Internet-of-things data online acquisition association method

Abstract

The invention relates to production data processing, in particular to an internet-of-things data online acquisition and association method, which comprises the following steps of: acquiring various data in a production process in real time, and standardizing the acquired production data; a unique identifier is given to the production data, and data classification is carried out; constructing a data association model, and defining association rules and constraint conditions among the production data in the data association model; continuously collecting new production data, removing redundant data in the new production data, and associating the redundancy-removed production data with the data association model; storing the associated production data into an associated database, performing regular maintenance and backup on the stored data, and optimizing and expanding the associated database according to requirements; key data are extracted from the association database and presented through a visual tool, data analysis is carried out, and potential production rules and optimization factors are mined; according to the technical scheme provided by the invention, the defect that the production data is difficult to effectively associate can be overcome.

Description

Technical Field

[0001] The present invention relates to production data processing, and particularly to an online acquisition and association method for Internet of Things data. Background Art

[0002] In modern industrial production, a production line usually consists of multiple different processes and devices, and a large amount of production data will be generated in each link, such as material information, equipment operation data, product processing data, and product quality data. However, the production data of each link is often scattered in distributed independent systems or databases, lacking effective association with each other, resulting in enterprises being difficult to overall grasp the operation status of the production line and unable to explore potential production rules and optimization factors. Therefore, how to effectively associate production data has become a key means to improve production quality and efficiency. Summary of the Invention

[0003] (1) Technical Problems to be Solved

[0004] In view of the above-mentioned disadvantages existing in the prior art, the present invention provides an online acquisition and association method for Internet of Things data, which can effectively overcome the defect that it is difficult to effectively associate production data existing in the prior art.

[0005] (2) Technical Solutions

[0006] To achieve the above object, the present invention is realized through the following technical solutions:

[0007] An online acquisition and association method for Internet of Things data, comprising the following steps:

[0008] S1. Deploy data acquisition devices at each key node of the production line, collect various types of data in real time during the production process, and perform standardization processing on the collected production data;

[0009] S2. Assign a unique identifier to the production data and perform data classification;

[0010] S3. Construct a data association model, and define the association rules and constraint conditions between production data in the data association model;

[0011] S4. Continuously collect new production data, remove redundant data in the new production data, and associate the production data after removing redundancy with the data association model;

[0012] S5. Store the associated production data in an association database, perform regular maintenance and backup on the stored data, and optimize and expand the association database according to requirements;

[0013] S6. Extract key data from the association database, present it through a visualization tool, and perform data analysis to explore potential production rules and optimization factors.

[0014] Preferably, in S1, data acquisition devices are deployed at each key node of the production line to collect various types of data during the production process in real time, and the collected production data is standardized, including:

[0015] Data acquisition devices are deployed at each key node of the production line to collect various types of data during the production process in real time;

[0016] The collected production data is standardized to ensure that production data from different data sources has a unified data structure and standardized coding, facilitating subsequent data identification and data classification;

[0017] Among them, various types of data during the production process include material information, equipment operation data, product processing data, and product quality data.

[0018] Preferably, in S2, a unique identifier is assigned to the production data, and data classification is performed, including:

[0019] A unique identifier is assigned to the production data, and this identifier contains sufficient information to determine the source, generation time, belonging process of the production data, and the potential relationship with other data;

[0020] The production data is classified according to the nature and use of the data. Through data classification, the characteristics of the production data and the logical relationship between them can be understood more clearly, providing a basis for subsequent data association;

[0021] Among them, the production data is divided into equipment data, process data, product data, and logistics data according to the nature and use of the data.

[0022] Preferably, in S3, a data association model is constructed, and association rules and constraint conditions between production data are defined in the data association model, including:

[0023] A data association model is constructed according to the production process flow and equipment layout of the production line. This data association model takes the production process flow as the main line, connects the production data generated by each process in chronological order and logical relationship, and forms a complete data chain;

[0024] In the data association model, association rules and constraint conditions between production data are defined.

[0025] Preferably, in S4, new production data is continuously collected, redundant data in the new production data is removed, and the production data after removing redundancy is associated with the data association model, including:

[0026] As the production line runs, new production data is continuously collected, and data fusion technology is used to process duplicate and complementary data from different data sources, remove redundant data from new production data, and improve data accuracy and reliability;

[0027] The de-redundant production data is associated with the data association model, and the de-redundant production data is inserted into the corresponding position in the data chain according to the identifier and classification information, and the data chain is updated to ensure the real-time and integrity of the data.

[0028] Preferably, in S5, the associated production data is stored in an associated database, the stored data is regularly maintained and backed up, and the associated database is optimized and expanded as required, including:

[0029] Store the associated production data in an associated database and use appropriate data storage structures and data indexing techniques to quickly query and retrieve the required data;

[0030] Regularly maintain and back up stored data to ensure data availability and security. At the same time, optimize and expand the associated database according to the needs of data analysis and production management to adapt to the increasing amount of data and data association complexity.

