An industrial network information system

By using the exception recognition detection model of convolutional neural network in industrial equipment monitors, the exception types of industrial equipment are distinguished, and the problem of rare exception error handling is solved, and the accurate exception handling of industrial network communication is realized and the key data storage is saved. Troubleshooting and system optimization.

CN118659960BActive Publication Date: 2024-11-08GUANGDONG HUANLIAN ELECTRONIC TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411151715.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-08
Estimated Expiration
2044-08-21

AI Technical Summary

Technical Problem

When industrial equipment receives rare abnormal errors, it lacks an effective processing mechanism, which leads to the inability to handle exceptions, affecting the accuracy of industrial network communication and the normal operation of equipment.

Method used

An industrial network information system was designed to collect and parse communication data through an industrial equipment monitor as a repeater, and use the exception recognition detection model of a convolutional neural network to distinguish between 'communication request denied' and 'exception data being Reject'Two types of work, adjust processing strategies, convert error types, or save exception data.

Benefits of technology

It realizes accurate handling of industrial network communication exceptions, avoids repeated errors in equipment, ensures the storage of critical data, and provides support for fault diagnosis and system optimization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118659960B_ABST
    Figure CN118659960B_ABST
Patent Text Reader

Abstract

The present application relates to the field of communication control technology, and in particular to an industrial network information system, which includes: industrial equipment, the industrial equipment communicates through a first local area network; an industrial equipment monitor, the industrial equipment monitor is connected to each industrial equipment to obtain the working parameters of each industrial equipment; the industrial equipment monitor acts as a repeater for industrial equipment to communicate in the first local area network, receives and forwards the communication packets sent and received by the industrial equipment to obtain the communication data of the industrial equipment; obtains the working parameters and communication data of the industrial equipment in the first sliding time window and inputs them into an abnormal identification detection model to obtain the working type of the industrial equipment; according to the working type of the industrial equipment, the communication packet of the current industrial equipment is sent to terminate the erroneous communication response of the industrial equipment or maintain the abnormal communication response of the industrial equipment. The present application can more accurately handle the anomalies that occur in industrial network communications.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communication control technology, and in particular to an industrial network information system. Background Art

[0002] Industrial environments generally require the use of a variety of industrial equipment. Since each industrial equipment is manufactured by a different manufacturer and country, different industrial equipment usually uses different communication protocols or customized communication protocols to complete corresponding data exchange.

[0003] Due to the use of different or self-modified communication protocols, when industrial equipment receives some rare abnormal error reports, if the communication protocol of a certain industrial equipment itself is not configured to handle such abnormal error reports, it will directly throw such errors and cannot handle such errors.

[0004] Therefore, there are still some problems in the existing technology, which result in the industrial network information system being unable to more accurately handle abnormalities occurring in industrial network communications. Summary of the Invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides an industrial network information system that can more accurately handle anomalies occurring in industrial network communications.

[0006] The present application provides an industrial network information system, comprising:

[0007] Industrial equipment, the industrial equipment communicating via a first local area network;

[0008] An industrial equipment monitor is connected to each industrial equipment to obtain operating parameters of each industrial equipment;

[0009] The industrial device monitor acts as a repeater for the industrial device to communicate in the first local area network, receives and forwards the communication packets sent and received by the industrial device to obtain the communication data of the industrial device;

[0010] Obtaining operating parameters and communication data of the industrial equipment in a first sliding time window of a preset length and inputting the data into a preset anomaly recognition and detection model to obtain the current operating type of the industrial equipment;

[0011] The communication packet sent to the current industrial device is changed according to the working type of the current industrial device to terminate the erroneous communication response of the industrial device or maintain the abnormal communication response of the industrial device.

[0012] Optionally, an industrial equipment monitor is connected to each industrial equipment to obtain operating parameters of each industrial equipment, including the following steps:

[0013] Industrial equipment monitors use system resource monitoring tools to obtain processor usage, memory usage, and disk read and write data of industrial equipment;

[0014] The industrial device monitor acts as a repeater for the industrial device to communicate in the first local area network, receives and forwards the communication packets sent and received by the industrial device to obtain the communication data of the industrial device, including the following steps:

[0015] Parsing communication packets sent and received by the industrial device to obtain the number of communication requests sent by the industrial device and the number of first error types received by the industrial device as communication data of the industrial device;

[0016] Obtaining the operating parameters and communication data of the industrial equipment in a first sliding time window of a preset length and inputting them into a preset anomaly recognition and detection model to obtain the current operating type of the industrial equipment includes the following steps:

[0017] The types of work include:

[0018] The communication request is rejected and the first error type returned cannot be recognized;

[0019] Exception data is rejected without being able to identify the first error type returned.

