Safety and energy efficiency monitoring system for station power utilization system based on multi-source information fusion

Abstract

The invention relates to the technical field of power monitoring, in particular to a station power utilization system safety and energy efficiency monitoring system based on multi-source information fusion, which comprises a signal analysis module, an anomaly identification module, a risk assessment module and an emergency response module. According to the method, the fineness and the response speed of power station monitoring are improved by integrating wavelet transformation and information entropy analysis, the time-frequency characteristics of signals are deeply analyzed through wavelet transformation, the capturing capacity for short-term and long-term changes is improved, the integrity and the accuracy of data analysis are further ensured, and the accuracy of power station monitoring is improved. The information entropy is introduced to assess the stability and uncertainty of the power station, a scientific basis is provided for predicting and recognizing potential risks of the system, and by combining real-time anomaly recognition and dynamic risk assessment, equipment faults and system failures can be effectively predicted, and energy consumption is optimized, so that early warning and prevention and control are performed in advance, the downtime is remarkably shortened, and the system reliability is improved. The maintenance cost is reduced, and the level and effect of energy efficiency management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power monitoring, and in particular to a station power system safety energy efficiency monitoring system based on multi-source information fusion. Background Art

[0002] The field of power monitoring technology involves the use of various sensors, instruments and systems to collect, analyze and report the operating data of the power system in real time, including the monitoring of voltage, current, power, frequency and other electrical parameters, aiming to ensure the efficient, reliable and safe operation of the power system, integrating advanced data analysis tools, artificial intelligence and machine learning algorithms to predict equipment failures and system failures, so as to take preventive measures in advance. Power monitoring technology also includes energy efficiency assessment to help organizations reduce energy costs, optimize energy consumption and support sustainable development.

[0003] Among them, the power system safety and energy efficiency monitoring system is a system specially designed to monitor the power usage in the power station. Its main purpose is to ensure the safety of power usage and improve energy efficiency. By integrating multi-source information and adopting advanced analysis technology, it can monitor and evaluate the energy consumption and efficiency of the power station in real time, predict potential power system failures, and thus reduce downtime and maintenance costs. In addition, the system can also help managers develop more effective energy usage strategies and optimize equipment operation to achieve the goal of energy conservation and emission reduction. It is of great significance to improve the operational efficiency and environmental responsibility of power stations, and is an indispensable part of modern power management.

[0004] Although existing technologies have basic functions in power monitoring and fault prediction, they are obviously insufficient in efficiently processing large-scale real-time data and carefully identifying complex fault modes. Conventional monitoring methods cannot meet the rapidly changing power demand in terms of data processing and update frequency, and the response speed is slow, which makes it easy to miss critical warning moments. In addition, existing technologies are also limited in the accuracy of comprehensive analysis and risk prediction. There is a lack of effective system stability and risk status assessment tools, making it difficult to conduct in-depth performance optimization and risk management, limiting the potential for improving the safety and energy efficiency of the power system. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a station power system safety energy efficiency monitoring system based on multi-source information fusion.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solution: A station power system safety energy efficiency monitoring system based on multi-source information fusion includes: The signal analysis module collects the power consumption data, voltage and current values ​​of the power station, decomposes the signal through wavelet transform, analyzes the time-frequency characteristics, evaluates the power quality and equipment efficiency based on the analysis results, integrates the performance indicators of the power station equipment, and generates power station performance evaluation data; The abnormality identification module compares the real-time data with the historical performance benchmark based on the power station performance evaluation data, identifies abnormal data points that deviate from the normal operating mode, analyzes the energy efficiency loss of the power station according to the abnormal data point identification results, reveals potential safety hazards and records abnormal patterns, and generates abnormal pattern identification results; The risk assessment module calculates the information entropy of current and voltage based on the abnormal pattern recognition results, evaluates the instability of the power station, constructs an interdependent network between key equipment and components of the power station according to the evaluation results, updates the conditional probability of the nodes to reflect the current risk status, and generates a dynamic safety risk assessment result; The emergency response module quantifies and grades the risk level according to the dynamic safety risk assessment result, initiates the emergency response strategy, adjusts the load of the power station and isolates the fault area, and generates an emergency operation execution record of the power station.

[0007] As a further solution of the present invention, the analysis step of the time-frequency characteristics is: Collect the real-time values ​​of power consumption, voltage and current of the power station, reflect the operation status of the power station, and obtain the original power operation data; Based on the original power operation data, using wavelet transform to perform signal processing, separate and identify the frequency components of the signal on the difference time scale, and obtain a decomposed signal; The decomposed signal is subjected to feature analysis to reveal the time series information and frequency distribution in the signal and generate a time-frequency analysis result.

