CN101963802B - Virtual measurement method in batch manufacture procedure and system therefor - Google Patents
Virtual measurement method in batch manufacture procedure and system therefor Download PDFInfo
- Publication number
- CN101963802B CN101963802B CN201010262348XA CN201010262348A CN101963802B CN 101963802 B CN101963802 B CN 101963802B CN 201010262348X A CN201010262348X A CN 201010262348XA CN 201010262348 A CN201010262348 A CN 201010262348A CN 101963802 B CN101963802 B CN 101963802B
- Authority
- CN
- China
- Prior art keywords
- module
- wafer
- data
- measurement
- manufacture procedure
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- 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]
Landscapes
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to a virtual measurement method in a batch manufacture procedure and a system therefor. The system comprises a manufacture procedure machine which performs a manufacture procedure on a batch of wafer to be processed and then outputs the processed wafers. Output ports of the manufacture procedure machine are respectively connected with a manufacture procedure control system and an error detection and classification system; an output part close to the manufacture procedure control system is provided with a measurement machine; the manufacture procedure control system, the error detection and classification system and the output port of the measurement machine are respectively with a data receiving engine module input port and a data receiving engine module output port is connected with a computer. In the invention, the advanced manufacture procedure control is adopted, the wafers is analyzed and processed timely by using the industrial statistics method, and then key variables affecting the change of the manufacture procedure can be found out; in addition, a rolling time window is utilized to capture working condition changes of the system, and translates or drifts the adverse impact on modelling so as to improve robustness of the model, reduce cycle time for processing the wafers, improve operation of the manufacture procedure tools and reduce burdens on the measurement tools and the cost of the wafers; moreover. The inference model established by the method and the system of the invention is suitable for fault diagnosis of the manufacture procedure.
Description
Technical field
The present invention relates to a kind of virtual measurement technical field of batch process, relate in particular to the virtual measurement predictor method and the system of the quality management of semiconductor manufacturing or TFT-LCD (thin film transistor (TFT)-LCD) processing procedure.
Background technology
At present; In semi-conductive batch process, employing to be the sampling observation method detect the product quality of producing board, that is: in a card casket that contains 25 wafer, extract 2～3 wafer out and carry out actual measurement; Whether stable with monitoring processing procedure quality, and the quality of decision product.The defective of this detection method is: if certain batch product is out of joint in the process of making; Must wait and just can find when to be detected; And the processing procedure of this moment possibly produce quite a few batches defective products; That is: go wrong performance variable with processing procedure of the quality that detects product changes certain hysteresis is arranged in time, and how in the shortest time, to dope the quality of product, is semiconductor maker's open question always.
Along with the semiconductor subassembly size is further dwindled, more need use strict process control, such as: the control between wafer and wafer needs the wafer of each sheet all to need measured.This just requires to use a large amount of survey instruments and increases considerably time production cycle, and inevitable generation measurement delay, causes complicated control problem.
Number of patent application is 200610108408.6; Name is called " method and system that prediction model was estimated and set up to the virtual measurement of semiconductor manufacturing " and discloses a kind of method of setting up prediction model; The defective of the method is: need set up a plurality of prediction models; And select best prediction model with index of correlation, if when a plurality of indexs of correlation of estimating all are lower than given threshold value, the no-output value can appear in system.In addition, need to cover the prediction model of all operating modes of board, otherwise can reduce the precision of prediction of model.
Number of patent application is 200610149890.8, name is called " method for measurement and virtual measurement system " and proposes a kind of method of setting up the virtual measurement model based on neural network; Its defective is: when the operating mode of system changes; Variation during such as adjustment processing procedure formula, this model need again, and training could produce predicted value accurately.
Summary of the invention
The objective of the invention is for time lag of overcoming system measurements in the above-mentioned prior art, need set up a plurality of prediction models or the deficiency of training network structure again in advance; Propose a kind of virtual measurement method that is applied to the quality control of batch process, in time, fast and accurately predict the usefulness of batch process and the yield of product.
Another object of the present invention is to propose a kind of simple in structure, virtual measurement system of measuring accurate batch process.
