CN116032969A - Cloud-edge cooperative intelligent numerical control workshop self-regulation system and control method - Google Patents
Cloud-edge cooperative intelligent numerical control workshop self-regulation system and control method Download PDFInfo
- Publication number
- CN116032969A CN116032969A CN202310014075.4A CN202310014075A CN116032969A CN 116032969 A CN116032969 A CN 116032969A CN 202310014075 A CN202310014075 A CN 202310014075A CN 116032969 A CN116032969 A CN 116032969A
- Authority
- CN
- China
- Prior art keywords
- data
- edge
- cloud
- module
- numerical control
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 11
- 230000009133 cooperative interaction Effects 0.000 claims abstract description 7
- 230000007246 mechanism Effects 0.000 claims abstract description 7
- 230000008447 perception Effects 0.000 claims description 24
- 238000004891 communication Methods 0.000 claims description 22
- 238000003754 machining Methods 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 12
- 238000013523 data management Methods 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 25
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 238000013461 design Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 238000005520 cutting process Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000003801 milling Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000007514 turning Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- General Factory Administration (AREA)
Abstract
The invention discloses a cloud-edge cooperative intelligent numerical control workshop self-regulation system and a control method, and belongs to the technical field of intelligent manufacturing. According to the cloud-edge cooperative intelligent numerical control workshop self-regulating mode provided by the invention based on the edge computing technology, an intelligent numerical control workshop manufacturing unit edge sensing-cloud cooperative operation-intelligent regulation and control framework is built on the basis of analyzing the operation mechanism and regulation and control characteristics of the numerical control workshop, cloud Bian Liangji cooperative interaction scene deployment is completed, and the computing performance of edge sensing nodes is improved through the judgment logic of a design rule engine; secondly, training and correcting a cloud edge processing model by adopting a long-period memory neural network, and formulating cloud edge cooperative production logic to finish the self-control of intelligent numerical control workshop equipment; finally, the application case verifies that the cloud edge collaborative framework has the characteristics of easy collaboration, easy regulation and control and low time delay, and provides technical support for realizing intelligent production of the numerical control workshop.
Description
Technical Field
The invention relates to a cloud-edge cooperative intelligent numerical control workshop self-regulation system and a control method, and belongs to the technical field of intelligent manufacturing.
Background
The continuous development of the internet of things accelerates the informatization and intelligence process of the manufacturing workshops, and helps to promote autonomous innovation and market competitiveness of manufacturing enterprises. The intelligent manufacturing (IntelligentManufacturing, IM) is a deep fusion of the manufacturing industry and the information technology of the Internet of things, is a necessary path for upgrading and optimizing enterprises, and is a key for promoting the Chinese manufacturing 2025 to become the leading edge of the world manufacturing industry in China. The intelligent numerical control workshop is an important embodiment in the IM production process, the continuous increase of the number and the variety of access equipment in the intelligent numerical control workshop can generate massive real-time process data, and how to efficiently use the data becomes the key of the intelligent numerical control workshop data processing technology. At present, most enterprises upload real-time industrial data generated by the cloud server for centralized and unified processing, however, the process of importing and exporting mass data from a cloud center is very complex, and the problems of insufficient bandwidth, large delay and the like affect the direct interaction between the cloud center and equipment. Therefore, the introduction of the edge computing technology well solves the problems that an edge gateway is deployed at the edge side of a network close to equipment or a data source, core capabilities of the network, computing, storage and the like are fused, the edge intelligent service is provided nearby, and the key requirements of different service fields are met.
In the face of massive heterogeneous multi-source data in an intelligent numerical control workshop, although the edge computing technology can meet the requirement of real-time computing, the edge computing technology cannot replace the high computing performance of a cloud server, and a great deal of research has been conducted around related works such as sensing of manufacturing resources of the intelligent numerical control workshop, layering processing of data, building of the cloud server and the like. Lv Youlong and the like propose an intelligent factory technical architecture of a data center and five industrial business layers, discuss a dynamic optimized big data analysis method aiming at the big data driven manufacturing process, and are beneficial to solving the problems of layering processing and data application of multi-source heterogeneous data of the intelligent factory. TAO and the like propose cloud manufacturing access resource classification, manufacturing resource aware access architecture and typical cases; li Hai and the like provide a machine tool equipment resource selection method based on multi-criterion decision-making aiming at cloud manufacturing environment access resources. However, the application of the cloud service platform in the industrial Internet of things is well expanded, but the real-time response requirement of the equipment end is not solved, so that the cloud edge cooperation technology based on edge calculation is a necessary trend of future development, the research of merging the cloud edge cooperation mode into workshop production is less at present, and the related research of the cloud edge cooperation mode for self-regulation of intelligent numerical control workshop production is lacking.
