CN110553644B - Accurate positioning system and method for mining electric shovel - Google Patents
Accurate positioning system and method for mining electric shovel Download PDFInfo
- Publication number
- CN110553644B CN110553644B CN201910889776.6A CN201910889776A CN110553644B CN 110553644 B CN110553644 B CN 110553644B CN 201910889776 A CN201910889776 A CN 201910889776A CN 110553644 B CN110553644 B CN 110553644B
- Authority
- CN
- China
- Prior art keywords
- electric shovel
- data
- module
- inertial navigation
- positioning module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Operation Control Of Excavators (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention provides a mining electric shovel accurate positioning system and method, which are characterized by comprising an electric shovel accurate positioning running track measurement terminal, a data analysis and management system and a user management terminal, wherein the electric shovel accurate positioning running track measurement terminal enters an enterprise internal network through a WIFI wireless workstation, is connected with the data analysis and management system and the user management terminal, adopts a deep learning calculation method to eliminate swinging of an electric shovel loading, researches actual running tracks, calculates and describes the running tracks through continuous training of a large amount of acquired real-time data, realizes real-time accurate positioning of the electric shovel, and realizes the measurement of the operation direction and the running distance according to shifts; the obtained real-time accurate data is transmitted to a background production management center for storage in real time, and a reliable basis is provided for electric shovel operation assessment.
Description
Technical Field
The invention relates to a precise positioning and running track measuring method for an electric shovel for open-pit mining by utilizing a combined technology of inertial navigation and Beidou satellite positioning.
Background
The inertial navigation system is a navigation attitude resolving system which is composed of an inertial sensor accelerometer and a gyroscope and an external magnetic sensor as basic measuring elements, integrates the disciplines of computer, control, mechanics, mathematics, optics, electromechanics and the like, and associates the disciplines together to form a modernization technology with high-tech content. The inertial navigation system is based on the theoretical basis of the inertial principle, not only does not rely on any information from the outside, but also radiates energy to the outside, and can independently and independently complete three-axis orientation and positioning by means of self-navigation characteristics no matter in any propagation medium space or no change of climate conditions. Other navigation systems also comprise astronomical navigation, radio navigation, satellite navigation and the like, and the performance of the navigation systems is superior to that of an inertial navigation system in certain aspect, however, the inertial navigation system has the unique advantages of concealment, autonomy, strong information output capability in real time, large information output and capability of acquiring complete motion information of a moving object, and cannot be exceeded by other navigation systems. Inertial navigation systems have long been widely used as important devices for navigation systems. The main sensitive elements of inertial sensors include accelerometers and gyroscopes. The accelerometer is used for measuring linear acceleration of an application object, the amplitude condition of micro vibration of the object and the like; the gyroscope is used for measuring various angle changes or object inclination angle changes when the moving object rotates.
In the process of strip mine production, an electric shovel is an important tool for mining and loading, and the operation direction and the actual running track are important foundations of a mining link. The position of the electric shovel carries the explosion stack material information, the error of the conventional electric shovel is about 5-15 m by adopting a GPS satellite positioning technology, the actual working distance of each shift of actual production mining is about 20 m, the electric shovel rotates left and right to load the production car at ordinary times, the material is required to be excavated forwards and backwards, the positioning point is like a random hemp, the working time of each shift is about 12 hours, and the actual working direction and the running track can not be recorded effectively. Therefore, the simple GPS can not meet the requirements of actual accurate positioning and running track measurement and assessment of production.
Meanwhile, due to vibration and interference of the electric shovel, some detection systems cannot operate on the electric shovel, and how to combine an inertial navigation system and a GPS to be introduced to the electric shovel so as to realize accurate positioning of the electric shovel becomes a key for solving the problem.
Disclosure of Invention
The invention aims to provide a mining electric shovel accurate positioning system and a mining electric shovel accurate positioning method, which take a dust discharging, vibration discharging and fanless industrial control computer as a core, realize an electric shovel accurate positioning and running track measurement technology through an inertia and Beidou satellite combined positioning technology, realize the aims of accurate mining and intelligent ore allocation, facilitate production management and improve production efficiency.
