CN113627283A - Material level measuring method based on radar echo signals, terminal equipment and storage medium - Google Patents
Material level measuring method based on radar echo signals, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN113627283A CN113627283A CN202110838714.XA CN202110838714A CN113627283A CN 113627283 A CN113627283 A CN 113627283A CN 202110838714 A CN202110838714 A CN 202110838714A CN 113627283 A CN113627283 A CN 113627283A
- Authority
- CN
- China
- Prior art keywords
- radar
- charge level
- denseblock
- dimensional matrix
- matrix array
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 239000000463 material Substances 0.000 title claims description 8
- 238000005259 measurement Methods 0.000 claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims abstract description 25
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 17
- 238000011176 pooling Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention relates to a charge level measuring method based on radar echo signals, terminal equipment and a storage medium, wherein the method comprises the following steps: s1: respectively acquiring echo curve data corresponding to each measuring position on a radius of the burden surface aiming at different burden surfaces in the blast furnace through a millimeter wave radar, and recording the height of each measuring position on the radius of the burden surface from the horizontal plane where the radar rotation center is located; s2: splicing echo curve data into a two-dimensional matrix array, and forming the two-dimensional matrix array and the heights of all charge levels into a training set; s3: constructing a convolutional neural network model based on DenseNet, and training the convolutional neural network model through a training set; s4: and splicing echo curve data corresponding to the charge level to be tested, which are acquired by the millimeter wave radar, into a two-dimensional matrix array, and outputting the two-dimensional matrix array through a trained convolutional neural network model to obtain the charge level to be tested. The invention can quickly and accurately measure the charge level and solves the problem of measurement inaccuracy caused by the beam angle emitted by the single-point radar.
Description
Technical Field
The invention relates to the field of blast furnace ironmaking detection, in particular to a charge level measuring method based on radar echo signals, terminal equipment and a storage medium.
Background
For blast furnace operators, the method can know the shape of the charge level in real time to improve the distribution of air flow in the furnace and improve the utilization rate of coal gas, and has important significance in the actual control of blast furnace production. At present, various methods for measuring the charge level of a blast furnace are available at home and abroad, wherein the methods comprise single-point measurement-based material level measuring instruments, such as an ultrasonic radar, a laser radar, a millimeter wave radar and the like, and partial equipment of infrared images and phased array radars is used for multi-dimensional imaging of the charge level.
The method of single-point measurement has the main problems that the measurement range is small in dimension or low in precision, and the result needs to be processed in a curve fitting mode. In particular, for millimeter wave radar, the transmitted wave itself inevitably has a beam angle, which brings large measurement errors. And the general equipment of multi-dimensional imaging measurement mode is complicated, needs to reform transform original furnace roof equipment structure, and it is easy out of order and difficult to maintain to handle high temperature high pressure air current environment in service, is unfavorable for implementing in the actual blast furnace production.
Disclosure of Invention
In order to solve the above problems, the present invention provides a charge level measuring method based on radar echo signals, a terminal device and a storage medium.
The specific scheme is as follows:
a charge level measuring method based on radar echo signals comprises the following steps:
s1: respectively acquiring echo curve data corresponding to each measuring position on a radius of the charge level aiming at different charge levels in the blast furnace through a millimeter wave radar arranged on the top of the blast furnace, and recording the height of each measuring position on the radius of the charge level from the horizontal plane where the radar rotation center is located;
s2: splicing the echo curve data corresponding to each charge level into a two-dimensional matrix array, taking the two-dimensional matrix array corresponding to each charge level and the recorded height as a set of training data, and forming a training set by the training data corresponding to all charge levels;
s3: constructing a convolutional neural network model based on DenseNet, training the convolutional neural network model through a training set, setting the input of the model as a two-dimensional matrix array, and outputting as the recorded height;
s4: and splicing echo curve data corresponding to the charge level to be tested, which are acquired by the millimeter wave radar, into a two-dimensional matrix array, and outputting the two-dimensional matrix array through a trained convolutional neural network model to obtain the charge level to be tested.
Furthermore, the echo curve is a frequency spectrum curve obtained after the radar difference frequency signal is processed, the horizontal axis of the frequency spectrum curve represents the distance, and the vertical axis represents the echo intensity.
Furthermore, the millimeter wave radar can rotate around the axis, and the millimeter wave radar is controlled to rotate by a rotation angle smaller than the beam angle of the radar every time, so that the millimeter wave radar scans each measuring position in a radius of the charge level, and echo curve data of each measuring position is obtained.
