CN110471374A - A kind of cement slurry predecomposition process disturbance reduction qualitative forecasting method - Google Patents
A kind of cement slurry predecomposition process disturbance reduction qualitative forecasting method Download PDFInfo
- Publication number
- CN110471374A CN110471374A CN201910608006.XA CN201910608006A CN110471374A CN 110471374 A CN110471374 A CN 110471374A CN 201910608006 A CN201910608006 A CN 201910608006A CN 110471374 A CN110471374 A CN 110471374A
- Authority
- CN
- China
- Prior art keywords
- data
- new
- indicate
- variable
- indicates
- 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
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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32368—Quality control
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a kind of cement slurry predecomposition process disturbances to reduce qualitative forecasting method.The present invention is first handled collected process data using Wavelet Denoising Method and orthogonal signalling, to reduce the association between variable；Then using treated, data carry out offset minimum binary modeling；In order to reduce the nonlinear problem of data, introduces support vector machines and carry out Modifying model.The shortcomings that it is complicated that present invention improves Classical forecast model modeling processes, can not handle nonlinear data, improves the ability of model following truthful data.
Description
Technical field
The invention belongs to fields of automation technology, are related to a kind of cement slurry predecomposition process disturbance reduction prediction of quality side
Method.
Background technique
The most incipient stage is feedstock processing in manufacture of cement, this stage will affect subsequent production if there is problem
Process.It is that boundary condition frequently changes in the characteristics of raw material predecomposition process, the quality index raw material of product is thus caused to decompose
Rate is too low or excessively high, causes subsequent production process to go wrong indirectly to increase the load of rotary kiln.It may result in work
A series of problems, such as factory's production task is delayed, fund loss, production accident.Therefore the predecomposition process of cement slurry is carried out
It monitors and reduces influence of the disturbance to result with very realistic meaning.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of cement slurry predecomposition process disturbances to reduce prediction of quality
Method.
The present invention is first handled collected process data using Wavelet Denoising Method and orthogonal signalling, to reduce variable
Between association；Then using treated, data carry out offset minimum binary modeling；In order to reduce the nonlinear problem of data, draw
Enter support vector machines and carries out Modifying model.
The technical scheme is that being acquired by data, data prediction, system modelling, data processing, parameter optimization
Etc. means, establish a kind of novel cement process disturbance and reduce qualitative forecasting method.
The step of the method for the present invention includes:
Step 1. acquires the data of sensor during cement, is handled and establishes novel course prediction model.Tool
Body step is:
Data during 1.1 acquisition cement carry out off-line modeling, and data are divided into two classes, process data X and qualitative data
Y, one shares N number of sample.
X=[x1,x2,…xm],x1,x2…xm∈RN×1
Y=[y1,y2,…yp],y1,y2…yp∈RN×1
Wherein, x1,x2,…xmEtc. the reactant concentration respectively indicated during cement, pressure, the m such as temperature ... valve opening
A variable, y1,y2…ypEtc. respectively indicating production concentration, the p variable relevant to quality such as product purity ... product temperatur.
1.2 use the noise in Wavelet noise-eliminating method removal process data.
Wherein, XpProcess data after indicating Wavelet Denoising Method, YpQualitative data after indicating Wavelet Denoising Method；lxExpression process
The threshold value of data, lyIndicate the threshold value of qualitative data.
1.3 pre-process collected initial data using Orthogonal Signal Correction Analyze algorithm.
t0=Xpw
In formula, tSIt indicates the corresponding first principal component of process data X, is calculated using Principal Component Analysis；tnewIt indicates
Direction and t along Y0Orthogonal vector；The weight vectors of w expression X；t0Indicate the score matrix of X；p0Indicate load vector；
XOSCIt indicates by orthogonal signalling decomposition algorithm treated process data.
1.4 are handled data obtained in step 1.3 using Partial Least Squares.
T=XOSCw
U=Ypq
In formula, t indicates XOSCCorresponding principal component；P indicates XOSCCorresponding load vector；Q indicates that quality variable is corresponding
Load vector；U indicates the corresponding score vector of quality variable.
1.5, by step 1.1-1.4, obtain system model.
In formula, a=1,2 ... A indicate principal component index；taIndicate a-th of latent variable corresponding with process variable X；pa
Indicate corresponding a-th of the load vector of process variable；The residual error of E expression process variable；uaIndicate that quality variable is a-th corresponding
Latent variable；qaIndicate a-th of load vector corresponding with quality variable；The residual error of F expression quality variable.
