Intelligent decision-making system and method based on industrial internet
By introducing intelligent decision-making systems into the industrial Internet, production data is collected and processed in real time, and machine learning algorithms are used to identify equipment failures and predict maintenance cycles, data processing lag problems are solved, real-time decision-making support is achieved, and production efficiency and product quality are improved.
Patent Information
- Application Number
- CN202411063768.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-12-03
AI Technical Summary
Data processing lags in traditional industrial manufacturing, resulting in companies being unable to respond to changes in the production process in a timely manner, affecting production efficiency and product quality, and decision-making relies on experience and intuition, and lacks scientific data analysis.
Design an intelligent decision-making system based on the industrial Internet, including data acquisition module, data processing module and intelligent analysis module, collect data in real time through IoT devices, use distributed message queues and stream processing frameworks to clean and format data, and apply Machine learning algorithms perform analysis, identify equipment failure factors and predict maintenance cycles, providing real-time decision support.
It improves the timeliness and accuracy of data processing, provides scientific decision-making basis, helps enterprises optimize production plans and resource allocation, reduce production costs, and improve production efficiency.
Smart Images

Figure CN119067465A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of industrial Internet, and specifically relates to an intelligent decision-making system and method based on industrial Internet. Background Art
[0002] Industrial Internet is a technology that uses the Internet of Things to fully connect devices and people in industrial production to achieve real-time data sharing. Industrial Internet promotes design collaboration, manufacturing collaboration, supply chain and sales chain collaboration, and management chain synchronization in industrial production, thereby improving the overall efficiency of industrial production. However, the current industrial production and manufacturing process still faces a series of challenges, especially in data processing and decision support.
[0003] In traditional industrial manufacturing processes, data collection, transmission, processing and analysis often have time lags. This lag makes it impossible for enterprises to respond to changes in the production process in a timely manner, thus affecting production efficiency and product quality. Take a large manufacturing company as an example. The sensors on its production line generate millions of data every day. However, due to the limitation of data processing capacity, these data cannot be analyzed in real time, which makes it difficult to find and solve problems in the production process in a timely manner. Moreover, in the absence of real-time and accurate data support, enterprises often rely on experience and intuition rather than scientific data analysis. This not only increases the risk of decision-making, but also limits the ability of enterprises to respond to market changes. In addition, traditional decision support systems can only provide static and historical data analysis, and cannot provide enterprises with real-time and dynamic decision support. This makes it difficult for enterprises to make timely and effective decisions when facing emergencies or market changes.
[0004] This is the shortcoming of the existing technology. Therefore, it is very necessary to provide an intelligent decision-making system and method based on the industrial Internet to address the above-mentioned defects in the existing technology. Summary of the invention
[0005] In view of the defect that the lag of data processing capability in the above-mentioned existing industrial production process in the prior art leads to the inability to meet the real-time decision-making needs of enterprises, the present invention provides an intelligent decision-making system and method based on the industrial Internet to solve the above-mentioned technical problems.
[0006] In a first aspect, the present invention provides an intelligent decision-making system based on the industrial Internet, comprising a data acquisition module and a central server;
[0007] Data acquisition module, used to collect production site data in real time through IoT devices;
[0008] The central server is equipped with a data processing module, an intelligent analysis module, and a decision support module;
[0009] The data processing module is used to clean, integrate and format the collected production site data through distributed message queues and stream processing frameworks;
[0010] The intelligent analysis module is used to use machine learning algorithms to analyze the processed production site data, identify the factors that cause production equipment failures, predict production equipment failures, and determine the maintenance cycle of production equipment; the decision support module is used to display the production equipment status, production equipment efficiency, and production progress based on the analysis results of the production site data, issue early warnings for production equipment failures and reduced production efficiency, generate production equipment maintenance plans, make production plan adjustments, and optimize production equipment configurations.