Furthermore, the set measuring positions are the same for different material surfaces.
Furthermore, before the two-dimensional matrix array is spliced, the echo curve data are preprocessed, and invalid data in the echo curve data are removed.
Furthermore, the network structure of the convolutional neural network model sequentially comprises a convolutional layer, a first DenseBlock, a transition layer, a second DenseBlock and a regression layer; wherein:
(1) the convolutional layer uses 32 convolutional kernels of size 3 × 3;
(2) the first DenseBlock and the second DenseBlock are both expressed as:
Xi=Hi([X0,X1,…,Xi-1]),i=1,2,…,n
wherein n represents the number of preset feature map layers in the DenseBlock, and i represents the serial number of the feature map layers in the DenseBlock; x0Represents the output of the previous layer of DenseBlock; [ …]Indicating a cascade of channels, i.e. X0To Xi-1All feature outputs of the layers are combined by channel; hi(.) represents the nonlinear transformation of the cascaded feature map, which comprises 4k 1 × 1 convolutional layers and k 3 × 3 convolutional layers in sequence, where k is H representing the preset valuei(.) number of channels of feature output;
(3) the transition layer is a convolution layer and a pooling layer, wherein the convolution layer adopts 40 1 × 1 convolution kernels; the pooling layer is an average pooling of 2 × 2 windows, and the sampling interval is 2;
(4) the regression layer converts the characteristic diagram into 1-dimensional data by adopting global average pooling, and then two full-connection layers are formed;
(5) the activation functions of all the convolution layers in the network structure adopt linear rectification units, normalization is carried out before the linear rectification units, and the input of the linear rectification units is normalized to standard normal distribution with the average value of 0 and the variance of 1;
(6) the loss function of the model uses the mean square error.
Further, the first DenseBlock in the convolutional neural network model is configured to have n-3 and k-16; the second DenseBlock is configured with n 6 and k 32.
A level measurement terminal device based on radar echo signals comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the method of the embodiment of the invention.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method as described above for an embodiment of the invention.
By adopting the technical scheme, the charge level can be measured quickly and accurately, and the problem of measurement inaccuracy caused by the beam angle emitted by the single-point radar is solved.
Drawings
Fig. 1 is a flowchart illustrating a first embodiment of the present invention.
Fig. 2 is a schematic view showing the installation of the millimeter wave radar in this embodiment.
Fig. 3 is a diagram showing an echo curve in this embodiment.
Fig. 4 is a schematic diagram showing a network structure of the convolutional neural network model in this embodiment.
Fig. 5 is a schematic diagram of the DenseBlock structure in this embodiment.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures.
The invention will now be further described with reference to the accompanying drawings and detailed description.
The first embodiment is as follows:
the embodiment of the invention provides a charge level measuring method based on radar echo signals, which comprises the following steps of:
s1: through a millimeter wave radar installed on the top of the blast furnace, echo curve data corresponding to each measuring position on a radius of the charge level are respectively collected aiming at different charge levels in the blast furnace, and the height of each measuring position on the radius of the charge level from the horizontal plane where the radar rotation center is located is recorded.
In the embodiment, different material levels adopt various ore coke material levels.
The measuring range of the millimeter wave radar installed on the top of the blast furnace can cover a certain radius range of the charge level, as shown in fig. 2, the millimeter wave radar installed in the embodiment is R, the millimeter wave radar is provided with a motion mechanism and can rotate around a certain axis, so that different positions on a straight line can be scanned according to different rotation angles, the straight line set for scanning here is a radius of the charge level (the rotation angle range is theta), and the specific operation mode can be as follows: the radar is controlled to rotate from the current measuring position to the next measuring position by a small angle (smaller than the radar beam angle) every time, and echo curve data obtained by measurement of each measuring position and the included angle between the radar direction corresponding to the measuring position and the horizontal plane are recorded.
Furthermore, because the different measurement positions of the burden surface can influence the accuracy of the training result of the subsequent model, in order to improve the accuracy of the output result of the model, the different burden surfaces in the blast furnace are preferably set, and all the corresponding measurement positions are the same during the data acquisition of the echo curve. In this embodiment, the radar pointing direction and the angle of each rotation at the start of scanning and at the end of scanning in the radar scanning process are set to be constant.
