Power station safety monitoring method and system based on Internet of Things

Abstract

The invention provides a power station safety monitoring method and system based on the Internet of Things, and relates to the technical field of power monitoring, and the method comprises the steps: sensing various parameters of power station equipment in real time, including temperature, humidity, current and voltage; processing and analyzing various parameters of the power station equipment by using a cloud platform, and extracting state information and an operation mode of the power station equipment to obtain a cloud platform analysis result; according to the analysis result of the cloud platform, the decision process of remote control equipment operation is optimized by remotely accessing equipment state information and applying a hunting search algorithm for simulating the interaction relationship between natural hunters and preys, and meanwhile, equipment fault alarm is remotely received, so that remote monitoring of power station equipment is realized, and the power station equipment is remotely controlled. And potential fault risks are found and processed. Comprehensive monitoring and intelligent decision making of power station equipment are achieved, meanwhile, the hierarchical extension method is adopted to evaluate the information safety risk, and the safety and reliability of power station operation are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and particularly to a power station safety monitoring method and system based on the Internet of Things. Background Art

[0002] In the traditional power station safety monitoring system, although various parameters of the equipment can be collected in real time, there are deficiencies in data processing and analysis.

[0003] For example, the system may not be able to efficiently process a large amount of real-time data, resulting in data delay or loss; or the analysis algorithm is not accurate enough to accurately extract the status information and operation mode of the equipment. This may affect the accurate judgment of the equipment status and further affect the subsequent monitoring and control decisions.

[0004] In addition, when the power station safety monitoring system conducts remote monitoring and decision-making, it often relies on rules and thresholds set manually. However, this method may not be able to adapt to the complexity and variability of the operation of power station equipment.

[0005] For example, in some abnormal situations, the system may not be able to quickly make accurate control decisions based on real-time status information, or the decision-making process is too cumbersome, resulting in too long response time. This may affect the safe and stable operation of the power station and even cause serious consequences. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a power station safety monitoring method and system based on the Internet of Things to monitor the operation status of power station equipment in real time and accurately.

[0007] To solve the above technical problem, the technical solution of the present invention is as follows:

[0008] In the first aspect, a power station safety monitoring method based on the Internet of Things, the method includes:

[0009] Perceive various parameters of power station equipment in real time, including temperature, humidity, current and voltage;

[0010] Use the cloud platform to process and analyze various parameters of power station equipment, extract the status information and operation mode of power station equipment, and obtain the cloud platform analysis result;

[0011] According to the cloud platform analysis result, remotely access the equipment status information, and use the hunting search algorithm that simulates the interaction relationship between natural predators and prey to optimize the decision-making process of remotely controlling the equipment operation. At the same time, remotely receive equipment fault alarms, realize remote monitoring of power station equipment, and discover and handle potential fault risks;

[0012] Build a power station framework including a perception layer, a network layer, a platform layer, and an application layer. Among them, the perception layer collects various parameters of power station equipment, the network layer conducts data transmission, the platform layer conducts data processing and analysis services, and the application layer realizes remote monitoring and intelligent decision-making functions according to the analysis results of the cloud platform;

[0013] For the information security risks in the power station framework, use the hierarchical extension method for assessment and take corresponding security measures according to the assessment results.

[0014] Furthermore, use the cloud platform to process and analyze various parameters of power station equipment, extract the status information and operation mode of power station equipment, and obtain the analysis results of the cloud platform, including:

[0015] Analyze various parameters of power station equipment, obtain the key features for identifying the status information and operation mode of power station equipment, and obtain the key feature set;

[0016] According to the key feature set, construct an initial decision tree model;

[0017] The decision tree model recursively divides the data set and forms a series of decision rules according to different branches of feature values;

[0018] Integrate the results of multiple decision trees to form an integrated decision tree model, and perform reasoning on the integrated decision tree model. Input new power station equipment parameter data and judge the status information and operation mode of the equipment according to the decision rules; the status information includes whether the equipment is working properly and whether there are potential fault hazards; the operation mode reflects the operation efficiency and energy consumption level of the equipment;

[0019] Sort out the status information and operation mode of the equipment to form the analysis results of the cloud platform.

[0020] Furthermore, according to the analysis results of the cloud platform, remotely access the equipment status information, and use the predator-prey interaction relationship hunting search algorithm that simulates nature to optimize the decision-making process of remotely controlling equipment operations. At the same time, remotely receive equipment fault alarms to achieve remote monitoring of power station equipment, discover and handle potential fault risks, including:

[0021] Receive and parse the analysis results of the cloud platform, and extract the current status, operation mode, and potential abnormal or fault information of the equipment;

[0022] Obtain the status information of the equipment in real time, and compare the real-time obtained equipment status information with the analysis results of the cloud platform to update the real-time status awareness of the equipment;

[0023] Take the real-time status awareness of the updated device as an input parameter of the predatory search algorithm, simulate the interaction between predators and prey in nature, and use a preset selection function to search and determine the final remote control operation decision in the decision set;

[0024] According to the final remote control operation decision, send a control instruction to the power station equipment, execute the corresponding operation, and monitor the response and status change of the equipment in real time. When an alarm signal is received, analyze the alarm cause, determine the fault point, and issue a fault handling instruction;

[0025] Continuously monitor the operating status of the equipment, combine with the continuously updated analysis results of the cloud platform, and discover and handle potential fault risks.

[0026] Furthermore, taking the real-time status awareness of the updated device as an input parameter of the predatory search algorithm, simulating the interaction between predators and prey in nature, and using a preset selection function to search and determine the final remote control operation decision in the decision set, including:

[0027] Define a set of operation decisions to form a decision set. The operation decisions include adjusting equipment parameters, starting / stopping the equipment, and switching working modes;

[0028] Randomly select several operation decisions in the decision set as the initial positions of the predators, and regard the current state of the equipment as the prey;

[0029] The predator perceives the state of the current environment and the position of the prey based on the real-time status awareness of the equipment, and evaluates the distance between the current position of the predator and the prey through a preset selection function to obtain the result of the selection function;

[0030] The predator searches and moves positions in the decision set according to the result of the selection function;

[0031] Repeat the processes of perceiving the environment, evaluating the selection function, and searching and moving until the preset number of iterations is reached. Determine the final operation decision according to the result of the selection function, and use the final operation decision as the remote control operation decision.

[0032] Furthermore, the calculation formula of the selection function is:

[0033]

[0034] where S(d,S r ,M) represents the comprehensive score of decision d under the given rule set S r and mode M; α, β, γ represent weight coefficients; k represents the number of dimensions in which decision d and the relevant rules in rule set S r are evaluated; d j represents the value of decision d in the jth dimension; Srj Denote the rule set S r The value of the rule related to decision d in the j-th dimension; j represents the dimension index; m represents the total number of rules in the rule set R; r represents a specific rule in the rule set R; R represents the rule set related to decision d; [c ifdr] is a conditional expression, indicating that if decision d satisfies rule r, then c is 1, otherwise c is 0; n represents the total number of possible failure types; i represents the index of the failure type; p i Denote the probability of the i-th failure occurring; c i Denote the loss value of the consequence of the i-th failure; ∈ i Denote the risk adjustment coefficient of the i-th failure.

