Industrial equipment intelligent management method and system based on cloud edge collaboration

Abstract

The invention provides an industrial equipment intelligent management method and system based on cloud edge collaboration. The method comprises the following steps: constructing a three-level collaborative architecture of a center end, an edge end and an equipment end, and establishing a two-way communication channel through a proxy tunnel mode; and the center end generates edge end instance configuration based on the equipment template metadata, and the edge end returns equipment state change data in real time by adopting an increment synchronization algorithm, only synchronizes the variable quantity and adopts priority queue management. The system comprises a center end module, an edge end module, an equipment end module, a communication module, a rule engine module and a side AI analysis module. According to the method, the problems of data synchronization delay, bandwidth waste and decision response lag are effectively solved, million-level equipment state millisecond-level consistency synchronization and intelligent closed-loop control are realized, and the industrial equipment management efficiency and the intelligent level are improved.

Description

Technical Field

[0001] This invention belongs to the field of industrial automation technology, and in particular relates to an intelligent management method and system for industrial equipment based on cloud-edge collaboration. Background Technology

[0002] Current industrial equipment management faces several technical bottlenecks that hinder the pace of industrial automation and intelligentization. Firstly, existing large-scale equipment status synchronization largely relies on central polling mechanisms, which result in high data latency and fail to meet real-time requirements. Secondly, the full transmission of raw data leads to a significant waste of network bandwidth. Inefficient data transmission not only consumes substantial communication resources but also exacerbates system lag, preventing the provision of timely control commands to industrial equipment. These problems severely restrict the response speed and intelligence level of industrial equipment management, necessitating the construction of a more efficient cloud-edge-device collaborative architecture. Summary of the Invention

[0003] (a) Purpose of the invention To overcome the above shortcomings, the purpose of this invention is to provide a cloud-edge collaborative intelligent management method and system for industrial equipment to solve the aforementioned technical problems.

[0004] (II) Technical Solution To achieve the above objectives, the technical solution provided in this application is as follows: A cloud-edge collaborative intelligent management method for industrial equipment, characterized by the following steps: S1 constructs a three-level collaborative architecture consisting of the central end, the edge end, and the device end, and establishes a two-way communication channel between the central end and the edge end through the proxy tunnel mode; The S2 central terminal generates edge terminal instance configurations based on device template metadata, and the edge terminal uses an incremental synchronization algorithm to transmit device status change data back in real time. The S3 edge terminal preprocesses the raw data from the device through a visual rule orchestration interface, including outlier filtering and time window aggregation operations. The S4 rules engine uploads the pre-processed data to the central terminal via the cloud-edge channel, while the edge AI analysis model provides real-time decision feedback to the device.

[0005] Preferably, S2 specifically includes: The central terminal automatically generates metadata templates for edge terminal instances based on device type; At the edge, a difference comparison algorithm is used to synchronize only the changes in device status. The synchronization process uses priority queue management, with data from critical devices being transmitted first.

[0006] Preferably, the rule engine in S3 supports hot reloading technology, and the policy update takes effect within 5 seconds, and the preprocessed rules include: Sliding window statistics are applied to time series data; Filter non-time-series data for abnormal fluctuation thresholds; Data weighting coefficients are generated based on the device health model.

[0007] Preferably, the edge AI analysis model in S4 is deployed in the following manner: The model parameters trained at the central end are sent to the edge end through an encrypted channel; Automatically adapt to local hardware resources when loading models at the edge; The model inference results are fed back to the device control module in real time.

[0008] Preferably, the incremental synchronization algorithm in S2 adopts a time-series-based difference comparison model, and the device status dataset is defined as follows: ; in: A unique identifier for the device. The timestamp represents the point in time when the record state change occurred; Calculated using the following formula: ; H is the device status hash value. This represents the XOR operation; when When the value is not equal to 0, synchronization is triggered.

