CN118428741A - Intelligent anti-misoperation processing method suitable for special operation and emergency operation - Google Patents

Abstract

The present invention discloses an intelligent error prevention processing method suitable for special operations and emergency operations, and relates to the technical field of intelligent error prevention processing. The method comprises the following steps: performing multimodal data fusion on monitoring data acquired by different types of sensors in a number of time periods, determining the weight assignment of the monitoring data in each time period, calculating the data fusion anomaly index, and judging the stability of the communication state of the sensor and the controller in an electromagnetic interference environment; performing a comprehensive analysis on the data fusion anomaly index and the stability of the communication state through fuzzy logic, evaluating the risk of the operation of the intelligent error prevention system, and performing corresponding early warning processing on different risk levels, thereby effectively improving the stability and reliability of the system in an electromagnetic interference environment, ensuring the safe operation of power equipment and the accuracy of emergency response, and thus preventing the risks of system failure, misleading operation and large-scale power outages.

Description

An intelligent error-proof processing method suitable for special operations and emergency operations

Technical Field

The present invention relates to the technical field of intelligent error prevention processing, and in particular to an intelligent error prevention processing method suitable for special operations and emergency operations.

Background technique

In the field of electric power, intelligent error prevention and control for special and emergency operations refers to the use of intelligent technology and system design to prevent the occurrence of misoperation and ensure the safety and reliability of operation through automated control, real-time monitoring and intelligent algorithms in complex or emergency situations, especially in emergencies such as power grid failures, equipment abnormalities or natural disasters. Provide accurate guidance and automated response to avoid human errors and further accidents. However, the intelligent error prevention and control system relies on a large number of electronic devices and sensors, which may be affected by electromagnetic interference under special circumstances. In extreme cases, large-scale electromagnetic interference may be triggered, causing the sensors and controllers of the intelligent error prevention system to fail or generate erroneous data. This situation will not only cause the system to fail to operate normally, but may also mislead operators and make incorrect emergency responses, ultimately causing damage to power equipment or large-scale power outages.

Summary of the invention

The purpose of the present invention is to provide an intelligent error-proof processing method suitable for special operations and emergency operations to solve the shortcomings of the background technology.

In order to achieve the above object, the present invention provides the following technical solution: an intelligent error-proof processing method suitable for special operations and emergency operations, comprising the following steps:

S1: Use multiple redundantly configured sensors to monitor the parameters of power equipment and operating environment in real time, and perform multimodal data fusion on the monitoring data obtained by different types of sensors in several time periods;

S2: Analyze the fused monitoring data, determine the weight assignment of the monitoring data in each time period, and calculate the data fusion anomaly index after weighted average calculation of the weight assignment of the monitoring data in each time period;

S3: Monitor the network communication between the sensor and the controller in real time to determine the stability of the communication status between the sensor and the controller in an electromagnetic interference environment;

S4: Comprehensively analyze the data fusion anomaly index and the stability of the communication status through fuzzy logic to evaluate the risk of the operation of the intelligent error prevention system;

S5: Based on the evaluation results, the risk of the intelligent error prevention system operation is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is carried out for different risk levels.

In a preferred embodiment, in S1, multimodal data is fused by principal component analysis, and the accuracy of the fused data is determined, specifically:

Standardize different types of sensor data, calculate the covariance matrix of the standardized data, calculate the eigenvalues and eigenvectors of the covariance matrix, sort them by eigenvalue size, select the eigenvectors corresponding to the first several eigenvalues as the principal components, project the standardized data onto the selected principal components to obtain the reduced-dimensional data, reconstruct the principal component data back to the original data space through inverse transformation, reversely project the reduced-dimensional data back to the original dimension to obtain the reconstructed data, calculate the error between the reconstructed data and the original data; compare the calculated reconstruction error with the reconstruction error threshold, if the reconstruction error is less than the reconstruction error threshold, mark the fused data as accurate data; if the reconstruction error is greater than or equal to the reconstruction error threshold, mark the fused data as inaccurate data.