[0035] Furthermore, the hierarchical extension method is adopted to evaluate the information security risks in the power station framework, and corresponding security measures are taken according to the evaluation results, including:

[0036] Determine the objectives of information security risk assessment in the power station framework, including identifying potential risk points, evaluating the likelihood and impact degree of risks, and determining the evaluation indicators related to information security risks, including equipment security, network transmission security, data processing security, and application layer access control;

[0037] Divide the information security risks into different levels, including the equipment layer, network layer, platform layer, and application layer, and determine the classical domain and section domain for each evaluation indicator;

[0038] According to the actual values of the evaluation indicators, classical domain, and section domain, calculate the correlation degrees of each evaluation indicator with each risk level;

[0039] According to the correlation degrees of each evaluation indicator with each risk level, judge the risk levels to which each evaluation indicator belongs, and obtain the risk assessment result;

[0040] Analyze the risk assessment result, identify high-risk areas and key links, and formulate a security plan according to the risk assessment result, including strengthening measures at the technical level and improvement measures at the management level.

[0041] Furthermore, the calculation formula for the correlation degree of each evaluation indicator with each risk level is:

[0042]

[0043] Among them, P j Denote the comprehensive evaluation result of risk level j; T represents the number of time points; t represents the time point; w t Denote the weight of time point t; N represents the number of individuals; I represents the index of the evaluation indicator; w Irepresents the weight of evaluation metric I; M represents the number of sub-factors under each evaluation metric I; k represents the index of the sub-factor of the evaluation metric; w Ik represents the weight of sub-factor k of evaluation metric I; a Ijk represents the constant correlation term between sub-factor k of evaluation metric I and risk level j; b Ijk represents the linear correlation coefficient between sub-factor k of evaluation metric I and risk level j; x Ik (t) represents the observed value of sub-factor k of the evaluation metric at time point t; e, k represent index variables; represents the number of interactions of sub-factors related to evaluation metric i; M I represents the number of sub-factors related to evaluation metric I; g represents; w Ikeg represents the interaction weight between sub-factor k of evaluation metric I and sub-factor g of evaluation metric e; r Ijkeg (t) represents the correlation degree value between sub-factor k of evaluation metric I and sub-factor g of evaluation metric e with risk level j at time point t.

[0044] In a second aspect, an Internet of Things-based power station safety monitoring system includes:

[0045] A sensing module for real-time sensing of various parameters of power station equipment, including temperature, humidity, current, and voltage;

[0046] A cloud platform processing module for processing and analyzing the power station equipment parameters collected by the sensing module, extracting the status information and operating mode of the power station equipment to obtain an analysis result;

[0047] A remote monitoring module for remotely accessing the equipment status information according to the analysis result of the cloud platform processing module, and optimizing the decision-making process of remotely controlling equipment operations using a predator search algorithm;

[0048] An alarm module for remotely receiving equipment fault alarms and realizing the discovery and handling of fault risks of power station equipment;

[0049] A power station architecture module for constructing a power station architecture including a sensing layer, a network layer, a platform layer, and an application layer, with each layer corresponding to functions of sensing equipment parameters, data transmission, cloud platform processing, remote monitoring, and alarm.

[0050] In a third aspect, a computing device includes:

[0051] One or more processors;

[0052] A storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the described method.

[0053] Fourthly, a computer-readable storage medium stores a program, which when executed by a processor implements the method described above.

[0054] The above solution of the present invention has at least the following beneficial effects:

[0055] By real-time sensing various parameters of power station equipment (such as temperature, humidity, current, voltage, etc.), abnormal changes in the equipment status can be detected in a timely manner, providing basic data support for the safe operation of the power station. Combining with the data processing and analysis capabilities of the cloud platform, equipment status information and operation modes can be quickly extracted, potential fault risks can be discovered in a timely manner, and remote receiving of equipment fault alarms can be achieved to enable rapid response and handling. Using the Predatory Search Algorithm that simulates the interaction relationship between natural predators and prey to optimize the decision-making process of remotely controlling equipment operations improves the intelligence and accuracy of decision-making. This algorithm can simulate the optimization process in nature to find the final solution, thereby improving the operation efficiency and energy utilization rate while ensuring the safe operation of the power station.

[0056] Construct a power station architecture including a sensing layer, a network layer, a platform layer, and an application layer, making the functions and responsibilities of each part of the system clearer and facilitating the management and maintenance of the system. The sensing layer is responsible for data collection, the network layer is responsible for data transmission, the platform layer is responsible for data processing and analysis, and the application layer is responsible for remote monitoring and intelligent decision-making. This hierarchical design improves the scalability and flexibility of the system. Using the hierarchical extension method to evaluate the information security risks in the power station architecture can comprehensively and objectively reflect the information security status of the system. Taking corresponding security measures according to the evaluation results can effectively reduce information security risks and ensure the safe and stable operation of the power station system. Through real-time monitoring, intelligent decision-making, and optimized control, equipment failures can be detected and processed in a timely manner, reducing power outage time and maintenance costs caused by failures. At the same time, the optimized control strategy can improve the operation efficiency and energy utilization rate of equipment, reduce the operation cost of the power station, and improve the overall reliability of the power station. Brief Description of the Drawings

[0057] Figure 1 is a schematic flowchart of a power station security monitoring method based on the Internet of Things provided by an embodiment of the present invention.

[0058] Figure 2 is a schematic diagram of a power station security monitoring system based on the Internet of Things provided by an embodiment of the present invention. Detailed Embodiments

[0059] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0060] As Figure 1 shown, an embodiment of the present invention proposes an Internet of Things-based power station safety monitoring method, and the method includes the following steps:

[0061] Step 11, real-time sense various parameters of power station equipment, including temperature, humidity, current, and voltage;

[0062] Step 12, use the cloud platform to process and analyze various parameters of power station equipment, extract the status information and operation mode of power station equipment, and obtain the cloud platform analysis result;

[0063] Step 13, according to the cloud platform analysis result, remotely access the equipment status information, and use the predator-prey interaction relationship in nature-based hunting search algorithm to optimize the decision-making process for remotely controlling equipment operations. At the same time, remotely receive equipment fault alarms, realize remote monitoring of power station equipment, and discover and handle potential fault risks;

[0064] Step 14, construct a power station architecture including a perception layer, a network layer, a platform layer, and an application layer. Among them, the perception layer collects various parameters of power station equipment, the network layer performs data transmission, the platform layer performs data processing and analysis services, and the application layer realizes remote monitoring and intelligent decision-making functions according to the cloud platform analysis result;

[0065] Step 15, evaluate the information security risks in the power station architecture using the hierarchical extension method, and take corresponding security measures according to the evaluation results.