[0009] Preferably, a synchronization efficiency quantification formula is introduced into the bidirectional synchronization mechanism as a decision criterion for dynamically switching transmission modes. Through quantified efficiency evaluation, adaptive optimization of the synchronization strategy is achieved. Synchronization efficiency is evaluated using a quantitative formula: ; in, The data volume for state changes. The data volume representing the complete device status; when When the value is less than 0.3, it indicates a drastic change in state, and the system automatically switches to full synchronization mode to calculate overhead incrementally.

[0010] Preferably, priority queue management adopts a priority scheduling strategy, and the device priority is determined by a linear weighted model: ; in, =0.6, =0.4; Assign weights to different equipment types: critical equipment = 1.0, general equipment = 0.6; H represents the real-time health score output by the side AI model.

[0011] Preferably, the aggregation function for the sliding window statistics is: ; Where N is the window size, The time decay weight is λ, where λ is the decay coefficient. satisfy , It is the core parameter of the aggregation function. As K increases, meaning the data point is older, Exponential decay indicates that recent data decays relative to the average. Their contribution is even greater.

[0012] A cloud-edge collaborative intelligent management system for industrial equipment, used to implement the aforementioned cloud-edge collaborative intelligent management method for industrial equipment, includes: Central module: Used to build a three-level collaborative architecture of central end, edge end, and device end, and generate edge end instance configuration based on device template metadata; Edge module: Used to transmit device status change data in real time using incremental synchronization algorithm, and to preprocess the raw data from the device through a visual rule orchestration interface; Device-side module: Used to collect device status data and transmit it to the edge module; Communication module: Used to establish a bidirectional communication channel between the central end and the edge end through proxy tunnel mode; Rule Engine Module: Used to upload preprocessed data to the central terminal via the cloud-edge channel, and to receive and update the rule policies issued by the central terminal; Side-side AI analysis module: used to make real-time decisions on the pre-processed data and feed them back to the device.

[0013] Beneficial effects: 1. Improved operation and maintenance efficiency: Reduced downtime for maintenance by hot-loading rules, and effectively reduced invalid traffic for device status synchronization.

[0014] 2. Improved response time: Optimized algorithms and priority queues reduce edge latency and improve data transmission efficiency. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the device status synchronization process structure of the present invention; Figure 2 This is a schematic diagram of the architecture according to one embodiment of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the following detailed embodiments are described in conjunction with the appendix. Figure 1-2 The present invention will be described in further detail below. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0017] This invention provides an intelligent management method for industrial equipment based on cloud-edge collaboration, comprising the following steps: S1 constructs a three-level collaborative architecture consisting of the central end, the edge end, and the device end, and establishes a two-way communication channel between the central end and the edge end through the proxy tunnel mode; The S2 central terminal generates edge instance configurations based on device template metadata. The edge terminals use an incremental synchronization algorithm to transmit device status change data back in real time, specifically including: The central terminal automatically generates metadata templates for edge terminal instances based on device type; At the edge, a difference comparison algorithm is used to synchronize only the changes in device status. The synchronization process uses priority queue management, with data from critical devices being transmitted first.

[0018] The incremental synchronization algorithm adopts a time-series-based difference comparison model, and defines the device status dataset as follows: ; in: A unique identifier for the device. The timestamp represents the point in time when the record state change occurred; Calculated using the following formula: ; H is the device status hash value. This represents the XOR operation; when When the value is not equal to 0, synchronization is triggered.

[0019] A synchronization efficiency quantification formula is introduced into the bidirectional synchronization mechanism as a decision criterion for dynamically switching transmission modes. Through quantified efficiency evaluation, adaptive optimization of the synchronization strategy is achieved, fundamentally solving the efficiency bottleneck problem of fixed synchronization mode in dealing with different changing scenarios. Thus, the dual goals of reducing invalid data transmission and ensuring synchronization reliability are stably achieved in complex industrial environments.

[0020] Synchronization efficiency is evaluated using a quantitative formula: ; in, The data volume for state changes. The data volume representing the complete device status; when When the value is less than 0.3, it indicates a drastic change in state, and the system automatically switches to full synchronization mode to calculate overhead incrementally.