[0011] Further, the data acquisition module includes an environmental data acquisition unit, an equipment operation parameter acquisition unit, a production parameter acquisition unit, a product parameter acquisition unit and a data transmission unit;
[0012] An environmental data collection unit, used to collect environmental data of the production site through sensors;
[0013] Equipment operation parameter collection unit, used to collect the operation status data of production equipment through the actuator of the PLC controller;
[0014] A production parameter collection unit, used to collect the output through the RFID tags set on the products, and to collect the energy consumption of the production process through the production time;
[0015] Product parameter collection unit, used to track and trace products through RFID tags set on products to complete product quality information collection;
[0016] The data transmission unit is used to transmit the collected production site data to the central server through a lightweight data transmission protocol.
[0017] Further, the data processing module includes a data storage unit, a data processing speed control unit, a data cleaning unit, a data integration unit and a data formatting unit;
[0018] A data storage unit, used to cache the collected production site data through a Kafka distributed message queue;
[0019] The data processing speed control unit is used to determine the data processing speed according to the grouping of the Kafka distributed message queue and the parallelism of the stream processing framework;
[0020] The data cleaning unit is used to use the stream processing framework and the calculated data processing speed to produce field data from the Kafka distributed message queue, remove the abnormal and repeated production field data outside the set threshold range, and fill in the missing production field data through interpolation;
[0021] The data integration unit is used to determine the target data model and the data source of the production site data, use the ETL tool to extract the cleaned production site data from each data source, split, merge and calculate the extracted production site data according to the requirements of the target data model, and then load it to the target location;
[0022] The data formatting unit is used to convert the loaded production site data into a unified format.
[0023] Further, the intelligent analysis module includes a data learning unit and a regularity and connection identification unit;
[0024] A data learning unit for classifying and predicting processed production site data using a supervised learning algorithm, and for identifying hidden patterns and structures in the production site data using an unsupervised learning algorithm;
[0025] The rule and relationship identification unit is used to analyze the relationship between equipment failure and production-level equipment operation time based on the classification, prediction results, hidden patterns and results of production site data, and to predict equipment maintenance cycles through time series analysis.
[0026] Further, the decision support module includes a production status monitoring unit, a problem early warning unit, a production forecasting unit, and a production optimization unit;
[0027] The production status monitoring unit is used to monitor the equipment status, equipment efficiency and production progress of the production site based on the analysis results of the production site data;
[0028] Problem warning unit, used to identify and warn of production equipment failures and declines in production efficiency in advance based on the analysis results of production site data;
[0029] Equipment maintenance unit, used to arrange maintenance plans based on the production equipment failures that are identified and warned;
[0030] The production optimization unit is used to adjust the production plan according to the production progress and optimize the equipment configuration.
[0031] In a second aspect, the present invention provides an intelligent decision-making method based on the industrial Internet, comprising the following steps: S1. collecting production site data in real time through Internet of Things devices;
[0032] S2. Clean, integrate and format the collected production site data through distributed message queues and stream processing frameworks;
[0033] S3. Use machine learning algorithms to analyze the processed production site data, identify production equipment failure factors, predict production equipment failures, and determine the maintenance cycle of production equipment;
[0034] S4. Based on the results of production site data analysis, the status of production equipment, production equipment efficiency, and production progress are displayed, early warnings are issued for production equipment failures and reduced production efficiency, a production equipment maintenance plan is generated, production plan adjustments are given, and the production equipment configuration is optimized.
[0035] Furthermore, the specific steps of step S1 are as follows:
[0036] S11. Collect environmental data of the production site through sensors;
[0037] S12. Collecting the operating status data of the production equipment through the actuator of the PLC controller;
[0038] S13. Collecting the operating status data of the production equipment through the actuator of the PLC controller;
[0039] S14. Collecting production volume through RFID tags set on products, and collecting energy consumption of production process through production time;
[0040] S15. Track and trace the product through the RFID tag set on the product to complete the collection of product quality information;
[0041] S16. Transmit the collected production site data to the central server through a lightweight data transmission protocol. Further, the specific steps of step S2 are as follows:
[0042] S21. Cache the collected production site data through the Kafka distributed message queue;
[0043] S22. Determine the data processing speed according to the grouping of the Kafka distributed message queue and the parallelism of the stream processing framework;
[0044] S23. Use the stream processing framework and the calculated data processing speed to process the production site data from the Kafka distributed message queue, remove the abnormal and repeated production site data outside the set threshold range, and fill in the missing production site data through interpolation;
[0045] S24. Determine the target data model and the data source of the production site data, use the ETL tool to extract the cleaned production site data from each data source, split, merge and calculate the extracted production site data according to the requirements of the target data model, and then load it into the target location;
[0046] S25. Convert the loaded production site data into a unified format.
