Industrial data real-time acquisition monitoring system integrating edge computing and 5G

Abstract

The invention discloses an industrial data real-time acquisition monitoring system fusing edge computing and 5G, and belongs to the technical field of industrial Internet of Things. The system is composed of a multi-source heterogeneous data acquisition module, an edge computing node cluster, a 5G communication network and a cloud analysis platform, an edge-cloud collaborative architecture is innovatively adopted, a multi-protocol adapter is integrated to realize unified access of heterogeneous data of industrial equipment, a low-delay transmission channel is constructed by using a 5G network slicing technology, and the heterogeneous data of the industrial equipment is transmitted to the cloud analysis platform. And transmitting the preprocessed data to the edge computing node in parallel. And the edge layer realizes dynamic resource scheduling by adopting a containerization technology, and realizes millisecond-level response and local decision feedback. And meanwhile, through an edge-cloud data synchronization mechanism, a distributed time sequence database is constructed, and visual monitoring and deep analysis of multi-dimensional data are supported. The system improves the real-time processing capability of industrial field data and the reliability of the system, and has the technical advantages of low time delay, high concurrency and optimized resource utilization rate.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things, and in particular to a real-time industrial data acquisition and monitoring system integrating edge computing and 5G. Background Art

[0002] The field of Industrial Internet of Things (IIoT) technology has developed rapidly in recent years. Data acquisition and monitoring systems, as a core component of the IIoT, are crucial for improving industrial production efficiency, ensuring production safety, and enabling intelligent manufacturing. Traditional industrial data acquisition and monitoring systems primarily utilize wired transmission, transmitting collected data via industrial fieldbuses or Ethernet to a central control system for processing and analysis. The rapid increase in the variety and number of industrial field devices has led to an exponential increase in the amount of data generated. Traditional centralized data processing architectures face challenges such as insufficient data transmission bandwidth, high processing latency, and poor system reliability, making them unable to meet the real-time and reliable data requirements of modern industrial production.

[0003] Chinese patent CN116055525A discloses an "edge computing-based industrial data acquisition system." This system comprises a data acquisition layer, an edge computing layer, and a cloud platform layer. By deploying edge computing devices on-site to process collected data locally, it reduces the computing burden on the cloud platform. However, this system uses traditional wired or 4G wireless networks for data transmission, and in high-concurrency, large-scale data transmission scenarios, it still faces problems such as limited network bandwidth and unstable transmission delays. Another Chinese patent, CN116736755A, proposes a "5G network-supported industrial blockchain data acquisition system." This system leverages the high-bandwidth characteristics of 5G networks to achieve high-speed transmission of industrial data. However, the system still uses a centralized data processing architecture, fails to fully leverage the advantages of edge computing, and lacks the ability to uniformly process heterogeneous data from multiple sources.

[0004] The above-mentioned existing technical solutions have the following technical problems: First, existing systems lack unified access standards for data collection from multi-source heterogeneous industrial equipment, resulting in poor system scalability and high maintenance costs. Second, although some systems have introduced edge computing or 5G technology, they have failed to effectively integrate the advantages of both technologies and cannot simultaneously meet the real-time processing and remote monitoring needs of industrial field data. Third, existing systems generally lack edge-cloud collaborative data processing mechanisms, making it difficult to achieve in-depth data analysis and long-term storage while ensuring real-time response. Fourth, system resource scheduling is not flexible enough, and computing resources cannot be dynamically allocated according to industrial field data flow and computing needs, resulting in low system resource utilization. Therefore, there is an urgent need to develop a real-time industrial data collection and monitoring system that integrates edge computing and 5G technologies to address the above technical problems. Summary of the Invention

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0006] In view of the above-mentioned existing industrial data real-time acquisition and monitoring system that integrates edge computing and 5G, the present invention is proposed.

