Cloud industrial data cooperative processing method based on multiple levels

Abstract

The invention belongs to the field of data processing, and provides a cloud industrial data cooperative processing method and system based on multiple levels, and the method comprises the following steps: obtaining industrial data through a sensor and a collection device; performing data filtering and preprocessing on the industrial data through edge computing equipment; analyzing the filtered and preprocessed industrial data, and performing priority division to obtain data priorities; formulating an uploading strategy according to the data priority, uploading the filtered and preprocessed industrial data to a cloud server through the uploading strategy, and recording the filtered and preprocessed industrial data as cloud data; cloud data are integrated in the cloud server, deep analysis is carried out on the cloud data, and anomaly detection and trend prediction are carried out by applying a machine learning model. According to the cooperative processing method provided by the embodiment of the invention, the industrial data processing efficiency and security can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of data processing, and specifically relates to a multi-level cloud-based industrial data collaborative processing method. Background Art

[0002] The Chinese patent publication number CN116170445A, "An Industrial Data Processing System Based on Cloud Computing", may have the following disadvantages when uploading data; centralized data transmission and processing methods may cause data transmission delays and excessive server load, especially when the data volume is large or the network conditions are poor, the system performance may be unstable. Secondly, the lack of a strategy for priority management of industrial data limits the system's emergency event handling and data transmission efficiency. Frequent network connections and disconnections also increase the system's maintenance costs and operational complexity. In addition, the failure to fully utilize edge computing devices for data preprocessing and preliminary filtering results in low overall data transmission efficiency.

[0003] Therefore, in order to improve the existing methods, it is necessary to introduce more flexible and efficient data processing and transmission strategies to improve the real-time, stability and responsiveness of the system, so as to better meet the needs of industrial data processing. Summary of the invention

[0004] The purpose of the present invention is to propose a multi-level cloud-based collaborative industrial data processing method to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0005] The present invention provides a multi-level cloud-based industrial data collaborative processing method, the method comprising the following steps: S100, acquires industrial data through sensors and acquisition devices; S200, performs data filtering and preprocessing on industrial data through edge computing devices; S300, analyzing the filtered and pre-processed industrial data, and performing priority classification to obtain data priority; S400, formulate an upload strategy according to the data priority, and upload the filtered and pre-processed industrial data to the cloud server through the upload strategy and record it as cloud data; S500,integrates cloud data on cloud servers, performs in-depth analysis on cloud data, and applies machine learning models for anomaly detection and trend prediction.

[0006] According to the collaborative processing method of the embodiment of the present invention, the shortcomings of ordinary cloud computing industrial data processing methods in data processing efficiency, real-time and intelligent analysis capabilities can be solved by introducing edge computing, priority management and dynamic upload strategies, thereby further improving the efficiency and security of industrial data processing.

[0007] Furthermore, in step S100, the data acquisition method of industrial data includes arranging sensors and acquisition equipment at the industrial site to monitor parameters in the industrial production process in real time, and the parameters include: temperature, pressure, vibration, equipment operation status, etc. The types of sensors and acquisition equipment for acquiring industrial data include temperature sensors, pressure sensors, flow meters, power monitoring equipment, etc.

[0008] In step S200, the process of filtering and preprocessing industrial data through edge computing devices includes: identifying and removing noise of instantaneous fluctuations in sensor data through statistical analysis, and then using smoothing algorithms (such as moving average or weighted average) to reduce random fluctuations in real-time industrial data; when missing values ​​appear in the detection data set, the industrial data is processed by interpolation, mean substitution or deletion of missing value rows, and finally the processed data is uploaded to the cloud or other data storage systems as needed as a basis for subsequent in-depth analysis and decision support.

[0009] In step S300, the filtered and pre-processed industrial data is analyzed and prioritized to obtain data priorities, including: Among them, priority division includes: the system divides data into high priority, medium priority and low priority data; among them, high priority data includes: safety alarms, equipment failure information, abnormal monitoring data, etc.; medium priority data includes: production monitoring data, environmental parameters, etc.; priority data includes historical data and routine operation data.

[0010] Specifically, the characteristics of high-priority data include alarm data related to safety and stability, equipment failure status, and monitoring data that exceeds the threshold. These data need to be uploaded to the cloud immediately for processing so that rapid response measures can be taken. The characteristics of medium-priority data include monitoring data that has a significant impact on the production process. These data can be set to be uploaded at a scheduled time or under specific conditions to ensure that important information is not missed. The characteristics of low-priority data include historical operation data, regular monitoring data, or data that does not affect immediate decision-making. These data can be uploaded in batches and can be performed when the network bandwidth is sufficient to reduce the burden of real-time transmission.

