CN110380880A - A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame - Google Patents
A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame Download PDFInfo
- Publication number
- CN110380880A CN110380880A CN201810329841.5A CN201810329841A CN110380880A CN 110380880 A CN110380880 A CN 110380880A CN 201810329841 A CN201810329841 A CN 201810329841A CN 110380880 A CN110380880 A CN 110380880A
- Authority
- CN
- China
- Prior art keywords
- data
- edge calculations
- architecture
- network
- intelligent plant
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/02—Standardisation; Integration
- H04L41/024—Standardisation; Integration using relational databases for representation of network management data, e.g. managing via structured query language [SQL]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
- H04L41/044—Network management architectures or arrangements comprising hierarchical management structures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/08—Protocols for interworking; Protocol conversion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present invention relates to a kind of, and the vehicle based on edge calculations frame manufactures the architecture of intelligent plant, comprising: device Domain executes operation for the acquisition, processing and storage of data, and according to the control instruction of network domains；Network domains, for realizing the network protocol conversion between device Domain and data field；Data field for the data sent by network domains to be pre-processed and stored, and is sent to application domain；Application domain for carrying out plant maintenance according to the data from data field, and carries out production control, sends each equipment operation that control instruction realizes device Domain.The present invention realizes filtering and analysis to data, therefore more efficient since edge calculations are closer apart from vehicle equipment at fringe node.
Description
Technical field
It is specifically a kind of based on the whole of edge calculations frame the present invention relates to the architecture of vehicle manufacture intelligent plant
The architecture of vehicle manufacture intelligent plant.
Background technique
The essence of intelligence manufacture is the depth integration by generation information technology and advanced manufacturing technology, is realized across enterprise
The horizontal integrating of value network, through the Top-down design and product of the different levels such as business equipment layer, control layer, management level
The end-to-end of Life cycle integrates." made in China 2025 " emphasizes energy conservation and new-energy automobile, and auto manufacturing is as China
The important component part of manufacturing industry continues to hold a post or title global production and marketing first in continuous 7 years, and wherein one of key factor is exactly new-energy automobile
The swift and violent growth of volume of production and marketing, China have become the maximum new-energy automobile consumption market in the whole world, and new energy also becomes domestic main
The investment orientation of Che Qixin.As new investment project, vehicle enterprise just considers in the manufacturing process of new energy vehicle at the beginning of planning
Implement intelligence manufacture, makes production of the completely new intelligent plant for new energy vehicle.However auto manufacturing's industrial chain complexity,
Consumer personalization's demand height, relevance and drive property are strong, these features are determined for vehicle manufacture intelligent plant operation
The value of administrative standard research and verification experimental verification will also have absolute lead and exemplary role to entire manufacturing transition.
To ensure that effectively industry internet system needs to improve its performance, scalability and efficiency.For quickly, widely
Complete deployment, it is necessary to ensure that the understandability of industry internet system, while industry internet system will have generally applicable, standard
System Framework and reference architecture change, open and cross-cutting are as support.Reference architecture is system, solves
The research and development of scheme and framework applications provide guidance, provide general and consistent definition, composition and design pattern, and for discussing
Universal word.
Summary of the invention
In view of relevant not yet for vehicle manufacture intelligent plant reference architecture aspect in the current enterprise of vehicle both at home and abroad
Standard, the present invention have investigated the system frame that the international and domestic more influential normal structure in current intelligence manufacture field is formulated
Standard in terms of structure, 4.0 reference model of industry (RAMI4.0) including Germany, what American industry internet alliance (IIC) formulated
Industry internet reference architecture, information physical system (CPS) ginseng that USA National Institute of Standard and Technology (NIST) formulates
The Internet of Things reference architecture for examining architecture and China's formulation, provides guidance and reference frame for formulation of the invention.
Present invention technical solution used for the above purpose is: a kind of vehicle manufacture based on edge calculations frame
The architecture of intelligent plant, comprising:
Device Domain executes operation for the acquisition, processing and storage of data, and according to the control instruction of network domains；
Network domains, for realizing the network protocol conversion between device Domain and data field；
Data field for the data sent by network domains to be handled and stored, and is sent to application domain；
Application domain for carrying out plant maintenance according to the data from data field, and carries out production control, sends control and refers to
Enable each equipment operation for realizing device Domain.
The device Domain includes sensor, actuator, controller.