1.6, which are introduced into algorithm of support vector machine, is modified the model in step 1.5:
U=f (T)+H=[f1(t1),f2(t2),…fa(ta)]+[h1,h2,…ha]
ua=fa(ta)+ha, a=1,2 ... A
In formula, U indicates the corresponding latent variable matrix of quality variable；T indicates the corresponding latent variable matrix of process variable；
F () indicates a nonlinear function；h1,h2…haThe 1,2nd is respectively indicated ... the corresponding residual error of a latent variable；It indicates
The predicted value of a-th of latent variable corresponding to quality variable；Indicate a regression coefficient；K(ta,i,ta) indicate
The corresponding kernel function of a-th of latent variable；B indicates prediction residual.
Step 2: the data newly obtained during acquisition cement process operation use offset minimum binary obtained in step 1
Model carries out on-line prediction, specifically:
The process data X newly obtained in 2.1 collection processnewWith qualitative data Ynew, collected new data is carried out small
Wave denoising.
Wherein, XpnewNew process data after indicating Wavelet Denoising Method, YpnewNew mass number after indicating Wavelet Denoising Method
According to.
2.1 are pre-processed using Orthogonal Signal Correction Analyze method.
t0new=Xpnewwnew
In formula, tsnewIndicate process data XnewCorresponding first principal component, is calculated using Principal Component Analysis；tnnew
It indicates along YnewDirection and t0newOrthogonal vector；The weight vectors of w expression X；t0newIndicate XnewScore matrix；p0new
Indicate load vector；XOSCnewIt indicates by orthogonal signalling decomposition algorithm treated process data.
2.2 handle new collected data using Partial Least Squares, calculate the latent variable of new data.
tt=XOSCnewwnew
unew=Ypnewqnew
In formula, ttIndicate XOSCnewCorresponding principal component；pnewIndicate XOSCnewCorresponding load vector；qnewIndicate that quality becomes
Measure corresponding load vector；unewIndicate the corresponding score vector of quality variable.
2.3 carry out on-line prediction using prediction model
In formula,Indicate process quality data YnewPredicted value；Q indicates the corresponding moment of load of process quality data
Battle array.FnewIndicate prediction residual.
Beneficial effects of the present invention: it is complicated that present invention improves Classical forecast model modeling processes, can not handle non-linear
The shortcomings that data, improves the ability of model following truthful data.
Specific embodiment
For raw material predecomposition process in cement production process:
Raw material mixed first, heated by cement slurry predecomposition process, it is broken reach specific particle requirement, then
Various raw materials are sent into grinder in proportion, are ground into the raw meal powder for meeting production requirement.Have in this course lime stone,
The material concentrations such as iron ore, the variables such as valve opening of various raw material input channels are analyzed.
Step 1. acquires the data of sensor during cement slurry predecomposition, is handled and establishes novel prediction mould
Type.It comprises the concrete steps that:
Data during 1.1 acquisition cement slurry predecomposition carry out off-line modeling, and data are divided into two classes, process data X
N number of sample is shared with qualitative data Y, one.
X=[x1, x2... xm], x1, x2…xm∈RN×1
Y=[y1, y2... yp], y1, y2…yp∈RN×1
Wherein, x1, x2... xmEtc. the material concentration respectively indicated during cement slurry predecomposition, reaction pressure, reaction
The m variable such as temperature ... valve opening, y1, y2…ypEtc. respectively indicating product quality, proportion of products ... product grain etc. and quality
Relevant p variable.
1.2 use the noise in Wavelet noise-eliminating method removal process data.
Wherein, XpProcess data after indicating Wavelet Denoising Method, YpQualitative data after indicating Wavelet Denoising Method；lxExpression process
The threshold value of data, lyIndicate the threshold value of qualitative data.
1.3 pre-process collected initial data using Orthogonal Signal Correction Analyze algorithm.
t0=Xpw
In formula, tsIt indicates the corresponding first principal component of process data X, is calculated using Principal Component Analysis；tnewIt indicates
Direction and t along Y0Orthogonal vector；The weight vectors of w expression X；t0Indicate the score matrix of X；p0Indicate load vector；
XOSCIt indicates by orthogonal signalling decomposition algorithm treated process data.
1.4 are handled data obtained in step 1.3 using Partial Least Squares.
