CN108800916B - A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision - Google Patents
A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision Download PDFInfo
- Publication number
- CN108800916B CN108800916B CN201810754696.5A CN201810754696A CN108800916B CN 108800916 B CN108800916 B CN 108800916B CN 201810754696 A CN201810754696 A CN 201810754696A CN 108800916 B CN108800916 B CN 108800916B
- Authority
- CN
- China
- Prior art keywords
- thickness
- feed layer
- grate
- cooler
- machine vision
- 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.)
- Active
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
- F27B7/00—Rotary-drum furnaces, i.e. horizontal or slightly inclined
- F27B7/20—Details, accessories, or equipment peculiar to rotary-drum furnaces
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
- F27B7/00—Rotary-drum furnaces, i.e. horizontal or slightly inclined
- F27B7/20—Details, accessories, or equipment peculiar to rotary-drum furnaces
- F27B7/42—Arrangement of controlling, monitoring, alarm or like devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D19/00—Arrangements of controlling devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27D—DETAILS OR ACCESSORIES OF FURNACES, KILNS, OVENS, OR RETORTS, IN SO FAR AS THEY ARE OF KINDS OCCURRING IN MORE THAN ONE KIND OF FURNACE
- F27D19/00—Arrangements of controlling devices
- F27D2019/0096—Arrangements of controlling devices involving simulation means, e.g. of the treating or charging step
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
- Incineration Of Waste (AREA)
Abstract
The present invention relates to a kind of grate-cooler thickness of feed layer model predictive control method based on machine vision, includes the following steps；Step 1: software and hardware is disposed；Step 2: measuring thickness of feed layer using machine vision technique；Step 3: off-line identification；Step 4: On-line Control；The present invention directly measures thickness of feed layer by machine vision, avoids indirect scale sign bring inaccuracy, interferes the problems such as big；Model Predictive Control Algorithm can stability contorting thickness of feed layer, keep the bed of material be uniformly distributed, improve heat exchange efficiency, is energy saving.Algorithm deployment is convenient, maintenance is simple, opens new approach for the measurement and control of grate-cooler thickness of feed layer.
Description
Technical field
The grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision that the present invention relates to a kind of.
Background technique
Grate-cooler is the key equipment in manufacture of cement, is mainly made of grate plate and grate.High temperature chamotte is transported by rotary kiln
It send to Cooler Bed Driving, grate plate pushes clinker to spread out, travels forward along grate and push clinker, and grate plate return later is transported again
Clinker and so on moves.Cooling wind below grate is allowed to cool across clinker, and cooling wind a part is by thermosetting Secondary Air
Into rotary kiln, a part of wind enters device for generating power by waste heat.
The thickness of the grate-cooler bed of material is most important to cooling machine equipment, and the bed of material is too thin, then the time that cooling wind passes through the bed of material
It is too short, short circuit is formed, it is fast by the cooling wind wind speed of the bed of material, air quantity is big, it will also result in the reduction of secondary air temperature；The bed of material is too thick,
Cooling wind is impermeable and the lower pressure increase that makes to comb, and then part occurs and blow through, and cooling wind is all blown away from blowing through position, other positions
" Red River " phenomenon is easily formed, grate plate hot-spot is caused, while thickness of feed layer increases so that lower pressure of combing increases therewith, for heat
The high pressure cold air of exchange is obstructed, and reduces into comb room air quantity, causes secondary air temperature to reduce, heat exchange efficiency can also reduce.Therefore
The control of grate-cooler, it is most important that the state for making thickness of feed layer thickness as far as possible and grate boil generally in one.Thickness of feed layer
Adjusted by the speed (hereinafter referred to as comb speed) that grate plate moves, speed of combing is very fast, clinker quickly through grate, thickness of feed layer will under
Drop；Combing, speed is slower, and clinker is accumulated in grate, and thickness of feed layer just will increase, and certain integral characteristic is presented in thickness of feed layer,
It can increase always.In addition, thickness of feed layer is also influenced by cooling wind air quantity, air quantity is big, then clinker is cooled fastly, clinker viscosity
Reduce so that the bed of material is easy to be pushed out grate-cooler, thickness of feed layer is reduced, and air quantity is small, and clinker is cooled slowly, clinker viscosity compared with
Height, so that clinker is not easy to be pushed out, thickness of feed layer increases.
