Optimized application method and equipment for OPC UA protocol in industrial automation field

Abstract

The invention belongs to the technical field of industrial automation, and discloses an optimization application method and device for an OPC UA protocol in the industrial automation field, and the method comprises the steps: obtaining the multi-dimensional context information of an industrial site, analyzing the future communication demands and behavior trends of a target OPC UA node through a preset prediction model, obtaining predictive behavior features, and carrying out the optimization application of the OPC UA protocol. And according to the predictive behavior characteristics and the current context information, an OPC UA communication optimization strategy is dynamically generated and adjusted, the OPC UA communication optimization strategy comprises a data sampling period, a release interval, a message queue size, a data coding mode and a security strategy level, and the optimization strategy is applied to a communication session between an OPC UA server and a client. According to the method, OPC UA communication parameters are dynamically optimized through intelligent perception and predictive analysis, the data transmission efficiency can be remarkably improved, the system resource consumption is reduced, the real-time performance and reliability of communication are enhanced, and the method is particularly suitable for a complex and dynamic industrial automation environment.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial automation, and relates to an optimized application method and device for the OPC UA protocol in the field of industrial automation. Background Art

[0002] OPC UA is a secure, reliable, and platform-independent information exchange standard based on a service-oriented architecture for the field of industrial automation. It is widely used in data integration between devices, from devices to control systems, and in enterprise management systems, achieving interoperability between devices and systems from different suppliers. OPC UA defines a rich information model, multiple communication services, and built-in security mechanisms, such as multiple communication services in cases like data access, historical data access, alarms, and conditions.

[0003] In traditional OPC UA applications, communication parameters between the server and the client, such as data sampling intervals, publishing intervals, message queue sizes, data encoding methods, and security policies (where the security policy can be encryption algorithms, signature algorithms, security modes), are usually statically set based on empirical values or expected operating conditions during system deployment or configuration. Once set, these parameters are rarely or never actively adjusted during operation.

[0004] However, modern industrial automation systems are becoming increasingly complex, showing the following characteristics: 1) Large scale and heterogeneity: A large number of connected devices with various types generate a huge amount of diverse data.

[0005] 2) Dynamically changing environment: Production tasks are frequently switched, the operating states of devices change dynamically, and network loads fluctuate greatly, especially in wireless communication scenarios.

[0006] 3) High requirements for real-time performance and reliability: Many industrial control and monitoring applications have strict requirements for data real-time performance and communication reliability.

[0007] Under the above background, the statically configured OPC UA communication strategy exposes some problems: Resource waste or insufficiency: When the system load is low or data changes slowly, overly high sampling and publishing frequencies can lead to unnecessary network bandwidth occupation and CPU resource consumption; conversely, when critical data changes rapidly or the network is congested, fixed communication parameters may not be able to ensure data real-time performance and integrity.

[0008] Poor adaptability: It is unable to dynamically adjust communication priorities and resource allocations according to real-time operating condition changes, such as device fault warnings and emergency production order issuances, which may lead to delays in the transmission of critical information.

[0009] Difficulty in optimizing configuration: In complex systems, manually optimizing the communication parameters of all OPC UA nodes is a daunting task and it is difficult to achieve global optimality.

[0010] Currently, there are some studies attempting to optimize the performance of OPC UA, such as by improving data compression algorithms and optimizing information models. However, most of them still focus on static optimization of a specific aspect and lack a systematic method and device that can comprehensively perceive the dynamic changes in the industrial field and accordingly perform intelligent, predictive, and adaptive adjustment of the overall communication strategy of OPC UA.

[0011] Therefore, there is an urgent need for a new method and device that can overcome the defects of the existing technology and achieve dynamic optimization of the OPC UA communication strategy to improve the efficiency, real-time performance, and intelligence level of information interaction in industrial automation systems. Summary of the Invention

[0012] The present invention aims to solve the technical problems in the existing OPC UA applications where the communication strategy configuration is static, difficult to adapt to the dynamic industrial environment, resulting in low resource utilization and difficulty in ensuring the real-time performance of key data. Specifically, the present invention is committed to providing a method and device that can dynamically optimize the OPC UA communication parameters based on real-time multi-dimensional context information and predictive behavior analysis.

