Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a 5G-based mining area unmanned transportation system and an unloading cooperative control method thereof by combining the advantages of a 5G communication technology and the requirements of unloading cooperative operation of a mine car and a bulldozer, so that the unloading efficiency of the mining area mineral aggregate is improved, and the unloading cooperative control of the unmanned mine car and the intelligent bulldozer is realized. The specific technical scheme of the invention is as follows:
a mining area unmanned transportation system based on 5G is characterized by comprising a cloud platform, an unmanned mine car, an intelligent bulldozer and a 5G communication module; the unmanned tramcar is provided with a first vehicle-mounted terminal, a first vehicle sensing module, a first vehicle control module and a first vehicle positioning module, and the intelligent bulldozer is provided with a second vehicle-mounted terminal, a second vehicle sensing module, a second vehicle control module and a second vehicle positioning module; wherein,
the cloud platform is used for performing information interaction, information processing and historical data storage with the first vehicle-mounted terminal on the unmanned mine car and the second vehicle-mounted terminal on the intelligent bulldozer, and performing path planning and scheduling on the unmanned mine car;
the 5G communication module is used for information transmission between the cloud platform and the unmanned mine car and between the cloud platform and the intelligent bulldozer;
the first vehicle-mounted terminal is used for receiving and processing information of the cloud platform, the first vehicle perception module, the first vehicle control module and the first vehicle positioning module; the second vehicle-mounted terminal is used for receiving and processing information of the cloud platform, the second vehicle perception module, the second vehicle control module and the second vehicle positioning module;
the first vehicle perception module and the second vehicle perception module comprise laser radars and millimeter wave radars and are used for perceiving surrounding environment information;
the first vehicle control module is used for receiving the first vehicle-mounted terminal control instruction and controlling the unmanned mine car to run autonomously; the second vehicle control module is used for receiving the second vehicle-mounted terminal control instruction and controlling the intelligent bulldozer to autonomously run;
the first vehicle positioning module is a GPS antenna installed on the unmanned mine car, is connected to the input end of the first vehicle-mounted terminal through a serial port, and is used for positioning the unmanned mine car;
the second vehicle positioning module is a GPS antenna installed on the intelligent bulldozer, is connected to the input end of the second vehicle-mounted terminal through a serial port, and is used for positioning the intelligent bulldozer.
The unloading cooperative control method based on the unmanned transport system is characterized by comprising the following steps:
s1: the first vehicle positioning module of the unmanned mine car and the second vehicle positioning module of the intelligent bulldozer acquire position information of the unmanned mine car in real time, transmit the position information to the first vehicle-mounted terminal and the second vehicle-mounted terminal through serial ports respectively, and upload the position information to a cloud platform in real time through 5G communication modules by the first vehicle-mounted terminal and the second vehicle-mounted terminal respectively;
s2, the cloud platform processes and updates the position information obtained in the step S1, and obtains the entrance position of the unloading area and the position of the full-load unmanned mine car at the current moment according to the historical storage information;
s3, the cloud platform plans a driving path by taking the position of the fully loaded unmanned mine car at the current moment of the step S2 as a starting point and the position of the entrance of the unloading area as a terminal point, and the planned paths are respectively sent to a first vehicle-mounted terminal of each fully loaded unmanned mine car;
s4: sensing the road condition of the fully loaded unmanned mine car by a first car sensing module, and controlling a car body to drive to an entrance of an unloading area to wait for unloading the mineral aggregate by a first car control module according to the planned path of the step S3;
s5: a first vehicle-mounted terminal of an entrance of the unloading area, which is fully loaded with unmanned mine cars, sends inquiry information whether to allow driving in to a second vehicle-mounted terminal of the intelligent bulldozer;
s6: the intelligent bulldozer determines the berthable unloading position and the berthable azimuth information of the full-load unmanned mine car, and the specific method comprises the following steps:
s6-1, the intelligent bulldozer senses the mineral stacking condition at the edge of the mineral storage pit through a second vehicle sensing module and transmits sensing information to a cloud platform;
s6-2: training according to historical information data based on a deep learning method to obtain a mineral stacking condition recognition model, and outputting a stacking area edge position H with the least mineral stacking amount at the edge of a mineral storage pit;
