CN112109713A - Concrete box girder handling device and control method - Google Patents
Concrete box girder handling device and control method Download PDFInfo
- Publication number
- CN112109713A CN112109713A CN202011023771.4A CN202011023771A CN112109713A CN 112109713 A CN112109713 A CN 112109713A CN 202011023771 A CN202011023771 A CN 202011023771A CN 112109713 A CN112109713 A CN 112109713A
- Authority
- CN
- China
- Prior art keywords
- data
- box girder
- road surface
- image
- driving
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 239000004567 concrete Substances 0.000 title claims abstract description 22
- 238000012546 transfer Methods 0.000 claims abstract description 83
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 42
- 238000001514 detection method Methods 0.000 claims description 39
- 238000012549 training Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 230000008713 feedback mechanism Effects 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 17
- 230000001276 controlling effect Effects 0.000 description 13
- 238000010276 construction Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000011178 precast concrete Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60P—VEHICLES ADAPTED FOR LOAD TRANSPORTATION OR TO TRANSPORT, TO CARRY, OR TO COMPRISE SPECIAL LOADS OR OBJECTS
- B60P3/00—Vehicles adapted to transport, to carry or to comprise special loads or objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a concrete box girder carrying device and a control method, which are used for carrying and advancing control of a box girder transfer trolley, wherein the box girder transfer trolley is provided with a traveling controller for controlling the traveling and steering of the box girder transfer trolley, and the carrying control method comprises the following steps: s1, acquiring a road image in front of the travelling route of the box girder transfer trolley, and generating a real-time travelling image; s2, acquiring a real-time advancing image, identifying a road surface undulating part in the real-time advancing image and generating road surface undulating data; s3, acquiring the running speed data and the frame shaking data of the box girder transfer trolley, and associating the running speed data and the frame shaking data with the road surface fluctuation data to acquire data correlation information; and S4, generating a driving control command for controlling the speed conversion of the box girder transfer vehicle according to the data correlation information, calling and selecting to execute by a driving controller of the box girder transfer vehicle, and providing a new idea for suppressing the vibration of the transportation for unmanned driving and auxiliary driving of box girder transportation by the transportation control method of the scheme, so that the transportation control method has the advantages of quick response and reliable implementation.
Description
Technical Field
The invention relates to the technical field of box girder transportation, in particular to a concrete box girder transporting device and a control method.
Background
The box girder carrying is taken as an important link in the road and bridge construction, because the number of the precast concrete box girders is dozens of tons or even hundreds of tons, the reliability and the stability in the transportation process directly influence whether the box girder can safely reach a preset area of a construction site or not, and a positioning placement mechanism is usually arranged on a box girder transfer trolley to be matched with a positioning structure on the lower end surface of the box girder, so that the box girder is stabilized on a frame of the box girder transfer trolley.
When the box girder is loaded on the box girder transfer trolley for transportation, if the road surface is fluctuated and uneven and the running speed is high, the frame can swing due to the contact of the road surface fluctuation conducted by the tires, so that the box girder can swing.
With the proposition of the operation concept of automatic and unmanned transportation, more and more application scenes begin to explore unmanned automatic transportation, when box girder transportation is transferred in a construction site, the box girder transportation has site conditions of unmanned transportation completely, in addition, corresponding trial possibility exists in some specific internal transportation sites, however, in the box girder transportation process, the shaking control of the box girder transfer trolley is a very critical technology, which is not only related to whether the box girder loaded on the box girder can not crack due to stress caused by vibration, but also related to whether the tire can be kept reliable when the box girder transfer trolley is in driving, once the box girder shakes too much for a long time and is difficult to control, the inertia force generated by the box girder under the condition of huge self mass of the box girder can be enough to crack, deform the tire of the transfer trolley and even cause serious accident of box girder slipping, at present, the vibration of the box girder is monitored, and the box girder transportation is carried out in the prior art, The technical records of prediction and feedback control are few, so the deep research is carried out on the aspect, and the important practical significance is brought to the subsequent unmanned transportation and auxiliary transportation of the box girder.
