CN107942659A - Transmitting device control method and equipment - Google Patents
Transmitting device control method and equipment Download PDFInfo
- Publication number
- CN107942659A CN107942659A CN201711106788.4A CN201711106788A CN107942659A CN 107942659 A CN107942659 A CN 107942659A CN 201711106788 A CN201711106788 A CN 201711106788A CN 107942659 A CN107942659 A CN 107942659A
- Authority
- CN
- China
- Prior art keywords
- transmitting device
- echo
- signal
- control signal
- range data
- 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 54
- 230000003287 optical effect Effects 0.000 claims abstract description 77
- 239000000463 material Substances 0.000 claims abstract description 35
- 230000011664 signaling Effects 0.000 claims abstract description 35
- 238000010801 machine learning Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000005540 biological transmission Effects 0.000 claims description 31
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 239000003245 coal Substances 0.000 description 17
- 238000013528 artificial neural network Methods 0.000 description 9
- 238000013527 convolutional neural network Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 239000002390 adhesive tape Substances 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012417 linear regression Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000007935 neutral effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000032370 Secondary transmission Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
This application discloses a kind of transmitting device control method and equipment, this method to include:The one or more optical radars of control are sending optical signalling from multiple directions to transmitting device at different moments;Receive the echo-signal of the optical signalling;Obtained and the relevant multiple range data of material on the transmitting device according to the echo-signal;The multiple range data is integrated to the transmitting device output control signal.The embodiment of the present application obtains the range data in multiple directions by optical radar, and the training pattern obtained using machine learning obtains the control signal to match with range data automatically, so that more accurate efficient control can be realized.
Description
Technical field
The application belongs to automatic control technology field, more particularly to a kind of transmitting device control method and equipment.
Background technology
In material transferring field, it is most basic also most urgent that material is transported to designated position by devices such as conveyer belts
Demand.But, on the one hand, Transmission system needs to consume the substantial amounts of energy when running;On the other hand, the transmission of material is often pressed
It need to carry out, its demand has very strong erratic behavior, and situation off and on is commonplace;That is, traditional transmission
System often carrys out substantial amounts of energy consumption because of system free-running belt, and efficiency is extremely low.
To avoid a series of problems that free-running belt is come, occur some intelligent control belt speeds of service in the prior art
Scheme, for example by installing infrared light curtain at the feed inlet of feed bin, the signal for identifying material according to infrared light curtain controls main skin
The startup and stopping of band;Or material is identified according to the image/video that camera gathers, and then control the startup of main belt
And stopping;Also utilize the scheme of the volume of material of lidar measurement feeding moment, its shape based on accurate conveyer belt
Model, carries out ranging using laser radar under the model, according to the mathematic interpolation volume of material of measured value and model, so that real
The instantaneous measurement of existing volume of material.
But inventor has found in the implementation of the present invention, the above-mentioned prior art is lacked there is more obvious
Fall into.Wherein, infrared light curtain can only identify whether to have material to cut light curtain in receiving terminal, can not accurate controlling transmission device operation
The parameters such as speed, power.And image/video analytical technology is higher to site environment requirement, but underground coal mine environment is more multiple
It is miscellaneous, for example can may cause the smudgy Chu of image/video there are substantial amounts of dust and water mist in coal production process, and
The accuracy of impact analysis.Laser radar range based on transmission band model depends critically upon the precision of model, its applicability
, can not promotion and application on a large scale and flexibility is very limited.
Therefore, in the prior art material transmitting device can not still be accomplished rationally and accurately and efficiently to control, energy waste
Situation it is universal and unmanageable.
The content of the invention
For the drawbacks described above of the prior art, the embodiment of the present application provides a kind of transmitting device controlling party that can be adaptive
Case.
In a kind of possible embodiment, there is provided a kind of transmitting device control method, the described method includes:
The one or more optical radars of control are sending optical signalling from multiple directions to transmitting device at different moments;
Receive the echo-signal of the optical signalling;
Obtained and the relevant multiple range data of material on the transmitting device according to the echo-signal;
The multiple range data is integrated to the transmitting device output control signal.
Alternatively, it is described to be obtained and the relevant multiple range data of material on the transmitting device according to the echo-signal
Including:
Determine that echo position is to the first of the optical radar in this direction according to the echo-signal in each direction
Range information;
By first range information compared with reference range information, with obtain in this direction the echo position to described
The second distance information on transmitting device surface.