s6-3: determining a tangent line L of the most convex edge point at the edge position H of the mineral stacking area;
s6-4: a straight line L' which is parallel to the tangent L of the step S6-3 and has a vertical distance equal to the safety distance d is a position where the tail end of the full-load unmanned tramcar can be parked and unloaded, and the parking azimuth information is an azimuth of the unmanned tramcar body which is perpendicular to the tangent L of the step S6-3 and the car head of which is back to the edge of the mineral piling area;
s7: the full-load unmanned mine car at the entrance of the unloading area is the first driveable full-load unmanned mine car which can be parked at the unloading position, and the second vehicle-mounted terminal of the intelligent bulldozer directly sends a driveable permission instruction and the information of the parked unloading position and the parked azimuth angle of the unmanned mine car obtained in the step S6 to the first driveable unmanned mine car;
if the unloaded unmanned mine car is driven out, sending a driving-in permission instruction and information of the parked unloading position and the parking azimuth angle of the unmanned mine car to a first vehicle-mounted terminal of the unmanned mine car at the entrance, and if the unloaded unmanned mine car is not driven out, waiting for the unloaded unmanned mine car to drive out of the normal unloading working range;
s8: taking the planned path information transmitted by the cloud platform as an expected path, and controlling the unmanned tramcar to drive into a berthable unloading position along the expected path by the first vehicle control module;
if the full-load unmanned mine car at the entrance of the unloading area is not the first full-load unmanned mine car to drive into in the step S7, the downloaded planning path information is the historical track uploaded by the previous unmanned mine car; if the fully loaded unmanned mine car at the entrance of the unloading area is the first driven-in fully loaded unmanned mine car in step S7, the downloaded planned path calculation information calculation method is as follows:
s8-1: determining a planning path range which can be traveled by the unmanned mine car:
extending the central longitudinal axis L1 of the unmanned tramcar at the entrance to the unloading area and the central longitudinal axis L2 of the unmanned tramcar at the parked unloading position results in an included angle θ of body orientation3The two axes being at an angle theta3The area range between the two areas is the range of the planned path which can be traveled by the unmanned mine car;
s8-2, determining a travelable path set phi ═ p in the planned path range1,p2...,pn},p1,p2,...,pnN travelable paths, respectively, all travelable path segment radii riSatisfy ri≥rminAnd path coordinate point (X)j,Yj,Zj) Mine edge point (X)k,Yk,Zk) And unload region edge points (X)l,Yl,Zl) Satisfies the conditions (1), rminThe minimum physical turning radius of the unmanned mine car body is defined, d is the minimum safe distance, and the condition (1) is as follows:
s8-3: selecting the path with the minimum length from the travelable path set as a downloaded planned path pchooseNamely: p is a radical ofchoose=min Φ;
S9: in the process that the unmanned mine car runs according to the expected path, sensing surrounding road conditions in real time according to a first vehicle sensing module, transmitting road condition information and vehicle actual path information to a cloud platform in real time through a 5G communication module, and storing the road condition information and the vehicle actual path information into an unmanned mine car historical path information module by the cloud platform;
s10: after unloading of the unmanned mine car is completed, marking as a no-load unmanned mine car, issuing a planned path from an unloading position of the unmanned mine car to an outlet of an unloading area to a first vehicle-mounted terminal of the no-load unmanned mine car by a cloud platform, and controlling execution by a first vehicle control module of the no-load unmanned mine car until the unmanned mine car completes unloading work;
s11: after the intelligent bulldozer judges that the no-load unmanned mine car runs out of the normal unloading working range of the berthable unloading position again, the cloud platform issues a planned path from the current position to the berthable unloading position to the intelligent bulldozer, and the planned path is controlled and executed by a second vehicle control module of the intelligent bulldozer;
s12: and after the intelligent bulldozer reaches the berthable unloading position, controlling the push shovel to push residual minerals at the edge of the mineral storage pit into the mineral storage pit, and after the intelligent bulldozer finishes operation at the current berthable unloading position, entering step S5 to finish a whole unloading cooperative control operation mode so as to carry out the unloading process of the next full-load unmanned mine car.
The invention has the beneficial effects that:
1. the invention adopts the absolute advantages of high speed and low time delay of the 5G communication module to transmit information, and realizes the real-time information transmission between the cloud platform and the unmanned mine car and the intelligent bulldozer.
