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
- transmission device
- distance
- signal
- control signal
- echo
- 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 48
- 230000003287 optical effect Effects 0.000 claims abstract description 76
- 239000000463 material Substances 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 32
- 230000005540 biological transmission Effects 0.000 claims description 106
- 230000002194 synthesizing effect Effects 0.000 claims description 7
- 230000011664 signaling Effects 0.000 abstract 2
- 239000003245 coal Substances 0.000 description 16
- 238000013528 artificial neural network Methods 0.000 description 12
- 238000013527 convolutional neural network Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012417 linear regression Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000003068 static effect 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
- 238000005303 weighing Methods 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 present application relates to the field of automatic control technologies, and in particular, to a method and an apparatus for controlling a transmission device.
Background
In the field of material conveying, conveying materials to a designated position through a conveying belt and the like is the most basic and urgent requirement. On the one hand, however, the transmission system is required to consume a large amount of energy when operating; on the other hand, the material is often conveyed according to the needs, the needs have strong irregularity, and the intermittent condition is common; that is, the conventional transmission system often causes a large amount of energy consumption due to the idling of the system, and the efficiency is extremely low.
In order to avoid a series of problems caused by idling, some schemes for intelligently controlling the running speed of the belt appear in the prior art, for example, an infrared light curtain is installed at a feed inlet of a storage bin, and the starting and the stopping of a main belt are controlled according to a signal for identifying materials by the infrared light curtain; or identifying the material according to the image/video collected by the camera, and further controlling the starting and stopping of the main belt; and the laser radar is used for measuring the material volume at the feeding moment, based on an accurate shape model of the conveyor belt, the laser radar is used for ranging under the model, and the material volume is calculated according to the difference value between the measured value and the model, so that the instantaneous measurement of the material volume is realized.
However, the inventor finds that the prior art has obvious defects in the process of implementing the invention. The infrared light curtain can only identify whether a material cutting light curtain exists at a receiving end, and the parameters such as the running speed, the power and the like of the transmission device cannot be accurately controlled. The image/video analysis technology has higher requirements on the field environment, but the underground environment of the coal mine is more complex, for example, a large amount of dust and water mist exist in the coal production process, so that the image/video is blurred and unclear, and the analysis accuracy is influenced. The laser radar ranging based on the conveyor belt model is seriously dependent on the accuracy of the model, has very limited applicability and flexibility, and cannot be popularized and applied on a large scale.
Therefore, the material conveying device in the prior art cannot be reasonably, accurately and efficiently controlled, and the condition of energy waste is common and difficult to control.
Disclosure of Invention
In view of the foregoing drawbacks of the prior art, embodiments of the present application provide a transmission apparatus control scheme capable of being adaptive.
In one possible embodiment, there is provided a transmission apparatus control method, the method including:
controlling one or more optical radars to transmit optical signals to a transmission device from multiple directions at different times;
receiving an echo signal of the optical signal;
obtaining a plurality of distance data related to the material on the transmission device according to the echo signal;
and synthesizing the plurality of distance data to output a control signal to the transmission device.
Optionally, the obtaining a plurality of distance data related to the material on the transmission device according to the echo signal includes:
determining first distance information from the echo position to the optical radar in each direction according to the echo signal in the direction;
and comparing the first distance information with reference distance information to obtain second distance information of the echo position to the surface of the transmission device in the direction.
Optionally, the reference distance information is preset information or is measured in advance by the optical radar.
Optionally, the synthesizing the plurality of distance data to output the control signal to the transmission device includes:
inputting the plurality of distance data into a training model obtained via machine learning;
the training model obtains a control signal which is most matched with the plurality of distance data according to a historical training item;
and outputting the control signal which is most matched with the plurality of distance data to the transmission device.
Optionally, the method further comprises:
receiving feedback information after the transmission device executes the control signal;
further machine learning is performed using the feedback information to modify the training model.
Optionally, the machine learning is performed using one or more of an artificial neural network, a convolutional neural network, and a deep neural network.
Optionally, the transmission apparatus is a multi-stage transmission apparatus, and in the method:
the optical signals are sent to one or more superior transmission devices;
the control signal is output to one or more subordinate transmission devices.