Disclosure of Invention
The invention provides a cloud-edge cooperative intelligent numerical control workshop self-regulation system and a control method, which process multi-source heterogeneous data in a numerical control workshop in a cloud computing and cloud computing coupling cooperative mode, and the numerical control workshop control center is used as a cloud application server to construct a cloud-edge cooperative framework by abstracting each process device of the numerical control workshop into an edge node, so that the problem of layered dispatching processing of the multi-source heterogeneous data in the numerical control workshop between the cloud center and the edge node is solved, the edge node and the numerical control device are utilized to cooperatively interact, the edge device responds rapidly, and the problem of manufacturing production self-regulation in the numerical control workshop is solved.
The technical scheme of the invention is as follows:
according to one aspect of the invention, an intelligent numerical control workshop self-regulation system with cloud edge coordination is provided, and the intelligent numerical control workshop self-regulation system comprises an intelligent numerical control workshop cloud application center, an intelligent numerical control workshop edge sensing node and an intelligent numerical control workshop terminal device; the intelligent numerical control workshop cloud application center is provided with a cloud database, a data application module and an edge application module, wherein the cloud database is used for storing non-sensitive data uploaded by an edge perception node; the data application module is used for data preprocessing of non-sensitive data in the cloud database and training and correcting of the prediction model; the edge application module is used for issuing an edge perception node prediction model and a processing program; the intelligent numerical control workshop edge perception node comprises an equipment service layer, a core data layer and a support service layer; the equipment service layer establishes communication with the intelligent numerical control workshop terminal equipment through a communication protocol to perform data acquisition and command interaction; the core data layer comprises a core data module, a data management module, an edge database and a command regulation module, wherein the core data module is used for displaying acquired data of the terminal equipment, the data management module is used for distinguishing sensitive data from non-sensitive data, the edge database is used for storing the sensitive data, and the command regulation module is used for receiving commands of a rule engine module and a processing program module of a support service layer and regulating and controlling the terminal equipment; the support service layer comprises an application service module, a rule engine module, an algorithm module and a processing program module, wherein the application service module is used for transmitting and interacting cloud edge data, the rule engine module is used for setting rules, the algorithm module is used for receiving a prediction model issued by a cloud application center to conduct real-time prediction, and the processing program module is used for receiving a processing program issued by the cloud application center to conduct processing of corresponding working procedures of a workpiece.
And the file transmission mode between the server and the client is adopted to realize the prediction model interaction between the intelligent numerical control workshop cloud application center and the intelligent numerical control workshop edge perception node.
According to another aspect of the present invention, there is also provided a control method of a cloud-edge cooperative intelligent numerical control workshop self-regulation system, where the method is applied to any one of the cloud-edge cooperative intelligent numerical control workshop self-regulation systems, and the method includes:
the intelligent numerical control workshop terminal equipment establishes communication with the intelligent numerical control workshop edge sensing node through a communication protocol of the equipment service layer, and acquires data to the core data module to display the data of the edge sensing node; the core data module transmits the data to the data management module for data processing, and the data is divided into sensitive data and non-sensitive data; the method comprises the steps that sensitive data are stored in an edge database for further application of edge sensing nodes, meanwhile, the sensitive data are also transmitted into a rule engine module for judgment according to preset rules, when the detected data exceed a limiting range, the rule is directly triggered to conduct command regulation and control to conduct action response of numerical control equipment, when the detected data accord with the limiting range, the detected data enter a prediction model for conducting real-time prediction of machining data, analysis and comparison are conducted, when the comparison result of a predicted value and a true value is inconsistent, the predicted value is transmitted into a machining program module for conducting program adjustment according to the predicted value, the program adjustment is conducted to a command regulation and control module, and the command regulation and control module conducts command regulation and control according to a communication protocol of an equipment service layer and terminal equipment of the machining program module, so that self-regulation and control of intelligent numerical control workshop terminal equipment are achieved; and establishing communication between the non-sensitive data and the intelligent numerical control workshop cloud application center through the application service module, transmitting the non-sensitive data into a cloud database for storage, preprocessing the non-sensitive data in the cloud database by the cloud application center data application module, training and correcting the prediction model, transmitting the corrected and updated prediction model into the edge perception node algorithm module by the cloud application center edge application module for periodical update of the prediction model, and realizing real-time update of the edge perception node prediction model through the cloud edge cooperative interaction mechanism.