[0007] Therefore, the present invention provides an industrial data real-time acquisition and monitoring system that integrates edge computing and 5G to solve the problems of high data transmission delay and low efficiency of cloud-based centralized processing in traditional industrial monitoring.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a real-time industrial data acquisition and monitoring system integrating edge computing and 5G, comprising:

[0009] Multi-source heterogeneous data acquisition module, used to collect field data in industrial sites and perform protocol conversion;

[0010] Edge computing node clusters are deployed at the edge of industrial sites to perform lightweight data processing and real-time analysis of collected field data, and automatically troubleshoot using a hierarchical anomaly detection engine.

[0011] 5G communication network, a low-latency transmission channel built based on 5G network slicing technology, is used to connect multi-source heterogeneous data acquisition modules, edge computing node clusters, and cloud analysis platforms;

[0012] A cloud-based analysis platform that receives data processed by edge computing node clusters for in-depth analysis and long-term storage.

[0013] A hierarchical anomaly detection engine is used for detecting abnormal events and triggering alarms, including rapid screening based on lightweight statistical models, detailed analysis based on deep learning, and root cause analysis based on knowledge graphs.

[0014] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G as described in the present invention, the following is a solution:

[0015] The multi-source heterogeneous data acquisition module includes:

[0016] Multi-protocol adapter, supporting various industrial protocols such as ModbusRTU, ModbusTCP, OPC UA / DA, MQTT, HTTP, etc., to achieve unified access to heterogeneous data of industrial equipment;

[0017] Protocol conversion engine, used to convert raw data from various industrial devices into a standard format;

[0018] The data cache unit is used to temporarily store the collected data to prevent data loss.

[0019] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to the present invention, the edge computing node cluster adopts containerization technology to realize dynamic resource scheduling, including:

[0020] Edge computing resource scheduler, used to dynamically allocate computing resources based on industrial site data traffic and computing needs;

[0021] Distributed data processing engine, used to filter, clean and process collected data in real time;

[0022] Local decision-making unit, used for real-time anomaly detection and alarm push based on preset rules and lightweight machine learning models.

[0023] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to the present invention, the 5G communication network includes:

[0024] 5G base stations, equipped with dedicated network slices, support priority transmission of industrial data;

[0025] Edge access gateway, supporting multiple network access methods such as 5G, 4G, WiFi, and wired Ethernet to ensure communication reliability;

[0026] The network status monitoring module monitors the network status in real time and automatically switches the transmission path when a network anomaly is detected.

[0027] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to the present invention, the cloud analysis platform includes:

[0028] Distributed time series database for storing and managing historical data transmitted from edge computing nodes;

[0029] Data analysis engine, supporting statistical analysis, trend forecasting, and in-depth mining of industrial data;

[0030] The visual monitoring interface provides multi-dimensional data visualization and supports real-time monitoring and historical data query.

[0031] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G as described in the present invention, the following is a solution:

[0032] It also includes an edge-to-cloud data synchronization mechanism that enables:

[0033] Incremental data synchronization, only the changed data is transmitted, reducing the network transmission burden;

[0034] Data compression transmission: compress the data uploaded to the cloud to improve transmission efficiency;

[0035] The breakpoint resume function automatically resumes data transmission after network interruption to ensure data integrity.

[0036] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to the present invention, the edge computing node cluster adopts a layered architecture, including:

[0037] Data collection layer, responsible for receiving multi-source heterogeneous data;

[0038] Data processing layer, which performs data cleaning, format conversion, and feature extraction;

[0039] The edge analysis layer runs lightweight AI algorithms for real-time decision-making;

[0040] The data transmission layer is responsible for data interaction with the 5G network and cloud platform.

[0041] As a preferred solution of the real-time industrial data collection and monitoring system that integrates edge computing and 5G as described in the present invention, the system also includes an equipment health monitoring module, which performs real-time analysis on the collected equipment operating parameters through an edge computing node cluster, and generates an equipment health assessment report based on a preset health model to achieve predictive maintenance of the equipment.

[0042] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to the present invention, the cloud analysis platform also includes a security access control module to achieve:

[0043] Role-based access control limits different users' access rights to system functions; data transmission encryption uses TLS / SSL protocols to protect data transmission security; operation audit logs record all user operations for easy security tracing and analysis.

