CN111948992B - Method and system for performing multistage progressive modeling on industrial batch type big data - Google Patents
Method and system for performing multistage progressive modeling on industrial batch type big data Download PDFInfo
- Publication number
- CN111948992B CN111948992B CN202010779095.7A CN202010779095A CN111948992B CN 111948992 B CN111948992 B CN 111948992B CN 202010779095 A CN202010779095 A CN 202010779095A CN 111948992 B CN111948992 B CN 111948992B
- Authority
- CN
- China
- Prior art keywords
- modeling
- data
- stand
- alone
- machine
- 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
Images
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]
- G05B19/41885—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 modeling, simulation of the manufacturing system
-
- 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
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
-
- 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 provides a method and a system for multi-stage progressive modeling of industrial batch type big data, which comprises the following single-machine modeling steps: performing single-machine data modeling on data of a single device; and (3) transmitting a model result: uploading the model result of each single machine data modeling to a local area center; and (3) comprehensive modeling step: and carrying out secondary modeling on the model result uploaded to the local center. The method solves the problem of data isolated island, and the modeling of the whole cluster does not need to upload the data of a single machine to the cloud end at first, so that the analysis and model results which are the same as the analysis and model results in the mode of collecting mass data at first can be obtained under the scene of not depending on common and private cloud construction and enterprise data platform construction; furthermore, the implementation of the invention can greatly reduce the requirement for enterprise-level large-scale data storage, and through the use of modern AI technology and modeling means, the intelligent factory management advocated by industry 4.0 is realized.
Description
Technical Field
The invention relates to the field of industrial big data, in particular to a method and a system for performing multistage progressive modeling on industrial batch type big data.
Background
The future industry 4.0 front trends are no longer single clouds up. The trend of future industry 4.0 is that industrial data applications will be solved on-the-fly, so developed countries need to implement on-the-cloud + on-the-fly solutions; for China, the problems of manufacturing quality and benefit can be solved with extremely low cost from the machine side, the machine runs quickly in small steps and is gradual, the construction cost for a cloud platform is reduced to a level capable of being widely borne, and the implementation time is greatly advanced.
The existing leading edge solution focuses on summarizing massive second-level data on each device to a minute or hour level, and mechanizing functions such as monitoring and early warning; however, in order to meet modeling requirements, summary data, although greatly reduced in magnitude, is currently uploaded to the cloud.
The invention of the prior document CN105095436B discloses an automatic modeling method for data source data, which comprises the following steps: multiple data source access and table structure analysis: accessing data in different data sources, and analyzing the table structures of all tables in each data source; identifying a business object for a table structure in a data source table: traversing all tables in a data source, extracting attribute lists needing modeling, and setting a business object name, a business object type and a business object aggregation mode for the attributes in each attribute list; merging the similar business objects: summarizing the attributes of all set business objects and merging the same items; analyzing the business object and modeling to generate a modeling structure set: and modeling the attribute of the set service object according to the set parameters, modeling the attribute of the unset service object according to a modeling rule, wherein the modeling rule comprises that the numerical attribute is marked as measurement, the non-numerical attribute is marked as dimensionality, and merging the same type service objects. The data modeling can be conveniently carried out, and the analysis of mass data of users is facilitated. But the above scheme does not solve the data islanding problem.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method and a system for performing multi-stage progressive modeling on industrial batch type big data.
The invention provides a multistage progressive modeling method for industrial batch type big data, which comprises the following steps:
a single machine modeling step: performing single-machine data modeling on data of a single device;
and (3) single-machine model result transmission: uploading the model result of each single machine data modeling to a local area center;
and (3) comprehensive modeling step: and comprehensively modeling the model result uploaded to the local center.
Preferably, the single device is configured with an intelligent device for modeling, and the local area center includes a local area server, and the local area server is in communication connection with the intelligent device.
Preferably, the stand-alone modeling step comprises:
tracking and identifying: tracking and identifying the operation scene and the movement scene transition of a single device, and continuously tracking a target index;
data real-time docking: carrying out cross-time-interval butt joint on the single-machine data, and accumulating and establishing complete modeling data;
single machine data modeling step: modeling by using single machine data;
an abnormity monitoring and early warning step: monitoring and early warning the abnormal running equipment or the abnormal product output situation by using the model;
and (3) factor analysis step: and carrying out quantitative analysis and execution guidance on the influencing factors of the target indexes according to the service requirements.
Preferably, secondary modeling is carried out on the models uploaded by the single machines on the local area server, and an overall model based on all single machine information is formed.