The beneficial effects of the invention are as follows: according to the cloud-edge cooperative intelligent numerical control workshop self-regulating mode provided by the invention based on the edge computing technology, an intelligent numerical control workshop manufacturing unit edge sensing-cloud cooperative operation-intelligent regulation and control framework is built on the basis of analyzing the operation mechanism and regulation and control characteristics of the numerical control workshop, cloud Bian Liangji cooperative interaction scene deployment is completed, and the computing performance of edge sensing nodes is improved through the judgment logic of a design rule engine; secondly, training and correcting a cloud edge processing model by adopting a long-period memory neural network, and formulating cloud edge cooperative production logic to finish the self-control of intelligent numerical control workshop equipment; finally, the application case verifies that the cloud edge collaborative framework has the characteristics of easy collaboration, easy regulation and control and low time delay, and provides technical support for realizing intelligent production of the numerical control workshop.
Drawings
FIG. 1 is a schematic diagram of a cloud-edge coordinated intelligent numerical control workshop self-regulation system architecture of the invention;
FIG. 2 is a flow chart of a control method of the cloud edge cooperative intelligent numerical control workshop self-regulation system;
FIG. 3 is a flow chart of an alternative application case self-tuning of the present invention;
FIG. 4 is a schematic diagram of a control method architecture according to an alternative embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples, but the invention is not limited to the scope.
As shown in fig. 1, the cloud-edge cooperative intelligent numerical control workshop self-regulation system comprises an intelligent numerical control workshop cloud application center, an intelligent numerical control workshop edge sensing node and an intelligent numerical control workshop terminal device; the intelligent numerical control workshop cloud application center is provided with a cloud database, a data application module and an edge application module, and can also comprise a visualization system, wherein the cloud database is used for storing non-sensitive data uploaded by an edge perception node; the data application module is used for data preprocessing of non-sensitive data in the cloud database and training and correcting of the prediction model; the edge application module is used for issuing an edge perception node prediction model and a processing program; the visualization system is used for the visual display of the intelligent numerical control workshop; the intelligent numerical control workshop edge perception node comprises an equipment service layer, a core data layer and a support service layer, wherein the equipment service layer establishes communication with intelligent numerical control workshop terminal equipment for various communication protocols to perform data acquisition and command interaction; the core data layer comprises a core data module, a data management module, an edge database and a command regulation and control module, wherein the core data module is used for displaying acquired data of terminal equipment, the data management module is used for distinguishing sensitive data from non-sensitive data, the edge database is used for storing the sensitive data of an edge perception node, the data which does not need to be uploaded to a cloud application center are directly stored, the storage pressure of the cloud is relieved, and the command regulation and control module receives commands for supporting a service layer rule engine module and a processing program module and regulates and controls the terminal equipment; the support service layer comprises an application service module, a rule engine module, an algorithm module and a processing program module, wherein the application service module is used for transmitting and interacting cloud edge data, the rule engine module is used for setting rules and ensuring that numerical control workshop equipment operates within a limited range, the algorithm module is used for receiving a prediction model issued by a cloud application center to conduct real-time prediction, and the processing program module is used for receiving a processing program issued by the cloud application center to conduct processing of corresponding working procedures of a workpiece.
Optionally, the terminal equipment of the intelligent numerical control workshop comprises numerical control equipment, a sensor and an early warning device, wherein the numerical control equipment comprises a numerical control machine tool, a detection device, a mechanical arm, an AGV trolley and the like.
Optionally, a file transmission mode between a server and a client is adopted to realize the prediction model interaction between the intelligent numerical control workshop cloud application center and the intelligent numerical control workshop edge perception node; specifically, in the embodiment of the invention, the LSTM prediction model constructed by the invention is based on a Tensorflow architecture, and the Tensorflow model mainly comprises a trained network parameter graph and parameter values, and after a neural network is trained, the model is saved into an HDF5 file format for direct use in the future. Therefore, when the prediction model is built, the built LSTM prediction network finishes training and introduces a model. Save (LSTM. H5) command for storage. By the method, the trained model is integrally stored, and the network and compiling model are not required to be defined in later loading and application, namely, the configuration information of the neural network such as the structure, weight, loss function, optimizer and state and the like is stored. The stored model exists in an LSTM.h5 format, and is sent and received by an edge application module through a python established cloud application center server and an edge perception node client, and is specifically realized by an SSHCLIent command of a Paramiko module in python.