T=XOSCw
U=Ypq
In formula, t indicates XOSCCorresponding principal component；P indicates XOSCCorresponding load vector；Q indicates that quality variable is corresponding
Load vector；U indicates the corresponding score vector of quality variable.
1.5 by step 1.1-1.4, available system model:
In formula, a=1,2 ... A indicate principal component index；taIndicate a-th of latent variable corresponding with process variable X；pa
Indicate corresponding a-th of the load vector of process variable；The residual error of E expression process variable；uaIndicate that quality variable is a-th corresponding
Latent variable；qaIndicate a-th of load vector corresponding with quality variable；The residual error of F expression quality variable.
1.6, which are introduced into algorithm of support vector machine, is modified the system model in step 1.5:
U=f (T)+H=[f1(t1), f2(t2) ... fa(ta)]+[h1, h2... ha]
ua=fa(ta)+ha, a=1,2 ... A
In formula, U indicates the corresponding latent variable matrix of quality variable；T indicates the corresponding latent variable matrix of process variable；
F () indicates a nonlinear function；h1, h2…haThe corresponding residual error of a latent variable that respectively indicates the 1st, 2 ...；It indicates
The predicted value of a-th of latent variable corresponding to quality variable；Indicate a regression coefficient；K(tA, i, ta) indicate
The corresponding kernel function of a-th of latent variable；B indicates prediction residual.
Step 2: the data newly obtained during acquisition cement slurry predecomposition process operation, using obtained in step 1
Prediction model carries out on-line prediction, specifically:
The process data X newly obtained in 2.1 collection processnewWith qualitative data Ynew, collected new data is carried out small
Wave denoising.
Wherein, XpnewNew process data after indicating Wavelet Denoising Method, YpnewNew mass number after indicating Wavelet Denoising Method
According to.
2.1 are pre-processed using Orthogonal Signal Correction Analyze method.
t0new=Xpnewwnew
In formula, tsnewIndicate process data XnewCorresponding first principal component, is calculated using Principal Component Analysis；tnnew
It indicates along YnewDirection and t0newOrthogonal vector；The weight vectors of w expression X；t0newIndicate XnewScore matrix；p0new
Indicate load vector；XOSCnewIt indicates by orthogonal signalling decomposition algorithm treated process data.
2.2 handle new collected data using Partial Least Squares, calculate the latent variable of new data.
tt=XOSCnewwnew
unew=Ypnewqnew
In formula, ttIndicate XOSCnewCorresponding principal component；pnewIndicate XOSCnewCorresponding load vector；qnewIndicate that quality becomes
Measure corresponding load vector；unewIndicate the corresponding score vector of quality variable.
2.3 carrying out on-line prediction using prediction model
In formula,Indicate process quality data YnewPredicted value；Q indicates the corresponding moment of load of process quality data
Battle array.FnewIndicate prediction residual.
Claims (1)
1. a kind of cement slurry predecomposition process disturbance reduces qualitative forecasting method, it is characterised in that this method includes following step
It is rapid:
Step 1. acquires the data of sensor during cement slurry predecomposition, is handled and establishes prediction model；Specific step
Suddenly it is:
Data during 1.1 acquisition cement slurry predecomposition carry out off-line modeling, and data are divided into two classes, process data X and matter
Data Y is measured, one shares N number of sample；
X=[x1,x2,…xm],x1,x2…xm∈RN×1
Y=[y1,y2,…yp],y1,y2…yp∈RN×1
Wherein, x1,x2,…xmRespectively indicate the material concentration during cement slurry predecomposition, reaction pressure, reaction temperature ...