Disclosure of Invention
In view of the above, the present invention provides a concrete box girder transporting apparatus and a control method thereof, which have reliable feedback, timely response and convenient implementation, and can analyze and predict the shaking condition of the frame during the transportation of the box girder in time.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
a concrete box girder carrying control method is used for carrying and advancing control of a box girder transfer trolley, a traveling controller used for controlling the travelling and steering of the box girder transfer trolley is arranged on the box girder transfer trolley, and the carrying control method comprises the following steps:
s1, acquiring a road image in front of the travelling route of the box girder transfer trolley, and generating a real-time travelling image;
s2, acquiring a real-time advancing image, identifying a road surface undulating part in the real-time advancing image and generating road surface undulating data;
s3, acquiring the running speed data and the frame shaking data of the box girder transfer trolley, and associating the running speed data and the frame shaking data with the road surface fluctuation data to acquire data correlation information;
and S4, generating a running control command for controlling the speed conversion of the box girder transfer vehicle according to the data correlation information, and calling and selecting to execute by the running controller of the box girder transfer vehicle.
As a possible implementation manner, further, step S2 further includes:
the method comprises the steps of obtaining the steering angle and the running speed of a running controller, generating steering data and running speed data, correlating a real-time advancing image with the steering data and the running speed data of a box girder transfer trolley, and generating an advancing track prediction image.
As a preferred implementation option, in step S2, the concrete steps of identifying the road surface undulation portion in the live-action image and generating the road surface undulation data preferably include:
s2.1, converting a video stream in the real-time moving image into image frames, and then extracting corresponding image frames according to a preset time interval to generate monitoring image frames;
and S2.2, identifying and positioning the road surface fluctuation part in the monitoring image frame through the positioning neural network and the detection neural network, and outputting road surface fluctuation data.
As a preferred implementation choice, in step S2.2, the positioning neural network preferably identifies the undulating portion located within the predicted travel trajectory range in the monitored image frame to generate a positioning frame, and the detection neural network directly detects the object in the positioning frame to output undulating data.
As a preferred implementation choice, preferably, the training method of the neural network in step S2.2 is:
inputting a plurality of preset road surface images, marking the road surface undulating parts and the corresponding convex and concave heights, and then reading and training by a positioning neural network;
inputting a plurality of verification road surface images, reading and outputting positioning results by a positioning neural network, manually checking, re-labeling the images failed or wrong in detection, inputting the images into the positioning neural network again for reading and outputting the positioning results until the detection is successful.
As a preferred implementation choice, preferably, the training method for detecting the neural network in step S2.2 is:
inputting a plurality of preset road surface images, marking the road surface undulating parts and the corresponding convex and concave heights, and reading and training by a detection neural network;
inputting a plurality of verification road surface images, reading and outputting detection results by a detection neural network, manually checking, re-labeling failed or wrong images, inputting the images into the detection neural network again for reading and outputting the detection results until the detection is successful.
As a possible implementation manner, further, in step S4,
when the amplitude in the vehicle frame shaking data is larger than a first preset threshold value, outputting a driving control instruction for uniform deceleration driving until the amplitude in the vehicle frame shaking data is smaller than the first threshold value, and calling and selectively executing by a driving controller;
when the amplitude in the vehicle frame shaking data is smaller than a preset second preset threshold value and the real-time road surface fluctuation data is larger than the preset threshold value, outputting a running control instruction for constant-speed running, and calling and selectively executing by a running controller;
when the amplitude in the vehicle frame shaking data is smaller than a preset second preset threshold value and the real-time road surface fluctuation data is smaller than the preset threshold value, outputting a running control instruction for accelerating running until the running speed reaches 80% of the preset highest running speed, and calling and selectively executing by a running controller;
the amplitude in the vehicle frame shaking data is larger than a second preset threshold value and smaller than a first preset threshold value, and meanwhile, when the road surface fluctuation data is larger than the preset threshold value, a driving control instruction for driving at a constant speed is output and called and selectively executed by a driving controller;
and when the amplitude in the vehicle frame shaking data is larger than a second preset threshold value and smaller than a first preset threshold value and the road surface fluctuation data is smaller than the preset threshold value, outputting a driving control command for accelerating driving until the traveling speed reaches 60% of the preset highest traveling speed, and calling and selectively executing by a driving controller.
As a preferred implementation choice, in step S4, it is preferable that the frame amplitude data in the frame shaking data within a certain time is selected according to the data correlation information to form a recording curve, then the trend line is correspondingly generated to predict the amplitude which the frame shaking data may reach after a preset time period, and a driving control command for controlling the speed conversion of the box girder transfer vehicle is generated according to the predicted amplitude and is called and selectively executed by the driving controller of the box girder transfer vehicle.
As a preferred implementation option, preferably, the transportation control method further includes an unmanned driving mode, a manual driving mode and an auxiliary driving mode,
when the unmanned driving mode is adopted, the travel speed control of the travel controller is controlled by the travel control command generated at step S4;
when the driving assistance mode is adopted, the driving controller calls the driving control command generated in step S4 to prompt, and the operator selects the command;
when the manual driving mode is adopted, the travel controller calls only the travel control command generated in step S4 to present the command.