In a preferred embodiment, in S2, the weight assignment of the monitoring data in each time period is determined according to the fusion status of the data fusion and the operating status of the sensor, including obtaining the data fusion fluctuation index to analyze the fusion status of the data fusion, and analyzing the operating status of the sensor through the stable value of the sensor's acquisition frequency.

In a preferred embodiment, the method for obtaining the data fusion fluctuation index is:

Acquire the monitoring data of the power equipment and the operating environment collected by the sensor in real time, perform weighted moving average calculation on it, determine the time window size n required to calculate the weighted moving average, determine the weight wi, and assign the weight wi to each time point in the time window;

Calculate the weighted moving average WMAt. For each time point t, calculate the weighted average of the time point and the previous n-1 time points. The specific calculation expression is: = ; In the formula, is the weighted moving average at time t, n is the size of the time window, that is, the number of time points required to calculate the average, wi is the weight of time t−i, It's time The data fusion volatility index is calculated by the absolute difference between the monitoring data and its weighted moving average. The specific calculation expression is: ; In the formula, is the data fusion volatility index, To monitor data in real time.

In a preferred embodiment, the method for acquiring the stable value of the acquisition frequency is:

Collect the data x(t) collected by the sensor within the time period s, record the timestamp of each collection, perform discrete Fourier transform on the time series data x(t), and convert the time domain signal to the frequency domain. ; Where X(k) is the frequency domain signal, x(n) is the time domain signal, N is the signal length, (k) is the frequency index, and j is a constant;

Calculate the spectrum P(k), P(k)= ; Where P(k) is the power spectrum density at frequency (k). Through spectrum analysis, the main frequency component f0 of the acquisition frequency and the frequency with the largest amplitude in the spectrum are identified, and the stable value of the acquisition frequency of the sensor is calculated. The specific calculation expression is: ; In the formula, is the stable value of the acquisition frequency.

In a preferred embodiment, the data fusion fluctuation index and the acquisition frequency stability value are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the weighted assignment labels of the monitoring data in each time period as the prediction target, and takes minimizing the sum of the prediction errors of the weighted assignment labels of the monitoring data in all time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weight assignment of the monitoring data in each time period is determined according to the model output results, and the data fusion anomaly index is calculated after the weighted average calculation of the weight assignment of the monitoring data in each time period.

In a preferred embodiment, by continuously monitoring and analyzing the data transmission quality and reliability between the sensor data and the controller, and by obtaining the signal interference index, the stability of the communication between the devices in the presence of electromagnetic interference is evaluated. The signal interference index is obtained as follows:

Collect the sampled data x(e) and expected signal d(e) of the sensor over a period of time, set the initial parameters of the adaptive filter, including the filter weight w(e) and the step size parameter μ, use the adaptive algorithm to filter the signal, and obtain the filtered output signal y(e). The specific calculation expression is: ; is the adaptive filter in time The weight at time , x(n−k) is the input signal at time −p is the sampling value, M is the order of the filter, and p is the time point;

Calculate the error m(e) between the filter output signal and the expected signal. The specific calculation expression is: m(e)= ; Analyze the error signal and calculate the signal interference index. The specific calculation expression is: ; In the formula, is the signal interference index, is the total number of data points.

In a preferred embodiment, the data fusion anomaly index and the stability of the communication state are comprehensively analyzed by fuzzy logic, specifically:

The data fusion anomaly index and signal interference index are used as input items, and the risk of the intelligent error prevention system operation is used as the output item;

Define a fuzzy set for each input variable, convert the actual values of the data fusion anomaly index and the signal interference index into fuzzy values, and define a membership function for each fuzzy set;

Input the actual data fusion anomaly index and signal interference index into the membership function to calculate its membership degree to each fuzzy set;

Formulate fuzzy rules to map the fuzzy values of input variables to the fuzzy outputs of risk assessment;

Apply fuzzy rules to input values using fuzzy reasoning methods to calculate fuzzy outputs for risk assessment;

According to the membership degree of the input variables, the corresponding fuzzy rules are activated;

Perform fuzzy operations on the activated rules to obtain the output fuzzy values of each rule, and convert the fuzzy reasoning results into specific risk assessment values.