This m variable of valve opening, y1,y2…ypProduct quality is respectively indicated, proportion of products ... product grain this p related to quality
Variable；
1.2 use the noise in Wavelet Denoising Method removal process data；
Wherein, XpProcess data after indicating Wavelet Denoising Method, YpQualitative data after indicating Wavelet Denoising Method；lxIndicate process data
Threshold value, lyIndicate the threshold value of qualitative data；
1.3 pre-process collected initial data using Orthogonal Signal Correction Analyze algorithm；
t0=Xpw
In formula, tsIt indicates the corresponding first principal component of process data X, is calculated using Principal Component Analysis；tnewIt indicates along Y
Direction and t0Orthogonal vector；The weight vectors of w expression X；t0Indicate the score matrix of X；p0Indicate load vector；XOSCIt indicates
By orthogonal signalling decomposition algorithm treated process data；
1.4 are handled data obtained in step 1.3 using Partial Least Squares；
T=XOSCw
U=Ypq
In formula, t indicates XOSCCorresponding principal component；P indicates XOSCCorresponding load vector；Q indicates the corresponding load of quality variable
Vector；U indicates the corresponding score vector of quality variable；
1.5, by step 1.1-1.4, obtain prediction model:
In formula, a=1,2 ... A indicate principal component index；taIndicate a-th of latent variable corresponding with process variable X；paIt indicates
Corresponding a-th of the load vector of process variable；The residual error of E expression process variable；uaIndicate quality variable it is corresponding a-th it is potential
Variable；qaIndicate a-th of load vector corresponding with quality variable；The residual error of F expression quality variable；
1.6, which are introduced into algorithm of support vector machine, is modified the model in step 1.5:
U=f (T)+H=[f1(t1),f2(t2),…fa(ta)]+[h1,h2,…ha]
ua=fa(ta)+ha, a=1,2 ... A
In formula, U indicates the corresponding latent variable matrix of quality variable；T indicates the corresponding latent variable matrix of process variable；f
() indicates a nonlinear function；h1,h2…haThe 1,2nd is respectively indicated ... the corresponding residual error of a latent variable；It indicates
The predicted value of a-th of latent variable corresponding to quality variable；Indicate a regression coefficient；K(ta,i,ta) indicate
The corresponding kernel function of a-th of latent variable；B indicates prediction residual；
Step 2: the data newly obtained during acquisition cement slurry predecomposition process operation are predicted using obtained in step 1
Model carries out on-line prediction, specifically:
The process data X newly obtained in 2.1 collection processnewWith qualitative data Ynew, small echo is carried out to collected new data and is gone
It makes an uproar processing；
Wherein, XpnewNew process data after indicating Wavelet Denoising Method, YpnewNew qualitative data after indicating Wavelet Denoising Method；
2.1 are pre-processed using Orthogonal Signal Correction Analyze method；
t0new=Xpnewwnew
In formula, tsnewIndicate process data XnewCorresponding first principal component, is calculated using Principal Component Analysis；tnnewIt indicates
Along YnewDirection and t0newOrthogonal vector；The weight vectors of w expression X；t0newIndicate XnewScore matrix；p0newIt indicates
Load vector；XOSCnewIt indicates by orthogonal signalling decomposition algorithm treated process data；
2.2 handle new collected data using Partial Least Squares, calculate the latent variable of new data；
tt=XoSCnewwnew
unew=Ypnewqnew
In formula, ttIndicate XOSCnewCorresponding principal component；pnewIndicate XOSCnewCorresponding load vector；qnewIndicate quality variable pair
The load vector answered；unewIndicate the corresponding score vector of quality variable；
2.3 carry out on-line prediction using prediction model
In formula,Indicate process quality data YnewPredicted value；Q indicates the corresponding load matrix of process quality data；Fnew
Indicate prediction residual.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910608006.XA CN110471374B (en) | 2019-07-08 | 2019-07-08 | Prediction method for disturbance reduction quality in cement raw material pre-decomposition process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910608006.XA CN110471374B (en) | 2019-07-08 | 2019-07-08 | Prediction method for disturbance reduction quality in cement raw material pre-decomposition process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110471374A true CN110471374A (en) | 2019-11-19 |
| CN110471374B CN110471374B (en) | 2020-07-28 |
Family
ID=68506790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910608006.XA Active CN110471374B (en) | 2019-07-08 | 2019-07-08 | Prediction method for disturbance reduction quality in cement raw material pre-decomposition process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110471374B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1492084A1 (en) * | 2003-06-25 | 2004-12-29 | Psytechnics Ltd | Binaural quality assessment apparatus and method |
| CN101872433A (en) * | 2010-05-21 | 2010-10-27 | 杭州电子科技大学 | Beer flavor prediction method based on neural network technique |