Based on the above transportation control method, the present invention also provides a transportation device capable of adopting the transportation control method, which includes:
a concrete box girder carrying device applying the carrying control method comprises a box girder transfer trolley, a running controller arranged on the box girder transfer trolley and used for controlling the running and steering of the box girder transfer trolley, and a road condition detection feedback mechanism connected with the running controller and used for providing feedback of the running road condition, wherein the road condition detection feedback mechanism comprises:
the image shooting unit is used for obtaining a road surface image in front of a travelling route of the box girder transfer trolley and generating a real-time travelling image;
the information acquisition module is used for acquiring the steering angle and the driving speed of the driving controller and generating steering data and driving speed data;
the route prediction unit is used for acquiring real-time advancing images and steering data and traveling speed data of the box girder transfer trolley and generating advancing track prediction images;
the vibration sensing unit is used for acquiring vehicle body vibration data of the box girder transfer vehicle in the process of proceeding;
the road condition detection unit is used for acquiring the real-time advancing image, identifying the road surface fluctuation position in the real-time advancing image and generating road surface fluctuation data;
the data association unit is used for acquiring vehicle body vibration data and road surface fluctuation data, associating the vehicle body vibration data and the road surface fluctuation data and generating traveling association data;
and the early warning feedback unit calculates to obtain vehicle body predicted jitter data according to the traveling correlation data, generates a traveling control instruction corresponding to the speed change of the box girder transfer vehicle according to a corresponding vehicle body jitter data preset threshold value, and is called and selectively executed by a traveling controller of the box girder transfer vehicle.
On the basis of the above transportation control method and the transportation device, if other existing transportation equipment has a corresponding hardware foundation, it also has a possibility of directly applying the control method of the present scheme, and based on this, the present scheme further provides a medium for storing the transportation control method, specifically as follows:
a storage medium, wherein at least one instruction, at least one program, code set, or instruction set is stored in the storage medium, and the at least one instruction, at least one program, code set, or instruction set is loaded by a processor and executed to implement the concrete box girder handling control method.
By adopting the technical scheme, compared with the prior art, the invention has the beneficial effects that: the scheme ingeniously carries out real-time monitoring on road conditions and vehicle frame shaking data when the box girder transfer trolley travels, then identifies and acquires the road surface fluctuation data through a fluctuation part of a traveling road surface, provides prediction and feedback instructions for traveling speed control of the box girder transfer trolley, obtains an expected traveling track prediction image by associating the current steering and the time speed of the box girder transfer trolley with a real-time traveling image as the traveling speed of a vehicle and the shaking of a vehicle frame are correlated, analyzes the traveling track prediction image of the box girder transfer trolley to the rough road surface condition to be traveled and rolled, and predicts whether the vehicle frame shaking exceeds a preset threshold value or not in the following traveling process by combining the vehicle body shaking condition in the past time period, therefore, feedback is carried out in advance, so that an operator can be reminded in the manual driving mode and the auxiliary driving mode to take corresponding measures in advance, and the response and the execution of the response deceleration corresponding measures can be carried out in the first time in the unmanned driving mode.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart showing the operation of example 1 of the present invention;
FIG. 2 is a schematic flow chart of example 2 of the present invention;
FIG. 3 is a schematic flow chart of a method for training a neural network for localization according to embodiment 2 of the present invention;
FIG. 4 is a schematic flow chart illustrating a training method for neural network detection according to embodiment 2 of the present invention;
FIG. 5 is a schematic connection diagram of an apparatus using the embodiment 2 of the present invention;
fig. 6 is a schematic diagram of a real-time traveling image of a box girder transporting vehicle according to a simplified simulation example of embodiment 2 of the present invention;
fig. 7 is a schematic view of a box girder truck travel track prediction image of a simplified simulation example according to embodiment 2 of the present invention;
fig. 8 is a schematic traveling condition record of the box girder transporting vehicle after the dry-run is performed by the embodiment 2 of the invention, wherein the recorded data of the road surface undulation and the vehicle frame amplitude during the traveling of the box girder transporting vehicle are shown;
fig. 9 is a schematic traveling condition record of the box girder transporting vehicle after the intervention by the embodiment 2 of the present invention, in which the vehicle speed of the box girder transporting vehicle and the variation of the amplitude corresponding to the current frame are shown.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be noted that the following examples are only illustrative of the present invention, and do not limit the scope of the present invention. Similarly, the following examples are only some but not all examples of the present invention, and all other examples obtained by those skilled in the art without any inventive work are within the scope of the present invention.