Preferably, the method further comprises the step of: managing the equipment and the local center, wherein the managed content comprises any one or more of the following items:
-an authorization management;
-hardware and software upgrade capacity expansion management;
-interacting with a cloud platform, managing uniformly;
-tracking, pre-warning, alarm management of personnel behaviour and equipment operating conditions.
The invention provides a big data multi-level progressive modeling system, which comprises the following modules:
a stand-alone modeling module: performing single-machine data modeling on data of a single device;
a model result transmission module: uploading the model result of each single machine data modeling to a local area center;
a comprehensive modeling module: and comprehensively modeling the model result uploaded to the local center.
Preferably, the single device is configured with an intelligent device for modeling, and the local area center includes a local area server, and the local area server is in communication connection with the intelligent device.
Preferably, the stand-alone modeling module comprises:
a tracking identification module: tracking and identifying the operation scene and the movement scene transition of a single device, and continuously tracking a target index;
the data real-time butt joint module: carrying out cross-time-interval butt joint on the single-machine data, and accumulating and establishing complete modeling data;
a stand-alone data modeling module: modeling by using single machine data;
an abnormity monitoring and early warning module: monitoring and early warning the abnormal running equipment or the abnormal product output situation by using the model;
a factor analysis module: and carrying out quantitative analysis and execution guidance on the influencing factors of the target indexes according to the service requirements.
Preferably, secondary modeling is carried out on the models uploaded by the single machines on the local area server, and an overall model based on all single machine information is formed.
Preferably, the system further comprises a management module: managing the equipment and the local center, wherein the managed content comprises any one or more of the following items:
-an authorization management;
-hardware upgrade capacity expansion management;
-interacting with a cloud platform, managing uniformly;
-tracking, pre-warning, alarm management of personnel behaviour and equipment operating conditions.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, model-level data, not modeling data, is only transmitted to the local area server through single-machine modeling at the machine side, and then secondary modeling is carried out, so that a large amount of data transmission is avoided, a method system for carrying out comprehensive modeling by using multi-machine sub-models is realized, and the problem of data isolated island is solved;
2. according to the modeling method, the data of a single machine does not need to be uploaded to the cloud end in the modeling of the whole cluster, the application of the cloud end is unnecessary for most manufacturers, and only an enterprise-level local storage scheme is needed, so that the same analysis and model results as those of a mode of collecting mass data at first can be obtained under the scene of not depending on common and private cloud construction and enterprise data platform construction;
3. the invention can greatly reduce the requirement on enterprise-level large-scale data storage, and realizes intelligent factory management advocated by industry 4.0 by using modern AI technology and modeling means.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic illustration of conventional modeling data preparation;
FIGS. 2 and 3 are schematic diagrams of the relationship between the edge tablet and the local server according to the present invention;
FIG. 4 is a schematic diagram of a modeling result process for a stand-alone device;
FIG. 5 is a schematic diagram of two-level modeling based on a stand-alone equipment model;
FIG. 6 is a flow chart of AI standalone modeling.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
Data islanding is a fundamental problem in big data modeling. At present, large-scale internet of things and cloud construction are carried out, and the fundamental purpose of the large-scale internet of things and cloud construction is to collect scattered data at one position, so that island data of equipment level are collected into integral data. The invention innovatively utilizes a hierarchical modeling system to perform secondary summary modeling on the model result based on the island data on the local area server through a specific modeling mode, thereby directly solving the problem of data island, namely the one-sidedness problem caused by independent modeling of single-machine data, and reducing or eliminating the dependence of industrial 4.0 process on the construction of a factory-level local or cloud big data platform.
The existing algorithm has great limitation, and the existing algorithm is realized by a regression equation:
Y＝C1+A11*X1+A12*X2+……+A1N*XN。
in the above formula, Y is a variable for finding explanation, such as defective rate and what is concerned; x1, X2, …, XN on the right of the equation are explanatory variables, i.e., causes for different results for Y. A11, A12, … and A1N are parameters obtained in model building; these parameters were obtained by a modeling process on the data, indicating the influence of the various explanatory variables on the variation of Y.
Specifically, as shown in fig. 1, the traditional modeling data has many dimensions, and the many dimensions can generate a huge amount of combined states, creating a laboratory environment for specially manufacturing the modeling data is deeply limited, and the time, the scarce human resources and the capital investment are multiplied for the processes with a large number of machines; the cost is higher for multi-process products. For the above reasons, modeling has long been difficult to implement in the product manufacturing field, and also limits manufacturing big data applications.