Optionally, the method further comprises:
and the one or more lower transmission devices realize downstream starting according to the control signal.
Optionally, the method further comprises:
acquiring image data of the transmission device;
and obtaining the control signal in an auxiliary manner according to the image data.
Optionally, the optical radar obtains the distance data by a time-of-flight ToF from the optical signal and the echo signal.
In another possible embodiment, there is also provided a transmission device control apparatus including:
a radar control unit for controlling one or more optical radars to transmit optical signals to the transmission device from multiple directions at different times;
an echo receiving unit for receiving an echo signal of the optical signal;
the distance acquisition unit is used for acquiring a plurality of distance data related to the material on the transmission device according to the echo signal;
and the control output unit is used for synthesizing the plurality of distance data and outputting a control signal to the transmission device.
Optionally, the distance obtaining unit includes:
the echo distance determining module is used for determining first distance information from the echo position to the optical radar in each direction according to the echo signal in the direction;
and the surface distance determining module is used for comparing the first distance information with reference distance information to obtain second distance information from the echo position to the surface of the transmission device in the direction.
Optionally, the reference distance information is preset information or is measured in advance by the optical radar.
Optionally, the control output unit includes:
a data input module to input the plurality of distance data into a training model obtained via machine learning;
the automatic matching module is used for enabling the training model to obtain a control signal which is most matched with the plurality of distance data according to a historical training item;
and the signal output module outputs the control signal which is most matched with the plurality of distance data to the transmission device.
Optionally, the apparatus further comprises:
a feedback receiving unit, configured to receive feedback information after the transmission apparatus executes the control signal;
a learning correction unit for performing further machine learning using the feedback information to correct the training model.
Optionally, the machine learning is performed using one or more of an artificial neural network, a convolutional neural network, and a deep neural network.
Optionally, the transmission device is a multi-stage transmission device, and in the apparatus:
the radar control unit is also used for sending the optical signals to one or more superior transmission devices;
the control output unit is further used for outputting the control signal to one or more lower transmission devices.
Optionally, the apparatus further comprises:
and the downstream starting unit is used for enabling the one or more lower-level transmission devices to realize downstream starting according to the control signal.
Optionally, the apparatus further comprises:
the image acquisition unit is used for acquiring the image data of the transmission device;
and the image auxiliary control unit is used for assisting in obtaining the control signal according to the image data.
Optionally, the optical radar obtains the distance data by a time-of-flight ToF from the optical signal and the echo signal.
The embodiment of the application provides a control method and equipment for a transmission device, distance data in multiple directions are obtained through an optical radar, and a training model obtained through machine learning is used for automatically obtaining a control signal matched with the distance data, so that more accurate and efficient control can be achieved. In addition, the scheme of the embodiment of the application can be quickly and automatically adapted to various different devices and environments, and the flexibility and the applicability of the scheme are far higher than those of the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application.
FIG. 1 is a schematic diagram of a control system with an optical radar in one embodiment of the present application;
fig. 2 is a schematic flow chart illustrating a control method of a transmission apparatus according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a convolutional neural network for machine learning in an embodiment of the present application;
fig. 4 is a schematic block diagram of a control apparatus of a transmission device according to an embodiment of the present application.
Detailed Description
In order to make the objects, features and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood by those within the art that the terms "first", "second", etc. in this application are used only to distinguish one device, module, parameter, etc., from another, and do not denote any particular technical meaning or necessary order therebetween.
The core of the material transmission control problem lies in how to accurately control the starting and stopping of the transmission device, so that the running speed of the transmission device is matched with the feeding amount, and the energy consumption caused by idling is avoided. In the prior art, the detection of the material is realized through an infrared light curtain, a camera or a laser radar, and the like, but the volume of the material is generally difficult to accurately measure by the existing scheme, and particularly the measurement cannot be carried out in a self-adaptive manner aiming at the environment with complex change. In the embodiment of the application, comprehensive detection is carried out through the optical radar, and the training model obtained by machine learning is utilized to generate the control signal, so that the measurement and transmission control of the material can be more accurate and efficient, and the device can be automatically adapted to various different devices and environments.
