CN112270613A - Manufacturing process big data modeling method for whole-process manufacturing management and control of manufacturing enterprise - Google Patents
Manufacturing process big data modeling method for whole-process manufacturing management and control of manufacturing enterprise Download PDFInfo
- Publication number
- CN112270613A CN112270613A CN202011047636.3A CN202011047636A CN112270613A CN 112270613 A CN112270613 A CN 112270613A CN 202011047636 A CN202011047636 A CN 202011047636A CN 112270613 A CN112270613 A CN 112270613A
- Authority
- CN
- China
- Prior art keywords
- data
- manufacturing
- service
- management
- business
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 189
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000007726 management method Methods 0.000 claims abstract description 83
- 238000013461 design Methods 0.000 claims abstract description 63
- 238000013499 data model Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims abstract description 4
- 239000000463 material Substances 0.000 claims description 47
- 238000012545 processing Methods 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 7
- 238000012417 linear regression Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 239000000306 component Substances 0.000 claims description 3
- 230000008094 contradictory effect Effects 0.000 claims description 3
- 239000008358 core component Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000003860 storage Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Fuzzy Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
Abstract
The invention discloses a manufacturing process big data modeling method facing manufacturing enterprise whole-process manufacturing management control, which comprises the steps of preprocessing relevant data generated by a manufacturing enterprise in the business including design, manufacture, management and service, then analyzing big data, adjusting data changed due to the influence of the business including design, management and service in the manufacturing process, and establishing the relation between manufacturing business and the business including design, management and service; and finally, establishing a big data model which is through with the whole system full value chain and faces to design, manufacture, management and service. The invention breaks through the problem that the existing data model is only oriented to single business, establishes a big data model which is mainly based on manufacturing business data and is complete in value chain communication with other business data, assists a manufacturing enterprise to make decisions, reasonably plans a production plan, improves the production efficiency of the enterprise and promotes the economic benefit increase of the enterprise.
Description
Technical Field
The invention relates to the technical field of production and manufacturing and big data, in particular to a manufacturing process big data modeling method for whole-process manufacturing management and control of a manufacturing enterprise.
Background
The manufacturing industry is one of the prop industries of national economy, and is the embodiment for realizing the modernization guarantee and the comprehensive national force. With the increasing development of economy and science and technology, the data volume generated by modern manufacturing industry is exponentially increased, so that the potential and value of big data are gradually accepted and received by society, and the combination of the big data and the manufacturing industry promotes the comprehensive reform of design, management, manufacturing and service modes of the manufacturing industry. However, such manufacturing data usually has characteristics of multiple sources, heterogeneity, complexity and the like, which is also one of the main problems that the manufacturing enterprise needs to face when modeling the big data.
The existing big data model is only a single service for a manufacturing enterprise, does not consider the correlation among the services, neglects the influence of the services such as design, management and service on the manufacturing process, and does not establish the incidence relation between the manufacturing service and other services, so that the data among the services of the manufacturing enterprise is not fully utilized, and the manufacturing process of the whole flow cannot be strictly controlled and reasonably planned.
In addition, most of the existing data modeling methods are based on a determined data mode, the uncertainty of multi-source, heterogeneous and complex manufacturing data of a manufacturing enterprise cannot be effectively coped with, a model covering multiple services such as design, management, manufacturing, service and the like is not established, and the manufacturing process cannot be comprehensively and effectively described.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a manufacturing process big data modeling method for whole-process manufacturing management and control of a manufacturing enterprise, and solves the problems that the existing big data model is only a single business oriented to the manufacturing enterprise, cannot effectively deal with the uncertainty of multi-source, heterogeneous and complex manufacturing data in the manufacturing enterprise, does not consider the correlation among businesses, neglects the influence of the businesses such as design, management and service on the manufacturing process, does not establish the incidence relation between the manufacturing business and other businesses, and the like.