Grate-cooler compares closing since internal environment is more severe, therefore the bed of material being difficult inside directly measurement is thick
Degree.How to judge that suitable thickness of feed layer is always the difficult point of grate-cooler optimization.It is industrial at present generally with thickness of feed layer phase
Indirect amount (comb lower pressure, secondary air temperature, grate-cooler hydraulic pressure signal etc.) the characterization thickness of feed layer closed.Traditional control strategy is thought
Amount meets linear relationship with thickness of feed layer indirectly, establishes the model indirectly between amount and speed of combing, by Model Predictive Control or
Control is implemented in fuzzy control.It is more complicated with the model of thickness of feed layer due to measuring indirectly, non-linear behavior is showed, and indirectly
Amount and thickness of feed layer relationship is affected by operating condition, and very big puzzlement is caused to thickness of feed layer optimal control, leads to current market
Upper grate-cooler optimization cannot achieve benefit promotion, and need human intervention in operating condition variation.
Summary of the invention
For overcome the deficiencies in the prior art, the present invention provides a kind of grate-cooler thickness of feed layer model based on machine vision
Predictive control algorithm, the algorithm use machine vision technique real-time measurement thickness of feed layer, establish thickness of feed layer between speed of combing
Relationship model, while using secondary air temperature and pushing power of combing as bound variable, pass through Model Predictive Control Algorithm and solves speed of combing, shape
At close loop control circuit.The algorithm can effectively solve the problems, such as the indirect scale sign inaccuracy of grate-cooler thickness of feed layer, be the bed of material
Thickness provides precise information information, may finally reach stability contorting thickness of feed layer, promotes clinker quality, improves heat exchange effect
Rate, the purpose of energy saving.
The technical scheme of the invention to solve the technical problem is: a kind of grate-cooler bed of material based on machine vision
Thickness model predictive control algorithm, includes the following steps；
(1) in grate-cooler bed of material exit upper side mounting industrial camera；It installs and marks in grate-cooler bed of material exit side
Ruler, disposes machine vision software in engineer station, receives industrial camera transmitting by industry communications protocol (TCP/IP, OPC etc.)
Two-dimensional image data；The triumphant expert's optimization system software for containing independent research in Nanjing is installed；
(2) ROI region delimited, RGB image is changed into gray-value image, extracted by smooth, filtering, edge detection ripe
The edge contour of material can calculate the thickness of the bed of material by carrying out ratiometric conversion with the size of scale；
(3) end OPC Server is sent by OPC by the thickness of feed layer being calculated, the history for recording thickness of feed layer becomes
Gesture；The historical trend of speed of combing, secondary air temperature, lower pressure of combing is recorded simultaneously；Comb speed is regarded as manipulating variable (MV), thickness of feed layer is made
For controlled variable (CV), secondary air temperature and pushing power of combing establish the integral mould of an input three output as bound variable (CCV)
Type carries out System Discrimination using expert's optimization system；
(4) model obtained using step (3) identification, implementation model PREDICTIVE CONTROL (MPC) in expert's optimization system,
MPC algorithm executes control by model prediction, rolling optimization, feedback compensation period；
Preferably, within the control period in each described step (4), rolling optimization is carried out to objective function.
Preferably, feedback compensation is carried out to the calculated predicted value of the rolling optimization.
Compared with the prior art, the advantages of the present invention are as follows:
Firstly, algorithm of the present invention by machine vision, and one camera is used, the mode that scale compares measures grate-cooler
It is complicated, at high cost to avoid the processes such as common binocular camera three-dimensional modeling measurement and infrared survey in the market for thickness of feed layer
Measurement method.
