A remote data monitoring method and system for a PLC controller

Abstract

The application discloses a kind of remote data monitoring method and system of PLC controller, it is related to PLC controller technical field, including: real-time monitoring PLC controller communication's spectral efficiency and channel state information feedback delay time;Trend analysis is carried out to spectral efficiency, the stability of control communication is evaluated;According to channel state information feedback delay time, it is estimated whether there is prediction error risk in channel;Multi-dimensional congestion early warning vector is constructed, input into pre-trained optimization decision model and analyzed, and the communication strategy of PLC controller is output;According to PLC controller communication strategy, the adaptive optimization of the performance of multiple control instructions concurrent communication is realized.The application has the advantages that: while ensuring the industrial signal-to-noise ratio gain, the communication interruption rate is significantly reduced and the energy consumption cost is optimized simultaneously, and the robustness, timeliness and energy efficiency ratio of industrial internet of things communication optimization are constructed.

Description

Technical Field

[0001] This invention relates to the field of PLC controller technology, and more specifically to a remote data monitoring method and system for PLC controllers. Background Technology

[0002] In the field of industrial automation, remote data monitoring of programmable logic controllers (PLCs) is a core component for achieving equipment interconnection and intelligent control. Traditional PLC communication systems are typically based on fixed frequency band allocation and static scheduling strategies, which can meet the basic control command transmission requirements under stable channel environments. However, with the development of Industry 4.0, the number of concurrent communication scenarios with multiple control commands has surged, and electromagnetic interference in production sites has intensified, leading to fierce competition for spectrum resources and frequent fluctuations in channel states. Existing technologies rely on periodic channel state information feedback mechanisms, whose inherent feedback delays often cause channel prediction errors. At the same time, insufficient detection capability for sudden changes in spectrum efficiency results in a persistently high communication interruption rate, severely restricting the execution efficiency of high real-time control tasks.

[0003] Current optimization solutions mainly focus on adjusting communication parameters in a single dimension. For example, power compensation is triggered by a fixed threshold, or time slot resources are pre-allocated based on historical data. These methods have significant limitations in dynamic industrial environments: firstly, they fail to construct a joint assessment system for spectrum stability and channel prediction risks, making it impossible to predict communication congestion caused by multivariate coupling; secondly, they lack adaptive decision-making mechanisms oriented towards control command characteristics, leading to frequency band allocation redundancy, time slot scheduling conflicts, and power control mismatch. Especially in scenarios with multiple concurrent control commands, existing systems struggle to achieve a dynamic balance between signal-to-noise ratio gain, interference suppression, and energy consumption costs, becoming a technical bottleneck restricting the performance improvement of industrial control systems. Summary of the Invention

[0004] To address the aforementioned technical problems, a remote data monitoring method and system for PLC controllers is provided. This technical solution solves the problem that existing systems struggle to achieve a dynamic balance between signal-to-noise ratio gain, interference suppression, and energy consumption costs, which has become a technical bottleneck restricting the performance improvement of industrial control systems.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for remote data monitoring of a PLC controller, comprising:

[0007] Real-time monitoring of the spectral efficiency and channel status information feedback delay time of PLC controller communication;

[0008] Perform trend analysis on spectrum efficiency, calculate abnormal characteristic values ​​of spectrum efficiency based on the stability of spectrum efficiency, and evaluate the stability of control communication.

[0009] Based on the feedback delay time of the channel state information, calculate the feedback delay characteristic value and assess whether there is a risk of prediction error in the channel.

[0010] The spectral efficiency anomaly feature value and the feedback delay feature value are used to construct a multi-dimensional congestion early warning vector, which is then input into a pre-trained optimization decision model for analysis, and outputs a PLC controller communication strategy.

[0011] Based on the PLC controller's communication strategy, frequency band allocation, time slot scheduling, and power control parameters are dynamically adjusted to achieve adaptive optimization of the concurrent communication performance of multiple control commands.

