Robust intelligent regulation and control method and system of adaptive environment industrial personal computer

Abstract

The invention relates to the technical field of regulation and control, and discloses a robust intelligent regulation and control method and system for an adaptive environment industrial personal computer, and the method comprises the following steps: building an electromagnetic interference space-time distribution model; the establishment of the electromagnetic interference space-time distribution model comprises the steps of collecting multi-point electromagnetic interference data, preprocessing the electromagnetic interference data, constructing an electromagnetic interference space-time distribution interpolation model and predicting electromagnetic interference time change; according to the method, a complete closed-loop feedback system is formed through multi-level strategy cooperative work such as real-time updating of an electromagnetic interference space-time distribution model, accurate classification of task sensitivity, dynamic adjustment of risk assessment and space-time elastic scheduling of task execution, so that a robust electromagnetic interference adaptation mechanism is constructed; the method can actively sense the environment change and make corresponding adjustment, improves the reliability and stability of the industrial control system in a complex electromagnetic environment, and guarantees the robust execution of a key task.

Description

Technical Field

[0001] The present invention relates to the field of control technology, and more specifically, to a method and system for robust intelligent control of an adaptive environment industrial control computer. Background Art

[0002] Industrial computer systems are widely used in manufacturing, metallurgy, petrochemicals, energy and other industrial fields, and are a core component of modern industrial automation control. However, industrial field environments often have complex electromagnetic interference, such as electromagnetic noise generated by large motor start-stop, arc welding, switching power supplies, inverters and other equipment. These interferences pose a serious threat to the stability and reliability of industrial computer systems.

[0003] Existing methods for improving the electromagnetic compatibility of industrial computers primarily include the following: First, enhancing the device's anti-interference capabilities through hardware reinforcement, such as using shielded enclosures, filters, and fiber optic isolation; second, optimizing system software design to enhance data error detection and correction capabilities; and third, optimizing task scheduling to avoid executing critical tasks during peak interference periods. However, these methods have significant shortcomings: hardware reinforcement solutions are costly and inflexible; software optimization methods, while able to mitigate the impact of interference, struggle to fundamentally address the problem; and traditional task scheduling methods lack the ability to accurately perceive and quantitatively model the temporal and spatial distribution characteristics of electromagnetic interference, making them incapable of precise control in complex and changing electromagnetic environments and resulting in insufficient system robustness.

[0004] In particular, existing industrial computer scheduling methods have significant deficiencies in the following aspects: first, the ability to finely model the spatiotemporal characteristics of electromagnetic interference is insufficient, and the non-uniform distribution characteristics of interference cannot be accurately characterized; second, the ability to implement differentiated protection for tasks of different importance levels is lacking, and resources cannot be allocated according to task sensitivity and importance; third, in an environment where the intensity of electromagnetic interference changes drastically, the real-time performance of critical tasks and the overall robust stability of the system cannot be guaranteed, resulting in a high task failure rate and unstable system response time.

[0005] Therefore, there is an urgent need for an industrial control computer system that can accurately perceive the spatiotemporal distribution characteristics of electromagnetic interference and implement intelligent control according to task sensitivity, so as to improve the reliability, robustness and stability of the industrial control system in complex electromagnetic environments. Summary of the Invention

[0006] The present invention provides a method and system for robust intelligent control of an industrial control computer in an adaptive environment, which solves the technical problem of intelligent control of an industrial control computer in an adaptive environment in related technologies.

[0007] The present invention provides a method for robust intelligent control of an industrial control computer in an adaptive environment, comprising the following steps:

[0008] Establishing a spatiotemporal distribution model of electromagnetic interference, which includes collecting multi-point electromagnetic interference data, pre-processing electromagnetic interference data, building an electromagnetic interference spatiotemporal distribution interpolation model, and predicting the temporal variation of electromagnetic interference;

[0009] Evaluate and classify mission electromagnetic sensitivity based on the spatiotemporal distribution model of electromagnetic interference;

[0010] Perform mission risk assessment and prediction based on electromagnetic interference spatiotemporal distribution models and mission electromagnetic sensitivity;

[0011] Perform dynamic allocation of robust anti-interference resources based on mission risk assessment and prediction results;

[0012] Based on the dynamic allocation of anti-interference resources, flexible task scheduling and execution are implemented to achieve robust intelligent scheduling of tasks in time and space dimensions, thereby improving the reliability and robustness of task execution.

[0013] As a further optimization solution of the present invention, in establishing the electromagnetic interference spatiotemporal distribution model, collecting multi-point electromagnetic interference data includes:

[0014] Deploy multiple electromagnetic interference monitoring sensors at different locations on the industrial site;

[0015] Collect electromagnetic interference intensity data at different spatial locations and time points to form a data set containing the monitoring location coordinates (x i ,y i , z i ), timestamp t i And the corresponding electromagnetic interference intensity value I i multidimensional spatiotemporal data points.

[0016] As a further optimization solution of the present invention, the construction of the electromagnetic interference spatiotemporal distribution interpolation model includes:

[0017] Apply clustering algorithm to the pre-processed electromagnetic interference data to identify the location of the interference source;

[0018] For each identified interference source, a propagation function model based on physical attenuation laws is established:

[0019]

[0020] Among them, d i (x, y, z, t) is the Euclidean distance from the spatial position (x, y, z) to the i-th interference source, Represents the change function of the i-th interference source in the time dimension;

[0021] Construct a continuous electromagnetic interference spatiotemporal distribution model:

[0022]

[0023] Where E(x,y,z,t) represents the electromagnetic interference intensity function at the spatial position (x,y,z) and time point t. represents the sum of all interference sources, represents the strength of the i-th interference source, represents the propagation function of the i-th interference source, n E Indicates the total number of interference sources identified.

