Factory multi-dimensional safety control method and system based on thermal power plant

Abstract

The invention relates to the technical field of safety management, in particular to a plant multi-dimensional safety management and control method and system based on a thermal power plant, and the method comprises the following steps: based on the position information of the thermal power plant, analyzing a building CAD drawing, scanning the internal structure of the thermal power plant, recognizing facility elements and spatial position information, constructing a building information model, and carrying out the building information model; and generating a model construction record. According to the invention, by analyzing a CAD drawing, collecting internal scanning data of a thermal power plant, constructing a building information model and realizing visualization of facility and equipment layout, safety monitoring is more visual and accurate, real-time data input of an Internet of Things sensor enhances the monitoring capability of the equipment health state, and through personnel identity verification, the safety of the equipment health state is improved. Unauthorized access and internal risk events are effectively prevented, the timeliness and effectiveness of prevention measures are enhanced in combination with risk behavior recognition, the states and positions of work tickets and operation tickets are monitored in real time, operation deviation and behavior risks are recognized, and operation safety and compliance are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of safety management, and in particular to a multi-dimensional safety management and control method and system for a thermal power plant. Background Art

[0002] The field of safety management technology focuses on the use of a variety of strategies, methods and tools to prevent, identify and respond to a variety of security threats, protect the safety of personnel, assets and information, and combine a variety of security theories and modern technologies, including the Internet of Things, data analysis, artificial intelligence and machine learning, to enhance the ability of safety monitoring and risk management. In an industrial environment, safety management technology focuses on formulating and implementing efficient safety policies, and preventing industrial accidents and improving emergency response speed through monitoring systems and automation tools. Combined with the recording and analysis of safety incidents, it continuously improves safety measures and response strategies.

[0003] Among them, the multi-dimensional safety management and control method based on thermal power plants focuses on realizing multi-dimensional safety management and control in thermal power plants. By integrating multiple security systems and technologies, a comprehensive safety management framework is constructed, including video surveillance, access control systems, personnel positioning and intelligent two-ticket systems, to improve the safety level of thermal power plants, reduce safety accidents, and ensure the safety of personnel and facilities. Combined with building information construction technology, all relevant safety information is displayed and managed in real time on a unified platform, making safety monitoring more intuitive and efficient, strengthening real-time monitoring of the plant area, improving preventive measures and emergency response capabilities, and ensuring the continued safe operation of the power plant.

[0004] Traditional plant safety management and control methods in thermal power plants and various industrial environments rely on static safety monitoring systems and lack the ability to dynamically respond to real-time data, resulting in insufficient response speed in equipment failure prevention and emergency response. They rely on late-stage event analysis and response rather than prevention through real-time analysis, which limits the foresight and preventive nature of risk management. The comprehensive location tracking and behavior analysis of personnel is insufficiently covered, resulting in blind spots in the identification and control of internal risks. In terms of personnel management, there is a lack of efficient identity authentication and location tracking integrated systems, which makes the plant security subject to the risk of unauthorized access, affecting the safety of personnel and facilities. 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 multi-dimensional safety management and control method and system for a thermal power plant.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme, a multi-dimensional safety control method for a thermal power plant, comprising the following steps:

[0007] S1: Based on the location information of the thermal power plant, the building CAD drawings are analyzed and the internal structure of the thermal power plant is scanned to identify the facility elements and spatial location information, build a building information model, and generate a model construction record;

[0008] S2: Based on the model construction record, the location information of the IoT sensor is collected and input into the building information model, and the health status of multiple devices is monitored in real time to generate device safety status information;

[0009] S3: Based on the equipment safety status information, real-time video information inside the thermal power plant is collected, the identity and authorization status of the personnel entering and leaving the thermal power plant are verified in real time, and the location information of multiple personnel is synchronized into the information model to generate personnel location tracking information;

[0010] S4: Based on the personnel location tracking information, by analyzing the video data, analyzing personnel behavior in real time and monitoring the factory perimeter, detecting personnel intrusion and abnormal behavior, and generating perimeter security event records;

[0011] S5: Based on the perimeter security event record, the behavior of the personnel inside the thermal power plant is analyzed using the video data, risk behaviors are identified and mapped to the building information model, and behavior analysis results are generated;

[0012] S6: Based on the behavior analysis results, the use process of the work ticket and the operation ticket is monitored in real time, and by tracking the status and location of the two tickets, operational deviations and behavioral risks are identified, and safety management and control monitoring records are generated.