[0012] Preferably, the evaluation of the stability of the control communication specifically includes:

[0013] The spectrum efficiency of PLC controller communication is acquired in real time, the trend of spectrum efficiency is analyzed, and the abnormal characteristic value of spectrum efficiency is calculated based on the stability of spectrum efficiency.

[0014] Determine whether the abnormal spectral efficiency characteristic value is greater than or equal to a preset threshold. If it is, the wireless communication is unstable; otherwise, the wireless communication is stable.

[0015] Preferably, the step of performing trend analysis on spectral efficiency and calculating abnormal characteristic values ​​of spectral efficiency based on the stability of spectral efficiency specifically includes:

[0016] Real-time acquisition of spectral efficiency sequences in PLC controller communication;

[0017] The Haar wavelet transform was applied to the spectral efficiency sequence for multi-scale decomposition to obtain detail coefficients and approximation coefficients.

[0018] Calculate the energy distribution of wavelet detail coefficients at each level;

[0019] Calculate the mean and standard deviation of all layers of Haar wavelet transform, and combine the energy distribution of wavelet detail coefficients of each layer to calculate the spectral efficiency anomaly characteristic value.

[0020] Preferably, the assessment of whether the channel has prediction error risk specifically includes:

[0021] The feedback delay time of channel status information in PLC controller communication is acquired in real time, and the feedback delay characteristic value is calculated based on the feedback delay time of channel status information.

[0022] Determine whether the feedback delay characteristic value is greater than or equal to a preset threshold. If it is, the channel has a prediction error risk; otherwise, the channel does not have a prediction error risk.

[0023] Preferably, the real-time acquisition of channel status information feedback delay time in PLC controller communication, and the calculation of feedback delay characteristic value based on channel status information feedback delay time specifically include:

[0024] Collect the channel status information sequence reported by multiple user equipment within a preset time period;

[0025] Construct the delay time matrix and then construct the delay covariance matrix based on random matrix theory;

[0026] Calculate the maximum and minimum eigenvalues ​​of the covariance matrix, and then calculate the feedback delay eigenvalues ​​based on the maximum and minimum eigenvalues.

[0027] Preferably, the step of constructing a multi-dimensional congestion warning vector from the spectral efficiency anomaly feature value and the feedback delay feature value, inputting it into a pre-trained optimization decision model for analysis, and outputting a PLC controller communication strategy specifically includes:

[0028] Obtain the spectral efficiency anomaly feature value and the feedback delay feature value, and construct a multi-dimensional congestion early warning vector from the spectral efficiency anomaly feature value and the feedback delay feature value;

[0029] The multidimensional congestion warning vector is input into the pre-trained optimization decision model. The optimization decision model outputs a set of optimal combinations of frequency band allocation, time slot scheduling and power control parameters. The optimization decision model uses the PLC controller communication strategy under different control command communication states as training samples and evaluates the expected benefits of different strategies based on the defined utility function, which comprehensively considers signal-to-noise ratio gain, interference cost and energy consumption cost.

[0030] Preferably, the training process of the optimized decision model is as follows:

[0031] The optimal PLC controller communication strategy is simulated under different network loads, channel conditions, and control scenarios, and used as training samples for the model.

[0032] A deep reinforcement learning architecture is adopted to establish a nonlinear mapping relationship between multidimensional congestion warning vectors and optimal PLC controller communication strategies through model training samples;

[0033] In actual operation, the optimization decision model dynamically adjusts the frequency band allocation strategy, time slot scheduling order and power control level based on the real-time input multi-dimensional congestion warning vector, so as to continuously optimize the performance of concurrent communication of multiple control commands, and continuously update the model parameters through an online incremental learning mechanism.

[0034] Preferably, the step of dynamically adjusting frequency band allocation, time slot scheduling, and power control parameters based on the PLC controller communication strategy to achieve adaptive optimization of the concurrent communication performance of multiple control commands specifically includes:

[0035] Based on the PLC controller communication strategy output by the optimization decision model, the target frequency band with the least interference and the best channel quality is dynamically selected for access allocation.

