KR20160148911A - Integrated information system - Google Patents
Integrated information system Download PDFInfo
- Publication number
- KR20160148911A KR20160148911A KR1020150085698A KR20150085698A KR20160148911A KR 20160148911 A KR20160148911 A KR 20160148911A KR 1020150085698 A KR1020150085698 A KR 1020150085698A KR 20150085698 A KR20150085698 A KR 20150085698A KR 20160148911 A KR20160148911 A KR 20160148911A
- Authority
- KR
- South Korea
- Prior art keywords
- data
- analysis
- manager
- framework
- container
- Prior art date
Links
- 238000000034 method Methods 0.000 claims abstract description 92
- 238000004458 analytical method Methods 0.000 claims abstract description 83
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000005516 engineering process Methods 0.000 claims abstract description 24
- 238000012795 verification Methods 0.000 claims abstract description 21
- 230000010354 integration Effects 0.000 claims abstract description 19
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 238000012800 visualization Methods 0.000 claims abstract description 15
- 238000004519 manufacturing process Methods 0.000 claims description 55
- 230000008569 process Effects 0.000 claims description 50
- 238000007405 data analysis Methods 0.000 claims description 44
- 238000013524 data verification Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 26
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 23
- 238000007726 management method Methods 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 16
- 238000007418 data mining Methods 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000013480 data collection Methods 0.000 claims description 9
- 238000013079 data visualisation Methods 0.000 claims description 9
- 238000007619 statistical method Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 22
- 238000006243 chemical reaction Methods 0.000 description 20
- 238000005259 measurement Methods 0.000 description 13
- 230000018109 developmental process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 8
- 238000011161 development Methods 0.000 description 6
- 238000003050 experimental design method Methods 0.000 description 6
- 238000002360 preparation method Methods 0.000 description 6
- 230000014509 gene expression Effects 0.000 description 5
- 230000006872 improvement Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 230000001788 irregular Effects 0.000 description 4
- 238000013439 planning Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000033772 system development Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010000372 Accident at work Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004374 forensic analysis Methods 0.000 description 1
- 238000007417 hierarchical cluster analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a framework for integrating IoT-based context recognition device and software using ARM, and a method for performing context recognition based on FPGA and collecting and processing data for providing to the framework through context recognition A situation recognition device, a data set and an API set for each industrial type that is processed and updated through the framework and used in the framework, and the collected data is analyzed and verified based on the data sets and API sets for each industry type A visualization module for visualizing data produced through analysis, verification, and processing, and a service support module for providing services in a mobile and a web, Implementation of information integration system based on verification technology and HW-SW fusion framework To parties.
Description
Various embodiments of the present invention are directed to an apparatus for collecting and processing data based on the Internet of objects, and more particularly, to an apparatus and method for analyzing and verifying data for all manufacturing processes and reducing manufacturing processes, reducing defect rates, Process data analysis and verification technology for each type of industry, and an information integration system based on the HW-SW fusion framework, which can optimize the manufacturing environment through process improvement and standard data acquisition in the manufacturing process.
The development of electronic and communication industries has been variously attempted for convergence devices in which electronic / wireless communication functions are combined with electronic devices. An example of this could be the internet of things (IoT) or the internet of Everything (IoE). IoT and IoE will be collectively referred to as the 'Internet of things'.
The Internet refers to an environment in which objects in daily life are connected to a wired / wireless network to share information. For example, the Internet of things includes not only household appliances and home appliances but also healthcare, remote reading of meters, smart factories, smart homes, smart cars, etc. It enables the sharing of information by connecting objects in various fields via networks. It can be expected that the Internet of Things will increase the demand for the utilization of information gathered in various fields.
An object of the present invention is to provide an information integration system based on HW-SW integration framework composed of devices and APIs using FPGA-based IoT context recognition chip technology for improvement of manufacturing process.
The present invention relates to a framework for integrating IoT-based context recognition device and software using ARM, and a method for performing context recognition based on FPGA and collecting and processing data for providing to the framework through context recognition A situation recognition device, a data set and an API set for each industrial type that is processed and updated through the framework and used in the framework, and the collected data is analyzed and verified based on the data sets and API sets for each industry type A visualization module for visualizing data produced through analysis, verification, and processing; and a service support module for providing services to the mobile and the web in general.
The present invention is advantageous in that it is possible to reduce the development cost and shorten the time by reusing software and to develop a standard API for data analysis and to maintain consistency in software development.
In addition, since the present invention can establish a standard analysis process for each industry type, it is possible to reflect requirements in various domains, and it is possible to establish a technical structure for each domain.
In addition, the present invention can be expected to improve processing speed and increase the efficiency of index storage and management through distributed processing for big data, and also can be applied to data analysis So that flexibility and objectivity can be secured.