[0008] As a further solution of the present invention, the step of acquiring the power station performance evaluation data is: Based on the time-frequency analysis results, the power quality of the power station equipment is evaluated, the power fluctuation, frequency stability and harmonic distortion parameters of the equipment are measured, and the power quality evaluation result is obtained; Based on the power quality assessment results, combined with the historical operation data of the power station equipment, the long-term trend and short-term performance of the equipment efficiency are analyzed, the potential factors of equipment performance degradation are identified, and the equipment efficiency analysis results are obtained; Based on the power quality assessment results and equipment efficiency analysis results, combined with the independent performance of the equipment and its contribution to the overall performance of the power station, the performance indicators of all key equipment in the power station are integrated to generate power station performance assessment data.

[0009] As a further solution of the present invention, the step of identifying abnormal data points is: Based on the power plant performance evaluation data, integrating the real-time monitoring data, extracting the real-time data and historical data pairs of each monitoring point, and generating a comprehensive data set; Based on the comprehensive data set, a differential analysis is performed on each data pair using the formula, ; Calculate the deviation percentage for each data point , generate deviation analysis results, where Represents real-time data value, Represents historical performance benchmark values; According to the deviation analysis results, set the abnormal threshold , for comparison, if , then it is determined to be an abnormal data point, and a list of abnormal data points is screened and output.

[0010] As a further solution of the present invention, the step of obtaining the abnormal pattern recognition result is: Calling the abnormal data point list, classifying each abnormal data point, assigning it to a corresponding device group, performing refinement processing based on the duration and deviation degree of the abnormal point, and obtaining a classified abnormal data point list; Based on the classified list of abnormal data points, the formula is used: ; Calculate the loss of power station energy efficiency caused by each abnormal point , generate energy efficiency loss results, where is the normal power output value, is the abnormal power output value, is the duration of the abnormal point, Indicates the number of outliers; Based on the energy efficiency loss results, combined with the equipment operation history data and safety standards, analyze the equipment aging and failure risks, evaluate the severity of safety hazards, record potential safety hazards, and generate abnormal pattern recognition results.

[0011] As a further solution of the present invention, the steps of evaluating the instability of the power station are: Based on the abnormal pattern recognition results, the data is analyzed, the actual description of the abnormal pattern is extracted and recorded, and the abnormal description content of the current and voltage data is generated; According to the abnormal description of current and voltage data, the formula is used: ; Calculating the information entropy of data , generate information entropy data of current and voltage, where The current or voltage is in an abnormal state The probability of Indicates the total number of abnormal states, is the base, the base of natural logarithm; The information entropy data of the current and voltage are used to analyze the instability of the power station system, and the risk level is evaluated by the level of the information entropy value to generate an instability evaluation result of the power station.

[0012] As a further solution of the present invention, the steps of obtaining the dynamic security risk assessment result are: Using the power station instability assessment results, identify key equipment and components in the power station system, construct a dependency relationship diagram between the equipment and components, and generate a network diagram of interdependence between key equipment and components in the power station; Based on the interdependence network diagram of the key equipment and components of the power station, the conditional probability of each node in the network is updated to reflect the risk level of the node in the current state, and an updated node failure probability is generated; Applying the updated node failure probability, the overall risk of the network is evaluated by simulating failure scenarios, using the formula, ; Calculate the total probability of at least one failure occurring in the entire network , generate dynamic security risk assessment results, where is the failure probability of the node after update, Indicates the total number of nodes.