As shown in fig. 2, a cloud-edge cooperative control method for a self-control system of an intelligent numerical control workshop is applied to the cloud-edge cooperative control system of the intelligent numerical control workshop, and includes: the intelligent numerical control workshop terminal equipment establishes communication with the intelligent numerical control workshop edge sensing node through a communication protocol of the equipment service layer, and acquires data to the core data module to display the data of the edge sensing node; the core data module transmits the data to the data management module for data processing, and the data is divided into sensitive data and non-sensitive data (the data applied to the edge sensing node is sensitive data, and the data applied to the intelligent numerical control workshop cloud application center is non-sensitive data); the method comprises the steps that sensitive data are stored in an edge database for further application of edge sensing nodes, the cloud application center is not required to be uploaded for storage, the storage pressure of the cloud application center is relieved, meanwhile, the sensitive data are also transmitted into a rule engine module for judgment according to preset rules, when the detected data exceed a limiting range, the rule is directly triggered to conduct command regulation and control to conduct action response of numerical control equipment, when the detected data accord with the limiting range, the data enter a prediction model for conducting real-time prediction of machining data, analysis and comparison are conducted, when the predicted value is inconsistent with a true value comparison result, the predicted value is transmitted into a command regulation and control module after being subjected to program regulation by a machining program module, the command regulation and control module is used for command regulation and control by a communication protocol of an equipment service layer and terminal equipment according to the machining program module, and therefore intelligent numerical control workshop terminal equipment self-regulation and control are achieved; if the two parameters are consistent, not adjusting the processing program; the method is characterized in that an initial prediction model of the edge perception node algorithm module is firstly trained and issued by the cloud data application module to obtain a prediction, and correction and update of the prediction model are carried out in the later period; and establishing communication between the non-sensitive data and the intelligent numerical control workshop cloud application center through the application service module, transmitting the non-sensitive data into a cloud database for storage, preprocessing the non-sensitive data in the cloud database by the cloud application center data application module, training and correcting the prediction model, transmitting the corrected and updated prediction model into the edge perception node algorithm module by the cloud application center edge application module for periodical update of the prediction model, and realizing real-time update of the edge perception node prediction model through the cloud edge cooperative interaction mechanism, so that the prediction effect of the edge perception node prediction model is always kept to be better.
Further, the process of the cooperative implementation among the working procedures of the intelligent numerical control workshop self-regulating system with cloud edge cooperation is provided as follows:
the intelligent numerical control workshop comprises 1 material warehouse (for storing workpieces to be processed/unqualified products/qualified products), 2 workpiece buffer areas to be processed (for storing the workpieces to be processed), 3 numerical control machine tools (numerical control lathes, numerical control milling machines and numerical control engraving machines), 1 AGV trolley (for material warehouse and material transportation between the workpieces to be processed), 1 mechanical arm (for material taking and clamping of the workpieces among three numerical control devices) and 1 image detection device. Each terminal device of the intelligent numerical control workshop is respectively provided with an edge sensing node, and the edge sensing node (EdgeAwareNode, EAN) is built by adopting RaspberryPi with the edge XFile and related software in a communication mode. The self-regulating system among the procedures of the intelligent numerical control workshop is as follows:
the cloud application center (hereinafter referred to as a cloud) sends instructions, machining programs or prediction models to edge sensing nodes of all the numerical control workshop equipment, the material storage EAN receives a goods taking instruction issued by the cloud, and the stacker takes out workpieces to be machined and conveys the workpieces to the workbench to wait for AGV to take goods. The AGVEAN receives a conveying path machining program issued by the cloud, conveys the workpiece to be machined in the material warehouse to a workpiece to be machined, waits for the mechanical arm EAN to clamp the workpiece, and meanwhile, moves to a finishing workbench to wait for the machined workpiece. The mechanical arm EAN receives a clamping machining program issued by the cloud end, and clamps a workpiece of a workbench to be machined to the numerical control lathe EAN. The method comprises the steps that a numerical control lathe EAN receives a numerical control turning program and a prediction model issued by a cloud end to start machining a workpiece, a sensor in numerical control lathe equipment detects whether clamping of the workpiece is completed, if clamping of a mechanical arm EAN is not completed, the numerical control lathe EAN sends an instruction to a three-grab chuck to clamp the workpiece, machining is performed according to the machining program, meanwhile, the prediction model issued by the cloud end predicts cutting force and workpiece roughness, a prediction result is used for comparing and adjusting the instruction in the machining program, the prediction model is updated in real time by the prediction model corrected by the cloud end, good prediction effect is maintained, and better quality of the machined