The technical scheme that virtual measurement of the present invention system adopts is: comprise the process work bench of a collection of wafer to be processed being carried out the wafer after the output processing behind the processing procedure; The output of said process work bench is joined with processing procedure control system and error detection and categorizing system respectively through signal wire; Output near the processing procedure control system is provided with measurement platform; Said processing procedure control system, error detection and the output of categorizing system, measurement platform are connected the input of Data Receiving engine modules respectively through signal wire, the output of Data Receiving engine modules connects computing machine; Said processing procedure control system monitoring process also writes down corresponding data; Said measurement platform is positioned in wafer lower position and the wafer after the processing after the processing sampling extracted and measures wafer and obtain the actual amount measured value; Said error detection and categorizing system produce error detection and grouped data after the batch wafer after the processing is accomplished; Said Data Receiving engine modules receives all data of error detection and categorizing system, processing procedure control system and measurement platform and delivers to computing machine; Said computing machine is carried out the virtual measurement automated procedures, data is carried out the prediction of quality of completion wafer after the screening of pre-treatment and data.
The technical scheme that virtual measurement method of the present invention adopts is to have following steps successively:
The 1st step: all state variable data that receive error detection and categorizing system and processing procedure control system by the Data Receiving engine modules;
The 2nd step: the handled of accomplishing all state variable data by characteristic extracting module and standardized module;
The 3rd step: judge whether to arrive the update time of model,, then directly jumped to for the 7th step if do not arrive;
The 4th step: the mass number value that is received measurement platform measurement sampling measurement wafer by data after the rolling time window module combination standard resume module and Data Receiving engine modules obtains the modeling data under the new data window;
The 5th step: regression algorithm obtains the key variables that influence the wafer quality after processing to select module to adopt progressively by key variables;
The 6th step: combine the 5th to go on foot the key variables that obtain by the multiple regression module, utilize least-squares algorithm to obtain prediction model;
The 7th step: the wafer of not sampling in the wafer after processing is carried out quality prediction by estimating the measurement module.
Advantage of the present invention is:
1, combine error detection and categorizing system, the advanced processing procedure of employing to control, wafer is in time analyzed and processing with the industrial statistics method; Finding influences the key variables that processing procedure changes, with the working conditions change that the timely capture systems of rolling time window takes place, and translation and the adverse effect of drift to modeling; Improve the robustness of model; Reduce the cycle length of wafer-process, improve the running of process tool, reduce the burden of measuring tool and the cost of wafer; Cut the waste, can be applicable to the semiconductor fabrication and the TFT-LCD processing procedure of form of ownership.
2, utilize progressively recurrence to set up multivariate statistical model; Through setting the number of the key variables that the threshold value decision selected; The complexity of consideration model is stipulated during by design, and progressively regression algorithm is fit to when the data of sampling are considerably less, use, and can use in the incipient stage of processing procedure; Progressively regression algorithm can be avoided the problem of overfitting effectively; And being well suited for computer program carries out; The variable of being selected has tangible physical significance, and the selection of variable is easy to combine with system actual constraint, and the inference pattern of being set up is applicable to the fault diagnosis of processing procedure.
3, with existing virtual measurement compared with techniques, the present invention catches the variation of board with the rolling time window data, can in time find the adjustment of board, and the primary variables that causes that current wafer makes a variation can be provided, and is convenient to analyze reason.
4, model structure is simple, need not increase the additional hardware condition, and model is roll to form, and need not to set up in advance a plurality of prediction models, also need not resemble the neural network again the training network structure to improve accuracy of predicting.
Description of drawings
Fig. 1 is the configuration diagram of virtual measurement system;
Fig. 2 is the connection synoptic diagram of each module of having in Fig. 1 system;
Fig. 3 is the displayed map of rolling time window module 220 among Fig. 2;
Fig. 4 is the process flow diagram of virtual measurement method;
Among the figure: 110. process work bench; 120. a collection of wafer to be processed; 130. error detection and categorizing system; 140. Data Receiving engine modules; 150. computing machine; 160. measurement platform; 170. the wafer after the processing; 180. sampling measures wafer; 190. processing procedure control system; 210. characteristics of variables extraction module; 220. moving window module; 230. key variables are selected module; 240. multivariate regression module; 250. virtual measurement modular type; 310. the time window of last time; 340. this event window.
Embodiment
As shown in Figure 1: the virtual measurement system of this batch process comprises: a process work bench 110, processing procedure control system (APC) 190, error detection and categorizing system (FDC) 130, measurement platform 160, Data Receiving engine modules 140, be used for the computing machine 150 of virtual measurement program run.At output measurement platform 160 is set near processing procedure control system 190.The output of process work bench 110 links to each other with categorizing system 130 with error detection with processing procedure control system 190 respectively through signal wire.The output of processing procedure control system 190, error detection and categorizing system 130, measurement platform 160 is connected the input of Data Receiving engine modules 140 respectively through signal wire, and the output of Data Receiving engine modules 140 connects computing machine 150.