The data field, processing and storage be specially data filtering and pretreatment, Data Integration, data analysis with calculate,
One of data processing and storage are a variety of:
Data filtering operation: data filtering or data cleansing are carried out to all data on automobile manufacturing process；
Data Integration: carrying out integration classification to the data of acquisition, merge to isomeric data, and similar data into
Row is unified to be sorted out；
Data analysis and calculating: carrying out mathematical function transformation according to application demand to the different types of data of acquisition, including
Square, evolution, summation, one of calculus of differences or a variety of；
Data processing and storage: file storage and/or database purchase are carried out to all data on automobile manufacturing process.
The data filtering or data cleansing specifically:
The value of missing is inserted by hand；
It identifies the error value outside setting range, or abnormal data value is checked using the rule base of setting, and remove mistake
Value and abnormal data value；
The identical record of attribute value is considered as repeating to record in database, judges whether the attribute value between record is equal,
Equal record merges into a record, does not otherwise handle.
The network domains, for the various network protocol services in vehicle manufacture intelligent plant to be unloaded and are disposed,
Specifically: it is identified according to network protocol, loads the corresponding network protocol of deployment automatically and communicated into memory；If there is no
Network communication unloads corresponding network protocol from memory automatically.
The application domain is used for plant maintenance, specifically: obtain the vibration of equipment, temperature, pressure in automobile manufacturing process
Power, data on flows；The diagnosis of equipment fault is carried out according to each data.
The application domain, for producing control, specifically: obtain status data, the vehicle of equipment in automobile manufacturing process
Production process data and various sensing datas are manufactured, production procedure is set according to user demand.
The invention has the following beneficial effects and advantage:
1. distributed and low delay calculates.On the fringe node of vehicle manufacture, edge calculations can be used for improving clothes
Business, it is possible to reduce network latency meets business need in time.Industrial system detection, control, the real-time height executed, side
Edge, which calculates, focuses real-time, short cycle data analyses, and the real-time intelligentization of local service can preferably be supported to handle and execute.
2. more efficient.Since edge calculations are closer apart from vehicle equipment, the mistake to data is realized at fringe node
Filter and analysis, thus it is more efficient.
3. intelligence computation.Calculating can be layered execution, be completed using the resource of network distal end.AI (artificial intelligence)+edge
The technology of artificial intelligence has exactly been merged in the combination of calculating in edge calculations, and there is data analysis to automatically process energy with business
Power, intelligence execute local business logic, significantly raising efficiency and can reduce cost；It can be completed certainly with dynamic realtime
I optimizes, adjusts implementation strategy.Edge calculations are allowed not terminate in calculating, more a intelligences.
4. sustainable energy consumption.Energy requirement can be growing, and the basic information of some built-in small equipment is adopted
Collection processing can be completed completely at end.Cloud computing and edge calculations combine, and cloud computing focuses non real-time, macrocyclic data point
Analysis can make the most of the advantage in fields such as business decision supports；Edge calculations focus real-time, short cycle data analyses, can be more preferable
Ground supports the real-time intelligentization processing of local service and executes.In addition, the two, there is also conspiracy relation, edge calculations are both close to be held
Row unit, the even more acquisition unit of high price Value Data needed for cloud, the big data analysis that can preferably support cloud to apply；Instead
It, cloud computing generates the business rule of optimization by data analysing methods such as machine learning, artificial intelligence, and is issued to edge
Side, edge calculations carry out the optimization processing of business execution based on new business rule.Net is transferred data to by sensor
Guan Hou, with regard to carrying out data filtering and processing by edge calculations, need not every initial data be all transmitted to cloud, this is eliminated greatly
The energy cost of amount, cost only have 39% that cloud computing is used alone.
5. coping with data explosion and network flow pressure.By executing data analysis on edge device, can successfully manage
Data explosion mitigates the flow pressure of network.Edge calculations can shorten the response time of equipment, reduce from equipment to cloud data
The data traffic at center, more effectively to distribute resource in a network.
Detailed description of the invention
Fig. 1 is the architectural schematic that the present invention manufactures intelligent plant in vehicle.
Specific embodiment
The present invention will be further described in detail below with reference to the embodiments.
Vehicle manufacturing process is huge, accurate, high speed a rigorous production process, needs people, equipment, management
The seamless perfect combination of means, could high speed, vehicle that is stable, effectively producing high-quality.