Secondly, the present invention directly measures thickness of feed layer, model inaccuracy when tradition is levied with indirect scale, environment are avoided
The influence of the uncertain factors such as interference, so that measurement result is more accurate.
Again, the present invention passes through the thickness of feed layer progress Model Predictive Control directly measured, thickness of feed layer can be made to keep
It is unlikely to the state for occurring locally erupting again thick as far as possible, the bed of material is maintained at best boiling form, makes secondary air temperature and comb to push
Power meets process requirements, improves heat exchange efficiency, reaches the target of quality environmental protection two-win.
Finally, it is not necessary to modify field devices in addition to industrial camera by the present invention, therefore dispose conveniently, which is grate-cooler material
Layer thickness measure and optimal control open new approach.
Detailed description of the invention
Fig. 1 is industrial camera scheme of installation of the invention；
Fig. 2 is Nanjing Kai Sheng expert's optimization system surface chart in the present invention；
Fig. 3 a is the original image of image processing process figure of the invention；
Fig. 3 b is the ROI region image of image processing process figure of the invention；
Fig. 3 c is gray processing treated the image of image processing process figure of the invention；
Fig. 3 d is the image of image processing process figure of the invention extracted after profile；
Fig. 4 is communication of the invention and control flow chart.
Specific embodiment
A kind of grate-cooler thickness of feed layer model predictive control method based on machine vision, includes the following steps；
Step 1: software and hardware is disposed；In grate-cooler bed of material exit upper side mounting industrial camera, protected by shield
Camera is interfered from high temperature；Scale is installed in grate-cooler bed of material exit side, for demarcating thickness of feed layer, industrial camera and mark
Industrial camera is installed on comb as shown in Figure 1, in order to collect bed of material image inside accurate grate-cooler by the scheme of installation of ruler
Cold exit upper side, in order to observe grate-cooler internal state with large viewing, additionally by mounting industrial shield
Avoid industrial camera by the interference of high temperature and dust etc.；Installation scale is exported in the grate-cooler bed of material, as shown in figure 1 blue vertical bar institute
Show；It is generally believed that thickness of feed layer is linear with scale, by the bed of material image information of acquisition, after image procossing with mark
Practical thickness of feed layer can be obtained in ruler conversion；Machine vision software is disposed in engineer station, passes through industry communications protocol (TCP/
IP, OPC etc.) receive the two-dimensional image data that industrial camera transmits；It is soft that the triumphant expert's optimization system for containing independent research in Nanjing is installed
Part, the industrial common control algolithm such as the Integrated Simulation identification, Model Predictive Control Algorithm, the interface of expert's optimization system
As shown in Figure 2；Nanjing Kai Sheng expert's optimization system covers the control such as Model Predictive Control, fuzzy control, generalized predictive control
Algorithm has the script technologies such as smooth, filtering, can (the manipulated variable MV in such as figure, controlled volume CV become with displaying live view controlling curve
Gesture), facilitate adjustment control parameter, setting variate-value etc..When actually using Model Predictive Control Algorithm, by manipulating variable MV,
Controlled variable CV etc. is configured to related OPC variable, and system optimization control can be realized in incorporating parametric configuration feature.
Step 2: measuring thickness of feed layer using machine vision technique；Since top temperature is higher in grate-cooler, top section
Clinker is in a molten state, therefore is in the picture in crimson color, and the insufficiently burnt clinker of bottom is in furvous；Therefore can pass through
ROI region delimited, RGB image is changed into gray-value image, the edge wheel of clinker is extracted by smooth, filtering, edge detection
Exterior feature, image processing process are shown in Fig. 3 (a~d)；Clinker and scale can be approximately considered, and equal proportion is distributed in the camera, therefore is passed through
The thickness of the bed of material can be calculated by carrying out ratiometric conversion with the size of scale；Grate-cooler thickness of feed layer image procossing mainly includes four
Part.First is that original image collecting part, original figure are acquired by industrial camera, and is reached and be mounted on by industry communications protocol
The machine vision software of engineer station；Second is that the two-dimensional image information that machine vision software will acquire is analyzed and processed, obtain
ROI region；Third is that the gray processing treatment process of ROI region；Fourth is that extracting bed of material profile from gray level image.Obtain bed of material profile
It can convert to obtain practical thickness of feed layer with scale bar later.