In order to achieve the above purpose, the present invention is realized by the following technical scheme:
the invention relates to a mining electric shovel accurate positioning system which is characterized by comprising an electric shovel accurate positioning running track measuring terminal, a data analysis and management system and a user management terminal,
the electric shovel accurate positioning running track measurement terminal comprises an industrial control computer, a power supply module, a keyboard mouse, a display module, a Beidou GPS positioning module, a WIFI communication module and an inertial navigation positioning module, wherein the power supply module, the keyboard mouse, the display module, the Beidou GPS positioning module and the inertial navigation positioning module are all electrically connected with the industrial control computer;
the data analysis management system comprises a production server, an enterprise intranet, a graphic terminal and a data storage module;
the user management terminal comprises a computer 1, a computer 2 and a computer n;
the electric shovel accurate positioning running track measurement terminal is connected with an internal network in the data analysis management system through the WIFI communication module and the WIFI wireless workstation, and meanwhile the internal network is also connected with the production server and all computers of the user management terminal.
The inertial navigation positioning module is an MPU6050 sensor arranged on the forklift and is embedded with a triaxial digital gyroscope.
The Beidou GPS positioning module is used for receiving satellite signals, the inertial navigation positioning module is used for more accurately positioning the position information of the electric shovel, and the position information of the electric shovel comprises longitude and latitude of the electric shovel, the running track direction of the electric shovel, the grade of the bucket and an electric shovel operation plan; the industrial control computer is used for calculating the position information of the electric shovel according to satellite signals received by the Beidou GPS positioning module and the inertial navigation positioning module dual-mode positioning module.
The invention relates to a precise positioning method of a mining electric shovel, which is characterized by comprising the following steps of:
(1) Initializing: initializing the Beidou GPS positioning module and the inertial navigation positioning module;
(2) Inertial navigation calibration: calibrating an accelerometer, a gyroscope, a magnetic field and a height 0 under a static condition of the inertial navigation positioning module, so as to ensure error analysis on measurement accuracy of the inertial navigation module and prevent the inertial navigation positioning module from drifting too much;
(3) And (3) data acquisition: the industrial control computer collects inertial navigation data and Beidou satellite signals every 10 milliseconds, receives data of the Beidou GPS positioning module and the inertial navigation module, transmits the collected data to the deep learning training machine, and performs model training;
(4) And (3) data processing: the method comprises the steps of collecting data of actual operation of an electric shovel according to a 10 millisecond collecting period, carrying out digital filtering, and generating data according to each second to carry out data processing;
(5) And (3) establishing a model: a regression model of a deep learning convolutional neural network matched with a time recurrent neural network is adopted, the convolutional neural network is used for extracting characteristic values of input signals, the time recurrent neural network is used for carrying out time sequence analysis on the extracted characteristic values, and a loss function formula of the model is adopted to obtain training model parameters;
(6) The industrial control computer performs data acquisition and signal processing according to the training model parameters, calculates the position and the operation direction of the electric shovel every 10 minutes according to a loss function formula of the model, and uploads longitude and latitude data to a production server through a wireless network;
(7) The production server stores the position and the operation direction of the 10 minutes in data storage, marks the position on an X-Y plane coordinate graph, displays the actual position according to a 100-meter square frame, and produces an operation distance and operation direction graph for each electric shovel in each production;
(8) Each manager inquires the current position of each electric shovel through a company internal network computer, and the moving distance and the position of each electric shovel every day and every shift comprise specific operation direction, starting position information and final position information.
4. The method for precisely positioning the mining shovel according to claim 3, wherein the loss function formula of the model is as follows:
wherein y is i Is the actual distance and angle identified in the training data,the distance and angle predicted by the model are calculated by iteration of the function of equation (1).