[0013] To achieve the above object, the present invention provides an optimized application method for the OPC UA protocol in the field of industrial automation, and the method includes the following steps: Step S1: Obtain real-time multi-dimensional context information of the industrial field. This information is the basis for subsequent analysis and decision-making and includes at least: Device operating status data: For example, the CPU load of the device, memory usage rate, key sensor readings, device fault codes or warning signals, etc.

[0014] Network environment parameters: For example, the network latency, available bandwidth, data packet loss rate, signal strength of the OPC UA communication link, where the signal strength corresponds to the wireless condition.

[0015] Current business priority information: For example, the priority levels of different data streams or OPC UA services defined according to the current production tasks and operation modes, where the operation modes are such as normal production, emergency shutdown, and equipment maintenance.

[0016] OPC UA historical interaction data: For example, the data publishing frequency, data volume size, subscription change situation, connection establishment / disconnection events, etc. of specific OPC UA nodes in the past period of time.

[0017] Step S2: Based on the obtained multi-dimensional context information, use a preset prediction model to predict and analyze the future communication requirements and behavior trends of the target OPC UA node, and obtain predictive behavior characteristics.

[0018] The preset prediction model can be obtained through machine learning or deep learning methods. Specifically, machine learning can be a time series model such as ARIMA or an LSTM long short-term memory network, and is trained using historical OPC UA interaction data and its corresponding multi-dimensional context information. This model can learn the patterns of data changes, the periodicity of network states, and the relevance of business requirements.

[0019] Predictive behavior characteristics may include: predicted values of the data generation rate of the target OPC UA node within one or more future time windows, predicted values of the data subscription request frequency, predicted values of network bandwidth requirements, prediction of potential connection instability, etc.

[0020] Step S3: Dynamically generate or adjust the OPC UA communication optimization strategy according to the predictive behavior characteristics and the current real-time multi-dimensional context information. This strategy is targeted and aims to balance performance, resources, and reliability. The communication optimization strategy at least includes adjustments to one or more of the following: Data sampling period: The frequency at which the server collects data.

[0021] Publication interval: The frequency at which the server sends notifications to the client.

[0022] Message queue size: The queue length used by the server or client to cache notification messages.

[0023] Data encoding method: For example, when bandwidth is limited, UA-Binary is preferred; when good readability or integration with other systems is required, XML or JSON can be considered. However, for system integration, bandwidth must be available, and XML or JSON must be supported.

[0024] Security policy level: For example, on edge devices in an internal trusted network with limited resources, the security level for non-sensitive data can be appropriately reduced to reduce computational overhead. Reducing the security level can be to sign only without encryption or use a lighter encryption algorithm; for highly sensitive data or in an untrusted network, a high security level must be used.

[0025] Step S4: Apply the generated OPC UA communication optimization strategy to the communication session between the target OPC UA server and the client. This may involve updating the parameters of the server or client through OPC UA service calls or specific configuration interfaces.

[0026] Further, to form a closed-loop optimization, the method may further include step S5: monitoring the actual communication effect after the application of the OPC UA communication optimization strategy, such as actual data throughput, latency, and resource consumption changes, and feeding back the monitoring results to the prediction model in step S2 for online learning or parameter fine-tuning of the model, and / or feeding back to the communication optimization strategy generation and adjustment process in step S3 to achieve iterative optimization of the model and adaptive adjustment of the strategy.

[0027] The present invention also provides an optimized application device for the OPC UA protocol in the field of industrial automation. This device is used to execute the above method and includes: Context information acquisition module: used to execute step S1.

[0028] Predictive analysis module: connected to the context information acquisition module, with a preset prediction model built-in, used to execute step S2.

[0029] Strategy generation and adjustment module: connected to the predictive analysis module and the context information acquisition module, used to execute step S3.

[0030] Strategy application module: connected to the strategy generation and adjustment module, used to execute step S4.

[0031] Optionally, the device may further include an effect monitoring and feedback module, used to execute step S5, and connected to the predictive analysis module and / or the strategy generation and adjustment module to form a closed-loop feedback.

[0032] Compared with the prior art, the present invention has the following beneficial effects: 1. By dynamically adjusting the sampling and publishing frequencies, data encoding, etc., the present invention avoids excessive communication during periods of slow data change or non-critical periods, reduces unnecessary network bandwidth and computing resource consumption, and can guarantee sufficient communication resources during peak data demand periods, effectively improving communication efficiency and resource utilization rate.