[0066] In the embodiment of the present invention, by real-time sensing the key parameters of power station equipment, it is possible to ensure a comprehensive and accurate grasp of the equipment status, providing reliable basic data for data processing and analysis. Real-time monitoring helps to detect abnormal changes in equipment parameters in a timely manner, thereby early warning potential faults and reducing losses caused by faults.

[0067] Step 12, the efficient data processing and analysis capabilities of the cloud platform can quickly extract the status information and operation mode of power station equipment, providing a scientific basis for decision-making support. Through the cloud platform analysis result, it is possible to more intuitively understand the operation status of the equipment, which helps to optimize the operation strategy and improve the operation efficiency and energy utilization rate of the power station.

[0068] Step 13: Optimize the decision-making process for the operation of the remote control device using the Predatory Search Algorithm, which can improve the intelligence and flexibility of decision-making, making the device operation more precise and efficient. The remote receiving device's fault alarm function can achieve real-time monitoring of power station equipment, promptly detect and handle potential fault risks, and ensure the safe and stable operation of the power station.

[0069] Step 14: The hierarchical design of the power station framework makes the functions and responsibilities of each part of the system clearer, facilitating system management and maintenance, and improving the scalability and flexibility of the system. Through the collaborative work of the perception layer, network layer, platform layer, and application layer, comprehensive monitoring and intelligent decision-making of power station equipment are achieved, improving the automation level and operation efficiency of the power station.

[0070] Step 15: Use the hierarchical extension method to evaluate the information security risks in the power station framework, which can comprehensively and objectively reflect the information security status of the system and provide a scientific basis for formulating security measures. Taking corresponding security measures according to the evaluation results can effectively reduce information security risks, ensure the information security and stable operation of the power station system, and guarantee the security and reliability of power station data.

[0071] In a preferred embodiment of the present invention, the above-mentioned Step 11 of real-time sensing of various parameters of power station equipment, including temperature, humidity, current, and voltage, may include:

[0072] In the embodiment of the present invention, a temperature sensor: is used to monitor the temperature of power station equipment, such as the bearing part and stator winding of a generator set. A humidity sensor: is used to monitor the humidity of the power station environment, especially in some equipment or areas sensitive to humidity, such as the interior of an outdoor terminal box. A current sensor: is used to monitor the current of power station equipment to ensure that the equipment operates within the rated current range. A voltage sensor: is used to monitor the voltage of power station equipment to prevent damage to the equipment caused by too high or too low voltage.

[0073] According to the layout and monitoring requirements of power station equipment, install corresponding sensors on key equipment. Ensure that the installation position of the sensors is accurate and can truly reflect the operating state of the equipment. For some special environments (such as high-temperature and high-humidity environments), sensors with corresponding protection levels need to be selected and corresponding installation measures need to be taken.

[0074] Establish a data acquisition system, which is connected to each sensor and is responsible for regularly collecting various data monitored by the sensors. The acquisition frequency can be set according to the importance and operating characteristics of the equipment. Generally, higher acquisition frequencies can be set for important equipment to ensure the real-time and accuracy of the data. Transmit the collected data to the data analysis platform.

[0075] In a preferred embodiment of the present invention, in step 12 above, the cloud platform is used to process and analyze various parameters of the power station equipment, extract the status information and operation mode of the power station equipment, and obtain the cloud platform analysis result, which may include:

[0076] Step 121, analyze various parameters of the power station equipment, obtain the features crucial for identifying the status information and operation mode of the power station equipment, and obtain the key feature set;

[0077] Step 122, construct an initial decision tree model according to the key feature set;

[0078] In step 123, the decision tree model recursively divides the data set, and forms a series of decision rules according to different branches of the feature values;

[0079] In step 124, integrate the results of multiple decision trees to form an integrated decision tree model, and perform reasoning on the integrated decision tree model. Input new power station equipment parameter data, and judge the status information and operation mode of the equipment according to the decision rules; the status information includes whether the equipment is working properly and whether there are potential fault hazards; the operation mode reflects the operation efficiency and energy consumption level of the equipment;

[0080] In step 125, organize the status information and operation mode of the equipment to form the cloud platform analysis result.

[0081] In the embodiment of the present invention, the original data collected from the power station equipment is cleaned to remove outliers, missing values, etc., to ensure the accuracy and integrity of the data. Using methods such as statistical analysis and correlation analysis, features closely related to the equipment status information and operation mode are selected from the original data. These features may include the average value and fluctuation range of temperature, the change trend of humidity, the peak value and effective value of current, the stability of voltage, etc. Further process the selected features, such as calculating statistical quantities such as the average value, standard deviation, maximum value, and minimum value of the features, and extracting the frequency domain information of the features through methods such as Fourier transform to form the key feature set.

[0082] In step 122, select the decision tree as the classification model, and set the initial parameters of the model, such as the depth of the tree, the splitting criterion (such as Gini coefficient, information gain, etc.). Divide the key feature set into a training set and a test set for model training and verification. Using the training set data, recursively divide the data set according to the splitting criterion to construct the initial decision tree model.

[0083] In step 123, at each node, divide the data set into several subsets according to different values of the feature value. For each subset, continue to recursively perform node splitting until the stopping condition is met (such as the depth of the tree reaches the preset value, the purity of the subset reaches a certain level, etc.). In this process, a series of decision rules based on the feature values are formed.

[0084] Step 124, using ensemble learning methods such as random forest and gradient boosting tree, integrate the results of multiple decision trees to improve the accuracy and stability of the model. Input new power station equipment parameter data, perform inference through the integrated decision tree model, and judge the status information and operating mode of the equipment according to the decision rules.

[0085] Step 125, organize the inferred equipment status information and operating mode to form structured data. Display the organized results in the form of charts, reports, etc. on the cloud platform for easy viewing and analysis by users.

[0086] Suppose there is a set of power station equipment parameter data, including temperature, humidity, current, and voltage. First, preprocess this data to remove outliers and missing values. Then, through feature selection methods, screen out the features closely related to the equipment status information and operating mode, such as the average value and fluctuation range of temperature, the peak value of current, etc. Next, use these key features to construct an initial decision tree model, and through recursive partitioning of the dataset, form a series of decision rules based on feature values.

[0087] For example, if the average temperature exceeds a certain threshold and the current peak also exceeds a certain threshold, it is determined that there is a potential fault in the equipment. Finally, integrate the results of multiple decision trees to form an integrated decision tree model. When new power station equipment parameter data is input, perform inference through the integrated decision tree model, judge the status information and operating mode of the equipment, and display the results on the cloud platform.

[0088] Through feature selection and extraction, as well as constructing and integrating decision tree models, it is possible to more accurately judge the status information and operating mode of power station equipment, improving the accuracy of monitoring. Using ensemble learning methods to integrate the results of multiple decision trees can reduce the risk of overfitting of a single model and enhance the stability of the model. Through data processing and analysis on the cloud platform, real-time monitoring and early warning can be achieved, potential fault risks can be discovered and processed in a timely manner, and the operating efficiency of the power station can be improved. Displaying the equipment status information and operating mode in the form of charts, reports, etc. on the cloud platform is convenient for users to view and analyze, improving the convenience of power station management.