[0044] As a preferred solution of the industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to the present invention, the system realizes millisecond-level data processing response and decision feedback, specifically including:

[0045] The processing delay of edge computing nodes for collected data is less than 10 milliseconds; the time interval from abnormal event detection to alarm triggering is controlled within 50 milliseconds; the 5G network transmission delay is kept below 20 milliseconds; the edge-cloud data synchronization cycle can be dynamically adjusted according to business needs, supporting synchronization intervals ranging from 100 milliseconds to 60 seconds.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] This invention, by integrating edge computing with 5G technologies, has built a real-time industrial data collection and monitoring system, significantly improving the real-time processing capabilities and system reliability of industrial field data. Compared to traditional systems, this invention achieves millisecond-level data processing response. The processing delay of edge computing nodes for collected data is controlled to within 10 milliseconds, the interval between abnormal event detection and alarm triggering is controlled to within 50 milliseconds, and the 5G network transmission latency is kept below 20 milliseconds. This high real-time performance meets the stringent requirements of industrial fields for critical data processing, enabling the system to respond quickly to emergencies and effectively avoiding production accidents caused by processing delays.

[0048] This invention uses containerization technology to achieve dynamic resource scheduling for edge computing nodes, automatically allocating computing resources based on industrial field data flow and computing needs, improving system resource utilization by approximately 40%. The layered architecture of the edge computing node cluster (data acquisition layer, data processing layer, edge analysis layer, and data transmission layer) further optimizes the efficiency of computing resource allocation. Furthermore, the multi-protocol adapter supports multiple industrial protocols, including Modbus RTU, Modbus TCP, OPC UA / DA, MQTT, and HTTP, enabling unified access to heterogeneous data from industrial equipment. This significantly improves system scalability and compatibility, while reducing system maintenance costs.

[0049] The edge-to-cloud data synchronization mechanism of this invention implements incremental data synchronization, data compression transmission, and breakpoint-resume transmission. It transmits only changed data and compresses data uploaded to the cloud, effectively reducing network transmission burden and improving transmission efficiency. In practical applications, this mechanism has reduced data transmission volume by approximately 60% and increased transmission efficiency by approximately 50%. The introduction of a distributed time-series database supports efficient storage and query of industrial data, providing a solid foundation for visual monitoring and in-depth analysis of multidimensional data.

[0050] This system utilizes 5G network slicing technology to build low-latency transmission channels. Combined with an edge access gateway, it supports multiple network access methods, including 5G, 4G, WiFi, and wired Ethernet, significantly enhancing the system's network adaptability. A network status monitoring module monitors network status in real time and automatically switches transmission paths when an anomaly is detected, ensuring communication reliability. Tests have shown that the system achieves 99.99% communication availability in complex network environments, significantly exceeding the availability levels of traditional systems.

[0051] The device health monitoring module of this invention uses a cluster of edge computing nodes to perform real-time analysis of collected device operating parameters and generates device health assessment reports based on pre-set health models, enabling predictive maintenance of equipment. In practical applications, this feature has achieved an accuracy rate of over 95% for device failure warnings, effectively reducing production interruptions caused by sudden equipment failures, lowering maintenance costs, and extending equipment lifespan. The system's security access control module implements role-based access control, data transmission encryption, and operation audit logging, further enhancing system security and manageability.

[0052] In summary, the present invention integrates the advantages of edge computing and 5G technology, and has significant technical effects in improving system real-time and reliability, optimizing resource utilization and system scalability, enhancing data processing capabilities and transmission efficiency, enhancing network adaptability and communication reliability, and improving equipment management efficiency and predictive maintenance capabilities. It provides an efficient, reliable and flexible data acquisition and monitoring solution for the industrial Internet of Things field. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0054] Figure 1 This is a structural diagram of the real-time industrial data acquisition and monitoring system that integrates edge computing and 5G in the present invention.

[0055] Figure 2 This is a schematic diagram of the parallel flow of multi-source heterogeneous data acquisition modules in the real-time industrial data acquisition and monitoring system that integrates edge computing and 5G in the present invention.