The invention provides a method and a system for multistage progressive modeling of industrial batch type big data, wherein the method comprises stand-alone equipment, a tablet personal computer and a local area server, the modeling is realized by adopting an AI algorithm, specifically, the tablet personal computer is installed on the stand-alone equipment or is arranged near the stand-alone equipment, and software programs and hardware preinstalled in the tablet personal computer comprise but are not limited to:
hardware and programs for acquisition, cleaning and standardization of stand-alone equipment data; the intermediate and final results of the data preparation process can be displayed or a PDF report can be generated through a page;
the UI display is used for monitoring and early warning the running state of the stand-alone equipment in real time, generating a model of early warning information and setting logic of a threshold value;
a unit for storing modeling data and model results for necessary parts in the raw data of the single-machine equipment;
AI programs and UI interfaces for modeling;
a unit for data output.
The local area server is arranged in a workshop office, is used for comprehensive modeling and directly provides services for the tablet personal computer, including management, software upgrading and comprehensive monitoring.
FIG. 6 is a detailed illustration of a standalone AI modeling process, specifically, AI modeling includes:
step 1: AI programming tracks the combination of each dimension in the production process in real time, and records the result of the target variable under each combination; each cell represents a dimension combination + target variable result; different cells can be formed along with the change of the dimension combination and the target variable in production; the honeycomb data is accumulated continuously to form honeycomb balls, namely the same dimension combination can appear for a plurality of times in different time periods.
Step 2: AI programming will delete the same combination of dimensional states to form a sequence, and cells with different state combinations constitute different cell sequences.
And step 3: for each cell sequence in step 2, the AI programming will reorganize and sort the data of each cell, integrate the data modeling this group of cells (same dimension combination), and form a model result curve.
And 4, step 4: uploading a model curve formed by the single device in the step 3 to a local area machine; AI programming on the local area machine carries out summary operation on curves from different single-machine equipment according to the same dimension, and a model for the cluster level is obtained. The algorithm solves the restriction that the regression model can not be summarized from a single-machine model to a cluster model.
The local server management mainly comprises the management of model versions and the updating of models. The upgraded version needs to be pushed remotely from the software provider to the local server and through the local server to the edge machine.
The local server comprehensively monitors the content comprising the following aspects:
monitoring whether the software and hardware running states of the local area server and the edge machine are normal or not; the algorithm in this patent contains these functions.
And monitoring the operation of each single machine device. And each single-side machine can display abnormal operation alarm, so that field personnel can take measures, and the same information can also appear on a display screen of the local area server. Meanwhile, the server can perform cross-equipment and cross-process comprehensive monitoring.
The local server can drive a plurality of terminal machines, and under the unified authorization management, different business or functional personnel carry out the following model application operations: formula optimization, production scheduling optimization, energy consumption optimization and cost optimization.
The invention adopts AI algorithm, tracks and automatically identifies the operation scene and the transition of the equipment;
continuously tracking target indexes such as defective rate, fault rate and track in each equipment operation scene;
transmitting the single-machine model to a local server for comprehensive modeling of online data;
the modeling of the equipment, whether real-time modeling or delayed modeling, is completed in the tablet computer;
monitoring, early warning and alarming of equipment operation abnormity or product abnormity are realized by using the established model and AI algorithm;
performing cross-period docking of modeling data, avoiding the dependence of traditional modeling on laboratory operation, namely building complete modeling data by accumulating real-time data in a real environment for a long time;
and receiving the instruction and service of the local area server, and uploading the machine side model to the local area server, thereby solving the problem of data island.
The invention realizes data integration through AI algorithm:
the dynamic real-time classification of the operation scene is adopted, so that the 'laboratory' data taking process in the traditional modeling is replaced;
summarizing the second-level data for modeling, and only reserving short-term high-frequency (second-level) data for inspection;
automatic switching of track tracking, namely establishing a starting point of a new track after the operation scene changes;
the same operation scene is automatically jointed at different periods to form longer sequence data, so that the life cycle process and long-term time sequence factors can be dynamically simulated.
The invention realizes dynamic modeling and real-time tracking, early warning and alarming through AI algorithm:
automatically recognizing a normal state track and an abnormal track for each index according to historical operating data;
comparing the real-time operation index with a normal track, determining early warning and alarming states through an algorithm and a rule, and displaying reasons at the same time;
and the sufficiency of the data scale is automatically identified, and the dimension is automatically reduced when the data is insufficient.
The method and system for multi-level progressive modeling of big data according to the present invention are described below by way of specific examples, and with reference to fig. 2, it is assumed that a production process of a product goes through N steps from start to end, i.e., step 1, step 2, … …, step N; each process has a plurality of single-machine equipment, such as M in the process 1 and L in the process N. Taking the process N as an example, an edge panel (equivalent to a tablet computer) is configured for each single-machine device, and is a basic module; each stand-alone unit is wirelessly connected to a local server, which is a local module. Multiple processes typically share a local area module; the local area module further performs wireless or wired interaction with the enterprise-level database or the cloud platform.