[0089] In a preferred embodiment of the present invention, in step 13 above, according to the analysis results of the cloud platform, remotely access the equipment status information, and use the predator search algorithm that simulates the interaction relationship between natural predators and prey to optimize the decision-making process for remotely controlling equipment operations. At the same time, remotely receive equipment fault alarms to achieve remote monitoring of power station equipment, discover and process potential fault risks, and may include:

[0090] Step 131: Receive and parse the analysis results from the cloud platform, and extract the current status, operating mode, and potential abnormal or fault information of the device;

[0091] Step 132: Obtain the status information of the device in real time, and compare the real-time obtained device status information with the analysis results of the cloud platform to update the real-time status perception of the device;

[0092] Step 133: Use the updated real-time status perception of the device as the input parameter of the predator search algorithm, simulate the interaction relationship between predators and prey in nature, and use a preset selection function to search and determine the final remote control operation decision in the decision set;

[0093] Step 134: According to the final remote control operation decision, send a control instruction to the power station device, execute the corresponding operation, and monitor the response and status changes of the device in real time. When an alarm signal is received, analyze the cause of the alarm, determine the fault point, and issue a fault handling instruction;

[0094] Step 135: Continuously monitor the operating status of the device, combine with the continuously updated analysis results of the cloud platform, and discover and handle potential fault risks.

[0095] In the embodiment of the present invention, the analysis result data sent by the cloud platform is received in real time through the API interface or data transmission protocol. The received data is parsed to extract the current status information of the device (such as normal operation, abnormal status), operating mode (such as high-efficiency operation, energy-saving mode), and potential abnormal or fault information (such as too high temperature, abnormal current, etc.), and the parsed information is stored in the local database or memory.

[0096] Step 132: Obtain the status information of the device in real time by remotely accessing the device, such as temperature, humidity, current, voltage, etc. Compare the real-time obtained device status information with the analysis results of the cloud platform to check for differences or abnormalities. According to the comparison result, update the real-time status perception of the device to ensure that the understanding of the device status is accurate and up-to-date.

[0097] Step 133: Use the updated real-time status perception of the device as the input parameter of the predator search algorithm. The algorithm simulates the interaction relationship between predators and prey in nature, regards the device status as the "prey", and the remote control operation decision as the "predator". Use a preset selection function to search and determine the final remote control operation decision in the decision set, such as adjusting device parameters, switching operating modes, etc. Output the finally determined remote control operation decision and prepare to send it to the device.

[0098] Step 134: Convert the final remote control operation decision into a control instruction through a remote communication protocol and send it to the power station equipment. After receiving the control instruction, the equipment performs corresponding operations, such as adjusting temperature, current, etc. Monitor the response and status changes of the equipment in real time to ensure that the operation is executed as expected. When receiving the alarm signal of the equipment, immediately analyze the alarm reason, determine the fault point, and issue a fault handling instruction, such as starting a standby device, notifying the maintenance personnel, etc.

[0099] Step 135: Continuously monitor the operating status of the equipment, and obtain and update the equipment status information in real time. Combine the equipment status information obtained in real time with the continuously updated analysis results of the cloud platform for comprehensive analysis. Through comprehensive analysis, discover and identify potential fault risks, such as equipment performance degradation, parameter anomalies, etc. For the discovered potential fault risks, take corresponding handling measures, such as adjusting equipment parameters, performing preventive maintenance, etc., to ensure the stable operation of the equipment.

[0100] Suppose a generator equipment of a power station is being monitored. Through the analysis results of the cloud platform, it is known that the generator is currently in an efficient operating state, but the temperature has slightly increased. Obtain the status information of the generator in real time and find that the temperature has exceeded the preset threshold. Then, use the updated equipment status perception as an input parameter of the predator search algorithm, simulate the interaction relationship between the predator and the prey, and search and determine the remote control operation decision to reduce the generator load in the decision set. Send a control instruction to the generator equipment to perform the operation of reducing the load, and monitor the response and status changes of the equipment in real time. When receiving the temperature alarm signal of the generator, immediately analyze the alarm reason and determine that the temperature increase is caused by excessive load. Then issue a fault handling instruction to notify the maintenance personnel to conduct inspections and repairs.

[0101] By remotely accessing the equipment status information and combining the analysis results of the cloud platform, it is possible to understand the operating status of the equipment in real time and accurately, improving the monitoring efficiency. Using the predator search algorithm to optimize the decision-making process for remotely controlling equipment operations can find a better decision-making scheme, improve the operating efficiency and stability of the equipment, can monitor the response and status changes of the equipment in real time, and when receiving an alarm signal, can quickly analyze the alarm reason, determine the fault point, and issue a fault handling instruction to detect and handle potential fault risks in a timely manner. By continuously monitoring the operating status of the equipment and combining the continuously updated analysis results of the cloud platform, the machine can predict the fault risks of the equipment, take preventive maintenance measures, reduce the maintenance cost and improve the reliability of the equipment.

[0102] In another preferred embodiment of the present invention, the above step 133, using the updated real-time status perception of the equipment as an input parameter of the predator search algorithm, simulating the interaction relationship between the natural predator and the prey, and using a preset selection function to search and determine the final remote control operation decision in the decision set, may include:

[0103] Step 1331: Define a set of operation decisions to form a decision set. The operation decisions include adjusting device parameters, starting / stopping the device, and switching working modes.

[0104] Step 1332: Randomly select several operation decisions from the decision set as the initial positions of the predators, and regard the current state of the device as the prey.

[0105] Step 1333: The predators perceive the state of the current environment and the position of the prey based on the real-time state awareness of the device, and evaluate the distance between the current position of the predators and the prey through a preset selection function to obtain the result of the selection function.

[0106] Step 1334: The predators search and move positions in the decision set according to the result of the selection function.

[0107] Step 1335: Repeat the processes of perceiving the environment, evaluating the selection function, and searching and moving until the preset number of iterations is reached. Determine the final operation decision according to the result of the selection function, and use the final operation decision as the remote control operation decision.

[0108] In the embodiment of the present invention, according to the operation manual and actual requirements of the power station equipment, a set of operation decisions are defined, such as adjusting device parameters (such as temperature, pressure, speed, etc.), starting / stopping the device, and switching working modes (such as switching from the automatic mode to the manual mode, or from the high-efficiency mode to the energy-saving mode). Summarize all the defined operation decisions to form a decision set for subsequent algorithms to use.

[0109] Step 1332: Randomly select several operation decisions from the decision set as the initial positions of the predators. These operation decisions will be used as the starting points for the algorithm search. Regard the current state of the device (such as real-time parameters such as temperature, current, and voltage) as the prey. The goal of the predators is to find the operation decision that is closest to the prey (i.e., the desired state of the device).