[0047] Furthermore, the specific steps of step S3 are as follows:
[0048] S31. Use supervised learning algorithms to classify and predict processed production site data, and use unsupervised learning algorithms to identify hidden patterns and structures in production site data;
[0049] S32. Analyze the relationship between equipment failure and production-level equipment operation time based on the classification, prediction results, hidden patterns and results of production site data, and predict equipment maintenance cycles through time series analysis.
[0050] Furthermore, the specific steps of step S4 are as follows:
[0051] S41. Monitor the equipment status, equipment efficiency and production progress of the production site based on the analysis results of the production site data;
[0052] S42. Based on the analysis results of production site data, early identification and warning of production equipment failures and declines in production efficiency are carried out;
[0053] S43. Arrange maintenance plans based on production equipment failures identified and warned;
[0054] S44. Adjust production plan and optimize equipment configuration according to production progress.
[0055] The beneficial effects of the present invention are:
[0056] The intelligent decision-making system and method based on the industrial Internet provided by the present invention improve the timeliness and accuracy of data processing through distributed message queues and stream processing frameworks; through machine learning algorithms, potential problems can be predicted and identified more accurately; the present invention also provides a scientific decision-making basis to help enterprises optimize production plans and resource allocation, reduce production costs, and improve production efficiency.
[0057] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect.
[0058] It can be seen that compared with the prior art, the present invention has outstanding substantive features and significant progress, and the beneficial effects of its implementation are also obvious. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] 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 description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0060] Figure 1 It is a schematic diagram of the intelligent decision-making system based on the industrial Internet of the present invention.
[0061] Figure 2 It is a flow chart of the intelligent decision-making method based on industrial Internet of the present invention. DETAILED DESCRIPTION
[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.
[0063] See also Figure 1 The figure shows an intelligent decision-making system based on the industrial Internet in a specific implementation, including a data acquisition module and a central server;
[0064] Data acquisition module, used to collect production site data in real time through IoT devices;
[0065] The central server is equipped with a data processing module, an intelligent analysis module, and a decision support module;
[0066] The data processing module is used to clean, integrate and format the collected production site data through distributed message queues and stream processing frameworks;
[0067] The intelligent analysis module is used to use machine learning algorithms to analyze the processed production site data, identify the factors that cause production equipment failures, predict production equipment failures, and determine the maintenance cycle of production equipment; the decision support module is used to display the production equipment status, production equipment efficiency, and production progress based on the analysis results of the production site data, issue early warnings for production equipment failures and reduced production efficiency, generate production equipment maintenance plans, make production plan adjustments, and optimize production equipment configurations.