workpiece is guaranteed. And the numerical control lathe finishes the machining of the workpiece unloaded by the mechanical arm and conveys the workpiece to a numerical control milling machine in the next working procedure for milling, and the milling process of clamping the workpiece by the mechanical arm until the workpiece is engraved by the numerical control engraving machine is the same as the turning process of the numerical control lathe. And after the numerical control engraving is finished, the mechanical arm clamps the workpiece to the image detection device for detection, the image detection EAN receives an image detection program issued by the cloud for analysis and comparison, judges whether the processed workpiece is a qualified product, if not, judges whether the processed workpiece can be reprocessed, and conveys the reprocessable workpiece to corresponding numerical control equipment for reprocessing. The detected workpiece is conveyed to a finishing workbench by the mechanical arm, and is conveyed back to a material warehouse by the waiting AGV trolley, and the material warehouse EAN feeds back inventory information to the cloud application center. And sending instructions and issuing a processing program or a prediction model to edge sensing nodes of all the equipment by the cloud, wherein all the edge sensing nodes finish the processing of the workpiece and the coordination among working procedures, so that the self-regulation and control of the intelligent numerical control workshop are achieved. The specific flow is shown in fig. 3.
The mechanical arm EAN regulation engine module is used for carrying out an example, the mechanical arm angle operation position limiting value is preset by the mechanical arm EAN regulation engine module, and when the information perceived by the EAN exceeds the limiting value set by the regulation module, the mechanical arm shutdown command is directly activated by the EAN regulation module to carry out mechanical arm obstacle avoidance regulation and control, so that the self regulation and control of the edge equipment are realized. Taking a mechanical arm shaft 2 (Axis 2 Pos) as an example, wherein the angle of the Axis2Pos is within the range of 5-35 degrees, and when the Axis2Pos detected by the rule engine is less than 5 degrees, triggering a set rule 1 to execute a mechanical arm stop instruction; when Axis2Pos detected by the rule engine is more than 35 degrees, triggering the set rule 2 to stop the mechanical arm, and realizing the self-regulation and control of the mechanical arm EAN obstacle avoidance.
As shown in fig. 4, specifically, the embodiment of the numerically controlled lathe is developed, the edge sensing node of the numerically controlled lathe is in communication with the numerically controlled lathe through the equipment service layer, the numerical control lathe equipment data, the numerical control lathe operation data, the roughness data and the cutting force data are collected and transmitted to the core data module, the core data module transmits the data to the data management module, the data management module processes the data and distinguishes the sensitive data from the non-sensitive data, the sensitive data are further applied to the edge sensing node and stored in the database of the edge sensing node, the cloud application center is not required to be uploaded for storage, the storage pressure of the application center is relieved, meanwhile, the sensitive data are also transmitted to the rule engine module to judge according to preset rules, the cutting force data is taken as an example, the limiting range of the cutting force is set, when the detected cutting force exceeds the set cutting range, the rule is triggered, the rule engine is in command regulation, the corresponding parameters of the numerically controlled lathe are controlled to restore the cutting force within the limiting range, when the detected data accord with the limiting range, the input data are transmitted to the prediction model, the LSTM neural network is adopted to predict the quality index of the machining data of the numerically controlled time sequence, the machining data is input into the numerical control lathe, the machining process parameters such as the real speed and the real-time index of the machining process is compared with the real-time index of the real-control value of the machining process, and the real-time index is compared with the real-time index, and the real-time-domain, and the machining roughness is not predicted, and the machining process is compared with the real-time-domain, and the machining speed is compared with the machining accuracy, and the machining speed is predicted and the machining speed and the real-time, and the machining speed is compared with the machining speed and the machining speed, the command regulation and control module regulates and controls control parameters of the numerical control lathe according to a processing program by a communication protocol of an equipment service layer, so that a prediction effect of a predicted value is achieved, and self regulation and control of the numerical control lathe is realized; if the two parameters are consistent, not adjusting the processing program; and establishing communication between the non-sensitive data and the cloud application center through the application service module, transmitting the non-sensitive data into a cloud application center database for storage, preprocessing a numerical control lathe data set in the database by the cloud application center data application module, transmitting the data into a prediction model for model training correction, setting a period for model training correction according to actual production and processing conditions, transmitting the corrected and updated prediction model into a numerical control lathe edge perception node algorithm module for periodical update of the prediction model by the cloud application center edge application module (the time for model issuing can also be subjected to custom setting), and realizing real-time update of the edge perception node prediction model through the cloud edge cooperative interaction mechanism, so that the prediction effect of the edge perception node prediction model is always kept to be better.