[0024] As a further optimization solution of the present invention, the task electromagnetic sensitivity assessment and grading includes:

[0025] Analyze the characteristic parameters of industrial control tasks and establish the task characteristic description vector:

[0026] T i =(C i , K i , D i , I i );

[0027] Among them, C i is the computational complexity of the task, which represents the computational load and resource requirements of the task; K i D is the mission criticality, which indicates the importance of the mission to the overall function of the system; i is the task time sensitivity, which indicates the task's tolerance to execution delay; I i is the task data integrity requirement, which indicates the task's sensitivity to data errors;

[0028] Evaluate the electromagnetic sensitivity characteristics of the industrial computer execution unit and construct the electromagnetic sensitivity description vector of the execution unit:

[0029] U j =(α j , β j , γ j );

[0030] Among them, α j is the unit type sensitivity coefficient, which represents the inherent electromagnetic sensitivity of different types of hardware units; β j is the unit shielding coefficient, which indicates the electromagnetic shielding degree of the hardware unit; γ j is the unit historical failure rate, which represents the historical failure statistics in the electromagnetic interference environment;

[0031] Calculate the sensitivity index S of the task in a specific electromagnetic environment i , industrial control tasks are divided into three levels: high sensitivity, medium sensitivity and low sensitivity.

[0032] As a further optimization solution of the present invention, the risk assessment and prediction of the execution task includes:

[0033] Combining the electromagnetic interference spatiotemporal distribution model and the task sensitivity index, a basic risk assessment model for tasks at specific spatiotemporal locations is constructed;

[0034] Considering the historical execution of tasks, a correction factor for historical task failure records is introduced;

[0035] Considering the competition for system resources, the current load status factor of the industrial computer is introduced;

[0036] By integrating the basic risk assessment model of tasks at specific time and space locations, the correction factor of historical task failure records, and the current load status factor of the industrial computer, a complete task risk assessment function is constructed to predict the failure risk probability of tasks at specific time and space locations.

[0037] As a further optimization solution of the present invention, the performing of dynamic allocation of anti-interference resources includes:

[0038] Define the anti-interference resource pool that can be allocated to the industrial computer system, including computing resources, memory resources, communication bandwidth resources and anti-interference hardware resources;

[0039] Calculate the resource priority index of each task based on the task risk probability and task importance level;

[0040] Implement dynamic resource allocation strategy based on task priority index;

[0041] Additional anti-interference resources are allocated to high-risk missions, including processing units with better electromagnetic shielding, data redundancy backup, and adjustment of mission execution clock frequency.

[0042] As a further optimization solution of the present invention, the implementation of flexible task scheduling includes:

[0043] Construct spatiotemporal electromagnetic interference maps to identify "electromagnetic safe areas" and "electromagnetic dangerous areas";

[0044] Implement task rescheduling strategies to adjust task execution times to avoid high-interference periods;

[0045] Implementing a task space re-arrangement strategy to assign high-risk tasks to hardware units or physical locations with lower electromagnetic interference;

[0046] Build backup execution paths for critical tasks to achieve rapid switching and recovery in the event of failure.

[0047] As a further optimization scheme of the present invention, the task flexible scheduling execution adopts a combination of improved shortest job first and priority scheduling algorithms. The scheduling algorithm maintains a multi-priority task queue and generates an optimal scheduling scheme through a risk-aware scheduler.

[0048] As a further optimization scheme of the present invention, the prediction of the time change of electromagnetic interference adopts a long short-term memory network model to model the electromagnetic interference intensity sequence of each spatial point, output the interference intensity prediction value of the next time window, and support the prediction of periodic interference, trend interference and sudden interference.

[0049] A system for implementing intelligent control of an industrial control computer in an adaptive environment, for executing the above-mentioned intelligent control method of an industrial control computer in an adaptive environment, comprising:

[0050] Electromagnetic interference monitoring module, used to collect multi-point electromagnetic interference data and monitor the electromagnetic environment status of industrial sites in real time;

[0051] Interference modeling module, used to build a spatiotemporal distribution model of electromagnetic interference and predict the changing trend of electromagnetic interference;

[0052] Mission sensitivity assessment module, used to analyze the characteristics of industrial control tasks, evaluate the electromagnetic sensitivity of tasks and classify them;

[0053] Risk assessment module, used to combine interference model and sensitivity to predict task execution risk;

[0054] Resource allocation module, used to dynamically allocate system anti-interference resources according to mission risk and priority;

[0055] The scheduling execution module is used to implement flexible scheduling of tasks in time and space to ensure reliable execution of tasks.

[0056] The beneficial effect of the present invention is that: the present invention forms a complete closed-loop feedback system through the collaborative work of multi-level strategies such as real-time update of the electromagnetic interference spatiotemporal distribution model, precise classification of task sensitivity, dynamic adjustment of risk assessment, and spatiotemporal flexible scheduling of task execution, so as to build a robust electromagnetic interference adaptation mechanism, which can actively perceive environmental changes and make corresponding adjustments, thereby improving the reliability and stability of the industrial control system in a complex electromagnetic environment and ensuring the robust execution of key tasks. Specifically, through precise electromagnetic interference modeling and risk assessment, combined with differentiated resource allocation strategies, the execution success rate of key tasks in a strong electromagnetic interference environment is improved, and the system failures and data errors caused by electromagnetic interference are effectively reduced; and the dynamic resource allocation and task spatiotemporal rearrangement strategies based on risk assessment are adopted to reduce the response time fluctuations of key tasks in an electromagnetic interference environment and improve the response time guarantee rate in an extreme electromagnetic environment; at the same time, the differentiated resource allocation mechanism based on task risk and importance realizes the precise delivery of resources. Compared with the traditional uniform task allocation method, the overall system throughput is improved, and more tasks can be processed under the same hardware conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1It is a flow chart of a method for robust intelligent control of an adaptive environment industrial control computer according to the present invention;

[0058] Figure 2 It is a detailed flow chart of constructing a spatiotemporal distribution model of electromagnetic interference according to the present invention;

[0059] Figure 3 It is a detailed flow chart of the construction task electromagnetic sensitivity assessment model of the present invention;

[0060] Figure 4 It is a detailed flow chart of the construction task execution risk assessment model of the present invention;

[0061] Figure 5 It is a detailed flow chart of constructing a dynamic resource allocation model of the present invention;

[0062] Figure 6 It is a detailed flow chart of the construction task elastic scheduling execution model of the present invention. DETAILED DESCRIPTION

[0063] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. Furthermore, features described in some examples may be combined in other examples.

[0064] At least one embodiment of the present invention discloses a method for robust intelligent control of an adaptive environment industrial control computer, such as Figures 1 to 5 As shown, the following steps are included:

[0065] Step 1: Establishing a spatiotemporal distribution model of electromagnetic interference. Establishing the spatiotemporal distribution model of electromagnetic interference includes collecting multi-point electromagnetic interference data, pre-processing the electromagnetic interference data, constructing a spatiotemporal distribution interpolation model of electromagnetic interference, and predicting the temporal variation of electromagnetic interference.