[0068] In this embodiment,
[0069] See also Figure 1 A method is shown in a specific implementation, comprising the following steps:
[0070] The data acquisition module includes an environmental data acquisition unit, an equipment operation parameter acquisition unit, a production parameter acquisition unit, a product parameter acquisition unit and a data transmission unit;
[0071] An environmental data collection unit, used to collect environmental data of the production site through sensors;
[0072] Equipment operation parameter collection unit, used to collect the operation status data of production equipment through the actuator of the PLC controller;
[0073] A production parameter collection unit, used to collect the output through the RFID tags set on the products, and to collect the energy consumption of the production process through the production time;
[0074] Product parameter collection unit, used to track and trace products through RFID tags set on products to complete product quality information collection;
[0075] A data transmission unit, used to transmit the collected production site data to a central server through a lightweight data transmission protocol;
[0076] The data processing module includes a data storage unit, a data processing speed control unit, a data cleaning unit, a data integration unit and a data formatting unit;
[0077] A data storage unit, used to cache the collected production site data through a Kafka distributed message queue;
[0078] The data processing speed control unit is used to determine the data processing speed according to the grouping of the Kafka distributed message queue and the parallelism of the stream processing framework;
[0079] The data cleaning unit is used to use the stream processing framework and the calculated data processing speed to produce field data from the Kafka distributed message queue, remove the abnormal and repeated production field data outside the set threshold range, and fill in the missing production field data through interpolation;
[0080] The data integration unit is used to determine the target data model and the data source of the production site data, use the ETL tool to extract the cleaned production site data from each data source, split, merge and calculate the extracted production site data according to the requirements of the target data model, and then load it to the target location;
[0081] A data formatting unit, used to convert the loaded production site data into a unified format;
[0082] The intelligent analysis module includes a data learning unit and a pattern and connection identification unit;
[0083] A data learning unit for classifying and predicting processed production site data using a supervised learning algorithm, and for identifying hidden patterns and structures in the production site data using an unsupervised learning algorithm;
[0084] The regularity and relationship identification unit is used to analyze the relationship between equipment failure and production-level equipment operation time based on the classification, prediction results, hidden patterns and results of production site data, and to predict equipment maintenance cycles through time series analysis;
[0085] The decision support module includes a production status monitoring unit, a problem early warning unit, a production forecasting unit, and a production optimization unit;
[0086] The production status monitoring unit is used to monitor the equipment status, equipment efficiency and production progress of the production site based on the analysis results of the production site data;
[0087] Problem warning unit, used to identify and warn of production equipment failures and declines in production efficiency in advance based on the analysis results of production site data;
[0088] Equipment maintenance unit, used to arrange maintenance plans based on the production equipment failures that are identified and warned;
[0089] The production optimization unit is used to adjust the production plan according to the production progress and optimize the equipment configuration.
[0090] The following is an embodiment of the intelligent decision-making method based on the Industrial Internet provided in the embodiments of the present disclosure. This method and the intelligent decision-making system based on the Industrial Internet in the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the intelligent decision-making method based on the Industrial Internet, please refer to the embodiment of the above-mentioned intelligent decision-making system based on the Industrial Internet.
[0091] like Figure 2 As shown, the method comprises the following steps:
[0092] S1. Collect production site data in real time through IoT devices;
[0093] S2. Clean, integrate and format the collected production site data through distributed message queues and stream processing frameworks;
[0094] S3. Use machine learning algorithms to analyze the processed production site data, identify production equipment failure factors, predict production equipment failures, and determine the maintenance cycle of production equipment;
[0095] S4. Based on the results of production site data analysis, the status of production equipment, production equipment efficiency, and production progress are displayed, early warnings are issued for production equipment failures and reduced production efficiency, a production equipment maintenance plan is generated, production plan adjustments are given, and the production equipment configuration is optimized.