1 is a schematic diagram schematically illustrating the configuration of a framework for integrating IoT-based context-aware devices and software using ARM, according to various embodiments of the present invention.
Figure 2 is a diagram illustrating the configuration of a context-aware device for IoT-based data collection and processing, in accordance with various embodiments of the present invention.
3 is a diagram illustrating a configuration of an HW-SW integration framework according to various embodiments of the present invention.
FIG. 4 is a diagram showing the configuration of the
5 is a view showing a configuration of the
FIG. 6 is a diagram showing a configuration of the
FIG. 7 is a diagram showing a configuration of the data analysis and
FIG. 8 is a view showing a configuration of the
FIG. 9 is a diagram showing the configuration of the
FIG. 10 is a diagram showing the configuration of the
11 is a diagram showing a method of developing an API according to the present invention in detail.
12 is a diagram showing a data analysis and verification technique and a data visualization technique according to the present invention.
FIG. 13 is a diagram showing a configuration of a
FIG. 14 is a diagram showing a configuration of the
15 is a view showing a forensic preparation diagram according to the present invention.
16 is a diagram illustrating a configuration of a forensic monitoring system according to the present invention.
Various embodiments of the invention will now be described with reference to the accompanying drawings. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes various modifications, equivalents, and / or alternatives of the embodiments of the invention. In connection with the description of the drawings, like reference numerals may be used for similar components.
In this document, the expressions " having, " " having, " " comprising, " or &Quot;, and does not exclude the presence of additional features.
In this document, the expressions "A or B," "at least one of A or / and B," or "one or more of A and / or B," etc. may include all possible combinations of the listed items . For example, "A or B," "at least one of A and B," or "at least one of A or B" includes (1) at least one A, (2) Or (3) at least one A and at least one B all together.
As used herein, the phrase " configured to " (or set) to be " configured according to circumstances may include, for example, having the capacity to, To be designed to, "" adapted to, "" made to, "or" capable of ". The term " configured (or set) to " may not necessarily mean " specifically designed to " Instead, in some situations, the expression " configured to " may mean that the device can " do " with other devices or components. For example, a processor configured (or configured) to perform the phrases " A, B, and C " may be a processor dedicated to performing the operation (e.g., an embedded processor), or one or more software programs To a generic-purpose processor (e.g., a CPU or an application processor) that can perform the corresponding operations.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the other embodiments. The singular expressions may include plural expressions unless the context clearly dictates otherwise. All terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by one of ordinary skill in the art. Commonly used predefined terms may be interpreted to have the same or similar meaning as the contextual meanings of the related art and are not to be construed as ideal or overly formal in meaning unless expressly defined in this document . In some cases, the terms defined in this document can not be construed to exclude embodiments of the present invention.
The IoT (internet of thins) based context recognition device proposed in the present invention can be used to collect and transmit raw data on a manufacturing site, to perform data processing including basic analysis and visualization for providing information to an operator, Storage of TA (Technical Architecture) and situation recognition rules derived from data analysis results, utilization of mobile storage device (SSD / SD Card), and the like.
At this time, the raw data are sensor data collected from the manufacturing equipment, equipment status information, characteristic values of the product, work instruction information, and the raw data is collected through the external interface of the developing device and transmitted to the server. The external interface uses serial communication such as RS232C and RS485, Ethernet based wired / wireless communication such as LAN / WiFi, and Bluetooth wireless communication technology. Inside the device, temporary storage of input data using a removable storage device (SSD / SD Card), context recognition processing based on input data, and analysis and information provision function through display and visualization module are performed. The input data transmitted from the device to the server derives the analysis result and information using the various analysis techniques developed and generates rules, standard data set, TA (Technical Architecture) for situation recognition and process management based on the obtained result, And feeds back to the device. These devices enable manufacturers in harsh environments to leverage the results of the Big Data analysis, which is captured in the work environment.
Specifically, the device for presenting the present invention, specifically, a situation recognition device for IoT-based data acquisition and processing, includes a property value, an initial value, and the like of a product that can be acquired at the time of manufacture and environmental data generated in a manufacturing environment of the product (Standard) data obtained by analyzing and verifying based on the Big Data-R statistical analysis method. Standard TA applied to the above equipment can be updated through continued analysis / verification. The set values and TA for various manufacturing equipments can be set, so it can be applied universally to various manufacturing equipments.
