CN115329670A - Data acquisition method for unmanned vehicle - Google Patents
Data acquisition method for unmanned vehicle Download PDFInfo
- Publication number
- CN115329670A CN115329670A CN202210966895.9A CN202210966895A CN115329670A CN 115329670 A CN115329670 A CN 115329670A CN 202210966895 A CN202210966895 A CN 202210966895A CN 115329670 A CN115329670 A CN 115329670A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- management platform
- representing
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 238000003860 storage Methods 0.000 claims abstract description 28
- 238000004088 simulation Methods 0.000 claims abstract description 23
- 238000013178 mathematical model Methods 0.000 claims abstract description 14
- 230000005540 biological transmission Effects 0.000 claims abstract description 7
- 238000007726 management method Methods 0.000 claims description 52
- 238000011084 recovery Methods 0.000 claims description 25
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000013499 data model Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000009194 climbing Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 230000007774 longterm Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 2
- 230000005764 inhibitory process Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 206010030312 On and off phenomenon Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Medical Informatics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a data acquisition method of an unmanned vehicle, belonging to the field of unmanned driving, and the data acquisition method comprises the following specific steps: (1) Collecting vehicle information and environment information and performing distributed storage; (2) Constructing a simulation environment model and operating an unmanned system; (3) Collecting the operation information of the unmanned vehicle and constructing a mathematical model; (4) the management platform performs cascade analysis on the analysis data; (5) the server periodically recovers data; the vehicle running information management system can automatically clean internal stored data, avoids reduction of data transmission efficiency caused by redundancy generated due to more stored data of the server, ensures that the server can efficiently and quickly respond to a management platform, improves use experience of workers, can more visually feed vehicle running information back to the workers to check by constructing a vehicle related mathematical model, can analyze reasons for torque fluctuation, facilitates the workers to adjust a vehicle driving scheme, and improves working efficiency of the workers.
Description
Technical Field
The invention relates to the field of unmanned driving, in particular to a data acquisition method of an unmanned vehicle.
Background
After the 80's of the 20 th century, ground unmanned vehicles were further developed with the breakthrough of autonomous vehicle technology and other related technologies, emerging as diverse autonomous and semi-autonomous mobile platforms. However, due to the performance limitations of key components such as a positioning navigation device, an obstacle recognition sensor, a calculation control processor and the like, the autonomous driving of the unmanned vehicle is realized to a certain extent, but the driving speed is low, the environmental adaptability is weak, and the semi-automatic ground unmanned vehicle is further developed due to the breakthroughs in the technical aspects such as computers, artificial intelligence, robot control and the like. After the 21 st century, with the great improvement of physical computing capacity, the rapid development of dynamic vision technology and the rapid development of artificial intelligence technology, key technologies such as route navigation, obstacle avoidance and burst decision are solved, and the unmanned driving technology makes a breakthrough progress; therefore, it becomes important to invent a data acquisition method for an unmanned vehicle;
through retrieval, the chinese patent No. CN201910856083.7 discloses a data acquisition method and system for unmanned vehicles, which increases the diversity and accuracy of unmanned data, greatly reduces the time and labor cost, and can collect data in large scale, but the server is easy to reduce the data transmission efficiency due to the redundancy generated by more stored data, so that the server cannot efficiently and quickly respond to the management platform; in addition, the existing data acquisition method for the unmanned vehicle cannot visually feed vehicle operation information back to the working personnel for checking, and is inconvenient for the working personnel to adjust the vehicle driving scheme; therefore, a data acquisition method of the unmanned vehicle is provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a data acquisition method of an unmanned vehicle.
In order to achieve the purpose, the invention adopts the following technical scheme:
a data acquisition method of an unmanned vehicle comprises the following specific steps:
(1) Collecting vehicle information and environment information and performing distributed storage;
(2) Constructing a simulation environment model and operating an unmanned system;
(3) Collecting the operation information of the unmanned vehicle and constructing a mathematical model;
(4) The management platform carries out cascade analysis on the analysis data;
(5) The server periodically performs data recovery.