[0066] This step uses multi-point monitoring technology to collect and quantify electromagnetic interference in industrial environments and build a spatiotemporal distribution model of electromagnetic interference. Specifically, it includes:

[0067] Step 1.1, collect multi-point electromagnetic interference data;

[0068] Specifically, multiple electromagnetic interference monitoring sensors are deployed at different locations in the industrial site to collect electromagnetic interference intensity data at different spatial locations and time points to form an original electromagnetic interference data set. The data recorded by each sensor includes the monitoring location coordinates (x i ,y i , z i), timestamp t i And the corresponding electromagnetic interference intensity value I i , the generated form is (x i ,y i , z i , t i , I i )’s multi-dimensional spatiotemporal data points.

[0069] Step 1.2, preprocessing electromagnetic interference data;

[0070] Specifically, the collected raw electromagnetic interference data is preprocessed, including outlier detection and correction, data smoothing and normalization, to obtain a cleaned electromagnetic interference data set. outlier , identified by the following function:

[0071] P outlier ={(x i ,y i , z i , t i , I i )||I i -μ E |>3σ E};

[0072] Among them, μ E is the mean value of electromagnetic interference intensity, σ E is the standard deviation. The identified outlier data points are replaced by the weighted average of the adjacent points.

[0073] Step 1.3: Construct an electromagnetic interference spatiotemporal distribution interpolation model;

[0074] Specifically, based on the processed electromagnetic interference data, a spatiotemporal interpolation algorithm is applied to construct a continuous electromagnetic interference spatiotemporal distribution model. The model is expressed as:

[0075]

[0076] Where E(x, y, z, t) represents the electromagnetic interference intensity function at the spatial position (x, y, z) and time point t, Indicates that all interference sources (from the 1st to the nth E The sum of represents the strength of the i-th interference source, represents the propagation function of the i-th interference source, n E Indicates the total number of interference sources identified.

[0077] Propagation Function Using a model based on physical attenuation laws:

[0078]

[0079] Among them, d i (x, y, z, t) is the Euclidean distance from the spatial position (x, y, z) to the i-th interference source, Represents the variation function of the i-th interference source in the time dimension.

[0080] In the specific implementation, the identification of interference sources is completed through clustering algorithm. According to the spatial distribution characteristics of the monitoring data, the density-based spatial clustering algorithm (DBSCAN) is used to identify the location of potential interference sources. For each identified interference source, its intensity is fitted by the least squares method. and time-varying functions Time-varying function Using Fourier series expansion form:

[0081]

[0082] in, is the constant term coefficient of the Fourier series expansion, Indicates that k ranges from 1 to m E The sum of is the Fourier series expansion of cos(kω E The coefficient of the term t) is is the Fourier series expansion of sin(kω E t) term, ω E is the fundamental frequency of the Fourier series, indicating the frequency of the interference period change, m E is the order of the Fourier series expansion, that is, the highest harmonic contained in the Fourier series.

[0083] In practical applications in industrial workshops, the spatiotemporal interpolation algorithm, combined with factory floor plans and equipment layout information, can accurately draw Figure 2 The electromagnetic interference heat map shown here visually displays the distribution of interference intensity in different areas. When transient electromagnetic interference events occur, such as motor startup and shutdown or high-power device switching, the model can update the interference distribution in real time, providing an accurate basis for subsequent task scheduling.

[0084] Step 1.4, predict the time variation of electromagnetic interference;

[0085] Specifically, by analyzing the temporal patterns of historical electromagnetic interference data, an electromagnetic interference time variation prediction model is constructed to predict the electromagnetic interference distribution at future time points.

[0086] The prediction model uses the time series analysis method to calculate the electromagnetic interference intensity sequence {E(x, y, z, t1), E(x, y, z, t2), ..., E(x, y, z, tk ) to model and output the predicted value of the next time window Among them, E(x, y, z, t1), E(x, y, z, t2), E(x, y, z, t k ) represent the first time point t1, the second time point t2, and the kth time point t at the spatial point (x, y, z) respectively. k The electromagnetic interference intensity, Indicates that at the spatial point (x, y, z), time point t k+1 The predicted electromagnetic interference intensity value.

[0087] In its implementation, the electromagnetic interference temporal variation prediction model utilizes a long short-term memory (LSTM) network architecture, which is particularly well-suited for processing long-term dependencies in time series data. The LSTM network consists of an input layer, an LSTM layer, and an output layer. The input layer receives normalized historical interference intensity data, while the LSTM layer consists of multiple LSTM units. Each LSTM unit includes an input gate, a forget gate, and an output gate to control information flow. The network structure parameters are determined based on the temporal characteristics of electromagnetic interference in actual industrial environments. In most application scenarios, a two-layer LSTM architecture is used, with each layer containing 64 LSTM units, a 10-minute time step, and a prediction window of one hour into the future.

[0088] In practical applications, this prediction model can identify and predict the following three typical electromagnetic interference time patterns: periodic interference: such as periodic electromagnetic interference caused by equipment start-up and shutdown, scheduled maintenance, etc. related to production shifts; trend interference: such as the gradually increasing interference caused by the gradual decline in electromagnetic shielding performance due to equipment aging; sudden interference: such as sudden interference caused by equipment failure, temporary high-power equipment operation, etc.

[0089] In a metal processing workshop application case, this prediction model can predict the increased electromagnetic interference caused by the startup of large CNC equipment 15-20 minutes in advance with an accuracy rate of 92%. This provides sufficient preparation time for the advance scheduling of industrial computer tasks and effectively avoids failures caused by the execution of critical tasks during high-interference periods.

[0090] Step 2: Based on the electromagnetic interference spatiotemporal distribution model, evaluate the electromagnetic sensitivity of the mission and classify it;

[0091] This step builds a task electromagnetic sensitivity assessment model based on the characteristics of industrial control tasks and the characteristics of the execution hardware units. It divides industrial control tasks into different sensitivity levels, including:

[0092] Step 2.1, analyze the characteristic parameters of industrial control tasks;

[0093] Specifically, we analyze the characteristic parameters of various tasks in the industrial computer and establish the task characteristic description vector T i .