A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame, manufactures intelligence aiming at vehicle
The characteristics of occurring in factory: the depth integration with generation information technology and advanced manufacturing technology is realized across firm value network
Horizontal integrating, through the full Life Cycle of Top-down design and product of the different levels such as business equipment layer, control layer, management level
Phase it is end-to-end integrated the features such as, and a kind of architecture of the suitable vehicle manufacture intelligent plant proposed.It includes equipment, net
Four domains of network, data and application: the design of vehicle manufacture intelligent plant is instructed, and by the promotion and implementation of project of standard development, to vehicle
Manufacture intelligent plant architecture is standardized, and is provided important criteria support for manufacture intelligent plant construction, is made to manufacture intelligence
Energy factory construction has something to base on, and helps to manufacture intelligent plant fast development, has important scientific value, economic induced effect
With huge social benefit, there is stronger impetus to manufacture intelligent plant development.It proposes to be suitble to the whole of China's national situation simultaneously
Vehicle intelligence manufacture factory's reference architecture and generic specifications have innovative significance, will be used to that vehicle to be instructed intelligently to make
Factory application deployment is made, the efficiency and level of China's vehicle intelligence production are promoted, transition manufacturing to entire vehicle also will
There is absolute lead and exemplary role.
As shown in Figure 1, the present invention includes following part:
(1) device Domain, pure Internet of Things (IoT) equipment occurred in vehicle manufacture production process, with automation
I/O acquisition compare, have different but also have lap.Those are used directly for optimizing in top layer, and do not join
It is that can be placed directly in device Domain to complete to handle with the data of control itself.
It (2) is network domains, in transportation level, direct end Internet of Things (IoT) data and from vehicle manufacturing automation
The data of producing line, transmission mode, mechanism, agreement all can be different, therefore, to solve the problems, such as the data standard of transmission here.
(3) data field, these data fields such as data storage, format after the related data transmission of vehicle manufacture need to solve
The problem of, also the mechanism and policing issue of inquiry and data interaction including data are all in need of consideration in this field ask
Topic；
(4) application domain, for the set for executing function using logic for realizing specific transactions function.Function in the domain be by
Optimized in a manner of macroscopic view, high-rise applied to global scope using logic, rule and model.Simultaneously this generic operation and it is traditional or
Novel industry internet specific transactions function (supporting operation flows and program activity including those) is integrated.
Device Domain:
Main effect is perceived to information, and function is such as the sensor that is widely used at this stage, to information, such as
The video acquisition of video monitoring, the data acquisition of rainwater monitoring.It is that sensor one-side can only adopt data at this stage
Collection, but be very difficult to carry out data analysis in equipment domain hierarchy.The device Domain of edge calculations, which but has, simply locates data
The effect of reason.Edge calculations solve Internet of Things predicament by adjusting the process demand of each application program, and low latency is utilized to need
It asks, edge network makes IoT equipment oneself run machine learning algorithm, scene operation edge calculations task, and equipment oneself handles number
According to and run calculating.
Network domains:
Main function is disposed to computing capability, realizes the conversion of various network protocols, and standardization network passes
It is defeated.The main function of edge calculations is exactly to carry out network deployment in fringe node, realizes the standardization to data.Further to
The network integration afterwards carries out intelligentized management.It should be noted the privacy and safety problem of network in this level.Wherein
Privacy concern be one important point it because marginal end is closest to the port of data, phase is carried out to data-privacy
The protection answered.
Data field:
The most important effect of edge calculations is exactly flexible data management and computing function, the proposition master of edge calculations
If carrying out the storage and calculating of data in marginal end, source data is simply handled, is then again passed the data of processing
Defeated to arrive cloud, main effect is exactly that " dirty data " that is collected into is abandoned to " data cleansing ", and only retaining has us
With being data.Edge calculations are exactly to the reasonable unloading of data progress and deployment, holding and cloud there are one important role
The efficient cooperation of collaboration.
Application domain:
Edge calculations and the main distinction of cloud computing are that edge calculations provide nearest platform management and calculating, cloud be into
The long-range connection of row." nearly object " characteristic of edge calculations determines the ability that it has fast reaction, reduces network transmission and is brought
Delay, realize the function that calculates in real time, independent localization can be especially carried out when network breaks down and is operated.Intelligence
Elevator is exactly a most apparent example, and when terminal (elevator) and network lose downlink connection because of failure, marginal end can be into
Row local computing, operates normally elevator.