[0011] The beneficial effects of this step are: by conducting in-depth analysis of filtered and preprocessed industrial data, and prioritizing it according to the characteristics of the data and the needs of the production process, timely processing and efficient transmission of key information are ensured; and such priority management not only optimizes the data upload strategy, but also improves the safety and production efficiency of industrial equipment.

[0012] S400, formulate an upload strategy according to the data priority, and upload the filtered and pre-processed industrial data to the cloud server through the upload strategy and record it as cloud data; Specifically, high-priority data adopts real-time upload or fast upload strategies to ensure that it is sent to the cloud immediately when an event occurs; medium-priority data is set to be uploaded at a scheduled time or when specific conditions are triggered to ensure that data is not missed; low-priority data adopts batch upload or periodic upload strategies, for example, the collected low-priority data is packaged and uploaded at one time at regular intervals (such as every hour).

[0013] Preferably, the system monitors the network status in real time, including bandwidth usage, latency, and packet loss rate, to ensure effective uploading even when the network conditions are poor.

[0014] Preferably, the system can dynamically adjust the frequency of data upload according to the network load. For example, when the network is congested, high-frequency uploads can be reduced and data packaging can be increased to reduce network pressure.

[0015] Preferably, the data packaging methods in the upload strategy include data compression and intelligent packaging; data compression is used for uploading large amounts of data, and by using compression technology (such as Gzip, LZ4, etc.) to reduce the data size, reduce the transmission bandwidth occupancy, and increase the transmission speed. Intelligent packaging is used to package data of the same type or similar time to reduce the overhead of multiple transmissions; for example, the status monitoring data within the same time period is merged into one data packet for uploading.

[0016] Preferably, a data integrity verification mechanism, such as a checksum or hash algorithm, is used during the upload process to ensure that the data is not tampered with or damaged during transmission.

[0017] Beneficial effects of this step: By formulating a scientific and reasonable upload strategy, combined with real-time monitoring of data priority and network conditions, this step can ensure timely upload of key data and efficient management of low-priority data, and optimize the overall data transmission process. This strategy provides a good data foundation for subsequent cloud analysis and improves the intelligent level of industrial data processing.

[0018] Furthermore, in step S500, the cloud data is integrated in the cloud server, and the cloud data is deeply analyzed, and the machine learning model is applied to perform anomaly detection and trend prediction, including the following steps: S501, after receiving the data uploaded from the edge device, the cloud server integrates it with the data of other edge nodes to form a complete data set. The integrated data can be uniformly managed and analyzed across regions and devices.

[0019] Specifically, the cloud server receives industrial data uploaded from various edge computing devices to obtain cloud data, which includes real-time monitoring data, historical records, alarm information, and preprocessing results, and uses encrypted transmission protocols (such as TLS) for data transmission.

[0020] Furthermore, the cloud data is standardized on the cloud server, where standardization includes unified formats and units. For example, the temperature data is standardized to degrees Celsius, and the timestamp is converted to a unified format to ensure data consistency. The integrated data is stored in a distributed database on the cloud, and the integrated data is identified and classified so that the required data can be quickly retrieved for subsequent analysis. Through these steps, the integrated cloud data set can support more comprehensive analysis and decision-making, and improve the efficiency of overall data management.

[0021] S502, the cloud server performs complex analysis operations through high-performance computing resources and big data analysis tools. In-depth analysis includes global optimization of the production process, equipment health status monitoring, energy consumption management, production efficiency analysis, etc.

[0022] Furthermore, by using a variety of big data analysis tools, the system can conduct a comprehensive assessment of each link in the production process, identify inefficient parts and make corresponding improvement suggestions, such as analyzing the data flow of the production line to find bottlenecks and optimize resource allocation. In addition, the cloud server will continuously monitor the key indicators of the equipment to detect and predict potential failures in a timely manner to ensure the normal operation of the equipment; and analyze the energy consumption data of the equipment and production process, identify abnormal consumption and make suggestions to reduce energy consumption, so as to achieve higher resource utilization. Finally, by analyzing cloud data to evaluate the impact of various factors on efficiency in the production process, data-based production decisions are generated, thereby improving overall production efficiency and the reliability of equipment operation.