The invention has the following advantages:
1. according to the invention, through an inertia and Beidou satellite combined positioning technology, an electric shovel accurate positioning and running track measurement technology is realized, and the aims of accurate mining and intelligent ore allocation are fulfilled;
the inertial navigation module calculates the azimuth: the distance between the east, the south, the west, the north, the northeast, the northwest, the southeast and the southwest along a certain direction is 8, inertial navigation is used as a main calculation basis, and the position accuracy of the shovel is improved.
2. The multi-sensing fusion correction parameter method of the Beidou and inertial navigation system fully plays the advantages of the Kalman filter in the positioning navigation technology, provides accurate positioning parameters, and provides a more powerful theoretical basis for positioning an electric shovel.
3. According to the production practice, an intelligent positioning and navigation system of the electric shovel is designed, the walking distance of the electric shovel in each shift is verified through a Beidou GPS positioning system, and the accuracy of the positioning system is ensured. Through the accurate positioning to the electric shovel, realize intelligent ore blending, improve mining production effect.
According to the invention, a combined technology based on inertial navigation and Beidou satellite is adopted, a large amount of electric shovel production real-time data is collected, an SVM-based hybrid dynamic algorithm is applied to analyze and predict, a deep learning data analysis and processing model is established, and the method is combined with the existing field total station measuring technology, so that the requirements of accurate mining and intelligent ore matching are met, and a convenient and quick expression mode and an information acquisition mode are provided for intelligent mines in the future.
Drawings
FIG. 1 is a block diagram of the system components of a mining electric shovel precision positioning system and method.
FIG. 2 is a general block diagram of the steps of a mining electric shovel precision positioning system and method;
FIG. 3 is a block diagram of a deep learning model of a mining electric shovel precision positioning system and method.
Fig. 4 is a schematic diagram of an active positioning technique of a mining shovel precision positioning system and method.
Fig. 5 is a schematic diagram of an electric shovel positioning system and method for accurate positioning of a mining electric shovel.
Fig. 6 is a schematic diagram of the electric shovel trajectory for a mining electric shovel precision positioning system and method.
Detailed Description
The technical content of the present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, the accurate positioning system of the mining electric shovel is characterized by comprising an electric shovel accurate positioning running track measuring terminal, a data analysis and management system and a user management terminal,
the electric shovel accurate positioning running track measurement terminal comprises an industrial control computer, a power supply module, a keyboard mouse, a display module, a Beidou GPS positioning module, a WIFI communication module and an inertial navigation positioning module, wherein the power supply module, the keyboard mouse, the display module, the Beidou GPS positioning module and the inertial navigation positioning module are all electrically connected with the industrial control computer;
the data analysis management system comprises a production server, an enterprise intranet, a graphic terminal and a data storage module;
the electric shovel accurate positioning running track measurement terminal is connected with an internal network in the data analysis management system through the WIFI communication module and the WIFI wireless workstation, and meanwhile the internal network is also connected with the production server and all computers of the user management terminal.
The inertial navigation positioning module is an MPU6050 sensor arranged on the forklift and is embedded with a triaxial digital gyroscope.
The Beidou GPS positioning module is used for receiving satellite signals, the inertial navigation positioning module is used for more accurately positioning the position information of the electric shovel, and the position information of the electric shovel comprises longitude and latitude of the electric shovel, the running track direction of the electric shovel, the grade of the bucket and an electric shovel operation plan; the industrial control computer is used for calculating the position information of the electric shovel according to satellite signals received by the Beidou GPS positioning module and the inertial navigation positioning module dual-mode positioning module.