The framework of edge calculations can be divided into device Domain (perception and control layer), network domains (connection and network layer), data
Domain (storage and service layer), application domain (business and intelligent layer).This four " layer domain " are exactly the computing object of edge calculations.More than
Four levels carry out intelligent processing to data, localization calculates and real-time Transmission so that edge calculations have information Perception
Function.Especially to the higher service of bandwidth demand, such as video monitoring.Simple process can be locally being carried out, to some quiet
Only picture or picture useless carry out the discarding of selectivity, and useful data are only transferred to cloud, will be greatly reduced
Bandwidth waste, and the time can also be saved.
Embodiment:
Background: certain vehicle production unit produces the automobile of product A type number, since the unmature world, national standard can
For reference, current vehicle enterprise demand presses own standard progress preconsolidation stress and design, opposite closure, limitation do not have
Extensive reference and industrialization promotion value, it is contemplated that the Industrial Effects power of auto manufacturing, shortage of standard state are unfavorable for whole
The cooperative development of a industry.The correct operation of various equipment and sensor in automobile manufacturing process is to guarantee automobile production quality
Important guarantee.There are many automobile sensor, when judging the failure that sensor occurs, should not consideration sensor itself, and take an examination
Consider the entire circuit to break down.According to the effect of sensor, measurement temperature, pressure, flow, position, gas can be classified as
The sensor of the functions such as concentration, speed, brightness, humidity, distance, Each performs its own functions for they, once some sensor failure, right
The device work answered will be abnormal or even work.Then solve the problems, such as that this process is as follows with the method for the invention:
(1) the internet of things equipment service layer of intelligent plant architecture is established
Device service layer includes the physical entity of edge calculations system, realizes and acquires from data, local data processing, local
Data storage and corresponding operation is executed according to control instruction, by close to or insertion sensing, instrument, robot and lathe etc.
The field node of equipment, support field device realize real-time intelligent interconnection and intelligent use.According to the difference of function, mechanical floor
Sensor, actuator, the physical units such as controller and edge calculations node can be divided into.
In addition to the automobile live video class big data that processing is complicated, device service layer also needs to handle a large amount of decimal
According to, such as motor, the auto industrys field device such as lathe data collected, and response in real time is provided.The place of this kind of data
Reason can use lightweight, low-power consumption, and zero configuration, ad hoc network, the perceptual computing system of cross-platform ability have at low cost, easy
In the large scale deployment the characteristics of.
Ensure the safety of the physical equipment of mechanical floor simultaneously, guarantees to obtain correct data.Including various sensing datas,
Device status information data, production process data and various information control datas etc.；
This layer interacts with the IoT physical equipment in vehicle production process, obtains various bottom datas, can be to perception
Information directly handled by web services layer and transmitted toward data service layer, while being transmitted from web services layer
Control information data, by mechanical floor go control bottom Internet of Things IoT equipment, guarantee vehicle manufacture intelligence production.
(2) web services layer of intelligent plant architecture is established
In auto manufacturing, industrial control system directly controls the manufacturing and processing of product, is the pass of quality guarantee
Key.Certainty means always under prescribed conditions, identical output always to be generated, without randomness.From the view of net connection
Angle is seen, it is necessary to ensure that the certainty of control signal transmitting.
Network is the foundation stone of system interconnection with data aggregate transmission.With the sharp increase of automobile production number of devices, network fortune
Dimension management, flexible expansion and guaranteed reliability face huge challenge.Meanwhile there are a large amount of isomeries in automobile production scene for a long time
Bus connection, the Industrial Ethernet of multiple types simultaneously deposits, and web services layer just solves compatible a variety of to couple and ensure to couple
It is real-time reliable.Web services layer just needs to solve the intercommunication between them, and a large amount of information island otherwise will be present.Support sea
The access and flexible expansion for measuring the network equipment provide the automation operation management of high efficiency, low cost, realize the plan of network and safety
It slightly cooperates with and merges.
