Intelligent data acquisition method and system of industrial edge gateway

Abstract

The invention relates to the field of data processing, in particular to an intelligent data acquisition method and system for an industrial edge gateway, and the method comprises the steps: obtaining industrial data of each industrial device, carrying out the preprocessing, and carrying out the data compression through employing an LZ78 algorithm, and obtaining a compression result; meanwhile, performing statistics on equipment parameters and data volume of the edge gateway, and calculating data acquisition pressure of the edge gateway and data acquisition burden indexes of various types of equipment; and according to the data acquisition burden index of each device and the compression result of each device, adjusting the data acquisition frequency, and performing data acquisition on the device accessed by the edge gateway at the adjusted acquisition frequency. According to the invention, the data acquisition frequency is dynamically adjusted, and the data flow is intelligently managed according to the data acquisition burden index and the compression result, so that unnecessary data transmission is reduced, and the consumption of network bandwidth and storage resources is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more specifically, to an intelligent data collection method and system for an industrial edge gateway. Background Art

[0002] Edge Gateway is a device or software deployed at the edge of the network, which plays a vital role in the edge computing architecture. The main function of the edge gateway is to connect different devices and networks, process data streams, and perform preliminary processing and analysis before the data is transmitted to the cloud or central data center. In the manufacturing execution system, data acquisition technology provides timely and detailed field information for the manufacturing execution system, and provides a reliable basis for production decision-making, scheduling, and equipment monitoring. Therefore, data acquisition technology is an important part of the manufacturing execution system. Usually, industrial field equipment is monitored in real time through the edge gateway, and the latest collected data is sent to the cloud platform, which then analyzes the collected data to complete the adjustment of production decisions and scheduling.

[0003] The existing Chinese patent application document with publication number CN117202126A discloses an industrial data acquisition method for an intelligent edge gateway based on a 5G network, which relates to the field of data acquisition technology; including: Step 1: connecting the data acquisition terminal to the intelligent edge gateway based on the 5G network, deploying data acquisition services, and configuring the data acquisition terminal driver according to the corresponding protocol, Step 2: collecting data by frequency through the data acquisition terminal according to the corresponding protocol, caching the collected data, and processing the data according to the rules, Step 3: using json as the transmission format, reporting and forwarding the collected data to a third-party system or saving it locally in the form of a file, Step 4: providing an RPC interface to the outside for related configuration of visualization software or applications and real-time presentation of data; greatly reducing the cost of subsequent maintenance and upgrades and enhancing the efficiency of on-site implementation.

[0004] In the application document, the cost of subsequent maintenance and upgrades is significantly reduced and the efficiency of on-site implementation is enhanced by quickly deploying data acquisition services, automated data acquisition, flexible data reporting and storage, and providing an RPC interface for real-time data presentation. Currently, edge gateway data acquisition programs generally use real-time monitoring, that is, periodically accessing text files or databases of industrial equipment to determine whether there is new data to be collected, which will cause a certain degree of resource waste. At the same time, if the number of acquisition devices is large, the number of requests processed by the cloud platform per unit time will increase dramatically, and the server will face the problem of excessive load. Summary of the invention

[0005] In order to solve the problem that the number of acquisition devices is huge, the requests processed by the cloud platform per unit time will increase dramatically, and the server will face the problem of excessive load. The present invention provides solutions in the following aspects.

[0006] In a first aspect, an intelligent data collection method for an industrial edge gateway includes: obtaining industrial data of each industrial device and preprocessing it, compressing the preprocessed industrial data using an LZ78 algorithm to obtain a compression result; obtaining device parameters of the edge gateway, counting the number of devices and data volume of each category actually connected to the edge gateway and the average collection speed of each category to calculate the data collection pressure of the edge gateway, and calculating the data collection burden index of each category of equipment according to the data collection pressure of the edge gateway and the data collected by the edge gateway when connected to each category of equipment; adjusting the data collection frequency according to the data collection burden index of each device and the compression result of each device, and collecting data from the devices connected to the edge gateway at the adjusted collection frequency; wherein, the collection frequency Satisfies the following relationship: ; In the formula, Indicates that the edge gateway is connected to Data collection burden index for this type of equipment, Indicates the maximum data collection frequency supported by the current edge gateway. Indicates that the edge gateway is connected to The first device in the The number of entries in the dictionary formed when a device performs data compression, Indicates the maximum number of entries in the dictionary formed when the edge gateway connects to all devices for data compression. Indicated by natural constant The exponential function of base .