[0013] As a further solution of the present invention, the steps for obtaining the emergency operation execution record of the power station are: Based on the dynamic security risk assessment results, key risk indicators are analyzed and compared with real-time data in a standardized manner. The formula is used. ; Calculate the normalized risk level , get the quantitative risk level record, where, Represents the current detection parameter value, represents the long-term average, represents standard deviation; Determine the emergency response level based on the quantitative risk level records, perform load adjustment and fault area isolation in combination with the operation manual and emergency cases, and formulate an emergency response strategy execution plan; Implement the emergency response strategy execution plan, monitor key operating indicators and system responses, record all key operations and system changes, and obtain the power station emergency operation execution record.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by integrating wavelet transform and information entropy analysis, the meticulousness and response speed of power station monitoring are improved. Wavelet transform enables in-depth analysis of the time-frequency characteristics of the signal, improves the ability to capture short-term and long-term changes, and further ensures the integrity and accuracy of data analysis. The introduction of information entropy evaluates the stability and uncertainty of the power station, providing a scientific basis for predicting and identifying potential risks of the system. Combined with real-time anomaly recognition and dynamic risk assessment, it can effectively predict equipment failures and system failures, optimize energy consumption, thereby providing early warning and prevention and control, significantly reducing downtime, reducing maintenance costs, and improving the level and effect of energy efficiency management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a system flow chart of the present invention; Figure 2 It is a flow chart of the analysis of the time-frequency characteristics of the present invention; Figure 3 A flowchart for obtaining power plant performance evaluation data according to the present invention; Figure 4 is a flow chart for identifying abnormal data points of the present invention; Figure 5 The present invention is a flowchart for obtaining abnormal pattern recognition results; Figure 6 is a flow chart for evaluating the instability of a power station according to the present invention; Figure 7 A flowchart for obtaining dynamic security risk assessment results of the present invention; Figure 8 This is a flow chart for obtaining emergency operation execution records of a power station according to the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 The station power system safety and energy efficiency monitoring system based on multi-source information fusion includes: The signal analysis module collects the power consumption data, voltage and current values ​​of the power station, decomposes the signal through wavelet transform, analyzes the time-frequency characteristics, evaluates the power quality and equipment efficiency based on the analysis results, integrates the performance indicators of the power station equipment, and generates power station performance evaluation data; The anomaly identification module compares real-time data with historical performance benchmarks based on power station performance evaluation data, identifies abnormal data points that deviate from normal operating modes, analyzes power station energy efficiency losses based on abnormal data point identification results, reveals potential safety hazards, records abnormal patterns, and generates abnormal pattern identification results; The risk assessment module calculates the information entropy of current and voltage based on the abnormal pattern recognition results, evaluates the instability of the power station, builds the interdependence network between the key equipment and components of the power station according to the evaluation results, updates the conditional probability of the nodes to reflect the current risk status, and generates dynamic safety risk assessment results; The emergency response module quantifies and grades the risk level according to the dynamic safety risk assessment results, initiates the emergency response strategy, adjusts the power station load and isolates the fault area, and generates the power station emergency operation execution record.

[0019] The power station performance evaluation data includes power quality indicators, equipment efficiency indicators and power station equipment performance fluctuation charts. The abnormal pattern recognition results include energy efficiency loss records, safety hazard lists and abnormal event logs. The dynamic safety risk assessment results include risk dependency network diagrams, risk probability update records and instability rating results. The power station emergency operation execution records include load adjustment details, fault area isolation measures and emergency response timeliness.

[0020] See also Figure 2 , the analysis steps of time-frequency characteristics are: Collect the real-time values ​​of power consumption, voltage and current of the power station, reflect the operation status of the power station, and obtain the original power operation data; When collecting data in the real-time monitoring system of the power station, the real-time values ​​of the system's power consumption, voltage and current are accurately captured. The data collection process should include data verification and error detection mechanisms to ensure the reliability and accuracy of the data. After the data collection is completed, the original power data is transmitted through the data interface to facilitate subsequent processing and analysis. The data directly reflects the operation of the power station. Through a coherent data processing process, the quality and integrity of the data can be effectively obtained and ensured, laying a solid foundation for further data analysis and feature extraction, and obtaining the original power operation data.

[0021] Based on the original power operation data, the wavelet transform is used for signal processing to separate and identify the frequency components of the signal on the difference time scale to obtain the decomposed signal; When using wavelet transform technology to process raw power operation data, it is first necessary to select the appropriate wavelet basis function and decomposition level. The selection process is based on the frequency characteristics of the data and the noise level of the signal to maximize the extraction of effective signals. The execution of wavelet transform includes multi-level decomposition. Each level of decomposition refines the frequency bandwidth of the signal to separate short-term high-frequency and long-term low-frequency components. The decomposition results of each level must be verified to ensure that the integrity of the signal is not destroyed. After decomposition, the signal data is rearranged according to time and frequency attributes to facilitate the next step of feature analysis. Detailed decomposed signal data can be obtained, which effectively reveals the time and frequency information of the power data, thereby obtaining a decomposed signal.

[0022] Perform feature analysis on the decomposed signal to reveal the time series information and frequency distribution in the signal and generate time-frequency analysis results; Based on the decomposed signal, feature analysis is performed to reveal the energy distribution and time changes of each frequency band, and the signal is converted into a time-frequency distribution diagram. The image can intuitively observe how the frequency components of the signal change at different time points. This is particularly critical for identifying transient events and continuous performance changes in the power system. The statistical characteristics of the signal must also be taken into account during the analysis process in order to more accurately identify and interpret frequency characteristics, which can reveal the dynamic characteristics of the power system and provide a deep understanding of equipment performance and system stability, thereby generating time-frequency analysis results.