[0020] Optionally, the anomaly recognition and detection model is trained by the following steps:

[0021] Collecting operating parameters and communication data of industrial equipment in a first sliding time window of multiple different operating types, and marking the corresponding operating types;

[0022] A convolutional neural network is used as the network framework of the anomaly recognition and detection model. The working parameters and communication data of industrial equipment in the first sliding time window of multiple different working types are used as the input of the convolutional neural network, and the corresponding working type is used as the label to train the anomaly recognition and detection model.

[0023] Optionally, selecting to change the communication packet sent to the current industrial device according to the working type of the current industrial device to terminate the erroneous communication response of the industrial device or maintain the abnormal communication response of the industrial device includes the following steps:

[0024] When the working type of the industrial device is that the communication request is rejected and the first error type returned cannot be identified, the first error type returned to the industrial device is modified to a second error type that can be identified so that the industrial device stops sending the communication request;

[0025] When the operation type of the industrial device is that abnormal data is rejected and the returned first error type cannot be identified, the device monitor only copies and saves the communication packet sent by the industrial device to maintain the abnormal communication response of the industrial device.

[0026] Optionally, the first error type is “EOPNOTSUPP”.

[0027] Optionally, the second error type is “NETWORKERROR”.

[0028] The technical solution provided by this application has the following advantages over the existing technology:

[0029] In this application, the distinction between two different work types, "communication request rejected" and "abnormal data rejected", is based on the difference between the monitored working parameters and communication data within the first sliding time window.

[0030] When communication requests are rejected, changes in operating parameters can occur because industrial equipment attempts to communicate with other devices or services multiple times, but each attempt is rejected, leading to frequent retries and a potentially high processor utilization rate. Changes in communication data can also be seen, such as a high frequency of communication requests and a high frequency of first error codes received.

[0031] When abnormal data is rejected, changes in operating parameters can cause disk read / write rates and memory usage to increase abnormally as the device attempts to process or temporarily store packets that cannot be sent. Furthermore, changes in communication data only result in the high frequency of the first error code.

[0032] By analyzing and comparing these indicators within the first sliding time window, the anomaly identification and detection model can clearly distinguish whether the device is rejected because of "communication request rejection" or "abnormal data rejection".

[0033] Therefore, the industrial network information system provided by this application can intelligently adjust its processing strategy based on the current device's operating type, such as converting unrecognizable error types into error messages that the device can understand, or retaining abnormal data for subsequent analysis. This strategy not only avoids repeated equipment errors caused solely by industrial equipment's inability to recognize them, but also ensures that key data can be saved when an industrial device does experience an abnormality, providing support for fault diagnosis and system optimization.

[0034] In summary, the industrial network information system of the present application can more accurately handle anomalies occurring in industrial network communications. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of the workflow of the industrial network information system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The technical solution in this application will be described below with reference to the accompanying drawings.

[0037] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application may also be implemented in other ways than those described herein. It is apparent that the embodiments described in the specification are only some of the embodiments of the present application, not all of them. It should be noted that the embodiments of the present application and the features therein may be combined with each other unless there is a conflict.

[0038] Industrial environments generally require the use of a variety of industrial equipment. Since each industrial equipment is manufactured by a different manufacturer and country, different industrial equipment usually uses different communication protocols or customized communication protocols to complete corresponding data exchange.

[0039] Due to the use of different or self-modified communication protocols, when industrial equipment receives some rare abnormal error reports, if the communication protocol of a certain industrial equipment itself is not configured to handle such abnormal error reports, it will directly throw such errors and cannot handle such errors.

[0040] If an exception error response is received and thrown directly after it is not configured, it is equivalent to the industrial device sending a communication data packet but not receiving a response. The industrial device will then create a new thread to resend the communication request or communication data packet after a period of time. As a result, all computing resources of the current industrial device are almost completely occupied by creating communication requests, causing the current industrial device to not operate normally.

[0041] However, if rare exception error responses are simply replaced with common errors—for example, replacing rare errors with common network errors—then the industrial device will stop sending data packets. In some cases, if the data sent by an industrial device is simply abnormal, another industrial device may reject the data and return an exception error because it cannot parse it. However, this abnormal data can still be useful. Abnormal data may be caused by a brief error in the industrial device, so it is necessary to wait for the industrial device to resume normal operation. In the worst case, the device should continue to receive and store this abnormal data for subsequent recovery.

