments due to the excitation of the road surface to the tire. The wheel center load of the tire has important significance for the study of the driving state of the tire, safety assessment and the like, is an important parameter for selecting load-bearing parts on the tire, and plays an important role in the analysis of the durability, the smoothness and the like of a suspension and a vehicle body. The current wheel center load of the vehicle is mainly obtained through a six-component tire sensor, the current wheel center sensor is expensive, the vehicle cost is increased, the installation process is complex, the tire assembly cost is increased, and finally, the tire assembly cost is difficult to realize in common use for tires of different models, so that the design cost of the tire can be increased.
The challenge in accurately estimating wheel center load is that, when operating under complex and constantly changing external environments and driving operations, the tires, suspensions, other components of the vehicle interact with the ground and the like, making the vehicle system highly non-linear. Non-linear models commonly used in non-linear system identification include polynomial models, gaussian processes, wavelet networks, artificial Neural Networks (ANN), and the like. However, simple models such as polynomial models often cannot represent complex system behavior resulting in poor model performance; while complex models, such as ANN, have high expression capacity, they not only lack generalization ability, but also require high computational cost. There is therefore a need for a low-cost, versatile wheel center load estimation method that balances the estimation performance and computational efficiency of the model.
Disclosure of Invention
The invention aims to solve the defects of the prior art and provides a wheel center load estimation method and system based on edge calculation and soft measurement.
In order to solve the problems, the invention adopts the following technical scheme:
a wheel center load estimation method based on edge calculation and soft measurement comprises the following steps:
step 1: the signal acquisition sensor acquires signals including acceleration signals and displacement signals; transmitting the collected signals to the edge computing equipment of the edge equipment layer;
step 2: the edge computing equipment inputs the acceleration signal and the displacement signal acquired by the signal acquisition sensor into a preset model to obtain an estimated value of the wheel center load;
and 3, step 3: and the edge computing equipment packages and uploads the obtained wheel center load estimated value, the acceleration signal and the displacement signal to a server of a cloud end layer through a communication layer, and the step is finished.
Further, the model in step 2 is a pre-trained finite impulse response model, wherein the step of obtaining the wheel center load specifically includes the following steps:
step 21: the edge computing equipment inputs the signals acquired by the signal acquisition sensor into the road condition estimation model to obtain an estimated road condition;
step 22: and inputting the signals acquired by the signal acquisition sensor into the load estimation model according to the estimated road condition to obtain the estimated wheel center load, and ending the step.
Further, the road condition estimation model in the step 21 is a pre-trained model; in the process of training the road condition estimation model, signals acquired by a part of sensors in the signal acquisition sensors are set as input, and signals acquired by the rest of sensors are output, so that the model training is completed.
Further, the input of the road condition estimation model is an acceleration signal acquired by an acceleration sensor, and the output is a displacement signal acquired by a displacement sensor.
Further, the load estimation model in step 22 is a pre-trained model; in the process of training the load estimation model, the input of the model is a plurality of groups of acceleration signals and displacement signals under any road condition, and the output of the model is the signals of the six-minute wheel sensor under the same road condition.
Further, the edge computing device in the step 2 is provided with three processes, namely receiving of the sensor signal, estimating of the wheel center load and packaging and uploading of data.
A wheel center load estimation system based on edge calculation and soft measurement is realized based on the estimation method, and comprises a communication layer, a cloud layer and an edge device layer; the edge device layer is connected with the cloud end layer through the communication layer; the communication layer adopts a wireless network to realize communication; the edge equipment layer is arranged on the unit to be measured; the edge equipment layer is used for acquiring real-time data of the detected vehicle, including acceleration and displacement; the cloud end layer is used for receiving, storing and analyzing data.
Further, the edge device layer comprises edge computing devices, a CAN concentrator and signal acquisition sensors, wherein the signal acquisition sensors are connected with the edge machine selection devices through the CAN concentrator.