[0096] In this embodiment, the specific steps of step S1 are as follows:
[0097] S11. Collect environmental data of the production site through sensors;
[0098] S12. Collecting the operating status data of the production equipment through the actuator of the PLC controller;
[0099] S13. Collecting the operating status data of the production equipment through the actuator of the PLC controller;
[0100] S14. Collecting production volume through RFID tags set on products, and collecting energy consumption of production process through production time;
[0101] S15. Track and trace the product through the RFID tag set on the product to complete the collection of product quality information;
[0102] S16. Transmit the collected production site data to the central server through a lightweight data transmission protocol;
[0103] The specific steps of step S2 are as follows:
[0104] S21. Cache the collected production site data through the Kafka distributed message queue;
[0105] S22. Determine the data processing speed according to the grouping of the Kafka distributed message queue and the parallelism of the stream processing framework;
[0106] S23. Use the stream processing framework and the calculated data processing speed to process the production site data from the Kafka distributed message queue, remove the abnormal and repeated production site data outside the set threshold range, and fill in the missing production site data through interpolation;
[0107] S24. Determine the target data model and the data source of the production site data, use the ETL tool to extract the cleaned production site data from each data source, split, merge and calculate the extracted production site data according to the requirements of the target data model, and then load it into the target location;
[0108] S25. Convert the loaded production site data into a unified format;
[0109] The specific steps of step S3 are as follows:
[0110] S31. Use supervised learning algorithms to classify and predict processed production site data, and use unsupervised learning algorithms to identify hidden patterns and structures in production site data;
[0111] S32. Analyze the relationship between equipment failure and production-level equipment operation time based on the classification, prediction results, hidden patterns and results of production site data, and predict equipment maintenance cycles through time series analysis;
[0112] The specific steps of step S4 are as follows:
[0113] S41. Monitor the equipment status, equipment efficiency and production progress of the production site based on the analysis results of the production site data;
[0114] S42. Based on the analysis results of production site data, early identification and warning of production equipment failures and declines in production efficiency are carried out;
[0115] S43. Arrange maintenance plans based on production equipment failures identified and warned;
[0116] S44. Adjust production plan and optimize equipment configuration according to production progress.
[0117] It should be understood that the order of execution of the steps in the above embodiment does not mean that the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0118] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.
Claims
1. An intelligent decision-making system based on the industrial Internet, characterized in that: Including data acquisition module and central server; Data acquisition module, used to collect production site data in real time through IoT devices; The central server is equipped with a data processing module, an intelligent analysis module, and a decision support module; The data processing module is used to clean, integrate and format the collected production site data through distributed message queues and stream processing frameworks; The intelligent analysis module is used to use machine learning algorithms to analyze the processed production site data, identify the factors that cause production equipment failures, predict production equipment failures, and determine the maintenance cycle of production equipment; the decision support module is used to display the production equipment status, production equipment efficiency, and production progress based on the analysis results of the production site data, issue early warnings for production equipment failures and reduced production efficiency, generate production equipment maintenance plans, make production plan adjustments, and optimize production equipment configurations.
2. The intelligent decision-making system based on the industrial Internet according to claim 1, characterized in that: The data acquisition module includes an environmental data acquisition unit, an equipment operation parameter acquisition unit, a production parameter acquisition unit, a product parameter acquisition unit and a data transmission unit; An environmental data collection unit, used to collect environmental data of the production site through sensors; Equipment operation parameter collection unit, used to collect the operation status data of production equipment through the actuator of the PLC controller; A production parameter collection unit, used to collect the output through the RFID tags set on the products, and to collect the energy consumption of the production process through the production time; Product parameter collection unit, used to track and trace products through RFID tags set on products to complete product quality information collection; The data transmission unit is used to transmit the collected production site data to the central server through a lightweight data transmission protocol.
3. The intelligent decision-making system based on the Industrial Internet as claimed in claim 2, characterized in that: The data processing module includes a data storage unit, a data processing speed control unit, a data cleaning unit, a data integration unit and a data formatting unit; A data storage unit, used to cache the collected production site data through a Kafka distributed message queue; The data processing speed control unit is used to determine the data processing speed according to the grouping of the Kafka distributed message queue and the parallelism of the stream processing framework; The data cleaning unit is used to use the stream processing framework and the calculated data processing speed to produce field data from the Kafka distributed message queue, remove the abnormal and repeated production field data outside the set threshold range, and fill in the missing production field data through interpolation; The data integration unit is used to determine the target data model and the data source of the production site data, use the ETL tool to extract the cleaned production site data from each data source, split, merge and calculate the extracted production site data according to the requirements of the target data model, and then load it to the target location; The data formatting unit is used to convert the loaded production site data into a unified format.