A collection of wafer to be processed 120 is positioned at the input position of process work bench 110, exports the wafer 170 after processing after 110 pairs of a collection of wafers 120 to be processed of process work bench are carried out a processing procedure, processing procedure control system 190 monitoring process, and write down corresponding data.Measurement platform 160 is positioned at wafer 170 lower positions after the processing, and the sampling that wafer 170 the insides after processing obtain measures wafer 180 and obtains the actual amount measured value.Error detection and categorizing system 130 produce error detection and grouped data after the wafer after the processing 170 is accomplished in batches.Data Receiving engine modules 140 receives all data of error detection and categorizing system 130, processing procedure control system 190 and measurement platform 160, and delivers to virtual measurement computing machine 150; Virtual measurement computing machine 150 is carried out the virtual measurement automated procedures, data is carried out the prediction of quality of completion wafer after the screening of pre-treatment and data.
As shown in Figure 2, have characteristic extracting module 210 and standardized module 211 in the Data Receiving engine modules 140, the output of characteristic extracting module 210 connects the input of standardized module 211.Having the rolling time window module 220, the key variables that are connected in series successively in the computing machine 150 selects module 220, multiple regression module 240 and estimates to measure module 250; The output of standardized module 211 connects the input of rolling time window module 220.When a collection of wafer 120 to be processed was processed on process work bench 110, characteristics of variables extraction module 210 extracted each parameter of processing procedure control system 190 and error detection and categorizing system 130 with the eigenwert (X that changes process time
1, X
2..., X
n), carrying out standardization by the eigenwert of 211 pairs of extractions of standardized module then, simultaneous computer 150 obtains the measuring value y of the sampling measurement wafer 180 of measurement platform 160, with eigenwert (X
1, X
2..., X
n) make up { X with measuring value y
1, X
2..., X
nY}; And upgrade the data set of training samples by wherein the rolling time window module that is connected with standardized module 211 220; The output of rolling time window module 220 is connected the input that key variables are selected module 220; Key variables select module 220 to obtain under new window, influencing the key variables of virtual measurement system, select the multiple regression module 240 of module 220 to obtain the parameter of prediction model by connecting key variables again, measure the quality that module 250 is not surveyed wafer through estimating at last.
The function of above-mentioned characteristic extracting module 210 is: these can characterize the variation characteristic of variable in the whole machining process process to obtain under mean value, median, maximum value and minimal value that sampling measures the wafer 170 after wafer 180 and the processing, the line area etc.
Standardized module 211 is to each characteristic variable
All sample value (x
I, 1, x
I, 2..., x
I, N) carry out the z-mark, that is: deduct average (μ
x), divided by standard deviation (σ
x).
In the processing procedure of routine, process work bench 10 wears out along with operation, drifts about; Perhaps because the mistake of process work bench 110 itself; Perhaps changed different operation person; Cause process work bench 110 that drift phenomenon takes place; The result that conventional virtual measurement automated procedures can't operate or estimate because of these disturbances is incorrect, and therefore, the present invention also proposes the generation that a kind of rolling time window is avoided the problems referred to above.Rolling time window module 220 is undertaken by the Data Update criterion, and with reference to Fig. 3, the wafer that at first preceding single sample is arrived is formed data window 310; And utilize the data modeling in this data window 310, and provide the estimated value of sample to be tested 320, wait for that measurement platform 160 obtains after the measured value; Up-to-date data are added among the training sample, and the oldest data are shifted out, obtain new data window 340; Estimate the sample to be tested 330 of this moment, so come and go, model is constantly upgraded.The data number of the rolling time window of this preferred embodiments is 50, and upgrading length is 10, in actual use, can do suitable adjustment according to different objects.