Further, the acceleration sensor adopts a three-axis sensor; the number of the acceleration sensors is 8, and the 8 acceleration sensors are respectively arranged on four wheels of the tested vehicle and front and rear vehicle bodies of the vehicle; the displacement sensors are four in number, and the four displacement sensors are respectively arranged at four suspension parts of the vehicle to be measured.
Further, the cloud end layer comprises a server, a Nebula tool is loaded on the server, and the Nebula tool is an edge application remote management tool.
The invention has the beneficial effects that:
by arranging the edge equipment layer on the tested vehicle, the edge equipment layer comprises an acceleration sensor, a displacement sensor, edge computing equipment and the like, and combining a preset algorithm or model, the estimated wheel center load can be directly obtained on the edge equipment layer, the equipment cost is reduced, and the structure of the equipment is simplified;
establishing a connection between the edge device layer and the cloud end layer through the communication layer, so that data collected and estimated by the detected vehicle can be uploaded to the cloud end layer, and a server of the cloud end layer can complete further analysis;
the wheel center load estimated value which is difficult to obtain is obtained through the acceleration data and the displacement data which are easy to collect and the model, so that the cost of the equipment is reduced, the structure of the equipment is simplified, and different vehicles can be adapted only by training the model due to the universality of the acceleration sensor and the displacement sensor;
by setting the road condition estimation model and the load estimation model, the road condition is judged firstly, then the wheel center load is estimated according to the road condition, the interference is eliminated, and the accuracy of the wheel center load estimation value is ensured.
Drawings
FIG. 1 is a general structural diagram of a first embodiment of the present invention;
FIG. 2 is a schematic diagram of the connection of the edge device layer according to the first embodiment of the present invention;
fig. 3 is a schematic position diagram of an acceleration sensor and a displacement sensor according to a first embodiment of the present invention;
FIG. 4 is a flowchart of an estimation method according to a first embodiment of the present invention;
fig. 5 is a schematic road condition diagram according to a first embodiment of the invention;
fig. 6 is a schematic diagram of positions of signal acquisition sensors in a model training process according to a first embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The first embodiment is as follows:
as shown in fig. 1, a wheel center load estimation system based on edge calculation and soft measurement includes a communication layer, a cloud layer, and an edge device layer; the edge device layer is connected with the cloud end layer through the communication layer; the communication layer adopts a wireless network to realize communication, and comprises 4G, 5G, wifi networks and the like; the edge equipment layer is arranged on a unit to be measured, in this case, a vehicle to be measured, and is used for acquiring real-time data of the unit to be measured, including acceleration, displacement and the like; the cloud end layer is used for receiving, storing and analyzing data.
As shown in fig. 2 and 3, in fig. 3, a circle represents an acceleration sensor, and a square represents a displacement sensor. The edge device layer comprises edge computing equipment, a CAN concentrator and a signal acquisition sensor, wherein the signal acquisition sensor is connected with the edge machine selection equipment through the CAN concentrator. The signal acquisition sensor is used for acquiring the state information of a unit to be measured and comprises an acceleration sensor and a displacement sensor. The acceleration sensors are three-axis sensors each capable of detecting acceleration in three directions of X, Y, and Z, and in this example, 8 acceleration sensors are used, the 8 acceleration sensors being provided on four wheels of the vehicle to be tested, respectively, and front and rear bodies of the vehicle, the front and rear bodies of the vehicle being provided with two acceleration sensors, respectively. The displacement sensors are four in total, in the example, the four displacement sensors are arranged at four suspension parts of the tested vehicle, and the four displacement sensors are used for measuring four displacementsThe sensors are respectively used for detecting displacement data of four suspensions of the tested vehicle. The CAN concentrator is used for converting data collected by the acceleration sensor and the displacement sensor into CAN data and then transmitting the CAN data to the edge computing equipment through a CAN bus; with the CAN hub, the edge computing device is freed from the limitation of the number of connected sensors while providing a free wiring manner. The edge computing device includes a CAN interface card, which is integrally disposed within the edge computing device in this example, and through the CAN interface card, the edge computing device may be connected to a CAN network through a PCIe interface, facilitating the reception and analysis of CAN data. The edge computing device adopts eIVP1300 device of Everfocus company, which is loaded with
Atom TM The E3845 dual-core processor has the operation performance of 2M cache and 1.91GHz clock frequency. The edge computing device can associate the collected acceleration data and displacement data with the wheel center load through a preset algorithm or model.