[0110] Step 1333: The predators perceive the state of the current environment based on the real-time state awareness of the device, including the real-time parameters and operating mode of the device. Evaluate the distance between the current position of the predators (i.e., the currently selected operation decision) and the prey (i.e., the desired state of the device) through a preset selection function.

[0111] Step 1334: The predators search and move to a new position (i.e., select a new operation decision) in the decision set according to the result of the selection function. The moving direction and step size can be determined according to the result of the selection function and the preset search strategy, and update the current position of the predators for the next round of search and evaluation.

[0112] Step 1335: Repeat the process of perceiving the environment, evaluating the selection function, and searching for a move until a preset number of iterations is reached or other stopping conditions are met. Based on the result of the selection function, determine the final operation decision, that is, find the operation decision closest to the desired state of the device. Use the final operation decision as the remote control operation decision and output it to the control system of the power station equipment for execution.

[0113] Suppose a boiler device of a power station is being monitored, and the current temperature of the boiler is higher than the set value and needs to be adjusted to lower the temperature. The following operation decisions are defined to form a decision set: adjust the fuel supply of the boiler, adjust the air intake of the boiler, start the standby cooling system. "Adjust the fuel supply of the boiler" is randomly selected as the initial position of the predator in the decision set. When it is sensed that the current temperature of the boiler is 220 °C and the set temperature is 200 °C. Through a preset selection function (such as the absolute value of the temperature difference), the distance between the current position of the predator and the prey is evaluated to be 20 °C. According to the result of the selection function, search in the decision set and decide to move to the new position of "adjust the air intake of the boiler". Repeat the process of perceiving the environment, evaluating the selection function, and searching for a move. After several iterations, it is found that the operation decision of "start the standby cooling system" can make the boiler temperature closest to the set value. Determine "start the standby cooling system" as the final operation decision and send it as the remote control operation decision to the control system of the boiler equipment for execution.

[0114] By simulating the interaction relationship between predators and prey in nature and using the predator search algorithm to search and determine the final operation decision in the decision set, the efficiency of decision-making can be improved, and the optimal or sub-optimal solution can be found quickly. By evaluating the distance between the current position of the predator and the prey through a preset selection function, it can be ensured that the selected operation decision is closest to the desired state of the device, thus enhancing the accuracy of decision-making. The predator search algorithm has strong adaptability and can dynamically adjust the search strategy and selection function according to the real-time state perception of the device to meet the needs of different devices and scenarios. The implementation of the predator search algorithm is relatively simple and is easy to integrate and expand in the existing monitoring system, providing a new intelligent means for the remote control of power station equipment.

[0115] In another preferred embodiment of the present invention, the calculation formula of the selection function is:

[0116]

[0117] where S(d, S r , M) represents the comprehensive score of decision d under the given rule set S r and mode M; α, β, γ represent weight coefficients; k represents the number of dimensions in which the relevant rules in decision d and rule set S r are evaluated; d jRepresents the value of decision d in the j-th dimension; S rj Represents the rule set S r The value of the rule related to decision d in the rule set S in the j-th dimension; j represents the dimension index; m represents the total number of rules in the rule set R; r represents a specific rule in the rule set R; R represents the rule set related to decision d; [c ifdr] is a conditional expression, indicating that if decision d satisfies rule r, then c is 1, otherwise c is 0; n represents the total number of possible failure types; i represents the index of the failure type; p i Represents the probability of the i-th failure occurring; c i Represents the loss value of the consequence of the i-th failure; ∈ i Represents the risk adjustment coefficient of the i-th failure.

[0118] In the embodiment of the present invention, the weight coefficients ɑ, β, γ are determined, and these coefficients will be used to adjust the importance of each part in the selection function, and the decision d and the rule set S are determined r The number of dimensions k in which the relevant rules in S are evaluated. Initialize the value d of decision d in each dimension j , and the rule set S r The value S of the rule related to decision d in the rule set S in each dimension rj , determine the total number m of rules in the rule set R, and the rule set R related to decision d. Initialize the total number n of failure types, and the occurrence probability p of each failure i , the loss value c of the consequence i and the risk adjustment coefficient ∈ i .

[0119] Calculate the sum of the weighted products of decision d and the relevant rules in the rule set S r in each dimension Calculate the square root of the weighted sum of squares of decision d in each dimension Calculate the square root of the weighted sum of squares of the rules related to decision d in the rule set S r in each dimension Substitute the above results into the formula of the first part of the selection function to calculate the score of this part

[0120] Traverse the rule set R. For each rule γ, judge whether decision d satisfies the rule. If decision d satisfies rule γ, then c is 1, otherwise c is 0. Calculate the ratio of the number of rules that satisfy the rule to the total number of rules, and multiply by the weight coefficient β to obtain the score of the second part of the selection function

[0121] Traverse all possible failure types. For each failure type, calculate its occurrence probability p i , the loss value c of the consequence iand the risk adjustment coefficient ∈ i The product of. Multiply the sum of the products of all failure types by the weight coefficient -γ to obtain the score of the third part of the selection function (note that it is a negative value, indicating the negative impact of the failure risk on the score).

[0122] Add the scores of the first part, the second part, and the third part of the selection function to obtain the comprehensive score S(d, S r and the mode M, i.e., S(d, S r , M). According to the comprehensive score S(d, S r , M), select the decision with the highest score in the decision set as the final operation decision.

[0123] The selection function comprehensively considers multiple dimensions such as the matching degree between the decision and the rule set, the number of rules satisfied by the decision, and the failure risk, making the finally selected decision more comprehensive and accurate. By adjusting the weight coefficients α, β, and γ, the importance of each part in the selection function can be flexibly adjusted according to actual needs to adapt to different application scenarios. The failure risk is explicitly considered in the selection function. By calculating the product of the occurrence probability of the failure, the loss value of the consequence, and the risk adjustment coefficient, the impact of the failure on the decision selection is quantified, making the decision safer and more reliable. By comprehensively scoring the decision through the selection function, the final decision can be quickly screened out, improving the efficiency of the decision.

[0124] In a preferred embodiment of the present invention, in step 14 above, a power station framework including a perception layer, a network layer, a platform layer, and an application layer is constructed. Among them, the perception layer collects various parameters of power station equipment, the network layer performs data transmission, the platform layer performs data processing and analysis services, and the application layer realizes remote monitoring and intelligent decision-making functions according to the analysis results of the cloud platform, which may include:

[0125] In the embodiment of the present invention, determine the types of power station equipment to be monitored, such as generators, transformers, switchgear, etc. For each type of equipment, clarify the parameters to be collected, such as temperature, pressure, current, voltage, power factor, etc. Select appropriate sensors and acquisition devices to ensure that the equipment parameters can be accurately and real-time collected. Deploy sensors and acquisition devices and connect them to the power station equipment to ensure the smooth progress of data acquisition. Design the data acquisition system architecture, including a sensor network, a data collector, a data storage unit, etc. Develop data acquisition software to realize the real-time acquisition, storage, and preliminary processing of sensor data. Formulate data standardization and formatting specifications to ensure the consistency and comparability of the collected data.