[0021] Priority queue management employs a priority scheduling strategy, with device priorities determined by a linear weighted model: ; in, =0.6, =0.4; Assign weights to different equipment types: critical equipment = 1.0, general equipment = 0.6; H represents the real-time health score output by the side AI model.

[0022] The S3 edge terminal preprocesses the raw data from the device through a visual rule orchestration interface, including outlier filtering and time window aggregation operations. The visual rules engine supports hot reloading technology, with policy updates taking effect within 5 seconds, and pre-processed rules include: Sliding window statistics are applied to time series data; Filter non-time-series data for abnormal fluctuation thresholds; Data weighting coefficients are generated based on the device health model.

[0023] The aggregation function for the sliding window statistics is: ; Where N is the window size, The time decay weight is λ, where λ is the decay coefficient. satisfy , It is the core parameter of the aggregation function. As K increases, meaning the data point is older, Exponential decay indicates that recent data decays relative to the average. Their contribution is even greater.

[0024] This design allows the aggregation results to more sensitively reflect the latest changes in equipment status, making it suitable for anomaly detection or real-time monitoring.

[0025] A cloud-edge channel is constructed, with edge node registration employing a two-way authentication mechanism. The central terminal issues X.509 certificates, and the edge terminals establish a WebSocket long-lived connection via an HTTPS handshake. Communication data is encrypted using AES-256 mode, and the key is rotated every 24 hours through the PKI system.

[0026] On the edge side, sensor data from the devices is transmitted to the edge nodes via industrial protocols such as OPC UA. The rules engine first performs preprocessing, applying sliding window aggregation to the temperature data, where the window size N=60 seconds, and applying dynamic threshold filtering to the vibration data. Abnormal data is cached locally, while normal data is compressed and then uploaded to the central end.

[0027] Decisions are synchronized in real time. The LSTM fault prediction model deployed on the edge outputs a real-time device health score. When the predicted fault probability is greater than 0.9, a device maintenance command is immediately triggered. The central device periodically verifies the device metadata version number, and the edge devices perform incremental synchronization via binary difference packets.

[0028] A cloud-edge collaborative intelligent management system for industrial equipment includes: Central module: Used to build a three-level collaborative architecture of central end, edge end, and device end, and generate edge end instance configuration based on device template metadata; Edge module: Used to transmit device status change data in real time using incremental synchronization algorithm, and to preprocess the raw data from the device through a visual rule orchestration interface; Device-side module: Used to collect device status data and transmit it to the edge module; Communication module: Used to establish a bidirectional communication channel between the central end and the edge end through proxy tunnel mode; Rule Engine Module: Used to upload preprocessed data to the central terminal via the cloud-edge channel, and to receive and update the rule policies issued by the central terminal; Side-side AI analysis module: used to make real-time decisions on the pre-processed data and feed them back to the device.

[0029] This invention constructs a three-tiered collaborative architecture of central end-edge end-device end, establishing a bidirectional communication channel through a proxy tunnel mode; it designs an incremental synchronization mechanism based on device template metadata, transmitting only state changes and using priority queues to manage critical device data; at the edge end, it implements visual rule orchestration, performing sliding window aggregation and dynamic threshold filtering preprocessing on the raw data; it introduces rule engine hot-loading technology to achieve rapid policy updates, and deploys edge-side AI models to automatically adapt to local hardware resources for real-time decision feedback. This solution effectively solves the problems of data synchronization delay, bandwidth waste, and decision response lag in industrial equipment management, achieving millisecond-level consistent synchronization and intelligent closed-loop control of the status of millions of devices.

[0030] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0031] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do 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 cloud-edge collaborative intelligent management method for industrial equipment, characterized in that, Includes the following steps: S1 constructs a three-level collaborative architecture consisting of the central end, the edge end, and the device end, and establishes a two-way communication channel between the central end and the edge end through the proxy tunnel mode; The S2 central terminal generates edge terminal instance configurations based on device template metadata, and the edge terminal uses an incremental synchronization algorithm to transmit device status change data back in real time. The S3 edge terminal preprocesses the raw data from the device through a visual rule orchestration interface, including outlier filtering and time window aggregation operations. The S4 rules engine uploads the pre-processed data to the central terminal via the cloud-edge channel, while the edge AI analysis model provides real-time decision feedback to the device.