[0023] S503, based on historical data and real-time data, the cloud applies machine learning models to perform anomaly detection and trend prediction. For example, the future state of the equipment can be predicted through the time series prediction model, helping enterprises to detect potential failures in advance and perform preventive maintenance.

[0024] In step S503, the cloud system realizes abnormality detection and trend prediction of industrial data by constructing and training machine learning models. First, the system uses a large amount of historical data to train the model to improve its ability to identify abnormal situations and predict future trends. The training models include support vector machines (SVM), random forests, and neural networks. At the same time, during the training process, real-time data will also be incorporated into the model to enable it to adapt to the latest production environment and ensure the accuracy and real-time nature of the prediction. In terms of abnormality detection, the trained model will continuously monitor the real-time data stream and quickly identify abnormal conditions of the equipment. For example, when the equipment parameters exceed the set threshold, the system will immediately issue an alarm to notify the management. Through the self-learning algorithm, the model can also be continuously adjusted and optimized according to new data to improve the detection accuracy of abnormal conditions. For trend prediction, the system predicts the future operating status of the equipment by applying time series prediction models (such as LSTM, ARIMA, etc.), helping enterprises to discover potential faults in advance and perform preventive maintenance. In addition, the regression model is used to predict changes in key parameters in production, such as equipment load and production efficiency, to help management make forward-looking decisions, optimize production plans and resource allocation, and thus improve overall production efficiency and equipment reliability.

[0025] The beneficial effects of the present invention are as follows: by introducing edge computing, priority management and dynamic upload strategies, the deficiencies of ordinary cloud computing industrial data processing methods in terms of data processing efficiency, real-time and intelligent analysis capabilities are solved, and the efficiency and security of industrial data processing are further improved.

[0026] To achieve the above-mentioned purpose, the second aspect embodiment of the present invention also proposes a multi-level cloud-based industrial data collaborative processing system, which includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in a multi-level cloud-based industrial data collaborative processing method. The multi-level cloud-based industrial data collaborative processing system runs on desktop computers, notebooks, PDAs, and computing devices in cloud data centers.

[0027] By executing a multi-level cloud-based industrial data collaborative processing method based on a multi-level cloud-based industrial data collaborative processing system, the introduction of edge computing, priority management and dynamic upload strategies can solve the shortcomings of ordinary cloud computing industrial data processing methods in data processing efficiency, real-time and intelligent analysis capabilities, and further improve the efficiency and security of industrial data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1 Shown is a flow chart of a multi-level cloud-based industrial data collaborative processing method; Figure 2 The figure shows a structure diagram of a multi-level cloud-based industrial data collaborative processing system. DETAILED DESCRIPTION

[0029] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0030] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0031] like Figure 1 The flowchart of a multi-level cloud industrial data collaborative processing method according to the present invention is shown below. Figure 1 A multi-level cloud-based industrial data collaborative processing method according to an embodiment of the present invention is described below.

[0032] The present invention proposes a multi-level cloud-based industrial data collaborative processing method, the method comprising the following steps: S100, acquires industrial data through sensors and acquisition devices; S200, performs data filtering and preprocessing on industrial data through edge computing devices; S300, analyzing the filtered and pre-processed industrial data, and performing priority classification to obtain data priority; S400, formulate an upload strategy according to the data priority, and upload the filtered and pre-processed industrial data to the cloud server through the upload strategy and record it as cloud data; S500,integrates cloud data on cloud servers, performs in-depth analysis on cloud data, and applies machine learning models for anomaly detection and trend prediction.

[0033] According to the collaborative processing method of the embodiment of the present invention, the shortcomings of ordinary cloud computing industrial data processing methods in data processing efficiency, real-time and intelligent analysis capabilities can be solved by introducing edge computing, priority management and dynamic upload strategies, thereby further improving the efficiency and security of industrial data processing.

[0034] Furthermore, in step S100, the data acquisition method of industrial data includes arranging sensors and acquisition equipment at the industrial site to monitor parameters in the industrial production process in real time, and the parameters include: temperature, pressure, vibration, equipment operation status, etc. The types of sensors and acquisition equipment for acquiring industrial data include temperature sensors, pressure sensors, flow meters, power monitoring equipment, etc.

[0035] In step S200, the process of filtering and preprocessing industrial data through edge computing devices includes: identifying and removing noise of instantaneous fluctuations in sensor data through statistical analysis, and then using smoothing algorithms (such as moving average or weighted average) to reduce random fluctuations in real-time industrial data; when missing values ​​appear in the detection data set, the industrial data is processed by interpolation, mean substitution or deletion of missing value rows, and finally the processed data is uploaded to the cloud or other data storage systems as needed as a basis for subsequent in-depth analysis and decision support.