Alternatively, the reference range information is in advance measured for presupposed information or by the optical radar.
Alternatively, the multiple range data of the synthesis includes to the transmitting device output control signal:
The training pattern that the input of the multiple range data is obtained via machine learning;
The training pattern obtains and the most matched control signal of the multiple range data according to history training program;
The described and most matched control signal of the multiple range data is exported to the transmitting device.
Alternatively, the method further includes:
Receive the transmitting device and perform the feedback information after the control signal;
Further machine learning is carried out using the feedback information, to correct the training pattern.
Alternatively, the machine learning uses one in artificial neural network, convolutional neural networks and deep neural network
Kind or a variety of progress.
Alternatively, the transmitting device is multistage transmitting device, in the method:
The optical signalling is to be sent to one or more higher level's transmitting devices;
The control signal is to be exported to one or more subordinate's transmitting devices.
Alternatively, the method further includes:
One or more of subordinate's transmitting devices realize that following current starts according to the control signal.
Alternatively, the method further includes:
Gather the view data of the transmitting device;
The control signal is obtained according to described image data auxiliary.
Alternatively, the optical radar is obtained according to the optical signalling and the echo-signal by flight time ToF
The range data.
In alternatively possible embodiment, a kind of transmitting device control device is also provided, including:
Radar control unit, for controlling one or more optical radars at different moments from multiple directions to transmitting device
Send optical signalling;
Echo receiving unit, for receiving the echo-signal of the optical signalling;
Distance acquiring unit, for according to the echo-signal obtain with the transmitting device on material it is relevant it is multiple away from
From data;
Output unit is controlled, for integrating the multiple range data to the transmitting device output control signal.
Alternatively, the distance acquiring unit includes:
Echo is apart from determining module, for determining echo position in this direction according to the echo-signal in each direction
To the first range information of the optical radar;
Surface distance determining module, for by first range information compared with reference range information, to obtain the party
Second distance information of the upward echo position to the transmitting device surface.
Alternatively, the reference range information is in advance measured for presupposed information or by the optical radar.
Alternatively, the control output unit includes:
Data input module, for the training pattern for obtaining the input of the multiple range data via machine learning;
Auto-matching module, for making the training pattern be obtained and the multiple range data according to history training program
Most matched control signal;
Signal output module, believes to transmitting device output is described with the most matched control of the multiple range data
Number.
Alternatively, the equipment further includes:
Feedback reception unit, for receiving the feedback information after the transmitting device performs the control signal;
Learn amending unit, for carrying out further machine learning using the feedback information, to correct the training
Model.
Alternatively, the machine learning uses one in artificial neural network, convolutional neural networks and deep neural network
Kind or a variety of progress.
Alternatively, the transmitting device is multistage transmitting device, in the equipment:
The radar control unit is additionally operable to send the optical signalling to one or more higher level's transmitting devices;
The control output unit is additionally operable to export the control signal to one or more subordinate's transmitting devices.
Alternatively, the equipment further includes:
Following current start unit, for making one or more of subordinate's transmitting devices realize following current according to the control signal
Start.
Alternatively, the equipment further includes:
Image acquisition units, for gathering the view data of the transmitting device;
Visual aids control unit, for obtaining the control signal according to described image data auxiliary.
Alternatively, the optical radar is obtained according to the optical signalling and the echo-signal by flight time ToF
The range data.
Embodiments herein provides a kind of transmitting device control method and equipment, the program and is obtained by optical radar
Range data in multiple directions, the training pattern obtained using machine learning obtain the control to match with range data automatically
Signal processed, so that more accurate efficient control can be realized.In addition, the scheme of the embodiment of the present application can it is fast automatic adapt to it is various not
Same equipment and environment, its flexibility and applicability is far above the prior art.
Brief description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of application.
Fig. 1 is the structure diagram for the control system that optical radar is carried in one embodiment of the application;
Fig. 2 be the application one embodiment in transmitting device control method flow diagram;
Fig. 3 carries out the schematic diagram of machine learning for convolutional neural networks in one embodiment of the application;
Fig. 4 be the application one embodiment in transmitting device control device modular structure schematic diagram.
Embodiment
To enable present invention purpose, feature, advantage more obvious and understandable, below in conjunction with the application
Attached drawing in embodiment, is clearly and completely described the technical solution in the embodiment of the present application, it is clear that described reality
It is only some embodiments of the present application to apply example, and not all embodiments.Based on the embodiment in the application, people in the art
Member's all other embodiments obtained without making creative work, shall fall in the protection scope of this application.