This layer be used to realize various network protocols (including OPC agreement, industrial Fieldbus protocols, serial port communicating protocol with
And wireless transmission protocol etc.) conversion, standardization network transmission.All kinds of numbers that web services layer obtains mechanical floor
According to changing into the data of unified standard, transmitted toward data service layer, guarantee that data transmission is correct, data format is correct.Simultaneously
All kinds of control information datas that web services layer transmits data Layer are accurately transmitted to device service layer, guarantee control life
It enables information assign bottom in time and carries out corresponding operating.The main function of edge calculations is exactly to carry out Network Dept. in fringe node
Administration realizes the standardization to data.Intelligentized management further is carried out to the later network integration.Solve number in Physical Network
The problem of according to isomery, it is necessary to edge calculations are disposed in network domains, with realize data format standardization and data transmitting
Standardization.
(3) data service layer of intelligent plant architecture is established
Data service layer provides data-optimized service, extraction, polymerization, interoperability, semantization and analysis including data
With the Life cycle service of presentation, and the security and privacy of data is ensured；
The data management range of data service layer includes from manufactruing equipment of automobile operation data, environmental data and Information Number
According to the processing and operation between generating to storage and accessing.This layer is mainly handled the data of acquisition, including data mistake
Filter and pretreatment, Data Integration, data analysis and four parts of calculating, data processing and storage.
1, data filtering operation refers to the various data completed on automobile manufacturing process, for existing for initial data one
A little problems: inconsistent；It repeats；Invalid data etc. carries out data filtering or data cleansing operation, using the calculation in bound section
Method is separated useful data from dirty data, and invalid data discard processing, guarantees the validity and just of data
True property；
2, Data Integration refers to that the data come up to acquisition carry out integration classification, merges to various isomeric datas, and
Similar data are carried out unified classification.Good Data Integration helps to reduce the redundancy of data set and inconsistent, guarantee number
According to it is correct, uniquely.
3, data analysis is exactly to carry out carry out standardization processing to the different types of data of acquisition with calculating, i.e., to original number
Carry out corresponding mathematical function transformation according to according to the demand of upper layer application, including square, evolution, summation, calculus of differences etc., meet
Demand of the upper layer application to data；
4, data processing and storage refer to that the file of equipment operating data, environmental data and data of information system is deposited in realization
The data of storage, relational database storage, real-time data base storage, NoSQL database, graphic data base, semantic database etc. are deposited
Store up function.
Data service support can integrality to data and consistency analyze, and carry out data cleaning, disappear
" dirty " data in system of going out.Dirty data refers to invalid data, incomplete data, the data of mistake and duplicate number
According to.Secondly, can dynamically be disposed to calculating and storage capacity and system load.
Data cleansing specifically: the process that data are examined and verified again, it is therefore intended that delete duplicate message, entangle
Just existing mistake, and data consistency is provided.Data cleansing is difficult to conclude unified method generally directed to concrete application
And step, but corresponding data heat-clearing method method can be provided according to data difference.
1. the method for solving deficiency of data (i.e. value missing)
In most cases, the value of missing must insert (i.e. manual cleanup) by hand.Certainly, certain missing values can be from this
Data source or other data sources derive that this can use average value, maximum value, minimum value or increasingly complex probability Estimation
Instead of the value of missing, to achieve the purpose that cleaning.
2. the detection and solution of error value
Identify possible error value or exceptional value with the method for statistical analysis, such as variance analysis, identification do not abide by distribution or
The value of regression equation can also check data value with simple rule library (common-sense rule, business ad hoc rules etc.), or using not
Data are detected and cleared up with the constraint between attribute, external data.
3. repeating detection and the removing method of record
In database attribute value it is identical record be considered as repeat record, by judge record between attribute value whether phase
Whether equal etc. to detect record, equal record merges into a record (i.e. merging/removing).Merging/removing disappears heavy
Basic skills.
4. the detection and solution of inconsistency (inside data source and between data source)
The data integrated from multi-data source may have semantic conflict, can define integrity constraint and be used to detect inconsistency,
It can also be by analysis data discovery connection, so that data are consistent.
Data service layer performs corresponding processing the Various types of data of intelligent plant and is saved in database, to application
Layer provides data and is applied；Meanwhile also the information and order that upper application layer is assigned accurately are passed to by network layer
Mechanical floor is executed, and guarantees the correct conduction of data information；
(4) application service layer of intelligent plant architecture is established
Application service layer system is after data service layer acquisition related data, so that it may realize that automobile production digital plant is raw
Produce resource virtualizing, modeling, association, retrieval, the real-time analog simulation of production process and optimization, production factors and production system dynamic
Organize the functions such as the virtual factory management, operation, control with information spaces such as reconstruct.Automobile production process can be optimized, rationally
It arranges production time of plan, controls cost, improve production efficiency.It can reinforce the management of metrical information, reduce energy consumption, be conducive to
The stabilization of production run reduces the probability occurred extremely.Meanwhile the business information of application service layer and control information are passed through number
According to layer, network layer, passes to device service layer and carry out execution operation.Specific mainly includes following components application:
Intelligence production: the upgrading of automobile manufacture factory becomes the intelligent network that can be managed and adaptively be adjusted, so that
Industry Control and optimised management use limited resources to greatest extent, so that the deployment cost of industry and resource is reduced,
So that production process can be carried out efficiently.