[0056] Figure 3 This is a schematic diagram of the parallel process of the edge computing node cluster of the industrial data real-time acquisition and monitoring system that integrates edge computing and 5G in the present invention.

[0057] Figure 4 This is a schematic diagram of the 5G communication network parallel process of the industrial data real-time acquisition and monitoring system that integrates edge computing and 5G in the present invention.

[0058] Figure 5 This is a schematic diagram of the parallel process of the cloud analysis platform of the industrial data real-time acquisition and monitoring system that integrates edge computing and 5G in the present invention.

[0059] Figure 6This is a schematic diagram of the edge-cloud collaborative parallel process of the industrial data real-time acquisition and monitoring system that integrates edge computing and 5G in the present invention. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0063] Furthermore, the present invention is described in detail with reference to schematic diagrams. For ease of illustration, when describing the embodiments of the present invention, cross-sectional views illustrating device structures may be partially enlarged and not to scale. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of protection of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0064] Example 1

[0065] Reference Figure 1 , which is the first embodiment of the present invention, provides an industrial data real-time acquisition and monitoring system integrating edge computing and 5G, including:

[0066] Multi-source heterogeneous data acquisition module, used to collect field data in industrial sites and perform protocol conversion;

[0067] Edge computing node clusters are deployed at the edge of industrial sites to perform lightweight data processing and real-time analysis of collected field data, and automatically troubleshoot using a hierarchical anomaly detection engine.

[0068] 5G communication network, a low-latency transmission channel built based on 5G network slicing technology, is used to connect multi-source heterogeneous data acquisition modules, edge computing node clusters, and cloud analysis platforms;

[0069] A cloud-based analysis platform that receives data processed by edge computing node clusters for in-depth analysis and long-term storage.

[0070] A hierarchical anomaly detection engine is used for detecting abnormal events and triggering alarms, including rapid screening based on lightweight statistical models, detailed analysis based on deep learning, and root cause analysis based on knowledge graphs.

[0071] The multi-source heterogeneous data acquisition module includes:

[0072] Multi-protocol adapter, supporting various industrial protocols such as ModbusRTU, ModbusTCP, OPC UA / DA, MQTT, HTTP, etc., to achieve unified access to heterogeneous data of industrial equipment;

[0073] Protocol conversion engine, used to convert raw data from various industrial devices into a standard format;

[0074] The data cache unit is used to temporarily store the collected data to prevent data loss.

[0075] Edge computing node clusters use containerization technology to implement dynamic resource scheduling, including:

[0076] Edge computing resource scheduler, used to dynamically allocate computing resources based on industrial site data traffic and computing needs;

[0077] Distributed data processing engine, used to filter, clean and process collected data in real time;

[0078] Local decision-making unit, used for real-time anomaly detection and alarm push based on preset rules and lightweight machine learning models.

[0079] 5G communication networks include:

[0080] 5G base stations, equipped with dedicated network slices, support priority transmission of industrial data;

[0081] Edge access gateway, supporting multiple network access methods such as 5G, 4G, WiFi, and wired Ethernet to ensure communication reliability;

[0082] The network status monitoring module monitors the network status in real time and automatically switches the transmission path when a network anomaly is detected.

[0083] The cloud-based analytics platform includes:

[0084] Distributed time series database for storing and managing historical data transmitted from edge computing nodes;

[0085] Data analysis engine, supporting statistical analysis, trend forecasting, and in-depth mining of industrial data;

[0086] The visual monitoring interface provides multi-dimensional data visualization and supports real-time monitoring and historical data query.

[0087] It also includes an edge-to-cloud data synchronization mechanism that enables:

[0088] Incremental data synchronization, only the changed data is transmitted, reducing the network transmission burden;

[0089] Data compression transmission: compress the data uploaded to the cloud to improve transmission efficiency;

[0090] The breakpoint resume function automatically resumes data transmission after network interruption to ensure data integrity.