As shown in fig. 3, the echo curve is a spectrum curve obtained by processing a radar difference frequency signal by Fast Fourier Transform (FFT) or the like, and the horizontal axis represents a distance in a range and the vertical axis represents echo intensity dB.
The radar transmitting antenna has a certain transmitting angle, so the wave peak section of the echo curve of the radar transmitting antenna represents the spectral intensity of the reflected signal in the spot irradiated by the transmitting signal beam on the measured target. In the radar scanning process, due to the fact that the irradiation angle and the measurement distance are different, different echo curve signals can be obtained through measurement at different angles.
S2: and splicing the echo curve data corresponding to each charge level into a two-dimensional matrix array, taking the two-dimensional matrix array corresponding to each charge level and the recorded height as a set of training data, and forming a training set by the training data corresponding to all charge levels.
Preferably, before the two-dimensional matrix array is spliced, the echo curve data is preprocessed, and invalid data in the echo curve data is eliminated, so that interference caused by noise is reduced. In the embodiment, the distance from the radar to the charge level is generally in a range of several meters to ten meters, so that an interception range is set, and data outside the interception range of the echo curve data are rejected.
And splicing the two-dimensional matrix arrays is to splice the echo curve data corresponding to different measurement positions of the charge level in sequence.
S3: and constructing a convolutional neural network model based on DenseNet, training the convolutional neural network model through a training set, setting the input of the model as a two-dimensional matrix array, and outputting as the recorded height.
When the radar rotates to measure the next measuring position by a small angle each time, most of the measured surfaces of the front and the back are repeated, namely most of echo curve data obtained by the front and the back are the same, and the echo curve data are changed by a part of different measured surfaces. Therefore, a suitable model (function) can be found, and by inputting these echo curve data with a slight change within an acceptable error, the model can extract the change characteristics from a large amount of data, and finally output the position distribution data (in this example, one-dimensional height data) of each measurement position on the charge level (in this example, the throat radius charge level).
Based on the principle, the convolutional neural network model is adopted in the embodiment, is a simplified network structure designed based on a DenseNet network, and is characterized in that the dense connection of all the layers in the front and the layers behind is established, so that the multiplexing of the characteristics on the channel dimension is realized, the phenomenon of gradient disappearance is relieved, and the performance of the convolutional neural network model is better than that of a general deep network under the condition of less parameters and calculated amount. The network structure is shown in fig. 4, wherein the parameter configuration details of different layers are shown in table 1, and it is assumed that the input two-dimensional array size is 256 × 60. The convolutional neural network model comprises a convolutional layer, a transition layer, a regression layer and two DenseBlock structures. Various parts and associated details are briefly described below:
(1) the model input is a two-dimensional matrix array, and the first convolutional layer to process the input uses 32 convolutional kernels of size 3 × 3.
(2) DenseBlock is the main feature learning structure in the model. As shown in fig. 5, the input of the i-th layer inside the DenseBlock is related not only to the output of the i-1 layer, but also to the outputs of all previous layers, i.e.:
Xi=Hi([X0,X1,…,Xi-1]),i=1,2,…,n
wherein n represents the number of preset feature map layers in the DenseBlock, and i represents the serial number of the feature map layers in the DenseBlock; x0Represents the output of the previous layer of DenseBlock; [ …]Indicating channel concatenation (splicing), i.e. X0To Xi-1All feature outputs of the layers are combined by channel; hi(.) represents the nonlinear transformation of the cascaded feature map, which comprises 4k 1 × 1 convolutional layers and k 3 × 3 convolutional layers in sequence, where k is H representing the preset valuei(.) the number of channels of the feature output. Specifically, in the convolutional neural network structure employed in this embodiment, DenseBlock (1) is configured to have n-3 and k-16, and DenseBlock (2) is configured to have n-6 and k-32.
(3) The transition layer is a convolution layer plus a pooling layer. Wherein the convolutional layer adopts 40 1 × 1 convolutional kernels; the pooling layer is an average pooling of 2 x 2 windows with a sampling interval of 2, doubling the output size.
(4) The regression layer is used as the output of the last layer of model, the feature map is converted into 1-dimensional data by adopting global average pooling, and then two full-connection layers are formed. In this embodiment, the final output vector is 64-dimensional, which means that 64 points are uniformly located on the radius of the charge level, and each value in the output vector represents the height (vertical distance) from the corresponding point on the charge level to the horizontal plane where the radar rotation center is located.