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
a manufacturing process big data modeling method for manufacturing enterprise full-process manufacturing management and control comprises the following steps:
s1, acquiring relevant data generated by the manufacturing enterprise in the business including design, manufacture, management and service;
s2, preprocessing the data acquired in the step S1;
s3, carrying out big data analysis on the data preprocessed in the step S2, adjusting the data changed due to the influence of the design, management and service services in the manufacturing process, and establishing the relation between the manufacturing service and the design, management and service services;
and S4, establishing a big data model which is through the whole system full value chain and is oriented to design, manufacture, management and service.
Further, the data preprocessing performed in step S2 includes data integration, data filtering, and data cleansing.
Further, the data integration can provide more complete and comprehensive data sharing for manufacturing business by effectively integrating various types of related data generated by manufacturing enterprises in the business including design, manufacture, management and service logically or physically.
Furthermore, the data screening screens out related data and eliminates irrelevant variables by analyzing the possibility of influence on the manufacturing process data in the three service data of design, management and service.
Further, the data cleansing includes: processing data with missing information; processing logically unreasonable data; processing mutually contradictory data; duplicate data is processed.
Further, the step S3 is performed based on a distributed message system Kafka for publishing subscriptions, where core components of the system Kafka mainly include:
the theme is a logic concept of storing messages and is regarded as a message set; the system Kafka classifies the messages according to different themes, the themes are divided into three themes of design, management and service, and the service data of different data sources are put into different themes;
the information is the most basic unit of message queue communication; the producer publishes information to the topic, and the consumer can obtain the information from the subscribed topic for consumption;
a producer, which is a data or message source responsible for sending data or messages to a certain topic; the service data preprocessed in the step S2 is used as a producer, and sends data to three subjects of design, management, and service according to the difference of data sources;
the consumer is a party which subscribes to the topic and extracts the message or data from the topic for consumption, namely, the party analyzes and processes the data in the system Kafka; the consumer immediately processes the acquired dynamic service data from the theme of the system Kafka, namely, the selected consumer is required to have a stream processing framework to deal with a real-time scene;
the Spark Streaming is a Spark-based component for calculating the real-time data stream, rapidly analyzes and feeds back dynamic data in real time, selects the Spark Streaming as a consumer, acquires data of a theme in the system Kafka on the basis of the Spark Streaming, and processes the stream data in real time.
Further, big data analysis is carried out on the obtained data resources, and data changed due to other business influences in the manufacturing process is adjusted, and the method mainly comprises the following steps:
the Spark Streaming reads data information including a design drawing and a design scheme acquired by a design service side from a design theme of the system Kafka, calls an API (application programming interface) to stream data acquired from the design side to perform statistical analysis on data information including the number of personnel, materials and equipment required by an order, disassembles the order, and sends the number of the materials required by order manufacturing to a management service side;
after receiving the material demand request, the management business end delivers the materials required by the manufacturing process, and if the materials required by the manufacturing are not in sufficient inventory, the materials are purchased according to the requirements; the material distribution data information of the management service end is sent to the management theme of the system Kafka after being preprocessed in the step S2;
the Spark Streaming reads the material information obtained by the management service end from the management theme of the system Kafka, calls the API to statistically analyze the distributed material quantity information, and sends the information to the manufacturing service end; adjusting material quantity information in the manufacturing business, reasonably distributing and producing personnel, equipment and materials according to the material quantity information in the manufacturing process, and accurately matching the materials required by the manufactured products to ensure the smooth operation of the manufacturing process;
the management business delivers the produced and manufactured part of products to the service business, and the service business delivers the products to the customers in time to deliver and deliver orders; the customer finds that flaws exist in the used product and feeds the flaws back to the service business; after the data preprocessing of step S2, the feedback information of the service end is sent to the service theme of the system Kafka;
the Spark Streaming reads feedback information obtained by a service business end from a service theme of the system Kafka, calls an API (application programming interface) to classify the feedback information according to products, then performs statistical analysis, traces product problems through analysis, and timely adjusts information including personnel, equipment and environment for problems in a manufacturing link; if the manufactured product needs to be produced again, repeating the material demand request and the material distribution step to finish the production and the manufacture.