[0007] The effect is: by reducing unnecessary data collection and compressing data, the number of requests processed by the cloud platform per unit time is reduced, thereby reducing the server load; the collection frequency is dynamically adjusted according to the data collection burden index and compression results, ensuring that resources are more reasonably allocated among different devices and data types; for devices with a low data collection burden index or high compression efficiency, the collection frequency is appropriately increased to ensure the real-time and accuracy of key data; by flexibly adjusting the collection frequency, the system can better adapt to different industrial scenarios and data collection needs, improving the robustness and stability of the system.

[0008] Preferably, the data collection pressure of the edge gateway includes:

[0009] The ratio of the total number of currently connected devices to the maximum number of connected devices on the edge gateway is taken as the saturation level of the access devices;

[0010] The ratio of the data volume produced and output by the current device to the maximum transmission bandwidth of the edge gateway is taken as the saturation level of data transmission;

[0011] The product of the saturation level of the access device and the saturation level of the data transmission is taken as the data collection pressure.

[0012] The effect is: by calculating the saturation level of access devices and the saturation level of data transmission, the data collection pressure of the edge gateway at the current moment can be more accurately evaluated. By reducing unnecessary data transmission and optimizing data flow, the throughput and response speed of the edge gateway can be improved, thereby improving the overall system performance.

[0013] Preferably, the data collection pressure of the edge gateway also includes:

[0014] The average energy consumption level is the average value of the sum of the ratios of the average energy consumption of all devices to the maximum energy consumption limit of the edge gateway;

[0015] The average value of the sum of the ratios between the highest priority data and all data in all devices is taken as the average priority level;

[0016] The product of the average energy consumption level and the average priority level is used as the data collection pressure.

[0017] The effect is that it not only takes into account the transmission and access pressure of data, but also integrates the impact of energy consumption and data priority. By calculating the average energy consumption level, it can identify devices or categories with high energy consumption, so as to take measures to reduce energy consumption and optimize energy use.

[0018] Preferably, the data collection burden index includes:

[0019] Obtain data from a production cycle of each type of equipment, and use the LSTM algorithm to make predictions to obtain data from the entire production cycle;

[0020] Based on the data of the complete production cycle, the amount of data generated by each device per unit time is taken as the data growth rate, and linear normalization is performed. The data acquisition pressure is taken as the exponential decay factor. The data acquisition burden index is obtained by combining the normalized data growth rate and the exponential decay factor.

[0021] The effect is: by calculating the amount of data generated per unit time, the data generation rate of each device can be quantified, providing accurate data support for the data collection plan. The data collection pressure acts as an exponential decay factor, allowing the system to dynamically adjust the data collection frequency according to the current pressure to adapt to the changing network and device status. When the data collection pressure is high, the load on the edge gateway can be reduced by reducing the data collection frequency to prevent system overload.

[0022] Preferably, the data collection burden index further includes:

[0023] Obtain data from a production cycle of each type of equipment, and use the LSTM algorithm to make predictions to obtain data from the entire production cycle;

[0024] Based on the data of the complete production cycle, the amount of highest priority data generated per unit time is taken as the growth rate of the highest priority data, and linear processing is performed. The product of the normalized growth rate of the highest priority data and the data collection pressure of the edge gateway is taken as the data collection burden index.

[0025] The effect is: by giving priority to high-priority data, the processing efficiency of key data can be improved, ensuring the continuity and response speed of key business processes; by distinguishing between high-priority and non-high-priority data, the occupation of system resources by non-critical data is reduced, and their interference with key data processing is reduced.