Set it will be understood by those skilled in the art that the term such as " first ", " second " in the application is only used for difference difference
Standby, module or parameter etc., neither represent any particular technology implication, also do not indicate that the inevitable logical order between them.
The core of material transferring control problem be how the start and stop of accurate controlling transmission device so that the fortune of transmitting device
Rotary speed matches with inlet amount, the energy consumption for avoiding free-running belt from.Pass through infrared light curtain, camera or sharp in the prior art
Optical radar etc. realizes the detection to material, but existing scheme is generally difficult to the volume that accurately measures material, especially can not
Measured for the environment self-adaption of complexity change.In embodiments herein, detected comprehensively by optical radar,
The training pattern obtained using machine learning produces control signal so that the measurement and transmission control of material can more precisely more
Efficiently, and a variety of equipment and environment can be adapted to automatically.
As shown in Figure 1, in the typical case scene of the application, pass through a control system for carrying optical radar
To carry out the control of the detection of material and transmitting device, transmitting device operation is moved it is achieved thereby that feeding situation according to material
State controls.In Fig. 1, the control system of transmitting device includes:Transmitting device 10, optical radar 20,30 and of radar control unit
Transmission control unit 40;Wherein, the transmitting device 10 includes material supporting part 11 and driving motor 12, the driving motor 12
The material supporting part 11 is driven to be moved to assigned direction by mechanical transmission component;The optical radar 20 includes optical signalling
Emission part 21 and echo signal reception portion 22, the optical radar 20 couple radar control unit 30, the optical radar 20
According to the radar control unit 30 provide radar control signal period property or adjust 21 He of optical signalling emission part at random
Number is launched and received to signal by the signal transmitting in the echo signal reception portion 22 and receiving angle, the optical radar 20 at the same time
According to feeding back to the radar control unit 30;The radar control unit 30 is also coupled to transmission control unit 30, by the signal
Transmitting and the range data received represented by data are supplied to the transmission control unit;The transmission control unit 30 couples institute
The driving motor 12 of transmitting device 10 is stated, the matched motor of 12 the output phase of motor is driven to described according to the range data
Control signal.
In embodiments herein, the range data in multiple directions is obtained by optical radar, uses machine learning
Obtained training pattern obtains the control signal to match with range data automatically, so that more accurate efficient control can be realized
System, and the control system of the embodiment of the present application fast automatic can adapt to a variety of equipment and environment, its flexibility and is applicable in
Property is far above the prior art.
Wherein, in embodiments herein, optical radar is by sending optical signalling and receiving the optical signalling anti-
Echo-signal caused by reflective surface, ranging is carried out by TOF (Time of Flight, flight time).In the application
Optical radar includes the use of the optical radar of different-waveband optical signalling (including visible ray and/or black light etc.).Further
Ground, with the progress of electronic device, the cost of laser radar technique is gradually reduced so that its application field is more and more wider.Due to
Laser radar has some superiority in terms of cost, precision, reliability and antijamming capability, in the preferred embodiment of the application
In, the optical radar includes single line and/or multi-line laser radar.
In embodiments herein, transmitting device is not limited to conveyer belt, also the transmitting device including other forms,
Such as scrapper conveyor, screw conveyor etc..Also, transmitting device is also not limited to single transmission part in the present invention, can also wrap
Include the Transmission system that multiple transmission parts are composed, such as multiple conveyer system, or conveyer belt and other transmitting devices
Combination etc..
Referring to Fig. 2, in embodiments herein, based on the above-mentioned control system with optical radar, also provide at the same time
A kind of transmitting device control method, including:
S1, controls one or more optical radars sending optical signalling from multiple directions to transmitting device at different moments.
Wherein, it is in order to obtain range data as comprehensive as possible, so as to a certain to send optical signalling from multiple directions
The volume of material at moment, which has, more accurately to be understood, and is accurately controlled to realize.And it is then sending optical signalling at different moments
In order to grasp material charging situation in real time, to be dynamically adjusted.Alternatively, it is described to include periodically in transmission at different moments
Send and/or random times are sent.
S2, receives the echo-signal of the optical signalling.
For each optical signalling, can pass through when it projects surface of material because reflecting to form an echo-signal
Receive the echo-signal, it will be appreciated that the propagation condition of corresponding optical signalling under the present circumstances.
S3, obtains and the relevant multiple range data of material on the transmitting device according to the echo-signal.