[0094] The mission characteristic description vector contains the following key parameters:

[0095] Task computational complexity C i : Indicates the computational load and resource requirements of the task;

[0096] Mission criticality K i : Indicates the importance of the task to the overall function of the system;

[0097] Task time sensitivity D i : Indicates the task's tolerance to execution delay;

[0098] Mission Data Integrity Requirements I i : Indicates the sensitivity of the task to data errors.

[0099] The task characteristic vector is expressed as: T i =(C i , K i , D i , I i );

[0100] Step 2.2, evaluate the electromagnetic sensitivity characteristics of the execution unit;

[0101] Specifically, the sensitivity characteristics of each execution unit of the industrial computer in the electromagnetic environment are evaluated, and the electromagnetic sensitivity description vector U of the execution unit is constructed. j .

[0102] The execution unit sensitivity vector contains the following parameters:

[0103] Unit type sensitivity coefficient α j : The inherent electromagnetic sensitivity of different types of hardware units (such as CPU, memory, I / O interface);

[0104] Unit shielding coefficient β j : The electromagnetic shielding degree of the hardware unit;

[0105] Unit historical failure rate γ j : Historical failure statistics in electromagnetic interference environment.

[0106] The execution unit sensitivity vector is expressed as: U j =(α j , β j , γ j );

[0107] Step 2.3, calculate the task sensitivity index;

[0108] Specifically, combined with the task feature vector Execution unit sensitivity vector U j and environmental electromagnetic characteristics E em , calculate the sensitivity index of the task in a specific electromagnetic environment

[0109]

[0110] in, represents the electromagnetic sensitivity index of task i, f() represents the sensitivity calculation function, is the weight coefficient, which is used to balance the influence of each factor, ||E em || represents the intensity norm of the environmental electromagnetic interference, indicating the comprehensive magnitude of the electromagnetic interference intensity.

[0111] Step 2.4: Classify tasks into different sensitivity levels;

[0112] Specifically, according to the calculated sensitivity index Industrial control tasks are divided into three levels: high sensitivity, medium sensitivity, and low sensitivity:

[0113] Highly sensitive tasks: Extremely sensitive to electromagnetic interference and requiring the highest level of protection;

[0114] Medium sensitive tasks: It is sensitive to electromagnetic interference and requires proper protection;

[0115] Low-sensitivity tasks: It is not sensitive to electromagnetic interference and can operate normally in high interference environments.

[0116] in, and It is a preset sensitivity threshold that can be dynamically adjusted according to system characteristics and environmental conditions.

[0117] Step 3: Perform mission risk assessment and prediction based on the electromagnetic interference spatiotemporal distribution model and mission electromagnetic sensitivity;

[0118] This step builds a task execution risk assessment model based on the electromagnetic interference spatiotemporal distribution model and the task sensitivity classification results to predict the failure risk probability of the task at a specific spatiotemporal location. Specifically, it includes:

[0119] Step 3.1: Build a basic risk assessment model;

[0120] Specifically, combining the electromagnetic interference spatiotemporal distribution model E(x, y, z, t) constructed in step 1 and the task sensitivity index calculated in step 2 Build Task T j At the spatial position (xj ,y j , z j ) and the basic risk assessment model at time t:

[0121]

[0122] Among them, T j represents task j, (x j ,y j , z j ) represents the spatial position coordinates of task j, t represents the time point, R base It represents the basic risk index, which is proportional to the mission sensitivity and the intensity of environmental electromagnetic interference. j ,y j , z j , t) means at position (x j ,y j , z j ) and time t.

[0123] Step 3.2: Introduce the task history failure record correction factor;

[0124] Specifically, considering the historical execution of the task, a correction factor for the historical failure record of the task is introduced

[0125] For each task T j , calculate its historical failure rate under different electromagnetic interference intensities, and construct the failure probability distribution function P fail (T j , E). Correction factor The calculation is as follows:

[0126]

[0127] in, Indicates that k ranges from 1 to m hist The sum of Represents task T j The failure flag at the kth execution (1 for failure, 0 for success), is the time decay weight of the kth execution, so that recent failures have a greater impact on the correction factor, m hist The total number of historical records.

[0128] Step 3.3: Introduce the current load status factor of the industrial computer;

[0129] Specifically, the current load state factor L(t) of the industrial computer is introduced to consider the impact of system resource competition on the risk of task execution. The load state factor is expressed as:

[0130]

[0131] Among them, CPU(t), MEM(t) and IO(t) represent the processor usage, memory occupancy and I / O load at time t respectively. max MEM max and IO max Represent the maximum capacity of processor utilization, memory occupancy and I / O load, α L , β L and γ L are the weight coefficients of processor usage, memory usage, and I / O load in the load status factor respectively.

[0132] Step 3.4: Construct a complete task risk assessment function;

[0133] Specifically, considering the above factors, a complete task risk assessment function is constructed to calculate the task T j The probability of failure risk at a specific time and space location:

[0134]

[0135] Among them, R base (T j , x j ,y j , z j , t) represents task T j At the spatial position (x j ,y j , z j ) and the basic risk index at time point t, which reflects the basic risk level of the task affected by electromagnetic interference at a specific time and space location; is the correction factor for task history failure record; L(t) is the current load state factor of the industrial computer; E(x j ,y j , z j , t) means at position (x j ,y j , z j ) and the electromagnetic interference intensity at time t; P(failure|T j , E) represents the task T under a given electromagnetic interference environment E j The failure probability of each task is σ; σ is a sigmoid function that maps the risk index to the interval [0, 1], representing the failure probability. Using this function, the system can dynamically assess the execution risk of each task under the current and predicted future electromagnetic environment, providing a basis for subsequent resource allocation and task scheduling decisions.

[0136] In its implementation, the mission risk assessment model uses the Gradient Boosting Decision Tree (GBDT) algorithm for training and optimization. This algorithm integrates multiple weak learners (decision trees) to construct a strong learner, effectively processing the complex relationships among multi-dimensional features such as mission characteristics, historical execution records, system load status, and electromagnetic interference. The training dataset contains historical records of industrial computer systems operating in different electromagnetic environments. Each record includes electromagnetic interference intensity, mission characteristics, system load status, and mission execution results (success / failure).

[0137] During model training, a five-fold cross-validation method was used to evaluate model performance, using AUC (area under the curve), precision, and recall as evaluation metrics. In actual deployment, the model was retrained every three months using newly collected data to adapt to changes in the industrial environment and task characteristics.