The cloud end layer comprises a server, wherein a Nebula tool is loaded on the server, is an edge application remote management tool and is a program developed by VMware company. The Nebula tool includes the following functions:
1) Supporting uploading of source codes of the model and the application, and remote deployment of the source codes to the edge computing equipment after configuration; when the model or the code needs to be updated, the original application can be uninstalled and then redeployed;
2) Sending start, restart and stop signals to the edge computing equipment to control the start and stop of the edge application; the edge application is an application program loaded by edge computing equipment;
3) The running state of the edge application and the use condition of the hardware resource of the edge computing device are displayed on the client website to monitor whether the service running is effective.
The server is used for storing data uploaded by the edge equipment layer, and performing durability and stability analysis and the like according to a preset model or algorithm, or providing model selection reference for vehicle accessories such as tires and the like.
In the implementation process, the edge equipment layer is arranged on the tested vehicle and comprises an acceleration sensor, a displacement sensor, edge calculation equipment and the like, and a preset algorithm or a preset model is combined, so that the estimated wheel center load can be directly obtained on the edge equipment layer, the equipment cost is reduced, and the structure of the equipment is simplified; the communication layer enables the edge device layer to be in contact with the cloud end layer, so that data collected and estimated by the detected vehicle can be uploaded to the cloud end layer, and a server of the cloud end layer can complete further analysis.
As shown in fig. 4, a wheel center load estimation method based on edge calculation and soft measurement includes the following steps:
step 1: the signal acquisition sensor acquires signals including an acceleration signal and a displacement signal; transmitting the collected signals to the edge computing equipment;
step 2: the edge computing equipment inputs the acceleration signal and the displacement signal acquired by the signal acquisition sensor into a preset model to obtain an estimated value of the wheel center load;
and step 3: and packaging and uploading the obtained wheel center load estimated value, the acceleration signal, the displacement signal and the like to a server of the cloud end layer by the edge computing equipment, and ending the step.
The edge computing device in the step 2 comprises three processes, namely receiving of sensor signals, estimation of wheel center loads and packaging and uploading of data, and the three processes can run simultaneously, so that the data processing efficiency is improved, and the real-time performance of the data is guaranteed. The model in the step 2 is a pre-trained finite impulse response model, wherein the step of obtaining the wheel center load specifically comprises the following steps:
step 21: the edge computing equipment inputs the signals acquired by the signal acquisition sensor into the road condition estimation model to obtain the estimated road condition;
step 22: and inputting the signals acquired by the signal acquisition sensors into the load estimation model under the corresponding road condition according to the estimated road condition to obtain the estimated wheel center load, and ending the step.
As shown in fig. 5, the road condition estimation model in step 21 is a pre-trained model, and in the process of training the road condition estimation model, signals acquired by a part of the signal acquisition sensors are used as inputs, and signals acquired by the remaining sensors are used as outputs, so as to complete model training; in the embodiment, an acceleration signal acquired by an acceleration sensor is used as input, and a displacement signal acquired by a displacement sensor is used as output; in some other embodiments, the acceleration signals collected by four of the acceleration sensors may be used as input, and the signals collected by the remaining four acceleration sensors and the displacement sensor may be used as output to obtain a road condition estimation model, or other combinations. The process of obtaining the traffic information through the traffic estimation model comprises the following steps:
step 211: firstly, setting K road conditions to be respectively expressed as (1, 2, \8230;, K); representing the signal of the sensor as an input as y I1 The sensor signal as output is denoted y I2 Obtaining input corresponding to K road conditions (y) I1,1 ,y I1,2 ,…,y I1,K ) And output (y) I2,1 ,y I2,2 ,…,y I2,K )；
Step 212: obtaining a road condition estimation model through training, wherein the model comprises K slave y I1 To y I2 Is represented as H; the input signal of the newly acquired signal of the sensor, in this case the signal acquired by the acceleration sensor, is then denoted y I1 ' input into the traffic estimation model, obtain the output of the traffic estimation model
Step 213: the output signal of the signal newly acquired by the sensor, in this case the signal acquired by the displacement sensor, is obtained, denoted y I2 '; it should be noted that the signals newly acquired by the sensors in step 213 and step 212 are signals acquired by corresponding sensors under the same condition;
step 214: comparison of y I2 ' and
get the closest evaluation value->
And K belongs to (1, K), wherein K is the obtained road condition information, and the step is finished.