Production procedure optimization: utilizing big data technology, establishes dummy model to the production process of industrial products, emulates and excellent
Change production procedure, when all processes and performance data can be rebuild in systems, this transparency will be helpful to manufacturer and change
Into its production procedure.
Device predicted maintenance: using the big data obtained, system and real-time dataBase system are monitored from field equipment state
The data such as vibration, temperature, pressure, the flow of equipment in middle acquisition automobile manufacturing process.By constructing rule-based failure
The models such as diagnosis, the prediction of the fault diagnosis based on case, equipment state degradation trend, residual service life of components prediction, pass through data
Analysis carries out equipment fault prediction and diagnosis.
Production plan and scheduling: the data such as customer order, production line, personnel are collected, big data scientific discovery history is passed through
Prediction and actual deviation probability consider that capacity constraints, the constraint of personnel's technical ability, material can use constraint, moulds of industrial equipment constraint, pass through
The genetic algorithm of intelligence formulates pre-planned scheduled production, and the actual deviation of Supervisory Surveillance Program and scene, dynamic plan for adjustment scheduled production.
Quality analysis and management: real time datas and the historical datas such as auto production line, product are collected, is built according to previous experiences
Vertical big data model, analyzes product quality, it is ensured that quality assurance during normal production.
Energy consumption control: by the discharge of each key link energy consumption of automobile manufacture production line and accessory drive transmission & distribution link
Real-time dynamic monitoring management, collect production line, the related datas such as key link energy consumption, establish energy simulation model, carry out more
The analysis of dimension energy consumption model simulation and prediction, obtains the energy saving space data of each link of production line, cooperating intelligent optimization load
With energy-consuming balance, to realize the consumption reduction emission reduction of whole production line flexible energy-saving；The exception or peak condition of discovery energy consumption in time, it is real
Energy consumption real-time optimization in existing production process.
Personalized customization: the letter such as customer personalized demand data, Automobile Enterprises creation data, external environment data is acquired
Breath, establishes personalized product model, by product information transmission to smart machine, carries out equipment adjustment, raw material preparation, produces
Meet the customed product of individual demand.
Claims (7)
1. a kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame, characterized by comprising:
Device Domain executes operation for the acquisition, processing and storage of data, and according to the control instruction of network domains；
Network domains, for realizing the network protocol conversion between device Domain and data field；
Data field for the data sent by network domains to be handled and stored, and is sent to application domain；
Application domain for carrying out plant maintenance according to the data from data field, and carries out production control, it is real to send control instruction
Each equipment operation of existing device Domain.
2. a kind of architecture of vehicle manufacture intelligent plant based on edge calculations frame according to claim 1,
It is characterized in that the device Domain includes sensor, actuator, controller.
3. a kind of architecture of vehicle manufacture intelligent plant based on edge calculations frame according to claim 1,
Be characterized in that the data field, processing and storage be specially data filtering and pretreatment, Data Integration, data analysis with calculate,
One of data processing and storage are a variety of:
Data filtering operation: data filtering or data cleansing are carried out to all data on automobile manufacturing process；
Data Integration: integration classification is carried out to the data of acquisition, isomeric data is merged, and similar data are united
One sorts out；
It data analysis and calculates: mathematical function transformation is carried out according to application demand to the different types of data of acquisition, including square,
One of evolution, summation, calculus of differences are a variety of；
Data processing and storage: file storage and/or database purchase are carried out to all data on automobile manufacturing process.
4. a kind of architecture of vehicle manufacture intelligent plant based on edge calculations frame according to claim 3,
It is characterized in that the data filtering or data cleansing specifically:
The value of missing is inserted by hand；
Identify setting range outside error value, or using setting rule base check abnormal data value, and remove error value and
Abnormal data value；
The identical record of attribute value is considered as repeating to record in database, judges whether the attribute value between record is equal, equal
Record merge into a record, otherwise do not handle.