Further, the step S4 is a specific step of establishing a big data model for designing, manufacturing, managing, and serving the whole system full value chain link as follows:
establishing a multiple linear regression model according to the data, wherein the model form of the multiple linear regression is as follows:
yi=β0+β1xi1+β2xi2+…+βpxip+εi;
in the above formula, y is a dependent variable, β is a undetermined coefficient, x is an independent variable, and ε is a residue term;
performing parameter estimation by a least square method to obtain beta and epsilon satisfying an equation, wherein the method comprises the following steps:
using formulasCalculating the actual observed value yi(i-1, 2,3, …, n) and the estimated value, the sum of squares of the differences is minimal, and the curve fitting is optimal, i.e. the residual sum of squares RSS is minimized;
finally, obtaining a coefficient which meets an equation and has the minimum sum of squares of errors with actual data, and finding out the optimal function matching;
after the coefficients are found, their regression significance needs to be checked:
suppose that: h0:βi=0sH1:βiNot equal to 0, i.e. assuming that β is all 0 or not all 0;
test statistics, where SST is the sum of the squares of the sums, SSE is the sum of the squares of the errors, p is the number of arguments, n is the number of packets of actual data:
through the constructed F statistic, the larger the F is, the better the fitting effect is; comparing the calculated F value with the value obtained by table look-up, if F is present>FWatch (A)Then, the regression equation is considered to be significant enough; and finally obtaining an optimal regression equation through significance test.
Compared with the prior art, the principle and the advantages of the scheme are as follows:
according to the scheme, relevant data generated by a manufacturing enterprise in the business including design, manufacture, management and service is preprocessed, then big data analysis is carried out, data changed due to the influence of the business including design, management and service in the manufacturing process is adjusted, and the relation between the manufacturing business and the design, management and service business is established; and finally, establishing a big data model which is through with the whole system full value chain and faces to design, manufacture, management and service.
The scheme breaks through the problem that the existing data model is only oriented to a single service, and the data generated by each service is not split, but the manufacturing service is used as a central point to establish a connection with other services to form a whole. The influence brought by other business data is considered in the manufacturing process, the data is taken out and fed back to the data of the manufacturing business, the data in the manufacturing process is adjusted in time, the data generated by other businesses are used in the manufacturing process, the decision making of a manufacturing enterprise is assisted, the production plan is reasonably planned, the production efficiency of the enterprise is improved, and the economic benefit increase of the enterprise is promoted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the services required for the embodiments or the technical solutions in the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing management and control according to the present invention;
FIG. 2 is a schematic diagram of data cleansing in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a manufacturing process for manufacturing enterprise-oriented full-flow manufacturing management and control in an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a core model of a manufacturing process for manufacturing enterprise-oriented full-flow manufacturing control according to an embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to specific examples:
as shown in fig. 1, the manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing management and control according to this embodiment includes the following steps:
s1, acquiring relevant data generated by the manufacturing enterprise in the business including design, manufacture, management and service; wherein the content of the first and second substances,
the design is the first link of the life cycle of a product, manufacturing enterprises select CAD software to design a product model scheme according to product types, and the CAD software is introduced into CAE software in modes of data interfaces and the like to perform finite element analysis of parts and complete machines and motion analysis of mechanisms, so that product structures are designed, results are simulated, and the product structures are put into production and manufacturing.
The big data sources for design business of manufacturing enterprises mainly include: CAD, CAE software simulation system data, design drawings, design schemes, design cases, design models and the like.
The management is taken as an important link of the life cycle of the product, the WMS system is used for carrying out full process control management on all the storage links, bar code label serial number management can be realized on the storage, transparent, timely and fine storage information is provided, management on the warehouse and the supply chain of an enterprise is realized, and accurate goods feeding and storage control of the enterprise are ensured.
The big data sources for the management business of a manufacturing enterprise mainly include: WMS system data, material inventory information, supply chain data, after-sales information, etc.
The service is a necessary link of a product life cycle, a manufacturing enterprise establishes a service platform through a website, WeChat, APP and other modes, unified management is carried out on service requests, the arrangement of after-sale data is facilitated, decision data is provided for the enterprise, and meanwhile, the excellent service is an effective means for establishing enterprise brands and propagating images and is one of enterprise core competitiveness.