[0042] An embodiment of the present application provides an industrial network information system, the industrial network information system comprising:

[0043] Industrial devices communicate via a first local area network.

[0044] S101: an industrial equipment monitor, the industrial equipment monitor is connected to each industrial equipment to obtain the working parameters of each industrial equipment;

[0045] Specifically, the industrial equipment monitor obtains the processor occupancy rate, memory occupancy rate, and disk read / write data of the industrial equipment through the system resource monitoring tool Nagios, thereby obtaining the working parameters of each industrial equipment.

[0046] S102: The industrial device monitor serves as a repeater for industrial devices to communicate in the first local area network, receiving and forwarding communication packets sent and received by the industrial device to obtain communication data of the industrial device.

[0047] Specifically, the industrial device monitor is an independent microcomputer operating system externally mounted on the industrial device, and is set between each industrial device and the first local area network to receive and forward communication packets sent and received by the industrial device.

[0048] Specifically, the communication data of the industrial equipment is obtained by the following steps: parsing the communication packets sent and received by the industrial equipment to obtain the number of communication requests sent by the industrial equipment and the number of first error types received by the industrial equipment as the communication data of the industrial equipment.

[0049] Specifically, in the embodiment of the present application, the Scapy library in Python is used to implement parsing of data packets, and pandas is used to calculate the number of request communications sent by each device and the number of first error types received.

[0050] S103: Obtaining operating parameters and communication data of the industrial equipment in a first sliding time window of a preset length and inputting the data into a preset anomaly recognition and detection model to obtain the current operating type of the industrial equipment;

[0051] Specifically, the first sliding time window of the preset length is 5 minutes, that is, within 5 minutes from the detection time to before the detection time.

[0052] In the embodiment of the present application, the work types include:

[0053] The communication request is rejected and the first error type returned cannot be recognized;

[0054] Exception data is rejected without being able to identify the first error type returned.

[0055] In this embodiment of the present application, the first error type is an "EOPNOTSUPP" error, which indicates that the operation is not supported. This type of error is a rare error type. In this embodiment of the present application, this error code is generated when an industrial device's request to communicate with another host is rejected by the network management software. This error type can also occur when an industrial device establishes a network connection with another industrial device and sends an abnormal data packet. The other industrial device, unable to parse the abnormal data packet, returns this error code based on its own communication protocol configuration.

[0056] Specifically, the anomaly recognition and detection model is trained through the following steps:

[0057] The operating parameters and communication data of the industrial equipment in the first sliding time window of multiple different operating types are collected, and the corresponding operating types are marked.

[0058] Specifically, the working parameter sequence of the first sliding time window is collected as the first feature matrix, the communication data of the first sliding time window is collected as the second feature matrix, and the first feature matrix and the second feature matrix are combined to obtain the feature matrix that is finally input into the anomaly recognition and detection model.

[0059] A convolutional neural network is used as the network framework of the anomaly recognition and detection model. The working parameters and communication data of industrial equipment in the first sliding time window of multiple different working types are used as the input of the convolutional neural network, and the corresponding working type is used as the label to train the anomaly recognition and detection model.

[0060] S104: Selecting to change the communication packet sent to the current industrial device according to the working type of the current industrial device to terminate the erroneous communication response of the industrial device or maintain the abnormal communication response of the industrial device.

[0061] Specifically, when the working type of the industrial device is that the communication request is rejected and the first error type returned cannot be identified, the first error type returned to the industrial device is modified to a second error type that can be identified so that the industrial device stops sending the communication request;

[0062] Specifically, the second error type is a "NETWORKERROR" error code, which means a network connection error. In other embodiments, it can be replaced with other common and general error codes.

[0063] When the operation type of the industrial device is that abnormal data is rejected and the returned first error type cannot be identified, the device monitor only copies and saves the communication packet sent by the industrial device to maintain the abnormal communication response of the industrial device.

[0064] In summary, the working principle and beneficial effects of the embodiments of the present application lie in the fact that, in the embodiments of the present application, the distinction between the two different work types, "communication request rejected" and "abnormal data rejected," is based on the differences between the monitored operating parameters and communication data within the first sliding time window. These two work types exhibit significant differences in the performance of the operating parameters and communication data, and these differences enable the anomaly detection model to effectively distinguish and handle these situations.

[0065] When communication requests are rejected, changes in operating parameters indicate that the device attempts to communicate with other devices or services multiple times, but each attempt is rejected, resulting in frequent retries and a potentially high processor usage trend. Changes in communication data also indicate a high frequency of communication requests and a high frequency of first error codes received.