The situation recognition device for IoT-based data collection and processing proposed in the present invention develops and uses a situation recognition chip using an FPGA (Field Programmable Gate Array) technology, and processes it with a basic analysis algorithm. In addition, various data (including 3D drawing data) can be collected and stored using the portable storage device and the EEPROM, and standard values for the manufacturing equipment and the manufacturing group can be inputted and modified. By reading the setting value for each manufacturing equipment from the EEPROM, it can cope with the variety of the installation situation. In addition, the developed TA is read from the EEPROM to maintain the optimized environment for each manufacturing process.
In this case, the Field Programmable Gate Array (FPGA) is a semiconductor device including a programmable logic element (logic block) and a programmable internal line. The logic block is a combination of AND, OR, XOR, NOT, Function can be duplicated and programmed. In addition, most FPGAs contain memory elements in logical blocks with simple flip-flops or more complete memory blocks. The programmable inner-line hierarchy allows the logic blocks of the FPGA to be interconnected as a single-chip programmable breadboard as system designers require. This logic block and the internal lines can be programmed by the consumer / designer after the manufacturing process and thus can perform any logic function required.
Meanwhile, the situation recognition device for the IoT-based data collection and processing can mount a portable storage device (SSD / SD card) and can perform backup of collected data periodically. That is, the situation recognition device acquires the collected data. It inputs the environmental measurement data such as temperature and humidity as well as the data provided by the manufacturing equipment, as data, and utilizes it for analysis. Also, when the manufacturing equipment measures and provides data on the surrounding environment, the relationship between the equipment and the environment can be analyzed by comparing the measurement value of the manufacturing equipment with the environmental measurement data using the sensor module of the device. If the manufacturing equipment does not measure and provide environmental data, it can analyze the relationship between the environment and the manufacturing process by utilizing the device's own measurement data. At this time, the collected data is collected using an interface such as RS485 / RS232C and a method provided by manufacturing equipment such as LAN / WIFI.
Meanwhile, the context recognition device for IoT-based data collection and processing proposed in the present invention performs basic analysis and data control on collected data, and the analysis result information is provided to an operator through a display. The technology is developed by applying FPGA technology, and the range of algorithms or modules that can be loaded into the device itself is determined and applied through iterative experiments. By reading the setting values for each manufacturing equipment from a portable storage device (SSD or SD card), it responds to the variety of installation situations. In addition, by reading the situation recognition rules, TA, and standard data sets derived from data analysis in the server, the environment optimized for each manufacturing process is maintained. The actual input data is transmitted to the server and stored in the cloud system. In order to cope with sudden state changes during operation, a temporary backup for a predetermined period is performed and updated in a removable storage device mounted on the device.
In the present invention, for the purpose of versatility of the situation recognition device, the characteristics of the manufacturing equipment to which the device is to be installed are set / stored in a portable storage device (SSD or SD card), and the variety of the installation situation is accommodated by utilizing the data. In addition, after the analysis / verification of the data is completed, the generated standard TA information can be stored in a portable storage device (SSD or SD card), and the data can be utilized to maintain the environment optimized for the manufacturing process.
In the present invention, data collected by the context recognition device is transmitted to a server for analysis, and the analysis performed by the context recognition device includes TA stored in a removable storage device (SSD or SD card) It is a basic statistical analysis based on information provided to the operator. In addition, the server uses various analysis techniques (experimental design method, data mining, etc.) to analyze the relationship of each factor and verify the analysis results.
In the present invention, a situation recognition technology is developed through a rule automatic generation method applying FCM (Fuzzy C-Means) clustering algorithm. The FCM is a technique for classifying each given data belonging to one cluster into k clusters and classifying the data into closest clusters according to degree of affiliation and is one of the most important tasks in pattern recognition, decision making, data analysis, and the like. The membership function U of the FCM clustering algorithm has elements having a value between 0 and 1, and the sum of membership degree values for the data set is always 1. The cost function of the FCM algorithm has the following form.
Since the FCM clustering algorithm is a classification-purpose algorithm, it is generally not suitable for numerical prediction. However, because it uses the similarity of each data using Euclidean distance, it is possible to classify it considering various situations that are not defined in advance.
In the present invention, a new control rule for context recognition is generated by using the range of the result cluster after FCM clustering is performed. The membership function determined by the FCM is transformed into a variable fuzzy membership function that can be controlled within the allowable range according to the input vector and applied to the algorithm. The number of membership functions generated through the FCM clustering algorithm is the same as the number of input vectors. That is, when many input vectors are used, the number of membership functions increases. The variable fuzzy membership function improves overall performance by reducing the number of membership functions for each input vector according to their similarity. When the FCM clustering algorithm is performed, a final center vector and a final membership function are derived. The number of fuzzy rules for generating the fuzzy rule uses asymmetric triangular fuzzy numbers with different sizes. The height of the triangular fuzzy number selects the value of the center vector derived from the result of FCM clustering. The left and right slope of the triangular fuzzy number is calculated by using the distance between the minimum vector of the input vector and the value of the belonging function without the value of the belonging function of the cluster being 0.