[0033] 2. The present invention can prioritize the timely and reliable transmission of critical data according to business priorities and predicted network conditions. For example, by shortening the publishing interval of critical data, or reserving bandwidth for critical data or adopting a more robust transmission strategy when a network congestion warning occurs, enhancing its real-time performance and reliability.

[0034] 3. The present invention makes OPC UA communication no longer statically configured, but can actively sense environmental changes and predict future trends, intelligently adjust its own behavior, better adapt to the complex and changeable industrial field environment, and improve the adaptability and intelligence level of the system.

[0035] 4. The present invention enables the automated optimization process to reduce the need for manual intervention and lower the difficulty of system configuration and maintenance, especially having significant advantages for large-scale OPC UA deployments.

[0036] 5. Through the prediction of communication behaviors and network states, the present invention can take preventive measures before potential problems occur, improving the overall availability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0038] Figure 1 It is a flowchart showing the optimization application method of the OPC UA protocol in the field of industrial automation according to the present invention; Figure 2 It is a structural block diagram of the optimization application device of the OPC UA protocol in the field of industrial automation according to the present invention; Figure 3 It is a schematic diagram showing the training and application of the prediction model according to the present invention; Figure 4 It is a schematic diagram of the decision logic for dynamically adjusting the OPC UA communication parameters in a specific embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0040] Embodiment 1: OPC UA Communication Optimization Method and System Based on LSTM Network Please refer to Figure 1 and Figure 2 As shown, this embodiment describes an OPC UA communication optimization method and system based on prediction analysis using a long short-term memory network (LSTM). The specific method steps are as follows: Step S1: Real-time acquisition of multi-dimensional context information, corresponding to Figure 1 step S1 in Figure 2 and is executed by the context information acquisition module 701 in Device operation status data: Read from PLC, DCS, SCADA systems or directly from intelligent devices via OPC UA or other protocols. For example, the current and temperature of the robotic arm joint motors on a production line, where temperature is a high-frequency sampling requirement, the vibration frequency of a large compressor, which is high-frequency when the device is abnormal, and the CPU / memory occupancy rate of each device.

[0041] Network environment parameters: Monitor via network management tools or probes built into OPC UA communication endpoints, which can also be OPC UA servers / clients, to obtain parameters such as the round-trip time (RTT) of OPC UA sessions, packet loss rate, signal strength of wireless APs, and channel occupancy rate.

[0042] Current business priority information: Obtain the current work order information, product type, and production rhythm requirements from the MES system or production scheduling system, and map them to the priorities of different OPC UA data sources. For example, P1 - highest, P3 - normal, and the key parameter points (KPCs) related to quality traceability are marked as P1 during the production process.

[0043] OPC UA historical interaction data: Record the historical sampling interval, publication interval, number of subscriptions, amount of published data, message queue overflow events, etc. of each OPC UA session, as well as the corresponding context information at that time, and store them in a time-series database.

[0044] Step S2: Predictive behavior analysis based on the LSTM model, corresponding to Figure 1 Step S2 in Figure 2 is executed by the predictive analysis module 702 in

[0045] Please refer to Figure 3 as shown for model training: In the offline phase, use the OPC UA historical interaction data accumulated in Step S1 as the target sequence. Here, the historical interaction data can be the amount of data published or the number of subscription requests, and use the device status, network parameters, and business priorities during the same period as the feature sequence.

[0046] For example, train a model \(M_{\text{load}}=\text{LSTM}(\text{Historical_Load},\text{Context_Features})\) to predict the data release volume (denoted as \(\text{Predicted_Load}\)) in the next \(T\) time steps (such as the next 5 minutes or 10 minutes), covering multiple predicted values from time step \(t + 1\) to \(t+T\) (e.g., multiple predicted values from \(t + 1\) to \(t+T\): \(\text{Predicted_Load}(t + 1)\), \(\text{Predicted_Load}(t + 2)\) up to \(\text{Predicted_Load}(t + T)\)).

[0047] Another model \(M_{\text{net}}=\text{LSTM}(\text{Historical_RTT},\text{Historical_Loss},\text{Context_Features})\) predicts future network latency and packet loss rate.

[0048] Optimizers such as Adam can be used in the training process, and the goal is to minimize the mean squared error (MSE) or other loss functions between the predicted values and the actual values.