Step 3: off-line identification；The end OPCServer is sent by OPC by the thickness of feed layer being calculated, records the bed of material
The historical trend of thickness；The historical trend of speed of combing, secondary air temperature, lower pressure of combing is recorded simultaneously；Regard comb speed as manipulating variable
(MV), it is defeated to establish one as bound variable (CCV) as controlled variable (CV), secondary air temperature and pushing power of combing for thickness of feed layer
The integral model for entering three outputs carries out System Discrimination using expert's optimization system.
Step 4: On-line Control；The model recognized using step 3, implementation model is predicted in expert's optimization system
It controls (MPC), MPC algorithm executes control by model prediction, rolling optimization, feedback compensation period.
The period is controlled at each, rolling optimization is carried out to objective function；The objective of institute's optimality criterion is: Ji Yaobao
It demonstrate,proves thickness of feed layer and is in bound restriction range as close as setting value, secondary air temperature and lower pressure of combing, while to avoid
Speed of combing acute variation.
The calculated predicted value of rolling optimization is subjected to feedback compensation；Since there are model mismatch, environment in actual motion
The X factors such as interference, may deviate from actual value by the predicted value that rolling optimization calculates, if utilizing letter in real time not in time
Breath carries out feedback compensation, and the optimization of next step will establish on the basis of the model prediction of inaccuracy, with the progress of process, prediction
Output is possible to increasingly deviate reality output.
Communication part of the invention relates generally to industrial camera and machine vision software, machine vision software and OPC
Communication between Server, OPC Client and OPC Server.Standard is followed between industrial camera and machine vision software
Industry communications protocol, such as TCP/IP, OPC DA, OPC UA etc.；Machine vision software and OPC Client and OPC Server it
Between be all made of OPC agreement and communicated.And control flow part is the prediction mould established between manipulating variable and controlled volume first
Type, this process can recognize to obtain by off-line model；The period followed by is controlled at each, controlled system is optimized,
It should guarantee that thickness of feed layer maintains thick as far as possible and equally distributed state, avoid the frequent strenuous vibration of speed of combing again；It is finally
To the feedback compensation of prediction output valve, to make up environmental disturbances, prediction model is distorted the problem of bring controls accuracy decline.
Grate-cooler compares closing since internal environment is more severe, therefore the bed of material being difficult inside directly measurement is thick
Degree.How to judge that suitable thickness of feed layer is always the difficult point of grate-cooler optimization.It is industrial at present generally with thickness of feed layer phase
Indirect amount (comb lower pressure, secondary air temperature, grate-cooler hydraulic pressure signal etc.) the characterization thickness of feed layer closed.Traditional control strategy is thought
Amount meets linear relationship with thickness of feed layer indirectly, establishes the model indirectly between amount and speed of combing, by Model Predictive Control or
Control is implemented in fuzzy control.It is more complicated with the model of thickness of feed layer due to measuring indirectly, non-linear behavior is showed, and indirectly
Amount and thickness of feed layer relationship is affected by operating condition, and very big puzzlement is caused to thickness of feed layer optimal control, leads to current market
Upper grate-cooler optimization cannot achieve benefit promotion, and need human intervention in operating condition variation.
The grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision that the invention discloses a kind of.The algorithm is adopted
The two dimensional image inside grate-cooler is shot with industrial camera, and is transmitted to machine vision software.Machine vision software is from X-Y scheme
Obtain ROI region as in, bed of material edge contour extracted by gray processing, smooth, filtering, edge detection, and with scale in image
It converts, obtains bed of material actual (real) thickness.Become thickness of feed layer as controlled volume, secondary air temperature and pushing power of combing as constraint
Amount, speed of combing are used as manipulating variable, obtain system model by off-line calculation.The system model established offline is introduced into Nanjing
The triumphant expert's optimization system for containing independent research implements on-time model PREDICTIVE CONTROL.Thickness of feed layer is directly measured by machine vision,
It avoids indirect scale sign bring inaccuracy, interfere the problems such as big.Model Predictive Control Algorithm being capable of stability contorting bed of material thickness
Degree keeps the bed of material to be uniformly distributed, improve heat exchange efficiency, is energy saving.Algorithm deployment is convenient, maintenance is simple, is grate-cooler material
The measurement and control of thickness degree open new approach.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of skill in the art that it still can be right
Technical solution documented by foregoing embodiments is modified, or is replaced on an equal basis to part of technical characteristic；And this
It modifies or replaces, the spirit and model of technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (3)
1. a kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision, includes the following steps；
(1) in grate-cooler bed of material exit upper side mounting industrial camera；Scale is installed in grate-cooler bed of material exit side,
Engineer station disposes machine vision software, and the two-dimensional image data of industrial camera transmitting is received by industry communications protocol；Installation
Expert's optimization system software；
(2) ROI region delimited, RGB image is changed into gray-value image, clinker is extracted by smooth, filtering, edge detection
Edge contour can calculate the thickness of the bed of material by carrying out ratiometric conversion with the size of scale；
(3) end OPC Server is sent by OPC by the thickness of feed layer being calculated, records the historical trend of thickness of feed layer；
The historical trend of speed of combing, secondary air temperature, lower pressure of combing is recorded simultaneously；Regard comb speed as manipulating variable (MV), thickness of feed layer conduct
Controlled variable (CV), secondary air temperature and pushing power of combing establish the integral mould of an input three output as bound variable (CCV)
Type carries out System Discrimination using expert's optimization system；
(4) obtained model is recognized using step (3), implementation model PREDICTIVE CONTROL (MPC) in expert's optimization system, MPC are calculated
Method executes control by model prediction, rolling optimization, feedback compensation period；
2. a kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision according to claim 1,
It is characterized in that, within the control period in each described step (4), rolling optimization is carried out to objective function.
3. a kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision according to claim 2,
It is characterized in that, feedback compensation is carried out to the calculated predicted value of the rolling optimization.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810754696.5A CN108800916B (en) | 2018-07-11 | 2018-07-11 | A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision |
| PCT/CN2019/088672 WO2020010937A1 (en) | 2018-07-11 | 2019-05-27 | Machine vision-based model predictive control algorithm for material layer thickness of grate cooler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810754696.5A CN108800916B (en) | 2018-07-11 | 2018-07-11 | A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108800916A CN108800916A (en) | 2018-11-13 |
| CN108800916B true CN108800916B (en) | 2019-07-05 |
Family
ID=64076013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810754696.5A Active CN108800916B (en) | 2018-07-11 | 2018-07-11 | A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108800916B (en) |
| WO (1) | WO2020010937A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108800916B (en) * | 2018-07-11 | 2019-07-05 | 南京凯盛国际工程有限公司 | A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision |
| CN110595397A (en) * | 2019-10-10 | 2019-12-20 | 南京凯盛国际工程有限公司 | Grate cooler working condition monitoring method based on image recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103363812A (en) * | 2013-07-03 | 2013-10-23 | 中国科学院沈阳自动化研究所 | Control method of cement clinker grate cooler |