Hereinafter, an information integration system based on HW / SW fusion framework and process data analysis and verification technology for each industry type according to various embodiments will be described with reference to the accompanying drawings.
FIGS. 1 to 16 are views showing a process data analysis and verification technique for each industry type according to a preferred embodiment of the present invention, and a configuration of an information integration system based on the HW-SW fusion framework.
Referring to FIG. 1, an information integration system according to various embodiments of the present invention includes a
The
The
Figure 2 is a diagram illustrating the configuration of a context-aware device for IoT-based data collection and processing, in accordance with various embodiments of the present invention.
2, a situation recognition device 200 (hereinafter referred to as a "
The
The
The
At this time, the
The
3 is a diagram illustrating a configuration of an HW-SW integration framework according to various embodiments of the present invention.
Referring to FIG. 3, the framework (FORESTA Framework) 300 according to the present invention supports efficient construction of applications by providing functions and architectures necessary for information system development in advance. It is possible to reduce the development cost and shorten the time by reusing software and develop standard API for data analysis, so that it is possible to maintain consistency in software development. In addition, it is possible to establish the standard analysis process by industry type, so it can reflect the requirements in various domains, establish the technical structure for each domain, and improve the processing speed and manageability through distributed processing for data analysis module. And the flexibility of data analysis method and objectivity can be ensured through selective application of analysis model according to the situation recognition and verification of analysis contents.
In addition, the
The
As shown in FIG. 4, the
4, the Device Control Rule Manager 302-1 manages device control rules generated using stored standard data, and the Industry Rule Manager 302- 2) manages control rules for each type using stored data sets for each industry type, and a standard data set manager 303-3 manages standard data sets for each part.
The Context-
As shown in FIG. 5, the
Big data container (Big Data Container: 306) is based on Hadoop system, which is widely used in big data analysis system. It also includes extended HDFS repository and unstructured data conversion module. It converts and distributes data around unstructured data, and converts and manages data in a format for analysis and verification by requirements analysis. The database format is based on NoSQL based Mongolian DB.
As shown in FIG. 6, the
Data Analysis and Verification Container (308) concurrently develops new analytical models composed of data analysis through regression analysis and hierarchical clustering analysis, and decision making techniques using AHP, and analyzed models , And the information updated by the feedback results is utilized as a comparative analysis criterion for the verification of the newly developed analytical model. Also, the data analysis and
Such a data analysis and
7, the statistical analysis module 308-1 provides a statistical analysis and verification function for the inputted data, and the experimental design method analysis module 308-2 analyzes the input data, Provides analytical and verification functions using the planning method. The data mining and machine learning module 308-3 performs data analysis and prediction using data mining techniques based on machine learning based on input data. The data visualization module 308-4 visualizes the analyzed, verified, and predicted data and provides the data to the user.
The Industry Process Container (310) according to the industry type analyzes and verifies various collected data such as the state data of the manufacturing equipment, the environmental data at the manufacturing time, the work instruction information, , And has a module of analyzed / verified data set (API). In addition, it consists of all the standard data, set values, data structure, and data flow indication table that the corresponding equipment can base on all parts of the manufacturing process. At this time, the TA data, method, and processing type may vary depending on the manufacturing equipment. In addition, the
The
As shown in FIG. 8, the Technical Standard Rule Manager 310-1 manages rules related to a technical standard for a corresponding industry type. The data level manager 310-2 manages the difficulty and the security level of each data for the corresponding industry type. The API Set Manager 310-3 manages a set of APIs for designing, developing, and operating a business process for each industry type. The Industry Process Manager 310-4 according to the industry type provides a service by implementing a business process defined for each industry type, and the implementation of the business process is implemented using the API set manager 310-3.
Security Container (316) defines the management rules (Master Rule) such as types, items, and elements based on the forensic readiness design and builds modeling for negative types by industry through data collection and analysis through forensic monitoring , Establishing standard TA through collection of evidence in accordance with policies and regulations, and re-identifying through problems and improvements. In the present invention, a general security-related scenario in which personal information is leaked by the external hacking and a typical privacy incident in which the internal staff violates the privacy policy are combined and the information privacy concept and the forensic preparedness concept are combined, The forensic readiness of the tree structure was applied.
The
The
That is, the
The authentication manager 314-1 manages the authentication of the user account and the device, and the rights manager 314-2 manages the authority of each user of each user. The encryption processing manager 314-3 has an encryption processing module for data to be transmitted and received, and the decryption processing manager 314-4 has a decryption processing module for data to be transmitted and received.