Taking a numerical control lathe EAN as an example, comparing the situations of an LSTM single prediction model and the cloud side interaction prediction model, wherein the single prediction model is trained by 2000 pieces of historical data, the cloud side interaction prediction model is updated by carrying out model correction on data uploaded by the EAN and is issued once every 2 hours to the numerical control lathe EAN for carrying out real-time prediction, and after 24 hours, the results of the table 1 are obtained through verification, wherein the mean square error value and the fitting value of the prediction effect of the single cloud center prediction model and the cloud side interaction prediction model are shown in the table 1:
table 1 comparison of experimental errors in two modes of LSTM predictive model
As can be seen from the data in the table 1, the cloud-edge collaborative interaction prediction model has better prediction effect, higher fitting degree and smaller mean square error, and the periodic cloud-edge interaction mechanism ensures that the LSTM prediction model is continuously corrected along with the updating of real-time data, and avoids the reduction of the prediction effect caused by the increase of the prediction model along with the time and the data.
While the present invention has been described in detail with reference to the drawings, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Claims (3)
1. The cloud-edge cooperative intelligent numerical control workshop self-regulation and control system is characterized by comprising an intelligent numerical control workshop cloud application center, an intelligent numerical control workshop edge sensing node and intelligent numerical control workshop terminal equipment;
the intelligent numerical control workshop cloud application center is provided with a cloud database, a data application module and an edge application module, wherein the cloud database is used for storing non-sensitive data uploaded by an edge perception node; the data application module is used for data preprocessing of non-sensitive data in the cloud database and training and correcting of the prediction model; the edge application module is used for issuing an edge perception node prediction model and a processing program;
the intelligent numerical control workshop edge perception node comprises an equipment service layer, a core data layer and a support service layer; the equipment service layer establishes communication with the intelligent numerical control workshop terminal equipment through a communication protocol to perform data acquisition and command interaction; the core data layer comprises a core data module, a data management module, an edge database and a command regulation module, wherein the core data module is used for displaying acquired data of the terminal equipment, the data management module is used for distinguishing sensitive data from non-sensitive data, the edge database is used for storing the sensitive data, and the command regulation module is used for receiving commands of a rule engine module and a processing program module of a support service layer and regulating and controlling the terminal equipment; the support service layer comprises an application service module, a rule engine module, an algorithm module and a processing program module, wherein the application service module is used for transmitting and interacting cloud edge data, the rule engine module is used for setting rules, the algorithm module is used for receiving a prediction model issued by a cloud application center to conduct real-time prediction, and the processing program module is used for receiving a processing program issued by the cloud application center to conduct processing of corresponding working procedures of a workpiece.
2. The cloud-edge collaborative intelligent numerical control workshop self-regulation system according to claim 1, wherein the prediction model interaction between an intelligent numerical control workshop cloud application center and an intelligent numerical control workshop edge sensing node is realized by adopting a file transmission mode between a server and a client.