[0036] Based on the PLC control type and flow requirements, dynamically adjust the time slot scheduling priority and allocation ratio;

[0037] The transmit power level is adjusted in real time based on link budget information.

[0038] Furthermore, a remote data monitoring system for a PLC controller is proposed to implement the remote data monitoring method for the PLC controller described above, specifically including:

[0039] The monitoring module is configured to monitor the spectral efficiency and channel status information feedback delay time of the PLC controller communication in real time.

[0040] An analysis module, connected to the monitoring module, is configured to: perform trend analysis on the spectral efficiency; calculate anomaly characteristic values ​​of spectral efficiency based on the stability of spectral efficiency to assess the stability of control communication; and calculate feedback delay characteristic values ​​based on the channel state information feedback delay time to assess the risk of channel prediction error.

[0041] A decision optimization module is connected to the analysis module. The decision optimization module has a built-in pre-trained optimization decision model. The decision optimization module is configured to: construct a multi-dimensional congestion warning vector from the spectrum efficiency anomaly feature value and the feedback delay feature value, input it into the optimization decision model for analysis, and output a PLC controller communication strategy.

[0042] A dynamic adjustment module is connected to the decision optimization module. The dynamic adjustment module is configured to dynamically adjust the frequency band allocation, time slot scheduling and power control parameters according to the PLC controller communication strategy to achieve adaptive optimization of the concurrent communication performance of multiple control instructions.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] This invention achieves industrial automation communication optimization by combining a multi-dimensional joint evaluation mechanism of spectral efficiency anomaly characteristics and feedback delay characteristics with the real-time decision-making capability of a pre-trained optimized decision model. At the communication stability level, the spectral efficiency evaluation technology based on multi-scale analysis significantly improves the sensitivity of abnormal fluctuation detection, enabling early and accurate warnings of sudden interference. In terms of risk control, the statistical characteristics of the delay covariance matrix are used to effectively quantify channel prediction error risk, significantly reducing the misjudgment rate of traditional feedback mechanisms. Finally, relying on the synergistic optimization of adaptive frequency band allocation, dynamic time slot scheduling, and power closed-loop control, it achieves a breakthrough solution to the real-time conflict problem in scenarios with multiple concurrent control commands. The overall system ensures industrial-grade signal-to-noise ratio gain while simultaneously achieving a significant reduction in communication interruption rate and optimized energy consumption costs, constructing an industrial IoT communication optimization system that combines robustness, timeliness, and energy efficiency. Attached Figure Description

[0045] Figure 1 This is a flowchart of the remote data monitoring method for the PLC controller proposed in this solution;

[0046] Figure 2 This is a flowchart of the method for calculating the spectral efficiency anomaly characteristic value proposed in this scheme;

[0047] Figure 3 This is a flowchart of the method for calculating the feedback delay characteristic value proposed in this scheme;

[0048] Figure 4 This is a flowchart illustrating the training process of the optimized decision-making model proposed in this scheme.

[0049] Figure 5 This is a flowchart illustrating the adaptive optimization of the concurrent communication performance of multiple control instructions proposed in this scheme. Detailed Implementation

[0050] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0051] Reference Figure 1 As shown, a remote data monitoring method for a PLC controller includes:

[0052] The system monitors the spectral efficiency and channel status information feedback delay of PLC controllers in real time. Specifically, a physical layer monitoring module deployed at the wireless access point periodically acquires the instantaneous transmission rate, channel bandwidth, and signal quality parameters of the PLC controller. Combining the amount of data successfully transmitted per unit time with the currently allocated spectrum resources, the system calculates the actual spectral efficiency value of the PLC controller and stores and updates this value according to a time series to reflect the spectrum utilization under the current network conditions. A CSI feedback mechanism is established between the wireless access point and each PLC controller, recording the time difference between initiating a CSI request from the access point and receiving complete channel status information, forming a single feedback delay sample. Statistical processing is performed on the feedback delay samples within multiple sampling periods to obtain the average feedback delay value of the PLC controller within the current time period.