As a further scheme of the invention, the specific steps of the distributed storage in the step (1) are as follows
The method comprises the following steps: a worker installs and starts a related software package on each group of servers in communication connection with the management platform, establishes connection with all the servers to form a cluster, disconnects the connection if abnormality exists during the establishment of the connection, and reconnects the related servers until the connection is successful;
step two: creating a storage volume and starting the storage volume to prepare storage directories for all servers, binding the servers corresponding to the storage directories by a management platform, and mounting the successfully bound storage directories;
step four: the management platform uses relevant commands to input data plates into the mounted storage directory by self, then checks the distribution condition on each server, records the servers with abnormal storage, cuts off the communication connection with the servers, and feeds back the server nodes to the manager for maintenance;
step five: after detection is completed, the management platform sends a writing request to each group of servers, each group of servers returns a writing address array, the collected vehicle information and the collected environment information are written into a changed data plate block from a first writing address node, the first node continues to transmit backwards, and the process is finished after the last node is reached.
As a further scheme of the invention, the specific steps of the simulation environment model construction in the step (2) are as follows:
the first step is as follows: the management platform extracts various types of environment information from the server, processes various groups of environment data into recognizable data of the management platform through symbol value conversion, and constructs a simulation environment model according to various types of environment data;
the second step is that: converting the characteristic information of each group of environmental data into a default analysis interval of a management platform through normalization, then performing characteristic dimension reduction on the normalized characteristic information, and dividing the characteristic information subjected to dimension reduction into a verification set, a test set and a training set;
the third step: repeatedly using each group of data in the verification set to verify the precision of the simulation environment model, simultaneously predicting each group of data once, and outputting the data with the best prediction result as the optimal parameter;
the fourth step: and carrying out standardization processing on the training set according to the optimal parameters to generate a training sample, then conveying the training sample to the simulation environment model, and carrying out real-time optimization on the simulation environment model by adopting a long-term iteration method.
As a further scheme of the invention, the specific steps of the data model construction in the step (3) are as follows:
s1.1: constructing a relevant vehicle model, matching the relevant vehicle model into a simulation environment model, collecting the running information of each hub motor when the unmanned vehicle runs, and extracting the collected vehicle whole vehicle quality and running speed from a server;
s1.2: the method comprises the steps that a management platform calculates the peak power, the rated power, the peak torque and the rated rotating speed of each hub motor, simultaneously constructs a three-phase natural coordinate system, constructs a related voltage equation, constructs a motor electromagnetic torque expression according to the principle of energy conversion, converts the three-phase natural coordinate system into an alpha beta 0 coordinate system through Clark conversion, obtains a dp0 coordinate system through Park conversion of the alpha beta 0 coordinate system, and obtains a voltage equation of the hub motor under the dp0 coordinate system;
s1.3: and generating a hub torque mathematical model according to a voltage equation under a dp0 coordinate system, analyzing the reasons of the hub motors in each environment torque fluctuation according to the digital model by the management platform, and adjusting each hub motor according to the reasons to reduce the torque fluctuation.
As a further scheme of the invention, a specific calculation formula of the peak power of the hub motor in S1.2 is as follows:
P max ＝max(P u ，P t ，P i ) (4)
in the formula, P u Representing the required power when the vehicle runs at the highest speed, M representing the whole vehicle mass, g representing the gravity acceleration, f representing the rolling resistance coefficient, C D Representing the coefficient of air resistance, A representing the frontal area, u representing the speed of the vehicle, eta T Representing transmission efficiency, alpha representing road grade, delta representing rotating mass conversion factor, P t Representing the power, P, required for full acceleration of the vehicle from a standing start to a specified speed i Represents the power required by the vehicle to meet the climbing performance, P max Representing the peak power of the vehicle hub motor;
the specific calculation formula of the rated power of the hub motor is as follows:
in the formula, P e Representing the rated power of the hub motor of the vehicle;
the specific calculation formula of the peak torque of the hub motor in S1.2 is as follows:
in the formula, T max Representing the peak torque of the hub motor, and R representing the diameter of the wheel;
the specific calculation formula of the rated rotating speed of the hub motor in S1.2 is as follows:
wherein, the formula (7) represents the relationship between the motor rotation speed and the running speed, n max Representing the peak rotational speed, u, of the in-wheel motor max Representing the maximum speed of the vehicle, n e Representing the nominal speed of rotation of the in-wheel motor, u c Representing the vehicle's economic speed.