5. a kind of architecture of vehicle manufacture intelligent plant based on edge calculations frame according to claim 1,
It is characterized in that the network domains, for the various network protocol services in vehicle manufacture intelligent plant to be unloaded and are disposed,
Specifically: it is identified according to network protocol, loads the corresponding network protocol of deployment automatically and communicated into memory；If there is no
Network communication unloads corresponding network protocol from memory automatically.
6. a kind of architecture of vehicle manufacture intelligent plant based on edge calculations frame according to claim 1,
It is characterized in that the application domain, is used for plant maintenance, specifically: obtain the vibration of equipment, temperature, pressure in automobile manufacturing process
Power, data on flows；The diagnosis of equipment fault is carried out according to each data.
7. a kind of architecture of vehicle manufacture intelligent plant based on edge calculations frame according to claim 1,
It is characterized in that the application domain, for producing control, specifically: obtain status data, the vehicle of equipment in automobile manufacturing process
Production process data and various sensing datas are manufactured, production procedure is set according to user demand.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810329841.5A CN110380880A (en) | 2018-04-13 | 2018-04-13 | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810329841.5A CN110380880A (en) | 2018-04-13 | 2018-04-13 | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110380880A true CN110380880A (en) | 2019-10-25 |
Family
ID=68243825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810329841.5A Pending CN110380880A (en) | 2018-04-13 | 2018-04-13 | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110380880A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996393A (en) * | 2019-12-12 | 2020-04-10 | 大连理工大学 | Single-edge computing server and multi-user cooperative computing unloading and resource allocation method |
| CN111026060A (en) * | 2019-12-24 | 2020-04-17 | 重庆奔腾科技发展有限公司 | Digital intelligent manufacturing system for high-performance mechanical basic components |
| CN111338582A (en) * | 2020-05-19 | 2020-06-26 | 北京东方通科技股份有限公司 | Industrial internet data acquisition method and system and terminal |
| CN111585823A (en) * | 2020-05-20 | 2020-08-25 | 石高峰 | Communication network optimization method and device based on block chain and edge calculation |
| CN113390559A (en) * | 2020-03-12 | 2021-09-14 | 中国科学院沈阳自动化研究所 | Vacuum monitoring instrument fault diagnosis system structure based on edge calculation framework |
| CN114253697A (en) * | 2020-09-22 | 2022-03-29 | 中国科学院沈阳自动化研究所 | Equipment state monitoring edge calculation framework for lithium ion battery cell manufacturing |
| CN114282620A (en) * | 2021-12-29 | 2022-04-05 | 汇鲲化鹏(海南)科技有限公司 | Multi-source information physical twin data fusion management method and management system |
| CN114967494A (en) * | 2022-03-25 | 2022-08-30 | 浙江工业大学 | Cloud digital twin workshop simulation system based on modular development |
| CN116975639A (en) * | 2023-07-28 | 2023-10-31 | 东莞盟大集团有限公司 | Abnormality prevention and control system and method for equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110105650A1 (en) * | 2008-01-16 | 2011-05-05 | Vincent Yan | Method and system for preparing densified lignocellulosic pulp for use in thermoplastic composite manufacturing processes |
| CN105759766A (en) * | 2016-04-12 | 2016-07-13 | 华南理工大学 | Industrial robot product assembling method based on internet of things |
| CN107819854A (en) * | 2017-11-14 | 2018-03-20 | 深圳市华讯方舟软件信息有限公司 | Public safety system and construction method based on cloud edge calculations |
-
2018
- 2018-04-13 CN CN201810329841.5A patent/CN110380880A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110105650A1 (en) * | 2008-01-16 | 2011-05-05 | Vincent Yan | Method and system for preparing densified lignocellulosic pulp for use in thermoplastic composite manufacturing processes |
| CN105759766A (en) * | 2016-04-12 | 2016-07-13 | 华南理工大学 | Industrial robot product assembling method based on internet of things |
| CN107819854A (en) * | 2017-11-14 | 2018-03-20 | 深圳市华讯方舟软件信息有限公司 | Public safety system and construction method based on cloud edge calculations |
Non-Patent Citations (2)
| Title |
|---|
| HTTP://WWW.ECCONSORTIUM.NET/LISTS/SHOW/ID/32.HTML: "边缘计算产业联盟白皮书", 《边缘计算产业联盟》 * |