[0036] In step S300, the filtered and pre-processed industrial data is analyzed and prioritized to obtain data priorities, including: Among them, priority division includes: the system divides data into high priority, medium priority and low priority data; among them, high priority data includes: safety alarms, equipment failure information, abnormal monitoring data, etc.; medium priority data includes: production monitoring data, environmental parameters, etc.; priority data includes historical data and routine operation data.

[0037] Specifically, the characteristics of high-priority data include alarm data related to safety and stability, equipment failure status, and monitoring data that exceeds the threshold. These data need to be uploaded to the cloud immediately for processing so that rapid response measures can be taken. The characteristics of medium-priority data include monitoring data that has a significant impact on the production process. These data can be set to be uploaded at a scheduled time or under specific conditions to ensure that important information is not missed. The characteristics of low-priority data include historical operation data, regular monitoring data, or data that does not affect immediate decision-making. These data can be uploaded in batches and can be performed when the network bandwidth is sufficient to reduce the burden of real-time transmission.

[0038] The beneficial effects of this step are: by conducting in-depth analysis of filtered and preprocessed industrial data, and prioritizing it according to the characteristics of the data and the needs of the production process, timely processing and efficient transmission of key information are ensured; and such priority management not only optimizes the data upload strategy, but also improves the safety and production efficiency of industrial equipment.

[0039] S400, formulate an upload strategy according to the data priority, and upload the filtered and pre-processed industrial data to the cloud server through the upload strategy and record it as cloud data; Specifically, high-priority data adopts real-time upload or fast upload strategies to ensure that it is sent to the cloud immediately when an event occurs; medium-priority data is set to be uploaded at a scheduled time or when specific conditions are triggered to ensure that data is not missed; low-priority data adopts batch upload or periodic upload strategies, for example, the collected low-priority data is packaged and uploaded at one time at regular intervals (such as every hour).

[0040] Preferably, the system monitors the network status in real time, including bandwidth usage, latency, and packet loss rate, to ensure effective uploading even when the network conditions are poor.

[0041] Preferably, the system can dynamically adjust the frequency of data upload according to the network load. For example, when the network is congested, high-frequency uploads can be reduced and data packaging can be increased to reduce network pressure.

[0042] Preferably, the data packaging methods in the upload strategy include data compression and intelligent packaging; data compression is used for uploading large amounts of data, and by using compression technology (such as Gzip, LZ4, etc.) to reduce the data size, reduce the transmission bandwidth occupancy, and increase the transmission speed. Intelligent packaging is used to package data of the same type or similar time to reduce the overhead of multiple transmissions; for example, the status monitoring data within the same time period is merged into one data packet for uploading.

[0043] Preferably, a data integrity verification mechanism, such as a checksum or hash algorithm, is used during the upload process to ensure that the data is not tampered with or damaged during transmission.

[0044] Beneficial effects of this step: By formulating a scientific and reasonable upload strategy, combined with real-time monitoring of data priority and network conditions, this step can ensure timely upload of key data and efficient management of low-priority data, and optimize the overall data transmission process. This strategy provides a good data foundation for subsequent cloud analysis and improves the intelligent level of industrial data processing.

[0045] Furthermore, in step S500, the cloud data is integrated in the cloud server, and the cloud data is deeply analyzed, and the machine learning model is applied to perform anomaly detection and trend prediction, including the following steps: S501, after receiving the data uploaded from the edge device, the cloud server integrates it with the data of other edge nodes to form a complete data set. The integrated data can be uniformly managed and analyzed across regions and devices.

[0046] Specifically, the cloud server receives industrial data uploaded from various edge computing devices to obtain cloud data, which includes real-time monitoring data, historical records, alarm information, and preprocessing results, and uses encrypted transmission protocols (such as TLS) for data transmission.

[0047] Furthermore, the cloud data is standardized on the cloud server, where standardization includes unified formats and units. For example, the temperature data is standardized to degrees Celsius, and the timestamp is converted to a unified format to ensure data consistency. The integrated data is stored in a distributed database on the cloud, and the integrated data is identified and classified so that the required data can be quickly retrieved for subsequent analysis. Through these steps, the integrated cloud data set can support more comprehensive analysis and decision-making, and improve the efficiency of overall data management.

[0048] S502, the cloud server performs complex analysis operations through high-performance computing resources and big data analysis tools. In-depth analysis includes global optimization of the production process, equipment health status monitoring, energy consumption management, production efficiency analysis, etc.