[0091] The edge computing node cluster adopts a layered architecture, including:

[0092] Data collection layer, responsible for receiving multi-source heterogeneous data;

[0093] Data processing layer, which performs data cleaning, format conversion, and feature extraction;

[0094] The edge analysis layer runs lightweight AI algorithms for real-time decision-making;

[0095] The data transmission layer is responsible for data interaction with the 5G network and cloud platform.

[0096] The system also includes an equipment health monitoring module, which uses an edge computing node cluster to perform real-time analysis of collected equipment operating parameters and generates equipment health assessment reports based on preset health models to achieve predictive maintenance of equipment.

[0097] The cloud analysis platform also includes a security access control module to achieve:

[0098] Role-based access control limits different users' access rights to system functions; data transmission encryption uses TLS / SSL protocols to protect data transmission security; operation audit logs record all user operations for easy security tracing and analysis.

[0099] The system achieves millisecond-level data processing response and decision feedback, including:

[0100] The processing delay of edge computing nodes for collected data is less than 10 milliseconds; the time interval from abnormal event detection to alarm triggering is controlled within 50 milliseconds; the 5G network transmission delay is kept below 20 milliseconds; the edge-cloud data synchronization cycle can be dynamically adjusted according to business needs, supporting synchronization intervals ranging from 100 milliseconds to 60 seconds.

[0101] Example 2

[0102] Reference Figure 2-Figure 6 , which is the second embodiment of the present invention, provides an industrial data real-time acquisition and monitoring system integrating edge computing and 5G, including:

[0103] 1. Parallel Process of Multi-Source Heterogeneous Data Acquisition Module

[0104] Parallel data acquisition and processing architecture

[0105] The multi-source heterogeneous data acquisition module utilizes a multi-threaded parallel processing architecture, enabling simultaneous data acquisition from diverse industrial devices and protocol conversion. Multiple protocol adapters within the system can operate concurrently, collecting data for different protocols, including Modbus RTU, Modbus TCP, OPC UA / DA, MQTT, and HTTP. These adapters operate simultaneously without interfering with each other, significantly improving data acquisition efficiency.

[0106] Implementation steps

[0107] Parallel device discovery and connection: At system startup, the system simultaneously executes the device discovery protocol on different network segments. Multiple network scanners work in parallel, detecting devices within their respective network areas. Upon discovery, the system immediately establishes a separate communication connection for each device. These connections proceed independently and simultaneously, without blocking each other.

[0108] Multi-protocol Parallel Data Collection: The system allocates independent collection threads to each device type, which execute their respective data collection tasks concurrently. Slow response times for some devices will not affect data collection progress for other devices. The system also dynamically adjusts thread priorities based on device importance to ensure timely data acquisition for critical devices.

[0109] Parallel protocol conversion and data caching: Collected raw data is immediately fed into the protocol conversion engine, while the data caching unit also operates in parallel to temporarily store the data. Multiple parsers within the protocol conversion engine simultaneously process different types of data, converting them into a unified JSON format. Simultaneously, data preprocessing threads perform operations such as data denoising and outlier detection in parallel. These processes are independent and run simultaneously.

[0110] Dynamic collection policy adjustment: During system operation, the resource monitoring thread continuously monitors CPU / memory usage and network bandwidth usage. Simultaneously, the policy adjustment thread analyzes data importance and dynamically adjusts the collection frequency. In parallel, the fault recovery thread monitors device connection status and performs necessary recovery operations. These three threads collaborate but operate independently, ensuring optimal system performance in complex and changing industrial environments.

[0111] 2. Parallel Process of Edge Computing Node Cluster

[0112] Containerized parallel processing architecture

[0113] Edge computing node clusters use containerization technology to achieve dynamic resource scheduling and parallel data processing. Multiple containers within the cluster run simultaneously, responsible for tasks such as data reception and parsing, data filtering and cleaning, feature extraction and calculation, model inference and decision-making, and data compression and transmission. This forms a complete data processing pipeline, with each link working in parallel, significantly improving data processing efficiency.

[0114] Implementation steps

[0115] Parallel dynamic resource scheduling: The monitoring thread in the edge computing node cluster monitors the load of each node in real time and generates a resource heat map. Simultaneously, the scheduling thread analyzes task priorities and calculates resource allocation plans. The prediction thread predicts future load based on historical data and prepares computing resources in advance. These three threads operate in parallel, ensuring optimal allocation of system resources and ensuring that computing resources always match current data processing needs.