As it was previously stated, optical radar is mainly by flight time TOF come ranging, more specifically, by one direction
The transmission receiving time of optical signalling and echo-signal is poor, recycles the transmission speed of light, can calculate the transmission range of light extraction,
Optical signalling emission part (i.e. optical radar) in this direction arrive the distance of echo position so as to draw (or echo position is to light
Learn the distance of radar echo signal receiving division).
S4, integrates the multiple range data to the transmitting device output control signal.
Typically, according to the distance of echo position in multiple directions to optical radar, the calculating of volume of material can be carried out,
So that according to the size of volume of material come the transmission speed of controlling transmission device.Certainly, in the alternative embodiment of the application, thing
Expect that the calculating of volume and/or the generation of control signal do not rely on merely formula and real-time operation, can also pass through such as engineering
The mode of habit carries out the matching of more intelligent and high-efficiency, here, the concrete mode of control signal is obtained by range data to be regarded
Make the limitation to the application embodiment.
In one embodiment of the application, by the way that echo distance to be obtained to material in this direction compared with reference range
Thickness.Specifically, determine that echo position is to the optical radar in this direction according to the echo-signal in each direction
First range information;By first range information compared with reference range information, to obtain the echo position in this direction
To the second distance information on the transmitting device surface.Alternatively, the reference range information is for presupposed information or by described
Optical radar measures in advance.
In the embodiment of the application, by taking the coal transmitting device with laser radar as an example, one is swashed
Optical radar sends optical signalling, and receives echo-signal to a transmitting device, such as conveyer belt, can according to echo-signal
Obtain the range information on a direction.By in different time, launch optical signalling using different launch angles and receive phase
The echo-signal answered, laser radar can obtain different time, multiple range informations on different directions.The range information is with sharp
Optical radar, can be with the distance between echo position in secondary indication a direction and transmitting device surface as a reference point.
Note that since laser radar transmitting signal carries certain directionality, this range information is simultaneously not equal to transmitting device surface coal
Height, but one with the relevant range information in laser radar position.OrderIt is expressed as i-th of time point, on j-th of direction
Distance, then one group of different time, the range data group of different directions can be expressed as:
Range data group d is input in a controller, and draws the control signal of transmitting device:
P=(d);
Wherein, p is the control signal of a transmitting device.In one embodiment, p is a speed control signal,
It is connected with a frequency converter, and then controls the transfer rate of transmission device.In addition, p can also be an indirect control
Signal, is input to the control device of next stage, and the transfer rate of transmission device is finally controlled by next stage control device.One
In kind embodiment, p is a continuous variable, and value can be arbitrary value within a certain range.In a kind of embodiment
In, p is a discrete variable, and value is one in multiple predetermined values.
There are a variety of methods to realize the implementation to control function f (), such as pass through a linear combination set in advance
Formula.Multiple variables in d are weighted average, and then obtain p value, wherein average weighted weights need accurate instruction and
Test, can be matched with increasing obtained p with the line speed of needs.In another embodiment, use is non-linear
Processing method, corresponding f () can also be obtained.Since the method for f () is there are infinite a variety of, do not enumerate herein.Another
In a kind of embodiment, handled using the method for machine learning information of adjusting the distance, and then obtain specific control function f
().The method of the machine learning is a kind of by training data, first Controlling model is trained, and then obtain one
A available Controlling model.The method of machine learning includes linear regression, nonlinear regression, K-Means, decision tree, random gloomy
The distinct methods such as woods, artificial neural network, convolutional neural networks or deep neural network.In one embodiment, can make
Continuous control signal p is obtained with linear regression.Specifically, using linear method by different time, different angle
Range information is weighted averagely, and then obtains the output valve of control signal, such as:
Wherein,It is expressed as i-th of time point, the distance weighting on j-th of direction;By the data of mark and right
The range data group answered, uses corresponding training method, it is possible to obtains the final weights of linear regressionPass through the model, it is possible to actual operating data is handled using equation below, is obtained each
The control signal of secondary transmission device:
In a kind of optional embodiment, the data group that can be adjusted the distance using convolutional neural networks is handled, and then
To discrete control signal.As shown in figure 3, this method, using range data group as an input, being input to one has multilayer
Convolutional neural networks among, and finally obtain single, discrete control signal.By using the training data with mark,
Such as using the range data group information for being labelled with optimum control signal, the neutral net can under the training of mass data,
Obtain a final neural network weight.Then, the data group collected in operation is inputted into the neutral net, so that it may
To obtain a discrete control signal.Due to the use of the mode of convolutional neural networks, discrete control signal can be appointed
The formulation of meaning, for example, control signal can be divided into 3 levels, represents 3 different speed respectively.In addition it is also possible to control
Signal processed is divided into 5 levels, represents 5 different speed respectively.The setting of control signal from any Controlling model limitation,
Only need to change corresponding markup information.