[0023] See also Figure 3 , the steps for obtaining power station performance evaluation data are: Based on the time-frequency analysis results, the power quality of the power plant equipment is evaluated, the power fluctuation, frequency stability and harmonic distortion parameters of the equipment are measured, and the power quality evaluation results are obtained; Based on the results of time-frequency analysis, we began to conduct a detailed assessment of the power quality of each device in the power station, read and processed a large amount of real-time monitoring data, and when analyzing the data, we first normalized the data to ensure that the statistical processing of the data would not affect the reliability of the results due to outliers or extreme data deviations. Then we calculated the power fluctuations of each device, using standard deviation and coefficient of variation to describe the volatility. Frequency stability was obtained through spectrum analysis, and harmonic distortion was quantified through the harmonic analysis module. Each step of data processing and calculation was strictly recorded for subsequent comparison and trend analysis to obtain accurate equipment power quality assessment results, ensuring the accuracy of the assessment and the continuity of operations.

[0024] Based on the power quality assessment results and combined with the historical operation data of power station equipment, the long-term trend and short-term performance of equipment efficiency are analyzed to identify potential factors of equipment performance degradation and obtain equipment efficiency analysis results; The power quality assessment results are combined with the historical performance data of the equipment for analysis. The current operating data of the equipment is compared with the historical records, especially the comparison of power fluctuations and efficiency changes. Statistical analysis tools such as variance analysis and regression models are used to reveal the changing trend of equipment performance and identify possible degradation factors, such as performance degradation caused by equipment aging or improper maintenance. Through comprehensive analysis, a detailed report on equipment efficiency can be obtained, which not only points out the current status of each device, but also predicts possible future trends, making equipment management more scientific and forward-looking, and providing data support for further maintenance and replacement decisions.

[0025] Comprehensive power quality assessment results and equipment efficiency analysis results, combined with the independent performance of the equipment and its contribution to the overall performance of the power station, integrate the performance indicators of all key equipment in the power station to generate power station performance evaluation data; Combining the analysis results of the first two steps, the comprehensive weighted scoring method is used to integrate the performance indicators of all key equipment in the power station. This evaluation model takes into account the individual performance of each device and its contribution to the system as a whole. First, the weight of each indicator is set. These weights are determined based on the operational importance and historical performance of the equipment. Then, the comprehensive performance score of each device is calculated by weighting. These scores are then summarized into the overall performance score of the power station. This process not only provides a quantitative performance evaluation result, but also allows managers to see the role and performance of each device in the overall system, making performance management more precise and targeted. The power station performance evaluation data finally generated provides a solid data foundation for the operation and optimization decision-making of the power station.

[0026] The comprehensive performance score is calculated using the formula: ; To calculate, in this formula, For the The overall performance score of the device. is the power factor of the device, For the efficiency of the equipment, is the failure rate of the equipment (the lower the failure rate, the better the performance). The indicators collected for a certain equipment are: power factor is 0.9, efficiency is 0.85, and failure rate is 0.1.

[0027] Substituting into the formula, we get: ; ; The results show that the comprehensive performance score of the device is 0.795, indicating that it performs well in the overall performance evaluation and can be used for further performance comparison and decision analysis.

[0028] See also Figure 4 , the steps for identifying abnormal data points are: Based on the power plant performance evaluation data, real-time monitoring data is integrated, and real-time data and historical data pairs of each monitoring point are extracted to generate a comprehensive data set; In the process of collecting power plant performance evaluation data and integrating real-time monitoring data, the original data is first collected through sensors installed at key locations of the power plant. The data includes but is not limited to physical parameters such as voltage, current, and power consumption, and the real-time data is summarized. At the same time, historical data is extracted from the database of the power plant management system, which includes past performance benchmark data sets. Each item of data undergoes preliminary quality control and screening to ensure the accuracy and reliability of the data. The real-time data is then matched with the historical data. A pair of real-time data and historical data for each monitoring point is formed. This pair of data will be used for subsequent analysis and comparison to generate a comprehensive data set, providing a basis for further analysis.