[0049] Furthermore, by using a variety of big data analysis tools, the system can conduct a comprehensive assessment of each link in the production process, identify inefficient parts and make corresponding improvement suggestions, such as analyzing the data flow of the production line to find bottlenecks and optimize resource allocation. In addition, the cloud server will continuously monitor the key indicators of the equipment to detect and predict potential failures in a timely manner to ensure the normal operation of the equipment; and analyze the energy consumption data of the equipment and production process, identify abnormal consumption and make suggestions to reduce energy consumption, so as to achieve higher resource utilization. Finally, by analyzing cloud data to evaluate the impact of various factors on efficiency in the production process, data-based production decisions are generated, thereby improving overall production efficiency and the reliability of equipment operation.

[0050] S503, based on historical data and real-time data, the cloud applies machine learning models to perform anomaly detection and trend prediction. For example, the future state of the equipment can be predicted through the time series prediction model, helping enterprises to detect potential failures in advance and perform preventive maintenance.

[0051] In step S503, the cloud system realizes abnormality detection and trend prediction of industrial data by constructing and training machine learning models. First, the system uses a large amount of historical data to train the model to improve its ability to identify abnormal situations and predict future trends. The training models include support vector machines (SVM), random forests, and neural networks. At the same time, during the training process, real-time data will also be incorporated into the model to enable it to adapt to the latest production environment and ensure the accuracy and real-time nature of the prediction. In terms of abnormality detection, the trained model will continuously monitor the real-time data stream and quickly identify abnormal conditions of the equipment. For example, when the equipment parameters exceed the set threshold, the system will immediately issue an alarm to notify the management. Through the self-learning algorithm, the model can also be continuously adjusted and optimized according to new data to improve the detection accuracy of abnormal conditions. For trend prediction, the system predicts the future operating status of the equipment by applying time series prediction models (such as LSTM, ARIMA, etc.), helping enterprises to discover potential faults in advance and perform preventive maintenance. In addition, the regression model is used to predict changes in key parameters in production, such as equipment load and production efficiency, to help management make forward-looking decisions, optimize production plans and resource allocation, and thus improve overall production efficiency and equipment reliability.

[0052] The beneficial effects of the present invention are as follows: by introducing edge computing, priority management and dynamic upload strategies, the deficiencies of ordinary cloud computing industrial data processing methods in terms of data processing efficiency, real-time and intelligent analysis capabilities are solved, and the efficiency and security of industrial data processing are further improved.

[0053] The multi-level cloud-based industrial data collaborative processing system includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned multi-level cloud-based industrial data collaborative processing method embodiment are implemented. The multi-level cloud-based industrial data collaborative processing system can be run on computing devices such as desktop computers, laptops, mobile phones, cell phones, tablet computers, PDAs, and cloud data centers. The executable system may include, but is not limited to, processors, memories, and server clusters.

[0054] The embodiment of the present invention provides a multi-level cloud-based industrial data collaborative processing system, such as Figure 2 As shown, a multi-level cloud-based industrial data collaborative processing system of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned multi-level cloud-based industrial data collaborative processing method embodiment are implemented. The processor executes the computer program to run in the following system units: A collection unit 21, used to obtain industrial data through sensors and collection equipment; A conversion unit 22, used for filtering and preprocessing industrial data through an edge computing device; The loading unit 23 is used to analyze the filtered and preprocessed industrial data and perform priority classification to obtain data priority; A management unit 24, used for formulating an upload strategy based on data priority, and uploading the filtered and pre-processed industrial data to a cloud server through the upload strategy and recording it as cloud data; The analysis unit 25 is used to integrate the cloud data in the cloud server, perform in-depth analysis on the cloud data, and apply machine learning models to perform anomaly detection and trend prediction.

[0055] The multi-level cloud-based industrial data collaborative processing system can run on computing devices such as desktop computers, laptops, PDAs, and cloud data centers. The multi-level cloud-based industrial data collaborative processing system includes, but is not limited to, processors and memories. Those skilled in the art will understand that the example is merely an example of a multi-level cloud-based industrial data collaborative processing method and system, and does not constitute a limitation on a multi-level cloud-based industrial data collaborative processing method and system, which may include more or fewer components than the example, or a combination of certain components, or different components. For example, the multi-level cloud-based industrial data collaborative processing system may also include input and output devices, network access devices, buses, etc.