[0138] In a distributed control system (DCS) application at a chemical plant, this risk assessment model achieved a 94.5% accuracy rate in predicting the failure risk of highly sensitive tasks (such as key parameter acquisition and safety interlock control), a 22 percentage point improvement over traditional rule-based methods. The model was particularly effective during periods of drastic electromagnetic interference fluctuations (such as the start-up and shutdown of large electric motors), accurately predicting the failure risk of marginal tasks. This provided a reliable basis for task scheduling and resource allocation, effectively avoiding localized system failures caused by electromagnetic interference.

[0139] Step 4: Perform dynamic allocation of robust anti-interference resources based on the mission risk assessment and prediction results;

[0140] This step builds a dynamic resource allocation model based on the task risk assessment results to provide differentiated resource guarantees for tasks of different risk levels. Specifically, it includes:

[0141] Step 4.1: Define the anti-interference resource pool that can be allocated to the industrial computer system;

[0142] Specifically, define the anti-interference resource pool R that can be allocated to the industrial computer system pool , including computing resources R cpu , memory resources R mem , communication bandwidth resources R bw and anti-interference hardware resources R anti (such as reserved redundant processing units, backup storage, etc.) The resource pool is represented as:

[0143] R pool ={R cpu , R mem , R bw ,R anti};

[0144] Each resource type has a maximum total amount:

[0145]

[0146] Among them, R cpu Indicates the amount of CPU resources currently allocated. Indicates the maximum available amount of CPU resources;

[0147] R mem Indicates the amount of memory resources currently allocated, Indicates the maximum available amount of memory resources;

[0148] R bw Indicates the amount of communication bandwidth resources currently allocated, Indicates the maximum available amount of communication bandwidth resources;

[0149] R anti Indicates the amount of anti-interference hardware resources currently allocated, Indicates the maximum available amount of anti-interference hardware resources.

[0150] Step 4.2: Calculate the task resource priority index;

[0151] Specifically, based on the task risk probability R(T j , t) and task importance level Calculate the resource priority index for each task

[0152]

[0153] in, and are the weight coefficients of risk factors and task importance in the resource priority index. Task importance level Pre-defined by the system administrator to reflect the importance of the task to the overall function of the system.

[0154] Step 4.3: Implement dynamic resource allocation strategy;

[0155] Specifically, according to the task priority index Implement dynamic resource allocation strategy. For each resource type R k , Task T j Resource share obtained The calculation is as follows:

[0156]

[0157] in, represents the maximum available amount of the k-th resource, For task T jThe demand weight for the k-th resource, is the demand weight of the i-th task for k-type resources, n task is the total number of tasks in the current system, represents the resource priority index of the i-th task at time t, Represents task T j The resource priority index at time t, Represents i from 1 to n task The sum of .

[0158] This step ensures that high-priority tasks get a larger share of resources.

[0159] Step 4.4: Allocate additional anti-interference resources to high-risk tasks;

[0160] Specifically, for high-risk tasks ( in, Represents the benchmark threshold of the mission risk probability. When the mission risk probability exceeds this threshold, it is judged as a high-risk mission. Additional anti-interference resources R are allocated. anti , including: allocating processing units with better electromagnetic shielding to computing tasks; increasing redundant backups for data storage and transmission; and adjusting the clock frequency of task execution to reduce sensitivity to electromagnetic interference.

[0161] For particularly critical and high-risk tasks, a resource exclusivity strategy is implemented to avoid sharing key hardware resources with other tasks and minimize the impact of electromagnetic interference. The resource allocation strategy can be expressed as a conditional allocation function:

[0162]

[0163] in, Represents task T j The amount of anti-interference resource allocation obtained at time t; Indicates the total amount of exclusive anti-interference resources; Represents the total amount of sharable anti-interference resources; R(T j , t) represents task T j The probability of risk at time t; Indicates a critical threshold for risk; A baseline threshold representing risk; Represents task T j level of importance; a critical threshold indicating importance; Represents task T j The resource priority index at time t; H risk represents a set of high-risk tasks, Indicates the sum of all tasks in the high-risk task set.

[0164] Step 5: Based on the dynamic allocation of anti-interference resources, flexible task scheduling is implemented to achieve robust intelligent scheduling of tasks in time and space dimensions, thereby improving the reliability and robustness of task execution.

[0165] This step builds a flexible task scheduling execution model based on the aforementioned electromagnetic interference spatiotemporal distribution model, task risk assessment results, and resource priority allocation strategy analysis. This model implements intelligent task scheduling in both temporal and spatial dimensions to avoid high electromagnetic interference areas and periods, improving task execution reliability. Specifically, it includes:

[0166] Step 5.1, constructing a spatiotemporal electromagnetic interference map;

[0167] Specifically, a spatiotemporal electromagnetic interference map is constructed to identify the "electromagnetic safe areas" and "electromagnetic dangerous areas" in the IPC operating environment. Based on the spatiotemporal electromagnetic interference distribution model E(x, y, z, t) established in step 1, the IPC environment is divided into different levels of areas:

[0168] Zone safe ={(x,y,z,t)|E(x,y,z,t) <E safe};

[0169] Zone warning ={(x,y,z,t)|E safe ≤E(x,y,z,t) <E danger};

[0170] Zone danger ={(x,y,z,t)|E(x,y,z,t)≥E danger};

[0171] Among them, (x, y, z, t) represents the spatial position coordinates (x, y, z) and time t, E safe and E danger They are the electromagnetic interference safety threshold and the electromagnetic interference danger threshold, which can be dynamically adjusted according to the overall tolerance of the system to electromagnetic interference. safe Indicates the electromagnetic safety zone, that is, the area where the interference intensity is lower than the safety threshold; Zone warning Indicates the electromagnetic warning zone, that is, the area where the interference intensity is between the safety threshold and the danger threshold; Zone danger Indicates electromagnetic hazard areas, that is, areas where interference intensity is higher than the hazard threshold.

[0172] Step 5.2: Implement task rescheduling strategy;

[0173] Specifically, the task time rescheduling strategy is implemented to adjust the task execution time according to the time distribution characteristics of electromagnetic interference to avoid high interference periods. j , its optimal execution time window t opt The calculation is as follows:

[0174]

[0175] where t current is the current system time, t deadline is the deadline by which the task must be completed, R(T j , t) is the task risk probability calculated in step 3, and argmin represents the value of the independent variable when the objective function reaches the minimum value.