In a preferred embodiment, the risk of the operation of the intelligent error prevention system is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is performed for different risk levels;

The acquired risk assessment value is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the risk assessment value is compared with the first standard threshold and the second standard threshold respectively;

If the risk assessment value is greater than the second standard threshold, the risk of the intelligent error prevention system operation is classified as high-risk operation, and a first-level warning signal is generated; if the risk assessment value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the risk of the intelligent error prevention system operation is classified as medium-risk operation, and a second-level warning signal is generated; if the risk assessment value is less than the first standard threshold, the risk of the intelligent error prevention system operation is classified as low-risk operation, and a third-level warning signal is generated.

In the above technical solution, the technical effects and advantages provided by the present invention are:

The present invention uses multiple redundant sensors to monitor the parameters of power equipment and operating environment in real time, and performs multimodal data fusion, combined with principal component analysis and weighted moving average calculation techniques to evaluate the accuracy and stability of the data. Based on real-time monitoring of the network communication status of sensors and controllers and acquisition of signal interference index, fuzzy logic is used to comprehensively analyze the data fusion anomaly index and signal interference index to accurately evaluate the risk of system operation. Corresponding warning signals are generated according to different risk levels to ensure the safety and reliability of the system in special operations and emergency operations;

The present invention uses advanced data processing and analysis technology to effectively deal with the uncertainty caused by electromagnetic interference and improve the system's anti-interference ability and data reliability. Through a multi-level early warning mechanism, potential risks can be identified and handled in a timely manner, the accuracy and efficiency of emergency response can be improved, and damage to power equipment and large-scale power outages can be avoided. Overall, the solution significantly enhances the stability and security of the intelligent anti-error processing system, ensuring the reliable operation of the power system in complex environments.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

FIG. 1 is a flow chart of the method of the present invention.

Detailed ways

In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Embodiment, please refer to FIG1, the embodiment of an intelligent error prevention method suitable for special operation and emergency operation, comprising the following steps:

S1: Use multiple redundantly configured sensors to monitor the parameters of power equipment and operating environment in real time, and perform multimodal data fusion on the monitoring data obtained by different types of sensors in several time periods;

S2: Analyze the fused monitoring data, determine the weight assignment of the monitoring data in each time period, and calculate the data fusion anomaly index after weighted average calculation of the weight assignment of the monitoring data in each time period;

S3: Monitor the network communication between the sensor and the controller in real time to determine the stability of the communication status between the sensor and the controller in an electromagnetic interference environment;

S4: Comprehensively analyze the data fusion anomaly index and the stability of the communication status through fuzzy logic to evaluate the risk of the operation of the intelligent error prevention system;

S5: Based on the evaluation results, the risk of the intelligent error prevention system operation is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is carried out for different risk levels.

Among them, in S1, multiple redundantly configured sensors are used to monitor the characteristic parameters of power equipment and operating environment in real time, and multi-modal data fusion is performed on the characteristic parameters obtained by different types of sensors in several time periods, specifically:

Deploy multiple types of sensors, including temperature sensors, current sensors, voltage sensors, vibration sensors, gas sensors, etc. at key locations of power equipment and operating environments.

These sensors are installed in a redundant configuration, that is, multiple sensors of each type are installed at the same monitoring point to ensure that when one sensor fails or is abnormal, the other sensors can still work normally and provide reliable monitoring data.

The sensors collect various parameters of power equipment and operating environment in real time, including equipment temperature, current, voltage, vibration frequency, ambient gas concentration, etc. The higher the collection frequency, the more subtle changes and emergencies in the operation of the power system can be captured.

Each sensor continuously collects data over several time periods. The data collected by the sensor in different time periods includes multiple dimensions and types, such as temperature, current and voltage data collected every minute within 10 minutes. Through the data recording and transmission system, these data are aggregated into a central processing unit or data processing center.

Preprocess the collected sensor data, including data cleaning, denoising, missing value filling, etc., to ensure the accuracy and integrity of the data. For redundantly configured sensor data, perform consistency checks, remove abnormal data points, and retain valid data. Integrate the data collected by different types of sensors in the same time period to form a multimodal data set. For example, combine the temperature, current, and voltage data in the same time period to form a comprehensive data point.