| CN104503242A (en) * | 2014-12-24 | 2015-04-08 | 浙江邦业科技有限公司 | Cement grate cooler self-adaptive model prediction controller |
| CN108268895A (en) * | 2018-01-12 | 2018-07-10 | 上海烟草集团有限责任公司 | The recognition methods of tobacco leaf position, electronic equipment and storage medium based on machine vision |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103808160B (en) * | 2014-01-26 | 2016-02-03 | 浙江邦业科技股份有限公司 | Based on the thickness of feed layer characterizing method of grate-cooler hydraulic pressure |
| WO2017109543A1 (en) * | 2015-12-22 | 2017-06-29 | Arcelormittal | Method and system for determining the mass of feedstock on a conveyor |
| CN108800916B (en) * | 2018-07-11 | 2019-07-05 | 南京凯盛国际工程有限公司 | A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision |
-
2018
- 2018-07-11 CN CN201810754696.5A patent/CN108800916B/en active Active
-
2019
- 2019-05-27 WO PCT/CN2019/088672 patent/WO2020010937A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103363812A (en) * | 2013-07-03 | 2013-10-23 | 中国科学院沈阳自动化研究所 | Control method of cement clinker grate cooler |
| CN104503242A (en) * | 2014-12-24 | 2015-04-08 | 浙江邦业科技有限公司 | Cement grate cooler self-adaptive model prediction controller |
| CN108268895A (en) * | 2018-01-12 | 2018-07-10 | 上海烟草集团有限责任公司 | The recognition methods of tobacco leaf position, electronic equipment and storage medium based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| 基于三维重建技术的篦冷机熟料冷却控制模型研究;张文明;《中国博士学位论文全文数据库》;20100815;全文 |
| 基于双目视觉的篦冷机熟料厚度场测量方法研究;张强;《中国优秀硕士学位论文全文数据库》;20070815;全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108800916A (en) | 2018-11-13 |
| WO2020010937A1 (en) | 2020-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| CN108800916B (en) | A kind of grate-cooler thickness of feed layer Model Predictive Control Algorithm based on machine vision | |
| CN116520915B (en) | Network center machine room temperature early warning control system based on thermal infrared image | |
| CN106925784A (en) | A kind of 3D printing course monitoring method and device based on camera captured in real-time | |
| CN102795627A (en) | Multi-parameter online monitoring and optimizing control device and method of polycrystalline silicon reduction furnace | |
| CN112620652A (en) | Self-adaptive control system and method for electric arc additive manufacturing process | |
| CN110369723A (en) | A kind of laser power optimization method of 3D laser printing | |
| CN110751669A (en) | Novel CBOCP online infrared converter tapping steel flow automatic detection and tracking method and system | |
| CN104392213A (en) | Image information state recognizing system applicable to melting process | |
| WO2021068497A1 (en) | Grate cooler working state monitoring method based on image recognition | |
| CN109308707B (en) | Non-contact type online measuring method for thickness of aluminum ingot | |
| CN109242833B (en) | Cutting control method for coal mining machine | |
| CN110597065A (en) | Adaptive control system for powder feeding type laser additive | |
| CN114187282A (en) | Grate cooler bed thickness measuring method based on image segmentation | |
| JP2014037001A (en) | Final solidification estimation method in continuous casting, solidification state estimation method of slab and continuous casting method | |
| CN114273494A (en) | Intelligent spinning processing control method | |
| CN112132428B (en) | Predictive regulation and control decision method for steam distribution station of steam heat supply network based on big data | |
| CN105463511B (en) | Aluminum cell electrolyte on-line temperature monitoring method and its device | |
| CN109201750A (en) | Hot rolling low temperature coiling band steel surface based on water area purges control method | |
| CN207623764U (en) | Casting machine camera controls automatic station-keeping system | |
| CN111879410A (en) | Heat balance management method and system thereof | |
| CN105807795A (en) | EB furnace titaniferous solution liquid level monitoring system and method based on video image processing | |
| CN112033493A (en) | Continuous casting molten pool liquid level detection system and continuous casting molten pool liquid level control method | |
| CN105718897A (en) | Numerical control lathe based on visual characteristics | |
| CN113085189B (en) | Smooth 3D printing device of high accuracy based on thing networking and sensing control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230802 Address after: No. 320 and 436 Pingtang East Road, Puxing Street, Xinjin District, Chengdu City, Sichuan Province, 611400 Patentee after: Sinoma Intelligent Technology (Chengdu) Co.,Ltd. Address before: 303 Hanzhongmen street, Gulou District, Nanjing City, Jiangsu Province Patentee before: NANJING KISEN INTERNATIONAL ENGINEERING Co.,Ltd. |
|
| TR01 | Transfer of patent right |