[0049] Example of a mathematical formula, a simplified representation of the LSTM cell, which is actually more complex: Input gate: Forget gate: Output gate: Candidate cell state: Cell state update: Hidden state, output: In the above update calculation formula of the LSTM cell, the specific meanings of each symbol are as follows: : Represents the feature vector input to the LSTM cell at the current time step \(t\), which may contain multi-dimensional context information such as the device state, network parameters, and service priority at the current moment.

[0050] : Represents the hidden state output of the LSTM cell at the previous time step \(t - 1\).

[0051] : Represents the cell state of the LSTM cell at the previous time step \(t - 1\).

[0052] , , , : weight matrices representing the input gate, forget gate, output gate, and candidate cell state, respectively.

[0053] , , , : bias vectors representing the input gate, forget gate, output gate, and candidate cell state, respectively.

[0054] : represents the Sigmoid activation function, whose output range is (0, 1), and is used to control the opening and closing degree of the threshold.

[0055] : represents the hyperbolic tangent activation function, whose output range is (-1, 1), and is used to generate the candidate cell state and the final hidden state.

[0056] : the output of the input gate at time step t, which determines how much information in the current input can be written into the cell state.

[0057] : the output of the forget gate at time step t, which determines how much information in the cell state at the previous moment needs to be forgotten.

[0058] : the output of the output gate at time step t, which determines how much information in the current cell state can be used as the current hidden state output.

[0059] : the candidate cell state calculated at time step t.

[0060] : the cell state updated at time step t, which combines the screening of the old state by the forget gate and the acceptance of new information by the input gate.

[0061] : the final hidden state output of the LSTM cell at time step t, which is based on the current cell state and is regulated by the output gate.

[0062] Through these gating mechanisms, the LSTM model can effectively learn and memorize long-term dependencies in time series data, thereby accurately predicting future communication demands and behavioral trends. For example, the model M_load = LSTM(Historical_Load, Context_Features) is used to predict future data publication volume based on historical load data (Historical_Load) and context features (Context_Features); the model M_net = LSTM(Historical_RTT, Historical_Loss, Context_Features) is used to predict future network latency and packet loss conditions based on historical network round-trip time (Historical_RTT), historical packet loss rate (Historical_Loss), and context features.

[0063] Online prediction: During runtime, the latest multi-dimensional context information obtained in step S1 is input into the trained LSTM model to obtain the predicted behavioral characteristics of the target OPC UA node, where the target OPC UA node can be a data source on a specific OPC UA server or the subscription behavior of a certain client.

[0064] For example, it is predicted that within the next 5 minutes, the data publication volume of node A will increase by 30%, and the network connection quality of node B may decrease by 10%.

[0065] Step S3: Dynamically generate and adjust the OPC UA communication optimization strategy, corresponding to Figure 1 step S3 in Figure 2 and is executed by the policy generation and adjustment module 703 in

[0066] The policy generation and adjustment module 703 generates a communication optimization strategy based on the predicted behavioral characteristics obtained in step S2 and the current context information in step S1 through a set of predefined rule engines or a small decision optimization model, where the small decision optimization model can specifically be a reinforcement learning agent or a decision maker based on a utility function.

[0067] Please refer to Figure 4 as shown, an example of decision logic: In step S3, in the process of dynamically generating and adjusting the OPC UA communication optimization strategy, its decision logic can be based on a series of input parameters. These input parameters include, for example: the predicted data rate of node A (denoted as Predicted_DataRate_NodeA), the current service priority of node A (denoted as Current_Priority_NodeA), the predicted network quality (denoted as Predicted_NetworkQuality), and the current device load of server X (denoted as Current_DeviceLoad_ServerX).

[0068] Based on these input parameters, the system can make decisions according to preset rules. The following are some examples of decision rules: Rule 1: When the system predicts that the data generation rate of node A will exceed the preset high threshold (Predicted_DataRate_NodeA > Threshold_High), and the current service priority of node A is the highest level (e.g., P1), and the predicted network quality is good (Predicted_NetworkQuality == Good), and the current load of server X is lower than its maximum capacity (Current_DeviceLoad_ServerX < Load_Max), the system will adjust and apply a set of high-performance communication strategies for node A. This strategy may specifically include: setting the data sampling interval (SamplingInterval) to the "fast" mode, setting the data publishing interval (PublishingInterval) to the "fast" mode as well, increasing the message queue size (QueueSize is set to Large), adopting binary data encoding (Encoding = Binary), and enabling a high-level security policy (Security = High).