The big data sources for the service business of the manufacturing enterprise mainly include: the system comprises product running state information, client feedback data, customer service records, order information, logistics distribution information and the like.
S2, preprocessing the data acquired in the step S1;
data generated by software and systems such as CAD, CAE and WMS cannot be directly identified and used by an MES system used in the manufacturing process, so certain data processing including data integration, data screening, data cleaning and the like is required to be carried out on other acquired business data resources, and data support is provided for establishing a big data model which is through and faces to the design, manufacture, management and service overall system full-value chain.
Various related data generated by manufacturing enterprises in the business of design, management, service and the like are converted regularly and effectively integrated logically or physically to form data or format which can be identified and used, thereby providing more complete and comprehensive data sharing for manufacturing business.
After the acquired data resources are integrated, data generated by other businesses of a manufacturing enterprise can be identified and used, but the manufacturing businesses are not affected by each mass of complex data, so that the data resources need to be screened, relevant data are screened out by analyzing the possibility of affecting the manufacturing process data in the business data such as design, management, service and the like, and irrelevant variables are removed.
As missing or singular values may be generated in the process of acquiring business data such as design, management, and service, the data resource needs to be cleaned to ensure the integrity and correctness of the data and avoid some unnecessary problems caused by incorrect data in the following process, as shown in fig. 2, the main steps of cleaning the data resource include:
processing of information missing data: for such data having information missing, the complementary missing information may be rewritten within a prescribed time. For data which can not be supplemented with information, the elimination processing is directly carried out because the elimination of individual samples in a large amount of data can not influence the final result.
Logically unreasonable data handling: it is also possible to modify logically unreasonable data within a prescribed time. And directly eliminating the data which is not corrected.
Processing mutually contradictory data; conflicting data may interfere with the analysis of the data to reach an erroneous conclusion, and thus the rejection process is performed directly.
And (3) processing repeated data: and if the data duplication is judged to exist through a certain rule, merging the duplicated data.
S3, carrying out big data analysis on the data preprocessed in the step S2, adjusting the data changed due to the influence of the design, management and service services in the manufacturing process, and establishing the relation between the manufacturing service and the design, management and service services;
this step is performed based on a distributed message system Kafka for publishing and subscribing, and the core components of the system Kafka mainly include:
the theme is a logic concept of storing messages and is regarded as a message set; the system Kafka classifies the messages according to different themes, the themes are divided into three themes of design, management and service, and the service data of different data sources are put into different themes;
the information is the most basic unit of message queue communication; the producer publishes information to the topic, and the consumer can obtain the information from the subscribed topic for consumption;
a producer, which is a data or message source responsible for sending data or messages to a certain topic; the service data preprocessed in the step S2 is used as a producer, and sends data to three subjects of design, management, and service according to the difference of data sources;
the consumer is a party which subscribes to the topic and extracts the message or data from the topic for consumption, namely, the party analyzes and processes the data in the system Kafka; the consumer immediately processes the acquired dynamic service data from the theme of the system Kafka, namely, the selected consumer is required to have a stream processing framework to deal with a real-time scene;
the Spark Streaming is a Spark-based component for calculating the real-time data stream, rapidly analyzes and feeds back dynamic data in real time, selects the Spark Streaming as a consumer, acquires data of a theme in the system Kafka on the basis of the Spark Streaming, and processes the stream data in real time.