In a typical application scenario of the present application, as shown in fig. 1, the material detection and the control of the conveying device are performed by a control system with optical radar, so that the dynamic control of the operation of the conveying device according to the material feeding condition is realized. In fig. 1, a control system of a transmission apparatus includes: the transmission device 10, the optical radar 20, the radar control unit 30, and the transmission control unit 40; the conveying device 10 comprises a material bearing part 11 and a driving motor 12, wherein the driving motor 12 drives the material bearing part 11 to move towards a specified direction through a mechanical transmission part; the optical radar 20 comprises an optical signal transmitting part 21 and an echo signal receiving part 22, the optical radar 20 is coupled to a radar control unit 30, the optical radar 20 periodically or randomly adjusts the signal transmitting and receiving angles of the optical signal transmitting part 21 and the echo signal receiving part 22 according to a radar control signal provided by the radar control unit 30, and the optical radar 20 simultaneously feeds back signal transmitting and receiving data to the radar control unit 30; the radar control unit 30 is further coupled to a transmission control unit 30, which is provided with range data represented by the signal transmission and reception data; the transmission control unit 30 is coupled to the driving motor 12 of the transmission device 10, and outputs a matched motor control signal to the driving motor 12 according to the distance data.
In the embodiment of the application, distance data in a plurality of directions are obtained through an optical radar, and a training model obtained through machine learning is used for automatically acquiring a control signal matched with the distance data, so that more accurate and efficient control can be realized.
In the embodiment of the present application, the optical radar performs ranging by TOF (Time of Flight) by transmitting an optical signal and receiving an echo signal generated by the optical signal on a reflection surface. The optical radar in the present application includes optical radars using optical signals of different wavelength bands (including visible light and/or invisible light, etc.). Further, with the progress of electronic devices, the cost of the laser radar technology is gradually reduced, so that the application field thereof is wider and wider. Since lidar has certain advantages in terms of cost, accuracy, reliability and interference rejection, in a preferred embodiment of the present application the optical radar comprises single and/or multi-line lidar.
In the embodiments of the present application, the conveying device is not limited to the conveyor belt, but includes other forms of conveying devices such as a scraper, a screw conveyor, and the like. The conveying device of the present invention is not limited to a single conveying member, and may include a conveying system in which a plurality of conveying members are combined, such as a multi-stage conveyor system, or a combination of a conveyor and another conveying device.
Referring to fig. 2, in an embodiment of the present application, based on the above control system with an optical radar, there is also provided a transmission device control method, including:
and S1, controlling one or more optical radars to send optical signals to the transmission device from multiple directions at different times.
Wherein the optical signals are sent from multiple directions in order to obtain distance data that is as comprehensive as possible, so that the material volume at a certain moment is known more accurately, so that an accurate control is achieved. The optical signals are sent at different moments so as to grasp the material feeding condition in real time and dynamically adjust the material feeding condition. Optionally, the transmitting at different time instants includes transmitting periodically and/or transmitting at random time instants.
And S2, receiving an echo signal of the optical signal.
For each optical signal, when the optical signal is projected to the surface of the material, an echo signal is formed due to reflection, and by receiving the echo signal, the propagation condition of the corresponding optical signal under the current environment can be known.
And S3, obtaining a plurality of distance data related to the materials on the transmission device according to the echo signals.
As described above, the optical radar mainly measures the distance by the time of flight TOF, and more specifically, the transmission distance of light can be calculated by using the transmission speed of light and the transmission/reception time difference between the optical signal and the echo signal in a certain direction, so as to obtain the distance from the optical signal transmitting unit (i.e., the optical radar) to the echo position (or the distance from the echo position to the optical radar echo signal receiving unit) in the certain direction.
And S4, synthesizing the distance data and outputting a control signal to the transmission device.
Typically, the calculation of the volume of the material is performed in dependence on the distance of the echo position from the optical radar in a plurality of directions, whereby the transport speed of the transport device is controlled in dependence on the size of the volume of the material. Of course, in alternative embodiments of the present application, the calculation of the volume of the material and/or the generation of the control signal do not depend on a formula and a real-time operation, and may be performed more intelligently and efficiently by a method such as machine learning, and here, the specific method of obtaining the control signal from the distance data should not be considered as a limitation to the embodiments of the present application.
