CN113469245A - Data identification method based on industrial internet - Google Patents
Data identification method based on industrial internet Download PDFInfo
- Publication number
- CN113469245A CN113469245A CN202110733918.7A CN202110733918A CN113469245A CN 113469245 A CN113469245 A CN 113469245A CN 202110733918 A CN202110733918 A CN 202110733918A CN 113469245 A CN113469245 A CN 113469245A
- Authority
- CN
- China
- Prior art keywords
- data
- network
- network structure
- industrial internet
- sub
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/25—Manufacturing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/75—Information technology; Communication
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/20—Information sensed or collected by the things relating to the thing itself
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y30/00—IoT infrastructure
- G16Y30/10—Security thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
Abstract
The invention discloses a data identification method based on an industrial internet, and relates to the technical field of data identification. The invention comprises the following steps: accessing network equipment and a host of an industrial Internet, and acquiring IDs (identity) of the network equipment and the host, description files, service interfaces and networking objects; acquiring an output signal of equipment in a working process by using an Ethernet communication interface to prepare a network data set; collecting the network data into a training sample set to generate a network structure of a data recognition model; the network data set trains a data recognition model having a sub-network structure to determine parameters of operation at each node in the sub-network structure to generate the data recognition model. According to the invention, the ID, the description file, the service interface and the networking object of the network equipment and the host are obtained, and the network data set is made by combining the output signals and is used as the training set to train the data recognition model, so that the speed and the accuracy of data recognition are improved.
Description
Technical Field
The invention belongs to the technical field of data identification, and particularly relates to a data identification method based on an industrial internet.
Background
Industrial internet is a result of the convergence of global industrial systems with advanced computing, analytics, sensing technologies and internet connectivity. The essence of the industrial internet is that equipment, production lines, factories, suppliers, products and customers are closely connected and fused through an open and global industrial-level network platform, and various element resources in industrial economy are efficiently shared, so that the cost is reduced, the efficiency is increased, the manufacturing industry is helped to extend the industrial chain, and the transformation development of the manufacturing industry is promoted through an automatic and intelligent production mode.
After many years of security construction of industrial internet, operators construct a complete security control system and system according to their own needs, especially in terms of data security, but with ever-growing business, the requirements for data security protection are higher and higher. The method mainly comprises the following two aspects:
(1) the data model expands rapidly, so that the control difficulty is increased: with the rapid development of industrial equipment, rapid change and iteration are required to be performed on a data model to adapt to business requirements, but usually, designers and operation and maintenance personnel cannot understand the data model from a global perspective, so that the data model has to be maintained in a 'patching' mode;
(2) the data cannot be accurately identified: at present, data recognition mainly depends on a dictionary matching method and a manual recognition method, but the two methods cannot achieve good effects and are mainly embodied as follows: the method has the advantages that the recognition precision is low, the dictionary matching adopts a mode of patterned matching, so that the recognition precision is determined by establishing a data dictionary, and when the dictionary is incomplete or wrong, the problem of reduced recognition progress can occur; secondly, the recognition speed is slow, the period is long, and the requirement on the professional quality of a processor is high; and thirdly, the judgment standards are not uniform, so that the equipment identification results have differences.
Disclosure of Invention
The invention aims to provide a data identification method based on an industrial internet, which is used for training a data identification model by acquiring IDs (identity) of network equipment and a host computer, description files, service interfaces and networking objects and combining output signals to make a network data set as a training set, and solves the problem that data cannot be accurately identified due to various industrial equipment in the prior art.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a data identification method based on an industrial internet, which comprises the following steps:
step S1: accessing network equipment and a host of an industrial Internet, and acquiring IDs (identity) of the network equipment and the host, description files, service interfaces and networking objects;
step S2: using an Ethernet communication interface to collect an output signal in the working process of equipment;
step S3: preprocessing the obtained ID, description file, service interface, networking object and output signal to make a network data set;
step S4: collecting the network data into a training sample set to generate a network structure of a data recognition model;
step S5: determining a network structure parameter space of a data identification model to be generated based on the data type to be identified, sampling parameters of a sub-network structure with a scale from the parameter space of the network structure, and constructing the network structure for the data identification model according to the parameters of the sub-network structure, so as to obtain the operation of each node of the sub-network structure;
step S6: the network data set trains a data recognition model having a sub-network structure to determine parameters of operation at each node in the sub-network structure to generate the data recognition model.