Example 1
The embodiment provides a general control idea based on the idea of the scheme of the invention, which specifically comprises the following steps:
as shown in fig. 1, the concrete box girder transporting control method of the embodiment is used for controlling the transporting and traveling of a box girder transfer trolley, wherein a traveling controller for controlling the traveling and steering of the box girder transfer trolley is arranged on the box girder transfer trolley, and the transporting control method comprises the following steps:
s1, acquiring a road image in front of the travelling route of the box girder transfer trolley, and generating a real-time travelling image;
s2, acquiring a real-time advancing image, identifying a road surface undulating part in the real-time advancing image and generating road surface undulating data;
s3, acquiring the running speed data and the frame shaking data of the box girder transfer trolley, and associating the running speed data and the frame shaking data with the road surface fluctuation data to acquire data correlation information;
and S4, generating a running control command for controlling the speed conversion of the box girder transfer vehicle according to the data correlation information, and calling and selecting to execute by the running controller of the box girder transfer vehicle.
The method has the advantages that the control instruction can be quickly obtained without occupying large computational resources, the hardware requirement is relatively low, the input cost is low, and the limitation is that the generated control instruction is relatively limited and not flexible enough.
Example 2
The present embodiment is used as a further optimization scheme of the embodiment 1, and mainly based on the embodiment 1, further converts the data obtained in each step to obtain more process data for reference or use, so as to improve the flexibility and reliability of the control method, and specifically, the following steps are performed:
as shown in fig. 2, the concrete box girder transporting control method of the embodiment is used for controlling the transporting and traveling of a box girder transfer trolley, wherein a traveling controller for controlling the traveling and steering of the box girder transfer trolley is arranged on the box girder transfer trolley, and the transporting control method comprises the following steps:
s1, acquiring a road image in front of the travelling route of the box girder transfer trolley, and generating a real-time travelling image;
s2 generation of predicted image of traveling locus and road surface undulation data
S2.1, acquiring a steering angle and a driving speed of a driving controller, generating steering data and driving speed data, associating the real-time advancing image with the steering data and the driving speed data of the box girder transfer trolley, and generating an advancing track prediction image;
s2.2, converting the video stream in the real-time moving image into image frames, and then extracting corresponding image frames according to a preset time interval to generate monitoring image frames;
s2.3, identifying and positioning the road surface fluctuation part in the monitoring image frame and outputting road surface fluctuation data through a positioning neural network and a detection neural network, wherein the positioning neural network identifies the fluctuation part in the monitoring image frame within the travel prediction track range and generates a positioning frame, and then the detection neural network directly detects an object in the positioning frame and outputs fluctuation data;
s3, acquiring the running speed data and the frame shaking data of the box girder transfer trolley, and associating the running speed data and the frame shaking data with the road surface fluctuation data to acquire data correlation information;
s4, generating a driving control command for controlling the speed conversion of the box girder transfer vehicle according to the data correlation information, and calling and selecting execution by the driving controller of the box girder transfer vehicle, wherein,
when the amplitude in the vehicle frame shaking data is larger than a first preset threshold value, outputting a driving control instruction for uniform deceleration driving until the amplitude in the vehicle frame shaking data is smaller than the first threshold value, and calling and selectively executing by a driving controller;
when the amplitude in the vehicle frame shaking data is smaller than a preset second preset threshold value and the real-time road surface fluctuation data is larger than the preset threshold value, outputting a running control instruction for constant-speed running, and calling and selectively executing by a running controller;
when the amplitude in the vehicle frame shaking data is smaller than a preset second preset threshold value and the real-time road surface fluctuation data is smaller than the preset threshold value, outputting a running control instruction for accelerating running until the running speed reaches 80% of the preset highest running speed, and calling and selectively executing by a running controller;
the amplitude in the vehicle frame shaking data is larger than a second preset threshold value and smaller than a first preset threshold value, and meanwhile, when the road surface fluctuation data is larger than the preset threshold value, a driving control instruction for driving at a constant speed is output and called and selectively executed by a driving controller;
and when the amplitude in the vehicle frame shaking data is larger than a second preset threshold value and smaller than a first preset threshold value and the road surface fluctuation data is smaller than the preset threshold value, outputting a driving control command for accelerating driving until the traveling speed reaches 60% of the preset highest traveling speed, and calling and selectively executing by a driving controller.