As a further scheme of the invention, the management platform cascade analysis in the step (4) comprises the following specific steps:
s2.1: the management platform establishes a cascade neural network, transmits each group of analysis data generated by the data model to the cascade neural network, and then a first-stage neural network generates a data pyramid to perform scale normalization processing on each group of analysis data and extract characteristic data of each group of analysis data;
s2.2: sending the extracted features into a bidirectional feature pyramid for feature fusion, classifying and regressing the output data, deducing each group of analysis data through a secondary neural network, gathering the results together for non-maximum suppression, and positioning the analysis data which possibly has abnormality for classification and regression;
s2.3: and searching a large number of secondary neural network architectures, searching parameters with the highest accuracy under the condition that the number of the secondary neural network parameters is less than a certain value, and transmitting the searched parameters to a mathematical model for adjustment and test to generate a related vehicle control scheme.
As a further scheme of the present invention, the server data recovery in step (5) specifically comprises the following steps:
p1: the server periodically performs recovery rate calculation updating on each group of data according to a cycle time value which is set by default or manually, and simultaneously feeds back the recovery rate value after each updating to the management platform for the staff to check, and then extracts each group of data stored in the server according to the corresponding cycle time value;
p2: and recovering the extracted groups of data according to the recovery rate ratio, feeding the recovery information back to the server, receiving the recovery information of each group by the server, performing imaging processing on the recovery information, and feeding the recovery information back to the management platform for the staff to check.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the data acquisition method of the unmanned vehicle, all groups of servers in communication connection with a management platform are connected through a worker to form a cluster, a storage volume is established and started to prepare a storage catalog for all the servers, then the acquired groups of data are stored in all the groups of servers, the servers periodically carry out recovery rate calculation updating on all the groups of data according to a cycle time value which is default or set manually by a system, meanwhile, the recovery rate value after each updating is fed back to the management platform for the worker to check, then all the groups of data stored in the servers are extracted according to the corresponding cycle time value, then all the extracted groups of data are recovered according to the proportion of the recovery rate, the recovered information is fed back to the servers, then the servers receive all the groups of recovered information, simultaneously carry out imaging processing on the recovered information and feed back to the management platform for the worker to check, the data can be automatically cleaned up, reduction of data transmission efficiency caused by redundancy generated by more data stored in the servers is avoided, the servers can be guaranteed that the servers can efficiently and the management platform can be quickly responded, and use experience of the worker is improved;
2. compared with the conventional single data acquisition method, the data acquisition method of the unmanned vehicle extracts various types of environment information from a server through a management platform, processes various groups of environment data into recognizable data of the management platform through symbolic value conversion, constructs and optimizes a simulation environment model according to various types of environment data, constructs a related vehicle model, matches the related vehicle model into the simulation environment model, constructs a three-phase natural coordinate system of the vehicle through the management platform, converts the three-phase natural coordinate system into an alpha beta 0 coordinate system through Clark conversion, obtains a dp0 coordinate system through Park conversion of the alpha beta 0 coordinate system, generates a hub torque mathematical model according to a voltage equation under the dp0 coordinate system, analyzes the reasons of the hub motor in various environment torque fluctuations according to the digital model, can more intuitively feed vehicle operation information back to a worker for checking through constructing the vehicle related mathematical model, can analyze the reasons of the torque fluctuations, facilitates the worker to adjust a vehicle driving scheme, and improves the working efficiency of the worker.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 is a flow chart of a data acquisition method for an unmanned vehicle according to the present invention.
Detailed Description
Example 1
Referring to fig. 1, a data acquisition method of an unmanned vehicle includes the following specific steps:
and collecting vehicle information and environment information and performing distributed storage.