In step 214, to complete the comparison of similarity, y needs to be verified first I2 The distribution rule of' specifically verifies the process as follows:
wherein B is 0 ,…,B n Model parameters representing one data model of the family of secondary models,
represents an estimated value of the data model, and ε (t) represents a residual error at time t; />
Indicates that at time t->
The value of (c). The formula (1) is simplified to obtain
Wherein phi (t) represents a regression matrix expressed by
Represents a tensor product, ->
Expression is->
And I is an identity matrix. Theta is a model parameter vector and has an expression of theta = vec ([ B ] 0 (t) … B n (t-n)] T ) Where vec (·) represents a vectorization operation. Assuming ε (t) follows a Gaussian distribution with a mean of zero and a variance of Σ, it is clear that ∈ is greater>
The following gaussian distribution:
wherein
And &>
The estimated value of the corresponding parameter is obtained by a maximum likelihood estimation method in the process of training the data model.
Based on the model structure of FIR, designing Bayes classifier, calculating posterior probability as follows:
wherein p (H) j ) Represents the prior probability given by the jth data model in the secondary model family H, j belongs to (1, K),
represents->
Probability density at time t; if no other disturbance factors are present, the prior probabilities for each data model in the traffic estimation model H are consistent, and therefore ≦>
The expression of (a) is:
wherein,
the model parameters and variance of the jth data model are shown, and s is the output dimension. Selecting a data model in the suitable road condition estimation model H by calculating the maximum value of the posterior probability as follows:
wherein K represents the road condition corresponding to the selected data model, and argmax and argmin represent a function respectively; estimated value
As shown in fig. 6, in which a circle represents an acceleration sensor, a square represents a displacement sensor, and a triangle represents a sextant wheel sensor. The load estimation model in step 22 is a pre-trained model, during the training of the load estimation model, the input of the model is a plurality of sets of acceleration signals and displacement signals, the output of the model is corresponding signals of the six-minute wheel sensor, it should be noted that corresponding road conditions of a plurality of sets of acceleration signals, displacement signals and signals of the six-minute wheel sensor used for training the same model are the same, corresponding road conditions of a plurality of sets of acceleration signals, displacement signals and signals of the six-minute wheel sensor used for training among different models are different, and in this example, at least one load estimation model is trained for each road condition. Road conditions include straight roads, turns, stone roads, belgium roads, brick and stone roads, square pit roads and the like; the acceleration signal, the displacement signal and the sextant wheel sensor signal are stored according to the road condition type, the load estimation model obtained by training can be stored in association with the road condition type, and after the estimation of the road condition is finished in the step 21, the load estimation model of the corresponding road condition can be called to finish the wheel center load estimation of the wheel, so that the accuracy of the estimated value is ensured.
In the implementation process, the acceleration and displacement data which are easy to collect are used, and the wheel center load estimated value which is difficult to obtain is obtained through the model, so that the cost of the equipment is reduced, the structure of the equipment is simplified, and different vehicles can be suitable only by training the model due to the universality of the acceleration sensor and the displacement sensor; by setting the road condition estimation model and the load estimation model, the road condition is judged firstly, and then the wheel center load is estimated according to the road condition, so that the interference is eliminated, and the accuracy of the wheel center load estimation value is ensured.
