A multimodal real-time control system and method for novel power systems

Abstract

This invention discloses a multimodal real-time control system and method for novel power systems. Relating to the field of power system technology, it solves the problem of achieving precise control under complex and variable operating conditions. This invention deeply mines monitoring parameters with data correlations within the power system, accurately identifying the trend characteristics between correlated monitoring parameters from historical operating data. This process not only considers the correspondence between numerical changes of monitoring parameters but also calculates the precise change value BH based on detailed analysis of numerical control segments and auxiliary data segments, forming a comprehensive record of trend characteristics. This allows for full consideration of multiple influencing factors during actual control, avoiding control deviations caused by ignoring changes in correlated parameters, thereby greatly improving the accuracy of the multimodal control process and ensuring the stable operation of the power system.

Description

Technical Field

[0001] This invention relates to the field of power system technology, specifically to a multimodal real-time control system and method for novel power systems. Background Technology

[0002] As new power systems develop towards high-proportion renewable energy integration and multi-source collaborative interaction, the system structure and operating characteristics are becoming increasingly complex, placing higher demands on the accuracy and reliability of real-time power system control.

[0003] Traditional power system control methods often focus on a single type of monitoring parameter or regulate power system parameters based on simple empirical rules, making it difficult to fully consider the complex correlation characteristics between different monitoring parameters.

[0004] In actual operation, there are close data coupling and mutual influence relationships among multiple monitoring parameters such as voltage, current, and power. When a certain parameter changes, other related parameters will also fluctuate accordingly. However, existing technologies cannot effectively capture and utilize these related trend characteristics.

[0005] In addition, existing control strategies lack the ability to dynamically adapt to the coordinated changes of related parameters during the regulation process, making it difficult to achieve precise regulation under complex and ever-changing operating conditions, resulting in poor control effects and potentially causing system stability problems.

[0006] At the same time, traditional methods also have shortcomings in anomaly monitoring, failing to identify and warn of abnormal situations in the control process in a timely and effective manner, thus increasing the operational risks of the power system.

[0007] Therefore, there is an urgent need for a new control method that can deeply mine the correlation characteristics of monitoring parameters, realize multimodal collaborative control, and have anomaly monitoring functions, so as to meet the needs of safe, efficient and stable operation of new power systems. Summary of the Invention