Only needed according to range data group using the method for machine learning, the output with regard to a control signal can be obtained,
The method avoids the limitation to transmitting device.Only need to obtain enough data, the processing method of machine learning is with regard to energy
The speed of the transmitting device of accurate control any form, without learning the specifying information of transmitting device, such as transmission dress in advance
The morphology put.In addition, only needed without the specific angle for considering each range information using the method for machine learning
The form of training data and actual operating data and acquisition mode is wanted to keep unified.
It is evidenced from the above discussion that the adaptability of the system is greatly improved using the method for machine learning so that this method
Can rapid deployment to arbitrary transmitting device, arbitrary laser radar set-up mode, arbitrary control signal hierarchical system it
In.
In another optional embodiment, the method for machine learning uses one group of reference range.Reference range information pair
Range data group under Ying Yuyi light condition.Its acquisition mode can be by way of prestoring, or in operation
The mode of actual acquisition obtains on transmitting device.For example, in the case of transmitting device zero load, recording laser radar obtains more
A range data group.By processing, a reference range data group is obtained.For another example controller passes through to multigroup range data
The data of group are handled, and judge that current transmission device is under light condition, are handled multi-group data, are obtained a stand-off
From data group.Reference range data group reflects the range information under light condition, which can be used as input, be input to instruction
Practice in data, machine learning Controlling model is trained.Also, in actual operation, the data are defeated also at the same time as input
Enter into Controlling model, obtain specific control signal.
For example, one group of reference range can be:
Thus, the range data group used in trained range data combination actual motion can make reference range group
For input, that is to say, that new range data group is changed into:
And the machine learning method used is constant, simply final model is otherwise varied.
In a kind of optional embodiment, outside laser radar extra imaging sensor can also be coordinated further to carry
Rise the robustness of control system.For example, an imaging sensor obtains one group of view data:
At this time, the data of imaging sensor and the data of laser radar can be input to machine learning at the same time as input
Algorithm in.That is, the data of machine learning are the data acquisition system of b and d.In one embodiment, described image passes
Sensor is a kind of depth transducer, that is to say, that the sensor can obtain pickup area by the processing to picture signal
On different directions with the distance between sensor information.For example,
Q=l (b);
L () is a depth extraction algorithm, by the processing to view data b, obtains depth information q.At this time, engineering
The data of habit are changed into the data acquisition system of b and q.
In a kind of optional embodiment, coal Transmission system includes multiple levels, and the transmitting device of multiple upper levels will
Coal is transmitted to the transmitting device of a next stage.For example, multiple conveyer belts by coal near coal-mine, be transferred to a main belt
On.At this time, coal of the next stage transmitting device due to carrying multiple upper level transmitting device transmission, it is therefore desirable to which consumption is more
The energy.Therefore, more energy sections can be brought to next stage transmitting device, such as the intelligent control of main belt
About.
In a kind of optional embodiment, the upward Primary Transmit device of laser radar sends optical signalling, receives echo letter
Number, and in the range information of acquisition of multiple time points multiple directions.Multiple data-signals are inputted into controller, controller makes
With one kind in above-mentioned machine learning method, and then obtain the control signal of next stage transmitting device.Such as:
diFor the range data group of i-th of higher level's transmitting device, multiple range data groups are inputted into above-mentioned machine learning side
In method, such as the method for linear regression or convolutional neural networks, it is possible to obtain the control signal of next stage transmitting device:
pmain=f (d1,d2,…,dI)。
Based on above method, next stage transmitting device can be by the laser installed on multiple upper level transmitting devices
The data of radar collection realize intelligent control.