[0053] Perform trend analysis on spectrum efficiency, calculate abnormal characteristic values ​​of spectrum efficiency based on the stability of spectrum efficiency, and evaluate the stability of control communication.

[0054] By using a multi-scale spectrum stability quantification mechanism, the blind spot of traditional threshold detection for slowly varying interference is overcome, enabling early and accurate identification of sudden spectrum anomalies, thus advancing the warning time for communication interruptions and improving the reliability of high real-time control tasks.

[0055] Based on the feedback delay time of the channel state information, calculate the feedback delay characteristic value and assess whether there is a risk of prediction error in the channel.

[0056] Based on the statistical feature analysis of the delay time matrix, random jitter and systematic congestion risks can be effectively distinguished, the misjudgment rate of channel state prediction error is reduced, and deterministic decision-making basis is provided for key operations such as power pre-compensation.

[0057] The spectral efficiency anomaly feature value and the feedback delay feature value are used to construct a multi-dimensional congestion early warning vector, which is then input into a pre-trained optimization decision model for analysis, and outputs a PLC controller communication strategy.

[0058] By using nonlinear dimension fusion and reinforcement learning decision-making mechanisms, a globally optimal communication strategy is generated.

[0059] Based on the PLC controller's communication strategy, frequency band allocation, time slot scheduling, and power control parameters are dynamically adjusted to achieve adaptive optimization of the concurrent communication performance of multiple control commands.

[0060] A closed-loop collaborative control chain of frequency band, time slot, and power is formed, achieving the dual core indicators of high reliability and low power consumption in industrial IoT under typical industrial interference scenarios.

[0061] Reference Figure 2 As shown, trend analysis of spectral efficiency is performed, and the anomaly characteristic values ​​of spectral efficiency are calculated based on the stability of spectral efficiency, specifically including:

[0062] Real-time acquisition of spectral efficiency sequences in PLC controller communication;

[0063] The Haar wavelet transform was applied to the spectral efficiency sequence for multi-scale decomposition to obtain detail coefficients and approximation coefficients.

[0064] Calculate the energy distribution of wavelet detail coefficients at each level;

[0065] Specifically, the formula for calculating energy distribution is:

[0066] ;

[0067] in, This indicates the number of decomposition levels in the Haar wavelet transform. Indicates the number of detail coefficients. Indicates the first The first layer of Haar wavelet transform A detailed coefficient, Indicates the first Energy of layered Haar wavelet transform;

[0068] Calculate the mean and standard deviation of all layers of Haar wavelet transform, and combine the energy distribution of wavelet detail coefficients of each layer to calculate the spectral efficiency anomaly characteristic value;

[0069] The formula for calculating the spectral efficiency anomaly characteristic value is:

[0070] ;

[0071] In the formula, This indicates anomaly characteristics in spectral efficiency. This represents the total number of decomposition levels in the Haar wavelet transform. This represents the mean of all layers of Haar wavelet transform. This represents the standard deviation of the Haar wavelet transform;

[0072] Determine whether the abnormal spectral efficiency characteristic value is greater than or equal to a preset threshold. If it is, the wireless communication is unstable; otherwise, the wireless communication is stable.

[0073] By introducing a computational mechanism for spectral efficiency anomaly features, a refined assessment of wireless communication stability is achieved. This mechanism performs multi-scale decomposition of the real-time acquired spectral efficiency sequence using Haar wavelet transform, extracting the energy distribution characteristics of the detail coefficients at each level. It then constructs a spectral efficiency anomaly feature value by combining the comprehensive deviation between the mean and standard deviation of the wavelet coefficients. This feature value reflects the fluctuation amplitude of spectral efficiency, thereby quantifying the current stability state of the communication link. When this feature value exceeds a preset threshold, the system is determined to be in an unstable state, triggering a resource optimization and adjustment process. Compared to traditional methods that rely solely on instantaneous channel quality indicators, this invention can detect abnormal fluctuations in communication performance earlier and more accurately, improving the system's robustness and adaptability in complex dynamic environments, demonstrating significant technological innovation and practical value.