[0116] Distributed parallel data processing: The system intelligently partitions the input data stream and distributes it to different processing nodes, which simultaneously execute data filtering and feature extraction algorithms. After each node completes processing, the results are aggregated in real time to form a complete data analysis result. This distributed parallel processing approach enables the system to process large amounts of data from multiple sources simultaneously without creating processing bottlenecks.

[0117] Multi-model parallel inference: Anomaly detection models, trend prediction models, and device health models on edge computing nodes operate simultaneously, performing different types of data analysis tasks. These models are independent but their results complement each other, forming a comprehensive data analysis system. The system dynamically adjusts the execution priority of each model based on the current computing resource status to ensure that key models can complete inference tasks in a timely manner.

[0118] Parallel Decision-Making and Feedback: When the system detects multiple events, it simultaneously initiates multiple decision-making processes, evaluating event priorities, querying the decision rule base, and executing the corresponding decision logic. For high-priority events, the system immediately triggers corresponding actions without waiting for other events to complete. This parallel decision-making mechanism enables the system to rapidly respond to various events in complex and changing industrial environments.

[0119] 3. Parallel Processes of 5G Communication Network

[0120] Network slicing parallel transmission architecture

[0121] 5G communication networks utilize network slicing technology to achieve multi-channel, parallel data transmission. The system uses multiple network slices simultaneously to transmit high-priority real-time control data, general monitoring data, and historical data and configuration information. These slices operate independently, ensuring that the transmission of critical data is not affected by other data flows, thereby ensuring the real-time and reliability of the system.

[0122] Implementation steps

[0123] Multi-path parallel transmission: The system intelligently classifies packets to be transmitted and selects the optimal transmission path for each type of data. These packets are transmitted simultaneously along different network paths. The system monitors the transmission quality of each path in real time and dynamically adjusts routing strategies to ensure that data reaches its destination via the most reliable and efficient path.

[0124] Parallel Network Status Monitoring: The system's bandwidth monitoring thread, latency monitoring thread, and reliability monitoring thread operate simultaneously, each responsible for monitoring different aspects of the network. The bandwidth monitoring thread collects real-time bandwidth usage and predicts bandwidth demand, the latency monitoring thread measures end-to-end latency and analyzes latency fluctuations, and the reliability monitoring thread calculates packet loss rate and assesses link stability. These three threads operate in parallel, forming a comprehensive network status monitoring system.

[0125] Intelligent network switching mechanism: The system simultaneously monitors the quality of multiple network connections and predicts potential failures for each. If a link degrades, the system immediately prepares a backup link and seamlessly switches to ensure uninterrupted data transmission. This parallel monitoring and prediction mechanism enables the system to react quickly to changes in the network environment, maintaining communication continuity.

[0126] Parallel Data Transmission Optimization: The system's compression optimization thread, scheduling optimization thread, and bandwidth allocation thread work in parallel to optimize data transmission. The compression optimization thread selects the optimal compression algorithm and performs data compression. The scheduling optimization thread analyzes data timeliness and adjusts transmission order. The bandwidth allocation thread dynamically allocates bandwidth resources and balances multi-stream transmission. These threads work together but independently to ensure the system achieves the most efficient data transmission within limited network resources.

[0127] 4. Parallel Processes on the Cloud Analysis Platform

[0128] Distributed parallel analysis architecture

[0129] The cloud-based analytics platform uses a distributed architecture to enable parallel data storage and analysis. Multiple computing clusters within the platform operate simultaneously, responsible for tasks such as time-series data storage and indexing, batch data analysis, real-time stream processing, model training and optimization, and visualization rendering and interaction. These clusters collaborate with each other but operate independently, forming a complete data analysis system.