According to the invention, the mining electric shovel accurate positioning system directly deduces the moving distance and direction of the forklift through the corresponding relation between the data acquisition of inertial navigation sensors (accelerometers, gyroscopes and the like) and Beidou GPS positioning modules arranged on the forklift and the position data of the forklift, so that the actual running position and track of the forklift can still be measured through inertial navigation data under the condition that the position data are unavailable, a regression model of a convolutional neural network matched with a time recursion neural network is adopted, the convolutional neural network is used for extracting the characteristic value of an input signal, the time recursion neural network is used for carrying out time sequence analysis on the extracted characteristic value, the output of a plurality of convolutional network layers is used as the input of the time recursion layers, the training speed of the model is improved, the system uses a structure of 4 convolutional layers and double time recursion layers, each convolutional layer is a pooling layer (4 x 2), the final model is a learning model of 11 layers and the time recursion layers, the actual running track of the electric shovel is eliminated by adopting a deep learning calculation method, and the actual running track is accurately calculated by carrying out the actual running and intermittent operation of the electric shovel.
The inertial navigation module is an MPU6050 sensor, and a triaxial digital gyroscope is embedded in the MPU6050 sensor.
The Beidou GPS positioning module is used for receiving satellite signals, the inertial navigation positioning module is used for more accurately positioning the position information of the electric shovel, and the position information of the electric shovel comprises longitude and latitude of the electric shovel, the running track direction of the electric shovel, the grade of the bucket and an electric shovel operation plan; the industrial control computer is used for calculating the position information of the electric shovel according to satellite signals received by the Beidou GPS positioning module and the inertial navigation positioning module dual-mode positioning module.
The data storage is connected with the production server for data backup and storage.
As shown in fig. 2, the invention relates to a precise positioning method for a mining electric shovel, which is characterized by comprising the following steps:
(1) Initializing: initializing the Beidou GPS positioning module and the inertial navigation positioning module;
(2) Inertial navigation calibration: calibrating an accelerometer, a gyroscope, a magnetic field and a height 0 under a static condition of the inertial navigation positioning module, so as to ensure error analysis on measurement accuracy of the inertial navigation module and prevent the inertial navigation positioning module from drifting too much;
(3) And (3) data acquisition: the industrial control computer collects inertial navigation data and Beidou satellite signals every 10 milliseconds, receives data of the Beidou GPS positioning module and the inertial navigation module, transmits the collected data to the deep learning training machine, and performs model training; the data acquisition comprises acquisition time, inertial navigation ax=x-axis acceleration, ay: y-axis acceleration, az: z-axis acceleration, pitch: x rotation angle, roll: y-axis rotation angle, yaw: z-axis rotation angle, wx: x-axis angular velocity, wy: y-axis angular velocity, wz: z-axis angular velocity, gv: earth velocity and Beidou satellite longitude and latitude data;
(4) And (3) data processing: the method comprises the steps of collecting data of actual operation of an electric shovel according to a 10 millisecond collecting period, carrying out digital filtering, and generating data according to each second to carry out data processing;
early 7 per day: 30 and late 18:30 calculating according to the shift time as a stationary state starting point, taking the longitude and latitude of the two time points as an origin of inertial navigation, converting the movement distance generated by the inertial navigation movement every 1 minute time into the longitude and latitude, and comparing the longitude and latitude changes generated by the Beidou satellite for 1 minute as an analysis control basis, wherein the calculation period is generally set to be 10 minutes because the movement distance of the electric shovel is not obvious due to the short 1 minute time.
(5) And (3) establishing a model: as shown in fig. 3, a regression model of a deep learning convolutional neural network matched with a time recurrent neural network is adopted, the convolutional neural network is used for extracting characteristic values of an input signal, the time recurrent neural network is used for carrying out time sequence analysis on the extracted characteristic values, and a loss function formula of the model is adopted to obtain training model parameters;
the model training optimizer is adam, and a structure of 4 layers of convolution layers and double time recursion layers is used. Each convolutional layer is accompanied by a pooling layer (4 x 2). The final model is a learning model of 11 layers of convolutional neural layers plus temporal recursion layers.
Wherein key parameters of the model are as follows:
number of convolution layers convolution kernel 32/64/128/64
Convolution kernel size of convolution layer 8
Convolutional layer convolutional kernel move step size 8
Pool layer moving step length 2
Pool layer pool size 4
Number of temporal recurrent layer neurons 64.