(5) The activation functions of all the convolution layers in the network structure adopt linear rectification units, normalization is carried out before the linear rectification units, and input of the linear rectification units is normalized to standard normal distribution with the average value of 0 and the variance of 1.
(6) Since the model is a regression learning of the charge level shape, the loss function (objective function) of the network used is the mean square error:
in the formula, n is the dimension of an output vector and represents that n points are uniformly taken on the radius; diIn the form of an actual value of the value,and the model output value represents the height from the ith point on the material surface to the horizontal plane where the radar rotation center is located.
TABLE 1
Since the model needs to be trained before use, the convolutional neural network model is trained through a training set. In the training process, when the regression error represented by the loss function is smaller than a preset threshold value, the network structure of the current parameters is determined as a final convolutional neural network model.
S4: and splicing echo curve data corresponding to the charge level to be tested, which are acquired by the millimeter wave radar, into a two-dimensional matrix array, and outputting the two-dimensional matrix array through a trained convolutional neural network model to obtain the charge level to be tested.
The echo curve data corresponding to the charge level to be measured is acquired in the same manner as in step S1.
The two-dimensional matrix array corresponding to the echo curve data is input into the trained convolutional neural network model, and the output of the model is the height from each measuring position (in the embodiment, 64 points are uniformly taken on the radius of the charge level) on the radius of the charge level to the horizontal plane where the radar rotation center is located, so that the shape of the charge level is represented.
The embodiment of the invention does not need complex sensor arrangement, has simpler required installation environment, and has higher precision and more comprehensive measurement effect compared with the measurement of a common single-point radar.
Example two:
the invention also provides a level measurement terminal device based on radar echo signals, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the method embodiment of the first embodiment of the invention.
Further, as an executable scheme, the level measurement terminal device based on the radar echo signal may be a desktop computer, a notebook, a palm computer, a cloud server, and other computing devices. The level measurement terminal device based on the radar echo signal can comprise, but is not limited to, a processor and a memory. It is understood by those skilled in the art that the above-mentioned structure of the level measurement terminal device based on the radar echo signal is only an example of the level measurement terminal device based on the radar echo signal, and does not constitute a limitation on the level measurement terminal device based on the radar echo signal, and may include more or less components than the above-mentioned structure, or combine some components, or different components, for example, the level measurement terminal device based on the radar echo signal may further include an input-output device, a network access device, a bus, etc., which is not limited by the embodiment of the present invention.
Further, as an executable solution, the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, and the like. The general processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of the radar echo signal based level measurement terminal device, and various interfaces and lines are used for connecting various parts of the whole radar echo signal based level measurement terminal device.
The memory can be used for storing the computer program and/or the module, and the processor can realize various functions of the level measurement terminal device based on the radar echo signal by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the mobile phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention also provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned method of an embodiment of the invention.
The integrated module/unit of the level measurement terminal device based on the radar echo signal can be stored in a computer readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), software distribution medium, and the like.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A charge level measuring method based on radar echo signals is characterized by comprising the following steps:
s1: respectively acquiring echo curve data corresponding to each measuring position on a radius of the charge level aiming at different charge levels in the blast furnace through a millimeter wave radar arranged on the top of the blast furnace, and recording the height of each measuring position on the radius of the charge level from the horizontal plane where the radar rotation center is located;
s2: splicing the echo curve data corresponding to each charge level into a two-dimensional matrix array, taking the two-dimensional matrix array corresponding to each charge level and the recorded height as a set of training data, and forming a training set by the training data corresponding to all charge levels;
s3: constructing a convolutional neural network model based on DenseNet, training the convolutional neural network model through a training set, setting the input of the model as a two-dimensional matrix array, and outputting as the recorded height;
s4: and splicing echo curve data corresponding to the charge level to be tested, which are acquired by the millimeter wave radar, into a two-dimensional matrix array, and outputting the two-dimensional matrix array through a trained convolutional neural network model to obtain the charge level to be tested.
2. The method of claim 1, wherein the method comprises: the echo curve is a frequency spectrum curve obtained after radar difference frequency signals are processed, the horizontal axis of the frequency spectrum curve represents distance, and the vertical axis of the frequency spectrum curve represents echo intensity.
3. The method of claim 1, wherein the method comprises: the millimeter wave radar can rotate around the axis, and the millimeter wave radar is controlled to rotate by a rotation angle smaller than the beam angle of the radar every time, so that the millimeter wave radar scans each measuring position in a radius of the charge level, and echo curve data of each measuring position are obtained.