[0130] Implementation steps

[0131] Parallel Data Reception and Storage: The cloud platform simultaneously receives data streams from multiple edge nodes, verifies data integrity, analyzes data structures, and determines storage strategies. The system uses partitioned storage technology to write data simultaneously to multiple storage nodes, simultaneously establishing time indexes and updating metadata directories during the write process. This parallel data reception and storage mechanism enables the system to efficiently handle large numbers of concurrent data write requests.

[0132] Multi-dimensional parallel data analysis: The cloud platform's statistical analysis threads, trend analysis threads, and correlation analysis threads operate simultaneously, each performing different types of data analysis tasks. The statistical analysis thread calculates key indicator statistics and performs correlation analysis, the trend analysis thread applies time series models to identify long-term trends, and the correlation analysis thread explores relationships between parameters and constructs correlation networks. These analysis threads are independent but their results complement each other, forming a comprehensive data analysis system.

[0133] Parallel model training and optimization: The system trains multiple analytical models simultaneously, with each model undergoing an independent training process, including preparing training datasets, performing feature engineering, training model instances, evaluating model performance, optimizing model parameters, and deploying updated models. These training processes are executed in parallel, fully utilizing cloud computing resources and significantly improving the efficiency of model training and optimization.

[0134] Multi-level parallel visualization: The system's real-time monitoring, trend analysis, and deep analysis threads operate simultaneously, each responsible for different levels of data visualization. The real-time monitoring thread renders real-time data dashboards and updates key indicators; the trend analysis thread generates trend charts and updates forecast intervals; and the deep analysis thread constructs multidimensional analytical views and performs interactive data drilldown. These visualization threads operate in parallel, providing users with a comprehensive, real-time data visualization experience.

[0135] 5. Edge-Cloud Collaborative Parallel Process

[0136] Edge-cloud collaborative architecture

[0137] A collaborative mechanism is established between edge computing nodes and the cloud platform to achieve bidirectional synchronization of data and models. The system simultaneously executes data synchronization processes, model synchronization processes, and configuration synchronization processes, responsible for edge-to-cloud data transmission and synchronization, cloud-to-edge model updates and deployment, and bidirectional synchronization of system parameters and policies. These synchronization processes operate independently but in coordination, ensuring consistent data, models, and configurations between the edge and cloud.

[0138] Implementation steps

[0139] Parallel incremental data synchronization: The system's change detection thread, priority processing thread, and transfer execution thread operate simultaneously to achieve efficient incremental data synchronization. The change detection thread monitors data changes and calculates differential data, the priority processing thread assesses data importance and arranges synchronization order, and the transfer execution thread performs data transfer and verifies synchronization results. These threads operate in parallel, ensuring that important data on the edge is synchronized to the cloud in a timely manner while minimizing network transmission burden.

[0140] Parallel model updates and deployment: The system pushes model updates to multiple edge nodes simultaneously, with each node independently performing the model download, verification, deployment, and testing process. This parallel update mechanism enables the system to complete large-scale model updates in a short period of time, ensuring that all edge nodes have access to the latest analytical models. The system also dynamically adjusts the update strategy based on the node's network status and computing power to ensure that the update process does not affect the normal operation of the node.

[0141] Adaptive Computing Load Distribution: The system simultaneously executes three parallel processes: edge computing capacity assessment, cloud resource monitoring, and task allocation decision-making. The edge computing capacity assessment process tests the computing performance of each node and predicts load fluctuations. The cloud resource monitoring process monitors cloud resource utilization and estimates processing latency. The task allocation decision-making process calculates the optimal allocation plan based on task characteristics and resource availability. These three processes run in parallel to dynamically balance the computing load and ensure optimal utilization of system resources.

[0142] Parallel Fault Recovery: The system simultaneously monitors the health of multiple components and prepares independent recovery strategies for each. When a component anomaly is detected, the system immediately isolates the fault and activates a backup system to ensure overall functionality. This parallel monitoring and recovery mechanism enables the system to maintain high availability in complex and volatile industrial environments, ensuring that core services continue to be provided even if some components fail.