The loss function formula of the model is as follows:
where yi is the actual distance and angle identified in the training data,the distance and the angle predicted by the model are calculated by the minimum value of the function iteration of the formula (1), so that the purpose of training the model parameters is achieved.
The model is trained by actually accumulating 8 ten thousand training data, and the error of the loss function is reduced to be within 1.0 meter and within 30 degrees.
According to the invention, the mining electric shovel accurate positioning system directly deduces the moving distance and direction of the forklift through the corresponding relation between the data acquisition of inertial navigation sensors (accelerometers, gyroscopes and the like) and Beidou GPS positioning modules arranged on the forklift and the position data of the forklift, so that the actual running position and track of the forklift can still be measured through inertial navigation data under the condition that the position data are unavailable, a regression model of a convolutional neural network matched with a time recursion neural network is adopted, the convolutional neural network is used for extracting the characteristic value of an input signal, the time recursion neural network is used for carrying out time sequence analysis on the extracted characteristic value, the output of a plurality of convolutional network layers is used as the input of the time recursion layers, the training speed of the model is improved, the system uses a structure of 4 convolutional layers and double time recursion layers, each convolutional layer is a pooling layer (4 x 2), the final model is a learning model of 11 layers and the time recursion layers, the actual running track of the electric shovel is eliminated by adopting a deep learning calculation method, and the actual running track is accurately calculated by carrying out the actual running and intermittent operation of the electric shovel.
(6) The industrial control computer performs data acquisition and signal processing according to the training model parameters, calculates the position and the operation direction of the electric shovel every 10 minutes according to a loss function formula of the model, and uploads longitude and latitude data to a production server through a wireless network;
(7) The production server stores the position and the operation direction of the 10 minutes in data storage, marks the position on an X-Y plane coordinate graph, displays the actual position according to a 100-meter square frame, and produces an operation distance and operation direction graph for each electric shovel in each production;
according to the present invention, in the step (2), the motion parameters of the MEMS sensor object are calculated and the related accuracy errors are analyzed, and the specific steps include:
a. the characteristics and the applicable conditions of the low-precision MEMS sensor are researched, the measurement precision of the low-precision MEMS sensor is improved, and the error is reduced;
b. an error model is established, an error calibration compensation experiment is carried out based on the model, the accuracy of the sensor is improved, and the sensor is expected to be used for accurately measuring the attitude and position information of the moving body;
before the inertial navigation module is used, the module needs to be calibrated, so that the main accurate measurement of the sensor is ensured. Calibration of the inertial navigation module includes gyroscope calibration, magnetic field calibration, and height setting of 0. The gyroscope calibration is used to remove zero bias of the gyroscope measurements. If the angular velocity number is not around 0/s when the module is stationary, the gyroscope needs to be recalibrated. And after the gyroscope calibration software is operated and the data to be read is stabilized, the calibration is completed. And then, the configuration software stores the zero bias data into the internal FLASH of the module so as to save power failure. Thereafter, in the rest state, the output of the gyroscope will return to around 0 °/s.
c. The calibration compensation is carried out on the acceleration sensor, so that the output error of the acceleration sensor is reduced, the accuracy of the sensor is improved, and the output data of the sensor is more accurate and reliable;
d. reading longitude and latitude of a Beidou GPS positioning module in a sensor and providing calibration parameters;
and each shift reads Beidou GPS positioning data once, corrects the Beidou GPS positioning data to form model correction error parameters, and continuously corrects the model correction error parameters, wherein the error calculated each time is an important link of calculation.
According to the invention, in the step (4), the electric shovel positioning principle based on the inertial navigation module comprises the following specific steps:
a. the principle of active positioning (Active positioning), see fig. 5, is to determine the position of the electric shovel by collecting and calculating the displacement and angle of the electric shovel movement. The positioning principle is very simple: as the initial coordinates (x 0 ，y 0 ，θ 0 ) Calculating coordinates (x) after the movement of the object using the measured movement displacement and angle 1 ，y 1 ，θ 1 ) After continuous iterative computation, the motion trail of the moving target is finally obtained.