4. The method of claim 1, wherein the method comprises: the set measuring positions are the same for different material surfaces.
5. The method of claim 1, wherein the method comprises: before the two-dimensional matrix array is spliced, preprocessing echo curve data and eliminating invalid data in the echo curve data.
6. The method of claim 1, wherein the method comprises: the network structure of the convolutional neural network model sequentially comprises a convolutional layer, a first DenseBlock, a transition layer, a second DenseBlock and a regression layer; wherein:
(1) the convolutional layer uses 32 convolutional kernels of size 3 × 3;
(2) the first DenseBlock and the second DenseBlock are both expressed as:
Xi=Hi([X0,X1,…,Xi-1]),i=1,2,…,n
wherein n represents the number of preset feature map layers in the DenseBlock, and i represents the serial number of the feature map layers in the DenseBlock; x0Represents the output of the previous layer of DenseBlock; [ …]Indicating a cascade of channels, i.e. X0To Xi-1All feature outputs of the layers are combined by channel; hi(.) represents the nonlinear transformation of the cascaded feature map, which comprises 4k 1 × 1 convolutional layers and k 3 × 3 convolutional layers in sequence, where k is H representing the preset valuei(.) number of channels of feature output;
(3) the transition layer is a convolution layer and a pooling layer, wherein the convolution layer adopts 40 1 × 1 convolution kernels; the pooling layer is an average pooling of 2 × 2 windows, and the sampling interval is 2;
(4) the regression layer converts the characteristic diagram into 1-dimensional data by adopting global average pooling, and then two full-connection layers are formed;
(5) the activation functions of all the convolution layers in the network structure adopt linear rectification units, normalization is carried out before the linear rectification units, and the input of the linear rectification units is normalized to standard normal distribution with the average value of 0 and the variance of 1;
(6) the loss function of the model uses the mean square error.
7. The method of claim 6, wherein the method comprises: the first DenseBlock in the convolutional neural network model is configured to be n-3 and k-16; the second DenseBlock is configured with n 6 and k 32.
8. The utility model provides a charge level measurement terminal equipment based on radar echo signal which characterized in that: comprising a processor, a memory and a computer program stored in said memory and running on said processor, said processor implementing the steps of the method according to any one of claims 1 to 7 when executing said computer program.
9. A computer-readable storage medium storing a computer program, characterized in that: the computer program when executed by a processor implementing the steps of the method as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110838714.XA CN113627283A (en) | 2021-07-23 | 2021-07-23 | Material level measuring method based on radar echo signals, terminal equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110838714.XA CN113627283A (en) | 2021-07-23 | 2021-07-23 | Material level measuring method based on radar echo signals, terminal equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113627283A true CN113627283A (en) | 2021-11-09 |
Family
ID=78380838
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110838714.XA Pending CN113627283A (en) | 2021-07-23 | 2021-07-23 | Material level measuring method based on radar echo signals, terminal equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113627283A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115204061A (en) * | 2022-09-09 | 2022-10-18 | 深圳市信润富联数字科技有限公司 | Method, device and equipment for automatically determining stamping modeling scale and storage medium |
CN115571656A (en) * | 2022-09-28 | 2023-01-06 | 华能伊敏煤电有限责任公司 | Automatic dumping control method and system based on material level detection |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5614911A (en) * | 1993-09-21 | 1997-03-25 | Endress + Hauser Gmbh + Co. | Radar-based method of level measurement |
WO2006068604A1 (en) * | 2004-12-23 | 2006-06-29 | Rosemount Tank Radar Ab | A radar level gauge system |
CN102676718A (en) * | 2011-03-07 | 2012-09-19 | 宝山钢铁股份有限公司 | System and method for alarming blast-furnace burden surface states |
US20130002443A1 (en) * | 2002-06-11 | 2013-01-03 | Intelligent Technologies International, Inc. | Remote monitoring of material storage containers |
CN109490861A (en) * | 2018-10-29 | 2019-03-19 | 北京科技大学 | A kind of blast-furnace line extracting method |
CN111220958A (en) * | 2019-12-10 | 2020-06-02 | 西安宁远电子电工技术有限公司 | Radar target Doppler image classification and identification method based on one-dimensional convolutional neural network |