In one embodiment of the application, the thickness of the material in the direction is obtained by comparing the echo distance with a reference distance. Specifically, first distance information from the echo position to the optical radar in each direction is determined according to the echo signal in the direction; and comparing the first distance information with reference distance information to obtain second distance information of the echo position to the surface of the transmission device in the direction. Optionally, the reference distance information is preset information or is measured in advance by the optical radar.
In one embodiment of the present application, taking a coal transmission device with a laser radar as an example, one laser radar transmits an optical signal to one transmission device, such as a conveyor belt, and receives an echo signal, and based on the echo signal, distance information in one direction can be obtained. By transmitting optical signals at different times and using different transmission angles and receiving corresponding echo signals, the laser radar can obtain a plurality of distance information at different times and in different directions. The distance information is recorded by laserAs a reference point, the distance between the echo position and the surface of the transmitting device in a certain direction can be indirectly represented. Note that since the lidar transmits a signal with a certain directivity, the distance information is not equal to the height of the coal on the surface of the transmission device, but is a distance information related to the position of the lidar. Order toExpressed as the distance in the ith time point and the jth direction, a set of distance data sets in different time and different directions can be expressed as:
the distance data set d is fed to a control unit and the control signals for the transmission device are derived:
p＝(d)；
where p is a control signal of a transmitting device. In one embodiment, p is a speed control signal that is coupled to a frequency converter to control the transmission speed of the transmission device. In addition, p may be an indirect control signal, which is input to the control device of the next stage, and the control device of the next stage finally controls the conveying speed of the conveying device. In one embodiment, p is a continuous variable and can take any value within a certain range. In one embodiment, p is a discrete variable that takes on one of a plurality of predetermined values.
There are various ways to implement the control function f (), for example, by a predetermined linear combination formula. And carrying out weighted average on a plurality of variables in d to obtain a p value, wherein the weight value of the weighted average needs accurate training and testing so as to increase the obtained p to be matched with the required conveyor belt speed. In another embodiment, the corresponding f () may also be obtained using a non-linear processing method. Since there are an infinite number of methods of f (), they are not listed here. In another embodiment, the distance information is processed using a machine learning method to obtain a specific control function f (). The machine learning method is to train a first control model through training data, and then obtain a usable control model. The machine learning method comprises different methods such as linear regression, nonlinear regression, K-Means, decision trees, random forests, artificial neural networks, convolutional neural networks or deep neural networks. In one embodiment, linear regression may be used to derive the continuous control signal p. Specifically, the output value of the control signal is obtained by weighted averaging the distance information at different times and different angles by using a linear method, for example:
wherein,distance weight in the jth direction expressed as the ith time point; the final weight of the linear regression can be obtained by using the labeled data and the corresponding distance data set and using the corresponding training methodBy means of the model, the actual operating data can be processed using the following formula, resulting in a control signal for each transport:
in an alternative embodiment, the distance data set may be processed using a convolutional neural network to obtain discrete control signals. As shown in fig. 3, the method takes the distance data set as an input, inputs the distance data set into a convolutional neural network with multiple layers, and finally obtains a single and discrete control signal. By using the labeled training data, for example, using the distance data set information labeled with the optimal control signal, the neural network can obtain a final neural network weight under the training of a large amount of data. Subsequently, a discrete control signal is obtained by inputting the data set acquired during operation into the neural network. Due to the use of the convolutional neural network, the discrete control signal can be arbitrarily set, for example, the control signal can be divided into 3 levels, each of which represents 3 different speeds. In addition, the control signal may be divided into 5 levels, each representing 5 different speeds. The setting of the control signal is not limited by any control model, and only the corresponding marking information needs to be modified.
The method using machine learning avoids the limitation of the transmission device by always obtaining an output of a control signal based on only the distance data set. The machine learning process can accurately control the speed of any form of transport device without prior knowledge of the transport device specific information, such as the surface geometry of the transport device, as long as sufficient data is available. In addition, the specific angle of each distance information does not need to be considered by using a machine learning method, and the formats and the collection modes of the training data and the actual operation data are kept uniform.