| CN103951299A (en) * | 2014-04-17 | 2014-07-30 | 中国科学院青海盐湖研究所 | Preparation method and application of magnesium phosphate cement |
| CN106778008A (en) * | 2016-12-28 | 2017-05-31 | 中南大学 | A kind of method for optimizing hydrocracking process reaction condition |
| CN108805325A (en) * | 2018-04-11 | 2018-11-13 | 杭州电子科技大学 | A kind of Production-Plan and scheduling integrated optimization method |
| CN109634104A (en) * | 2019-01-28 | 2019-04-16 | 辽宁工业大学 | The intelligent optimal control device and its control method of cement raw mix proportioning process |
-
2019
- 2019-07-08 CN CN201910608006.XA patent/CN110471374B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1492084A1 (en) * | 2003-06-25 | 2004-12-29 | Psytechnics Ltd | Binaural quality assessment apparatus and method |
| CN101872433A (en) * | 2010-05-21 | 2010-10-27 | 杭州电子科技大学 | Beer flavor prediction method based on neural network technique |
| CN103951299A (en) * | 2014-04-17 | 2014-07-30 | 中国科学院青海盐湖研究所 | Preparation method and application of magnesium phosphate cement |
| CN106778008A (en) * | 2016-12-28 | 2017-05-31 | 中南大学 | A kind of method for optimizing hydrocracking process reaction condition |
| CN108805325A (en) * | 2018-04-11 | 2018-11-13 | 杭州电子科技大学 | A kind of Production-Plan and scheduling integrated optimization method |
| CN109634104A (en) * | 2019-01-28 | 2019-04-16 | 辽宁工业大学 | The intelligent optimal control device and its control method of cement raw mix proportioning process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110471374B (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101482750B (en) | Cobalt oxalate granularity prediction method in hydrometallurgical synthesis process | |
| CN106933099B (en) | Coal preparation plant thickener and filter press medicament adding cooperative control system | |
| CN108629091B (en) | Mill load parameter prediction method based on selective fusion multichannel mechanical signal frequency spectrum multi-feature subset | |
| CN110263488B (en) | Industrial rubber compound Mooney viscosity soft measurement method based on integrated instant learning | |
| Dai et al. | Hardware-in-the-loop simulation platform for supervisory control of mineral grinding process | |
| TW201816533A (en) | Production process analysis method | |
| US3972710A (en) | Method of upgrading tantalum and niobium concentration in slags | |
| CN110908361B (en) | Fermentation process soft measurement method based on online twin support vector regression | |
| CN110471374A (en) | A kind of cement slurry predecomposition process disturbance reduction qualitative forecasting method | |
| Ueda et al. | A study of springback in the stretch bending of channels | |
| Li et al. | Soft sensor and expert control for blending and digestion process in alumina metallurgical industry | |
| CN105404147B (en) | A kind of self-optimizing control method of hydrometallurgy gold cyanidation-leaching process | |
| Costa et al. | N4sid method applied to obtain a discrete-time linear state space system as a mathematical model of a jaw crusher prototype | |
| CN110794672B (en) | Explicit control method for furnace temperature of decomposing furnace in cement production process | |
| CN109242224A (en) | A kind of novel chemical procedure quality prediction technique | |
| Hulbert | The state of the art in the control of milling circuits | |
| CN112598618B (en) | Image recognition technology-based ore feeding amount prediction method for mill | |
| Navia et al. | On dealing with measured disturbances in the modifier adaptation method for real-time optimization | |
| Lott et al. | Fuzzy decision support system for the calibration of laboratory-scale mill press parameters | |
| Beynon et al. | Inclusion of metallurgical development in the modelling of industrial hot rolling of metals | |
| CN207026994U (en) | A kind of fastener process equipment based on automatic technology design | |
| Bonvin et al. | Optimal operation of batch processes via the tracking of active constraints | |
| CN107451386A (en) | Grinding process mill power online soft sensor method | |
| Ruppen | A contribution to the implementation of adaptive optimal operation for discontinnuous chemical reactors | |
| RU2379384C1 (en) | Method of control of efficiency of breaking process |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210628 Address after: 311831 Huandong Industrial Park, Zhuji Economic Development Zone, Shaoxing City, Zhejiang Province Patentee after: ZHEJIANG BONYEAR TECHNOLOGY Co.,Ltd. Address before: 310018 No. 2 street, Xiasha Higher Education Zone, Hangzhou, Zhejiang Patentee before: HANGZHOU DIANZI University Patentee before: ZHEJIANG BONYEAR TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210726 Address after: Room 1906, building S3, Herui Science Park, 475 Changhe Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province, 310051 Patentee after: Zhongsai Bangye (Hangzhou) Intelligent Technology Co.,Ltd. Address before: 311831 Huandong Industrial Park, Zhuji Economic Development Zone, Shaoxing City, Zhejiang Province Patentee before: ZHEJIANG BONYEAR TECHNOLOGY Co.,Ltd. |