The active positioning is simple and reliable in positioning principle and low in cost, and the positioning accuracy is mainly influenced by the design of a self positioning system and the accuracy of a positioning element, and is less interfered by external environment factors, so that the active positioning is particularly suitable for positioning requirements in a small range, low cost and complex environment, and has very high application prospect and research value.
b. The principle of electric shovel positioning (Active positioning), see figure 6, is different from passive positioning, and the position of the electric shovel is determined only by collecting and calculating the displacement and the angle of the movement of the electric shovel without the aid of external positioning equipment.
Knowing the initial coordinates (x 0, y 0) of the positioning object, if its displacement is measured
S1 and the angle Q1, the coordinates (x 1, y 1) after the movement of the target can be calculated by the equation (2.2).
And obtaining the moving track and the position coordinates of the positioning target through continuous iterative calculation.
c. And drawing the running track of the electric shovel according to the moving track and the position coordinates.
Because the vibration and the interference of the electric shovel, the interference, the environmental interference, the vibration interference, the electromagnetic interference and the like exist in the inertial navigation module, the difficulty of positioning the direction of the electric shovel is caused, and the distance measurement of the electric shovel can reach 3 percent by adopting software filtering elimination processing.
(8) Each manager inquires the current position of each electric shovel through a company internal network computer, and the moving distance and the position of each electric shovel every day and every shift comprise specific operation direction, starting position information and final position information.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (4)
1. The mining electric shovel accurate positioning method is characterized by adopting a mining electric shovel accurate positioning system, wherein the system comprises an electric shovel accurate positioning running track measurement terminal, a data analysis and management system and a user management terminal, and the mining electric shovel accurate positioning method comprises the following steps:
(1) Initializing: initializing the Beidou GPS positioning module and the inertial navigation positioning module;
(2) Inertial navigation calibration: the inertial navigation positioning module is calibrated by an accelerometer, a gyroscope, a magnetic field and a height 0 under the static condition, so that the measurement accuracy of the inertial navigation module is ensured to be subjected to error analysis, and the inertial navigation positioning module is prevented from drifting too much;
(3) And (3) data acquisition: the industrial control computer collects inertial navigation data and Beidou satellite signals every 10 milliseconds, receives data of the Beidou GPS positioning module and the inertial navigation positioning module, transmits the collected data to the deep learning training machine, and performs model training;
(4) And (3) data processing: the method comprises the steps of collecting data of actual operation of an electric shovel according to a 10 millisecond collecting period, carrying out digital filtering, and generating data according to each second to carry out data processing;
(5) And (3) establishing a model: a regression model of a deep learning convolutional neural network matched with a time recurrent neural network is adopted, the convolutional neural network is used for extracting characteristic values of input signals, the time recurrent neural network is used for carrying out time sequence analysis on the extracted characteristic values, and a loss function formula of the model is adopted to obtain training model parameters;
(6) The industrial control computer performs data acquisition and signal processing according to the field reality, calculates the position and the operation direction of the electric shovel every 10 minutes through a loss function formula of the model, and uploads longitude and latitude data to a production server through a wireless network;
(7) The production server stores the position and the operation direction of the 10 minutes in data storage, marks the position on an X-Y plane coordinate graph, displays the actual position according to a 100-meter square frame, and produces an operation distance and operation direction graph for each electric shovel in each production;
(8) Each manager inquires the current position of each electric shovel through a company internal network computer, and the moving distance and the position of each electric shovel every day and every shift comprise specific operation direction, starting position information and final position information;
the electric shovel accurate positioning running track measurement terminal comprises an industrial control computer, a power supply module, a keyboard mouse, a display module, a Beidou GPS positioning module, a WIFI communication module and an inertial navigation positioning module, wherein the power supply module, the keyboard mouse, the display module, the Beidou GPS positioning module and the inertial navigation positioning module are all electrically connected with the industrial control computer;
the data and analysis management system comprises a production server, an enterprise intranet, a graphic terminal and a data storage module;
the user management terminal comprises a computer 1, a computer 2 and a computer n;
the electric shovel accurate positioning running track measurement terminal is connected with an internal network in the data analysis management system through the WIFI communication module and the WIFI wireless workstation, and meanwhile the internal network is also connected with the production server and all computers of the user management terminal.