The multimodal data is fused through principal component analysis, and the accuracy of the fused data is determined. Specifically:

Standardize different types of sensor data to make them have the same dimension. This is done by subtracting the mean from each data point and dividing it by its standard deviation. Standardization ensures that the scales of different sensor data are consistent, making the PCA process more accurate.

Calculate the covariance matrix for the standardized data. The covariance matrix describes the linear correlation between different variables (i.e. different sensor data).

Calculate the eigenvalues and eigenvectors of the covariance matrix. The eigenvalues represent the variance of the data in the direction of the corresponding eigenvectors. Through these eigenvalues and eigenvectors, we can find the direction with the largest change and the most concentrated information in the data.

Sort by eigenvalues and select the eigenvectors corresponding to the first several eigenvalues as principal components. Usually, eigenvectors are selected that make the cumulative variance contribution rate reach a certain threshold (for example, 95%). The cumulative variance contribution rate indicates the proportion of the total variance of the data that can be explained by the selected principal component.

Project the standardized data onto the selected principal components to obtain the reduced-dimensional data. These principal components are linear combinations of the original data and contain most of the variation information in the original data. The reduced-dimensional data reduces the dimension but retains the main features of the data.

The principal component data is reconstructed back to the original data space through inverse transformation to evaluate data loss. The reduced-dimensional data is back-projected back to the original dimension to obtain the reconstructed data.

Calculate the error between the reconstructed data and the original data. Common error metrics include mean square error (MSE) or mean absolute error (MAE).

The calculated reconstruction error is compared with the reconstruction error threshold. If the reconstruction error is less than the reconstruction error threshold, it means that the data obtained after PCA fusion processing can well represent the original multimodal data, and the fused data is marked as accurate data; if the reconstruction error is greater than or equal to the reconstruction error threshold, it means that the data obtained after PCA fusion processing cannot well represent the original multimodal data, and the fused data is marked as inaccurate data. It may be necessary to adjust the number of principal components or improve the data preprocessing method to improve the accuracy of data fusion.

S2: Analyze the fused monitoring data, determine the weight assignment of the monitoring data in each time period, and calculate the data fusion anomaly index after performing weighted average calculation on the weight assignment of the monitoring data in each time period.

The fused monitoring data refers to a unified data set obtained by integrating the data of different types of sensors through the principal component analysis (PCA) method. These data reflect the status of power equipment and operating environment in different time periods.

Weight assignment is an assignment process based on the importance and credibility of each monitoring data in a specific time period. The weight assignment of monitoring data in each time period is determined based on the fusion status of data fusion and the operating status of the sensor, including obtaining the data fusion fluctuation index to analyze the fusion status of data fusion, and analyzing the operating status of the sensor through the stable value of the sensor's acquisition frequency.

Among them, the method for obtaining the data fusion volatility index is:

Acquire the monitoring data of the power equipment and operating environment collected by the sensor in real time, perform weighted moving average calculation on it, determine the time window size n required to calculate the weighted moving average, determine the weight wi, and assign weight wi to each time point in the time window. Usually, the sum of the weights is 1, and the weight of the closer time point is larger.

Calculate the weighted moving average WMAt. For each time point t, calculate the weighted average of the time point and the previous n-1 time points. The specific calculation expression is: = ; In the formula, is the weighted moving average at time t, n is the size of the time window, that is, the number of time points required to calculate the average, wi is the weight of time t−i, It's time The data fusion volatility index is calculated by the absolute difference between the monitoring data and its weighted moving average. The specific calculation expression is: ; In the formula, is the data fusion volatility index, To monitor data in real time.

Some sensors may be faulty or interfered with, resulting in large deviations in the data, which in turn causes fluctuations in the overall data. The power equipment or operating environment may have changed significantly, such as sudden failures, severe load fluctuations, or drastic changes in environmental conditions (such as temperature and humidity), causing abnormal fluctuations in sensor data. Unstable data acquisition frequency or delays and packet loss during data transmission may also increase the volatility of data fusion.