[0126] Build a communication network to ensure that the data collected by the sensing layer can be reliably transmitted to the platform layer. Considering the security of the network, encryption technology is adopted to protect the privacy and integrity during data transmission. Develop a data transmission protocol to clarify the data transmission format, transmission frequency, error handling mechanism, etc. Develop data transmission software to achieve real-time and efficient data transmission. Establish a network management system to monitor, configure and manage network devices, and conduct network maintenance regularly to ensure the stability and reliability of the network. Select data processing and analysis technologies, such as big data processing frameworks (Hadoop, Spark, etc.), data analysis algorithms (machine learning, deep learning, etc.), build a data processing and analysis platform to achieve real-time processing, storage, analysis and visualization of data, develop data processing and analysis software to provide functions such as data cleaning, transformation, aggregation, and mining, and design a data storage architecture to select a suitable database system (relational database, non-relational database, etc.).

[0127] Establish a data management system to achieve data storage, query, backup and recovery, and ensure data security and privacy protection by adopting technologies such as access control and data encryption. Develop a data analysis service interface to provide functions such as data query, analysis, and mining. Customize data analysis services according to the requirements of the application layer, such as equipment status monitoring, fault diagnosis, performance prediction, etc. Design the architecture of the remote monitoring system, including the monitoring interface, alarm system, data visualization, etc. Develop remote monitoring software to achieve functions such as real-time monitoring of equipment, status display, and alarm prompt, and provide a user-friendly monitoring interface to facilitate operators to remotely view and manage power station equipment. According to the analysis results of the cloud platform, develop an intelligent decision-making system to achieve functions such as intelligent scheduling, optimized operation, and fault handling of equipment. Design decision-making algorithms and models, consider factors such as the operating status of equipment, load demand, and energy price, and formulate the final decision-making plan. Provide a decision support interface to display the decision results and suggestions to facilitate operators to make decisions. Integrate the sensing layer, network layer, platform layer, and application layer to ensure data flow and functional collaboration between layers. Deploy the system to the actual power station environment for on-site debugging and optimization, establish a system operation and maintenance mechanism, and conduct maintenance, upgrade, and fault handling of the system regularly to ensure the long-term stable operation of the system.

[0128] In a preferred embodiment of the present invention, step 15, using the hierarchical extension method to evaluate the information security risks in the power station framework and taking corresponding security measures according to the evaluation results, may include:

[0129] Step 151, determine the objectives of the information security risk assessment in the power station framework, including identifying potential risk points, evaluating the likelihood and impact of risks, and determining the evaluation indicators related to information security risks, including equipment security, network transmission security, data processing security, and application layer access control;

[0130] Step 152: Classify the information security risks into different levels, including the device layer, network layer, platform layer, and application layer, and determine the classical domain and section domain for each evaluation index.

[0131] Step 153: Calculate the correlation degree between each evaluation index and each risk level according to the actual value of the evaluation index, the classical domain, and the section domain.

[0132] Step 154: Judge the risk level to which each evaluation index belongs according to the correlation degree between each evaluation index and each risk level, and obtain the risk assessment result.

[0133] Step 155: Analyze the risk assessment result, identify the high-risk areas and key links, and formulate a security plan according to the risk assessment result, including reinforcement measures at the technical level and improvement measures at the management level.

[0134] In the embodiment of the present invention, each component (device layer, network layer, platform layer, application layer) in the power station framework is carefully examined. By means of historical data analysis, vulnerability scanning, penetration testing, etc., identify possible information security risk points. Establish a risk point list, clarify the location, nature, and possible impacts of the risk points, conduct a possibility analysis for each risk point, consider factors such as the attacker's motivation, ability, and resources, evaluate the impact degree on aspects such as power station operation, data security, and user privacy after the risk occurs, and use a method combining qualitative and quantitative methods to quantify the possibility and impact degree of the risk.

[0135] According to the characteristics of the power station framework and information security requirements, determine evaluation indexes such as device security, network transmission security, data processing security, and application layer access control, and formulate specific measurement criteria and evaluation methods for each evaluation index.

[0136] Step 152: Classify the information security risks in the power station framework into four levels: device layer, network layer, platform layer, and application layer, clarify the main functions and possible risk types of each level, determine the classical domain for each evaluation index, that is, the value range of the index under normal conditions, and determine the section domain, that is, the value range or threshold of the index when it may be affected by risks. The determination of the classical domain and the section domain should be based on industry standards and historical data.

[0137] Step 153: Collect the actual values of each evaluation index through means such as monitoring systems, log analysis, and security audits. Calculate the correlation degree between the actual value of each evaluation index and the classical domain and the section domain. The correlation degree reflects the distance between the index value and the classical domain or the section domain, and is an important basis for judging the risk level.

[0138] Step 154: Based on the degree of relevance, determine the risk levels (such as low risk, medium risk, high risk) to which each evaluation indicator belongs. The division of risk levels should be based on pre-set standards or thresholds. Summarize the risk levels of each evaluation indicator to form an overall information security risk assessment result. The assessment result includes the location of the risk point, the risk level, the possible impacts, and the recommended countermeasures.

[0139] Step 155: Conduct an in-depth analysis of the evaluation result, identify high-risk areas and key links, analyze the causes of risks, possible development trends, and potential consequences. Based on the evaluation result, formulate a targeted security plan. Technical-level reinforcement measures may include upgrading device firmware, strengthening network encryption, optimizing data processing processes, etc. Management-level improvement measures include strengthening access control, conducting regular audits, training employees, etc.

[0140] Suppose the evaluation indicator for the network layer in the power station framework is "network transmission delay", its classical domain is [0, 50] milliseconds, and the extension domain is [50, 100] milliseconds. At a certain moment, the monitoring system detects that the network transmission delay is 60 milliseconds. Calculate the relevance between the network transmission delay and the classical domain and the extension domain. Suppose the relevance between the network transmission delay and the extension domain is relatively high, and the relevance with the classical domain is relatively low. Based on the degree of relevance, determine that the network transmission delay belongs to the medium risk level, automatically trigger the alarm system, and notify the network administrator. The network administrator decides to take reinforcement measures such as optimizing the network configuration and increasing bandwidth according to the risk level and the evaluation result.

[0141] Evaluating the information security risks in the power station framework through the hierarchical extension method can comprehensively and accurately identify potential risk points. The evaluation result provides a basis for formulating a targeted security plan, which helps to improve the information security level of the power station. The hierarchical extension method can quantify the possibility and impact degree of risks, helping the power station managers better understand the risk situation. Through regular evaluation, the power station can timely discover new risk points, adjust the security plan, and enhance the risk response ability. The evaluation result can identify high-risk areas and key links, guiding the power station to reasonably allocate security resources. By giving priority to dealing with high-risk points, the power station can more effectively utilize limited security resources and improve the overall security. The hierarchical extension method provides a scientific method and tool for the information security management of the power station. Through the feedback and continuous improvement of the evaluation result, the power station can continuously improve the security management process and promote the standardization of security management.