The
That is, as shown in FIG. 10, the evidence data manager 312-1 performs management of evidence data on selected items in the log and monitoring data to be stored, and the item manager 312-2 stores the evidence data items Etc. Forensic readiness management is performed on the data items used in the diagram. The main rule manager 312-3 manages the operating rules of the system for preparing the forensic preparation, and the monitoring processing manager 312-4 manages the monitored items, processing rules, and processing contents.
The
11 is a diagram illustrating a method for developing an API according to an embodiment of the present invention. The R analysis model base for the system according to the present invention can be divided into a new analysis model for data mining and system, and a new analysis model development can be divided into a data analysis API And the TA is designed after the data feedback process necessary for the verification. The data mining technique developed and applied a verification algorithm that can present both qualitative and quantitative prediction results and judgment criteria through cross-validation and feedback between various quantitative analysis and prediction algorithms through existing analysis techniques and machine learning Design the TA.
Referring to FIG. 11,
Reference numeral 700 denotes a process for selecting and developing an API for implementing the model after adopting an analysis model showing excellent results by using the existing
12 is a diagram showing a data analysis and verification technique and a data visualization technique according to the present invention. The data conversion tool according to the present invention reads data from a text filter (Text Extractor) and extracts raw text data. In the Text Parser (Text Analyzer), morphological analysis (accuracy), unstructured data classification (similar to Excel text length setting) Analyze the data (Trim applied). The analysis results are stored in various predefined formats (Json, Text, XML, etc.). Batch Job (Batch Analysis) periodically performs conversion according to batch setting, and it is difficult to analyze in real time when big data is stored. Interactive Job (analysis by user request) Execute by user request Immediate Conversion Execute, Interactive Manager makes related setting. Real-time Job (Real-time analysis: To-be model) Receives the set information in real time and sets it in Real-time Manager. In order to analyze and verify standard data, analysis model developed based on statistical based data mining and experimental design including machine learning is analyzed by applying R statistical analysis tool and data analysis API developed by itself. In addition, we have developed a verification algorithm that can provide both qualitative and quantitative prediction results and judgment criteria through cross-validation and feedback between prediction algorithms by performing various quantitative analyzes through existing analysis techniques and machine learning. To be applied. Data is composed of unstructured data and regular data. It stores data by distributed processing using its own big data analyzer, which has functions such as Flume Agent and Flume sink of Hadoop. Through data conversion tool (CT), the accuracy, data length, and characteristics are separated through filtering, text extraction, morphological analysis, etc., and data is finally stored in a database having an index, and TA generation and redesign are performed. Data visualization is divided into three categories: output of 2D images (printed matter, online image, etc.), motion images (motion infographic, data visualization), and interactions (interactive web / app). Most of them use interactive web to show the huge amount of data Big Data has. Visual Analytics Tool: Many Eyes, TableauPublic, Impure R, Data Hero, and Quadrigram are tools for visual analysis of information. have. By providing templates in the form of processing and analyzing data on the web and sharing the results, even if you do not have any prior knowledge of data visualization, you can produce the desired results if you know only the type and type of information. Data collected through IoT data collection interface is classified into categories according to industry type, and classification and formatting data are classified and collected, converted, stored, and managed through data analysis, distributed processing to HDFS storage, data analysis and verification conversion module And stores it as an index file such as Sql or No Sql. It analyzes and verifies data on the overall manufacturing process from raw material input used in manufacturing to production and verification of the product. In addition to the information provided by the manufacturing equipment and the environmental information, how the company's know-how has been applied to various situations based on the work instruction sheet (characteristic value, factor value, etc.) Analysis and verification, and develop standardized TA based on the analysis results to provide information to the operator. Developed devices with versatility applicable to a variety of manufacturing equipment also provide the standard data set and TA based on the analysis results to the operator using the analysis functions developed based on the FPGA based context recognition chip.
Referring to FIG. 12,
As described above, the repository (Data Source) 520 is a repository for receiving and storing
That is, the atypical data 520-1 refers to a data source for irregularities. In this case, reference numeral 520-3 denotes a Flume Agent technology for collecting data input to an irregular data source 520-1, reference numeral 520-4 denotes a process for collecting irregular data through Flume technology, Reference numeral 520-5 denotes an unstructured data store for storing collected irregular data 520-4.
The format data 520-2 is a source for the formatted data, and includes sensor measurement data, data on the RDB, XML, and data represented by JSON.