The AI algorithm included in the present application relates to the execution and implementation at both the tablet and local module levels. The local area machine uses a unified management platform in modeling and model application to uniformly manage each flat machine in each procedure, and the content includes but is not limited to authorization management, hardware upgrading and capacity expansion, interaction with a cloud platform and unified model management; on the monitoring level, the monitoring system comprises but is not limited to tracking, early warning and alarming of personnel behaviors and equipment operation conditions.
Compared with all the currently known modeling modes, the model adopted in the patent application has fundamental innovation on a design framework; the innovation enables a model established based on single-machine equipment data, not massive data, to be aggregated and secondarily modeled after being uploaded to a local area server; the obtained result is that the method for establishing the Internet of things and the big data platform in advance is completely the same.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (8)
1. A method for carrying out multistage progressive modeling on industrial batch type big data is characterized by comprising the following steps:
a single machine modeling step: performing stand-alone data modeling aiming at data of stand-alone equipment;
and (3) single-machine model result transmission: uploading the model result of each single machine data modeling to a local area center;
and (3) comprehensive modeling step: carrying out secondary modeling on the model result uploaded to the local center;
the stand-alone modeling step comprises:
tracking and identifying: tracking and identifying the operation scene and the movement scene transition of a single device, and continuously tracking a target index;
data real-time docking: carrying out cross-time-interval butt joint on the single-machine data, and accumulating and establishing complete modeling data;
single machine data modeling step: modeling by using single machine data;
an abnormity monitoring and early warning step: monitoring and early warning the abnormal running equipment or the abnormal product output situation by using the model;
and (3) factor analysis step: and carrying out quantitative analysis and execution guidance on the influencing factors of the target indexes according to the service requirements.
2. The method for multi-level progressive modeling of industrial batch-type big data according to claim 1, wherein a single machine is configured with an intelligent device for modeling, the local center comprises a local server, and the local server is in communication connection with the intelligent device.
3. The method for modeling industrial batch-type big data in a multi-level progressive manner according to claim 1, wherein the models uploaded by each single machine are modeled secondarily on the local server to form an overall model based on information of all single machines.
4. The method for multi-level progressive modeling of industrial batch-type big data according to claim 1, further comprising the step of managing: the stand-alone equipment and the local area center are managed, and the managed content comprises any one or more of the following items:
-an authorization management;
-upgrade extension management of hardware and software;
-interacting with a cloud platform, managing uniformly;
-tracking, pre-warning, alarm management of personnel behaviour and equipment operating conditions.
5. A system for multi-stage progressive modeling of industrial batch type big data is characterized by comprising the following modules:
a stand-alone modeling module: performing stand-alone data modeling on data of stand-alone equipment;
a model result transmission module: uploading the model result of each single machine data modeling to a local area center;
a comprehensive modeling module: comprehensively modeling the model result uploaded to the local center;
the stand-alone modeling module comprises:
a tracking identification module: tracking and identifying the operation scene and the movement scene transition of a single device, and continuously tracking a target index;
the data real-time butt joint module: carrying out cross-time-interval butt joint on the single-machine data, and accumulating and establishing complete modeling data;
a stand-alone data modeling module: modeling by using single machine data;
an abnormity monitoring and early warning module: monitoring and early warning the abnormal running equipment or the abnormal product output situation by using the model;
a factor analysis module: and carrying out quantitative analysis and execution guidance on the influencing factors of the target indexes according to the service requirements.
6. The system for multi-level progressive modeling of industrial batch-type big data according to claim 5, wherein the stand-alone device is configured with an intelligent device for modeling, the local center comprises a local server, and the local server is in communication connection with the intelligent device.
7. The system for multi-level progressive modeling of industrial batch-type big data according to claim 5, wherein the models uploaded by each single machine are secondarily modeled on the local server to form an overall model based on information of all single machines.