In a kind of optional embodiment, in the actual production of colliery, in order to ensure the security of personnel and equipment, colliery
Car mode is substantially opened using inverse coal stream in sealing-tape machine opens car mode and carries out equipment startup, so-called inverse coal stream Qi Chewei is from unloading
Loading point starts progressively to carry out opening car to gatehead, and can be related to a plurality of adhesive tape conveyor overlap joint during car is entirely opened, therefore
When inverse coal stream is completed, the adhesive tape conveyor of overlap joint is in idling conditions among whole tape transport system, uses in the past
The suitable coal stream Qi Chezhong that belt conveyer scale e measurement technology changes, since belt conveyer scale belongs to contact weighing-appliance, when sealing-tape machine is transported at a high speed
Go and sealing-tape machine adhesive tape junction connector is by that can cause sealing-tape machine adhesive tape and belt conveyer scale non-contact condition occur after belt conveyer scale,
Therefore the erroneous judgement of control system can be caused, cause the control mistake of control system, lidar measurement skill is being based on using above-mentioned
Art is that material distance is measured from sealing-tape machine surface, solves the situation of belt conveyer scale wrong report.And then it can reach along coal stream
Car operation is opened, car process is opened to unloading point step by step from belt gatehead along coal stream Qi Chewei, can be evaded during car is opened whole
The idle running of the superior and the subordinate's adhesive tape conveyor in belt conveyor system.That is, by controlling above-mentioned control signal pmainIn
Function f (), it is possible to realize above-mentioned desired suitable coal stream Starting mode so that the adhesive tape per level-one is only transported when necessary
Turn.Likewise, f () can be obtained using a predefined formula, such as using average weighted mode by all higher levels
The range information of conveyer belt is weighted averagely, obtains pmainSignal.Average weighted weights by advance instruction and emulation,
So that pmainThe output of signal can realize the demand started along coal stream.That is when higher level's conveyer belt does not have material, pmain
Export subordinate's conveyer belt quieting control signal.In another embodiment, the method that machine learning can also be used, by right
Controlling model is trained, and obtains the stronger Controlling model of adaptivity.Whole model by neutral net and training data come
Realize, avoid the calculating and instruction to weights.This method can more accurately realize the demand that starts along coal stream you, while energy
Enough it is suitable for a variety of conveyer belt scenes and different multiple conveyers configures.
Further as shown in figure 4, corresponding with the method in above-described embodiment, embodiments herein also provides one kind
Transmitting device control device 400, including:
Radar control unit 410, for controlling one or more optical radars at different moments from multiple directions to transmission
Device sends optical signalling;
Echo receiving unit 420, for receiving the echo-signal of the optical signalling;
Distance acquiring unit 430 is relevant more with material on the transmitting device for being obtained according to the echo-signal
A range data;
Output unit 440 is controlled, for integrating the multiple range data to the transmitting device output control signal.
Alternatively, the distance acquiring unit includes:
Echo is apart from determining module, for determining echo position in this direction according to the echo-signal in each direction
To the first range information of the optical radar;
Surface distance determining module, for by first range information compared with reference range information, to obtain the party
Second distance information of the upward echo position to the transmitting device surface.
Alternatively, the reference range information is in advance measured for presupposed information or by the optical radar.
Alternatively, the control output unit includes:
Data input module, for the training pattern for obtaining the input of the multiple range data via machine learning;
Auto-matching module, for making the training pattern be obtained and the multiple range data according to history training program
Most matched control signal;
Signal output module, believes to transmitting device output is described with the most matched control of the multiple range data
Number.
Alternatively, the equipment further includes:
Feedback reception unit, for receiving the feedback information after the transmitting device performs the control signal;
Learn amending unit, for carrying out further machine learning using the feedback information, to correct the training
Model.
Alternatively, the machine learning uses one in artificial neural network, convolutional neural networks and deep neural network
Kind or a variety of progress.
Alternatively, the transmitting device is multistage transmitting device, in the equipment:
The radar control unit is additionally operable to send the optical signalling to one or more higher level's transmitting devices;
The control output unit is additionally operable to export the control signal to one or more subordinate's transmitting devices.
Alternatively, the equipment further includes:
Following current start unit, for making one or more of subordinate's transmitting devices realize following current according to the control signal
Start.
Alternatively, the equipment further includes:
Image acquisition units, for gathering the view data of the transmitting device;
Visual aids control unit, for obtaining the control signal according to described image data auxiliary.
Alternatively, the optical radar is obtained according to the optical signalling and the echo-signal by flight time ToF
The range data.
It will be understood by those skilled in the art that in the above method of the application embodiment, the sequence number of each step
Size is not meant to the priority of execution sequence, and the execution sequence of each step should be determined with its function and internal logic, without answering
Any restriction is formed to the implementation process of the application embodiment.