Specifically, a worker installs and starts a related software package on each group of servers in communication connection with a management platform, then all the servers are connected to form a cluster, if abnormality exists during connection, the connection is disconnected, the related servers are reconnected until the connection is successful, a storage volume is created and started to prepare storage directories for all the servers, the management platform binds the servers corresponding to the storage directories and mounts the storage directories which are successfully bound, the management platform uses related commands to record data plates in the mounted storage directories by itself, then checks the distribution conditions on the servers and records the servers with abnormal storage, meanwhile, communication connection with the servers is cut off, the server nodes are fed back to the manager for maintenance, after detection is completed, the management platform sends writing requests to the group of servers, each group of servers returns writing address arrays, collected vehicle information and environment information are written into a first writing address node, the first node continues to transmit the data plates backwards, and the last node is reached.
And constructing a simulation environment model and operating an unmanned system.
Specifically, the management platform extracts various types of environment information from the server, processes various groups of environment data into data which can be identified by the management platform through symbol value conversion, constructs a simulation environment model according to the various types of environment data, converts the characteristic information of the various groups of environment data into a management platform default analysis interval through normalization, performs characteristic dimension reduction on the normalized characteristic information, divides the characteristic information subjected to the dimension reduction processing into a verification set, a test set and a training set, repeatedly uses various groups of data in the verification set to verify the precision of the simulation environment model, performs primary prediction on each group of data, outputs the data with the best prediction result as an optimal parameter, performs standardization processing on the training set according to the optimal parameter to generate a training sample, then transmits the training sample to the simulation environment model, and performs real-time optimization on the simulation environment model by adopting a long-term iteration method.
And collecting the operation information of the unmanned vehicle and constructing a mathematical model.
The method comprises the steps that a management platform constructs a related vehicle model, the related vehicle model is matched into a simulation environment model, operation information of each hub motor when the unmanned vehicle runs is collected, the collected vehicle whole quality and the operation speed of the unmanned vehicle are extracted from a server, the management platform calculates the peak power, the rated power, the peak torque and the rated rotation speed of each hub motor, a three-phase natural coordinate system is constructed, a related voltage equation is constructed, a motor electromagnetic torque expression is constructed according to the energy conversion principle, the three-phase natural coordinate system is converted into an alpha beta 0 coordinate system through Clark conversion, then the alpha beta 0 coordinate system is converted into a dp0 coordinate system through Park conversion, a voltage equation of the hub motor under the dp0 coordinate system is obtained, a hub torque mathematical model is generated according to the voltage equation under the dp0 coordinate system, the management platform analyzes the reasons of the hub motor in each environmental torque fluctuation according to the digital model, each hub motor is adjusted according to the reasons to reduce torque fluctuation, the vehicle related mathematical model is constructed, the operation information can be viewed by a worker intuitively, meanwhile, the reasons of the hub motor fluctuation can be analyzed by the management platform, the working efficiency of the worker can be conveniently improved, and the worker can conveniently analyze the working efficiency of the vehicle.
It should be further explained that the specific calculation formula of the peak power of the hub motor is as follows:
P max ＝max(P u ，P t ，P i ) (4)
in the formula, P u Representing the required power when the vehicle runs at the highest speed, M representing the whole vehicle mass, g representing the gravity acceleration, f representing the rolling resistance coefficient, C D Represents the air resistance coefficient, A represents the windward area, u represents the vehicle speed, eta T Representing transmission efficiency, alpha representing road grade, delta representing a rotating mass conversion factor, P t Representing the power, P, required for full acceleration of the vehicle from a standing start to a specified speed i Represents the power required by the vehicle to meet the climbing performance, P max Representing the peak power of the vehicle hub motor;
the specific calculation formula of the rated power of the hub motor is as follows:
in the formula, P e Representing the rated power of the hub motor of the vehicle;
the specific calculation formula of the peak torque of the hub motor is as follows:
in the formula, T max Representing the peak torque of the hub motor, and R representing the diameter of the wheel;
the specific calculation formula of the rated rotating speed of the hub motor is as follows:
wherein, the formula (7) represents the relationship between the motor rotation speed and the running speed, n max Representing the peak rotational speed, u, of the in-wheel motor max Representing the maximum speed of the vehicle, n e Representing the nominal speed of rotation of the in-wheel motor, u c Representing the economic vehicle speed of the vehicle.