2. The intelligent management method for industrial equipment based on cloud-edge collaboration according to claim 1, characterized in that, S2 specifically includes: The central terminal automatically generates metadata templates for edge terminal instances based on device type; At the edge, a difference comparison algorithm is used to synchronize only the changes in device status. The synchronization process uses priority queue management, with data from critical devices being transmitted first.

3. The intelligent management method for industrial equipment based on cloud-edge collaboration according to claim 1, characterized in that, The rule engine in S3 supports hot reloading technology, and policy updates take effect within 5 seconds. Preprocessed rules include: Sliding window statistics are applied to time series data; Filter non-time-series data for abnormal fluctuation thresholds; Data weighting coefficients are generated based on the device health model.

4. The intelligent management method for industrial equipment based on cloud-edge collaboration according to claim 1, characterized in that, The edge AI analysis model in S4 is deployed in the following ways: The model parameters trained at the central end are sent to the edge end through an encrypted channel; Automatically adapt to local hardware resources when loading models at the edge; The model inference results are fed back to the device control module in real time.

5. The intelligent management method for industrial equipment based on cloud-edge collaboration according to claim 2, characterized in that, The incremental synchronization algorithm in S2 adopts a time-series-based difference comparison model, and the device status dataset is defined as follows: ； in: A unique identifier for the device. The timestamp represents the point in time when the record state change occurred; Calculated using the following formula: ； H is the device status hash value. Represents the XOR operation; when When the value is not equal to 0, synchronization is triggered.

6. A cloud-edge collaborative intelligent management method for industrial equipment according to claim 5, characterized in that, A synchronization efficiency quantification formula is introduced into the bidirectional synchronization mechanism as a decision criterion for dynamically switching transmission modes. Through quantified efficiency evaluation, adaptive optimization of the synchronization strategy is achieved. Synchronization efficiency is evaluated using a quantitative formula: ； in, The data volume for state changes. The data volume representing the complete device status; when When the value is less than 0.3, it indicates a drastic change in state, and the system automatically switches to full synchronization mode to calculate overhead incrementally.

7. A cloud-edge collaborative intelligent management method for industrial equipment according to claim 5, characterized in that, Priority queue management employs a priority scheduling strategy, with device priorities determined by a linear weighted model: ； in, =0.6， =0.4； Assign weights to different equipment types: critical equipment = 1.0, general equipment = 0.6; H represents the real-time health score output by the side AI model.

8. A cloud-edge collaborative intelligent management method for industrial equipment according to claim 3, characterized in that, The aggregation function for the sliding window statistics is: ； Where N is the window size, The time decay weight is λ, where λ is the decay coefficient. satisfy , It is the core parameter of the aggregation function. As K increases, meaning the data point is older, Exponential decay indicates that recent data decays relative to the average. Their contribution is even greater.

9. An intelligent management system for industrial equipment based on cloud-edge collaboration, characterized in that, A method for intelligent management of industrial equipment based on cloud-edge collaboration, as described in any one of claims 1-8, characterized in that it comprises: Central module: Used to build a three-level collaborative architecture of central end, edge end, and device end, and generate edge end instance configuration based on device template metadata; Edge module: Used to transmit device status change data in real time using incremental synchronization algorithm, and to preprocess the raw data from the device through a visual rule orchestration interface; Device-side module: Used to collect device status data and transmit it to the edge module; Communication module: Used to establish a bidirectional communication channel between the central end and the edge end through proxy tunnel mode; Rule Engine Module: Used to upload preprocessed data to the central terminal via the cloud-edge channel, and to receive and update the rule policies issued by the central terminal; Side-side AI analysis module: used to make real-time decisions on the pre-processed data and feed them back to the device.

Images