[0069] Rule 2: If the system predicts that the data generation rate of node A is lower than the preset low threshold (Predicted_DataRate_NodeA < Threshold_Low), and the current service priority of node A is at the normal level (e.g., P3), then the system will adjust and apply a set of energy-saving or low-overhead communication strategies for node A. This strategy may specifically include: setting the data sampling interval to the "slow" mode, setting the data publishing interval to the "slow" mode as well, and reducing the size of the message queue (QueueSize = Small).

[0070] Rule 3: When the network quality is predicted to be poor (Predicted_NetworkQuality==Poor), the system will take differentiated measures for different types of nodes. For all critical nodes (Critical_Nodes), the system will increase the redundancy of communication or adopt a more robust data encoding method (Increase_Redundancy_Or_RobustEncoding) to ensure the reliability of data transmission. For all non-critical nodes (NonCritical_Nodes), the system can choose to increase its data publishing interval (Increase_PublishingInterval) or reduce its security level (Decrease_SecurityLevel_If_Allowed) if allowed to reduce network congestion.

[0071] The parameters mentioned in the above strategies, such as "Fast" or "Slow", will be quantified into specific values ​​in actual applications. For example, the "Fast" sampling interval can be specifically set to 100 milliseconds (ms), while the "Slow" sampling interval can be set to 1000 milliseconds (ms). Similarly, a "High" security strategy can correspond to a combination of security protocols such as AES256 encryption, SHA256 signature, and RsaPss key negotiation, while a "Low" security strategy may only require data signing (Sign) or use lighter encryption measures.

[0072] Regarding data encoding, the system usually uses UA-Binary format by default to improve efficiency. However, in certain situations, such as when it is predicted that network bandwidth is very sufficient and detailed debugging analysis is required, if the OPC UA server supports and has the corresponding XML configuration, the system can temporarily switch the data encoding method to XML format.

[0073] For more complex decision-making scenarios, the system can introduce an optimization objective function U to guide the selection and adjustment of communication strategies, with the goal of maximizing the function value. The optimization objective function U can be expressed as: In this function: Represents a real-time performance indicator, which can be quantified, for example, by the inverse of the normalized average data transmission delay.

[0074] Represents a communication reliability indicator, which can be measured, for example, by the successful delivery rate of data packets within a statistical period.

[0075] Represents a resource consumption metric, which can be, for example, the normalized CPU occupancy rate of a key device (such as an OPC UA server) or the network bandwidth utilization rate of a specific communication link.

[0076] Represents a security risk assessment value, which can be, for example, mapped to a preset risk score according to the selected security policy level, or obtained by comprehensively evaluating the occurrence probability and impact degree of potential security threats.

[0077] , , , Are the weight factors corresponding to each indicator respectively. These weight factors can be dynamically evaluated and adjusted according to the current overall policy, prediction results, and current context information (such as business priority, device status, etc.). By maximizing the U value, the system aims to seek the best balance among real-time performance, reliability, resource consumption, and security risk.

[0078] Step S4: Apply the OPC UA communication optimization strategy, corresponding to Figure 1 Step S4 in Figure 2 It is executed by the policy application module 704 in

[0079] For the adjustment of OPC UA server-side parameters, such as the sampling interval, it may be done through the server's internal API or management interface.

[0080] For session-related parameters, it can be through standard OPC UA service calls. For example, the client sends a ModifySubscription request to the server, which contains new revisedPublishingInterval, revisedLifetimeCount, etc. Among them, the session-related parameters are specifically the publishing interval and queue size. ModifySubscription is a standard service name in OPC UA, revisedPublishingInterval is a parameter in the ModifySubscription service, and revisedLifetimeCount is also a parameter in the ModifySubscription service.

[0081] The adjustment of the security policy may involve renegotiating the security channel.

[0082] The adjustment of the data encoding method may require both the server and the client to support the encoding and negotiate.

[0083] Step S5: Effect Monitoring and Feedback, corresponding to Figure 2 the effect monitoring and feedback module 705 in Monitoring: Continuously collect the actual performance metrics after the application of the strategy, such as actual data throughput, end-to-end latency, changes in server CPU / memory occupancy, message queue overflow rate, etc.