[0026] Preferably, the pre-processed industrial data is compressed using the LZ78 algorithm to obtain a compression result, including:

[0027] According to the importance of the equipment, the real-time requirements of the data and the historical data mode, an initial collection frequency is set for each type of equipment, and data is collected from the connected equipment according to the initially set frequency to obtain industrial data; the industrial data is preprocessed using the UTF-8 encoding method, wherein the preprocessing includes: data cleaning, formatting and encoding conversion;

[0028] During the compression process, the dictionary constructed by each industrial device when compressing data is obtained in real time, and the LZ78 algorithm is used to store repeated patterns in the data according to the constructed dictionary, thereby achieving data compression and obtaining the compression result.

[0029] Preferably, adjusting the data collection frequency includes:

[0030] In response to the difference between the collection frequency and the initial collection frequency being less than the preset threshold of the initial collection frequency, the collection frequency will not be changed; conversely, when the difference between the collection frequency and the initial collection frequency is greater than or equal to the preset threshold of the initial collection frequency, the initial collection frequency of the edge gateway to the access device is adjusted to the collection frequency.

[0031] In a second aspect, an intelligent data collection system for an industrial edge gateway includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent data collection method for the industrial edge gateway is implemented.

[0032] The present invention has the following effects:

[0033] 1. The present invention dynamically adjusts the data collection frequency and intelligently manages the data flow according to the data collection burden index and the compression result, thereby reducing unnecessary data transmission and reducing the consumption of network bandwidth and storage resources. It not only improves the resource utilization of the edge gateway, but also helps to reduce the operating costs of the enterprise, especially in terms of data transmission and storage costs.

[0034] 2. The present invention ensures that the edge gateway can still operate stably and will not crash due to overload when the number of devices is huge or the amount of data increases dramatically by real-time monitoring and adjusting the data collection pressure. At the same time, the rapid response and processing of high-priority data improves the system's support capabilities for key business processes and enhances the system's real-time and robustness.

[0035] 3. The present invention uses the LZ78 algorithm to perform data compression and implements an automated data collection process through computer program instructions, thereby reducing human intervention and improving the level of intelligent data processing; it not only improves the efficiency and accuracy of data processing, but also provides technical support for the dynamic adaptation of the industrial Internet of Things and the optimal allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0037] Figure 1 It is a method flow chart of steps S1 to S3 in an intelligent data collection method for an industrial edge gateway in an embodiment of the present invention.

[0038] Figure 2 It is a structural block diagram of an intelligent data acquisition system of an industrial edge gateway according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0040] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0041] Specific implementation scenario: In a large manufacturing plant, there are tens of thousands of sensors and devices distributed on the production line, including temperature sensors, pressure sensors, machine status monitoring devices, etc. These devices continuously generate a large amount of real-time data, which is essential for monitoring production processes, optimizing operations, and predicting maintenance; the edge gateway is deployed at the edge of the factory network as the entry point of the data flow, and is mainly responsible for collecting data from various sensors and devices on the production line.

[0042] Reference Figure 1 , an intelligent data collection method for an industrial edge gateway includes steps S1 to S3, which are specifically as follows:

[0043] S1: Obtain the industrial data of each industrial device and perform preprocessing, and use the LZ78 algorithm to compress the preprocessed industrial data to obtain a compression result.

[0044] According to the importance of the equipment, the real-time requirements of the data and the historical data mode, an initial collection frequency is set for each type of equipment. According to the initially set frequency, data is collected from the connected equipment to obtain industrial data.

[0045] Use UTF-8 encoding to pre-process industrial data, including data cleaning, formatting and encoding conversion;

[0046] During the compression process, the dictionary constructed by each industrial device when compressing data is obtained in real time, and the LZ78 algorithm is used to store repeated patterns in the data according to the constructed dictionary, thereby achieving data compression and obtaining the compression result.

[0047] It should be noted that, among them, building a dictionary is a step in the compression process of the LZ78 algorithm, and the dictionary is used to store repeated patterns or sequences that appear in the data. When the algorithm encounters the same pattern again, it can be replaced with a reference in the dictionary, thereby reducing data redundancy.