As shown in fig. 3, the main steps of analyzing big data of the acquired data resource and adjusting data changed due to other business influences in the manufacturing process include:
the Spark Streaming reads data information including a design drawing and a design scheme acquired by a design service side from a design theme of the system Kafka, calls an API (application programming interface) to stream data acquired from the design side to perform statistical analysis on data information including the number of personnel, materials and equipment required by an order, disassembles the order, and sends the number of the materials required by order manufacturing to a management service side;
after receiving the material demand request, the management business end delivers the materials required by the manufacturing process, and if the materials required by the manufacturing are not in sufficient inventory, the materials are purchased according to the requirements; the material distribution data information of the management service end is sent to the management theme of the system Kafka after being preprocessed in the step S2;
the Spark Streaming reads the material information obtained by the management service end from the management theme of the system Kafka, calls the API to statistically analyze the distributed material quantity information, and sends the information to the manufacturing service end; adjusting material quantity information in the manufacturing business, reasonably distributing and producing personnel, equipment and materials according to the material quantity information in the manufacturing process, and accurately matching the materials required by the manufactured products to ensure the smooth operation of the manufacturing process;
the management business delivers the produced and manufactured part of products to the service business, and the service business delivers the products to the customers in time to deliver and deliver orders; the customer finds that flaws exist in the used product and feeds the flaws back to the service business; after the data preprocessing of step S2, the feedback information of the service end is sent to the service theme of the system Kafka;
the Spark Streaming reads feedback information obtained by a service business end from a service theme of the system Kafka, calls an API (application programming interface) to classify the feedback information according to products, then performs statistical analysis, traces product problems through analysis, and timely adjusts information including personnel, equipment and environment for problems in a manufacturing link; if the manufactured product needs to be produced again, repeating the material demand request and the material distribution step to finish the production and the manufacture.
And S4, establishing a big data model which is through the whole system full value chain and is oriented to design, manufacture, management and service.
Referring to fig. 4, the data in the manufacturing process not only interacts with the business data such as design, management and service, but also affects the production efficiency of the manufacturing enterprise. The data can be used for establishing a big data model which is oriented to design, manufacture, management and service and is through with the whole system full value chain, predicting data such as production condition, production progress and the like, helping manufacturing enterprises to evaluate progress, making production plans and guaranteeing production, and the method comprises the following steps:
establishing a multiple linear regression model according to the data, wherein the model form of the multiple linear regression is as follows:
yi=β0+β1xi1+β2xi2+…+βpxip+εi
where y is a dependent variable, β is a regression coefficient, x is an independent variable, and ε is a residue term.
In this embodiment, 5 data are selected, and the 5 data are respectively: personnel information, equipment data, material information, production data and environmental information. And taking the production and manufacturing conditions of the manufacturing enterprises as dependent variables, and taking the 5 data as independent variables to perform multiple linear regression.
Performing parameter estimation by a least square method to obtain beta and epsilon satisfying an equation, wherein the method comprises the following steps:
using formulasCalculating the actual observed value yi(i-1, 2,3, …, n) and the estimated value, the sum of squares of the differences is minimal, and the curve fitting is optimal, i.e. the residual sum of squares RSS is minimized;
finally, a coefficient which meets the equation and has the minimum sum of squares of errors with actual data is obtained, and the optimal function matching is found out.
After the coefficients are found, their regression significance needs to be checked:
suppose that: h0:βi=0sH1:βiNot equal to 0, i.e. assuming that beta is all 0 or not all 0
Test statistics, where SST is the sum of the squares of the sums, SSE is the sum of the squares of the errors, p is the number of arguments, n is the number of packets of actual data:
through the constructed F statistic, the larger the F is, the better the fitting effect is; comparing the calculated F value with the value obtained by table look-up, if F is present>FWatch (A)Then, the regression equation is considered to be significant enough; and finally obtaining an optimal regression equation through significance test.
The embodiment breaks through the problem that the existing data model is only oriented to a single service, and the data generated by each service is not split, but the manufacturing service is taken as a central point to establish a connection with other services to form a whole. The influence brought by other business data is considered in the manufacturing process, the data is taken out and fed back to the data of the manufacturing business, the data in the manufacturing process is adjusted in time, the data generated by other businesses are used in the manufacturing process, the decision making of a manufacturing enterprise is assisted, the production plan is reasonably planned, the production efficiency of the enterprise is improved, and the economic benefit increase of the enterprise is promoted.
The above-mentioned embodiments are merely preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, so that variations based on the shape and principle of the present invention should be covered within the scope of the present invention.