Preferably, in the step S1, the IDs of the network device and the host are globally unique identifiers of devices in the industrial internet; the description file is a digital specification for expressing the characteristics and functions of equipment in the industrial Internet; the service interface is an interface for data and information retrieval, query and interaction between equipment in the industrial internet and the internet; the networked object is a target object with communication capability.
Preferably, in step S2, the acquiring device for acquiring the output signal of the equipment engineering process includes: the device comprises a main control unit, and an analog signal amplification unit, a switching value signal acquisition unit, an output unit and a communication unit which are respectively connected with the main control unit; the acquisition device is used for amplifying and acquiring external analog signals through an amplifier arranged in the main control unit or an analog signal amplification unit, acquiring external switching value signals and transmitting the acquired external signals to superior equipment.
Preferably, in step S3, the preprocessing includes performing data cleaning, data integration, data transformation, and data specification on the acquired ID, description file, service interface, networking object, and output signal in sequence, and the preprocessed data can be made into a JSON data set.
Preferably, in step S4, the training sample set needs to be subjected to complexity calculation, and the scale of the network structure of the data recognition model generated by the updated training sample set is calculated based on the complexity.
Preferably, the complexity is intra-class complexity, inter-class complexity, or a combination of intra-class complexity and inter-class complexity.
Preferably, the scale of the network structure represents the scale of the data recognition model through the number of network layers and the number of channels; the parameter space of the network structure comprises the number of network layers, the number of channels, a tensor operation mode adopted by each layer of network and a connection mode among the layer networks, each part of the parameter space of the network structure is represented by a number in a specific value range, and a vector formed by the numbers of the determined values of each part of the parameter space of the network structure represents a determined sub-network structure.
Preferably, in the step S5, in the process of training the data recognition model of the sub-network structure to determine the operation and the parameters involved in the operation at each node in the sub-network structure,
when the scale of the updated training sample set is smaller than that of the current training sample set, the scale of the updated model is smaller than that of the previous model: pruning and fine-tuning parameters of a previous model to accelerate the training speed of the updated sub-network;
and when the scale of the updated training sample set is larger than that of the current training sample set, training the data recognition model with the network structure with the adaptive size added on the basis of the current data recognition model by using the updated training sample set, and accelerating the training speed by adopting parameter replication fine tuning or characteristic normalization scale transformation.
The invention has the following beneficial effects:
according to the invention, the IDs, the description files, the service interfaces and the networking objects of the network equipment and the host are obtained, and the network data set is made by combining the output signals and is used as the training set for training the data recognition model, and the acquired data is directly input into the data recognition model for recognition, so that the speed and the accuracy of data recognition are improved.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a step diagram of a data identification method based on the industrial internet according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a data identification method based on industrial internet, including the following steps:
step S1: accessing network equipment and a host of an industrial Internet, and acquiring IDs (identity) of the network equipment and the host, description files, service interfaces and networking objects;
step S2: using an Ethernet communication interface to collect an output signal in the working process of equipment;
step S3: preprocessing the obtained ID, description file, service interface, networking object and output signal to make a network data set;
step S4: collecting the network data into a training sample set to generate a network structure of a data recognition model;
step S5: determining a network structure parameter space of a data identification model to be generated based on the data type to be identified, sampling parameters of a sub-network structure with a scale from the parameter space of the network structure, and constructing the network structure for the data identification model according to the parameters of the sub-network structure, so as to obtain the operation of each node of the sub-network structure;
step S6: the network data set trains a data recognition model having a sub-network structure to determine parameters of operation at each node in the sub-network structure to generate the data recognition model.
In step S1, the IDs of the network device and the host are global unique identifiers of devices in the industrial internet, that is, permanent and one name symbols for identifying and distinguishing industrial internet components are used, and Handle identification codes are used as an identification technology of the industrial internet components in the present application document, so as to improve the practicability of the industrial internet components; the description file is a digital specification for expressing the characteristics and functions of equipment in the industrial Internet, and is also a definition and a directory list for activating various functions, information, communication and other services of a content object of the basic components of the industrial Internet into a hierarchical range, and the self description of the components can be read by referring to the description file, so that information interaction is carried out on the components in a proper mode; the service interface is an interface for data and information retrieval, query and interaction between equipment in the industrial internet and the internet; the networked object is a target object with communication capability.