Those of ordinary skill in the art may realize that each exemplary list described with reference to the embodiments described herein
Member and method and step, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical solution.Professional technician
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
Scope of the present application.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, the technical solution of the application is substantially in other words
The part to contribute to original technology or the part of the technical solution can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server, or network equipment etc.) perform each embodiment the method for the application all or part of step.
Embodiment of above is merely to illustrate the present invention, and not limitation of the present invention, in relation to the common of technical field
Technical staff, without departing from the spirit and scope of the present invention, can also make a variety of changes and modification, therefore all
Equivalent technical solution falls within scope of the invention, and scope of patent protection of the invention should be defined by the claims.
Claims (10)
- A kind of 1. transmitting device control method, it is characterised in that the described method includes:The one or more optical radars of control are sending optical signalling from multiple directions to transmitting device at different moments;Receive the echo-signal of the optical signalling;Obtained and the relevant multiple range data of material on the transmitting device according to the echo-signal;The multiple range data is integrated to the transmitting device output control signal.
- 2. according to the method described in claim 1, it is characterized in that, described obtained according to the echo-signal fills with the transmission Putting the relevant multiple range data of material includes:Determine that echo position is to the first distance of the optical radar in this direction according to the echo-signal in each direction Information;By first range information compared with reference range information, with obtain in this direction the echo position to the transmission The second distance information of apparatus surface.
- 3. according to the method described in claim 1, it is characterized in that, the multiple range data of the synthesis is filled to the transmission Putting output control signal includes:The training pattern that the input of the multiple range data is obtained via machine learning;The training pattern obtains and the most matched control signal of the multiple range data according to history training program;The described and most matched control signal of the multiple range data is exported to the transmitting device.
- 4. according to the method described in claim 3, it is characterized in that, the method further includes:Receive the transmitting device and perform the feedback information after the control signal;Further machine learning is carried out using the feedback information, to correct the training pattern.
- 5. according to the described method of any one of claim 1-4, it is characterised in that the transmitting device fills for multistage transmission Put, in the method:The optical signalling is to be sent to one or more higher level's transmitting devices;The control signal is to be exported to one or more subordinate's transmitting devices.
- 6. according to the method described in claim 5, it is characterized in that, the method further includes:One or more of subordinate's transmitting devices realize that following current starts according to the control signal.
- 7. according to the method described in claim 1, it is characterized in that, the method further includes:Gather the view data of the transmitting device;The control signal is obtained according to described image data auxiliary.
- 8. a kind of transmitting device control device, it is characterised in that the equipment includes:Radar control unit, for controlling one or more optical radars being sent at different moments from multiple directions to transmitting device Optical signalling;Echo receiving unit, for receiving the echo-signal of the optical signalling;Distance acquiring unit, it is relevant multiple apart from number with material on the transmitting device for being obtained according to the echo-signal According to;Output unit is controlled, for integrating the multiple range data to the transmitting device output control signal.
- 9. equipment according to claim 8, it is characterised in that the distance acquiring unit includes:Echo is apart from determining module, for determining that echo position is to institute in this direction according to the echo-signal in each direction State the first range information of optical radar;Surface distance determining module, for by first range information compared with reference range information, to obtain in this direction Second distance information of the echo position to the transmitting device surface.