[0142] In a preferred embodiment of the present invention, the calculation formula for the relevance between each evaluation indicator and each risk level is:

[0143]

[0144] Wherein, P jRepresents the comprehensive evaluation result of risk level j; T represents the number of time points; t represents a time point; w t Represents the weight of time point t; N represents the number of individuals; I represents the index of evaluation indicators; w I Represents the weight of evaluation indicator I; M represents the number of sub - factors under each evaluation indicator I; k represents the index of the sub - factor of the evaluation indicator; w Ik Represents the weight of sub - factor k of evaluation indicator I; a Ijk Represents the constant correlation term between sub - factor k of evaluation indicator I and risk level j; b Ijk Represents the linear correlation coefficient between sub - factor k of evaluation indicator I and risk level j; x Ik (t) represents the observed value of sub - factor k of the evaluation indicator at time point t; e, k are index variables; represents the number of interactions between sub - factors related to evaluation indicator i; M I Represents the number of sub - factors related to evaluation indicator I; g represents; w Ikeg Represents the interaction weight between sub - factor k of evaluation indicator I and sub - factor g of evaluation indicator e; r Ijkeg (t) represents the correlation degree value between sub - factor k of evaluation indicator I and sub - factor g of evaluation indicator e at time point t with risk level j.

[0145] In the embodiment of the present invention, clarify the evaluation indicators involved in the information security risk assessment in the power station framework, such as equipment security, network transmission security, data processing security, and application layer access control, etc. Determine the sub - factors under each evaluation indicator. For example, equipment security may include sub - factors such as equipment firmware version, equipment physical security, and equipment access control. Define risk levels, such as low risk, medium risk, high risk, etc., and set corresponding thresholds or standards for each risk level. At each time point t, collect the observed values x Ik (t) of each evaluation indicator and its sub - factors. Determine the weight w t of time point t, which can be determined according to the importance of the time point. For each evaluation indicator I, its sub - factor k, and risk level j, determine the constant correlation term a Ijk , the linear correlation coefficient b Ijk and the interaction weight w Ikeg .

[0146] For each evaluation indicator I, calculate the correlation degree between its sub - factor k and risk level j. This includes the sum of the constant correlation term a Ijk and the linear correlation term b Ijk ×x Ik (t). Considering the interaction between evaluation indicators, for other evaluation indicators e related to evaluation indicator I, calculate the correlation degree r between its sub - factor g and sub - factor k of evaluation indicator I at time point t with risk level jIjkeg (t), and multiply it by the corresponding interaction weight w Ikeg .

[0147] Add the above two parts to obtain the total correlation degree of the evaluation index I at time point t and risk level j. Perform a weighted sum over all time points t to obtain the comprehensive correlation degree of the evaluation index I and risk level j. Perform a weighted sum over all evaluation indices I to obtain the comprehensive evaluation result P of risk level j j . According to the comprehensive evaluation result P j , compare it with a pre-set threshold or standard to determine the risk level to which the information security risk of the power station framework belongs. Based on the risk assessment result, identify high-risk areas and key links, and formulate reinforcement measures at the technical level and improvement measures at the management level for high-risk areas and key links, implement security measures, and continuously monitor the information security status of the power station framework and conduct risk assessments regularly

[0148] By considering multiple evaluation indices and their sub-factors, as well as their interactions, the information security risk status in the power station framework can be more comprehensively reflected. By introducing the weights of time points and evaluation indices, the impact of different time points and evaluation indices on the risk level can be more accurately evaluated. This formula can quantify the comprehensive evaluation result of each risk level, providing a basis for formulating targeted security measures. By identifying high-risk areas and key links, the power station can prioritize the handling of these areas and links to improve the efficiency and effectiveness of risk response. By regularly evaluating and judging the risk level, the power station can continuously improve the security management process and enhance the scientific and standardized level of security management. Through the feedback of the evaluation result, the power station can reasonably allocate security resources to ensure that high-risk areas and key links receive sufficient attention and protection. By optimizing the allocation of security resources, the power station can improve the overall security and reduce the occurrence probability and impact degree of information security risks

[0149] As Figure 2 shown, an embodiment of the present invention further provides an Internet of Things-based power station security monitoring system, including:

[0150] A sensing module for real-time sensing of various parameters of power station equipment, including temperature, humidity, current, and voltage;

[0151] A cloud platform processing module for processing and analyzing the power station equipment parameters collected by the sensing module, extracting the status information and operation mode of the power station equipment to obtain an analysis result;

[0152] A remote monitoring module for remotely accessing the equipment status information according to the analysis result of the cloud platform processing module and optimizing the decision-making process of remotely controlling the equipment operation using a predator search algorithm;

[0153] An alarm module, which is used to remotely receive equipment fault alarms and realize the discovery and handling of fault risks of power station equipment;

[0154] A power station architecture module, which is used to construct a power station architecture including a perception layer, a network layer, a platform layer, and an application layer. Each layer corresponds to functions of sensing equipment parameters, data transmission, cloud platform processing, remote monitoring, and alarm respectively.

[0155] It should be noted that this system corresponds to the above method. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0156] An embodiment of the present invention further provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0157] An embodiment of the present invention further provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is made to execute the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0158] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An Internet of Things-based power plant safety monitoring method, characterized in that, The method includes: Real-time sensing of various parameters of power station equipment, including temperature, humidity, current, and voltage; Using the cloud platform to process and analyze various parameters of power station equipment, extracting the status information and operation mode of power station equipment, and obtaining the cloud platform analysis result; According to the cloud platform analysis result, remotely access the equipment status information, and use the predator-prey search algorithm that simulates the interaction relationship between natural predators and prey to optimize the decision-making process for remotely controlling equipment operations. At the same time, remotely receive equipment fault alarms, realize remote monitoring of power station equipment, and discover and handle potential fault risks; Construct a power station architecture including a sensing layer, a network layer, a platform layer, and an application layer. Among them, the sensing layer collects various parameters of power station equipment, the network layer conducts data transmission, the platform layer provides data processing and analysis services, and the application layer realizes remote monitoring and intelligent decision-making functions according to the cloud platform analysis result; For the information security risks in the power station architecture, use the hierarchical extension method for assessment, and take corresponding security measures according to the assessment results.