In step S2, the acquisition device for acquiring the output signal in the process of equipment engineering includes: the device comprises a main control unit, and an analog signal amplification unit, a switching value signal acquisition unit, an output unit and a communication unit which are respectively connected with the main control unit; the acquisition device is used for amplifying and acquiring external analog signals through an amplifier arranged in the main control unit or an analog signal amplification unit, acquiring external switching value signals and transmitting the acquired external signals to superior equipment.
In step S3, the preprocessing includes data cleaning, data integration, data change, and data specification sequentially performed on the acquired ID, description file, service interface, networking object, and output signal, and the preprocessed data can be made into a JSON data set.
In step S4, the training sample set needs to be subjected to complexity calculation, and the scale of the network structure of the data recognition model generated by the updated training sample set is calculated based on the complexity.
Wherein the complexity is intra-class complexity, inter-class complexity, or a combination of intra-class complexity and inter-class complexity.
The scale of the network structure represents the scale of the data identification model through the number of network layers and the number of channels; the parameter space of the network structure comprises the number of network layers, the number of channels, a tensor operation mode adopted by each layer network and a connection mode among the layer networks, each part of the parameter space of the network structure is represented by a number in a specific value range, and a vector formed by the determined value numbers of each part of the parameter space of the network structure represents a determined sub-network structure.
Wherein, in step S5, in the process of training the data recognition model of the sub-network structure to determine the operation at each node in the sub-network structure and the parameters involved in the operation,
when the scale of the updated training sample set is smaller than that of the current training sample set, the scale of the updated model is smaller than that of the previous model: pruning and fine-tuning parameters of a previous model to accelerate the training speed of the updated sub-network;
and when the scale of the updated training sample set is larger than that of the current training sample set, training the data recognition model with the network structure with the adaptive size added on the basis of the current data recognition model by using the updated training sample set, and accelerating the training speed by adopting parameter replication fine tuning or characteristic normalization scale transformation.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. A data identification method based on industrial Internet is characterized by comprising the following steps:
step S1: accessing network equipment and a host of an industrial Internet, and acquiring IDs (identity) of the network equipment and the host, description files, service interfaces and networking objects;
step S2: using an Ethernet communication interface to collect an output signal in the working process of equipment;
step S3: preprocessing the obtained ID, description file, service interface, networking object and output signal to make a network data set;
step S4: collecting the network data into a training sample set to generate a network structure of a data recognition model;
step S5: determining a network structure parameter space of a data identification model to be generated based on the data type to be identified, sampling parameters of a sub-network structure with a scale from the parameter space of the network structure, and constructing the network structure for the data identification model according to the parameters of the sub-network structure, so as to obtain the operation of each node of the sub-network structure;
step S6: the network data set trains a data recognition model having a sub-network structure to determine parameters of operation at each node in the sub-network structure to generate the data recognition model.
2. The industrial internet-based data identification method according to claim 1, wherein in the step S1, the IDs of the network device and the host are globally unique identifiers of devices in the industrial internet; the description file is a digital specification for expressing the characteristics and functions of equipment in the industrial Internet; the service interface is an interface for data and information retrieval, query and interaction between equipment in the industrial internet and the internet; the networked object is a target object with communication capability.
3. The industrial internet-based data recognition method of claim 1, wherein in the step S2, the collecting device for collecting the output signal of the equipment engineering process comprises: the device comprises a main control unit, and an analog signal amplification unit, a switching value signal acquisition unit, an output unit and a communication unit which are respectively connected with the main control unit; the acquisition device is used for amplifying and acquiring external analog signals through an amplifier arranged in the main control unit or an analog signal amplification unit, acquiring external switching value signals and transmitting the acquired external signals to superior equipment.
4. The industrial internet-based data identification method according to claim 1, wherein in the step S3, the preprocessing includes performing data cleansing, data integration, data transformation and data specification on the obtained ID, description file, service interface, networking object and output signal in sequence, and the preprocessed data can be made into a JSON data set.
5. The industrial internet-based data identification method of claim 1, wherein in the step S4, the training sample set is required to be subjected to complexity calculation, and the scale of the network structure of the data identification model generated by the updated training sample set is calculated based on the complexity.
6. The industrial internet-based data identification method of claim 5, wherein the complexity is an intra-class complexity, an inter-class complexity, or a combination of the intra-class complexity and the inter-class complexity.