[0029] Based on the comprehensive data set, a difference analysis is performed on each data pair using the formula, ; Calculate the deviation percentage for each data point , generate deviation analysis results, where Represents real-time data value, Represents historical performance benchmark values; The real-time measurement value of a data point is 120 units, while the historical baseline value is 100 units. The calculation process is as follows: ; This shows that the real-time data is 20% higher than the historical benchmark, indicating that there is potential deviation from the normal operating mode at this monitoring point, and further investigation is needed into the possible causes and their impact on the operation of the power station.

[0030] According to the deviation analysis results, set the abnormal threshold , for comparison, if , then it is determined as an abnormal data point, and the abnormal data point list is screened and output; Setting anomaly thresholds In the process of screening abnormal data points by comparing whether the deviation percentage of each data point exceeds this threshold, firstly, a threshold is set according to the operation safety standards of the power station and past abnormality handling experience, for example, it is set to 10%, and then the deviation percentage calculated above is used as the With threshold For data points exceeding the threshold, they are marked as abnormal data points and recorded in the abnormal data list ( The above data points should be marked as abnormal data points, which will be used for subsequent detailed analysis and formulation of fault prevention measures to generate a list of abnormal data points.

[0031] See also Figure 5 , the steps to obtain the abnormal pattern recognition results are: Call the abnormal data point list, classify each abnormal data point, assign it to the corresponding equipment group, and perform detailed processing based on the duration and deviation degree of the abnormal point to obtain the classified abnormal data point list; To call the generated list of abnormal data points, you first need to obtain relevant monitoring data from each equipment module of the power station. The data should include the operating status of each device in different time periods and the records of abnormal points. Then, the abnormal points are classified according to the equipment type, such as generator sets, transformers, etc., and the abnormal points under each equipment category are further refined. The refinement is based on the degree of abnormal deviation of each data point and the duration of occurrence. The degree of data deviation is obtained by calculating the difference between the actual output power and the expected output power, and the duration is based on the abnormal duration record of the system. The obtained classification information of each abnormal point is stored in the data table, which is convenient for the subsequent calculation of energy efficiency loss and analysis of safety hazards.

[0032] Based on the classified list of abnormal data points, the formula is used: ; Calculate the loss of power station energy efficiency caused by each abnormal point , generate energy efficiency loss results, where is the normal power output value, is the abnormal power output value, is the duration of the abnormal point, Indicates the number of outliers; The normal power of a generator set is 2000MW, but when an abnormality occurs, the output power drops to 1800MW, and the abnormality lasts for 4 hours. The energy efficiency loss is calculated as follows: ; Calculations show that the abnormal point caused a total energy efficiency loss of 800MW hours within 4 hours. This value represents the power generation lost by the power station due to equipment abnormality, which means that further measures need to be taken to resolve these energy efficiency loss points in order to restore normal operation of the system.

[0033] Based on the energy efficiency loss results, combined with the equipment operation history data and safety standards, analyze the equipment aging and failure risks, evaluate the severity of safety hazards, record potential safety hazards, and generate abnormal pattern recognition results; The energy efficiency loss results are called up, combined with the equipment operation history data and the maintenance records of the power equipment. By comparing the equipment's energy efficiency loss with its historical operating efficiency change trend, it is determined whether the equipment has wear, aging or potential failure risks. Specific operations include issuing equipment early warnings when the energy efficiency loss exceeds a certain threshold, or when the historical operating efficiency shows a long-term downward trend, further analyzing the degree of equipment wear, recording possible equipment problems and their hidden dangers, and then organizing and archiving potential safety hazards to form detailed abnormal pattern analysis results, including equipment classification, energy efficiency loss analysis, safety hazard records and other information, which are used for power station maintenance decision-making and further optimization of equipment monitoring systems.

[0034] See also Figure 6 , the evaluation steps of the power station instability situation are: Based on the abnormal pattern recognition results, the data is analyzed, the actual description of the abnormal pattern is extracted and recorded, and the abnormal description content of the current and voltage data is generated; After calling the abnormal pattern recognition results from the power system monitoring, the machine learning algorithm is used to conduct in-depth analysis of the data in order to extract abnormal current and voltage waveforms from a large amount of monitoring data. Specific operations include data preprocessing, such as filtering and denoising, to clearly identify possible abnormal points; then, cluster analysis methods are used to classify abnormal waveforms, identify frequently occurring abnormal types and occasional abnormal events, and generate more detailed abnormal pattern descriptions of current and voltage data. In this process, the potential impact of various abnormal patterns on system stability will also be evaluated. For example, excessive voltage fluctuations may cause equipment damage or system power instability. This information will be used for further risk assessment and the formulation of preventive measures to ensure the reliability of the power station system and the stability of continuous operation.