2. According to the invention, the unmanned mine car is ensured to be safely and accurately parked in the unloading area through the positioning technology, the sensing technology, the path planning technology and the deep learning method, and the efficient and cooperative operation control of the unmanned mine car and the bulldozer is realized.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 2 is a schematic diagram of a 5G-based unmanned mining area transportation system, which is a 5G-based unmanned mining area transportation system and comprises a cloud platform, an unmanned mine car, an intelligent bulldozer and a 5G communication module; the unmanned mine car is provided with a first vehicle-mounted terminal, a first vehicle sensing module, a first vehicle control module and a first vehicle positioning module, and the intelligent bulldozer is provided with a second vehicle-mounted terminal, a second vehicle sensing module, a second vehicle control module and a second vehicle positioning module; wherein,
the cloud platform is used for interacting information, processing information and storing historical data with a first vehicle-mounted terminal on the unmanned mine car and a second vehicle-mounted terminal on the intelligent bulldozer, and planning and scheduling a path of the unmanned mine car;
the 5G communication module is used for information transmission between the cloud platform and the unmanned mine car and between the cloud platform and the intelligent bulldozer;
the first vehicle-mounted terminal is used for receiving and processing information of the cloud platform, the first vehicle sensing module, the first vehicle control module and the first vehicle positioning module; the second vehicle-mounted terminal is used for receiving and processing information of the cloud platform, the second vehicle perception module, the second vehicle control module and the second vehicle positioning module;
the first vehicle perception module and the second vehicle perception module comprise laser radars and millimeter wave radars and are used for perceiving surrounding environment information;
the first vehicle control module is used for receiving a first vehicle-mounted terminal control instruction and controlling the unmanned mine car to autonomously run; the second vehicle control module is used for receiving a second vehicle-mounted terminal control instruction and controlling the intelligent bulldozer to autonomously run;
the first vehicle positioning module is a GPS antenna installed on the unmanned mine car, is connected to the input end of the first vehicle-mounted terminal through a serial port and is used for positioning the unmanned mine car;
the second vehicle positioning module is a GPS antenna installed on the intelligent bulldozer, is connected to the input end of the second vehicle-mounted terminal through a serial port, and is used for positioning the intelligent bulldozer.
As shown in fig. 1, the unloading cooperative control method of the unmanned transportation system is characterized by comprising the following steps:
s1: the first vehicle positioning module of the unmanned mine car and the second vehicle positioning module of the intelligent bulldozer acquire position information of the unmanned mine car in real time, transmit the position information to the first vehicle-mounted terminal and the second vehicle-mounted terminal through serial ports respectively, and upload the position information to a cloud platform in real time through 5G communication modules by the first vehicle-mounted terminal and the second vehicle-mounted terminal respectively;
s2, the cloud platform processes and updates the position information obtained in the step S1, and obtains the entrance position of the unloading area and the position of the full-load unmanned mine car at the current moment according to the historical storage information;
s3, the cloud platform plans a driving path by taking the position of the fully loaded unmanned mine car at the current moment of the step S2 as a starting point and the position of the entrance of the unloading area as a terminal point, and the planned paths are respectively sent to a first vehicle-mounted terminal of each fully loaded unmanned mine car;
s4: sensing the road condition of the fully loaded unmanned mine car by a first car sensing module, and controlling a car body to drive to an entrance of an unloading area to wait for unloading the mineral aggregate by a first car control module according to the planned path of the step S3;
s5: a first vehicle-mounted terminal of an entrance of the unloading area, which is fully loaded with unmanned mine cars, sends inquiry information whether to allow driving in to a second vehicle-mounted terminal of the intelligent bulldozer;
s6: the intelligent bulldozer determines the berthable unloading position and the berthable azimuth information of the full-load unmanned mine car, and the specific method comprises the following steps:
s6-1, the intelligent bulldozer senses the mineral stacking condition at the edge of the mineral storage pit through a second vehicle sensing module and transmits sensing information to a cloud platform;
s6-2: outputting a stacking area edge position H with the minimum mineral stacking amount at the edge of the mineral storage pit based on a deep learning method, as shown in fig. 3, wherein the edge position of the mineral storage pit corresponding to the mark H is the stacking area edge position H with the minimum mineral stacking amount, and the acquisition method of the area position identification model with the minimum mineral stacking amount is as follows:
s621, identifying sample collection of the area position with the minimum mineral stacking amount:
the method comprises the steps that sample data of a mineral stacking area are collected from a monitoring video of an unloading area, a position area with the minimum mineral stacking amount is marked on a picture with minerals stacked on the edge of a mineral storage pit through manual marking, a group of area position identification sample sets with the minimum mineral stacking amount are obtained according to the method, and in order to increase the diversity of samples and enhance the generalization capability of a model, the collection of the samples is carried out in various conditions such as day, night, sunny days and cloudy days;
s622: designing a deep learning network structure, and pre-training the sample set:
the deep learning network structure designed by the invention is a Caffe-SSD network structure, and by adjusting learning parameters, 70% of sample sets are randomly selected as training sets, the rest 30% of sample sets are selected as testing sets, images of minerals stacked at the edge of a mineral storage pit are taken as input, and the images marked by the images are taken as output, so that the network structure is trained and tested, and an area position identification model with the minimum mineral stacking amount is obtained;
s6-3: determining a tangent line L of the most convex edge point at the edge position H of the mineral stacking area;
s6-4: a straight line L' which is parallel to the tangent L of the step S6-3 and has a vertical distance equal to the safety distance d is a position where the tail end of the full-load unmanned tramcar can be parked and unloaded, and the parking azimuth information is an azimuth of the unmanned tramcar body which is perpendicular to the tangent L of the step S6-3 and the car head of which is back to the edge of the mineral piling area;
s7: the full-load unmanned mine car at the entrance of the unloading area is the first driveable full-load unmanned mine car which can be parked at the unloading position, and the second vehicle-mounted terminal of the intelligent bulldozer directly sends a driveable permission instruction and the information of the parked unloading position and the parked azimuth angle of the unmanned mine car obtained in the step S6 to the first driveable unmanned mine car;
if the unloaded unmanned mine car is driven out, sending a driving-in permission instruction and information of the parked unloading position and the parking azimuth angle of the unmanned mine car to a first vehicle-mounted terminal of the unmanned mine car at the entrance, and if the unloaded unmanned mine car is not driven out, waiting for the unloaded unmanned mine car to drive out of the normal unloading working range;
s8: taking the planned path information transmitted by the cloud platform as an expected path, and controlling the unmanned tramcar to drive into a berthable unloading position along the expected path by the first vehicle control module;
if the full-load unmanned mine car at the entrance of the unloading area is not the first full-load unmanned mine car to drive into in the step S7, the downloaded planning path information is the historical track uploaded by the previous unmanned mine car;
if the fully loaded unmanned mine car at the entrance of the unloading area is the first fully loaded unmanned mine car to drive into in step S7, the calculation method of the downloaded planned path information is as follows:
s8-1: determining a planning path range which can be traveled by the unmanned mine car:
as shown in FIG. 3, extending the central longitudinal axis L1 of the unmanned tramcar at the entrance to the unloading area and the central longitudinal axis L2 of the unmanned tramcar at the parked unloading position results in an included body orientation angle θ3The two axes being at an angle theta3The area range between the two areas is the range of the planned path which can be traveled by the unmanned mine car;
s8-2, determining a travelable path set phi ═ p in the planned path range1,p2...,pn},p1,p2,...,pnN travelable paths, respectively, all travelable path segment radii riSatisfy ri≥rminAnd path coordinate point (X)j,Yj,Zj) Mine edge point (X)k,Yk,Zk) And unload region edge points (X)l,Yl,Zl) Satisfies the conditions (1), rminThe minimum physical turning radius of the unmanned mine car body is defined, d is the minimum safe distance, and the condition (1) is as follows:
p in FIG. 31Radius of the path section is equal to the minimum physical turning radius r of the unmanned mine car bodyminPossible travel path of p2、pnFor a travelable path whose path coordinate point satisfies the condition (1), only part of the travelable path is drawn in fig. 3, at p1And p2And p2And pnThere are numerous traversable paths in between.
S8-3: selecting the path with the minimum length from the travelable path set as the pathPlanning a path p for a downloadchooseNamely: p is a radical ofchoose=min Φ;
S9: in the process that the unmanned mine car runs according to the expected path, sensing surrounding road conditions in real time according to a first vehicle sensing module, transmitting road condition information and vehicle actual track information to a cloud platform in real time through a 5G communication module, and storing the road condition information and the vehicle actual track information into an unmanned mine car historical track information module by the cloud platform;
s10: after unloading of the unmanned mine car is completed, marking as a no-load unmanned mine car, issuing a planned path from an unloading position of the unmanned mine car to an outlet of an unloading area to a first vehicle-mounted terminal of the no-load unmanned mine car by a cloud platform, and controlling execution by a first vehicle control module of the no-load unmanned mine car until the unmanned mine car completes unloading work;
s11: after the intelligent bulldozer judges that the no-load unmanned mine car runs out of the normal unloading working range of the berthable unloading position again, the cloud platform issues a planned path from the current position to the berthable unloading position to the intelligent bulldozer, and the planned path is controlled and executed by a second vehicle control module of the intelligent bulldozer;
s12: and after the intelligent bulldozer reaches the berthable unloading position, controlling the push shovel to push residual minerals at the edge of the mineral storage pit into the mineral storage pit, and after the intelligent bulldozer finishes operation at the current berthable unloading position, entering step S5 to finish a whole unloading cooperative control operation mode so as to carry out the unloading process of the next full-load unmanned mine car.
The mineral storage pit of the present invention may also be a crushing station.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, "above" or "below" a first feature means that the first and second features are in direct contact, or that the first and second features are not in direct contact but are in contact with each other via another feature therebetween. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly under and obliquely below the second feature, or simply meaning that the first feature is at a lesser elevation than the second feature.
In the present invention, the terms "first", "second", "third", and "fourth" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "plurality" means two or more unless expressly limited otherwise.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.