2. The accurate positioning method of the mining electric shovel according to claim 1, wherein the loss function formula of the model is as follows:
（1）
the actual distance and angle identified in the training data are the distance and angle predicted by the model, and the model obtains the minimum value of the deviation through iteration of the function of the formula (1).
3. The accurate positioning method of the mining electric shovel according to claim 1, wherein the inertial navigation positioning module is an MPU6050 sensor installed on a forklift and is embedded with a three-axis digital gyroscope.
4. The accurate positioning method of the mining electric shovel according to claim 1, wherein the Beidou GPS positioning module is used for receiving satellite signals, the inertial navigation positioning module is used for more accurately positioning position information of the electric shovel, and the position information of the electric shovel comprises longitude and latitude of the electric shovel, the direction of the running track of the electric shovel, the grade of a bucket and an electric shovel operation plan; the industrial control computer is used for calculating the position information of the electric shovel according to satellite signals received by the Beidou GPS positioning module and the inertial navigation positioning module dual-mode positioning module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910889776.6A CN110553644B (en) | 2019-09-20 | 2019-09-20 | Accurate positioning system and method for mining electric shovel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910889776.6A CN110553644B (en) | 2019-09-20 | 2019-09-20 | Accurate positioning system and method for mining electric shovel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110553644A CN110553644A (en) | 2019-12-10 |
| CN110553644B true CN110553644B (en) | 2023-07-21 |
Family
ID=68740978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910889776.6A Active CN110553644B (en) | 2019-09-20 | 2019-09-20 | Accurate positioning system and method for mining electric shovel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110553644B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111811507B (en) * | 2020-04-08 | 2022-05-17 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining posture of mobile equipment, storage medium and electronic equipment |
| CN113942941A (en) * | 2020-07-16 | 2022-01-18 | 上海宝信软件股份有限公司 | Grab mechanism swing GPS positioning system, method and medium |
| CN112285751A (en) * | 2020-10-14 | 2021-01-29 | 深圳市城安物联科技有限公司 | Method for monitoring drilling operation by using positioning system |
| CN113093253A (en) * | 2021-04-06 | 2021-07-09 | 辽宁工程技术大学 | Accurate positioning system and method for mining electric shovel |
| CN112762932B (en) * | 2021-04-07 | 2021-07-13 | 智道网联科技(北京)有限公司 | Trajectory calculation method and device based on neural network model |
| CN112985462B (en) * | 2021-04-21 | 2021-07-23 | 智道网联科技(北京)有限公司 | Method and device for correcting inertial measurement data based on convolutional neural network model |
| CN113175936B (en) * | 2021-06-28 | 2021-08-31 | 智道网联科技(北京)有限公司 | Vehicle track calculation method and device based on neural network model |
| CN114021071A (en) * | 2021-11-12 | 2022-02-08 | 北京中矿华沃科技股份有限公司 | Method and device for weighing electric shovel and computer readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103776463A (en) * | 2013-12-31 | 2014-05-07 | 中国矿业大学 | Test method for automatic memorization and coal cutting self-positioning device of manless working face coal mining machine |
| CN105352504A (en) * | 2015-12-01 | 2016-02-24 | 中国矿业大学 | Inertial navigation-laser scanning integrated coal mining machine positioning device and method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7162367B2 (en) * | 1999-11-29 | 2007-01-09 | American Gnc Corporation | Self-contained/interruption-free positioning method and system thereof |