[0176] Step 5.3: Implement the task space rearrangement strategy;

[0177] Specifically, a task space rearrangement strategy is implemented to assign high-risk tasks to hardware units or physical locations with lower electromagnetic interference. j , its optimal execution position (X opt ,y opt , z opt ) is calculated as follows:

[0178]

[0179] Among them, (X opt ,y opt , z opt Represents task T j The optimal execution position coordinates of the target function, argmin represents the value of the independent variable when the objective function is minimized, AvailableUnits represents the set of available hardware execution units, and the elements in the set are the hardware units that can be used for task execution, E(x, y, z, t scheduled ) represents the position (x, y, z) and the planned execution time t scheduled The electromagnetic interference intensity, is the task sensitivity index.

[0180] Step 5.4: Build a backup execution path for critical tasks.

[0181] Specifically, a backup execution path is built for critical tasks to achieve fast switching and recovery in case of failure. j ( in, Represents task T j The importance level, Indicates the critical threshold of importance), prepare backup execution resource B in a low electromagnetic interference area in advance j, and establish a state synchronization algorithm between the main and standby execution units. When the main execution path detects an anomaly, the automatic switching condition is triggered:

[0182]

[0183] Among them, Switch(T j ) represents task T j A Boolean value indicating whether to switch to the backup execution path. switch The electromagnetic interference threshold for switching triggers. When the threshold is higher than this, the backup execution path switching is triggered. Error(T j ) represents task T j The number of errors detected during execution.

[0184] The flexible task scheduling execution model uses a combination of an improved Shortest Job First (SJF) and priority scheduling algorithms. The system maintains a multi-priority task queue, each of which employs a time-space risk-weighted sorting strategy. The core of the scheduling algorithm is a dynamically adaptive risk-aware scheduler that receives input from a risk assessment model and generates an optimal scheduling solution based on task deadline constraints, resource requirements, and the current system state.

[0185] The main steps of the scheduling algorithm are as follows:

[0186] Initially sort all tasks to be scheduled according to risk assessment results and priority;

[0187] For high-risk tasks ( Among them, R(T j , t) represents task T j The risk assessment value at time t, (represents the risk threshold of high-risk tasks) to optimize the execution time window and find the execution time period with the lowest electromagnetic interference within the next Δt time;

[0188] Perform spatial location optimization for medium- and high-risk tasks, assigning them to hardware execution units with lower electromagnetic interference;

[0189] Generate primary and backup execution plans for critical tasks to ensure that they can quickly switch to the backup path when the primary execution path fails; regularly (every 30 seconds) re-evaluate the current environment and task status and dynamically adjust the scheduling plan.

[0190] By executing steps 1 to 5, the adaptive environment industrial computer intelligent control method provided in this embodiment can achieve accurate perception, quantitative evaluation and intelligent response to electromagnetic interference in industrial sites, ensuring the reliable operation of the industrial computer system in complex electromagnetic environments.

[0191] This implementation achieves precise perception and intelligent response to electromagnetic interference in industrial environments through technical means such as building an electromagnetic interference spatiotemporal distribution model, task electromagnetic sensitivity assessment and classification, task risk assessment and prediction, dynamic allocation of anti-interference resources, and flexible task scheduling and execution. It has the following significant technical effects:

[0192] Significantly improved system reliability: Through precise electromagnetic interference modeling and risk assessment, combined with differentiated resource allocation strategies, the success rate of critical tasks in strong electromagnetic interference environments has been improved, effectively reducing system failures and data errors caused by electromagnetic interference. This has particularly reduced the failure rate of highly sensitive tasks.

[0193] Enhanced real-time guarantee capability: The adoption of dynamic resource allocation and task spatiotemporal rescheduling strategies based on risk assessment reduces the response time fluctuations of key tasks in electromagnetic interference environments, and improves the response time guarantee rate in extreme electromagnetic environments, which is far higher than traditional methods.

[0194] Improved system resource utilization efficiency: A differentiated resource allocation mechanism based on task risk and importance enables precise resource delivery. Compared with the traditional uniform task allocation method, the overall system throughput is improved, and more tasks can be processed under the same hardware conditions, achieving a balance between electromagnetic interference protection and system performance.

[0195] Strong environmental adaptability: Through real-time monitoring and prediction of electromagnetic interference, combined with adaptive task scheduling strategies, the system can automatically adjust protection strategies as the environment changes. It can adapt to electromagnetic interference environments of different degrees and distribution characteristics without human intervention, greatly improving its applicability.

[0196] Reliability cost reduction: Compared with the traditional method of improving electromagnetic compatibility through hardware reinforcement, this implementation adopts an intelligent control strategy that combines software and hardware. While achieving the same reliability, it reduces the system hardware cost. At the same time, it reduces the time and energy consumption caused by task retries and system restarts, and increases the service life of industrial control equipment in harsh environments.

[0197] The adaptive environment intelligent control method for industrial control computers provided in this embodiment effectively solves the problem of reliable operation of industrial control computer systems in industrial electromagnetic interference environments, and has significant technological advancement and practical value.

[0198] Real application examples of this embodiment

[0199] Application scenario description

[0200] This implementation has been put to practical use in the industrial control system of a rolling mill at a large steel mill. The mill, covering approximately 15,000 square meters, houses a large number of high-power electrical equipment, including variable-frequency motors, electric arc furnaces, and large transformers. These devices generate significant electromagnetic interference during operation, exhibiting significant spatial and temporal non-uniformity. The mill's industrial control computer system controls key parameters of the rolling production line, including rolling pressure, speed control, temperature monitoring, and safety interlocks. The system comprises 24 industrial control computers, distributed throughout the mill and connected to over 500 I / O points.

[0201] Before implementing this method, the rolling mill's industrial control system faced severe electromagnetic interference issues. This was particularly true during the startup and shutdown of large motors, where control parameter acquisition errors, communication interruptions, and control command execution failures frequently occurred. Local system failures occurred an average of 3-5 times per week, severely impacting production efficiency and product quality. After implementing this method, system reliability was significantly improved, achieving stable operation in complex electromagnetic environments.

[0202] Implementation process instance

[0203] Step 1 Example: In the steel rolling mill, we first deployed electromagnetic interference monitoring equipment.

[0204] As shown in Table 1, 12 electromagnetic interference monitoring sensors were installed in the workshop, covering the areas around key equipment and industrial control computers.