In step S4, frame amplitude data in frame jitter data within a certain time may be selected according to the data correlation information to form a recording curve, then a trend line is correspondingly generated to predict an amplitude which may be reached after a preset duration, and the amplitude is compared with a first preset threshold and a second preset threshold according to the predicted amplitude, and then a driving control instruction for controlling speed conversion of the box girder transport vehicle is generated and invoked and selectively executed by a driving controller of the box girder transport vehicle.
It should be noted that the control method of this embodiment may be used for determining the traveling speed control in the unmanned driving mode, and may also be used as a prompt reference in the manual driving mode or the auxiliary driving mode, and the specific idea is as follows:
when the unmanned driving mode is adopted, the travel speed control of the travel controller is controlled by the travel control command generated at step S4;
when the driving assistance mode is adopted, the driving controller calls the driving control command generated in step S4 to prompt, and the operator selects the command;
when the manual driving mode is adopted, the travel controller calls only the travel control command generated in step S4 to present the command.
In addition, referring to fig. 3, the training method of the neural network in this embodiment includes:
inputting a plurality of preset road surface images, marking the road surface undulating parts and the corresponding convex and concave heights, and then reading and training by a positioning neural network;
inputting a plurality of verification road surface images, reading and outputting positioning results by a positioning neural network, manually checking, re-labeling the images failed or wrong in detection, inputting the images into the positioning neural network again for reading and outputting the positioning results until the detection is successful.
Referring to fig. 4, the training method for detecting a neural network according to this embodiment includes:
inputting a plurality of preset road surface images, marking the road surface undulating parts and the corresponding convex and concave heights, and reading and training by a detection neural network;
inputting a plurality of verification road surface images, reading and outputting detection results by a detection neural network, manually checking, re-labeling failed or wrong images, inputting the images into the detection neural network again for reading and outputting the detection results until the detection is successful.
Since the real-time moving image obtained in real time has a certain time difference in the vibration sensed by the vehicle vibration sensing unit, that is, the vibration data sensed by the vibration sensing unit of the current vehicle is the driving feedback result of the moving image data obtained at the previous time node, when the real-time moving image is associated with the vehicle frame shaking data, the time difference needs to be adjusted, that is, the horizontal distance between the wheel position and the real-time moving image obtaining device is divided by the average vehicle speed of the distance, so as to obtain the time difference.
Based on the transportation control method of the present embodiment, the present embodiment further provides a transportation device that can adopt the transportation control method, which includes:
referring to fig. 5, a concrete box girder transporting device using the transporting control method includes a box girder transfer vehicle, a driving controller disposed on the box girder transfer vehicle and used for controlling the traveling and steering of the box girder transfer vehicle, and a road condition detection feedback mechanism connected to the driving controller and used for providing feedback of traveling road conditions, wherein the road condition detection feedback mechanism includes:
the image shooting unit is used for obtaining a road surface image in front of a travelling route of the box girder transfer trolley and generating a real-time travelling image;
the information acquisition module is used for acquiring the steering angle and the driving speed of the driving controller and generating steering data and driving speed data;
the route prediction unit is used for acquiring real-time advancing images and steering data and traveling speed data of the box girder transfer trolley and generating advancing track prediction images;
the vibration sensing unit is used for acquiring vehicle body vibration data of the box girder transfer vehicle in the process of proceeding;
the road condition detection unit is used for acquiring the real-time advancing image, identifying the road surface fluctuation position in the real-time advancing image and generating road surface fluctuation data;
the data association unit is used for acquiring vehicle body vibration data and road surface fluctuation data, associating the vehicle body vibration data and the road surface fluctuation data and generating traveling association data;
and the early warning feedback unit calculates to obtain vehicle body predicted jitter data according to the traveling correlation data, generates a traveling control instruction corresponding to the speed change of the box girder transfer vehicle according to a corresponding vehicle body jitter data preset threshold value, and is called and selectively executed by a traveling controller of the box girder transfer vehicle.