Example 2
Referring to fig. 1, a data acquisition method of an unmanned vehicle includes the following specific steps:
and the management platform performs cascade analysis on the analysis data.
Specifically, the management platform establishes a cascade neural network, transmits each group of analysis data generated by a data model to the cascade neural network, then the first-stage neural network generates a data pyramid to perform scale normalization processing on each group of analysis data, extracts feature data of each group of analysis data, sends the extracted features to a bidirectional feature pyramid for feature fusion, performs classification regression on output data, deduces each group of analysis data through a secondary neural network, gathers results together for non-maximum suppression, then locates analysis data possibly abnormal for classification and regression, performs a large amount of search on a secondary neural network framework, searches for a parameter with the highest accuracy rate under the condition that the number of parameters of the secondary neural network is less than a certain value, and transmits the searched parameter to a mathematical model for adjustment and test to generate a related vehicle control scheme.
The server periodically performs data recovery.
Specifically, the server periodically carries out recovery rate calculation updating on each group of data according to a cycle time value which is set by default or manually, meanwhile, the recovery rate value after each updating is fed back to the management platform to be checked by workers, then each group of data stored in the server is extracted according to the corresponding cycle time value, then each extracted group of data is recovered according to the proportion of the recovery rate, the recovered information is fed back to the server, then the server receives each group of recovered information, meanwhile, the server carries out imaging processing on the recovered information, and feeds back the recovered information to the management platform to be checked by the workers, the internal stored data can be automatically cleaned, the problem that data transmission efficiency is reduced due to the fact that more server stored data generate redundancy is avoided, the server can efficiently and rapidly respond to the management platform, and the use experience of the workers is improved.
Claims (7)
1. A data acquisition method of an unmanned vehicle is characterized by comprising the following specific steps:
(1) Collecting vehicle information and environment information and performing distributed storage;
(2) Constructing a simulation environment model and operating an unmanned system;
(3) Collecting the operation information of the unmanned vehicle and constructing a mathematical model;
(4) The management platform carries out cascade analysis on the analysis data;
(5) The server periodically performs data recovery.
2. The data collection method of the unmanned vehicle as claimed in claim 1, wherein the step (1) of the distributed storage comprises the following specific steps
The method comprises the following steps: a worker installs and starts a related software package on each group of servers in communication connection with the management platform, establishes connection with all the servers to form a cluster, disconnects the connection if abnormality exists during the establishment of the connection, and reconnects the related servers until the connection is successful;
step two: creating a storage volume and starting the storage volume to prepare storage directories for all servers, binding the servers corresponding to the storage directories by a management platform, and mounting the successfully bound storage directories;
step four: the management platform uses relevant commands to input data plates into the mounted storage directory by self, then checks the distribution condition on each server, records the servers with abnormal storage, cuts off the communication connection with the servers, and feeds back the server nodes to the manager for maintenance;
step five: after detection is completed, the management platform sends a writing request to each group of servers, each group of servers returns a writing address array, the collected vehicle information and the collected environment information are written into a changed data plate block from a first writing address node, the first node continues to transmit backwards, and the process is finished after the last node is reached.
3. The data acquisition method of the unmanned vehicle as claimed in claim 2, wherein the simulation environment model in step (2) is constructed by the following specific steps:
the first step is as follows: the management platform extracts various types of environment information from the server, processes various groups of environment data into data which can be identified by the management platform through symbol value conversion, and constructs a simulation environment model according to various types of environment data;
the second step is that: converting the characteristic information of each group of environmental data into a default analysis interval of a management platform through normalization, then performing characteristic dimension reduction on the normalized characteristic information, and dividing the characteristic information subjected to dimension reduction into a verification set, a test set and a training set;
the third step: repeatedly using each group of data in the verification set to verify the precision of the simulation environment model, simultaneously predicting each group of data once, and outputting the data with the best prediction result as the optimal parameter;
the fourth step: and carrying out standardization processing on the training set according to the optimal parameters to generate training samples, then conveying the training samples to the simulation environment model, and carrying out real-time optimization on the simulation environment model by adopting a long-term iteration method.