When the data fusion volatility index is large, the sensor data has a high volatility, indicating that the data is unstable. This instability may come from a variety of factors, including sensor failure, external interference, equipment abnormality, etc.

When the fluctuation index continues to be large, it indicates that there is an abnormality in the operation of the power system or equipment, which may lead to increased potential risks. It is necessary to promptly investigate and deal with the abnormal situation to avoid possible safety accidents.

Data with a large volatility index has a relatively low credibility. In this case, it may be necessary to further verify the data or adopt other data fusion and processing methods to improve the reliability of the data.

The method for obtaining the stable value of the acquisition frequency is:

Collect the data x(t) collected by the sensor within the time period s, record the timestamp of each collection, perform discrete Fourier transform on the time series data x(t), and convert the time domain signal to the frequency domain. DFT can be expressed as: ; Where X(k) is the frequency domain signal, x(n) is the time domain signal, and N is the signal length. is the frequency index, j is a constant;

Calculate the spectrum P(k), which represents the intensity of the frequency components of the signal. The spectrum can be obtained by taking the square of the modulus of the DFT result, P(k) = ; where P(k) is the frequency The power spectral density at is the modulus value of the DFT result;

Through spectrum analysis, the main frequency component f0 of the acquisition frequency and the frequency with the largest amplitude in the spectrum are identified, and the stable value of the acquisition frequency of the sensor is calculated. The specific calculation expression is: ; In the formula, is the stable value of the acquisition frequency.

A large acquisition frequency stability value indicates that the sensor's acquisition frequency is very uniform and the time interval between data points varies little. This stability ensures the consistency and continuity of the data and helps reduce errors caused by uneven acquisition frequency.

Data fusion relies on a continuous and uniform data stream provided by the sensors. A higher stable value of the acquisition frequency means that the time intervals between sensor data are uniform, which can improve the effectiveness of the data fusion algorithm and reduce the errors caused by inconsistent data acquisition intervals.

A high stable value of the acquisition frequency indicates that the sensor itself is reliable and in stable working condition. The sensor can continuously collect data at the predetermined time interval, reducing the fluctuation of the data acquisition frequency caused by hardware or software problems.

The data fusion fluctuation index and the stable value of the acquisition frequency are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the weighted assignment label of the monitoring data in each time period with each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the weighted assignment labels of the monitoring data in all time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weight assignment of the monitoring data in each time period is determined according to the output results of the model, and the data fusion anomaly index is calculated after the weighted average calculation of the weight assignment of the monitoring data in each time period.

The method for obtaining the weight assignment of the monitoring data in each time period is as follows: from the first feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, is the data fusion volatility index, is the stable value of the acquisition frequency, Assign weights to the monitoring data in each time period.

S3: Monitor the network communication between the sensor and the controller in real time to determine the stability of the communication status between the sensor and the controller in an electromagnetic interference environment.

By continuously monitoring and analyzing the data transmission quality and reliability between the sensor data and the controller, and obtaining the signal interference index, the stability of communication between devices in the presence of electromagnetic interference is evaluated. The signal interference index is obtained as follows:

Collect the sampled data x(e) and expected signal d(e) of the sensor over a period of time, set the initial parameters of the adaptive filter, including the filter weight w(e) and the step size parameter μ, use the adaptive algorithm to filter the signal, and obtain the filtered output signal y(e). The specific calculation expression is: ; is the adaptive filter in time The weight at , x(n-p) is the sample value of the input signal at time e-p, M is the order of the filter, and p is the time point;

Calculate the error m(e) between the filter output signal and the expected signal. The specific calculation expression is: m(e)= ; Analyze the error signal and calculate the signal interference index. The specific calculation expression is: ; In the formula, is the signal interference index, is the total number of data points.

The larger the signal interference index is, the larger the mean square value of the error signal is, that is, the more serious the interference to the communication between the sensor and the controller is.

The increase in the amplitude of the error signal indicates that the adaptive filter cannot effectively eliminate interference, and the difference between the filtered signal and the expected signal increases. A high interference index usually means that the electromagnetic interference intensity in the environment is large, affecting the quality and accuracy of data transmission.