In order to intuitively explain the technical idea of the present embodiment, the present embodiment further provides a simulation example, which is shown in one of fig. 6 to fig. 9, and the following operation flow is briefly described with reference to fig. 8 and fig. 9:
s1, starting the box girder transfer trolley and carrying out uniform acceleration running along a preset travelling route to reach a preset speed;
s2, acquiring a road image in front of the travelling route of the box girder transfer trolley, and generating a real-time travelling image, referring to FIG. 6;
s3, generation of the predicted image of the traveling track and the road surface undulation data
S3.1, acquiring the steering angle and the driving speed of the driving controller, generating steering data and driving speed data, associating the real-time advancing image with the steering data and the driving speed data of the box girder transfer trolley, and generating an advancing track prediction image, referring to FIG. 7;
s3.2, converting the video stream in the real-time moving image into image frames, and then extracting corresponding image frames according to a preset time interval to generate monitoring image frames;
s3.3, identifying and positioning the road surface fluctuation part in the monitoring image frame and outputting road surface fluctuation data through a positioning neural network and a detecting neural network, wherein the positioning neural network identifies the fluctuation part in the monitoring image frame within the travel prediction track range and generates a positioning frame, then the detecting neural network directly detects an object in the positioning frame and outputs fluctuation data, and the specifically modified road surface fluctuation data is shown in a reference figure 8;
s4, acquiring the running speed data and the frame shaking data of the box girder transfer trolley, and associating the running speed data and the frame shaking data with the road surface fluctuation data to acquire data correlation information;
s5, according to the data correlation information, then generating a corresponding prediction curve for the variation of the amplitude in the vehicle frame jitter data in a preset period DeltaT, according to the prediction curve, when the time node is T3, the prediction amplitude of the vehicle frame is higher than a first preset threshold value, and at the moment, in order to avoid the occurrence of adverse consequences, a driving control instruction for controlling the speed change of the box girder transfer vehicle is generated in advance at the time node T1 before T3 and called and selectively executed by a driving controller of the box girder transfer vehicle, so that the vehicle frame amplitude data after the time node T1 is in a descending trend, while the amplitude in the vehicle frame jitter data obtained at the time node T2 is larger than a second preset threshold value and smaller than the first preset threshold value, and meanwhile, when the road surface fluctuation data is larger than the preset threshold value, outputting a driving control instruction for driving at a constant speed, calling and selectively executing by the driving controller, fig. 9 shows a running speed change curve of the vehicle after two speed change running commands are inserted.
The amplitude is the swing amplitude of the frame in one vibration cycle, and the road surface undulation height difference of the road surface undulation data is the difference between the highest point and the lowest point of the road surface within a preset distance difference (for example, within 10-30 cm, namely the effective contact length range of the wheels and the ground).
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be substantially or partially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a part of the embodiments of the present invention, and not intended to limit the scope of the present invention, and all equivalent devices or equivalent processes performed by the present invention through the contents of the specification and the drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A concrete box girder carrying control method is used for carrying and advancing control of a box girder transfer trolley, and a traveling controller used for controlling the travelling and steering of the box girder transfer trolley is arranged on the box girder transfer trolley, and is characterized by comprising the following steps:
s1, acquiring a road image in front of the travelling route of the box girder transfer trolley, and generating a real-time travelling image;
s2, acquiring a real-time advancing image, identifying a road surface undulating part in the real-time advancing image and generating road surface undulating data;
s3, acquiring the running speed data and the frame shaking data of the box girder transfer trolley, and associating the running speed data and the frame shaking data with the road surface fluctuation data to acquire data correlation information;
and S4, generating a running control command for controlling the speed conversion of the box girder transfer vehicle according to the data correlation information, and calling and selecting to execute by the running controller of the box girder transfer vehicle.
2. The concrete box girder transfer control method according to claim 1, wherein the step S2 further includes:
the method comprises the steps of obtaining the steering angle and the running speed of a running controller, generating steering data and running speed data, correlating a real-time advancing image with the steering data and the running speed data of a box girder transfer trolley, and generating an advancing track prediction image.
3. The method for controlling the transportation of a concrete box girder according to claim 2, wherein the concrete steps of identifying the road surface undulation portion in the real-time traveling image and generating the road surface undulation data in step S2 include:
s2.1, converting a video stream in the real-time moving image into image frames, and then extracting corresponding image frames according to a preset time interval to generate monitoring image frames;
and S2.2, identifying and positioning the road surface fluctuation part in the monitoring image frame through the positioning neural network and the detection neural network, and outputting road surface fluctuation data.
4. The method as claimed in claim 3, wherein in step S2.2, the positioning neural network identifies the undulation portion within the range of the predicted path of travel in the monitoring image frame to generate a positioning frame, and the detecting neural network directly detects the object within the positioning frame and outputs undulation data.
5. The concrete box girder transport control method according to claim 4, wherein the training method of the positioning neural network in the step S2.2 comprises the following steps:
inputting a plurality of preset road surface images, marking the road surface undulating parts and the corresponding convex and concave heights, and then reading and training by a positioning neural network;
inputting a plurality of verification road surface images, reading and outputting positioning results by a positioning neural network, manually checking, re-labeling the images failed or wrong in detection, inputting the images into the positioning neural network again for reading and outputting the positioning results until the detection is successful.