[0008] To address the shortcomings of existing technologies, this invention provides a multimodal real-time control system and method for novel power systems, solving the problem of achieving precise control under complex and ever-changing operating conditions.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a multimodal real-time control method for novel power systems, comprising the following steps: Step 1: Identify multiple monitoring parameters with data correlation within the power system, and confirm the trend characteristics between the correlated monitoring parameters from historical operating data, recording them sequentially. The specific method is as follows: The monitoring parameters that are identified as having associated markers are marked as associated monitoring parameter sets. Each associated monitoring parameter set includes only two monitoring parameters. The historical operating data associated with the corresponding monitoring parameter is identified from the historical operating data associated with the corresponding monitoring parameter set. Based on the identified historical operational data, the control nodes corresponding to the monitoring parameters in the associated monitoring parameter set are confirmed, thereby identifying the numerical control segments belonging to the corresponding monitoring parameters. The control time associated with the numerical control segment is recorded as the numerical control time. In the control data of another set of monitoring parameters, the parameter data associated with the corresponding numerical control time is confirmed. The confirmed parameter data segments are recorded as the subordinate data segments of this numerical control segment, and the numerical control segments and subordinate data segments are processed as follows: Confirm the change characteristic value T1 of adjacent time intervals in the numerical control segment, and then confirm the change characteristic value T2 of the same time interval in the auxiliary data segment. Use BH=T1÷T2 to confirm the corresponding change value BH, and record it as trend characteristics (T1, BH). Record several sets of trend characteristics associated with the associated monitoring parameters in sequence. Step 2: Identify the monitoring parameters that need to be regulated, confirm the regulation characteristics, select the optimal regulation trend from the trend characteristics associated with these monitoring parameters, and simultaneously confirm the characteristic range associated with the optimal regulation trend. The specific method is as follows: Based on the confirmed control characteristics, which include the value to be adjusted and the specific time of control, the parameter associated with the current corresponding monitoring parameter is denoted as CS, the value to be adjusted in the control characteristics is denoted as DS, and the specific time for control is denoted as Ts. The difference value to be adjusted, Cz, is confirmed using the formula: Cz = DS - CS, and the minimum trend value, Dq, is confirmed using the formula: Cz ÷ Ts = Dq. Based on the confirmed minimum trend value Dq, if Dq > 0, then from the recorded trend characteristics, the trend characteristics with a value greater than Dq are recorded as candidate trends; if Dq < 0, the trend characteristics with a value less than Dq are recorded as candidate trends. From the trend characteristics associated with different candidate trends, the variance of several sets of change values ​​BH associated with a single candidate trend is processed to confirm that they belong to the variance characteristics associated with the corresponding candidate trend. Based on the different variance characteristics associated with different candidate trends, the minimum value is selected, and the candidate trend associated with the minimum value is taken as the best control trend. Based on the confirmed optimal control trend, the multiple sets of change values ​​BH associated with this optimal control trend are confirmed, and the minimum and maximum values ​​associated with the corresponding change values ​​BH are locked to confirm the characteristic range associated with this optimal control trend. Step 3: Based on the selected optimal control trend and characteristic range, parameter limits are applied to the numerical control process between the associated monitoring parameters to complete the multimodal real-time control process between the associated monitoring parameters. The specific method is as follows: Based on the determined optimal control trend, the value change of the monitoring parameter to be adjusted is controlled within a unit time. The monitoring parameter to be adjusted is the monitoring parameter that needs to be controlled by parameter limitation. Based on the determined characteristic interval, another set of monitoring parameters within the associated monitoring parameter set is identified. This other set of monitoring parameters is recorded as the auxiliary monitoring parameters. The numerical values ​​of the auxiliary monitoring parameters are synchronously adjusted, and the value adjusted per unit time is the minimum value of the characteristic interval. Monitor the parameter changes of the auxiliary monitoring parameters at the specific time of regulation, identify the unit change value of adjacent time, propose the parameter monitored at the previous time within the adjacent time and record it as J1, propose the parameter monitored at the next time and record it as J2, and adopt: unit change value = J2 - J1; If the unit change value is not equal to 0, then confirm whether the change trends of the auxiliary monitoring parameter and the monitoring parameter to be adjusted are consistent during the same period. If they are consistent, then increase the original selected control value of the auxiliary monitoring parameter until the unit change value is 0. If they are inconsistent, then decrease the original selected control value of the auxiliary monitoring parameter until the unit change value is 0. In the specific numerical control process of the monitoring parameter to be adjusted, the control logic determined above is used to control the values ​​associated with the auxiliary monitoring parameters in real time. If the unit change value is 0, then the original selected control value of the auxiliary monitoring parameter remains unchanged.

[0010] Preferred options also include: Step 4: Assess the anomalies in parameter changes within a specific timeframe, identify any abnormalities in the control process, and confirm the control anomaly signals based on the identified anomalies. The specific method is as follows: Confirm several sets of unit variable values ​​associated with the auxiliary monitoring parameters within a specific time period of regulation. Select |BZ|max from the confirmed sets of unit variable values ​​BZ and record it as the characteristic value to be verified. Then confirm the optimal control trend associated with the monitoring parameter to be adjusted within the specific control time period, and simultaneously determine the minimum value of the characteristic interval. The evaluation value is calculated as: optimal control trend ÷ minimum value of characteristic interval. If the |evaluation value| is greater than or equal to the feature value to be verified, no processing is required; otherwise, an abnormal control signal is generated and displayed.

[0011] Preferably, a multimodal real-time control system for novel power systems includes: The trend feature recording end identifies multiple monitoring parameters with data correlation within the power system, confirms the trend features between the correlated monitoring parameters from historical operating data, and records them sequentially. The optimal trend confirmation end identifies the monitoring parameters that need to be regulated, confirms the regulation characteristics, selects the optimal regulation trend from the trend characteristics associated with these monitoring parameters, and simultaneously confirms the characteristic range associated with the optimal regulation trend. The real-time control processing end, based on the selected optimal control trend and characteristic range, limits the numerical control process between the associated monitoring parameters and completes the multimodal real-time control process between the associated monitoring parameters. The parameter early warning terminal assesses the abnormal changes in parameters within a specific time period, identifies any abnormalities in the control process, and displays the control abnormality signals in real time based on the identified abnormalities.