Due to electromagnetic interference, data transmission between sensors and controllers becomes unstable, and there may be problems such as packet loss, increased transmission delays, and data errors. In a high-interference environment, the reliability of the communication system is significantly reduced, which may result in the failure to transmit critical data in a timely manner, thus affecting the overall performance and security of the system.

S4: Comprehensively analyze the data fusion anomaly index and the stability of the communication status through fuzzy logic to evaluate the risk of the operation of the intelligent error prevention system.

The data fusion anomaly index and signal interference index are used as input items, and the risk of the intelligent error prevention system operation is used as the output item;

Define fuzzy sets for each input variable, for example: Low, Medium, High.

Convert the actual values of the data fusion anomaly index and the signal interference index into fuzzy values. Define membership functions for each fuzzy set, such as triangular or trapezoidal functions. For the data fusion anomaly index, three fuzzy set membership functions can be defined:

Low: membership function μLow (data fusion anomaly index);

Medium: membership function μMedium (data fusion anomaly index);

High: membership function μHigh (data fusion anomaly index);

Similarly, the membership function is defined for the signal interference index:

Low: membership function μLow (signal interference index);

Medium: Membership function μMedium (signal interference index)

High: Membership function μHigh (signal interference index).

The actual data fusion anomaly index and signal interference index are input into the membership function to calculate its membership degree to each fuzzy set.

According to expert experience and system requirements, fuzzy rules are formulated to map the fuzzy values of input variables to the fuzzy output of risk assessment. The rule form is as follows:

If the data fusion anomaly index is Low and the signal interference index is Low, then the risk is Low;

If the data fusion anomaly index is Low and the signal interference index is Medium, then the risk is Medium;

If the data fusion anomaly index is High and the signal interference index is High, the risk is High.

Apply fuzzy rules to input values using fuzzy reasoning methods such as Mamdani fuzzy reasoning to calculate the fuzzy output of risk assessment.

According to the membership degree of the input variables, the corresponding fuzzy rules are activated.

Perform fuzzy operations on the activated rules (such as the minimum value method) to obtain the output fuzzy values of each rule. Convert the fuzzy reasoning results into specific risk assessment values.

S5: Based on the evaluation results, the risk of the intelligent error prevention system operation is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is carried out for different risk levels.

The acquired risk assessment value is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the risk assessment value is compared with the first standard threshold and the second standard threshold respectively;

If the risk assessment value is greater than the second standard threshold, the risk of the intelligent error prevention system operation is classified as high risk operation, and a first-level warning signal is generated; the emergency response procedure is initiated and the relevant operators and management are notified immediately. If a serious problem is found, consider shutting down or switching to the backup system to avoid accidents.

If the risk assessment value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the risk of the intelligent error prevention system operation is classified as medium risk operation, and a secondary warning signal is generated; the system monitoring frequency is increased, and the potential problem areas are monitored in particular. Technical personnel are arranged to conduct on-site inspections, assess risk factors, and make necessary adjustments and maintenance. Temporary measures are taken to reduce risks, such as adjusting operating parameters, switching partial loads, etc., to ensure that the system operates within a controllable range.

If the risk assessment value is less than the first standard threshold, the risk of the intelligent error prevention system operation is classified as low risk operation, and a third-level warning signal is generated. Perform routine inspections and maintenance to ensure the normal operation of all parts of the system. Record low-risk warning information for regular review and analysis. Continue to maintain normal monitoring and pay attention to changes in the system's operating status. Ensure that all sensors and controllers are operating normally and calibrate the equipment regularly.

It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and the importance of the second-level warning signal is greater than that of the third-level warning signal. Dividing the operation risk of the intelligent error prevention system into different levels of warning signals will help to take appropriate response measures according to the severity of the risk, ensure timely and efficient handling of potential problems, prevent accidents, improve the safety and reliability of the system, and optimize the allocation and management of resources.