Key variables select module 230 to pick out the crucial parameter that the influence sampling measures wafer 180 quality by stepwise regression method.All predictive variables are done the action of a screening; Be not that all variablees are brought simultaneously and predicted; But according to the size of interpretability, the influence of inspecting each predictive variable progressively will be chosen as the final employed variable of model to the contributive predictive variable of model.Each step choosing is advanced or the foundation of rejecting variable is partial F value (a F value partially).Suppose that the partial F value of working as certain parameter is greater than certain definite value F
InShi Ze selects the progressive die type with this variable, and when the partial F value of variable less than certain setting value F
OutShi Ze eliminates model with this variable.Usually, have following relation of plane to exist:
F
in≥F
out (2)
Select module through crucial parameter, can obtain the crucial parameter
of influence processing wafer 170 quality
Multiple regression module 240 nationalitys are used least-squares algorithm by the multiple regression procedure of statistics, obtain the parameter beta of prediction model:
Estimate and measure 250 of modules and select the wafer 170 parameter results
after 230 pairs of processing of module to utilize the prediction model parameter beta, the quality of the wafer of not sampled according to characteristic extracting module 210 and key variables:
As shown in Figure 4: the present invention is come a certain process results of predicting wafer by the virtual measurement automated procedures; Receive the information of the service part of a certain process tool processing earlier; Wherein this information comprises a plurality of in order to the variable of representing this process characteristics and the measuring value of sampling measurement wafer 180; From the information of this collection, extract the eigenwert of each procedure of processing of processing procedure again, all extract non-key variable in characteristics by the statistical analysis technique filtering, in order to the noise information that the reduces information influence that makes a variation together; The mistake that reduces predictor method takes place, and is obtained the prediction model of virtual measurement at last by multiple regression procedure.
Above-mentioned method for measurement specifically is to carry out according to the following steps:
The 1st step: the data S410 that collects processing procedure control system 190 and error detection and categorizing system 130; This process is the related data that is received error detection and categorizing system 130 and processing procedure control system 160 by Data Receiving engine modules 140, and content comprises the wafer 170 all state variables (as: flow, pressure, temperature, voltage etc.) in process work bench 110 and processing procedure control system 190 after the processing.
The 2nd step: data pre-service S420.This process is to be accomplished by characteristic extracting module 210 and standardized module 211, receives Data Receiving engine modules 140 to such an extent that all state variable data are handled accordingly.
The 3rd step: S430 update time that whether arrives model.If do not arrive, then directly jumped to for the 7th step.
The 4th step: get data S440 in the rolling time window.Receive measurement platform 160 by data after 211 processing of rolling time window module 220 combination standard modules and Data Receiving engine modules 140 and measure the quality numerical value that sampling measures wafers 180; And adopt method shown in Figure 3, obtain the modeling data under the new data window 340.
The 5th step: key variables are selected S450.Select module 230 to adopt progressively regression algorithm by key variables, obtain the key variables of wafer 170 quality after influence is processed.
The 6th step: multiple regression S460.Combine the 5th to go on foot the key variables that obtain by multiple regression module 240, utilize least-squares algorithm, obtain the prediction model S470 of Prediction System.
The 7th step: predicted value output S480.Carry out quality prediction by estimating the wafer of not sampling in the wafer 170 that measures after 250 pairs of processing of module.
Claims (3)
1. the virtual measurement system of a batch process; Comprise process work bench (110) to the wafer (170) after the output processing behind a collection of wafer to be processed (120) execution one processing procedure; It is characterized in that: the output of said process work bench (110) is joined with processing procedure control system (190) and error detection and categorizing system (130) respectively through signal wire; Output near processing procedure control system (190) is provided with measurement platform (160); Said processing procedure control system (190), error detection and the output of categorizing system (130), measurement platform (160) are connected the input of Data Receiving engine modules (140) respectively through signal wire, the output of Data Receiving engine modules (140) connects computing machine (150);
Said processing procedure control system (190) monitoring process also writes down corresponding data;
Said measurement platform (160) is positioned at the sampling of extracting in wafer (170) lower position and wafer (170) lining after processing after the processing and measures wafer (180) and obtain the actual amount measured value;
Said error detection and categorizing system (130) produce error detection and grouped data after the wafer after the processing (170) is accomplished in batches;
Said Data Receiving engine modules (140) receives all data of error detection and categorizing system (130), processing procedure control system (190) and measurement platform (160) and delivers to computing machine (150);
Said computing machine (150) is carried out the virtual measurement automated procedures, data is carried out the prediction of quality of completion wafer after the screening of pre-treatment and data;
Have characteristic extracting module (210) and standardized module (211) in the said Data Receiving engine modules (140), the output of characteristic extracting module (210) connects the input of standardized module (211); Having the rolling time window module (220), the key variables that are connected in series successively in the said computing machine (150) selects module (220), multiple regression module (240) and estimates to measure module (250); The output of said standardized module (211) connects the input of rolling time window module (220).