[0048] Industrial equipment data is divided into: industrial site data and equipment data. Industrial site data includes but is not limited to: personnel data, material data, and workstation detection data; equipment data includes but is not limited to: operating parameter information, operating status information, and alarm information.

[0049] That is to say, since there are many types of industrial equipment data, the industrial equipment data needs to be preprocessed. In this embodiment, UTF-8 encoding is adopted. UTF-8 encoding is a well-known technology in the field and will not be described in detail.

[0050] Further analysis shows that in large-scale industrial scenarios, a variety of industrial automation operations need to be performed, and there are a variety of industrial equipment, so a large amount of data needs to be collected. Since the data transmission capacity of the edge gateway is limited, the present invention calculates the data transmission pressure of the edge gateway by the number of industrial equipment and the amount of data that the edge gateway needs to collect. The specific analysis steps are as follows:

[0051] S2: Obtain the device parameters of the edge gateway, count the number of devices and data volume of each category actually connected to the edge gateway, and the average collection speed of each category, so as to calculate the data collection pressure of the edge gateway. According to the data collection pressure of the edge gateway and the data collected by the edge gateway when connected to each category of devices, calculate the data collection burden index of each category of equipment.

[0052] The ratio of the total number of currently connected devices to the maximum number of connected devices on the edge gateway is taken as the saturation level of the access devices;

[0053] The ratio of the data volume produced and output by the current device to the maximum transmission bandwidth of the edge gateway is taken as the saturation level of data transmission;

[0054] The product of the saturation level of the access device and the saturation level of the data transmission is taken as the data collection pressure.

[0055] Specifically, the data collection pressure satisfies the following relationship:

[0056] ;

[0057] In the formula, Indicates the data collection pressure of the edge gateway, Indicates the maximum number of devices connected to the edge gateway. Indicates the edge gateway's currently connected The number of devices of this class, Indicates the number of device types currently connected to the edge gateway. Indicates the edge gateway's currently connected Average data collection speed for this type of device, Indicates the maximum transmission bandwidth of the edge gateway.

[0058] That is to say, Indicates the saturation level of the number of devices connected to the edge gateway. The larger the value, the more devices the edge gateway needs to collect data from, and the greater the data collection pressure on the edge gateway; the smaller the value, the fewer devices the edge gateway needs to collect data from, and the smaller the data collection pressure on the edge gateway. Indicates the data transmission saturation of the edge gateway. The faster the data collection speed of the industrial equipment connected to the gateway, The larger the value, the greater the data collection pressure of the industrial edge gateway. When the data collection speed of the industrial equipment connected to the gateway is slower, The smaller it is, the less pressure there is on data collection on the industrial edge gateway.

[0059] In addition, in another embodiment, the average value of the sum of the ratios of the average energy consumption of all devices to the maximum energy consumption limit of the edge gateway is taken as the average energy consumption level;

[0060] The average value of the sum of the ratios between the highest priority data and all data in all devices is taken as the average priority level;

[0061] The product of the average energy consumption level and the average priority level is taken as the data collection pressure.

[0062] Specifically, the data collection pressure satisfies the following relationship:

[0063] ;

[0064] In the formula, Indicates the data collection pressure of the edge gateway, Indicates the number of device types currently connected to the edge gateway. Indicates the edge gateway's currently connected The number of devices of this class, Indicates The ratio between the average energy consumption of a device and its maximum energy consumption. Indicates The ratio of the highest priority data to all data in the device class.

[0065] In other words, the higher the average energy consumption level, the greater the energy consumption pressure on the edge gateway; similarly, the higher the average priority level, the greater the pressure on the edge gateway in processing high-priority data.

[0066] Data collection burden index, including:

[0067] Obtain data from a production cycle of each type of equipment, and use the LSTM algorithm to make predictions to obtain data from the entire production cycle;

[0068] Based on the data of the complete production cycle, the amount of data generated by each device per unit time is taken as the data growth rate, and linear normalization is performed. The data collection pressure is taken as the exponential decay factor. The data collection burden index is obtained by combining the normalized data growth rate and the exponential decay factor.