The above description is only one specific example of the present invention and should not be construed as limiting the invention in any way. It will be apparent to persons skilled in the relevant art that various modifications and changes in form and detail can be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A wheel center load estimation method based on edge calculation and soft measurement is characterized by comprising the following steps:
step 1: the signal acquisition sensor acquires signals including acceleration signals and displacement signals; transmitting the collected signals to the edge computing equipment of the edge equipment layer;
step 2: the edge computing equipment inputs the acceleration signal and the displacement signal acquired by the signal acquisition sensor into a preset model to obtain an estimated value of the wheel center load;
the model in the step 2 is a pre-trained finite impulse response model, wherein the step of obtaining the wheel center load specifically comprises the following steps:
step 21: the edge computing equipment inputs the signals acquired by the signal acquisition sensor into the road condition estimation model to obtain an estimated road condition;
step 22: inputting the signals acquired by the signal acquisition sensor into the load estimation model according to the estimated road condition to obtain the estimated wheel center load, and ending the step;
the road condition estimation model in the step 21 is a pre-trained model; in the process of training the road condition estimation model, signals acquired by a part of sensors in the signal acquisition sensors are set as input, and signals acquired by the rest sensors are output to finish the model training;
the load estimation model in step 22 is a pre-trained model; in the process of training the load estimation model, the input of the model is a plurality of groups of acceleration signals and displacement signals under any road condition, and the output of the model is signals of a six-minute wheel sensor under the same road condition;
and step 3: and the edge computing equipment packages and uploads the obtained wheel center load estimated value, the acceleration signal and the displacement signal to a server of a cloud end layer through a communication layer, and the step is finished.
2. The method as claimed in claim 1, wherein the input of the road condition estimation model is an acceleration signal collected by an acceleration sensor, and the output is a displacement signal collected by a displacement sensor.
3. The wheel center load estimation method based on edge calculation and soft measurement as claimed in claim 2, wherein the displacement signals collected by the displacement sensor are displacement data of four suspensions of the vehicle under test.
4. The wheel center load estimation method based on edge calculation and soft measurement as claimed in claim 1, wherein the edge calculation device in step 2 is provided with three processes, namely, reception of sensor signals, estimation of wheel center load and packed uploading of data.
5. A wheel center load estimation system based on edge calculation and soft measurement, which is realized based on the estimation method of any one of claims 1-4, and comprises a communication layer, a cloud layer and an edge device layer; the edge device layer is connected with the cloud end layer through the communication layer; the communication layer adopts a wireless network to realize communication; the edge equipment layer is arranged on the tested vehicle; the edge equipment layer is used for acquiring real-time data of the detected vehicle, including acceleration and displacement; the cloud end layer is used for receiving, storing and analyzing data.
6. The wheel center load estimation system based on edge calculation and soft measurement as claimed in claim 5, wherein the edge device layer comprises an edge calculation device, a CAN hub and a signal acquisition sensor, wherein the signal acquisition sensor is connected with the edge calculation device through the CAN hub.
7. The wheel center load estimation system based on edge calculation and soft measurement as claimed in claim 6, wherein the acceleration sensor employs a three-axis sensor; the number of the acceleration sensors is 8, and the 8 acceleration sensors are respectively arranged on four wheels of the tested vehicle and front and rear vehicle bodies of the vehicle; the displacement sensors are four in number, and the four displacement sensors are respectively arranged at four suspension parts of the vehicle to be measured.