2. The method for power station safety monitoring based on the Internet of Things according to claim 1, characterized in that, Using the cloud platform to process and analyze various parameters of power station equipment, extracting the status information and operation mode of power station equipment, and obtaining the cloud platform analysis result, including: Analyze various parameters of power station equipment, obtain the key features for identifying the status information and operation mode of power station equipment, and obtain the key feature set; According to the key feature set, construct an initial decision tree model; The decision tree model recursively divides the data set, and forms a series of decision rules according to different branches of feature values; Integrate the results of multiple decision trees to form an integrated decision tree model, and perform reasoning on the integrated decision tree model. Input new power station equipment parameter data, and judge the status information and operation mode of the equipment according to the decision rules; the status information includes whether the equipment is working properly and whether there are potential fault hazards; the operation mode reflects the operation efficiency and energy consumption level of the equipment; Sort out the status information and operation mode of the equipment to form the cloud platform analysis result.

3. The method for power station safety monitoring based on the Internet of Things according to claim 2, characterized in that, According to the cloud platform analysis result, remotely access the equipment status information, and use the predator-prey search algorithm that simulates the interaction relationship between natural predators and prey to optimize the decision-making process for remotely controlling equipment operations. At the same time, remotely receive equipment fault alarms, realize remote monitoring of power station equipment, and discover and handle potential fault risks, including: Receive and parse the cloud platform analysis result, and extract the current status, operation mode, and potential abnormal or fault information of the equipment; Obtain the status information of the equipment in real time, and compare the real-time obtained equipment status information with the cloud platform analysis result to update the real-time status awareness of the equipment; Use the updated real-time status awareness of the equipment as the input parameter of the predator-prey search algorithm, simulate the interaction relationship between natural predators and prey, and use the preset selection function to search and determine the final remote control operation decision in the decision set; According to the final remote control operation decision, send a control instruction to the power station equipment, execute the corresponding operation, and monitor the response and status change of the equipment in real time. When an alarm signal is received, analyze the alarm reason, determine the fault point, and issue a fault handling instruction; Continuously monitor the operating status of the device, and combine with the continuously updated analysis results of the cloud platform to discover and handle potential failure risks.

4. The method for power station safety monitoring based on the Internet of Things according to claim 3, characterized in that, Use the updated real-time status awareness of the device as an input parameter for the predatory search algorithm, simulate the interaction between predators and prey in nature, and use a preset selection function to search and determine the final remote control operation decision in the decision set, including: Define a set of operation decisions to form a decision set. The operation decisions include adjusting device parameters, starting / stopping the device, and switching the working mode; Randomly select several operation decisions in the decision set as the initial positions of the predators, and regard the current state of the device as the prey; Based on the real-time status awareness of the device, the predator perceives the state of the current environment and the position of the prey, and evaluates the distance between the current position of the predator and the prey through a preset selection function to obtain the result of the selection function; Based on the result of the selection function, the predator searches and moves positions in the decision set; Repeat the processes of perceiving the environment, evaluating the selection function, and searching and moving until the preset number of iterations is reached. Based on the result of the selection function, determine the final operation decision, and use the final operation decision as the remote control operation decision.

5. The method for power plant safety monitoring based on the Internet of Things according to claim 4, wherein The calculation formula of the selection function is: Among them, S(d, S r , M) represents the comprehensive score of decision d under the given rule set S r and pattern M; α, β, γ represent weight coefficients; k represents the number of dimensions in which the relevant rules in decision d and rule set S r are evaluated; d j represents the value of decision d in the j-th dimension; S rj represents the value of the rule in rule set S r related to decision d in the j-th dimension; j represents the dimension index; m represents the total number of rules in rule set R; r represents a specific rule in rule set R; R represents the rule set related to decision d; [cifdr] is a conditional expression, indicating that if decision d satisfies rule r, then c is 1, otherwise c is 0; n represents the total number of possible failure types; i represents the index of the failure type; p i represents the probability of the i-th failure occurring; c i represents the loss value of the consequences of the i-th failure; ∈ i represents the risk adjustment coefficient of the i-th failure.

6. The method for power station safety monitoring based on the Internet of Things according to claim 5, characterized in that, Adopt the hierarchical extension method to evaluate the information security risks in the power station framework, and take corresponding security measures according to the evaluation results, including: Determine the objectives of information security risk assessment in the power station framework, including identifying potential risk points, evaluating the likelihood and impact degree of risks, and determining evaluation indicators related to information security risks, including device security, network transmission security, data processing security, and application layer access control; Divide the information security risks into different levels, including the device layer, network layer, platform layer, and application layer, and determine the classical domain and section domain for each evaluation indicator; According to the actual values of the evaluation indicators, classical domain, and section domain, calculate the correlation degrees of each evaluation indicator with each risk level; According to the correlation degrees of each evaluation indicator with each risk level, judge the risk levels to which each evaluation indicator belongs, and obtain the risk assessment result; Analyze the risk assessment result, identify high-risk areas and key links, and formulate a security plan according to the risk assessment result, including strengthening measures at the technical level and improvement measures at the management level.

7. The method for power station safety monitoring based on the Internet of Things according to claim 6, wherein, The calculation formula of the correlation degree of each evaluation indicator with each risk level is: Among them, P j represents the comprehensive evaluation result of risk level j; T represents the number of time points; t represents a time point; w t represents the weight of time point t; N represents the number of individuals; I represents the index of evaluation indicators; w I represents the weight of evaluation indicator I; M represents the number of sub-factors under each evaluation indicator I; k represents the index of the sub-factor of the evaluation indicator; w Ik represents the weight of sub-factor k of evaluation indicator I; a Ijk represents the constant correlation term between sub-factor k of evaluation indicator I and risk level j; b Ijk represents the linear correlation coefficient between sub-factor k of evaluation indicator I and risk level j; x Ik (t) represents the observed value of sub-factor k of the evaluation indicator at time point t; e, k represent index variables; represents the number of interactions between sub-factors related to evaluation indicator i; M I represents the number of sub-factors related to evaluation indicator I; g represents; w Ikeg represents the interaction weight between sub-factor k of evaluation indicator I and sub-factor g of evaluation indicator e; r Ijkeg (t) represents the correlation degree value between sub-factor k of evaluation indicator I and sub-factor g of evaluation indicator e with risk level j at time point t.

8. An Internet of Things-based power station safety monitoring system, which implements the method described in any one of claims 1 to 7, characterized in that, Including: A sensing module for real-time sensing of various parameters of power station equipment, including temperature, humidity, current, and voltage; A cloud platform processing module for processing and analyzing the power station equipment parameters collected by the sensing module, extracting the status information and operating mode of the power station equipment to obtain analysis results; A remote monitoring module for remotely accessing the device status information according to the analysis results of the cloud platform processing module, and optimizing the decision-making process for remotely controlling device operations using the predatory search algorithm; An alarm module for remotely receiving device fault alarms and realizing the discovery and handling of fault risks of power station equipment; Power station architecture module, used to construct a power station architecture including a sensing layer, a network layer, a platform layer and an application layer, and each layer corresponds to sensing device parameters, data transmission, cloud platform processing, remote monitoring and alarm functions respectively.

9. A computing device, characterized in that, It includes: One or more processors; A storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images