Claims (8)
1. A manufacturing process big data modeling method for manufacturing enterprise full-process manufacturing management and control is characterized by comprising the following steps:
s1, acquiring relevant data generated by the manufacturing enterprise in the business including design, manufacture, management and service;
s2, preprocessing the data acquired in the step S1;
s3, carrying out big data analysis on the data preprocessed in the step S2, adjusting the data changed due to the influence of the design, management and service services in the manufacturing process, and establishing the relation between the manufacturing service and the design, management and service services;
and S4, establishing a big data model which is through the whole system full value chain and is oriented to design, manufacture, management and service.
2. The method as claimed in claim 1, wherein the data preprocessing performed in step S2 includes data integration, data screening and data cleaning.
3. The manufacturing process big data modeling method facing manufacturing enterprise whole flow manufacturing management and control as claimed in claim 2, wherein the data integration is effective to integrate various types of related data generated by manufacturing enterprise in the business including design, manufacturing, management and service logically or physically, so as to provide more complete and comprehensive data sharing for manufacturing business.
4. The manufacturing process big data modeling method oriented to manufacturing enterprise whole-flow manufacturing management and control as claimed in claim 2, wherein the data screening screens out relevant data and eliminates irrelevant variables by analyzing possibility of influence on manufacturing process data in three business data of design, management and service.
5. The manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing management and control according to claim 2, wherein the data cleaning comprises: processing data with missing information; processing logically unreasonable data; processing mutually contradictory data; duplicate data is processed.
6. The manufacturing process big data modeling method facing manufacturing enterprise whole flow manufacturing management and control as claimed in claim 1, wherein said step S3 is performed based on a distributed message system Kafka of publishing and subscribing, and the core components of the system Kafka mainly include:
the theme is a logic concept of storing messages and is regarded as a message set; the system Kafka classifies the messages according to different themes, the themes are divided into three themes of design, management and service, and the service data of different data sources are put into different themes;
the information is the most basic unit of message queue communication; the producer publishes information to the topic, and the consumer can obtain the information from the subscribed topic for consumption;
a producer, which is a data or message source responsible for sending data or messages to a certain topic; the service data preprocessed in the step S2 is used as a producer, and sends data to three subjects of design, management, and service according to the difference of data sources;
the consumer is a party which subscribes to the topic and extracts the message or data from the topic for consumption, namely, the party analyzes and processes the data in the system Kafka; the consumer immediately processes the acquired dynamic service data from the theme of the system Kafka, namely, the selected consumer is required to have a stream processing framework to deal with a real-time scene;
the Spark Streaming is a Spark-based component for calculating the real-time data stream, rapidly analyzes and feeds back dynamic data in real time, selects the Spark Streaming as a consumer, acquires data of a theme in the system Kafka on the basis of the Spark Streaming, and processes the stream data in real time.
7. The manufacturing process big data modeling method oriented to manufacturing enterprise full-flow manufacturing management and control according to claim 6, characterized by performing big data analysis on the acquired data resources and adjusting data changed due to other business influences in the manufacturing process, and mainly comprising the steps of:
the Spark Streaming reads data information including a design drawing and a design scheme acquired by a design service side from a design theme of the system Kafka, calls an API (application programming interface) to stream data acquired from the design side to perform statistical analysis on data information including the number of personnel, materials and equipment required by an order, disassembles the order, and sends the number of the materials required by order manufacturing to a management service side;
after receiving the material demand request, the management business end delivers the materials required by the manufacturing process, and if the materials required by the manufacturing are not in sufficient inventory, the materials are purchased according to the requirements; the material distribution data information of the management service end is sent to the management theme of the system Kafka after being preprocessed in the step S2;
the Spark Streaming reads the material information obtained by the management service end from the management theme of the system Kafka, calls the API to statistically analyze the distributed material quantity information, and sends the information to the manufacturing service end; adjusting material quantity information in the manufacturing business, reasonably distributing and producing personnel, equipment and materials according to the material quantity information in the manufacturing process, and accurately matching the materials required by the manufactured products to ensure the smooth operation of the manufacturing process;
the management business delivers the produced and manufactured part of products to the service business, and the service business delivers the products to the customers in time to deliver and deliver orders; the customer finds that flaws exist in the used product and feeds the flaws back to the service business; after the data preprocessing of step S2, the feedback information of the service end is sent to the service theme of the system Kafka;
the Spark Streaming reads feedback information obtained by a service business end from a service theme of the system Kafka, calls an API (application programming interface) to classify the feedback information according to products, then performs statistical analysis, traces product problems through analysis, and timely adjusts information including personnel, equipment and environment for problems in a manufacturing link; if the manufactured product needs to be produced again, repeating the material demand request and the material distribution step to finish the production and the manufacture.