[0084] Feedback: Compare the actual performance metrics with the predicted values, calculate the error, and use it for online adjustment or retraining of the LSTM model in Step S2. For example, adjust the learning rate or trigger batch retraining after accumulating a certain amount.

[0085] Feed back the current system state and the execution effect of the strategy to the strategy generation module in Step S3, enabling it to perform self-correction and optimization of the strategy. For example, adjust the threshold of the rule or the reward function of the reinforcement learning agent.

[0086] Please refer to Figure 2 as shown, the device structure: The optimization application device 70 of the present invention can be an independent hardware entity, such as an industrial gateway or an edge computing device, or can be embedded in an existing OPC UA server, client, or management platform in the form of a software module.

[0087] Context Information Acquisition Module 701: Includes various sensor interfaces, network listening interfaces, and communication interfaces with other industrial systems (MES, SCADA).

[0088] Predictive Analysis Module 702: Usually includes one or more processors, specifically CPUs / GPUs / TPUs, for running LSTM or other machine learning models, and memory for storing the models.

[0089] Strategy Generation and Adjustment Module 703: Includes an execution unit of a rule engine or a decision optimization algorithm.

[0090] Strategy Application Module 704: Includes interfaces of the OPC UA client / server stack for performing OPC UA service calls or configuring parameters.

[0091] Effect Monitoring and Feedback Module 705: Includes performance data collection and analysis units. Data interaction between these modules is carried out through an internal bus or network. The device also includes necessary memory, power module, and communication interfaces, where the memory is used to store programs, data, and models, and the communication interface can be Ethernet, Wi-Fi, 5G, etc.

[0092] Embodiment 2: Optimization in a Specific Scenario - OPC UA Optimization for Large-Scale Distributed Robot Collaboration In this scenario, a large number of robots need to perform status synchronization and task coordination through OPC UA.

[0093] Context information: the current tasks of the robots, motion states, battery levels, surrounding environments, relative positions with other robots, where the current tasks can specifically be handling or welding, the motion states can specifically be positions or speeds, and the surrounding environments can specifically be whether there are obstacles.

[0094] Prediction model: predicting potential collision risks between robots, synchronization requirements at task handover points, data bursts, such as task completion signals.

[0095] Optimization strategy: when a robot approaches a task handover point or predicts high coordination requirements, dynamically shorten its OPC UA publishing interval with the coordination server, where the coordination server can also be other robots, to increase the refresh rate of position and status data.

[0096] For non - urgent status information, such as a slow decrease in battery level, use a longer publishing interval.

[0097] When the network is congested, prioritize ensuring the transmission of collision avoidance and key task synchronization data, and temporarily reduce the publishing frequency of non - critical robot status data or use more aggressive data compression.

[0098] When a robot is idle or performing independent tasks, reduce its OPC UA communication frequency to save energy consumption and network resources.

[0099] The core of the present invention lies in its closed - loop intelligent optimization mechanism of "perception - prediction - decision - execution - feedback", enabling OPC UA communication to dynamically adapt to complex industrial environments rather than relying solely on static configurations. In this way, the utilization efficiency of system resources can be maximized while ensuring the performance of key services.

[0100] Although the specific implementation manners of the present invention are described above, those skilled in the art should understand that these specific implementation manners are merely examples. Without departing from the principles and essence of the present invention, those skilled in the art can make various omissions, substitutions, and changes to the details of the above - mentioned methods and systems. For example, combining the above - mentioned method steps, and thus performing substantially the same function according to a substantially the same method to achieve substantially the same result belongs to the scope of the present invention. Therefore, the scope of the present invention is only defined by the appended claims.

Claims

1. An optimized application method for the OPC UA protocol in the field of industrial automation, characterized in that, Including the following steps: Step S1: Obtain multi-dimensional context information of the industrial site in real time, where the multi-dimensional context information at least includes device operation status data, network environment parameters, current business priority information, and OPC UA historical interaction data; Step S2: Based on the multi-dimensional context information, use a preset prediction model to predict and analyze the future communication requirements and behavior trends of the target OPC UA node, and obtain the predictive behavior characteristics of the target OPC UA node; Step S3: Dynamically generate or adjust the OPC UA communication optimization strategy according to the predictive behavior characteristics of the target OPC UA node and the current multi-dimensional context information. The communication optimization strategy includes adjustments to at least one of the OPC UA data sampling period, publishing interval, message queue size, data encoding method, and security policy level; Step S4: Apply the OPC UA communication optimization strategy to the communication session between the target OPC UA server and the client.