[0074] Reference Figure 3 As shown, the feedback delay time of channel status information in PLC controller communication is acquired in real time. Based on the feedback delay time of channel status information, the feedback delay characteristic value is calculated, specifically including:

[0075] Collect the channel status information sequence reported by multiple user equipment within a preset time period;

[0076] Construct the delay time matrix and then construct the delay covariance matrix based on random matrix theory. ;

[0077] ;

[0078] in, This represents the conjugate transpose operation. The covariance matrix representing the delay time. Represents the time delay matrix. Indicates the number of users;

[0079] Calculate the covariance matrix Maximum eigenvalue and minimum eigenvalue According to the largest eigenvalue and minimum eigenvalue The feedback delay characteristic value is calculated using the following expression:

[0080] ;

[0081] In the formula, This represents the feedback delay characteristic value;

[0082] By determining whether the feedback delay characteristic value is greater than or equal to a preset threshold, if yes, the channel has a prediction error risk; otherwise, the channel does not have a prediction error risk.

[0083] By collecting the CSI feedback delay time reported by the PLC controller within a preset time period, a delay time matrix is ​​constructed. Combined with random matrix theory, a delay covariance matrix is ​​then constructed, and its maximum and minimum eigenvalues ​​are extracted to calculate the feedback delay eigenvalue. This method fully considers the spatial correlation and dynamic fluctuation of feedback delay in a multi-instruction control environment, effectively identifying the channel state prediction error risk caused by excessive or abnormally distributed feedback delay. By comparing the feedback delay eigenvalue with a preset threshold, it can accurately determine whether the current channel is in a state of prediction inaccuracy risk, thus providing a key decision-making basis for subsequent resource scheduling strategy adjustments. Compared with traditional methods that rely solely on average delay or fixed delay models, this invention has higher sensitivity and discrimination accuracy, significantly improving the channel prediction reliability and resource scheduling intelligence level of the system in highly dynamic, multi-user concurrent scenarios, demonstrating outstanding innovation and engineering application value.

[0084] A multi-dimensional congestion warning vector is constructed from the spectral efficiency anomaly characteristic value and the feedback delay characteristic value. This vector is then input into a pre-trained optimization decision model for analysis. The output PLC controller communication strategy specifically includes:

[0085] Obtain the spectral efficiency anomaly feature value and the feedback delay feature value, and construct a multi-dimensional congestion early warning vector from the spectral efficiency anomaly feature value and the feedback delay feature value;

[0086] The multidimensional congestion warning vector is input into the pre-trained optimization decision model. The optimization decision model outputs a set of optimal combinations of frequency band allocation, time slot scheduling and power control parameters. The optimization decision model uses the PLC controller communication strategy under different control command communication states as training samples and evaluates the expected benefits of different strategies based on the defined utility function, which comprehensively considers signal-to-noise ratio gain, interference cost and energy consumption cost.

[0087] Among them, reference Figure 4 As shown, the training process for the optimized decision model is as follows:

[0088] The optimal PLC controller communication strategy is simulated under different network loads, channel conditions, and control scenarios, and used as training samples for the model.

[0089] A deep reinforcement learning architecture is adopted to establish a nonlinear mapping relationship between multidimensional congestion warning vectors and optimal PLC controller communication strategies through model training samples;

[0090] In actual operation, the optimization decision model dynamically adjusts the frequency band allocation strategy, time slot scheduling order and power control level based on the real-time input multi-dimensional congestion warning vector, so as to continuously optimize the performance of concurrent communication of multiple control commands, and continuously update the model parameters through an online incremental learning mechanism.