7. The industrial internet-based data recognition method according to claim 5, wherein the scale of the network structure represents the scale of the data recognition model by the number of network layers and the number of channels; the parameter space of the network structure comprises the number of network layers, the number of channels, a tensor operation mode adopted by each layer of network and a connection mode among the layer networks, each part of the parameter space of the network structure is represented by a number in a specific value range, and a vector formed by the numbers of the determined values of each part of the parameter space of the network structure represents a determined sub-network structure.
8. The industrial Internet-based data recognition method of claim 1, wherein in the step S5, in the process of training a data recognition model of a sub-network structure to determine the operation at each node in the sub-network structure and the parameters involved in the operation,
when the scale of the updated training sample set is smaller than that of the current training sample set, the scale of the updated model is smaller than that of the previous model: pruning and fine-tuning parameters of a previous model to accelerate the training speed of the updated sub-network;
and when the scale of the updated training sample set is larger than that of the current training sample set, training the data recognition model with the network structure with the adaptive size added on the basis of the current data recognition model by using the updated training sample set, and accelerating the training speed by adopting parameter replication fine tuning or characteristic normalization scale transformation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110733918.7A CN113469245A (en) | 2021-06-30 | 2021-06-30 | Data identification method based on industrial internet |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110733918.7A CN113469245A (en) | 2021-06-30 | 2021-06-30 | Data identification method based on industrial internet |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113469245A true CN113469245A (en) | 2021-10-01 |
Family
ID=77874344
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110733918.7A Pending CN113469245A (en) | 2021-06-30 | 2021-06-30 | Data identification method based on industrial internet |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113469245A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107197001A (en) * | 2017-05-05 | 2017-09-22 | 工业和信息化部电信研究院 | A kind of industry internet module information method |
CN111985601A (en) * | 2019-05-21 | 2020-11-24 | 富士通株式会社 | Data identification method for incremental learning |
-
2021
- 2021-06-30 CN CN202110733918.7A patent/CN113469245A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107197001A (en) * | 2017-05-05 | 2017-09-22 | 工业和信息化部电信研究院 | A kind of industry internet module information method |
CN111985601A (en) * | 2019-05-21 | 2020-11-24 | 富士通株式会社 | Data identification method for incremental learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Khare et al. | Big data in IoT | |
CN114816909B (en) | Real-time log detection early warning method and system based on machine learning | |
CN109150640A (en) | A kind of method for discovering network topology and system based on double layer network agreement | |
US20150188879A1 (en) | Apparatus for grouping servers, a method for grouping servers and a recording medium | |
Cemernek et al. | Big data as a promoter of industry 4.0: Lessons of the semiconductor industry | |
CN113176948B (en) | Edge gateway, edge computing system and configuration method thereof | |
CN113179190B (en) | Edge controller, edge computing system and configuration method thereof | |
CN112860676B (en) | Data cleaning method applied to big data mining and business analysis and cloud server | |
CN112182007A (en) | Cloud computing data processing method based on artificial intelligence and artificial intelligence platform | |
CN113810489A (en) | Industrial internet control system and method | |
CN114153980A (en) | Knowledge graph construction method and device, inspection method and storage medium | |
CN106874442B (en) | Method and device for realizing self-carrying characteristic information of data through naming of data name | |
CN112100402A (en) | Power grid knowledge graph construction method and device | |
Li et al. | Street-Level Landmarks Acquisition Based on SVM Classifiers. | |
CN113672692A (en) | Data processing method, data processing device, computer equipment and storage medium | |
CN113469245A (en) | Data identification method based on industrial internet | |
US20150058466A1 (en) | Device for server grouping | |
CN111368060A (en) | Self-learning method, device and system for conversation robot, electronic equipment and medium | |
CN108427744B (en) | Intelligent data association relation determining method based on information operation and maintenance | |
CN116599857A (en) | Digital twin application system suitable for multiple scenes of Internet of things | |
CN111817935A (en) | Internet intelligent home data processing method and system | |
CN113761121B (en) | Knowledge extraction method for structured data | |
CN106296420A (en) | A kind of community discovery method | |
CN113986990B (en) | Data resource acquisition and labeling method and device based on block chain data mining | |
CN117041121B (en) | Internet of Things anomaly monitoring method and system based on data mining |
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: 20211001 |