2. The optimized application method of the OPC UA protocol in the field of industrial automation according to claim 1, wherein The device operation status data includes device load rate, key parameter values, and fault warning information; the network environment parameters include network latency, bandwidth utilization rate, and data packet loss rate; the business priority information includes the data importance level associated with the current industrial application scenario.

3. The optimized application method of the OPC UA protocol in the field of industrial automation according to claim 1, characterized in that, The preset prediction model is a machine learning model or a deep learning model based on time series analysis, and is trained by learning the OPC UA historical interaction data and the corresponding multi-dimensional context information.

4. The optimized application method of the OPC UA protocol in the field of industrial automation according to claim 3, characterized in that, The predictive behavior characteristics include predicted values of the data generation rate, data subscription request frequency, or network bandwidth demand of the target OPC UA node within one or more future time windows.

5. The optimized application method of the OPC UA protocol in the field of industrial automation according to claim 1, wherein, In step S3, dynamically generating or adjusting the OPC UA communication optimization strategy specifically includes: if it is predicted that the data generation rate of the target OPC UA node will increase significantly and the current business priority is high, then correspondingly shorten the data sampling period and the publishing interval, and optionally adopt a data encoding method with a higher compression rate; if it is predicted that the network bandwidth will become congested or the network latency will increase, then appropriately increase the publishing interval, or reduce the security policy level of non-critical data to reduce overhead.

6. The optimized application method of the OPC UA protocol in the field of industrial automation according to claim 1, characterized in that, It further includes step S5: Monitor the actual communication effect after applying the OPC UA communication optimization strategy, and feedback the monitoring result to the prediction model in step S2 and / or the process of generating and adjusting the communication optimization strategy in step S3 to achieve iterative optimization of the model and adaptive adjustment of the strategy.

7. An apparatus for an optimized application method of the OPC UA protocol in the field of industrial automation according to any one of claims 1-6, characterized in that, Including: A context information acquisition module for obtaining multi-dimensional context information of the industrial site in real time, where the multi-dimensional context information at least includes device operation status data, network environment parameters, current business priority information, and OPC UA historical interaction data; A predictive analysis module connected to the context information acquisition module for predicting and analyzing the future communication requirements and behavior trends of the target OPC UA node based on the multi-dimensional context information, and obtaining the predictive behavior characteristics of the target OPC UA node; A strategy generation and adjustment module, connected to the predictive analysis module and the context information acquisition module, is configured to dynamically generate or adjust an OPC UA communication optimization strategy according to the predictive behavior characteristics of the target OPC UA node and the current multi-dimensional context information. The communication optimization strategy includes adjustments to at least one of the OPC UA data sampling period, publication interval, message queue size, data encoding method, and security policy level; A strategy application module, connected to the strategy generation and adjustment module, is configured to apply the OPC UA communication optimization strategy to the communication session between the target OPC UA server and the client.

8. An optimized application device for the OPC UA protocol in the field of industrial automation according to claim 7, characterized in that, The predictive analysis module incorporates a machine learning model or a deep learning model based on time series analysis, which is trained by learning OPC UA historical interaction data and corresponding multi-dimensional context information.

9. The optimized application device of the OPC UA protocol in the field of industrial automation according to claim 7, characterized in that, The strategy generation and adjustment module is further configured to: when receiving predictive behavior characteristics indicating that the data generation rate of the target OPC UA node will increase significantly and the current business priority is high, generate instructions to shorten the data sampling period and publication interval, and optionally instruct the use of a data encoding method with a higher compression ratio; when receiving predictive behavior characteristics indicating that the network bandwidth will become congested or the network latency will increase, generate instructions to appropriately increase the publication interval, or instruct to lower the security policy level for non-critical data.

10. The optimized application device of the OPC UA protocol in the field of industrial automation according to claim 7, characterized in that, It further includes: An effect monitoring and feedback module, connected to the strategy application module, is configured to monitor the actual communication effect after the application of the OPC UA communication optimization strategy, and feedback the monitoring results to the predictive analysis module and / or the strategy generation and adjustment module to achieve iterative optimization of the preset prediction model and adaptive adjustment of the communication optimization strategy.

Images