From the above description, the adaptability of the system is greatly improved by using the machine learning method, so that the method can be rapidly deployed in any transmission device, any laser radar setting mode and any control signal level system.
In yet another alternative embodiment, the method of machine learning uses a set of reference distances. The reference distance information corresponds to a distance data set in the idle state. The acquisition mode can be obtained in a pre-stored mode or in an actual acquisition mode on an operating transmission device. For example, a plurality of distance data records obtained by the lidar are recorded in the case of an empty transmission device. Through processing, a reference distance data set is obtained. For another example, the controller processes the data of the plurality of distance data sets, determines that the current transmission device is in the idle state, and processes the plurality of data sets to obtain a reference distance data set. The reference distance data set reflects distance information in an unloaded state, which can be input as input into training data for training the machine learning control model. In actual operation, the data is also input into the control model as input to obtain specific control signals.
For example, a set of reference distances may be:
thus, the distance data set used in the actual operation of the trained distance data set can take the reference distance set as input, that is, the new distance data set becomes:
the machine learning method used is not changed, but only the final model is different.
In an alternative embodiment, an additional image sensor may be used in addition to the lidar to further improve the robustness of the control system. For example, one image sensor obtains a set of image data:
in this case, the data of the image sensor and the data of the laser radar may be simultaneously input as input to the algorithm of the machine learning. That is, the machine-learned data is a data set of b and d. In one embodiment, the image sensor is a depth sensor, that is, the sensor can obtain information about the distance between the sensor and the image sensor in different directions of the acquisition area through processing of the image signal. For example,
q＝l(b)；
l () is a depth extraction algorithm that obtains depth information q by processing image data b. At this time, the machine-learned data becomes a data set of b and q.
In an alternative embodiment, the coal transfer system comprises a plurality of levels, with a plurality of transfer devices of an upper level transferring coal to a transfer device of a lower level. For example, multiple conveyors transfer coal from a pit onto a main conveyor. In this case, the next-stage conveying device is loaded with coal conveyed by a plurality of previous-stage conveying devices, and therefore, more energy is consumed. Therefore, the intelligent energy-saving control of the next-stage transmission device, such as the main conveyor belt, can bring more energy conservation.
In an alternative embodiment, the lidar transmits an optical signal to the upper transmission device, receives an echo signal, and obtains range information in multiple directions at multiple points in time. The plurality of data signals are input into a controller, and the controller uses one of the machine learning methods to further obtain a control signal of the next-stage transmission device. For example:
difor the distance data set of the ith upper transmission device, inputting a plurality of distance data sets into the machine learning method, such as a linear regression or convolutional neural network method, the control signal of the next transmission device can be obtained:
pmain＝f(d1,d2,…,dI)。
based on the method, the next-stage transmission device can realize intelligent energy-saving control through data collected by the laser radars arranged on the plurality of previous-stage transmission devices.
In an optional embodiment, in the actual production of a coal mine, in order to ensure the safety of personnel and equipment, the coal mine basically adopts a reverse coal flow starting mode to start the equipment in a belt conveyor starting mode, the so-called reverse coal flow starting mode is a starting mode from an unloading point to a loading point step by step, a plurality of belt conveyors are overlapped in the whole starting process, so that the belt conveyors overlapped in the middle of the whole belt conveyor system are in an idle state when the reverse coal flow is finished, in a coal flow starting mode changed by the conventional belt scale measuring technology, as the belt scales belong to contact weighing equipment, when a connecting port at the connecting position of the belt conveyor and the belt of the belt conveyor runs at a high speed and passes through the belt scales, the non-contact condition between the belt conveyor and the belt scales can be caused, the misjudgment of a control system can be caused, the control error of the control system can be caused, and the distance of materials can be measured from the surface of the belt conveyor by using the laser radar-based measuring technology, the situation of belt weigher misinformation is solved. And the operation of starting the vehicle along the coal flow can be further achieved, the process of starting the vehicle along the coal flow from a belt loading point to an unloading point step by step is adopted, and the idling of the belt conveyors at the upper and lower levels in the whole belt conveyor transportation system can be avoided in the process of starting the vehicle. That is, by controlling the above-mentioned control signal pmainThe desired down-flow start-up mode described above can be implemented such that the tape at each stage is only operational when necessary. Similarly, f () can be obtained using a predefined formula, for example, by weighted averaging the distance information of all superordinate conveyor belts to obtain pmainA signal. The weighted average weight value is adjusted and simulated in advance to ensure that p ismainThe output of the signal can realize the requirement of coal-flowing starting. I.e. when the upper conveyor belt is empty of material, pmainAnd outputting a lower-level conveyor belt static control signal. In another embodiment, a more adaptive control model can be obtained by training the control model using a machine learning method. Entire model through neural network and training dataThe method is realized, and the calculation and teaching of the weight value are avoided. The method can more accurately meet the requirement of coal-following flow starting, and is suitable for various different conveyor belt scenes and different multistage conveyor belt configurations.