FIG. 14 is a diagram illustrating a configuration of a data conversion tool (CT) 530 according to an embodiment of the present invention. Referring to FIG. 14, the
Reference numeral 530-4 denotes an engine (Conversion Tool Engine, CT Engine) for performing data conversion. Reference numeral 530-5 denotes a text extractor for extracting text from the input data, and the extracted text data is transferred to the text parser 530-6. Reference numeral 530-6 denotes a parser for converting the text data transmitted from the text extractor 530-5 into a form that can be parsed and structured.
Reference numeral 530-7 converts the parsed text data 530-6 into structured text, and the converted structured text is passed to the store 530-11 and the search index 530-9. Reference numeral 530-8 denotes an ETL (Extract, Transform, Load) process, and includes items 530-5, 530-6, and 530-7 shown above.
Reference numeral 530-9 denotes a search index for retrieving information from the repository, and creates an index based on the structured text data. Reference numeral 530-10 denotes data input in the JSON format. Since the JSON data is already structured, it can be directly input into the storage 530-11. Reference numeral 530-11 denotes a storage for storing structured data. Reference numeral 530-12 denotes a search engine for searching for a repository of structured data, and performs search using the received search index 530-9.
FIG. 15 is a forensic preparation diagram presented in the present invention, and FIG. 16 is a forensic monitoring configuration diagram.
Referring to FIG. 15, in the present invention, it is necessary to satisfy the three conditions of preserving the original digital evidence, proper selection and analysis of the analysis tool, and preparing the forensic preparation. Configure environments and policies for efficient digital evidence collection. Forensic preparedness is used to detect fraud through the fraud detection rules generated based on the evaluation of industry fraud types, and it is located before the fraud type fraud occurs.
The procedures of the system of the present invention using the forensic readiness are as follows: (1) industry negative assessment, (2) preparation for forensic policy and policy, (3) fraud detection and response plan, (4) accident occurrence, (5) forensic analysis and related evidence collection, . It analyzes the types of lawsuits, industrial accidents and disputes that arise during the manufacturing process, models them for the measurement items, extracts related data, and stores them in the forensic DB.
In the past, although the cause and the responsibility of the product were unclear in the event of the occurrence of the risk situation and the bad product, the cause and the responsibility of the product were clarified by the forensic monitoring, Manufacturing process management is possible.
FIG. 16 shows a process for forensic monitoring. The data collecting and analyzing
The negative type step (620) for each industry derives analysis scenarios based on the risk level, determines the priority through risk measurement after determining the availability of data, and sets up a scenario-specific model based on process and system details. In other words, as a process of grasping a negative type according to each industry based on the collected and analyzed
The type analysis and measurement item modeling steps (630, 640) model the type analysis and the measurement items according to the designed policies, procedures, and regulations, and then collect and monitor the data of transactions, income, expenditure, and exceptions in real time, It is automatically stored in the system so that it can be used as evidence for collection of accidents and subsequent accidents. The
The master rule (policy and regulation)
The evidence collection and
Claims (10)
A framework for integrating IoT based context aware devices and software using ARM;
A context recognition device for performing context recognition based on the FPGA and performing the collection and processing of data to be provided to the framework through context recognition;
An industry type-specific data set and API set that is processed and updated through the framework, and used by the framework;
A component for performing data analysis and verification for performing data analysis and verification based on the data sets and API sets for each industry type;
A visualization module for visualizing data produced through analysis, verification, and processing;
And a service support module to be provided to the mobile and the web. The information integration system based on HW-SW fusion framework and the process data analysis and verification technology for each industry type.
The situation recognition device is connected to various types of manufacturing equipment, and the manufacturing equipment is a manufacturing equipment that is subject to collection of raw data such as sensor data, equipment status information, characteristic values of a product, work instruction information, and the like Process data analysis and verification technology by industry type and information integration system based on HW-SW fusion framework.
The situation recognition device comprising:
A sensing technology module for collecting environmental data measured in a manufacturing environment of the product,
A device module for processing data based on an ARM CPU in the context recognition device,
And a server for deriving information of the input data transmitted from the situation recognition device and generating a rule, a standard data set, and a TA for situation recognition and process management based on the obtained result. Which is based on the HW-SW fusion framework.
The device module comprising:
With ARM CPU,
A situation recognition chip for performing situation recognition based on data,
A visualization module for displaying data to a worker and a user through a display of the situation recognition device,
A portable storage device for storing / updating input and processed data and standard data updated after analysis,
And an information integration system based on HW-SW convergence framework, which is characterized by comprising a display for displaying visualized data.