[0031] Preferably, in S6, key data is extracted from the associated database, presented through a visualization tool, and data analysis is performed to explore potential production rules and optimization factors, including:

[0032] Extract key data from the relational database and present it to production managers and decision makers in the form of intuitive charts, graphs or reports through visualization tools;

[0033] Based on visualized data, data analysis methods and tools are used to analyze data and explore potential production rules and optimization factors.

[0034] (III) Beneficial effects

[0035] Compared with the prior art, the method for online collection and association of IoT data provided by the present invention has the following beneficial effects:

[0036] 1) Improve production efficiency: By correlating production data in real time, production managers can obtain comprehensive and accurate production information in a timely manner, quickly identify bottlenecks and problems in the production process, and make corresponding decisions and adjustments in a timely manner, thereby effectively improving production efficiency and reducing production cycles and costs;

[0037] 2) Optimize product quality: Through in-depth data analysis of production data, we can accurately identify various factors that affect product quality, and take targeted measures to optimize and improve them. Through real-time monitoring and adjustment of production process parameters, we can ensure the stability and consistency of product quality, improve product qualification rate and customer satisfaction;

[0038] 3) Realize refined management: Through real-time correlation and data analysis of production data at all stages of the production process, enterprises can achieve reasonable allocation of production resources, effective control of materials, precise maintenance of equipment, and scientific evaluation of personnel performance, thereby comprehensively improving the production management level and competitiveness of the enterprise;

[0039] 4) Support intelligent decision-making: By converting production data into intuitive and easy-to-understand visual data, and combining data analysis technology to explore potential production rules and optimization factors, it provides decision makers with a scientific and reliable basis for decision-making, helping enterprises to formulate reasonable production plans, investment strategies and development plans, adapt to market changes, and achieve sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] A method for online collection and association of IoT data, such as Figure 1 As shown, S1. Data collection devices are deployed at key nodes of the production line to collect various data in the production process in real time and perform standardized processing on the collected production data, including:

[0044] Deploy data collection devices at key nodes of the production line to collect various data in the production process in real time;

[0045] Standardize the collected production data to ensure that production data from different data sources has a unified data structure and standardized coding, facilitating subsequent data identification and data classification;

[0046] Among them, various types of data in the production process include material information (such as material types, batches, quantities, etc.), equipment operation data (such as temperature, pressure, rotation speed, etc.), product processing data (such as dimensions, weights, processing times, etc.), and product quality data (such as defect types, defective product quantities, etc.).

[0047] S2. Assign a unique identifier to the production data and conduct data classification, specifically including:

[0048] Assign a unique identifier to the production data, which contains sufficient information to determine the source, generation time, belonging process of the production data, and potential relationships with other data;

[0049] Conduct data classification on the production data according to the nature and use of the data. Through data classification, the characteristics of the production data and the logical relationships between them can be understood more clearly, providing a basis for subsequent data association;

[0050] Among them, the production data is divided into equipment data, process data, product data, and logistics data according to the nature and use of the data.

[0051] S3. Build a data association model and define the association rules and constraint conditions between production data in the data association model, specifically including:

[0052] Build a data association model according to the production process flow and equipment layout of the production line (for example, if there is a direct association between the product processing data of a certain equipment and the product quality data after processing, then by establishing the corresponding data model or statistical relationship, the specific form and strength of this association can be determined). This data association model takes the production process flow as the main line, connects the production data generated by each process in chronological order and logical relationship, and forms a complete data chain;

[0053] In the data association model, define the association rules and constraint conditions between production data (for example, the input time and quantity of materials should match the output time and quantity of products. According to the requirements of the production process, the constraint conditions regarding time and quantity between materials and products can be set).

[0054] S4. Continuously collect new production data, remove redundant data from the new production data, and associate the production data after removing redundancy with the data association model, specifically including:

[0055] As the production line runs, new production data is continuously collected. Data fusion technology is used to process duplicate data and complementary data from different data sources, removing redundant data in the new production data (for example, for multiple product quality data of the same product, a weighted average, Kalman filter or other fusion algorithms can be used to obtain a comprehensive product quality index as the final evaluation of the product quality), improving the accuracy and reliability of the data;

[0056] Associate the production data after redundancy removal with the data association model, and insert the production data after redundancy removal into the corresponding position in the data chain according to the identifier and classification information, updating the data chain to ensure the timeliness and integrity of the data.