[0012] This invention provides a multimodal real-time control system and method for novel power systems. Compared with existing technologies, it has the following advantages: This invention deeply mines data from monitoring parameters in the power system that exhibit data correlation, accurately identifying the trend characteristics between these parameters from historical operating data. This process not only considers the correspondence between numerical changes in the monitoring parameters but also calculates the precise change value BH based on detailed analysis of numerical control segments and auxiliary data segments, forming a comprehensive record of trend characteristics. This allows for the full consideration of multiple influencing factors during actual control, avoiding control deviations caused by neglecting changes in related parameters, thereby greatly improving the accuracy of multimodal control processes and ensuring the stable operation of the power system. When selecting the optimal control trend, the method combines the control characteristics input by the operator, scientifically calculates the adjustment difference value and the lowest trend value, accurately screens the candidate trends, and innovatively uses variance processing to select the optimal solution. This method can extract the most stable and effective control trend from historical data, ensuring that the control strategy can not only meet the control requirements but also guarantee the accuracy and stability of numerical control, thereby achieving efficient and precise control of power system parameters. In the process of limiting the parameters of the associated monitoring parameters based on the optimal control trend and characteristic range, dynamic coordinated control of the monitoring parameters to be controlled and the auxiliary monitoring parameters is realized. Not only are the control rules of the two within a unit time clearly defined, but also feedback adjustments are made by monitoring the unit change value in real time to ensure that the change trends of the two are consistent, avoid system fluctuations caused by asynchronous parameter control, and improve the coordination and stability of the overall operation of the power system. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the principle framework of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] First Embodiment Please see Figure 1 This application provides a multimodal real-time control method for novel power systems, comprising the following steps: Step 1: Identify multiple monitoring parameters with data correlation within the power system, and confirm the trend characteristics between these parameters from historical operating data, recording them sequentially. A trend characteristic refers to how a change in one monitoring parameter synchronously affects a corresponding change in another set of monitoring parameters. To ensure accuracy in the multi-modal control process, these multiple influences need to be considered. The specific method for confirming trend characteristics is as follows: The monitoring parameters that are identified as having associated markers (their associated markers are all preset markers, which are marked in advance by relevant operators based on experience to facilitate subsequent marker confirmation) are marked as associated monitoring parameter sets. Each associated monitoring parameter set includes only two sets of monitoring parameters. The historical operating data associated with the corresponding associated monitoring parameter set is identified from the historical operating data associated with the corresponding monitoring parameter. Based on the identified historical operational data, the control nodes (i.e., the time points when the values ​​are controlled) of the corresponding monitoring parameters are identified, thus confirming the numerical control segments belonging to the corresponding monitoring parameters. The control time associated with the numerical control segment is recorded as the numerical control time. In the control data of another set of monitoring parameters, the parameter data associated with the corresponding numerical control time is identified, and the identified parameter data segments are recorded as the subordinate data segments of this numerical control segment. The numerical control segments and subordinate data segments are then processed as follows: From the numerical control segment, confirm the change characteristic value T1 of adjacent time intervals (the change characteristic value is the monitoring parameter corresponding to the next time interval minus the monitoring parameter corresponding to the previous time interval), then confirm the change characteristic value T2 of the same time interval in the auxiliary data segment, and use BH=T1÷T2 to confirm the corresponding change value BH, and record it as trend feature (T1, BH). Record several sets of trend features associated with the associated monitoring parameter set in sequence. Specifically, each associated monitoring parameter set has two sets of monitoring parameters. When a single monitoring parameter undergoes numerical adjustment and change, it will generate several sets of trend characteristics. This allows for verification and confirmation of the change trend between the two sets of monitoring parameters, facilitating the subsequent actual numerical adjustment process and achieving a more precise multimodal control process. Step 2: Identify the monitoring parameters that need to be regulated, identify the regulation characteristics, select the best regulation trend from the trend characteristics associated with these monitoring parameters, and simultaneously identify the characteristic range associated with the best regulation trend. The specific method for selecting the optimal control trend is as follows: Based on the confirmed control characteristics, which are the values ​​input by the operator, including the value to be adjusted and the specific time of control, the parameter associated with the current corresponding monitoring parameter is denoted as CS, the value to be adjusted in the control characteristics is denoted as DS, and the specific time to be controlled is denoted as Ts. The difference value to be adjusted, Cz, is confirmed using the formula: Cz = DS - CS, and the minimum trend value of change, Dq, is confirmed using the formula: Cz ÷ Ts = Dq. Based on the confirmed minimum trend value Dq, if Dq > 0 (meaning the value needs to be adjusted upwards), then from the recorded trend characteristics, the trend characteristics with a value greater than Dq are recorded as candidate trends; if Dq < 0 (meaning the value needs to be adjusted downwards), the trend characteristics with a value less than Dq are recorded as candidate trends. From the trend characteristics associated with different candidate trends, the variance of several sets of change values ​​BH associated with a single candidate trend is processed to confirm that they belong to the variance characteristics associated with the corresponding candidate trend. Based on the different variance characteristics associated with different candidate trends, the minimum value is selected, and the candidate trend associated with the minimum value is taken as the best control trend. Among them, there are a lot of the same trends in the parameters before each trend feature. So the same trend may correspond to different BH values. Based on the confirmed candidate trends, several groups of BH values ​​can be verified by feature, and the verification features can be locked to facilitate the confirmation of the best control trend in the future. Specifically, historical data can be used to identify different variance features associated with different trends. These different variance features have different numerical characteristics. The smaller the numerical value, the more concentrated the features associated with the corresponding trend are. In this case, the corresponding trend can not only effectively regulate the corresponding parameters, but also ensure the accuracy of the subsequent numerical regulation process. The specific method for confirming the associated feature interval is as follows: Based on the confirmed optimal control trend, the multiple sets of change values ​​BH associated with this optimal control trend are confirmed, and the minimum and maximum values ​​associated with the corresponding change values ​​BH are locked in. The characteristic interval associated with this optimal control trend is confirmed, and the characteristic interval can be expressed as [BHmin, BHmax].