[0035] According to the abnormal description of current and voltage data, the formula is used. ; Calculating the information entropy of data , generate information entropy data of current and voltage, where The current or voltage is in an abnormal state The probability of Indicates the total number of abnormal states, is the base, the base of natural logarithm; There are five abnormal states of the monitored current, and the probability of occurrence of each state is 0.1, 0.2, 0.3, 0.2, and 0.2. The base of natural logarithm , the parameters in the formula is the probability of each state, which is calculated as follows: ; ; Calculate each item specifically: ; ; ; ; ; Add up to get information entropy: ; The calculated information entropy is 1.5569, which indicates that the power system exhibits a moderate level of uncertainty and instability within the current monitoring window. The large value indicates that the system state changes frequently, requiring further monitoring and possible intervention measures to reduce risks.

[0036] The information entropy data of current and voltage are used to analyze the instability of the power station system, and the risk level is evaluated by the high and low information entropy values ​​to generate the instability assessment results of the power station; The information entropy of the calculated current and voltage is used to conduct an in-depth analysis of the instability of the power station system. The risk level of the system is assessed by the quantitative information entropy value. A high information entropy value usually indicates that the state of the system is highly uncertain and there may be a greater risk of instability. By comparing with historical data, the changing trend of information entropy is analyzed to identify possible sources of risk, such as equipment aging, operating errors, or external environmental influences. In addition, the analysis results will directly affect the risk management and decision-making of the power station, and provide data support for the formulation of response measures and prevention strategies. During the analysis process, the deviation between real-time data and historical patterns will also be taken into account in order to accurately assess the current system status and potential risk levels, and finally generate an assessment result of the instability of the power station, providing a scientific basis for the safe and stable operation of the power system.

[0037] See also Figure 7 ,The steps to obtain the dynamic security risk assessment results are: Using the power station instability assessment results, identify the key equipment and components in the power station system, build a dependency diagram between the equipment and components, and generate a network diagram of the interdependence of key equipment and components in the power station; Using the results of the power station instability assessment, the key equipment and components in the system are identified. By constructing a dependency graph, the relationships between the equipment and components are clarified, and key nodes are extracted. Based on the historical fault records of the equipment and combined with real-time monitoring data, the equipment status is analyzed, the importance weights are determined, and finally an interdependent network graph is generated, which provides a basis for subsequent analysis. The construction of the dependency graph includes graphically representing the connection and dependency of each device, considering the communication and control relationship between devices, ensuring data integrity and accuracy, gradually improving the connection information of each node in the graph, and confirming the role of each device in the overall system. The interdependent network graph finally generated provides an important basis for subsequent risk assessment.

[0038] Based on the interdependent network diagram of key equipment and components in the power station, the conditional probability of each node in the network is updated to reflect the risk level of the node in the current state and generate an updated node failure probability; Based on the interdependent network diagram, the failure probability of the node is updated. First, the operating data of each device is collected, including failure history, maintenance records and real-time monitoring data. By analyzing the data, the conditional probability of each node is calculated to form a probability matrix. The risk level of each device in the current state is clarified. The historical failure data is used, combined with the performance of the device under different operating conditions, to adjust the parameters to reflect the mutual influence between devices and ensure the accuracy of the node failure probability. Finally, an updated failure probability data set is generated to provide reliable basic data for subsequent dynamic risk assessment.

[0039] According to the formula: ; Calculate the conditional probability of a node ,in For equipment The number of failures, For equipment The failure data of equipment A, B, C, D, and E are as follows: Equipment A failed 3 times, with a total running time of 1,000 hours, Equipment B failed 5 times, with a total running time of 2,000 hours, Equipment C failed 2 times, with a total running time of 1,500 hours, Equipment D failed 1 time, with a total running time of 500 hours, and Equipment E failed 4 times, with a total running time of 3,000 hours.

[0040] The calculation is as follows: For device A: ; For device B: ; For device C: ; For device D: ; For device E: ; In summary, the failure probability of each device is: ; ; ; ; ; It will be used for subsequent dynamic risk assessment and provide a basis for quantitative analysis of equipment status.