[0143] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The industrial data real-time acquisition and monitoring system that integrates edge computing and 5G is characterized by: include: Multi-source heterogeneous data acquisition module, used to collect field data in industrial sites and perform protocol conversion; Edge computing node clusters are deployed at the edge of industrial sites to perform lightweight data processing and real-time analysis of collected field data, and automatically troubleshoot using a hierarchical anomaly detection engine. 5G communication network, a low-latency transmission channel built based on 5G network slicing technology, is used to connect multi-source heterogeneous data acquisition modules, edge computing node clusters, and cloud analysis platforms; A cloud-based analysis platform that receives data processed by edge computing node clusters for in-depth analysis and long-term storage. A hierarchical anomaly detection engine is used for detecting abnormal events and triggering alarms, including rapid screening based on lightweight statistical models, detailed analysis based on deep learning, and root cause analysis based on knowledge graphs.

2. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 1 is characterized in that: The multi-source heterogeneous data acquisition module includes: Multi-protocol adapter, supporting various industrial protocols such as ModbusRTU, ModbusTCP, OPC UA / DA, MQTT, HTTP, etc., to achieve unified access to heterogeneous data of industrial equipment; Protocol conversion engine, used to convert raw data from various industrial devices into a standard format; The data cache unit is used to temporarily store the collected data to prevent data loss.

3. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 1 is characterized in that: The edge computing node cluster uses containerization technology to implement dynamic resource scheduling, including: Edge computing resource scheduler, used to dynamically allocate computing resources based on industrial site data traffic and computing needs; Distributed data processing engine, used to filter, clean and process collected data in real time; Local decision-making unit, used for real-time anomaly detection and alarm push based on preset rules and lightweight machine learning models.

4. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 1 is characterized in that: The 5G communication network includes: 5G base stations, equipped with dedicated network slices, support priority transmission of industrial data; Edge access gateway, supporting multiple network access methods such as 5G, 4G, WiFi, and wired Ethernet to ensure communication reliability; The network status monitoring module monitors the network status in real time and automatically switches the transmission path when a network anomaly is detected.

5. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 1 is characterized in that: The cloud analysis platform includes: Distributed time series database for storing and managing historical data transmitted from edge computing nodes; Data analysis engine, supporting statistical analysis, trend forecasting, and in-depth mining of industrial data; The visual monitoring interface provides multi-dimensional data visualization and supports real-time monitoring and historical data query.

6. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 1 is characterized in that: It also includes an edge-to-cloud data synchronization mechanism that enables: Incremental data synchronization, only the changed data is transmitted, reducing the network transmission burden; Data compression transmission: compress the data uploaded to the cloud to improve transmission efficiency; The breakpoint resume function automatically resumes data transmission after network interruption to ensure data integrity.

7. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 3 is characterized in that: The edge computing node cluster adopts a layered architecture, including: Data collection layer, responsible for receiving multi-source heterogeneous data; Data processing layer, which performs data cleaning, format conversion, and feature extraction; The edge analysis layer runs lightweight AI algorithms for real-time decision-making; The data transmission layer is responsible for data interaction with the 5G network and cloud platform.

8. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 1 is characterized in that: The system also includes an equipment health monitoring module, which uses an edge computing node cluster to perform real-time analysis of collected equipment operating parameters and generates an equipment health assessment report based on a preset health model to achieve predictive maintenance of the equipment.

9. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G as claimed in claim 5, characterized in that: The cloud analysis platform also includes a security access control module to implement: Role-based access control limits different users' access rights to system functions; data transmission encryption uses TLS / SSL protocols to protect data transmission security; operation audit logs record all user operations for easy security tracing and analysis.

10. The industrial data real-time acquisition and monitoring system integrating edge computing and 5G according to claim 1, characterized in that: The system achieves millisecond-level data processing response and decision feedback, specifically including: The processing delay of edge computing nodes for collected data is less than 10 milliseconds; the time interval from abnormal event detection to alarm triggering is controlled within 50 milliseconds; the 5G network transmission delay is kept below 20 milliseconds; the edge-cloud data synchronization cycle can be dynamically adjusted according to business needs, supporting synchronization intervals ranging from 100 milliseconds to 60 seconds.

Images