In this embodiment, multiple redundantly configured sensors are used to monitor the parameters of power equipment and operating environment in real time, and the monitoring data obtained by different types of sensors in several time periods are fused into multimodal data; the fused monitoring data is analyzed to determine the weight assignment of the monitoring data in each time period, and the weight assignment of the monitoring data in each time period is weighted averaged to calculate the data fusion anomaly index; the network communication between the sensor and the controller is monitored in real time to determine the stability of the communication state of the sensor and the controller in the electromagnetic interference environment; the data fusion anomaly index and the stability of the communication state are comprehensively analyzed through fuzzy logic to evaluate the risk of the operation of the intelligent anti-error system; according to the evaluation results, the risk of the operation of the intelligent anti-error system is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is performed for different risk levels. The stability and reliability of the system in the electromagnetic interference environment are effectively improved, the safe operation of the power equipment and the accuracy of the emergency response are ensured, thereby preventing the risk of system failure, misleading operation and large-scale power outages.

The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

It should be understood that the term "and/or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character "/" in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and/or" relationship. Please refer to the context for specific understanding.

It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims (9)

1. An intelligent error-prevention method for special operations and emergency operations, characterized in that it includes the following steps: S1: Use multiple redundantly configured sensors to monitor the parameters of power equipment and operating environment in real time, and perform multimodal data fusion on the monitoring data obtained by different types of sensors in several time periods; S2: Analyze the fused monitoring data, determine the weight assignment of the monitoring data in each time period, and calculate the data fusion anomaly index after weighted average calculation of the weight assignment of the monitoring data in each time period; S3: Monitor the network communication between the sensor and the controller in real time to determine the stability of the communication status between the sensor and the controller in an electromagnetic interference environment; S4: Comprehensively analyze the data fusion anomaly index and the stability of the communication status through fuzzy logic to evaluate the risk of the operation of the intelligent error prevention system; S5: Based on the evaluation results, the risk of the intelligent error prevention system operation is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is carried out for different risk levels. 2. According to claim 1, an intelligent error prevention method for special operations and emergency operations is characterized in that: in S1, multimodal data is fused by principal component analysis, and the accuracy of the fused data is judged, specifically: Standardize different types of sensor data, calculate the covariance matrix of the standardized data, calculate the eigenvalues and eigenvectors of the covariance matrix, sort them by eigenvalue size, select the eigenvectors corresponding to the first several eigenvalues as the principal components, project the standardized data onto the selected principal components to obtain the reduced-dimensional data, reconstruct the principal component data back to the original data space through inverse transformation, reversely project the reduced-dimensional data back to the original dimension to obtain the reconstructed data, calculate the error between the reconstructed data and the original data; compare the calculated reconstruction error with the reconstruction error threshold, if the reconstruction error is less than the reconstruction error threshold, mark the fused data as accurate data; if the reconstruction error is greater than or equal to the reconstruction error threshold, mark the fused data as inaccurate data. 3. According to claim 2, an intelligent error-prevention processing method suitable for special operations and emergency operations is characterized in that: in S2, the weight assignment of the monitoring data in each time period is determined according to the fusion status of the data fusion and the operating status of the sensor, including obtaining the data fusion fluctuation index to analyze the fusion status of the data fusion, and analyzing the operating status of the sensor through the stable value of the sensor's acquisition frequency. 4. According to claim 3, an intelligent error prevention method for special operations and emergency operations, characterized in that: the method for obtaining the data fusion fluctuation index is: Acquire the monitoring data of the power equipment and the operating environment collected by the sensor in real time, perform weighted moving average calculation on it, determine the time window size n required to calculate the weighted moving average, determine the weight wi, and assign the weight wi to each time point in the time window; Calculate the weighted moving average WMAt. For each time point t, calculate the weighted average of the time point and the previous n-1 time points. The specific calculation expression is: = ; In the formula, is the weighted moving average at time t, n is the size of the time window, that is, the number of time points required to calculate the average, wi is the weight of time t−i, It's time The data fusion volatility index is calculated by the absolute difference between the