3. A control method of a cloud-edge cooperative intelligent numerical control workshop self-regulation system, which is characterized in that the method is applied to the cloud-edge cooperative intelligent numerical control workshop self-regulation system according to any one of claims 1-2, and comprises the following steps:
the intelligent numerical control workshop terminal equipment establishes communication with the intelligent numerical control workshop edge sensing node through a communication protocol of the equipment service layer, and acquires data to the core data module to display the data of the edge sensing node;
the core data module transmits the data to the data management module for data processing, and the data is divided into sensitive data and non-sensitive data;
the method comprises the steps that sensitive data are stored in an edge database for further application of edge sensing nodes, meanwhile, the sensitive data are also transmitted into a rule engine module for judgment according to preset rules, when the detected data exceed a limiting range, the rule is directly triggered to conduct command regulation and control to conduct action response of numerical control equipment, when the detected data accord with the limiting range, the detected data enter a prediction model for conducting real-time prediction of machining data, analysis and comparison are conducted, when the comparison result of a predicted value and a true value is inconsistent, the predicted value is transmitted into a machining program module for conducting program adjustment according to the predicted value, the program adjustment is conducted to a command regulation and control module, and the command regulation and control module conducts command regulation and control according to a communication protocol of an equipment service layer and terminal equipment of the machining program module, so that self-regulation and control of intelligent numerical control workshop terminal equipment are achieved;
and establishing communication between the non-sensitive data and the intelligent numerical control workshop cloud application center through the application service module, transmitting the non-sensitive data into a cloud database for storage, preprocessing the non-sensitive data in the cloud database by the cloud application center data application module, training and correcting the prediction model, transmitting the corrected and updated prediction model into the edge perception node algorithm module by the cloud application center edge application module for periodical update of the prediction model, and realizing real-time update of the edge perception node prediction model through the cloud edge cooperative interaction mechanism.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310014075.4A CN116032969B (en) | 2023-01-05 | 2023-01-05 | Cloud-edge cooperative intelligent numerical control workshop self-regulation system and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310014075.4A CN116032969B (en) | 2023-01-05 | 2023-01-05 | Cloud-edge cooperative intelligent numerical control workshop self-regulation system and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116032969A true CN116032969A (en) | 2023-04-28 |
| CN116032969B CN116032969B (en) | 2024-02-20 |
Family
ID=86079057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310014075.4A Active CN116032969B (en) | 2023-01-05 | 2023-01-05 | Cloud-edge cooperative intelligent numerical control workshop self-regulation system and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116032969B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116542656A (en) * | 2023-07-05 | 2023-08-04 | 煤炭科学技术研究院有限公司 | Cloud-edge combined intelligent operation and maintenance system and method for mining equipment |
| CN116740821A (en) * | 2023-08-16 | 2023-09-12 | 南京迅集科技有限公司 | Intelligent workshop control method and system based on edge calculation |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112073461A (en) * | 2020-08-05 | 2020-12-11 | 烽火通信科技股份有限公司 | Industrial Internet system based on cloud edge cooperation |
| CN112270429A (en) * | 2020-08-31 | 2021-01-26 | 中国科学院合肥物质科学研究院 | Cloud edge cooperation-based power battery pole piece manufacturing equipment maintenance method and system |
| WO2021067140A1 (en) * | 2019-10-04 | 2021-04-08 | Intel Corporation | Edge computing technologies for transport layer congestion control and point-of-presence optimizations based on extended in-advance quality of service notifications |
| CN113379135A (en) * | 2021-06-18 | 2021-09-10 | 浙江大学 | Intelligent production line product quality low-delay integrated prediction method and system based on cloud edge collaborative computing |
| CN114924889A (en) * | 2022-06-21 | 2022-08-19 | 浙江大学 | Cloud-edge-end-cooperation-based ultra-low emission intelligent regulation and control system and method |
| CN114971574A (en) * | 2022-06-14 | 2022-08-30 | 北京航天长峰科技工业集团有限公司 | Multi-mode information composite sensing and fusion framework and method based on cloud edge cooperation |
| CN115086315A (en) * | 2022-06-08 | 2022-09-20 | 徐州医科大学 | Cloud edge collaborative security authentication method and system based on image sensitivity identification |