[0069] It should be noted that the specific method for predicting the data size of all devices connected to the edge gateway during a complete production cycle is as follows:

[0070] Data collection: collect the sequence of data sizes collected by all devices connected to the edge gateway at each moment within a period of time. In this embodiment, the time period is 1 hour. The implementer can determine the length of the time period based on the approximate time of a complete production cycle.

[0071] Create input and output data pairs: use a data length of 1 minute as the size of the sliding window, slide in the above data sequence, use the data in the sliding window at each moment as the input of the network, and the data in the sliding window at the next moment of each moment as the label of the above input.

[0072] Network selection: In this example, the LSTM network is used. Implementers can also use sequence prediction networks such as bidirectional LSTM according to actual conditions.

[0073] Loss function: In this example, the cross entropy loss function is used. The implementer can also choose other loss functions according to the actual situation.

[0074] Data prediction: The data prediction network is trained in the above manner, and the trained network is used for continuous reasoning to obtain the data size of all devices connected to the edge gateway during a complete production cycle.

[0075] By using the LSTM algorithm to predict data trends within the complete production cycle and reducing the time to collect the complete data cycle, the reliance on real-time data collection can be reduced, thereby saving the time and resources required for continuous monitoring and data collection. This also helps to reduce the frequency of data collection during periods of low data generation rates and increase the frequency of data collection during periods of high data generation rates.

[0076] Specifically, the data collection burden index satisfies the following relationship:

[0077] ;

[0078] In the formula, Indicates that the edge gateway is connected to Data collection burden index for this type of equipment, Indicates the data collection pressure of the edge gateway, Indicates that the edge gateway is connected to The average amount of data generated by all devices in the same class in a complete production cycle, Indicates that the edge gateway is connected to The time interval for all devices in the class to generate new data, represents the linear normalization function, Indicated by natural constant The exponential function of base .

[0079] That is to say, Indicates The average data generation rate of the device type. The larger the value, the faster the edge gateway accesses the The larger the amount of data that a device of this type needs to transmit, the greater the data collection burden index of this type of device; the smaller the value, the smaller the edge gateway access to the The smaller the amount of data that a device needs to transmit, the smaller the data collection burden index of the device. Normalization was performed.

[0080] It is still necessary to explain that in different industrial production scenarios: the edge gateway will face different data collection pressures. For the edge gateway in the industrial production scenario with heavy data collection pressure, the greater the burden on the gateway is, the greater the burden on the gateway is. right Make corrections when The bigger the The smaller the right The greater the correction capability, the greater the data collection burden index of the device. For edge gateways in industrial production scenarios with low data collection pressure, the smaller the burden of the access device on it, the less it needs to be corrected. Make corrections, so when The more hours, The larger the right The smaller the correction ability.

[0081] In addition, in another embodiment, the data collection burden index further includes:

[0082] Obtain data from a production cycle of each type of equipment, and use the LSTM algorithm to make predictions to obtain data from the entire production cycle;

[0083] Based on the data of the complete production cycle, the amount of highest priority data generated per unit time is taken as the growth rate of the highest priority data, and linear processing is performed. The product of the normalized growth rate of the highest priority data and the data collection pressure of the edge gateway is taken as the data collection burden index.

[0084] Specifically, the data collection burden index satisfies the following relationship:

[0085] ;

[0086] In the formula, Indicates that the edge gateway is connected to Data collection burden index for this type of equipment, Indicates the data collection pressure of the edge gateway, No. The average value of the highest priority data in the data of the class device, Indicates that the edge gateway is connected to The time interval for all devices in the class to generate new data, represents the linear normalization function.

[0087] Further analysis shows that due to the limited storage capacity of industrial equipment, the data stored in the industrial equipment needs to be compressed, which will also reduce the pressure on the industrial edge gateway when collecting data. Therefore, the present invention compresses the data collected by industrial equipment through the LZ78 compression algorithm, and adjusts the data collection frequency according to the data collection burden index of each type of equipment and the data compression result of each device.