- 10. equipment according to claim 8, it is characterised in that the control output unit includes:Data input module, for the training pattern for obtaining the input of the multiple range data via machine learning;Auto-matching module, for making the training pattern be obtained according to history training program with the multiple range data most The control signal matched somebody with somebody;Signal output module, the described and most matched control signal of the multiple range data is exported to the transmitting device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711106788.4A CN107942659B (en) | 2017-11-10 | 2017-11-10 | Transmission device control method and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711106788.4A CN107942659B (en) | 2017-11-10 | 2017-11-10 | Transmission device control method and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107942659A true CN107942659A (en) | 2018-04-20 |
CN107942659B CN107942659B (en) | 2024-05-14 |
Family
ID=61934823
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711106788.4A Active CN107942659B (en) | 2017-11-10 | 2017-11-10 | Transmission device control method and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107942659B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2199236A2 (en) * | 2008-12-16 | 2010-06-23 | BEA Elektrotechnik und Automation Technische Dienste Lausitz GmbH | Positioning device for conveyer belt assemblies |
WO2011150131A1 (en) * | 2010-05-26 | 2011-12-01 | Amazon Technologies, Inc. | System and method for process management in a materials handling facility |
CN105022273A (en) * | 2015-07-25 | 2015-11-04 | 南通大学 | Multistage belt conveyer coordination control system based on internet of things and method |
CN106352951A (en) * | 2016-09-29 | 2017-01-25 | 上海沃纳机电设备有限公司 | Multi-frequency radar level gauge and material level measuring method based on same |
CN206095359U (en) * | 2016-09-29 | 2017-04-12 | 上海沃纳机电设备有限公司 | Multi -frequency radar charge level indicator |
CN106597425A (en) * | 2016-11-18 | 2017-04-26 | 中国空间技术研究院 | Radar object positioning method based on machine learning |
CN106702060A (en) * | 2016-12-01 | 2017-05-24 | 北京科技大学 | Blast furnace material flowing track measuring device and method based on radar |
-
2017
- 2017-11-10 CN CN201711106788.4A patent/CN107942659B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2199236A2 (en) * | 2008-12-16 | 2010-06-23 | BEA Elektrotechnik und Automation Technische Dienste Lausitz GmbH | Positioning device for conveyer belt assemblies |
WO2011150131A1 (en) * | 2010-05-26 | 2011-12-01 | Amazon Technologies, Inc. | System and method for process management in a materials handling facility |
CN105022273A (en) * | 2015-07-25 | 2015-11-04 | 南通大学 | Multistage belt conveyer coordination control system based on internet of things and method |
CN106352951A (en) * | 2016-09-29 | 2017-01-25 | 上海沃纳机电设备有限公司 | Multi-frequency radar level gauge and material level measuring method based on same |
CN206095359U (en) * | 2016-09-29 | 2017-04-12 | 上海沃纳机电设备有限公司 | Multi -frequency radar charge level indicator |
CN106597425A (en) * | 2016-11-18 | 2017-04-26 | 中国空间技术研究院 | Radar object positioning method based on machine learning |
CN106702060A (en) * | 2016-12-01 | 2017-05-24 | 北京科技大学 | Blast furnace material flowing track measuring device and method based on radar |
Non-Patent Citations (2)
Title |
---|
张晓芳;: "基于机器学习的激光雷达目标自动检测方法研究", 激光杂志, no. 10 * |
马远;魏萌;徐科军;: "基于反向回波的导波雷达物位计信号处理方法", 化工自动化及仪表, no. 12 * |
Also Published As
Publication number | Publication date |
---|---|
CN107942659B (en) | 2024-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9454907B2 (en) | System and method for placement of sensors through use of unmanned aerial vehicles | |
CN105022273B (en) | A kind of multilevel belt type conveyer control method for coordinating based on Internet of Things | |
CN104089960A (en) | Device and method for detecting defects on surface of conical bearing roller | |
CN206281972U (en) | Maritime radar monitoring system | |
CN106382869B (en) | The control method of on-site mixed explosive Work robot | |
CN102968133B (en) | Feed supplement control method, device and system | |
CN204421832U (en) | Based on the belt material measuring system of laser ranging | |
CN108287548A (en) | A kind of automation guide rail toter and the robot collaboration means of delivery and system | |
CN203772403U (en) | Belt weigher measurement monitoring system | |
CN110381253A (en) | A kind of control method of quality testing, apparatus and system | |
CN107942659A (en) | Transmitting device control method and equipment | |
CN105466534A (en) | Logistic freight automatic calculating device and calculating method thereof | |
CN110428347A (en) | A kind of high-building construction matches feeding system and method with intelligent-tracking | |
CN208555097U (en) | A kind of workpiece shapes based on computer vision detection and sorting device | |
CN207397012U (en) | Control system with optical radar | |
CN110000844A (en) | A kind of material receiving desk method for sorting, system and automatic cutting bed equipment | |
CN106779246A (en) | A kind of useful load of coal is calculated and distribution method and device | |
CN107024821A (en) | The method and lighting device of a kind of lighting device capturing information | |
CN114545833B (en) | Intelligent interactive processing system of facility agriculture based on internet of things | |
CN205139366U (en) | Material flows detection device | |
CN115540755B (en) | Automatic workstation for rapidly detecting workpiece size, measuring system and method | |
CN105107748B (en) | A kind of candling apparatus | |
CN205008248U (en) | Equipment is examined to lamp | |
CN110989382A (en) | Multifunctional cloud service home robot | |
CN109230356B (en) | Material blocking monitoring alarm system and monitoring method for horizontal line production equipment |
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 |