| 李栋: "边缘计算在智能制造中的解决方案", 《自动化博览》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996393A (en) * | 2019-12-12 | 2020-04-10 | 大连理工大学 | Single-edge computing server and multi-user cooperative computing unloading and resource allocation method |
| CN110996393B (en) * | 2019-12-12 | 2023-04-11 | 大连理工大学 | Single-edge computing server and multi-user cooperative computing unloading and resource allocation method |
| CN111026060A (en) * | 2019-12-24 | 2020-04-17 | 重庆奔腾科技发展有限公司 | Digital intelligent manufacturing system for high-performance mechanical basic components |
| CN113390559A (en) * | 2020-03-12 | 2021-09-14 | 中国科学院沈阳自动化研究所 | Vacuum monitoring instrument fault diagnosis system structure based on edge calculation framework |
| CN111338582A (en) * | 2020-05-19 | 2020-06-26 | 北京东方通科技股份有限公司 | Industrial internet data acquisition method and system and terminal |
| CN111585823A (en) * | 2020-05-20 | 2020-08-25 | 石高峰 | Communication network optimization method and device based on block chain and edge calculation |
| CN111585823B (en) * | 2020-05-20 | 2021-03-19 | 江苏永鼎通信有限公司 | Communication network optimization method and device based on edge calculation and industrial production |
| CN114253697A (en) * | 2020-09-22 | 2022-03-29 | 中国科学院沈阳自动化研究所 | Equipment state monitoring edge calculation framework for lithium ion battery cell manufacturing |
| CN114282620A (en) * | 2021-12-29 | 2022-04-05 | 汇鲲化鹏(海南)科技有限公司 | Multi-source information physical twin data fusion management method and management system |
| CN114967494A (en) * | 2022-03-25 | 2022-08-30 | 浙江工业大学 | Cloud digital twin workshop simulation system based on modular development |
| CN116975639A (en) * | 2023-07-28 | 2023-10-31 | 东莞盟大集团有限公司 | Abnormality prevention and control system and method for equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110380880A (en) | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame | |
| US20220164502A1 (en) | Pump machine unit optimized operation regulation system and method based on digital twin | |
| WO2022257181A1 (en) | Aiot paas internet of things operation platform | |
| CN110209716A (en) | Intelligent internet of things water utilities big data processing method and system | |
| CN112731887A (en) | Digital twin intelligent monitoring system and method for petrochemical unattended loading and unloading line | |
| CN108718345A (en) | A kind of digitlization workshop industrial data Network Transmitting system | |
| CN112418523B (en) | After-sales equipment predictive maintenance cooperative system based on digital twinning | |
| CN102176723A (en) | Manufacturing cloud system for supporting on-demand use and dynamic collaboration of manufacturing resources and manufacturing capacities | |
| CN112085261A (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
| CN112462696A (en) | Intelligent manufacturing workshop digital twin model construction method and system | |
| CN105467953A (en) | Knowledge representation facing industrial big data and automation application method thereof | |
| CN109492774A (en) | A kind of cloud resource dispatching method based on deep learning | |
| WO2012062184A1 (en) | System energy efficiency controller in smart energy network, control method thereof, and control method for terminal device | |
| CN110390020A (en) | The modeling method of semantic gateway and semantic gateway | |
| Kim et al. | Server-Edge dualized closed-loop data analytics system for cyber-physical system application | |
| TW202020887A (en) | Intelligent pre-diagnosis and health management system modeling method and computer program product thereof wherein the method includes a new tree building step, a two-branch modeling step, and a model self-adaptive optimization step | |
| CN113673952A (en) | Cloud service system based on industrial internet platform | |
| CN116050754A (en) | Digital twinning-based virtual power plant collaborative management and control method and system | |
| CN110442446A (en) | The method of processing high-speed digital signal data flow in real time | |
| CN101963804A (en) | Management-control integrated flexible assembly line for mechanical products | |
| CN113659712A (en) | Power equipment big data label operation platform and method | |
| CN102298648A (en) | Out-of-process access method of open real-time database | |
| CN116149849A (en) | Edge computing method for intelligent water affair complex time scale data fusion | |
| Grauer et al. | Towards an IT-framework for digital enterprise integration | |
| CN109978503A (en) | Data processing method based on micro services |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191025 |