[0066] When abnormal data is rejected, changes in operating parameters can cause disk read / write rates and memory usage to increase abnormally as the device attempts to process or temporarily store packets that cannot be sent. Furthermore, changes in communication data only result in the high frequency of the first error code.

[0067] By analyzing and comparing these indicators within the first sliding time window, the anomaly identification and detection model can clearly distinguish whether the device is rejected because of "communication request rejection" or "abnormal data rejection".

[0068] Therefore, the industrial network information system provided by the embodiments of this application can intelligently adjust the corresponding processing strategy based on the current operating type of the equipment, such as converting unrecognizable error types into error messages that the equipment can understand, or retaining abnormal data for subsequent analysis. This strategy not only avoids repeated equipment erroneous operations caused solely by the industrial equipment's inability to recognize, but also ensures that key data can be saved when an industrial equipment anomaly does occur, providing support for fault diagnosis and system optimization.

[0069] In summary, the industrial network information system of the present application can more accurately handle anomalies occurring in industrial network communications.

[0070] It should be noted that, in this document, relational terms such as "first" and "second" are used solely to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Furthermore, the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article, or device comprising the element. Furthermore, in the description of the embodiments of this application, unless otherwise specified, " / " represents or. For example, A / B can represent either A or B. "And / or" herein is merely a description of an associative relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, in the description of the embodiments of the present application, “plurality” refers to two or more than two.

[0071] The foregoing description is intended only to provide specific embodiments of the present application, which will enable those skilled in the art to understand and implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments described herein, but is intended to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. An industrial network information system, characterized in that: include: Industrial equipment, the industrial equipment communicating via a first local area network; An industrial equipment monitor, which is connected to each industrial equipment to obtain operating parameters of each industrial equipment; The industrial device monitor acts as a repeater for the industrial device to communicate in the first local area network, receives and forwards the communication packets sent and received by the industrial device to obtain the communication data of the industrial device; Obtaining the working parameters and communication data of the industrial equipment in a first sliding time window of a preset length and inputting them into a preset abnormality recognition and detection model to obtain the working type of the current industrial equipment; Selecting to change the communication packet sent to the current industrial device according to the working type of the current industrial device to terminate the erroneous communication response of the industrial device or to maintain the abnormal communication response of the industrial device; The industrial equipment monitor is connected to each industrial equipment to obtain the working parameters of each industrial equipment, including the following steps: Industrial equipment monitor obtains processor occupancy, memory occupancy, and disk read / write data of industrial equipment through system resource monitoring tools; The industrial device monitor acts as a repeater for the industrial device to communicate in the first local area network, receives and forwards the communication packets sent and received by the industrial device to obtain the communication data of the industrial device, including the following steps: Parsing the communication packets sent and received by the industrial device to obtain the number of communication requests sent by the industrial device and the number of first error types received by the industrial device as communication data of the industrial device; Obtaining the working parameters and communication data of the industrial equipment in the first sliding time window of a preset length and inputting them into a preset abnormality recognition detection model to obtain the working type of the current industrial equipment includes the following steps: The types of work include: The communication request is rejected and the first error type returned cannot be recognized; Abnormal data is rejected without being able to identify the first error type returned; According to the working type of the current industrial device, the communication packet sent to the current industrial device is changed to terminate the erroneous communication response of the industrial device or maintain the abnormal communication response of the industrial device, including the following steps: When the working type of the industrial device is that the communication request is rejected and the first error type returned cannot be identified, the first error type returned to the industrial device is modified to a second error type that can be identified so that the industrial device stops sending the communication request; When the working type of the industrial device is that abnormal data is rejected and the returned first error type cannot be identified, the device monitor only copies and saves the communication packet sent by the industrial device to maintain the abnormal communication response of the industrial device.

2. The industrial network information system according to claim 1, characterized in that: The anomaly recognition and detection model is trained by the following steps: Collecting working parameters and communication data of industrial equipment in a first sliding time window of multiple different working types, and marking the corresponding working types; A convolutional neural network is used as the network framework of the anomaly recognition and detection model. The working parameters and communication data of industrial equipment in the first sliding time window of multiple different working types are used as the input of the convolutional neural network, and the corresponding working type is used as a label to train the anomaly recognition and detection model.

3. The industrial network information system according to claim 1, characterized in that: The first error type is "EOPNOTSUPP".

4. The industrial network information system according to claim 1, characterized in that: The second error type is "NETWORKERROR".