monitoring data and its weighted moving average. The specific calculation expression is: ; In the formula, is the data fusion volatility index, To monitor data in real time. 5. According to claim 4, an intelligent error prevention method suitable for special operations and emergency operations is characterized in that: the acquisition method of the stable value of the acquisition frequency is: Collect the data x(t) collected by the sensor within the time period s, record the timestamp of each collection, perform discrete Fourier transform on the time series data x(t), and convert the time domain signal to the frequency domain. ; Where X(k) is the frequency domain signal, x(n) is the time domain signal, N is the signal length, (k) is the frequency index, and j is a constant; Calculate the spectrum P(k), P(k)= ; Where P(k) is the power spectrum density at frequency (k). Through spectrum analysis, the main frequency component f0 of the acquisition frequency and the frequency with the largest amplitude in the spectrum are identified, and the stable value of the acquisition frequency of the sensor is calculated. The specific calculation expression is: ; In the formula, is the stable value of the acquisition frequency. 6. According to claim 5, an intelligent error-prevention processing method suitable for special operations and emergency operations is characterized in that: the data fusion fluctuation index and the acquisition frequency stability value are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the weighted assignment label of the monitoring data in each time period as the prediction target, and minimizes the sum of the prediction errors of the weighted assignment labels of the monitoring data in all time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weight assignment of the monitoring data in each time period is determined according to the model output results, and the data fusion anomaly index is calculated after the weighted average calculation of the weight assignment of the monitoring data in each time period. 7. According to claim 6, an intelligent error prevention method for special operations and emergency operations is characterized in that: by continuously monitoring and analyzing the data transmission quality and reliability between the sensor data and the controller, by obtaining the signal interference index, the stability of communication between devices in the presence of electromagnetic interference is evaluated, and the method for obtaining the signal interference index is as follows: Collect the sampled data x(e) and expected signal d(e) of the sensor over a period of time, set the initial parameters of the adaptive filter, including the filter weight w(e) and the step size parameter μ, use the adaptive algorithm to filter the signal, and obtain the filtered output signal y(e). The specific calculation expression is: ; is the adaptive filter in time The weight at time , x(n−k) is the input signal at time −p is the sampling value, M is the order of the filter, and p is the time point; Calculate the error m(e) between the filter output signal and the expected signal. The specific calculation expression is: m(e)= ; Analyze the error signal and calculate the signal interference index. The specific calculation expression is: ; In the formula, is the signal interference index, is the total number of data points. 8. According to claim 7, an intelligent error prevention method for special operations and emergency operations is characterized in that: a comprehensive analysis of the data fusion abnormality index and the stability of the communication state is performed through fuzzy logic, specifically: The data fusion anomaly index and signal interference index are used as input items, and the risk of the intelligent error prevention system operation is used as the output item; Define a fuzzy set for each input variable, convert the actual values of the data fusion anomaly index and the signal interference index into fuzzy values, and define a membership function for each fuzzy set; Input the actual data fusion anomaly index and signal interference index into the membership function to calculate its membership degree to each fuzzy set; Formulate fuzzy rules to map the fuzzy values of input variables to the fuzzy outputs of risk assessment; Apply fuzzy rules to input values using fuzzy reasoning methods to calculate fuzzy outputs for risk assessment; According to the membership degree of the input variables, the corresponding fuzzy rules are activated; Perform fuzzy operations on the activated rules to obtain the output fuzzy values of each rule, and convert the fuzzy reasoning results into specific risk assessment values. 9. According to claim 8, an intelligent error prevention processing method suitable for special operations and emergency operations is characterized in that the risk of the operation of the intelligent error prevention system is divided into high-risk operation, medium-risk operation and low-risk operation, and corresponding early warning processing is performed for different risk levels; The acquired risk assessment value is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the risk assessment value is compared with the first standard threshold and the second standard threshold respectively; If the risk assessment value is greater than the second standard threshold, the risk of the intelligent error prevention system operation is classified as high-risk operation, and a first-level warning signal is generated; if the risk assessment value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the risk of the intelligent error prevention system operation is classified as medium-risk operation, and a second-level warning signal is generated; if the risk assessment value is less than the first standard threshold, the risk of the intelligent error prevention system operation is classified as low-risk operation, and a third-level warning signal is generated.