[0013] As a further solution of the present invention, the model construction record includes building structure information, facility space configuration data, and location information mapping records; the equipment safety status information includes equipment operation data sets, sensor location information, and sensor data input records to the building information model; the personnel location tracking information includes employee identity recognition results, personnel location coordinate information, and personnel movement trajectory diagrams; the perimeter security event records include alarm triggering events, location information of the event, and time information of the event; the behavior analysis results include identified risk behavior type information, personnel identification information, and the area where the behavior occurs; the security management and control monitoring records include two-ticket status tracking records, deviation operation identification records, and operator identity information verification records.

[0014] As a further solution of the present invention, based on the location information of the thermal power plant, the steps of analyzing the building CAD drawings and scanning the internal structure of the thermal power plant, identifying the facility elements and the spatial location information, constructing the building information model, and generating the model construction record are specifically as follows:

[0015] S101: Based on the location information of the thermal power plant, the structural design data in the architectural CAD drawings are analyzed to identify the spatial layout and various key structural elements, and generate an internal structure data set;

[0016] S102: Based on the internal structure data set, perform a three-dimensional scan of the internal structure of the thermal power plant, perform quality enhancement and feature extraction on the scanned image, identify and annotate location information of multiple key facility elements, and generate facility element positioning data;

[0017] S103: Based on the facility element positioning data, a building information model of the thermal power plant is constructed, and the location data is mapped into the model, the equipment location information in the model is synchronized and corrected, and a model construction record is generated.

[0018] As a further solution of the present invention, based on the model construction record, the location information of the IoT sensor is collected and input into the building information model, and the health status of multiple devices is monitored in real time to generate the device safety status information in the following steps:

[0019] S201: Based on the model construction record, the location information of multiple IoT sensors inside the thermal power plant is collected, the type information of the sensors is recorded, and a sensor configuration list is generated;

[0020] S202: mapping multiple sensors into a building information model according to the sensor configuration list, and receiving monitoring data of the sensors in real time to generate a real-time sensor data stream;

[0021] S203: Analyze the real-time sensor data stream, monitor various operating parameters of multiple key equipment inside the thermal power plant, including temperature, pressure and power, evaluate the health status of multiple equipment and input it into the building information model to generate equipment safety status information.

[0022] As a further solution of the present invention, based on the equipment safety status information, real-time video information inside the thermal power plant is collected, the identity and authorization status of the personnel entering and leaving are verified in real time, and the location information of multiple personnel is synchronized to the information model. The steps of generating personnel location tracking information are specifically as follows:

[0023] S301: Based on the equipment safety status information, using an image acquisition device, real-time video information of multiple locations of the thermal power plant, including multiple key locations at the entrance and inside, is collected to generate a video data collection record;

[0024] S302: Based on the video data collection record, by analyzing the video data at the entrance, identifying the identity of the person entering and leaving and comparing it with the authorization information in the database, identifying the authorization status, and generating an identity authentication result;

[0025] S303: Based on the identity authentication result, by analyzing the video data of multiple internal locations, the location information and movement trajectories of multiple persons are identified and recorded, and synchronously mapped to the building information model to generate personnel location tracking information.

[0026] As a further solution of the present invention, based on the personnel location tracking information, by analyzing the video data, analyzing personnel behavior in real time and monitoring the factory perimeter, detecting personnel intrusion and abnormal behavior, and generating perimeter security event records are specifically as follows:

[0027] S401: Based on the personnel location tracking information, use an image acquisition device to monitor the perimeter of the factory area in real time, map the location information to a building information model, and generate perimeter monitoring data;

[0028] S402: Based on the perimeter monitoring data, analyzing the moving objects in the video, recording the moving path and speed of the objects, identifying abnormal behaviors and intrusion behaviors, calculating the degree of abnormality, and generating abnormal behavior detection results;

[0029] S403: Based on the abnormal behavior detection result, according to the location and time information of the abnormal behavior and the intrusion behavior, the warning information content is matched and sent to the management personnel to generate a perimeter security event record.

[0030] As a further solution of the present invention, the specific formula for calculating the abnormality degree is:

[0031]

[0032] Among them, u and v represent the optical flow vector components in the horizontal and vertical directions, the numerical value represents the speed change, which is used to capture the motion state of the object in the picture, T represents the set speed threshold, and E represents the calculated speed anomaly index, which is used to determine whether it exceeds the threshold and identify potential abnormal behavior.