[0041] Apply the updated node failure probability and evaluate the overall risk of the network by simulating failure scenarios. Using the formula, ; Calculate the total probability of at least one failure occurring in the entire network , generate dynamic security risk assessment results, where is the failure probability of the node after update, Indicates the total number of nodes; At a certain evaluation time, there are 5 nodes in the network, namely devices A1, B1, C1, D1, and E1, and their failure probabilities are 0.1, 0.2, 0.15, 0.05, and 0.3 respectively. The probability of no failure of each node is calculated by the formula: ; ; ; ; ; Multiply the probabilities of no failure: ; Substituting into the formula, calculate the total probability of at least one failure: ; The results show that the probability that at least one node in the network fails is , which means that the power station faces a higher safety risk and needs to take corresponding emergency measures.

[0042] See also Figure 8 , the steps for obtaining the emergency operation execution record of the power station are: Based on the dynamic security risk assessment results, key risk indicators are analyzed and compared with real-time data in a standardized manner. ; Calculate the normalized risk level , get the quantitative risk level record, where, Represents the current detection parameter value, represents the long-term average, represents standard deviation; ; The current data collected in the past 30 days is: 85, 88, 92, 90, 93, 91, 89, 87, 90, 91, 90, 95, 92, 88, 89, 90, 94, 91, 89, 90, 88, 92, 90, 91, 89, 90, 92, 93, 90, 91, 92. The total is 2702A, so: ; calculate : ; By placing each and Add the squares of the differences and divide by the number of data points , the calculated standard deviation is 5A (the calculation process is omitted).

[0043] Current , substitute into the formula to calculate: ; The results show that the risk level It is 1.986, indicating that the risk of the current power system has increased significantly compared with the historical average, indicating that corresponding risk management measures need to be taken.

[0044] Determine the emergency response level based on the quantitative risk level records, perform load adjustment and fault area isolation in combination with the operation manual and emergency cases, and formulate an emergency response strategy execution plan; Based on the quantitative risk level records, the emergency response level is determined. According to the operation manual and historical emergency cases, specific emergency response strategies are formulated for different risk levels. First, the correlation between the risk level specified in the report and the past accident response is analyzed, and the deviation between the current parameters and the historical average parameters is compared to establish the priority of emergency measures. According to the actual operation needs, the load adjustment plan and fault isolation strategy of the power station are designed, and the steps and expected goals of each operation are planned in detail to ensure that each measure can specifically alleviate or block the path of risk diffusion, focus on isolating high-risk areas, and optimize and adjust the core loads. Finally, a specific and feasible emergency response strategy execution plan is formulated, which directly affects the stable operation of the power system and the speed of fault recovery.

[0045] Implement emergency response strategy execution plan, monitor key operating indicators and system response, record all key operations and system changes, and obtain emergency operation execution records of power stations; According to the emergency response strategy execution plan, specific operations are implemented, including necessary load adjustments and fault area isolation of the power station. First, monitoring equipment is deployed to capture key parameters before and after the adjustment, such as voltage, current, etc., in real time to ensure accurate data recording during the operation. Then load adjustment is performed. According to the risk level and regional characteristics, resources are accurately allocated to optimize power distribution and reduce the overall pressure on the system. At the same time, fault area isolation is performed to quickly identify and isolate the source of the fault to avoid the spread of risks. All key operating steps and system responses are recorded to ensure the stability of the power system. Finally, detailed emergency operation execution records of the power station are generated. The records will be used for subsequent system evaluation and continuous improvement plans to ensure that all measures can be effectively implemented and enhance the system's risk resistance.

[0046] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. The station power system safety and energy efficiency monitoring system based on multi-source information fusion is characterized by: The system comprises: The signal analysis module collects the power consumption data, voltage and current values ​​of the power station, decomposes the signal through wavelet transform, analyzes the time-frequency characteristics, evaluates the power quality and equipment efficiency based on the analysis results, integrates the performance indicators of the power station equipment, and generates power station performance evaluation data; The abnormality identification module compares the real-time data with the historical performance benchmark based on the power station performance evaluation data, identifies abnormal data points that deviate from the normal operating mode, analyzes the energy efficiency loss of the power station according to the abnormal data point identification results, reveals potential safety hazards and records abnormal patterns, and generates abnormal pattern identification results; The risk assessment module calculates the information entropy of current and voltage based on the abnormal pattern recognition results, evaluates the instability of the power station, constructs an interdependent network between key equipment and components of the power station according to the evaluation results, updates the conditional probability of the nodes to reflect the current risk status, and generates a dynamic safety risk assessment result; The emergency response module quantifies and grades the risk level according to the dynamic safety risk assessment result, initiates the emergency response strategy, adjusts the load of the power station and isolates the fault area, and generates an emergency operation execution record of the power station.

2. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 1 is characterized by: The analysis steps of the time-frequency characteristics are: Collect the real-time values ​​of power consumption, voltage and current of the power station, reflect the operation status of the power station, and obtain the original power operation data; Based on the original power operation data, using wavelet transform to perform signal processing, separate and identify the frequency components of the signal on the difference time scale, and obtain a decomposed signal; The decomposed signal is subjected to feature analysis to reveal the time series information and frequency distribution in the signal and generate a time-frequency analysis result.

3. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 2 is characterized by: The steps for obtaining the power station performance evaluation data are as follows: Based on the time-frequency analysis results, the power quality of the power station equipment is evaluated, the power fluctuation, frequency stability and harmonic distortion parameters of the equipment are measured, and the power quality evaluation result is obtained; Based on the power quality assessment results, combined with the historical operation data of the power station equipment, the long-term trend and short-term performance of the equipment efficiency are analyzed, the potential factors of equipment performance degradation are identified, and the equipment efficiency analysis results are obtained; Based on the power quality assessment results and equipment efficiency analysis results, combined with the independent performance of the equipment and its contribution to the overall performance of the power station, the performance indicators of all key equipment in the power station are integrated to generate power station performance assessment data.

4. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 3 is characterized by: The steps for identifying abnormal data points are: Based on the power plant performance evaluation data, integrating the real-time monitoring data, extracting the real-time data and historical data pairs of each monitoring point, and generating a comprehensive data set; Based on the comprehensive data set, a differential analysis is performed on each data pair using the formula, ; Calculate the deviation percentage for each data point , generate deviation analysis results, where Represents real-time data value, Represents historical performance benchmark values; According to the deviation analysis results, set the abnormal threshold , for comparison, if , then it is determined to be an abnormal data point, and a list of abnormal data points is screened and output.

5. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 4 is characterized by: The steps for obtaining the abnormal pattern recognition result are: Calling the abnormal data point list, classifying each abnormal data point, assigning it to a corresponding device group, performing refinement processing based on the duration and deviation degree of the abnormal point, and obtaining a classified abnormal data point list; Based on the classified list of abnormal data points, the formula is used: ; Calculate the loss of power station energy efficiency caused by each abnormal point , generate energy efficiency loss results, where is the normal power output value, is the abnormal power output value, is the duration of the abnormal point, Indicates the number of outliers; Based on the energy efficiency loss results, combined with the equipment operation history data and safety standards, analyze the equipment aging and failure risks, evaluate the severity of safety hazards, record potential safety hazards, and generate abnormal pattern recognition results.

6. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 5 is characterized by: The steps for evaluating the instability of the power station are: Based on the abnormal pattern recognition results, the data is analyzed, the actual description of the abnormal pattern is extracted and recorded, and abnormal description content of current and voltage data is generated; According to the abnormal description of current and voltage data, the formula is used: ; Calculating the information entropy of data , generate information entropy data of current and voltage, where The current or voltage is in an abnormal state The probability of Indicates the total number of abnormal states, is the base, the base of natural logarithm; The information entropy data of the current and voltage are used to analyze the instability of the power station system, and the risk level is evaluated by the level of the information entropy value to generate an instability evaluation result of the power station.

7. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 6 is characterized by: The steps for obtaining the dynamic security risk assessment results are: Using the power station instability assessment results, identify key equipment and components in the power station system, construct a dependency relationship diagram between the equipment and components, and generate a network diagram of interdependence between key equipment and components in the power station; Based on the interdependence network diagram of the key equipment and components of the power station, the conditional probability of each node in the network is updated to reflect the risk level of the node in the current state, and an updated node failure probability is generated; Applying the updated node failure probability, the overall risk of the network is evaluated by simulating failure scenarios, using the formula, ; Calculate the total probability of at least one failure occurring in the entire network , generate dynamic security risk assessment results, where is the failure probability of the node after update, Indicates the total number of nodes.

8. The station power system safety energy efficiency monitoring system based on multi-source information fusion according to claim 7 is characterized by: The steps for obtaining the emergency operation execution record of the power station are: Based on the dynamic security risk assessment results, key risk indicators are analyzed and compared with real-time data in a standardized manner. The formula is used. ; Calculate the normalized risk level , get the quantitative risk level record, where, Represents the current detection parameter value, represents the long-term average, represents standard deviation; Determine the emergency response level based on the quantitative risk level records, perform load adjustment and fault area isolation in combination with the operation manual and emergency cases, and formulate an emergency response strategy execution plan; Implement the emergency response strategy execution plan, monitor key operating indicators and system responses, record all key operations and system changes, and obtain the power station emergency operation execution record.

Images