[0088] S3: According to the data collection burden index of each device and the compression result of each device, the data collection frequency is adjusted, and data is collected from the devices connected to the edge gateway at the adjusted collection frequency.

[0089] Specifically, the acquisition frequency satisfies the following relationship:

[0090] ;

[0091] In the formula, Indicates that the edge gateway is connected to The first device in the The data collection frequency of each device, Indicates that the edge gateway is connected to Data collection burden index for this type of equipment, Indicates the maximum data collection frequency supported by the current edge gateway. Indicates that the edge gateway is connected to The first device in the The number of entries in the dictionary formed when a device performs data compression, Indicates the maximum number of entries in the dictionary formed when the edge gateway connects to all devices for data compression. Indicated by natural constant The exponential function of base .

[0092] That is to say, The larger the value, the heavier the edge gateway collection burden, which means that the data collection rate of such devices is faster, the data volume is larger, or the transmission frequency is higher; in this case, if a higher data collection frequency is used, it may bring greater pressure to the transmission resources of the edge gateway. The larger the value, the lower the collection frequency should be to avoid overloading the edge gateway.

[0093] on the contrary, The smaller it is, the lighter the edge gateway collection burden is, which means that the transmission requirements of such devices are low and the edge gateway resources are less occupied; at the same time, such devices have small data volumes and weak collection requirements, and higher frequencies will not significantly affect the overall resources of the gateway. The smaller it is, the less need there is to reduce the frequency of data collection, thus improving the real-time performance of data collection.

[0094] Since edge gateways usually collect data at the maximum frequency To collect data from the device, right Make adjustments, The larger the right The greater the adjustment force, the lower the frequency of data collection from the edge gateway to the device. The smaller the right The smaller the adjustment force, the real-time data collection of the device can be maintained.

[0095] It should be noted that The larger it is, it means that during the data compression process, the data collected by the device contains a large amount of different information. This type of data may still occupy more bandwidth resources after compression. In order to reduce the pressure of data transmission, the data collection frequency of the device should be appropriately reduced to make the data collection frequency of the device as small as possible.

[0096] on the contrary, The smaller the value, the more the data collected by the device contains a lot of identical information during the data compression process. The compression effect is good and may not cause a large burden on the transmission bandwidth. Therefore, the collection frequency of the device can be reduced to ensure the continuity and real-time nature of the data. The way to Normalized.

[0097] In response to the difference between the collection frequency and the initial collection frequency being less than the preset threshold of the initial collection frequency, the collection frequency will not be changed; conversely, when the difference between the collection frequency and the initial collection frequency is greater than or equal to the preset threshold of the initial collection frequency, the initial collection frequency of the edge gateway to the access device is adjusted to the collection frequency.

[0098] To further illustrate, in this embodiment, the preset threshold is 10%, which can be adjusted according to actual conditions.

[0099] The data collection frequency of the gateway for each access device is obtained by the above method. The edge gateway only needs to obtain the dictionary obtained by LZ78 in real time, and there is no need to access the database or text files of all access devices in real time, which reduces the operating pressure of the industrial edge gateway. The data collection frequency is calculated and data is collected by this method, which enables the industrial edge gateway to flexibly adjust the collection frequency and collection time to ensure the robustness, stability and resource utilization of the system.

[0100] The present invention also provides an intelligent data acquisition system for an industrial edge gateway. Figure 2 As shown, the system includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent data collection method for an industrial edge gateway according to the first aspect of the present invention is implemented.