[0033] As a further solution of the present invention, based on the perimeter security event record, the behavior of personnel inside the thermal power plant is analyzed using video data, risk behaviors are identified and mapped to the building information model, and the steps of generating behavior analysis results are specifically as follows:

[0034] S501: Based on the perimeter safety event record, by analyzing the video data inside the thermal power plant, identifying and recording the safety equipment wearing status of the operators, including recording the identity and location information of the personnel who are not wearing safety helmets, and generating safety equipment inspection results;

[0035] S502: Based on the safety equipment inspection results, analyze the video data to identify illegal operation behaviors, including entering a prohibited operation area, using unauthorized tools and equipment, and violating operating procedures, record the time and location of the violation, and generate a violation record;

[0036] S503: According to the violation record, the location data and identity data of the violator are input into the building information model to generate a behavior analysis result.

[0037] As a further solution of the present invention, according to the behavior analysis results, the use process of the work ticket and the operation ticket is monitored in real time, and the operation deviation and behavior risk are identified by tracking the status and location of the two tickets, and the steps of generating a safety control monitoring record are specifically as follows:

[0038] S601: Based on the behavior analysis results, the usage of the work ticket and the operation ticket is tracked in real time, the issuance and usage status of the two tickets are recorded, and a ticket usage tracking record is generated;

[0039] S602: Analyze the ticket usage tracking record, identify the usage of the two tickets that does not meet the safety standards by real-time tracking the location and usage information of the two tickets, and generate an operation deviation analysis result;

[0040] S603: According to the operation deviation analysis results, identify and record the operation deviation and behavior risks, send warning information to the management personnel, and generate security management and control monitoring records.

[0041] A multi-dimensional safety control system for a thermal power plant, the multi-dimensional safety control system for a thermal power plant is used to execute the multi-dimensional safety control method for a thermal power plant, the system comprising:

[0042] The model building module uses the location information of the thermal power plant, the building CAD drawings and the internal structure scanning data to identify and extract the spatial location information of the facility, build a building information model, enter the location data, and generate the structural information mapping results;

[0043] The data integration module collects the location information of multiple IoT sensors based on the structural information mapping result and inputs it into the building information model, and monitors the operating status of multiple devices in real time to generate device status monitoring records;

[0044] The identity authentication module performs facial recognition verification on the in-and-out personnel through the image acquisition device based on the equipment status monitoring record, and tracks the position of the personnel in the building information model in real time to generate the personnel access permission status;

[0045] The behavior monitoring module monitors the personnel behavior and perimeter security in the factory area in real time based on the personnel access rights status, identifies abnormal behavior, and performs risk assessment to record the location, personnel identity, and time information of risk events, and generates perimeter and behavior security information;

[0046] Based on the perimeter and behavioral security information, the security audit module tracks and reviews the use of work tickets and operation tickets in real time, evaluates the compliance of operations, identifies operational deviations and behavioral risks, and generates security management and control monitoring records.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by analyzing CAD drawings and collecting internal scanning data of thermal power plants, a building information model is constructed to realize the visualization of facility and equipment layout, making safety monitoring more intuitive and accurate. The real-time data input of IoT sensors enhances the monitoring capability of equipment health status. Through personnel identity authentication, unauthorized access and internal risk events are effectively prevented. Combined with the identification of risky behaviors, the timeliness and effectiveness of preventive measures are enhanced. The status and location of work tickets and operation tickets are monitored in real time, and operational deviations and behavioral risks are identified, thereby improving the safety and compliance of operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0056] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0057] 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.

[0058] 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.

[0059] See also Figure 1 The present invention provides a technical solution, a multi-dimensional safety control method for a thermal power plant, comprising the following steps:

[0060] S1: Based on the location information of the thermal power plant, the building CAD drawings are analyzed and the internal structure of the thermal power plant is scanned to identify the facility elements and spatial location information, build a building information model, and generate a model construction record;

[0061] S2: Based on the model construction record, the location information of the IoT sensor is collected and input into the building information model, and the health status of multiple devices is monitored in real time to generate device safety status information;

[0062] S3: Based on the equipment safety status information, real-time video information inside the thermal power plant is collected, the identity and authorization status of the personnel entering and leaving the thermal power plant are verified in real time, and the location information of multiple personnel is synchronized into the information model to generate personnel location tracking information;