6. The concrete box girder transport control method according to claim 4, wherein the training method for detecting the neural network in the step S2.2 comprises the following steps:
inputting a plurality of preset road surface images, marking the road surface undulating parts and the corresponding convex and concave heights, and reading and training by a detection neural network;
inputting a plurality of verification road surface images, reading and outputting detection results by a detection neural network, manually checking, re-labeling failed or wrong images, inputting the images into the detection neural network again for reading and outputting the detection results until the detection is successful.
7. The concrete box girder transfer control method according to claim 1, wherein in step S4,
when the amplitude in the vehicle frame shaking data is larger than a first preset threshold value, outputting a driving control instruction for uniform deceleration driving until the amplitude in the vehicle frame shaking data is smaller than the first threshold value, and calling and selectively executing by a driving controller;
when the amplitude in the vehicle frame shaking data is smaller than a preset second preset threshold value and the real-time road surface fluctuation data is larger than the preset threshold value, outputting a running control instruction for constant-speed running, and calling and selectively executing by a running controller;
when the amplitude in the vehicle frame shaking data is smaller than a preset second preset threshold value and the real-time road surface fluctuation data is smaller than the preset threshold value, outputting a running control instruction for accelerating running until the running speed reaches 80% of the preset highest running speed, and calling and selectively executing by a running controller;
the amplitude in the vehicle frame shaking data is larger than a second preset threshold value and smaller than a first preset threshold value, and meanwhile, when the road surface fluctuation data is larger than the preset threshold value, a driving control instruction for driving at a constant speed is output and called and selectively executed by a driving controller;
and when the amplitude in the vehicle frame shaking data is larger than a second preset threshold value and smaller than a first preset threshold value and the road surface fluctuation data is smaller than the preset threshold value, outputting a driving control command for accelerating driving until the traveling speed reaches 60% of the preset highest traveling speed, and calling and selectively executing by a driving controller.
8. A concrete box girder transfer control method according to any one of claims 1 to 7, wherein said transfer control method further comprises an unmanned mode, a manned mode and an assisted driving mode for one of the modes,
when the unmanned driving mode is adopted, the travel speed control of the travel controller is controlled by the travel control command generated at step S4;
when the driving assistance mode is adopted, the driving controller calls the driving control command generated in step S4 to prompt, and the operator selects the command;
when the manual driving mode is adopted, the travel controller calls only the travel control command generated in step S4 to present the command.
9. A concrete box girder transporting apparatus to which the transporting control method according to any one of claims 1 to 8 is applied, comprising a box girder transfer vehicle and a travel controller provided on the box girder transfer vehicle for controlling travel and steering thereof, wherein it further comprises a road condition detection feedback mechanism connected to the travel controller for providing a feedback of a traveling road condition, the road condition detection feedback mechanism comprising:
the image shooting unit is used for obtaining a road surface image in front of a travelling route of the box girder transfer trolley and generating a real-time travelling image;
the information acquisition module is used for acquiring the steering angle and the driving speed of the driving controller and generating steering data and driving speed data;
the route prediction unit is used for acquiring real-time advancing images and steering data and traveling speed data of the box girder transfer trolley and generating advancing track prediction images;
the vibration sensing unit is used for acquiring vehicle body vibration data of the box girder transfer vehicle in the process of proceeding;
the road condition detection unit is used for acquiring the real-time advancing image, identifying the road surface fluctuation position in the real-time advancing image and generating road surface fluctuation data;
the data association unit is used for acquiring vehicle body vibration data and road surface fluctuation data, associating the vehicle body vibration data and the road surface fluctuation data and generating traveling association data;
and the early warning feedback unit calculates to obtain vehicle body predicted jitter data according to the traveling correlation data, generates a traveling control instruction corresponding to the speed change of the box girder transfer vehicle according to a corresponding vehicle body jitter data preset threshold value, and is called and selectively executed by a traveling controller of the box girder transfer vehicle.