[0056] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete component gate circuits or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the multi-level cloud-based industrial data collaborative processing system, and uses various interfaces and lines to connect the various sub-regions of the multi-level cloud-based industrial data collaborative processing system.

[0057] The memory can be used to store the computer program and / or module, and the processor realizes the various functions of the multi-level cloud-based industrial data collaborative processing method and system by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0058] The present invention provides a multi-level cloud-based industrial data collaborative processing method, which obtains industrial data through sensors and acquisition devices; filters and preprocesses industrial data through edge computing devices; analyzes the filtered and preprocessed industrial data, and prioritizes the data to obtain data priority; formulates an upload strategy according to the data priority, and uploads the filtered and preprocessed industrial data to the cloud server through the upload strategy and records it as cloud data; integrates the cloud data on the cloud server, and deeply analyzes the cloud data, and applies machine learning models to perform anomaly detection and trend prediction. According to the collaborative processing method of the embodiment of the present invention, the efficiency and security of industrial data processing can be improved. Although the description of the present invention has been quite detailed and several of the embodiments are described in particular, it is not intended to be limited to any of these details or embodiments or any special embodiments, so as to effectively cover the intended scope of the present invention. In addition, the above describes the present invention with the foreseeable embodiments of the inventor, the purpose of which is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen may still represent equivalent changes to the present invention.

Claims

1. A multi-level cloud-based industrial data collaborative processing method, characterized in that: The method comprises the following steps: S100, acquires industrial data through sensors and acquisition devices; S200, performs data filtering and preprocessing of industrial data through edge computing devices; S300, analyzing the filtered and pre-processed industrial data, and performing priority classification to obtain data priority; S400, formulate an upload strategy according to the data priority, and upload the filtered and pre-processed industrial data to the cloud server through the upload strategy and record it as cloud data; S500,integrates cloud data on cloud servers, performs in-depth analysis on cloud data, and applies machine learning models for anomaly detection and trend prediction.

2. The multi-level cloud-based industrial data collaborative processing method according to claim 1 is characterized in that: In step S100, the data acquisition method of industrial data includes arranging sensors and acquisition equipment at the industrial site to monitor parameters in the industrial production process in real time, and the parameters include: temperature, pressure, vibration, and equipment operation status; Among them, the types of sensors and collection equipment for obtaining industrial data include temperature sensors, pressure sensors, flow meters, and power monitoring equipment.

3. The multi-level cloud-based industrial data collaborative processing method according to claim 1 is characterized in that: In step S200, the process of filtering and preprocessing industrial data by edge computing devices includes: Statistical analysis is used to identify and remove noise from instantaneous fluctuations in sensor data, and a smoothing algorithm is used to reduce random fluctuations in real-time industrial data. When missing values ​​appear in the detection data set, the industrial data is processed by interpolation, mean substitution, or deletion of missing value rows. Finally, the processed data is uploaded to the cloud or other data storage systems as needed, serving as the basis for subsequent in-depth analysis and decision support.

4. The multi-level cloud-based industrial data collaborative processing method according to claim 1 is characterized in that: In step S300, the filtered and pre-processed industrial data is analyzed and prioritized to obtain data priority. include: Among them, priority division includes: the system divides data into high priority, medium priority and low priority data; among them, high priority data includes: safety alarms, equipment failure information, abnormal monitoring data; medium priority data includes: production monitoring data, environmental parameters; priority data includes historical data, routine operation data.

5. The multi-level cloud-based industrial data collaborative processing method according to claim 4 is characterized in that: In step S400, an upload strategy is formulated according to the data priority, and the filtered and pre-processed industrial data is uploaded to the cloud server and recorded as cloud data through the upload strategy, including: high-priority data adopts real-time upload or fast upload strategy to ensure that it is immediately sent to the cloud when an event occurs; medium-priority data is set to be uploaded at a scheduled time or when triggered by specific conditions to ensure that data is not missed; low-priority data adopts batch upload or periodic upload strategy.

6. The multi-level cloud-based industrial data collaborative processing method according to claim 1 is characterized in that: In step S500, the cloud data is integrated in the cloud server, and the cloud data is deeply analyzed. The application of the machine learning model for anomaly detection and trend prediction includes the following steps: S501, after receiving the data uploaded from the edge device, the cloud server integrates it with the data of other edge nodes to form a complete data set; S502, the cloud server performs complex analysis operations using high-performance computing resources and big data analysis tools; S503, based on historical data and real-time data, the cloud applies machine learning models to perform anomaly detection and trend prediction.

Images