[0205] Table 1: Deployment of electromagnetic interference monitoring sensors

[0206] Sensor number Installation location Monitoring scope Data collection frequency S01 Next to the main rolling mill control cabinet 5m radius 100Hz S02 Inverter area 8m radius 100Hz S03 Electric arc furnace control area 10m radius 200Hz S04 Industrial computer server room 3m radius 100Hz ... ... ... ... S12 Finished product area control cabinet 4m radius 50Hz

[0207] By continuously collecting data for 30 days, we accumulated over 25 million data points, forming a raw EMI dataset. Using a clustering algorithm to identify interference sources, we identified seven major EMI sources within the workshop, as shown in Table 2.

[0208] Table 2: Characteristics of the main EMI sources identified

[0209] Interference source number Location Interference Type Interference intensity (relative value) Time characteristics I01 Main motor area Frequency conversion harmonics 0.85 Related to motor start and stop I02 Electric Arc Furnace Pulse interference 0.92 Cyclical fluctuations I03 Main transformer Low-frequency interference 0.65 Load related ... ... ... ... ... I07 welding area High-frequency interference 0.58 intermittent

[0210] Based on the identified interference sources, a spatiotemporal interpolation algorithm was applied to construct a workshop electromagnetic interference distribution model, generating an electromagnetic interference heat map that visually displays the distribution of interference intensity in different areas and time periods. Specifically, the LSTM model successfully predicted the changing trend of interference intensity during the main motor startup process, achieving a prediction accuracy of 91.6%.

[0211] Example of Step 2: In this application, we performed sensitivity assessment and classification for all tasks in a steel rolling control system.

[0212] First, the task characteristics in the system are analyzed, as shown in Table 3.

[0213] Table 3: Characteristic parameters of typical tasks in the system

[0214] Task Type Computational complexity Criticality Time sensitivity Data integrity requirements Rolling pressure control 0.7 0.95 0.9 0.9 Temperature monitoring 0.3 0.7 0.5 0.8 Speed ​​adjustment 0.6 0.9 0.95 0.85 Safety interlock 0.4 1.0 1.0 1.0 Data Recording 0.5 0.4 0.3 0.7

[0215] Combined with the sensitive characteristics of the execution unit and the electromagnetic characteristics of the environment, the sensitivity index of each task is calculated and the sensitivity index is calculated according to the preset threshold (S high =0.75, S medium =0.5) were graded, and the results are shown in Table 4.

[0216] Table 4: Task sensitivity grading results

[0217] Task Type Sensitivity Index Sensitivity level Rolling pressure control 0.82 High sensitivity Temperature monitoring 0.61 Moderately sensitive Speed ​​adjustment 0.88 High sensitivity Safety interlock 0.93 High sensitivity Data Recording 0.48 Hyposensitivity

[0218] Example of Step 3: Based on the established electromagnetic interference model and task sensitivity classification, we conducted a risk assessment for key tasks in the system. For the "rolling pressure control" task, we developed a risk assessment model using a gradient boosting decision tree algorithm, taking into account the baseline risk index, historical failure records, and system load conditions.

[0219] In practical applications, the model successfully predicted the impact of electromagnetic interference (EMI) caused by motor startup on the rolling pressure control task. The model predicted the peak of EMI 17 minutes earlier than the actual time, and the accuracy of the predicted probability of mission failure was 93.4%.

[0220] Example of steps 4 and 5: Based on the risk assessment results, the system implements differentiated resource allocation strategies and flexible task scheduling.

[0221] Table 5 shows the system's resource allocation and scheduling optimization for different types of tasks.

[0222] Table 5: Resource allocation and scheduling optimization for different types of tasks

[0223]

[0224] When electromagnetic interference intensity exceeds a preset threshold, the system automatically increases resource allocation to critical tasks and activates backup execution units. During a high-interference event caused by the start-up of an electric arc furnace, the system successfully shifted highly sensitive tasks to a low-interference area, ensuring stable operation.

[0225] Technical effect verification

[0226] This implementation method has achieved significant technical results in actual application in the steel mill's rolling mill. We focused on verifying two key technical effects: improving system reliability and ensuring real-time performance.

[0227] 1. System reliability improvement effect:

[0228] We counted the system failures within 6 months before and after the application, focusing on system anomalies and task failures caused by electromagnetic interference.

[0229] As shown in Table 6, after applying this method, the overall failure rate of the system is significantly reduced.

[0230] Table 6: Comparison of system failure statistics before and after application

[0231] Fault type Number of failures before application / month Number of failures after application / month Reduce the ratio Control parameter collection error 15.3 1.2 92.2％ Communication interruption 8.6 0.5 94.2％ Control instruction execution failed 6.2 0.3 95.2％ Partial system restart 4.5 0.2 95.6％ total 34.6 2.2 93.6％

[0232] Especially for highly sensitive tasks, the success rate has significantly improved in environments with strong electromagnetic interference. In the strongest interference environment (relative intensity > 0.8), the success rate was only 68.5% before the application, but increased to 98.7% after the application, a 30.2 percentage point increase.

[0233] 2. Real-time guarantee effect:

[0234] We also verified the system's real-time guarantee capability in an electromagnetic interference environment.

[0235] As shown in Table 7, after applying this method, the response time fluctuation of key tasks is significantly reduced, especially in strong interference environments.

[0236] Table 7: Task response time statistics before and after application (unit: ms)

[0237]

[0238] In an extreme electromagnetic interference environment (relative intensity > 0.8), the system response time guarantee rate (the probability of responding within the required time window) was only 76.3% before application, but increased to 99.5% after application, an increase of 23.2 percentage points.

[0239] The application results of this implementation in actual industrial environments have fully demonstrated its effectiveness and practical value, significantly improving the reliability and real-time performance of industrial control systems in complex electromagnetic environments, and providing reliable control guarantees for industrial production.

[0240] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make more forms of equivalent embodiments based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. A robust intelligent control method for an industrial computer in an adaptive environment, characterized in that: The following steps are involved: Establishing a spatiotemporal distribution model of electromagnetic interference, which includes collecting multi-point electromagnetic interference data, pre-processing electromagnetic interference data, building an electromagnetic interference spatiotemporal distribution interpolation model, and predicting the temporal variation of electromagnetic interference; Evaluate and classify mission electromagnetic sensitivity based on the spatiotemporal distribution model of electromagnetic interference; Perform mission risk assessment and prediction based on electromagnetic interference spatiotemporal distribution models and mission electromagnetic sensitivity; Perform dynamic allocation of robust anti-interference resources based on mission risk assessment and prediction results; Based on the dynamic allocation of anti-interference resources, flexible task scheduling and execution are implemented to achieve robust intelligent scheduling of tasks in time and space dimensions, thereby improving the reliability and robustness of task execution.