As further shown in fig. 4, corresponding to the method in the foregoing embodiment, an embodiment of the present application also provides a transmission device control apparatus 400, including:
a radar control unit 410 for controlling one or more optical radars to transmit optical signals from multiple directions to the transmission device at different times;
an echo receiving unit 420 for receiving an echo signal of the optical signal;
a distance obtaining unit 430, configured to obtain a plurality of distance data related to the material on the transmission device according to the echo signal;
a control output unit 440 for outputting a control signal to the transmission device by integrating the plurality of distance data.
Optionally, the distance obtaining unit includes:
the echo distance determining module is used for determining first distance information from the echo position to the optical radar in each direction according to the echo signal in the direction;
and the surface distance determining module is used for comparing the first distance information with reference distance information to obtain second distance information from the echo position to the surface of the transmission device in the direction.
Optionally, the reference distance information is preset information or is measured in advance by the optical radar.
Optionally, the control output unit includes:
a data input module to input the plurality of distance data into a training model obtained via machine learning;
the automatic matching module is used for enabling the training model to obtain a control signal which is most matched with the plurality of distance data according to a historical training item;
and the signal output module outputs the control signal which is most matched with the plurality of distance data to the transmission device.
Optionally, the apparatus further comprises:
a feedback receiving unit, configured to receive feedback information after the transmission apparatus executes the control signal;
a learning correction unit for performing further machine learning using the feedback information to correct the training model.
Optionally, the machine learning is performed using one or more of an artificial neural network, a convolutional neural network, and a deep neural network.
Optionally, the transmission device is a multi-stage transmission device, and in the apparatus:
the radar control unit is also used for sending the optical signals to one or more superior transmission devices;
the control output unit is further used for outputting the control signal to one or more lower transmission devices.
Optionally, the apparatus further comprises:
and the downstream starting unit is used for enabling the one or more lower-level transmission devices to realize downstream starting according to the control signal.
Optionally, the apparatus further comprises:
the image acquisition unit is used for acquiring the image data of the transmission device;
and the image auxiliary control unit is used for assisting in obtaining the control signal according to the image data.
Optionally, the optical radar obtains the distance data by a time-of-flight ToF from the optical signal and the echo signal.
It is understood by those skilled in the art that, in the method according to the embodiments of the present application, the sequence numbers of the steps do not mean the execution sequence, and the execution sequence of the steps should be determined by their functions and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The functions, if implemented in the form of software functional units 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 application or portions thereof that substantially contribute to the prior art may be embodied 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, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application.
The above embodiments are only for illustrating the invention and are not to be construed as limiting the invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention, therefore, all equivalent technical solutions also belong to the scope of the invention, and the scope of the invention is defined by the claims.
Claims (10)
1. A transmission apparatus control method, characterized in that the method comprises:
controlling one or more optical radars to transmit optical signals to a transmission device from multiple directions at different times;
receiving an echo signal of the optical signal;
obtaining a plurality of distance data related to the material on the transmission device according to the echo signal;
and synthesizing the plurality of distance data to output a control signal to the transmission device.
2. The method of claim 1, wherein obtaining a plurality of range data related to the material on the conveyor from the echo signal comprises:
determining first distance information from the echo position to the optical radar in each direction according to the echo signal in the direction;
and comparing the first distance information with reference distance information to obtain second distance information of the echo position to the surface of the transmission device in the direction.