| JP2007064853A (en) * | 2005-08-31 | 2007-03-15 | Hitachi Ltd | Controller, system and program for positioning mobile object by using complex positioning |
| US20120245850A1 (en) * | 2009-10-30 | 2012-09-27 | Jon Bang | Azimuth initialization and calibration of wellbore surveying gyroscopic and inertial instruments by means of an external navigation system |
| CN105528644A (en) * | 2015-09-16 | 2016-04-27 | 鞍钢集团矿业公司 | Dynamic mine shoveling, transporting and dumping efficiency optimization system and method |
| CN108776474B (en) * | 2018-05-24 | 2022-03-15 | 中山赛伯坦智能科技有限公司 | Robot embedded computing terminal integrating high-precision navigation positioning and deep learning |
| CN109059909A (en) * | 2018-07-23 | 2018-12-21 | 兰州交通大学 | Satellite based on neural network aiding/inertial navigation train locating method and system |
-
2019
- 2019-09-20 CN CN201910889776.6A patent/CN110553644B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103776463A (en) * | 2013-12-31 | 2014-05-07 | 中国矿业大学 | Test method for automatic memorization and coal cutting self-positioning device of manless working face coal mining machine |
| CN105352504A (en) * | 2015-12-01 | 2016-02-24 | 中国矿业大学 | Inertial navigation-laser scanning integrated coal mining machine positioning device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110553644A (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110553644B (en) | Accurate positioning system and method for mining electric shovel | |
| CN102519470B (en) | Multi-level embedded integrated navigation system and navigation method | |
| CN100356139C (en) | Miniature assembled gesture measuring system for mini-satellite | |
| CN108731670A (en) | Inertia/visual odometry combined navigation locating method based on measurement model optimization | |
| CN111707260B (en) | Positioning method based on frequency domain analysis and convolutional neural network | |
| CN113252033B (en) | Positioning method, positioning system and robot based on multi-sensor fusion | |
| CN104406586A (en) | Pedestrian navigation device and pedestrian navigation method based on inertial sensor | |
| CN109781098B (en) | Train positioning method and system | |
| CN112378399B (en) | Coal mine tunnel tunneling robot precise positioning and orientation method based on strapdown inertial navigation and digital total station | |
| CN105865450A (en) | Zero-speed update method and system based on gait | |
| CN110057356B (en) | Method and device for positioning vehicles in tunnel | |
| CN102087110B (en) | Miniature underwater moving vehicle autonomous attitude detecting device and method | |
| CN105547300A (en) | All-source navigation system and method used for AUV (Autonomous Underwater Vehicle) | |
| CN110672095A (en) | Pedestrian indoor autonomous positioning algorithm based on micro inertial navigation | |
| Zhou et al. | DeepVIP: Deep learning-based vehicle indoor positioning using smartphones | |
| CN104897155A (en) | Personal portable auxiliary multisource locating information correcting method | |
| CN112325878A (en) | Ground carrier combined navigation method based on UKF and air unmanned aerial vehicle node assistance | |
| CN103256932B (en) | Replacement and extrapolation combined navigation method | |
| Forno et al. | Techniques for improving localization applications running on low-cost IoT devices | |
| Ludwig | Investigation of orientation estimation of multiple imus | |
| CN104897157A (en) | Personal navigation system and method based on foot attitude-heading reference and shoulder electronic compass | |
| Zhu et al. | A hybrid step model and new azimuth estimation method for pedestrian dead reckoning | |
| Aravind et al. | Enhancing GPS Position Estimation Using Multi-Sensor Fusion and Error-State Extended Kalman Filter | |
| Meng et al. | A GNSS/INS integrated navigation compensation method based on CNN-GRU+ IRAKF hybrid model during GNSS outages | |
| Fang et al. | Integrating SINS sensors with odometer measurements for land vehicle navigation system |
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 |