2. The method for robust intelligent control of an adaptive environment industrial computer according to claim 1, characterized in that: In establishing the electromagnetic interference spatiotemporal distribution model, collecting electromagnetic interference data at multiple points includes: Deploy multiple electromagnetic interference monitoring sensors at different locations on the industrial site; Collect electromagnetic interference intensity data at different spatial locations and time points to form a data set containing the monitoring location coordinates (x i ,y i , z i ), timestamp t i And the corresponding electromagnetic interference intensity value I i multidimensional spatiotemporal data points.

3. The method for robust intelligent control of an industrial computer in an adaptive environment according to claim 1, characterized in that: The constructing of the electromagnetic interference spatiotemporal distribution interpolation model comprises: Apply clustering algorithm to the pre-processed electromagnetic interference data to identify the location of the interference source; For each identified interference source, a propagation function model based on physical attenuation laws is established: Among them, d i (x, y, z, t) is the Euclidean distance from the spatial position (x, y, z) to the i-th interference source, Represents the change function of the i-th interference source in the time dimension; Construct a continuous electromagnetic interference spatiotemporal distribution model: Where E(x, y, z, t) represents the electromagnetic interference intensity function at the spatial position (x, y, z) and time point t, represents the sum of all interference sources, represents the strength of the i-th interference source, represents the propagation function of the i-th interference source, n E Indicates the total number of interference sources identified.

4. The method for robust intelligent control of an industrial computer in an adaptive environment according to claim 1, characterized in that: The assessment and grading of electromagnetic sensitivity of the task include: Analyze the characteristic parameters of industrial control tasks and establish the task characteristic description vector: T i =(C i ,K i ,D i I i ); Among them, C i is the computational complexity of the task, which represents the computational load and resource requirements of the task; K i D is the mission criticality, which indicates the importance of the mission to the overall function of the system; i is the task time sensitivity, which indicates the task's tolerance to execution delay; I i is the task data integrity requirement, which indicates the task's sensitivity to data errors; Evaluate the electromagnetic sensitivity characteristics of the industrial computer execution unit and construct the electromagnetic sensitivity description vector of the execution unit: U j =(a j ,b j ,c j ); Among them, α j is the unit type sensitivity coefficient, which represents the inherent electromagnetic sensitivity of different types of hardware units; β j is the unit shielding coefficient, which indicates the electromagnetic shielding degree of the hardware unit; γ j is the unit historical failure rate, which represents the historical failure statistics in the electromagnetic interference environment; Calculate the sensitivity index S of the task in a specific electromagnetic environment i , industrial control tasks are divided into three levels: high sensitivity, medium sensitivity and low sensitivity.

5. The method for robust intelligent control of an adaptive environment industrial computer according to claim 1, characterized in that: The risk assessment and prediction of mission execution includes: Combining the electromagnetic interference spatiotemporal distribution model and the task sensitivity index, a basic risk assessment model for tasks at specific spatiotemporal locations is constructed; Considering the historical execution of tasks, a correction factor for historical task failure records is introduced; Considering the competition for system resources, the current load status factor of the industrial computer is introduced; By integrating the basic risk assessment model of tasks at specific time and space locations, the correction factor of historical task failure records, and the current load status factor of the industrial computer, a complete task risk assessment function is constructed to predict the failure risk probability of tasks at specific time and space locations.

6. The method for robust intelligent control of an industrial computer in an adaptive environment according to claim 1, characterized in that: The performing of dynamic allocation of anti-interference resources includes: Define the anti-interference resource pool that can be allocated to the industrial computer system, including computing resources, memory resources, communication bandwidth resources and anti-interference hardware resources; Calculate the resource priority index of each task based on the task risk probability and task importance level; Implement dynamic resource allocation strategy based on task priority index; Additional anti-interference resources are allocated to high-risk missions, including processing units with better electromagnetic shielding, data redundancy backup, and adjustment of mission execution clock frequency.

7. The method for robust intelligent control of an industrial computer in an adaptive environment according to claim 1, characterized in that: The implementation of flexible task scheduling includes: Construct a spatiotemporal electromagnetic interference map to identify "electromagnetic safe areas" and "electromagnetic dangerous areas"; Implement task rescheduling strategies to adjust task execution times to avoid high-interference periods; Implementing a task space re-arrangement strategy to assign high-risk tasks to hardware units or physical locations with lower electromagnetic interference; Build backup execution paths for critical tasks to achieve rapid switching and recovery in the event of failure.

8. The method for robust intelligent control of an industrial computer in an adaptive environment according to claim 1, characterized in that: The task flexible scheduling is performed by combining an improved shortest job first and priority scheduling algorithms. The scheduling algorithm maintains a multi-priority task queue and generates an optimal scheduling solution through a risk-aware scheduler.

9. The method for robust intelligent control of an industrial computer in an adaptive environment according to claim 1, characterized in that: The method for predicting the time variation of electromagnetic interference adopts a long short-term memory network model to model the electromagnetic interference intensity sequence of each spatial point, output the interference intensity prediction value of the next time window, and support the prediction of periodic interference, trend interference and sudden interference.

10. A system for realizing intelligent control of an industrial control computer in an adaptive environment, used for executing the intelligent control method of an industrial control computer in an adaptive environment according to any one of claims 1 to 9, characterized in that: include: Electromagnetic interference monitoring module, used to collect multi-point electromagnetic interference data and monitor the electromagnetic environment status of industrial sites in real time; Interference modeling module, used to build a spatiotemporal distribution model of electromagnetic interference and predict the changing trend of electromagnetic interference; Mission sensitivity assessment module, used to analyze the characteristics of industrial control tasks, evaluate the electromagnetic sensitivity of tasks and classify them; Risk assessment module, used to combine interference model and sensitivity to predict task execution risk; Resource allocation module, used to dynamically allocate system anti-interference resources according to mission risk and priority; The scheduling execution module is used to implement flexible scheduling of tasks in time and space to ensure reliable execution of tasks.

Images