4. The data acquisition method for the unmanned vehicle as claimed in claim 3, wherein the data model in step (3) is constructed by the following specific steps:
s1.1: constructing a relevant vehicle model, matching the relevant vehicle model into a simulation environment model, simultaneously collecting the running information of each hub motor when the unmanned vehicle runs, and simultaneously extracting the collected vehicle whole quality and running speed from a server;
s1.2: the method comprises the following steps that a management platform calculates the peak power, the rated power, the peak torque and the rated rotating speed of each hub motor, simultaneously constructs a three-phase natural coordinate system, constructs a related voltage equation, constructs a motor electromagnetic torque expression according to the energy conversion principle, converts the three-phase natural coordinate system into an alpha beta 0 coordinate system through Clark conversion, obtains a dp0 coordinate system through Park conversion on the alpha beta 0 coordinate system, and obtains a voltage equation of the hub motor under the dp0 coordinate system;
s1.3: and generating a wheel hub torque mathematical model according to a voltage equation under a dp0 coordinate system, analyzing reasons of the wheel hub motors in each environment torque fluctuation according to the digital model by the management platform, and adjusting the wheel hub motors according to the reasons so as to reduce the torque fluctuation.
5. The data acquisition method of the unmanned vehicle as claimed in claim 4, wherein the specific calculation formula of the peak power of the hub motor in S1.2 is as follows:
P max ＝max(P u ，P t ，P i ) (4)
in the formula, P u Representing the required power when the vehicle runs at the highest speed, M representing the whole vehicle mass, g representing the gravity acceleration, f representing the rolling resistance coefficient, C D Represents the air resistance coefficient, A represents the windward area, u represents the vehicle speed, eta T Representing transmission efficiency, alpha representing road grade, delta representing rotating mass conversion factor, P t Representing the power, P, required for full acceleration of the vehicle from a standing start to a specified speed i Representing the power required by the vehicle to meet the climbing performance, P max Representing the peak power of the vehicle hub motor;
the specific calculation formula of the rated power of the hub motor is as follows:
in the formula, P e Represents the vehicleRated power of the hub motor;
the specific calculation formula of the peak torque of the hub motor in S1.2 is as follows:
in the formula, T max Representing the peak torque of the hub motor, and R representing the diameter of the wheel;
the specific calculation formula of the rated rotating speed of the hub motor in S1.2 is as follows:
wherein, the formula (7) represents the relationship between the motor rotation speed and the running speed, n max Representing the peak rotational speed, u, of the in-wheel motor max Representing the maximum speed of the vehicle, n e Representing the nominal speed of the in-wheel motor, u c Representing the economic vehicle speed of the vehicle.
6. The data acquisition method of the unmanned vehicle as claimed in claim 5, wherein the management platform cascade analysis in step (4) comprises the following specific steps:
s2.1: the management platform establishes a cascade neural network, transmits each group of analysis data generated by the data model to the cascade neural network, and then a first-stage neural network generates a data pyramid to perform scale normalization processing on each group of analysis data and extract characteristic data of each group of analysis data;
s2.2: sending the extracted features into a bidirectional feature pyramid for feature fusion, classifying and regressing the output data, deducing each group of analysis data through a secondary neural network, gathering the results together for non-maximum value inhibition, and positioning the analysis data which possibly has abnormality for classification and regression;
s2.3: and searching a large number of secondary neural network architectures, searching parameters with the highest accuracy under the condition that the secondary neural network parameters are less than a certain value, and transmitting the searched parameters to a mathematical model for adjustment and test to generate a related vehicle control scheme.