4. The intelligent decision-making system based on the industrial Internet as claimed in claim 3, characterized in that: The intelligent analysis module includes a data learning unit and a rule and connection identification unit; A data learning unit for classifying and predicting processed production site data using a supervised learning algorithm, and for identifying hidden patterns and structures in the production site data using an unsupervised learning algorithm; The rule and relationship identification unit is used to analyze the relationship between equipment failure and production-level equipment operation time based on the classification, prediction results, hidden patterns and results of production site data, and to predict equipment maintenance cycles through time series analysis.
5. The intelligent decision-making system based on the industrial Internet as claimed in claim 4, characterized in that: The decision support module includes a production status monitoring unit, a problem early warning unit, a production forecasting unit, and a production optimization unit; The production status monitoring unit is used to monitor the equipment status, equipment efficiency and production progress of the production site based on the analysis results of the production site data; Problem warning unit, used to identify and warn of production equipment failures and declines in production efficiency in advance based on the analysis results of production site data; Equipment maintenance unit, used to arrange maintenance plans based on the production equipment failures that are identified and warned; The production optimization unit is used to adjust the production plan according to the production progress and optimize the equipment configuration.
6. An intelligent decision-making method based on the industrial Internet, characterized in that: The steps include: S1. Collect production site data in real time through IoT devices; S2. Clean, integrate and format the collected production site data through distributed message queues and stream processing frameworks; S3. Use machine learning algorithms to analyze the processed production site data, identify production equipment failure factors, predict production equipment failures, and determine the maintenance cycle of production equipment; S4. Based on the results of production site data analysis, the status of production equipment, production equipment efficiency, and production progress are displayed, early warnings are issued for production equipment failures and reduced production efficiency, a production equipment maintenance plan is generated, production plan adjustments are given, and the production equipment configuration is optimized.
7. The intelligent decision-making method based on the Industrial Internet according to claim 6, characterized in that: The specific steps of step S1 are as follows: S11. Collect environmental data of the production site through sensors; S12. Collecting the operating status data of the production equipment through the actuator of the PLC controller; S13. Collecting the operating status data of the production equipment through the actuator of the PLC controller; S14. Collecting production volume through RFID tags set on products, and collecting energy consumption of production process through production time; S15. Track and trace the product through the RFID tag set on the product to complete the collection of product quality information; S16. Transmit the collected production site data to the central server via a lightweight data transmission protocol.
8. The intelligent decision-making method based on the Industrial Internet according to claim 6, characterized in that: The specific steps of step S2 are as follows: S21. Cache the collected production site data through the Kafka distributed message queue; S22. Determine the data processing speed according to the grouping of the Kafka distributed message queue and the parallelism of the stream processing framework; S23. Use the stream processing framework and the calculated data processing speed to process the production site data from the Kafka distributed message queue, remove the abnormal and repeated production site data outside the set threshold range, and fill in the missing production site data through interpolation; S24. Determine the target data model and the data source of the production site data, use the ETL tool to extract the cleaned production site data from each data source, split, merge and calculate the extracted production site data according to the requirements of the target data model, and then load it into the target location; S25. Convert the loaded production site data into a unified format.
9. The intelligent decision-making method based on the Industrial Internet according to claim 6, characterized in that: The specific steps of step S3 are as follows: S31. Use supervised learning algorithms to classify and predict processed production site data, and use unsupervised learning algorithms to identify hidden patterns and structures in production site data; S32. Analyze the relationship between equipment failure and production-level equipment operation time based on the classification, prediction results, hidden patterns and results of production site data, and predict equipment maintenance cycles through time series analysis.
10. The intelligent decision-making method based on the Industrial Internet according to claim 6, characterized in that: The specific steps of step S4 are as follows: S41. Monitor the equipment status, equipment efficiency and production progress of the production site based on the analysis results of the production site data; S42. Based on the analysis results of production site data, early identification and warning of production equipment failures and declines in production efficiency are carried out; S43. Arrange maintenance plans based on production equipment failures identified and warned; S44. Adjust production plan and optimize equipment configuration according to production progress.
Citation Information
Cited By
A multi-domain expression and decision engine automatic construction method for industrial intelligent decision
CN122837400A