The framework comprising:
An IoT device container for collecting IoT-based data composed of equipment status data provided by the manufacturing equipment, environmental data measured in a surrounding environment, and work instruction data from a device and performing preprocessing;
A context-aware container for managing according to a context-aware rule through data collected and managed from the IoT device container, classifying certain data collected through a data collection interface and delivering the classified data to a big data container,
A victim container for performing preprocessing on the victim transmitted from the situation recognition container,
A data analysis and verification container for analyzing, verifying and visualizing the converted data through the bigter container,
Process management for each type of industry that generates technical data such as standard data and settings for the corresponding work based on analysis and verification results of the collected data of the manufacturing equipment state data, environmental data at the time of manufacturing, and work instruction information The container,
A security container for managing a security module between a framework and an external interface; and an information integration system based on HW-SW fusion framework.
The IoT device container comprising:
A device control rule manager for managing device control rules generated using stored standard data;
A rule manager for each type of industry that manages control rules for each type using stored data sets for each industry type,
And a standard data set manager for managing the standard data set for each part. The information integration system based on HW-SW fusion framework and the process data analysis and verification technology for each industry type.
The situation recognition container includes:
A network control rule manager for managing the established network,
A context aware rule manager for managing context aware rules,
A data set manager for embedded devices, and an information integration system based on the HW-SW fusion framework.
The data analysis and verification container comprising:
A statistical analysis module for providing a statistical analysis and verification function on inputted data,
An analysis method module for analyzing and applying a test program based on input data,
A data mining and machine learning module for analyzing and predicting data by using data mining technology based on machine learning based on input data;
And a data visualization module that performs a function of visualizing the analyzed, verified, and predicted data and providing the visualized data to the user. The data analysis and verification technology for each industry type and the information integration system based on the HW-SW fusion framework .
The industry-specific process management container includes:
A technical standard rule manager for managing rules relating to technical standards for the type of industry concerned,
A data class manager that manages the difficulty and the security level of each data for the corresponding industrial type,
An API set manager for managing a set of APIs for designing, developing and operating business processes for each type of industry,
And a processor manager for each type of industry that provides a service by implementing a business process defined for each type of industry, and a HW-SW fusion framework based information integration system.
The security container comprising:
A general security manager configured as an authentication manager for authenticating access rights, an authority manager, an encryption processing manager, and a decryption processing manager;
Which is composed of a data manager, an item manager, a main rule manager, and a monitoring processing manager, and includes a forensic readiness manager for monitoring and processing records of the entire system. -SW fusion framework based information integration system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150085698A KR20160148911A (en) | 2015-06-17 | 2015-06-17 | Integrated information system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150085698A KR20160148911A (en) | 2015-06-17 | 2015-06-17 | Integrated information system |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20160148911A true KR20160148911A (en) | 2016-12-27 |
Family
ID=57736937
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020150085698A KR20160148911A (en) | 2015-06-17 | 2015-06-17 | Integrated information system |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20160148911A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20180094584A (en) | 2017-02-16 | 2018-08-24 | 주식회사 포에스텍 | Fusion type internet of things middleware system |
CN109086573A (en) * | 2018-07-30 | 2018-12-25 | 东北师范大学 | Multi-source biology big data convergence platform |
WO2019050108A1 (en) * | 2017-09-06 | 2019-03-14 | 주식회사 씨티아이랩 | Technology for analyzing abnormal behavior in deep learning-based system by using data imaging |
KR20190056502A (en) * | 2017-11-17 | 2019-05-27 | 숭실대학교산학협력단 | Monitoring, analyzing and controlling platform, fog server equipped with the same and fog computing system including the fog server |
JP2019096008A (en) * | 2017-11-21 | 2019-06-20 | 株式会社テクロック・スマートソリューションズ | Measurement solution service providing system |
KR20190135306A (en) * | 2018-05-28 | 2019-12-06 | 주식회사 이유랩 | Web based intergrated control monitoring method |