[0057] S5. Store the associated production data in the associated database, perform regular maintenance and backup on the stored data, and optimize and expand the associated database according to requirements, specifically including:

[0058] Store the associated production data in the associated database, and adopt appropriate data storage structures and data indexing technologies (such as establishing indexes according to key fields such as product batch, production time, equipment number, etc.) to improve data access efficiency, so as to quickly query and retrieve the required data;

[0059] Perform regular maintenance and backup on the stored data to ensure the availability and security of the data. At the same time, optimize and expand the associated database according to the requirements of data analysis and production management to adapt to the increasing data volume and data association complexity.

[0060] S6. Extract key data from the associated database, present it through visualization tools, and perform data analysis to mine potential production rules and optimization factors, specifically including:

[0061] Extract key data from the associated database, and present the key data to production managers and decision-makers in the form of intuitive charts, graphs or reports through visualization tools (such as drawing equipment operation status diagrams, product quality trend diagrams, material consumption and inventory change diagrams, etc., so that production managers and decision-makers can timely understand the overall operation situation and existing problems of the production line);

[0062] Based on the visualized data, use data analysis methods and tools to perform data analysis, mining potential production rules and optimization factors (such as by analyzing the relationship between equipment failure data and product processing data, predicting the probability and time of equipment failure, arranging equipment maintenance in advance, reducing production interruptions; another example is that by performing data analysis on product quality data, the key factors affecting product quality can be found, optimizing product processing data, and improving the stability and consistency of product quality).

[0063] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for online collection and association of IoT data, characterized in that: The following steps are involved: S1. Deploy data collection devices at key nodes of the production line to collect various data in the production process in real time and perform standardized processing on the collected production data; S2. Assign unique identifiers to production data and classify the data; S3. Build a data association model, and define association rules and constraints between production data in the data association model; S4. Continuously collect new production data, remove redundant data from the new production data, and associate the de-redundant production data with the data association model; S5. Store the associated production data in the associated database, perform regular maintenance and backup of the stored data, and optimize and expand the associated database as needed; S6. Extract key data from the associated database, present it through visualization tools, and conduct data analysis to explore potential production rules and optimization factors.

2. The method for online collection and association of IoT data according to claim 1, characterized in that: In S1, data collection devices are deployed at key nodes of the production line to collect various data in the production process in real time and perform standardized processing on the collected production data, including: Deploy data collection devices at key nodes of the production line to collect various data in the production process in real time; Standardize the collected production data to ensure that the production data from different data sources have a unified data structure and standardized coding, which is convenient for subsequent data identification and data classification; Among them, various types of data in the production process include material information, equipment operation data, product processing data and product quality data.

3. The method for online collection and association of IoT data according to claim 2, characterized in that: S2 assigns a unique identifier to production data and classifies the data, including: Assign a unique identifier to the production data, which contains sufficient information to determine the source of the production data, when it was generated, the process to which it belongs, and the potential relationship between it and other data; Classify production data according to the nature and purpose of the data. Through data classification, the characteristics of production data and the logical relationship between them can be more clearly understood, providing a basis for subsequent data association; Among them, production data is divided into equipment data, process data, product data and logistics data according to the nature and purpose of the data.

4. The method for online collection and association of IoT data according to claim 3 is characterized in that: A data association model is built in S3, and association rules and constraints between production data are defined in the data association model, including: A data association model is built based on the process flow and equipment layout of the production line. The data association model takes the process flow as the main line and connects the production data generated by each process in chronological order and logical relationship to form a complete data chain. In the data association model, the association rules and constraints between production data are defined.

5. The method for online collection and association of IoT data according to claim 4, characterized in that: S4 continuously collects new production data, removes redundant data from the new production data, and associates the de-redundant production data with the data association model, including: As the production line runs, new production data is continuously collected, and data fusion technology is used to process duplicate and complementary data from different data sources, remove redundant data from new production data, and improve data accuracy and reliability; The de-redundant production data is associated with the data association model, and the de-redundant production data is inserted into the corresponding position in the data chain according to the identifier and classification information, and the data chain is updated to ensure the real-time and integrity of the data.

6. The method for online collection and association of IoT data according to claim 5, characterized in that: S5 stores the associated production data in the associated database, performs regular maintenance and backup of the stored data, and optimizes and expands the associated database as needed, including: Store the associated production data in an associated database and use appropriate data storage structures and data indexing techniques to quickly query and retrieve the required data; Regularly maintain and back up stored data to ensure data availability and security. At the same time, optimize and expand the associated database according to the needs of data analysis and production management to adapt to the increasing amount of data and data association complexity.

7. The method for online collection and association of IoT data according to claim 6, characterized in that: S6 extracts key data from the relational database, presents it through visualization tools, and performs data analysis to explore potential production rules and optimization factors, including: Extract key data from the relational database and present it to production managers and decision makers in the form of intuitive charts, graphs or reports through visualization tools; Based on visualized data, data analysis methods and tools are used to analyze data and explore potential production rules and optimization factors.

Images