7. The data collection method of the unmanned vehicle as claimed in claim 6, wherein the server data recovery in step (5) comprises the following specific steps:
p1: the server periodically calculates and updates the recovery rate of each group of data according to the default or manual cycle time value of the system, simultaneously feeds back the recovery rate value after each update to the management platform for the staff to check, and then extracts each group of data stored in the server according to the corresponding cycle time value;
p2: and recovering the extracted groups of data according to the recovery rate ratio, feeding the recovery information back to the server, receiving the recovery information of each group by the server, carrying out imaging processing on the recovery information, and feeding back the recovery information to the management platform for the staff to check.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210966895.9A CN115329670A (en) | 2022-08-11 | 2022-08-11 | Data acquisition method for unmanned vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210966895.9A CN115329670A (en) | 2022-08-11 | 2022-08-11 | Data acquisition method for unmanned vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115329670A true CN115329670A (en) | 2022-11-11 |
Family
ID=83922976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210966895.9A Pending CN115329670A (en) | 2022-08-11 | 2022-08-11 | Data acquisition method for unmanned vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115329670A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110203075A (en) * | 2019-05-31 | 2019-09-06 | 武汉理工大学 | A kind of four-wheel hub motor Vehicular system power matching method |
| CN111162710A (en) * | 2019-12-25 | 2020-05-15 | 江苏交科能源科技发展有限公司 | Torque ripple suppression method for permanent magnet hub motor |
| CN112529023A (en) * | 2019-09-18 | 2021-03-19 | 上海钛空猫智能科技有限公司 | Configured artificial intelligence scene application research and development method and system |
| CN112701973A (en) * | 2020-12-23 | 2021-04-23 | 江苏大学 | Construction method of energy composite controller of permanent magnet hub motor of electric automobile |
| CN112905849A (en) * | 2021-02-18 | 2021-06-04 | 中国第一汽车股份有限公司 | Vehicle data processing method and device |
| CN113947150A (en) * | 2021-10-19 | 2022-01-18 | 辽宁工程技术大学 | High-reliability intrusion detection method based on conformal prediction |
| CN113972876A (en) * | 2021-08-31 | 2022-01-25 | 东风商用车有限公司 | Permanent magnet synchronous motor controller with torque estimation function and driving equipment |
| CN114565603A (en) * | 2022-03-10 | 2022-05-31 | 辽宁工程技术大学 | Integrated flood disaster accurate monitoring and early warning method |
| CN114771498A (en) * | 2022-04-29 | 2022-07-22 | 天津大学 | Engine torque control system for mode switching of hybrid electric vehicle |
| CN114786314A (en) * | 2022-05-24 | 2022-07-22 | 重庆锐锦科技有限公司 | Control system for lighting of intelligent tunnel of urban rail transit |
| CN114789557A (en) * | 2022-05-16 | 2022-07-26 | 马鞍山嘉兰智造科技有限公司 | Multi-nozzle printing method of 3d printer |
| CN114841714A (en) * | 2022-04-23 | 2022-08-02 | 广州中南网络技术有限公司 | Product traceability system based on block chain |
| CN115082661A (en) * | 2022-07-11 | 2022-09-20 | 阿斯曼尔科技(上海)有限公司 | Method for reducing assembly difficulty of sensor |
| CN115310960A (en) * | 2022-08-09 | 2022-11-08 | 广州中南网络技术有限公司 | Digital economy method based on internet |
| CN115604301A (en) * | 2022-08-31 | 2023-01-13 | 沧州幼儿师范高等专科学校（Cn） | Planting environment monitoring system based on artificial intelligence |
-
2022
- 2022-08-11 CN CN202210966895.9A patent/CN115329670A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110203075A (en) * | 2019-05-31 | 2019-09-06 | 武汉理工大学 | A kind of four-wheel hub motor Vehicular system power matching method |
| CN112529023A (en) * | 2019-09-18 | 2021-03-19 | 上海钛空猫智能科技有限公司 | Configured artificial intelligence scene application research and development method and system |
| CN111162710A (en) * | 2019-12-25 | 2020-05-15 | 江苏交科能源科技发展有限公司 | Torque ripple suppression method for permanent magnet hub motor |
| CN112701973A (en) * | 2020-12-23 | 2021-04-23 | 江苏大学 | Construction method of energy composite controller of permanent magnet hub motor of electric automobile |