[0101] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0102] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0103] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0104] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. An intelligent data collection method for an industrial edge gateway, characterized in that: include: Obtain the industrial data of each industrial device and perform preprocessing, and use the LZ78 algorithm to compress the preprocessed industrial data to obtain a compression result; Obtain the device parameters of the edge gateway, count the number of devices and data volume of each category actually connected to the edge gateway, and the average collection speed of each category, so as to calculate the data collection pressure of the edge gateway. According to the data collection pressure of the edge gateway and the data collected by the edge gateway connected to each category of devices, calculate the data collection burden index of each category of devices; According to the data collection burden index of each device and the compression result of each device, the data collection frequency is adjusted, and the data of the devices connected to the edge gateway are collected at the adjusted collection frequency; Among them, the acquisition frequency Satisfies the following relationship: ; In the formula, Indicates that the edge gateway is connected to Data collection burden index for this type of equipment, Indicates the maximum data collection frequency supported by the current edge gateway. Indicates that the edge gateway is connected to The first in the category of equipment The number of entries in the dictionary formed when a device performs data compression, Indicates the maximum number of entries in the dictionary formed when the edge gateway connects to all devices for data compression. Indicated by natural constant The exponential function of base .

2. The intelligent data collection method of an industrial edge gateway according to claim 1 is characterized in that: The data collection pressure of the edge gateway includes: The ratio of the total number of currently connected devices to the maximum number of connected devices on the edge gateway is taken as the saturation level of the access devices; The ratio of the data volume produced and output by the current device to the maximum transmission bandwidth of the edge gateway is taken as the saturation level of data transmission; The product of the saturation level of the access device and the saturation level of the data transmission is taken as the data collection pressure.

3. The intelligent data collection method of an industrial edge gateway according to claim 1 is characterized in that: The data collection pressure of the edge gateway also includes: The average energy consumption level is the average value of the sum of the ratios of the average energy consumption of all devices to the maximum energy consumption limit of the edge gateway; The average value of the sum of the ratios between the highest priority and all the data in all the devices is taken as the average priority level; The product of the average energy consumption level and the average priority level is used as the data collection pressure.

4. The intelligent data collection method of an industrial edge gateway according to claim 1 is characterized in that: The data collection burden index includes: Obtain data from a production cycle of each type of equipment, and use the LSTM algorithm to make predictions to obtain data from the entire production cycle; Based on the data of the complete production cycle, the amount of data generated by each device per unit time is taken as the data growth rate, and linear normalization is performed. The data acquisition pressure is taken as the exponential decay factor. The data acquisition burden index is obtained by combining the normalized data growth rate and the exponential decay factor.

5. The intelligent data collection method of an industrial edge gateway according to claim 1 is characterized in that: The data collection burden index also includes: Obtain data from a production cycle of each type of equipment, and use the LSTM algorithm to make predictions to obtain data from the entire production cycle; Based on the data of the complete production cycle, the amount of highest priority data generated per unit time is taken as the growth rate of the highest priority data, and linear processing is performed. The product of the normalized growth rate of the highest priority data and the data collection pressure of the edge gateway is taken as the data collection burden index.

6. The intelligent data collection method of an industrial edge gateway according to claim 1 is characterized in that: The pre-processed industrial data is compressed using the LZ78 algorithm to obtain a compression result, including: According to the importance of the equipment, the real-time requirements of the data and the historical data mode, an initial collection frequency is set for each type of equipment, and data is collected from the connected equipment according to the initially set frequency to obtain industrial data; the industrial data is preprocessed using the UTF-8 encoding method, wherein the preprocessing includes: data cleaning, formatting and encoding conversion; During the compression process, the dictionary constructed by each industrial device when compressing data is obtained in real time, and the LZ78 algorithm is used to store repeated patterns in the data according to the constructed dictionary, thereby achieving data compression and obtaining the compression result.

7. The intelligent data collection method of an industrial edge gateway according to claim 1, characterized in that: Adjust the frequency of data collection, including: In response to the difference between the collection frequency and the initial collection frequency being less than the preset threshold of the initial collection frequency, the collection frequency will not be changed; conversely, when the difference between the collection frequency and the initial collection frequency is greater than or equal to the preset threshold of the initial collection frequency, the initial collection frequency of the edge gateway to the access device is adjusted to the collection frequency.

8. An intelligent data acquisition system for an industrial edge gateway, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent data collection method for the industrial edge gateway according to any one of claims 1 to 7 is implemented.

Images