[0091] During the model training process, simulation training is performed based on the model training samples. The goal is to maximize the utility function. A nonlinear mapping relationship is constructed between the multidimensional congestion warning vector and the optimal PLC controller communication strategy, thereby realizing the generation of the optimal PLC controller communication strategy under the multidimensional congestion warning vector.

[0092] Through deep reinforcement learning and dynamic evolution of pre-training and online incremental learning in diverse industrial scenarios, and relying on the nonlinear mapping relationship built by multi-dimensional scenario pre-training, the system can generate historically verified optimal strategies in milliseconds when facing sudden channel congestion, completely eliminating the response delay of human experience-based decision-making. Through an incremental learning mechanism that continuously absorbs actual operating data, the model is endowed with the ability to self-evolve against equipment aging and environmental changes, effectively curbing the decision failure of traditional static models caused by scenario drift. Furthermore, with the maximization of utility function as the training objective, it fundamentally coordinates the balanced optimization of signal-to-noise ratio gain, energy consumption cost, and latency constraints, forming a closed-loop intelligent decision-making system that does not rely on manual parameter tuning, achieving Pareto optimality of dynamic allocation of communication resources in industrial sites with severe frequency conversion interference.

[0093] Reference Figure 5 As shown, the adaptive optimization of the concurrent communication performance of multiple control commands by dynamically adjusting frequency band allocation, time slot scheduling, and power control parameters according to the PLC controller's communication strategy specifically includes:

[0094] Based on the PLC controller communication strategy output by the optimization decision model, the target frequency band with the least interference and the best channel quality is dynamically selected for access allocation. Specifically, by analyzing the channel occupancy rate, noise intensity and historical throughput data of each frequency band in real time, combined with the spectrum scan results of the PLC controller's location, the communication quality indicators of each available frequency band are evaluated, and the PLC control communication is preferentially allocated to the best non-overlapping frequency band in the current environment to reduce spectrum conflicts and improve spectrum utilization.

[0095] Based on the PLC control type and flow requirements, the priority and allocation ratio of time slot scheduling are dynamically adjusted. Specifically, the urgency level of control instructions is identified, and corresponding scheduling priority queues are set according to the sensitivity of different control instructions to delay and bandwidth. The proportion of high-priority control instructions in time resources is also dynamically adjusted.

[0096] The transmit power level is adjusted in real time by combining link budget information. Specifically, based on the signal strength and bit error rate information fed back by the receiver, the minimum transmit power required to meet the communication quality is dynamically calculated. This ensures link stability while reducing interference to other users, thereby achieving dual optimization of energy saving and anti-interference.

[0097] Furthermore, based on the same inventive concept as the aforementioned remote data monitoring method for PLC controllers, this solution also proposes a remote data monitoring system for PLC controllers, specifically including:

[0098] The monitoring module is configured to monitor the spectral efficiency and channel status information feedback delay time of the PLC controller communication in real time.

[0099] The analysis module, connected to the monitoring module, is configured to: perform trend analysis on spectral efficiency; calculate anomaly characteristic values ​​of spectral efficiency based on the stability of spectral efficiency to assess the stability of control communication; and calculate feedback delay characteristic values ​​based on the feedback delay time of channel state information to assess the risk of channel prediction error.

[0100] The decision optimization module is connected to the analysis module. The decision optimization module has a built-in pre-trained optimization decision model. The decision optimization module is configured to: construct a multi-dimensional congestion early warning vector from the spectral efficiency anomaly feature value and the feedback delay feature value, input it into the optimization decision model for analysis, and output the PLC controller communication strategy.

[0101] The dynamic adjustment module, connected to the decision optimization module, is configured to dynamically adjust frequency band allocation, time slot scheduling, and power control parameters according to the PLC controller's communication strategy, thereby achieving adaptive optimization of the concurrent communication performance of multiple control commands.