8. The system for multi-level progressive modeling of industrial batch-type big data according to claim 7, wherein the content of management includes any one or more of:
-an authorization management;
-hardware and software upgrade capacity expansion management;
-interacting with a cloud platform, managing uniformly;
-tracking, pre-warning, alarm management of personnel behaviour and equipment operating conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010779095.7A CN111948992B (en) | 2020-08-05 | 2020-08-05 | Method and system for performing multistage progressive modeling on industrial batch type big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010779095.7A CN111948992B (en) | 2020-08-05 | 2020-08-05 | Method and system for performing multistage progressive modeling on industrial batch type big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111948992A CN111948992A (en) | 2020-11-17 |
| CN111948992B true CN111948992B (en) | 2021-09-10 |
Family
ID=73338014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010779095.7A Active CN111948992B (en) | 2020-08-05 | 2020-08-05 | Method and system for performing multistage progressive modeling on industrial batch type big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111948992B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1605958A (en) * | 2004-11-16 | 2005-04-13 | 冶金自动化研究设计院 | Combined modeling method and system for complex industrial process |
| CN105095436A (en) * | 2015-07-23 | 2015-11-25 | 苏州国云数据科技有限公司 | Automatic modeling method for data of data sources |
| CN107423823A (en) * | 2017-08-11 | 2017-12-01 | 成都优易数据有限公司 | A kind of machine learning Modeling Platform architecture design method based on R language |
| CN109409922A (en) * | 2018-08-31 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Data aggregate modeling method, device, computer equipment and storage medium |
| CN110689448A (en) * | 2019-09-30 | 2020-01-14 | 石化盈科信息技术有限责任公司 | Factory modeling method and system for process industry |
| CN111461818A (en) * | 2020-03-20 | 2020-07-28 | 上海数据交易中心有限公司 | Data transaction method and data transaction platform |
-
2020
- 2020-08-05 CN CN202010779095.7A patent/CN111948992B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1605958A (en) * | 2004-11-16 | 2005-04-13 | 冶金自动化研究设计院 | Combined modeling method and system for complex industrial process |
| CN105095436A (en) * | 2015-07-23 | 2015-11-25 | 苏州国云数据科技有限公司 | Automatic modeling method for data of data sources |
| CN107423823A (en) * | 2017-08-11 | 2017-12-01 | 成都优易数据有限公司 | A kind of machine learning Modeling Platform architecture design method based on R language |
| CN109409922A (en) * | 2018-08-31 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Data aggregate modeling method, device, computer equipment and storage medium |
| CN110689448A (en) * | 2019-09-30 | 2020-01-14 | 石化盈科信息技术有限责任公司 | Factory modeling method and system for process industry |
| CN111461818A (en) * | 2020-03-20 | 2020-07-28 | 上海数据交易中心有限公司 | Data transaction method and data transaction platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111948992A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Peng et al. | A hybrid data mining approach on BIM-based building operation and maintenance | |
| US11275357B2 (en) | Event analyzing device, event analyzing system, event analyzing method, and non-transitory computer readable storage medium | |
| CN107909300A (en) | Intelligent plant management platform and method | |
| CN101639687B (en) | Integrated technology quality control system and realization method thereof | |
| CN103425085A (en) | Data-warehouse-based industrial control upper computer management system and data processing method | |
| CN111948992B (en) | Method and system for performing multistage progressive modeling on industrial batch type big data | |
| Wen et al. | A dual energy benchmarking methodology for energy-efficient production planning and operation of discrete manufacturing systems using data mining techniques | |
| CN116166655B (en) | Big data cleaning system | |
| CN116993052A (en) | Intelligent factory production on-line monitoring analysis system based on digital twinning | |
| CN109886434B (en) | Intelligent drilling platform maintenance system and method | |
| CN114676015A (en) | Automatic generation method and system for monitoring and self-checking report of operation state of measurement and control device | |
| CN102231081B (en) | Energy utilization state diagnosis method for process industrial equipment | |
| Zhang | Portrait analysis of power transmission line for smart grid based on external data association fusion | |
| CN115623872A (en) | Data processing method, device, equipment and storage medium | |
| CN112560325A (en) | Prediction method, system, equipment and storage medium for battery swapping service | |
| CN114968744B (en) | Implementation method and system based on financial industry capacity management prediction analysis AI algorithm | |
| TWI673723B (en) | Intelligent pre-diagnosis and health management system and method | |
| Hu et al. | Digital twin–based dynamic prediction and simulation model of carbon efficiency in gear hobbing process | |
| CN115034695B (en) | Real-time monitoring method for production and operation conditions of manufacturing and hatching enterprises based on big data | |
| Zhang et al. | Batch sizing control of a flow shop based on the entropy-function theorems | |
| CN116468292A (en) | Nuclear power equipment health assessment method and system based on data analysis | |
| CN117194456A (en) | Policy registration management system | |
| CN105787580A (en) | Periodic report refreshing completion time prediction method and device | |
| Chen | Research on the overall planning of digital workshop for equipment manufacturing | |
| CN117391579A (en) | Equipment information analysis method, system and storage medium |
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 |