CN111273287A (en) * | 2020-02-25 | 2020-06-12 | 南京华雷电子工程研究所有限公司 | Blast furnace charge level imaging device, system and measuring method thereof |
-
2021
- 2021-07-23 CN CN202110838714.XA patent/CN113627283A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5614911A (en) * | 1993-09-21 | 1997-03-25 | Endress + Hauser Gmbh + Co. | Radar-based method of level measurement |
US20130002443A1 (en) * | 2002-06-11 | 2013-01-03 | Intelligent Technologies International, Inc. | Remote monitoring of material storage containers |
WO2006068604A1 (en) * | 2004-12-23 | 2006-06-29 | Rosemount Tank Radar Ab | A radar level gauge system |
CN102676718A (en) * | 2011-03-07 | 2012-09-19 | 宝山钢铁股份有限公司 | System and method for alarming blast-furnace burden surface states |
CN109490861A (en) * | 2018-10-29 | 2019-03-19 | 北京科技大学 | A kind of blast-furnace line extracting method |
CN111220958A (en) * | 2019-12-10 | 2020-06-02 | 西安宁远电子电工技术有限公司 | Radar target Doppler image classification and identification method based on one-dimensional convolutional neural network |
CN111273287A (en) * | 2020-02-25 | 2020-06-12 | 南京华雷电子工程研究所有限公司 | Blast furnace charge level imaging device, system and measuring method thereof |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115204061A (en) * | 2022-09-09 | 2022-10-18 | 深圳市信润富联数字科技有限公司 | Method, device and equipment for automatically determining stamping modeling scale and storage medium |
CN115204061B (en) * | 2022-09-09 | 2023-01-06 | 深圳市信润富联数字科技有限公司 | Method, device and equipment for automatically determining stamping modeling scale and storage medium |
CN115571656A (en) * | 2022-09-28 | 2023-01-06 | 华能伊敏煤电有限责任公司 | Automatic dumping control method and system based on material level detection |
CN115571656B (en) * | 2022-09-28 | 2023-06-02 | 华能伊敏煤电有限责任公司 | Automatic soil discharging control method and system based on material level detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113627283A (en) | Material level measuring method based on radar echo signals, terminal equipment and storage medium | |
CN108872985B (en) | Near-field circumference SAR rapid three-dimensional imaging method | |
US20070127036A1 (en) | Interference measurement system self-alignment method | |
CN110674835B (en) | Terahertz imaging method and system and nondestructive testing method and system | |
CN106569191A (en) | Method of acquiring target RCS by using high resolution imaging | |
CN114415140A (en) | Target RCS (radar cross section) measuring method based on near-field plane scanning three-dimensional wave number domain imaging | |
CN109884627B (en) | Short-range millimeter wave rapid three-dimensional imaging method of any linear array configuration | |
CN107678025B (en) | Sea wave height calculation method and device, storage medium and processor | |
CN113486961A (en) | Radar RD image target detection method and system based on deep learning under low signal-to-noise ratio and computer equipment | |
CN109683134A (en) | A kind of high-resolution localization method towards rotation sound source | |
JPWO2017154125A1 (en) | Synthetic aperture radar signal processor | |
CN112068133B (en) | System simulation method for multimode microwave remote sensor scatterometer mode | |
CN115953604B (en) | Real estate geographic information mapping data acquisition method | |
CN115825894B (en) | Method, device, terminal equipment and medium for determining wind energy capturing position | |
CN105527624B (en) | A kind of method and weather radar system of radar return dynamic estimation noise | |
WO2023000540A1 (en) | Method and terminal device for measuring burden surface profile of blast furnace, and storage medium | |
CN115932760A (en) | Calibration method and device for special-shaped linear array radar, radar and storage medium | |
CN113359196B (en) | Multi-target vital sign detection method based on subspace method and DBF | |
Lobato et al. | Deconvolution with neural grid compression: A method to accurately and quickly process beamforming results | |
CN113839711A (en) | Peak detection method based on dynamic threshold distance centroid algorithm | |
CN105403884A (en) | Data quantification method of three-dimensional near-field scanning system | |
CN114252876A (en) | High-resolution one-dimensional imaging method based on multi-scattering point model | |
CN116068503A (en) | Combined calibration method and device for millimeter wave radar and laser radar and terminal equipment | |
CN111637837A (en) | Method and system for measuring size and distance of object by monocular camera | |
Dao et al. | Research on Improved Algorithm of Frequency Estimation Based on Complex Modulation. |
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 |