[0102] In summary, the advantages of this invention are as follows: Through a multi-dimensional joint evaluation mechanism of spectral efficiency anomaly characteristics and feedback delay characteristics, combined with the real-time decision-making capability of a pre-trained optimized decision model, industrial automation communication optimization is achieved. At the communication stability level, the spectral efficiency evaluation technology based on multi-scale analysis significantly improves the sensitivity of abnormal fluctuation detection, enabling early and accurate warnings of sudden interference. In terms of risk control, the statistical characteristics of the delay covariance matrix are used to effectively quantify channel prediction error risk, significantly reducing the misjudgment rate of traditional feedback mechanisms. Finally, relying on the synergistic optimization of frequency band adaptive allocation, time slot dynamic scheduling, and power closed-loop control, the real-time conflict problem in scenarios with multiple concurrent control commands is solved in a breakthrough manner. The overall system ensures industrial-grade signal-to-noise ratio gain while simultaneously achieving a significant reduction in communication interruption rate and optimization of energy consumption costs, constructing an industrial IoT communication optimization system that combines robustness, timeliness, and energy efficiency.

[0103] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method of remote data monitoring of a PLC controller, characterized by, The method comprises the following steps: Real-time monitoring of the spectrum efficiency and channel state information feedback delay time of PLC controller communication; Trend analysis of the spectrum efficiency, calculation of the spectrum efficiency anomaly characteristic value according to the stability of the spectrum efficiency, and evaluation of the stability of the control communication; According to the channel state information feedback delay time, the feedback delay characteristic value is calculated to evaluate whether there is a prediction error risk in the channel; The spectrum efficiency anomaly characteristic value and the feedback delay characteristic value are constructed into a multi-dimensional congestion early warning vector, which is input into a pre-trained optimization decision model for analysis, and the PLC controller communication strategy is output; According to the PLC controller communication strategy, the frequency band allocation, time slot scheduling and power control parameters are dynamically adjusted to realize the adaptive optimization of the multi-control instruction concurrent communication performance; Wherein, the trend analysis of the spectrum efficiency, the calculation of the spectrum efficiency anomaly characteristic value according to the stability of the spectrum efficiency specifically comprises: Real-time acquisition of the spectrum efficiency sequence in the PLC controller communication; Applying Haar wavelet transform to the spectrum efficiency sequence for multi-scale decomposition to obtain detail coefficients and approximation coefficients; Calculate the energy distribution of each layer wavelet detail coefficient; Calculate the mean and standard deviation of all layers of Haar wavelet transform, and combine the energy distribution of each layer wavelet detail coefficient to calculate the spectrum efficiency anomaly characteristic value.

2. The remote data monitoring method of a PLC controller according to claim 1, wherein, The evaluation of the stability of the control communication specifically comprises: Real-time acquisition of the spectrum efficiency of the PLC controller communication, trend analysis of the spectrum efficiency, calculation of the spectrum efficiency anomaly characteristic value according to the stability of the spectrum efficiency; Determine whether the spectrum efficiency anomaly characteristic value is greater than or equal to the preset threshold, if yes, the wireless communication is unstable, if not, the wireless communication is stable.

3. The method of claim 2, wherein the PLC controller is a programmable logic controller (PLC) and the remote data monitoring method is a method of monitoring data of a PLC controller, the method comprising: The evaluation of whether there is a prediction error risk in the channel specifically comprises: Real-time acquisition of the channel state information feedback delay time in the PLC controller communication, calculation of the feedback delay characteristic value according to the channel state information feedback delay time; Determine whether the feedback delay characteristic value is greater than or equal to the preset threshold, if yes, the channel has a prediction error risk, if not, the channel has no prediction error risk.