[0063] S4: Based on the personnel location tracking information, by analyzing the video data, analyzing personnel behavior in real time and monitoring the factory perimeter, detecting personnel intrusion and abnormal behavior, and generating perimeter security event records;

[0064] S5: Based on the perimeter security event record, the behavior of the personnel inside the thermal power plant is analyzed using the video data, risk behaviors are identified and mapped to the building information model, and behavior analysis results are generated;

[0065] S6: Based on the behavior analysis results, the use process of the work ticket and the operation ticket is monitored in real time, and by tracking the status and location of the two tickets, operational deviations and behavioral risks are identified, and safety management and control monitoring records are generated.

[0066] The model construction record includes building structure information, facility space configuration data, and location information mapping records; the equipment safety status information includes equipment operation data sets, sensor location information, and sensor data input records to the building information model; the personnel location tracking information includes employee identity recognition results, personnel location coordinate information, and personnel movement trajectory diagrams; the perimeter security event records include alarm triggering events, location information of the event, and time information of the event; the behavior analysis results include identified risk behavior type information, personnel identification information, and the area where the behavior occurs; the security management and control monitoring records include two-ticket status tracking records, deviation operation identification records, and operator identity information verification records.

[0067] See also Figure 2 ,Based on the location information of the thermal power plant, the architectural CAD drawings are analyzed and the internal structure of the thermal power plant is scanned, the facility elements and spatial location information are identified, and the building information model is constructed. The specific steps of generating the model construction record are as follows:

[0068] S101: Based on the location information of the thermal power plant, the structural design data in the architectural CAD drawings are analyzed to identify the spatial layout and various key structural elements, and generate an internal structure data set;

[0069] In sub-step S101, the location information from the thermal power plant is analyzed, and the CAD software is used to identify the structural design data and analyze the spatial layout. The image processing technology is used to identify the structural elements in the CAD drawings, such as beams, columns and supporting structures. The edge detection algorithms Canny and Sobel algorithms are used to extract the boundaries and structural contours of the architectural drawings. The image data is processed through the computer vision library OpenCV, and the geometric information and dimensional data in the image are extracted to form a structured data set. The data set includes the location, size and relative relationship of all key structural elements with multiple elements, supports subsequent spatial layout analysis and internal design planning, and continuously adjusts the accuracy of element recognition through multiple iterations of the optimization algorithm to generate an internal structure data set to ensure high data quality and availability.

[0070] S102: Based on the internal structure data set, perform a three-dimensional scan of the internal structure of the thermal power plant, perform quality enhancement and feature extraction on the scanned image, identify and annotate location information of multiple key facility elements, and generate facility element positioning data;

[0071] In the above content, a three-dimensional scan of a thermal power plant is performed based on the internal structure data set, and the formula Calculate distances between facility elements;

[0072] Where D is the Euclidean distance between two points, x1, y1, z1 represent the three-dimensional coordinate starting point of a key facility element, and x2, y2, z2 represent the three-dimensional coordinate end point of another key facility element;

[0073] Detailed explanation of the formula and the process of formula calculation and derivation:

[0074] Assume that the starting coordinates of a key facility in a thermal power plant are (0, 0, 0) and the ending coordinates are (3, 4, 12). Calculate the Euclidean distance between the two points:

[0075]

[0076] Result 13 shows that the straight-line distance between the two facility elements is 13 meters. The distance data is used to correct and synchronize the equipment location information to the building information model to ensure that the facility layout in the model is consistent with the actual structure.

[0077] S103: constructing a building information model of the thermal power plant based on the facility element positioning data, mapping the location data into the model, synchronizing and correcting the equipment location information in the model, and generating a model construction record;

[0078] In sub-step S103, the building information modeling software Revit is used to construct the building information model of the thermal power plant based on the facility element positioning data. During the model construction process, the equipment location data obtained from two-dimensional and three-dimensional scanning is accurately mapped to the model. The mapping adopts coordinate transformation and data fusion technology, and uses transformation matrix and alignment algorithm to ensure data consistency and accuracy. The location information of each device in the model is corrected and synchronized in real time to reflect the actual physical layout. The model construction record generated after completing the target step includes all the construction history of the model, equipment information and position correction records, ensuring that the model can be updated in real time and consistent with the actual structure. The record provides important data support for subsequent operation and maintenance.