8. The manufacturing process big data modeling method facing manufacturing enterprise whole-flow manufacturing management and control as claimed in claim 1, wherein the step S4 is implemented by the following steps of establishing a holistic system whole-value chain through big data model facing design, manufacturing, management and service:
establishing a multiple linear regression model according to the data, wherein the model form of the multiple linear regression is as follows:
yi=β0+β1xi1+β2xi2+…+βpxip+εi;
in the above formula, y is a dependent variable, β is a undetermined coefficient, x is an independent variable, and ε is a residue term;
performing parameter estimation by a least square method to obtain beta and epsilon satisfying an equation, wherein the method comprises the following steps:
using formulasCalculating the actual observed value yi(i-1, 2,3, …, n) and the estimated value, the sum of squares of the differences is minimal, and the curve fitting is optimal, i.e. the residual sum of squares RSS is minimized;
finally, obtaining a coefficient which meets an equation and has the minimum sum of squares of errors with actual data, and finding out the optimal function matching;
after the coefficients are found, their regression significance needs to be checked:
suppose that: h0:βi=OvsH1:βiNot equal to 0, i.e. assuming that β is all 0 or not all 0;
test statistics, where SST is the sum of the squares of the sums, SSE is the sum of the squares of the errors, p is the number of arguments, n is the number of packets of actual data:
by constructed F statisticsThe larger the F is, the better the fitting effect is; comparing the calculated F value with the value obtained by table look-up, if F is present>FWatch (A)Then, the regression equation is considered to be significant enough; and finally obtaining an optimal regression equation through significance test.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011047636.3A CN112270613B (en) | 2020-09-29 | 2020-09-29 | Manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing control |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011047636.3A CN112270613B (en) | 2020-09-29 | 2020-09-29 | Manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing control |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112270613A true CN112270613A (en) | 2021-01-26 |
CN112270613B CN112270613B (en) | 2024-04-26 |
Family
ID=74349046
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011047636.3A Active CN112270613B (en) | 2020-09-29 | 2020-09-29 | Manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing control |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112270613B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7574383B1 (en) * | 2001-04-11 | 2009-08-11 | I2 Technologies Us, Inc. | System and method for providing distributed inventory management |
KR20160051582A (en) * | 2014-10-29 | 2016-05-11 | 한국생산기술연구원 | Platform structure making support services of manufacturing enterprises based on 3 dimensional data |
CN106156909A (en) * | 2015-03-30 | 2016-11-23 | 沈阳铝镁设计研究院有限公司 | A kind of electrolytic aluminium factory cloud control system integrated based on full price value chain information |
CN108734540A (en) * | 2017-04-25 | 2018-11-02 | 上海缇安埃信息科技有限公司 | A kind of fashion industry intelligent anti-flexible supply chain collaborative platform and its working method soon |
CN109272155A (en) * | 2018-09-11 | 2019-01-25 | 郑州向心力通信技术股份有限公司 | A kind of corporate behavior analysis system based on big data |
CN109753684A (en) * | 2018-11-29 | 2019-05-14 | 国网江苏省电力有限公司盐城供电分公司 | One kind being used for the modified multiple linear regression modeling method of substation's energy consumption benchmark |
CN110868322A (en) * | 2019-11-15 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Network management method, system, device and storage medium for distributed message service |
CN111079997A (en) * | 2019-12-03 | 2020-04-28 | 北京仿真中心 | Modeling and collaborative optimization method |
CN111077870A (en) * | 2020-01-06 | 2020-04-28 | 浙江中烟工业有限责任公司 | Intelligent OPC data real-time acquisition and monitoring system and method based on stream calculation |
-
2020