8. The wheel center load estimation system based on edge computing and soft measurement as claimed in claim 5, wherein the cloud end layer comprises a server, and a Nebula tool is loaded on the server and is an edge application remote management tool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111423214.6A CN113954850B (en) | 2021-11-26 | 2021-11-26 | Wheel center load estimation method and system based on edge calculation and soft measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111423214.6A CN113954850B (en) | 2021-11-26 | 2021-11-26 | Wheel center load estimation method and system based on edge calculation and soft measurement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113954850A CN113954850A (en) | 2022-01-21 |
| CN113954850B true CN113954850B (en) | 2023-04-07 |
Family
ID=79472282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111423214.6A Active CN113954850B (en) | 2021-11-26 | 2021-11-26 | Wheel center load estimation method and system based on edge calculation and soft measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113954850B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1123425A (en) * | 1997-07-07 | 1999-01-29 | Toyota Central Res & Dev Lab Inc | Load distribution estimator, acceleration/deceleration operating unit for chassis and pavement state estimator |
| CN113656994A (en) * | 2021-07-02 | 2021-11-16 | 东风汽车集团股份有限公司 | Method and device for acquiring suspension force of automobile suspension system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3798668B2 (en) * | 2001-10-11 | 2006-07-19 | 本田技研工業株式会社 | Road friction coefficient calculation device |
| JP4012727B2 (en) * | 2001-12-18 | 2007-11-21 | 株式会社日立製作所 | Braking fluid pressure estimation device |
| DE10208815B4 (en) * | 2002-03-01 | 2011-05-19 | Continental Teves Ag & Co. Ohg | Method for determining a maximum coefficient of friction |
| GB2533658A (en) * | 2014-12-22 | 2016-06-29 | Continental Automotive Gmbh | Method and system for determining a wheel load acting on a tire of a vehicle |
| DE102017207620B4 (en) * | 2017-05-05 | 2019-05-29 | Continental Automotive Gmbh | Method and device for determining wheel loads on wheels of a vehicle |
-
2021
- 2021-11-26 CN CN202111423214.6A patent/CN113954850B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1123425A (en) * | 1997-07-07 | 1999-01-29 | Toyota Central Res & Dev Lab Inc | Load distribution estimator, acceleration/deceleration operating unit for chassis and pavement state estimator |
| CN113656994A (en) * | 2021-07-02 | 2021-11-16 | 东风汽车集团股份有限公司 | Method and device for acquiring suspension force of automobile suspension system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113954850A (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679557B (en) | Driving model training method, driver identification method, device, equipment and medium | |
| CN106095963B (en) | Vehicle driving behavior analysis big data public service platform under internet + era | |
| CN110184885B (en) | Method for testing pavement evenness based on smart phone | |
| US20180113173A1 (en) | Method and system for predicting energy consumption of a vehicle through application of a statistical model utilizing sensor and database data | |
| CN104246516B (en) | A kind of method and device for determining vehicle acceleration | |
| US9128116B2 (en) | Automatic alignment of a vehicle three-axes accelerometer | |
| US20220274452A1 (en) | Tire physical information estimation system | |
| WO2022241705A1 (en) | Vehicle monitoring method, apparatus, and device, and computer-readable storage medium | |
| CN112440629B (en) | Method for extracting variations in tyre characteristics | |
| US20230289663A1 (en) | Vehicle resiliency, driving feedback and risk assessment using machine learning-based vehicle wear scoring | |
| CN109154498A (en) | Road monitoring method and system | |
| CN110133524B (en) | Battery charge state calculation method, device, server and medium | |
| CN112997225B (en) | Road surface vertical section estimation device, road surface vertical section estimation system, road surface vertical section estimation method, and storage medium | |
| CN111191824B (en) | Power battery capacity attenuation prediction method and system | |
| CN108885719B (en) | Stereo vision based random map generation and bayesian updating | |
| CN108228994B (en) | Stress calculation method for vehicle and working device under random excitation of off-road | |
| US20230123850A1 (en) | Tire physical information estimation system and arithmetic operation model generation system | |
| Menegazzo et al. | Multi-contextual and multi-aspect analysis for road surface type classification through inertial sensors and deep learning | |
| CN111638034A (en) | Strain balance temperature gradient error compensation method and system based on deep learning | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| JP2015161580A (en) | road surface inspection system and road surface inspection method | |
| CN110210326B (en) | Online train identification and speed estimation method based on optical fiber vibration signals | |
| CN113340392B (en) | Vehicle load detection method and device based on acceleration sensor | |
| Kumar et al. | Integrating on-board diagnostics speed data with sparse GPS measurements for vehicle trajectory estimation | |
| CN113954850B (en) | Wheel center load estimation method and system based on edge calculation and soft measurement |
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 |