2. the virtual measurement system of batch process according to claim 1 is characterized in that:
Wafer (170) after said characteristic extracting module (210) is obtained sampling measurement wafer (180) and processed is at whole machining process process feature variable;
Said standardized module (211) deducts behind the average again divided by standard deviation to all sample values of each characteristic variable;
Said rolling time window module (220) is at first formed data window (310) modeling with the wafer that preceding single sample arrives; Provide the estimated value of sample to be tested (320); Wait for that again measurement platform (160) obtains after the measured value up-to-date data being added in the training sample, the oldest data are shifted out obtain new data window (340) at last, estimate another sample to be tested (330) of this moment; So come and go, model is brought in constant renewal in;
Said key variables select module (230) to obtain the crucial parameter of influence processing wafer (170) quality;
Said multiple regression module (240) obtains the prediction model parameter with least-squares algorithm;
Said estimating measures module (250) and utilizes the do not sampled quality of wafer of said prediction model parameter.
3. virtual measurement method of the virtual measurement system of batch process according to claim 1 is characterized in that adopting successively following steps:
The 1st step: all state variable data that receive error detection and categorizing system (130) and processing procedure control system (160) by Data Receiving engine modules (140);
The 2nd step: the handled of accomplishing all state variable data by characteristic extracting module (210) and standardized module (211);
The 3rd step: judge whether to arrive the update time of model,, then directly jumped to for the 7th step if do not arrive;
The 4th step: the mass number value that is received measurement platform (160) measurement sampling measurement wafer (180) by data after rolling time window module (220) combination standard module (211) processing and Data Receiving engine modules (140) obtains the modeling data under the new data window (340);
The 5th step: regression algorithm obtains the key variables that influence wafer (170) quality after processing to select module (230) to adopt progressively by key variables;
The 6th step: combine the 5th to go on foot the key variables that obtain by multiple regression module (240), utilize least-squares algorithm to obtain prediction model;
The 7th step: the wafer of not sampling in the wafer (170) after processing is carried out quality prediction by estimating measurement module (250).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010262348XA CN101963802B (en) | 2010-08-25 | 2010-08-25 | Virtual measurement method in batch manufacture procedure and system therefor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010262348XA CN101963802B (en) | 2010-08-25 | 2010-08-25 | Virtual measurement method in batch manufacture procedure and system therefor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101963802A CN101963802A (en) | 2011-02-02 |
| CN101963802B true CN101963802B (en) | 2012-08-15 |
Family
ID=43516715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010262348XA Expired - Fee Related CN101963802B (en) | 2010-08-25 | 2010-08-25 | Virtual measurement method in batch manufacture procedure and system therefor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101963802B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110808222A (en) * | 2019-11-15 | 2020-02-18 | 深圳市华星光电半导体显示技术有限公司 | Control method and device of manufacturing equipment |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278714B (en) * | 2013-05-15 | 2015-10-28 | 江苏大学 | A kind of virtual measurement method and system mixing processing procedure |
| CN105573279B (en) * | 2015-12-31 | 2018-12-21 | 广州中国科学院先进技术研究所 | A method of industrial processes are monitored based on sensing data |
| TWI625615B (en) * | 2016-11-29 | 2018-06-01 | 財團法人工業技術研究院 | Prediction model building method and associated predicting method and computer software product |
| US10393802B2 (en) * | 2017-06-14 | 2019-08-27 | Nuvoton Technology Corporation | System and method for adaptive testing of semiconductor product |
| CN108942639A (en) * | 2018-06-11 | 2018-12-07 | 上海华力微电子有限公司 | A kind of feedback of making technology parameter |
| CN111190393B (en) * | 2018-11-14 | 2021-07-23 | 长鑫存储技术有限公司 | Semiconductor process automation control method and device |
| TWI829807B (en) * | 2018-11-30 | 2024-01-21 | 日商東京威力科創股份有限公司 | Hypothetical measurement equipment, hypothetical measurement methods and hypothetical measurement procedures for manufacturing processes |
| US11899417B2 (en) | 2019-05-02 | 2024-02-13 | Fisher-Rosemount Systems, Inc. | Methods and apparatus to implement predictive analytics for continuous control system processes |
| CN112397404B (en) * | 2019-08-14 | 2022-03-22 | 长鑫存储技术有限公司 | Semiconductor process detection method and system |