| CN112905849A (en) * | 2021-02-18 | 2021-06-04 | 中国第一汽车股份有限公司 | Vehicle data processing method and device |
| CN113972876A (en) * | 2021-08-31 | 2022-01-25 | 东风商用车有限公司 | Permanent magnet synchronous motor controller with torque estimation function and driving equipment |
| CN113947150A (en) * | 2021-10-19 | 2022-01-18 | 辽宁工程技术大学 | High-reliability intrusion detection method based on conformal prediction |
| CN114565603A (en) * | 2022-03-10 | 2022-05-31 | 辽宁工程技术大学 | Integrated flood disaster accurate monitoring and early warning method |
| CN114841714A (en) * | 2022-04-23 | 2022-08-02 | 广州中南网络技术有限公司 | Product traceability system based on block chain |
| CN114771498A (en) * | 2022-04-29 | 2022-07-22 | 天津大学 | Engine torque control system for mode switching of hybrid electric vehicle |
| CN114789557A (en) * | 2022-05-16 | 2022-07-26 | 马鞍山嘉兰智造科技有限公司 | Multi-nozzle printing method of 3d printer |
| CN114786314A (en) * | 2022-05-24 | 2022-07-22 | 重庆锐锦科技有限公司 | Control system for lighting of intelligent tunnel of urban rail transit |
| CN115082661A (en) * | 2022-07-11 | 2022-09-20 | 阿斯曼尔科技(上海)有限公司 | Method for reducing assembly difficulty of sensor |
| CN115310960A (en) * | 2022-08-09 | 2022-11-08 | 广州中南网络技术有限公司 | Digital economy method based on internet |
| CN115604301A (en) * | 2022-08-31 | 2023-01-13 | 沧州幼儿师范高等专科学校（Cn） | Planting environment monitoring system based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| 毛钰;左曙光;林福;: "转矩波动下电动轮系统机电耦合振动特性", 吉林大学学报(工学版), no. 03, 31 May 2017 (2017-05-31) * |
| 陶胜超: "基于IPSO的PMSM矢量控制PI参数优化", 《计算机仿真》, 31 January 2018 (2018-01-31), pages 315 - 320 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829236A (en) | A kind of Compressor Fault Diagnosis method based on XGBoost feature extraction | |
| CN115013298B (en) | Real-time performance online monitoring system and monitoring method of sewage pump | |
| CN113173104B (en) | New energy vehicle power battery early warning method and system | |
| CN109765879A (en) | A kind of remote monitoring system of new-energy automobile | |
| CN112966853A (en) | Urban road network short-term traffic flow prediction method based on space-time residual error mixed model | |
| CN112763215B (en) | Multi-working-condition online fault diagnosis method based on modular federal deep learning | |
| JP3245325U (en) | Solar power plant cluster monitoring system | |
| CN117829296A (en) | Charging pile fault diagnosis model based on large language model | |
| CN103944957B (en) | Off-line data collecting method and its acquisition system used in a kind of industrial monitoring system | |
| CN114186617B (en) | Mechanical fault diagnosis method based on distributed deep learning | |
| CN115329670A (en) | Data acquisition method for unmanned vehicle | |
| CN202939486U (en) | Automobile fault remote diagnosis system | |
| CN103853145A (en) | Automobile fault remote diagnosis system | |
| CN115452376A (en) | Bearing fault diagnosis method based on improved lightweight deep convolution neural network | |
| CN116523429B (en) | Intelligent logistics monitoring system and method based on Internet of things | |
| CN111381161A (en) | Remote online health state diagnosis method for generator set | |
| CN116163894A (en) | Wind farm fan blade state detection method, system and storage medium | |
| CN112782584B (en) | Method, system, medium and device for predicting remaining usage amount of battery electric quantity | |
| CN109754069B (en) | Coal wall property identification device and method based on improved ELM and multi-source parameters | |
| CN113987013A (en) | Management and control system and method based on time sequence data platform power generation vehicle data acquisition | |
| CN110428516B (en) | GJB289A bus data recording and processing method | |
| CN114741447A (en) | Distributed energy station data processing method and device | |
| CN210515359U (en) | Transformer substation secondary equipment fault monitoring system based on edge calculation | |
| CN118170125B (en) | Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method | |
| CN117792476B (en) | Automatic BLOCK detection and processing method based on satellite environment data in space |
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 |