3. The method of claim 1, wherein said synthesizing said plurality of range data to output a control signal to said transmitting device comprises:
inputting the plurality of distance data into a training model obtained via machine learning;
the training model obtains a control signal which is most matched with the plurality of distance data according to a historical training item;
and outputting the control signal which is most matched with the plurality of distance data to the transmission device.
4. The method of claim 3, further comprising:
receiving feedback information after the transmission device executes the control signal;
further machine learning is performed using the feedback information to modify the training model.
5. Method according to any of claims 1-4, wherein the transmission device is a multi-stage transmission device, and wherein:
the optical signals are sent to one or more superior transmission devices;
the control signal is output to one or more subordinate transmission devices.
6. The method of claim 5, further comprising:
and the one or more lower transmission devices realize downstream starting according to the control signal.
7. The method of claim 1, further comprising:
acquiring image data of the transmission device;
and obtaining the control signal in an auxiliary manner according to the image data.
8. A transmission device control apparatus, characterized in that the apparatus comprises:
a radar control unit for controlling one or more optical radars to transmit optical signals to the transmission device from multiple directions at different times;
an echo receiving unit for receiving an echo signal of the optical signal;
the distance acquisition unit is used for acquiring a plurality of distance data related to the material on the transmission device according to the echo signal;
and the control output unit is used for synthesizing the plurality of distance data and outputting a control signal to the transmission device.
9. The apparatus according to claim 8, wherein the distance acquisition unit includes:
the echo distance determining module is used for determining first distance information from the echo position to the optical radar in each direction according to the echo signal in the direction;
and the surface distance determining module is used for comparing the first distance information with reference distance information to obtain second distance information from the echo position to the surface of the transmission device in the direction.
10. The apparatus of claim 8, wherein the control output unit comprises:
a data input module to input the plurality of distance data into a training model obtained via machine learning;
the automatic matching module is used for enabling the training model to obtain a control signal which is most matched with the plurality of distance data according to a historical training item;
and the signal output module outputs the control signal which is most matched with the plurality of distance data to the transmission 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 |
|---|---|---|
| US10376926B2 (en) | Inspection and sorting system | |
| CN106842918B (en) | A kind of calculation method of the real-time coal amount of drag conveyor | |
| CN104648970B (en) | Proportioning control method and system | |
| CN110104408B (en) | Method and system for tracking and controlling material flow on belt conveyor | |
| CN114803382B (en) | Conveying control method, system, device, conveyor equipment and readable storage medium | |
| US11971704B2 (en) | Zone drive of transducers for extended linearity | |
| CN106829393A (en) | Ribbon conveyer automatic speed-regulating method | |
| CN109941698A (en) | A kind of belt conveyor speed adjusting method considering fatigue rupture | |
| CN109761015A (en) | A kind of main transporting equipment autocontrol method based on shaft production coal amount | |
| CN107942659A (en) | Transmitting device control method and equipment | |
| CN207397012U (en) | Control system with optical radar | |
| CN109532118A (en) | Splicing control method, device and production management system | |
| CN106452429A (en) | Method and system for calculating stock volume of storage cabinet based on virtual pulses | |
| JP7178659B2 (en) | Weighing machine learning device, weighing machine learning system and weighing system | |
| CN117330145A (en) | Material flow detection method, device, system and storage medium | |
| CN109230356B (en) | Material blocking monitoring alarm system and monitoring method for horizontal line production equipment | |
| CN102937476A (en) | Online coating weight monitoring method | |
| CN206422727U (en) | Tyre surface severing governing system | |
| CN105425825A (en) | Dynamic plasterboard tracking device and dynamic plasterboard tracking method | |
| CN117053727B (en) | Scanning detection device for accumulating volume of outer surface of material by ranging method | |
| JPH09205295A (en) | Substrate carrying method and device | |
| CN116500609B (en) | Composite microwave radar measurement system for detecting blanking state and material level fluctuation state | |
| RU2802263C1 (en) | Energy efficient control of the device for continuous material transportation | |
| CN116674957B (en) | Optimization method and system for coal conveying belt drive | |
| JPH09235014A (en) | Carrier controller |
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 |