-
2023
- 2023-01-05 CN CN202310014075.4A patent/CN116032969B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021067140A1 (en) * | 2019-10-04 | 2021-04-08 | Intel Corporation | Edge computing technologies for transport layer congestion control and point-of-presence optimizations based on extended in-advance quality of service notifications |
| CN112073461A (en) * | 2020-08-05 | 2020-12-11 | 烽火通信科技股份有限公司 | Industrial Internet system based on cloud edge cooperation |
| CN112270429A (en) * | 2020-08-31 | 2021-01-26 | 中国科学院合肥物质科学研究院 | Cloud edge cooperation-based power battery pole piece manufacturing equipment maintenance method and system |
| CN113379135A (en) * | 2021-06-18 | 2021-09-10 | 浙江大学 | Intelligent production line product quality low-delay integrated prediction method and system based on cloud edge collaborative computing |
| CN115086315A (en) * | 2022-06-08 | 2022-09-20 | 徐州医科大学 | Cloud edge collaborative security authentication method and system based on image sensitivity identification |
| CN114971574A (en) * | 2022-06-14 | 2022-08-30 | 北京航天长峰科技工业集团有限公司 | Multi-mode information composite sensing and fusion framework and method based on cloud edge cooperation |
| CN114924889A (en) * | 2022-06-21 | 2022-08-19 | 浙江大学 | Cloud-edge-end-cooperation-based ultra-low emission intelligent regulation and control system and method |
Non-Patent Citations (2)
| Title |
|---|
| ZHIFENG YUE、ZHIXIANG ZHU: ""Research on Big Data Processing Model of Edge-Cloud Collaboration in Cyber Physical Systems"", 《2020 5TH IEEE INTERNATIONAL CONFERENCE ON BIG DATA ANALYTICS (ICBDA)》, 27 May 2020 (2020-05-27) * |
| 杨绍光;房秉毅;王增森;郭澄宇;曲秀超;: "云边协同关键技术及应用场景研究", 信息通信技术, no. 04, 15 August 2020 (2020-08-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116542656A (en) * | 2023-07-05 | 2023-08-04 | 煤炭科学技术研究院有限公司 | Cloud-edge combined intelligent operation and maintenance system and method for mining equipment |
| CN116542656B (en) * | 2023-07-05 | 2023-09-22 | 煤炭科学技术研究院有限公司 | Cloud-edge combined intelligent operation and maintenance system and method for mining equipment |
| CN116740821A (en) * | 2023-08-16 | 2023-09-12 | 南京迅集科技有限公司 | Intelligent workshop control method and system based on edge calculation |
| CN116740821B (en) * | 2023-08-16 | 2023-10-24 | 南京迅集科技有限公司 | Intelligent workshop control method and system based on edge calculation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116032969B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116032969B (en) | Cloud-edge cooperative intelligent numerical control workshop self-regulation system and control method | |
| US20210237136A1 (en) | Method and machine system for controlling an industrial operation | |
| Liu et al. | Cyber-physical machine tool–the era of machine tool 4.0 | |
| US11156985B2 (en) | System for optimization of industrial machine operation through modification of standard process parameter input | |
| WO2020007016A1 (en) | Dynamic linkage control method for automatic production process of intelligent workshop based on digital twin | |
| JP2018530829A (en) | Industrial robot process cloud system and method of operating the same | |
| US10423152B2 (en) | Information processing apparatus for processing machining information between plurality of manufacturing cells | |
| US20210390160A1 (en) | Base analytics engine modeling for monitoring, diagnostics optimization and control | |
| WO2017142470A1 (en) | Method and machine system for controlling an industrial operation | |
| JP7221196B2 (en) | Processing equipment error correction method and system | |
| CN112558576A (en) | Safe and efficient automatic integrated control method and system | |
| US10678231B2 (en) | Production controller equipped with function of identifying cause upon operation stop of production facility including manufacturing facilities | |
| CN111352398A (en) | Intelligent precision machining unit | |
| Djurdjanovic et al. | Process and operations control in modern manufacturing | |
| Azizi et al. | Applications of control engineering in industry 4.0: utilizing internet of things to design an agent based control architecture for smart material handling system | |
| Zhang et al. | A model-driven dynamic synchronization mechanism of lifecycle business activity for complicated and customized products | |
| KR20230081136A (en) | Platform system for recommendating cutting tool according usage | |
| Schmid et al. | Tacit knowledge based acquisition of verified machining data | |
| CN116165966B (en) | Informationized self-adaptive material regulation and control method and system for numerical control machine tool | |
| Živanović et al. | Machine tools and industry 4.0-trends of development | |
| Kononov et al. | Intelligent solutions for industrial automation | |
| Škulj et al. | Geometry and temperature data fusion for automated measurement during open die forging of large hot workpieces | |
| Liu et al. | Technology Architecture and Key Technologies of Discrete Manufacturing Digital Workshop | |
| SE1651097A1 (en) | Modification of input data | |
| Deshayes et al. | Towards an information processing representation for dynamic process optimization in smart machining systems |
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 |