10. A storage medium, characterized by: the storage medium stores at least one instruction, at least one program, a set of codes, or a set of instructions that is loaded by a processor and executed to implement a method of controlling handling of concrete box girders as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011023771.4A CN112109713B (en) | 2020-09-25 | 2020-09-25 | Concrete box girder handling device and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011023771.4A CN112109713B (en) | 2020-09-25 | 2020-09-25 | Concrete box girder handling device and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112109713A true CN112109713A (en) | 2020-12-22 |
| CN112109713B CN112109713B (en) | 2021-09-03 |
Family
ID=73797770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011023771.4A Active CN112109713B (en) | 2020-09-25 | 2020-09-25 | Concrete box girder handling device and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112109713B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108639065A (en) * | 2018-05-15 | 2018-10-12 | 辽宁工业大学 | A kind of vehicle safe driving control method of view-based access control model |
| US20190227543A1 (en) * | 2018-01-24 | 2019-07-25 | Hanwha Land Systems Co., Ltd. | Driving information display device, driving information display method, and method of controlling driving speed of working vehicle |
| CN111178237A (en) * | 2019-12-27 | 2020-05-19 | 上海工程技术大学 | Pavement state recognition method |
| CN111347831A (en) * | 2020-03-13 | 2020-06-30 | 北京百度网讯科技有限公司 | Vehicle running stability control method, device, equipment and storage medium |
| CN111516692A (en) * | 2020-04-20 | 2020-08-11 | 重庆长安汽车股份有限公司 | Control system and method for vehicle running on hollow road surface |
-
2020
- 2020-09-25 CN CN202011023771.4A patent/CN112109713B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190227543A1 (en) * | 2018-01-24 | 2019-07-25 | Hanwha Land Systems Co., Ltd. | Driving information display device, driving information display method, and method of controlling driving speed of working vehicle |
| CN108639065A (en) * | 2018-05-15 | 2018-10-12 | 辽宁工业大学 | A kind of vehicle safe driving control method of view-based access control model |
| CN111178237A (en) * | 2019-12-27 | 2020-05-19 | 上海工程技术大学 | Pavement state recognition method |
| CN111347831A (en) * | 2020-03-13 | 2020-06-30 | 北京百度网讯科技有限公司 | Vehicle running stability control method, device, equipment and storage medium |
| CN111516692A (en) * | 2020-04-20 | 2020-08-11 | 重庆长安汽车股份有限公司 | Control system and method for vehicle running on hollow road surface |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112109713B (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8401732B2 (en) | Vehicle control device and vehicle control method | |
| CN112052776B (en) | Unmanned vehicle autonomous driving behavior optimization method and device and computer equipment | |
| KR102416203B1 (en) | Self-learning vehicle control system | |
| TWI611280B (en) | Tele-operated vehicle, and vehicle control device and control method thereof | |
| CN110371112A (en) | A kind of intelligent barrier avoiding system and method for automatic driving vehicle | |
| EP2752347B1 (en) | Vehicular information-processing device and vehicular information-processing method | |
| KR101874186B1 (en) | Method for predicting driving path of object vehicle by maching learning and method for controlling vehicle using the same | |
| CN113324554B (en) | Automatic driving route planning method and device, readable storage medium and electronic equipment | |
| CN112109713B (en) | Concrete box girder handling device and control method | |
| WO2023197417A1 (en) | Crane stability analysis method and apparatus, and crane anti-overturn control method and apparatus | |
| JP2013199222A (en) | Driving evaluation apparatus | |
| CN116691626B (en) | Vehicle braking system and method based on artificial intelligence | |
| CN113651221A (en) | Method and device for taking escalator by robot and storage medium | |
| CN113450407B (en) | Positioning method, operation method, electronic device, track device, and storage medium | |
| CN113902197B (en) | Method and system for improving service efficiency of container based on big data application | |
| JP7124973B2 (en) | parking assistance system | |
| KR101992098B1 (en) | Chassis location guide system and Method thereof | |
| CN118131754A (en) | Control method, device and system for ladle car and storage medium | |
| US20230406298A1 (en) | Method for Training and Operating Movement Estimation of Objects | |
| CN117601838B (en) | Energy distribution method, device, equipment and medium for hybrid forklift running system | |
| KR20190027619A (en) | Truck head recognition and adjacent container detection and Method thereof | |
| WO2024017413A2 (en) | Method and apparatus for port entry/exit detection of vehicle, device, and storage medium | |
| WO2022257056A1 (en) | Autonomous driving system, method and apparatus for vehicle, and computer device and storage medium | |
| CN115038618A (en) | Method and device for classifying accident processes in connection with two-wheeled vehicles | |
| JP2023005576A (en) | Driving support device, monitoring device, driving support method, and program |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240108 Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Dragon totem Technology (Hefei) Co.,Ltd. Address before: 350108 No. 200 Xiyuan Gong Road, Minhou County, Fuzhou City, Fujian Province Patentee before: MINJIANG University |
|
| TR01 | Transfer of patent right |