[0016] Step 3: Based on the selected optimal control trend and characteristic range, parameter constraints are applied to the numerical control process between the associated monitoring parameters to complete the multimodal real-time control process between the associated monitoring parameters. The specific method for parameter constraint is as follows: Based on the determined optimal control trend, the value change of the monitoring parameter to be adjusted is controlled within a unit time. The monitoring parameter to be adjusted is the monitoring parameter that needs to be controlled by parameter limitation. Based on the determined characteristic interval, another set of monitoring parameters within the associated monitoring parameter set is identified. This other set of monitoring parameters is recorded as the auxiliary monitoring parameters. The numerical values ​​of the auxiliary monitoring parameters are synchronously adjusted, and the value adjusted per unit time is the minimum value of the characteristic interval. Monitor the parameter changes of the auxiliary monitoring parameters at the specific time of regulation, identify the unit change value of adjacent time, propose the parameter monitored at the previous time within the adjacent time and record it as J1, propose the parameter monitored at the next time and record it as J2, and adopt: unit change value = J2 - J1; If the unit change value is 0, then the original selected control value of the auxiliary monitoring parameter remains unchanged (its control value comes from the characteristic interval). If the unit change value is not equal to 0, then confirm whether the change trends of the auxiliary monitoring parameter and the monitoring parameter to be adjusted are consistent during the same period. If they are consistent, then increase the original selected control value of the auxiliary monitoring parameter until the unit change value is 0. If they are inconsistent, it means that the corresponding control value is too large, and reverse adjustment is required. The corresponding control value needs to be reduced, and the original selected control value of the auxiliary monitoring parameter is reduced until the unit change value is 0. In the specific numerical control process of the monitoring parameter to be adjusted, the control logic determined above is used to adjust the values ​​associated with the auxiliary monitoring parameter in real time, so as to achieve a better multimodal control process and a better control effect.