| CN112563152B (en) * | 2019-09-25 | 2023-01-31 | 长鑫存储技术有限公司 | Manufacturing method and system |
| US11551954B2 (en) | 2019-11-21 | 2023-01-10 | Nanya Technology Corporation | Advanced process control system |
| CN113094893A (en) * | 2021-04-06 | 2021-07-09 | 江苏大学 | Wafer quality virtual measurement method and device, computer equipment and storage medium |
| CN113191017B (en) * | 2021-05-21 | 2022-12-27 | 成都数之联科技股份有限公司 | Virtual measurement model construction method, virtual measurement method, system, electronic device and computer-readable storage medium |
| CN113269658B (en) * | 2021-07-16 | 2022-01-21 | 北京达佳互联信息技术有限公司 | Method, device and equipment for estimating production time of core data and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1916796A (en) * | 2005-08-16 | 2007-02-21 | 力晶半导体股份有限公司 | System and method for controlling batches in layers of reaction chamber |
| CN101140464A (en) * | 2007-10-11 | 2008-03-12 | 中国科学院长春光学精密机械与物理研究所 | Observe and control equipment digital communications system |
| US7505836B2 (en) * | 2001-09-25 | 2009-03-17 | Yamaha Marine Kabushiki Kaisha | Inspection system for watercraft |
| CN101792981A (en) * | 2010-03-23 | 2010-08-04 | 华南理工大学 | Optimization control system for energy system of drying part of paper machine |
| CN201540479U (en) * | 2009-06-26 | 2010-08-04 | 徐州凯莫尔重工科技有限公司 | CAN-BUS control system of spreading machine |
-
2010
- 2010-08-25 CN CN201010262348XA patent/CN101963802B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7505836B2 (en) * | 2001-09-25 | 2009-03-17 | Yamaha Marine Kabushiki Kaisha | Inspection system for watercraft |
| CN1916796A (en) * | 2005-08-16 | 2007-02-21 | 力晶半导体股份有限公司 | System and method for controlling batches in layers of reaction chamber |
| CN101140464A (en) * | 2007-10-11 | 2008-03-12 | 中国科学院长春光学精密机械与物理研究所 | Observe and control equipment digital communications system |
| CN201540479U (en) * | 2009-06-26 | 2010-08-04 | 徐州凯莫尔重工科技有限公司 | CAN-BUS control system of spreading machine |
| CN101792981A (en) * | 2010-03-23 | 2010-08-04 | 华南理工大学 | Optimization control system for energy system of drying part of paper machine |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110808222A (en) * | 2019-11-15 | 2020-02-18 | 深圳市华星光电半导体显示技术有限公司 | Control method and device of manufacturing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101963802A (en) | 2011-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101963802B (en) | Virtual measurement method in batch manufacture procedure and system therefor | |
| CN105955241B (en) | A kind of quality fault localization method based on joint data-driven production process | |
| CN110303380B (en) | Method for predicting residual life of cutter of numerical control machine tool | |
| EP3055747B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN107146004A (en) | A kind of slag milling system health status identifying system and method based on data mining | |
| CN105511445A (en) | Multi-modal process fault detection method based on local neighbor standardization matrix | |
| CN105629958B (en) | A kind of batch process method for diagnosing faults based on sub-period MPCA SVM | |
| EP3055746B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| CN109948860A (en) | A kind of mechanical system method for predicting residual useful life and system | |
| CN113657221B (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
| CN109446189A (en) | A kind of technological parameter outlier detection system and method | |
| CN102789545A (en) | Method for predicating remaining life of turbine engine based on degradation model matching | |
| JP4568786B2 (en) | Factor analysis apparatus and factor analysis method | |
| CN109389314B (en) | Quality soft measurement and monitoring method based on optimal neighbor component analysis | |
| CN111046582A (en) | Nuclear power station diesel generating set coil temperature early warning method and system | |
| CN101118422A (en) | Virtual measurement prediction generated by semi-conductor, method for establishing prediction model and system | |
| CN115407753B (en) | Industrial fault diagnosis method for multi-variable weighting integrated learning | |
| CN113094893A (en) | Wafer quality virtual measurement method and device, computer equipment and storage medium | |
| US8649990B2 (en) | Method for detecting variance in semiconductor processes | |
| CN116186499A (en) | Numerical control machining surface roughness prediction method | |
| CN115034094A (en) | Prediction method and system for operation state of metal processing machine tool | |
| Brophy et al. | AI-based condition monitoring of the drilling process | |
| CN103278714B (en) | A kind of virtual measurement method and system mixing processing procedure | |
| CN116821828A (en) | Multi-dimensional time sequence prediction method based on industrial data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120815 Termination date: 20140825 |
|
| EXPY | Termination of patent right or utility model |