4. The remote data monitoring method of a PLC controller according to claim 3, wherein, The real-time acquisition of the channel state information feedback delay time in the PLC controller communication, the calculation of the feedback delay characteristic value according to the channel state information feedback delay time specifically comprises: Collecting the channel state information sequence reported by the multi-user equipment within a preset time period; Constructing a delay time matrix and constructing a delay covariance matrix based on random matrix theory; Calculate the maximum and minimum eigenvalues of the covariance matrix, and calculate the feedback delay characteristic value according to the maximum and minimum eigenvalues.

5. The method of claim 4, wherein the PLC controller is a programmable logic controller (PLC) and the remote data monitoring method is a method of monitoring data of the PLC controller from a remote location. The spectrum efficiency anomaly characteristic value and the feedback delay characteristic value are constructed into a multi-dimensional congestion early warning vector, which is input into a pre-trained optimization decision model for analysis, and the PLC controller communication strategy is output specifically comprises: Obtain the spectrum efficiency anomaly characteristic value and the feedback delay characteristic value, and construct the spectrum efficiency anomaly characteristic value and the feedback delay characteristic value into a multi-dimensional congestion early warning vector; The multi-dimensional congestion early warning vector is input into a pre-trained learning optimization decision model, and the optimization decision model outputs a set of optimal frequency band allocation, time slot scheduling and power control parameter combinations. The optimization decision model takes PLC controller communication strategies under different control instruction communication states as training samples, and evaluates the expected returns of different strategies based on a defined utility function, wherein the utility function comprehensively considers signal-to-noise ratio gain, interference cost and energy consumption cost.

6. The remote data monitoring method of a PLC controller according to claim 5, wherein, The training process of the optimization decision model is as follows: Simulate the optimal PLC controller communication strategies under different network loads, channel conditions and control scenarios as model training samples; Use a deep reinforcement learning architecture to establish a nonlinear mapping relationship between the multi-dimensional congestion early warning vector and the optimal PLC controller communication strategy through the model training samples; In actual operation, the optimization decision model dynamically adjusts the frequency band allocation strategy, time slot scheduling order and power control level according to the real-time input multi-dimensional congestion early warning vector to continuously optimize the performance of concurrent communication of multiple control instructions, and continuously updates the model parameters through an online incremental learning mechanism.

7. The method of claim 6, wherein the PLC controller is a programmable logic controller (PLC) and the remote data monitoring method is a method of monitoring data of the PLC controller from a remote location. The dynamic adjustment of the frequency band allocation, time slot scheduling and power control parameters according to the PLC controller communication strategy to realize the adaptive optimization of the performance of concurrent communication of multiple control instructions specifically includes: According to the PLC controller communication strategy output by the optimization decision model, dynamically select the target frequency band with the minimum interference and the optimal channel quality for access allocation; Based on the PLC control type and traffic demand, dynamically adjust the time slot scheduling priority and allocation ratio; Combine the link budget information to adjust the transmission power level in real time.

8. A remote data monitoring system for a PLC controller, characterized by, A remote data monitoring method for implementing the PLC controller according to any one of claims 1-7, specifically comprising: A monitoring module configured to monitor the spectral efficiency and channel state information feedback delay time of PLC controller communication in real time; An analysis module connected with the monitoring module, the analysis module is configured to: trend analysis of the spectral efficiency, calculation of the spectral efficiency anomaly characteristic value according to the stability of the spectral efficiency, to evaluate the stability of control communication; calculate the feedback delay characteristic value according to the channel state information feedback delay time, to evaluate the channel prediction error risk; A decision optimization module connected with the analysis module, the decision optimization module is built-in pre-trained optimization decision model; the decision optimization module is configured to: construct the spectral efficiency anomaly characteristic value and the feedback delay characteristic value into a multi-dimensional congestion early warning vector, input the optimization decision model for analysis, and output the PLC controller communication strategy; A dynamic adjustment module connected with the decision optimization module, the dynamic adjustment module is configured to: dynamically adjust the frequency band allocation, time slot scheduling and power control parameters according to the PLC controller communication strategy, to realize the adaptive optimization of the performance of concurrent communication of multiple control instructions.

Images