[0017] Step Four: This step is a further processing step following Step Three. It is used to assess the anomalies in the parameter changes within a specific timeframe, identify any abnormalities in the control process, and display the control anomaly signals in real time based on the identified anomalies. The specific method for identification is as follows: Confirm several sets of unit variable values ​​associated with the auxiliary monitoring parameters within a specific time period of regulation (the confirmed parameters are the specific parameters generated after regulation treatment). From the confirmed sets of unit variable values ​​BZ, select |BZ|max and record it as the characteristic value to be verified. Then confirm the optimal control trend associated with the monitoring parameter to be adjusted within the specific control time period, and simultaneously determine the minimum value of the characteristic interval. The evaluation value is calculated as: optimal control trend ÷ minimum value of characteristic interval. If the |evaluation value| is greater than or equal to the feature value to be verified, no processing is required. Otherwise, an abnormal control signal will be generated and displayed, indicating that there is a specific abnormality in the corresponding auxiliary monitoring parameter during the control process, which requires maintenance personnel to perform maintenance.

[0018] Second Embodiment Combination Figure 2 A multimodal real-time control system for novel power systems includes: The trend feature recording terminal determines multiple monitoring parameters that are correlated within the power system, identifies the trend features between the correlated monitoring parameters from historical operating data, and records them sequentially.

[0019] The optimal trend confirmation end identifies the monitoring parameters that need to be regulated, confirms the regulation characteristics, selects the optimal regulation trend from the trend characteristics associated with these monitoring parameters, and simultaneously confirms the characteristic range associated with the optimal regulation trend. The real-time control processing end, based on the selected optimal control trend and characteristic range, limits the numerical control process between the associated monitoring parameters and completes the multimodal real-time control process between the associated monitoring parameters. The parameter early warning terminal assesses the abnormal changes in parameters within a specific time period, identifies any abnormalities in the control process, and displays the control abnormality signals in real time based on the identified abnormalities.

[0020] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0021] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A multimodal real-time control method for novel power systems, characterized in that, Includes the following steps: Step 1: Identify multiple monitoring parameters with data correlation within the power system, and confirm the trend characteristics between the correlated monitoring parameters from historical operating data, recording them sequentially. The specific method is as follows: The monitoring parameters that are identified as having associated markers are marked as associated monitoring parameter sets. Each associated monitoring parameter set includes only two monitoring parameters. The historical operating data associated with the corresponding monitoring parameter is identified from the historical operating data associated with the corresponding monitoring parameter set. Based on the identified historical operational data, the control nodes corresponding to the monitoring parameters in the associated monitoring parameter set are confirmed, thereby identifying the numerical control segments belonging to the corresponding monitoring parameters. The control time associated with the numerical control segment is recorded as the numerical control time. In the control data of another set of monitoring parameters, the parameter data associated with the corresponding numerical control time is confirmed. The confirmed parameter data segments are recorded as the subordinate data segments of this numerical control segment, and the numerical control segments and subordinate data segments are processed as follows: Confirm the change characteristic value T1 of adjacent time intervals in the numerical control segment, and then confirm the change characteristic value T2 of the same time interval in the auxiliary data segment. Use BH=T1÷T2 to confirm the corresponding change value BH, and record it as trend characteristics (T1, BH). Record several sets of trend characteristics associated with the associated monitoring parameters in sequence. Step 2: Identify the monitoring parameters that need to be regulated, identify the regulation characteristics, select the best regulation trend from the trend characteristics associated with these monitoring parameters, and simultaneously identify the characteristic range associated with the best regulation trend. Step 3: Based on the selected optimal control trend and characteristic range, limit the parameters of the numerical control process between the associated monitoring parameters to complete the multimodal real-time control process between the associated monitoring parameters.

2. The multimodal real-time control method for a new type of power system according to claim 1, characterized in that, In step two, the specific method for selecting the optimal control trend is as follows: Based on the confirmed control characteristics, which include the value to be adjusted and the specific time of control, the parameter associated with the current corresponding monitoring parameter is denoted as CS, the value to be adjusted in the control characteristics is denoted as DS, and the specific time for control is denoted as Ts. The difference value to be adjusted, Cz, is confirmed using the formula: Cz = DS - CS, and the minimum trend value, Dq, is confirmed using the formula: Cz ÷ Ts = Dq. Based on the confirmed minimum trend value Dq, if Dq > 0, then from the recorded trend characteristics, the trend characteristics with a value greater than Dq are recorded as candidate trends; if Dq < 0, the trend characteristics with a value less than Dq are recorded as candidate trends. From the trend characteristics associated with different candidate trends, the variance of several sets of change values ​​BH associated with a single candidate trend is processed to confirm the variance characteristics associated with the corresponding candidate trend. Based on the different variance characteristics associated with different candidate trends, the minimum value is selected, and the candidate trend associated with the minimum value is taken as the best control trend.