- 2020-09-29 CN CN202011047636.3A patent/CN112270613B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7574383B1 (en) * | 2001-04-11 | 2009-08-11 | I2 Technologies Us, Inc. | System and method for providing distributed inventory management |
KR20160051582A (en) * | 2014-10-29 | 2016-05-11 | 한국생산기술연구원 | Platform structure making support services of manufacturing enterprises based on 3 dimensional data |
CN106156909A (en) * | 2015-03-30 | 2016-11-23 | 沈阳铝镁设计研究院有限公司 | A kind of electrolytic aluminium factory cloud control system integrated based on full price value chain information |
CN108734540A (en) * | 2017-04-25 | 2018-11-02 | 上海缇安埃信息科技有限公司 | A kind of fashion industry intelligent anti-flexible supply chain collaborative platform and its working method soon |
CN109272155A (en) * | 2018-09-11 | 2019-01-25 | 郑州向心力通信技术股份有限公司 | A kind of corporate behavior analysis system based on big data |
CN109753684A (en) * | 2018-11-29 | 2019-05-14 | 国网江苏省电力有限公司盐城供电分公司 | One kind being used for the modified multiple linear regression modeling method of substation's energy consumption benchmark |
CN110868322A (en) * | 2019-11-15 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Network management method, system, device and storage medium for distributed message service |
CN111079997A (en) * | 2019-12-03 | 2020-04-28 | 北京仿真中心 | Modeling and collaborative optimization method |
CN111077870A (en) * | 2020-01-06 | 2020-04-28 | 浙江中烟工业有限责任公司 | Intelligent OPC data real-time acquisition and monitoring system and method based on stream calculation |
Non-Patent Citations (1)
Title |
---|
刘传超等: "订货型中小制造企业订单处理分析建模", 机电工程技术, vol. 42, no. 02, 15 February 2013 (2013-02-15), pages 1 - 6 * |
Also Published As
Publication number | Publication date |
---|---|
CN112270613B (en) | 2024-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cui et al. | Manufacturing big data ecosystem: A systematic literature review | |
Subramaniyan et al. | An algorithm for data-driven shifting bottleneck detection | |
US20070162496A1 (en) | Comparison of models of a complex system | |
US8027859B2 (en) | Analysis of a model of a complex system, based on two models of the system, wherein the two models represent the system with different degrees of detail | |
Braguinsky et al. | Product innovation, product diversification, and firm growth: Evidence from japan’s early industrialization | |
KR20090046738A (en) | Manufacturing prediction server | |
CN111552728B (en) | Data processing method, system, terminal and storage medium of block chain | |
CN105607566B (en) | A kind of self-adapting regulation method of production material | |
CN109684295A (en) | Environmental protection equipment running state analysis methods, devices and systems | |
Shoval et al. | Managing complexity of assembly with modularity: a cost and benefit analysis | |
Barad et al. | CIM flexibility measures: a review and a framework for analysis and applicability assessment | |
US11016736B2 (en) | Constraint programming using block-based workflows | |
CN111650912A (en) | Intelligent manufacturing production management platform for intelligent factory/workshop | |
Queiroz et al. | Agent-based distributed data analysis in industrial cyber-physical systems | |
KR20230051994A (en) | Information processing integrated logistics control system based on edge cloud | |
CN112270613B (en) | Manufacturing process big data modeling method for manufacturing enterprise full-flow manufacturing control | |
CN112488730A (en) | Product recall task processing method, device and equipment | |
CN111966726A (en) | System and method for generating self-adaptive data analysis report based on different types of clients | |
CN114789557B (en) | Multi-nozzle printing method of 3d printer | |
CN112347069B (en) | Manufacturing enterprise prediction type maintenance service method based on manufacturing big data | |
CN114358910A (en) | Abnormal financial data processing method, device, equipment and storage medium | |
US20200019910A1 (en) | Block-based prediction for manufacturing environments | |
TWI821666B (en) | Service management system and adaption method of service information process | |
US20190236508A1 (en) | Kpi spotlight for manufacturing process | |
Zhao et al. | Collaboration of smart device in cloud manufacturing: a case of active recommendation model based on service agent |
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 |