KR20190135299A (en) * | 2018-05-28 | 2019-12-06 | 주식회사 이유랩 | Web based control monitoring intergrated system |
WO2020085733A1 (en) * | 2018-10-23 | 2020-04-30 | 주식회사 씨티아이랩 | Deep learning-based system abnormality analysis technology using data imaging |
KR20210021249A (en) * | 2019-08-15 | 2021-02-25 | 아이캔컨트롤 테크 씨오 엘티디 | Intelligent industrial internet of things system using bidirectional channel-like neural network architecture |
KR102540669B1 (en) * | 2021-12-17 | 2023-06-08 | 주식회사 그리다에너지 | System for Job history authentication using encrypted and non-editable job data |
CN116362462A (en) * | 2022-11-18 | 2023-06-30 | 麦高(广东)数字科技有限公司 | Full-closed-loop production management system based on Internet of things and big data analysis |
-
2015
- 2015-06-17 KR KR1020150085698A patent/KR20160148911A/en active IP Right Grant
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20180094584A (en) | 2017-02-16 | 2018-08-24 | 주식회사 포에스텍 | Fusion type internet of things middleware system |
US11379689B2 (en) | 2017-09-06 | 2022-07-05 | Ctilab Co., Ltd. | Technology for analyzing abnormal behavior using deep learning-based system and data imaging |
WO2019050108A1 (en) * | 2017-09-06 | 2019-03-14 | 주식회사 씨티아이랩 | Technology for analyzing abnormal behavior in deep learning-based system by using data imaging |
KR20190027237A (en) * | 2017-09-06 | 2019-03-14 | 주식회사 씨티아이랩 | System Anomaly Behavior Analysis Technology based on Deep Learning Using Imaged Data |
KR20190056502A (en) * | 2017-11-17 | 2019-05-27 | 숭실대학교산학협력단 | Monitoring, analyzing and controlling platform, fog server equipped with the same and fog computing system including the fog server |
US11500357B2 (en) | 2017-11-21 | 2022-11-15 | Teclock Smartsolutions Co., Ltd. | Measurement solution service providing system |
JP2019096008A (en) * | 2017-11-21 | 2019-06-20 | 株式会社テクロック・スマートソリューションズ | Measurement solution service providing system |
KR20190135306A (en) * | 2018-05-28 | 2019-12-06 | 주식회사 이유랩 | Web based intergrated control monitoring method |
KR20190135299A (en) * | 2018-05-28 | 2019-12-06 | 주식회사 이유랩 | Web based control monitoring intergrated system |
CN109086573B (en) * | 2018-07-30 | 2021-08-24 | 东北师范大学 | Multi-source biological big data fusion system |
CN109086573A (en) * | 2018-07-30 | 2018-12-25 | 东北师范大学 | Multi-source biology big data convergence platform |
WO2020085733A1 (en) * | 2018-10-23 | 2020-04-30 | 주식회사 씨티아이랩 | Deep learning-based system abnormality analysis technology using data imaging |
KR20210021249A (en) * | 2019-08-15 | 2021-02-25 | 아이캔컨트롤 테크 씨오 엘티디 | Intelligent industrial internet of things system using bidirectional channel-like neural network architecture |
KR102540669B1 (en) * | 2021-12-17 | 2023-06-08 | 주식회사 그리다에너지 | System for Job history authentication using encrypted and non-editable job data |
CN116362462A (en) * | 2022-11-18 | 2023-06-30 | 麦高(广东)数字科技有限公司 | Full-closed-loop production management system based on Internet of things and big data analysis |
CN116362462B (en) * | 2022-11-18 | 2023-10-17 | 麦高(广东)数字科技有限公司 | Full-closed-loop production management system based on Internet of things and big data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR20160148911A (en) | Integrated information system | |
US11480944B2 (en) | CAD-based design control | |
Wang | Towards zero-defect manufacturing (ZDM)—a data mining approach | |
CN113597634B (en) | Process mapping and monitoring using artificial intelligence | |
CN112580813B (en) | Contextualization of industrial data at device level | |
US20170351226A1 (en) | Industrial machine diagnosis and maintenance using a cloud platform | |
CN113820993A (en) | Method, system, and non-transitory computer readable medium for generating industrial control programming | |
CN117270482A (en) | Automobile factory control system based on digital twin | |
US11556837B2 (en) | Cross-domain featuring engineering | |
US20200160208A1 (en) | Model sharing among edge devices | |
KR101888637B1 (en) | Analysis methodology and platform architecture system for big data based on manufacturing specialized algorithm template | |
Kuehn | Simulation in digital enterprises | |
CN117575222A (en) | Production management method, system, equipment and storage medium | |
US20220365518A1 (en) | Development of a product using a process control plan digital twin | |
US20190188574A1 (en) | Ground truth generation framework for determination of algorithm accuracy at scale | |
Pulikottil et al. | Big data life cycle in shop-floor–trends and challenges | |
EP4369121A1 (en) | Industrial data extraction | |
KR102437917B1 (en) | Equipment operation system | |
Yue et al. | Big data for furniture intelligent manufacturing: conceptual framework, technologies, applications, and challenges | |
Latsou et al. | A unified framework for digital twin development in manufacturing | |
dos Santos et al. | Simulation-based digital twins monitoring: an approach focused on models’ accreditation | |
US20240112151A1 (en) | System and method for managing end-of-life products | |
KR102302147B1 (en) | Method, apparatus and coumputer-readable medium of standardize manufacturing data for smart factory construction | |
US20240094701A1 (en) | Information provision device, information provision method, and storage medium storing information provision program | |
CN117952323B (en) | Product creation system, method, equipment and medium based on digital twin |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
N231 | Notification of change of applicant | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right |