3. The multimodal real-time control method for a new type of power system according to claim 2, characterized in that, In step two, the specific method for confirming the feature interval is as follows: Based on the confirmed optimal control trend, the multiple sets of change values ​​BH associated with this optimal control trend are confirmed, and the minimum and maximum values ​​associated with the corresponding change values ​​BH are locked in, thus confirming the characteristic range associated with this optimal control trend.

4. The multimodal real-time control method for a new type of power system according to claim 1, characterized in that, In step three, the specific method for limiting the numerical control process between the associated monitoring parameters is as follows: Based on the determined optimal control trend, the value change of the monitoring parameter to be adjusted is controlled within a unit time. The monitoring parameter to be adjusted is the monitoring parameter that needs to be controlled by parameter limitation. Based on the determined characteristic interval, another set of monitoring parameters within the associated monitoring parameter set is identified. This other set of monitoring parameters is recorded as the auxiliary monitoring parameters. The numerical values ​​of the auxiliary monitoring parameters are synchronously adjusted, and the value adjusted per unit time is the minimum value of the characteristic interval. Monitor the parameter changes of the auxiliary monitoring parameters at the specific time of regulation, identify the unit change value of adjacent time, propose the parameter monitored at the previous time within the adjacent time and record it as J1, propose the parameter monitored at the next time and record it as J2, and adopt: unit change value = J2 - J1; If the unit change value is not equal to 0, then confirm whether the change trends of the auxiliary monitoring parameter and the monitoring parameter to be adjusted are consistent during the same period. If they are consistent, then increase the original selected control value of the auxiliary monitoring parameter until the unit change value is 0. If they are inconsistent, then decrease the original selected control value of the auxiliary monitoring parameter until the unit change value is 0. In the specific numerical control process of the monitoring parameter to be adjusted, the control logic determined above is used to control the values ​​associated with the auxiliary monitoring parameters in real time.

5. The multimodal real-time control method for a novel power system according to claim 4, characterized in that, If the unit change value is 0, then the original selected control value of the auxiliary monitoring parameter remains unchanged.

6. The multimodal real-time control method for a novel power system according to claim 4, characterized in that, Also includes: Step 4: Assess the abnormality of parameter changes within a specific time period, identify any abnormalities in the control process, and confirm the abnormal control signals based on the identified abnormalities.

7. A multimodal real-time control method for a novel power system according to claim 6, characterized in that, In step four, the specific method for confirming the abnormal control signal is as follows: Confirm several sets of unit variable values ​​associated with the auxiliary monitoring parameters within a specific time period of regulation. Select |BZ|max from the confirmed sets of unit variable values ​​BZ and record it as the characteristic value to be verified. Then confirm the optimal control trend associated with the monitoring parameter to be adjusted within the specific control time period, and simultaneously determine the minimum value of the characteristic interval. The evaluation value is calculated as: optimal control trend ÷ minimum value of characteristic interval. If the |evaluation value| is greater than or equal to the feature value to be verified, no processing is required; otherwise, an abnormal control signal is generated and displayed.

8. A multimodal real-time control system for novel power systems, wherein the control system operates based on the multimodal real-time control method for novel power systems according to any one of claims 1-7, characterized in that, include: The trend feature recording end identifies multiple monitoring parameters with data correlation within the power system, confirms the trend features between the correlated monitoring parameters from historical operating data, and records them sequentially. The optimal trend confirmation end identifies the monitoring parameters that need to be regulated, confirms the regulation characteristics, selects the optimal regulation trend from the trend characteristics associated with these monitoring parameters, and simultaneously confirms the characteristic range associated with the optimal regulation trend. The real-time control processing end, based on the selected optimal control trend and characteristic range, limits the numerical control process between the associated monitoring parameters and completes the multimodal real-time control process between the associated monitoring parameters. The parameter early warning terminal assesses the abnormal changes in parameters within a specific time period, identifies any abnormalities in the control process, and displays the control abnormality signals in real time based on the identified abnormalities.

Images