[0079] See also Figure 3 , based on the model construction record, the location information of the IoT sensor is collected and input into the building information model, and the health status of multiple devices is monitored in real time. The steps of generating device safety status information are as follows:

[0080] S201: Based on the model construction record, the location information of multiple IoT sensors inside the thermal power plant is collected, the type information of the sensors is recorded, and a sensor configuration list is generated;

[0081] In sub-step S201, the location information of IoT sensors inside the thermal power plant is collected, and the database management system MySQL is used to record the type and location information of the sensors. The data collection is completed through IoT sensors installed at key structural points of the thermal power plant. Target sensors such as temperature sensors, pressure sensors and flow sensors have their unique identifiers and network addresses, and upload their location and status information to the central database in real time. The entry of each sensor in the database includes type, installation location, model, and production date. The network transmission protocol uses MQTT and CoAP to ensure the real-time and accuracy of the data. The generated sensor configuration list is to facilitate the subsequent accurate mapping and management of sensors in the building information model, ensuring the integrity of the data flow and the maintainability of the system.

[0082] S202: mapping multiple sensors into a building information model according to the sensor configuration list, and receiving monitoring data of the sensors in real time to generate a real-time sensor data stream;

[0083] In sub-step S202, according to the sensor configuration list, the sensor data is integrated into the building information model, and data fusion and model synchronization technology are used to operate through the BIM software Autodesk Revit. The process of receiving sensor data in real time involves the use of the IoT platform Thingworx, which supports multiple communication protocols and can process large amounts of data streams. A data channel is established for each sensor to ensure real-time updating and transmission of all monitoring data. The target data stream includes key operating indicators such as temperature and pressure, which provides a dynamic monitoring function for the system to ensure the safety and efficiency of the thermal power plant operation. The building information model reflects the data status and changes of each sensor in real time, enhancing the interactivity and practicality of the model.

[0084] S203: Analyze the real-time sensor data stream, monitor various operating parameters of multiple key equipment in the thermal power plant, including temperature, pressure and power, evaluate the health status of multiple equipment and input it into the building information model to generate equipment safety status information;

[0085] In sub-step S203, based on the real-time sensor data stream, the operating parameters of key equipment such as pumps, compressors and motors in the thermal power plant are monitored according to the formula

[0086] Calculate the health status indicators of the equipment and generate equipment safety status information;

[0087] In the formula, T represents the current temperature of the device, T ref is the reference temperature for normal operation of the equipment, P represents the current pressure, P ref is the reference value of normal operating pressure, W is the current power, Wref is the reference value of normal power, W T , W P , W W are the weight coefficients of temperature, pressure, and power in health status assessment, respectively, and H is the equipment health status indicator;

[0088] Detailed explanation of the formula and the process of formula calculation and derivation:

[0089] Assume that the temperature of a device during the test is 80°C, the normal reference temperature is 70°C, the current pressure is 100psi, the normal reference pressure is 90psi, the current power is 500kW, the normal reference power is 450kW, and the weight coefficients of temperature, pressure and power are 0.3, 0.3 and 0.4 respectively. Calculate the device health status index:

[0090]

[0091] The result H≈32.56 indicates that the current operating status of the equipment has a certain deviation compared with the reference normal value, and the health status index is high, indicating that the equipment needs maintenance and inspection. The results provide a practical quantitative evaluation for equipment operation health monitoring.

[0092] See also Figure 4 Based on the equipment safety status information, real-time video information inside the thermal power plant is collected, the identity and authorization status of the personnel entering and leaving the plant are verified in real time, and the location information of multiple personnel is synchronized to the information model. The steps for generating personnel location tracking information are as follows:

[0093] S301: Based on the equipment safety status information, using an image acquisition device, real-time video information of multiple locations of the thermal power plant, including multiple key locations at the entrance and inside, is collected to generate a video data collection record;

[0094] In sub-step S301, image acquisition equipment is used to conduct video surveillance of the thermal power plant, including the entrance and key internal locations. The equipment is set up in key locations, including the control room entrance, key channels and key mechanical equipment areas, covering important parts of the plant. The real-time acquired video data is transmitted to the central monitoring system through the optical fiber network and processed using the video analysis software MilestoneXProtect. The software is configured with motion detection and event-triggered recording functions to ensure that all key events are automatically recorded and saved. The generated video data acquisition record contains timestamps, location information and video clips. The target record provides real-time data support for security monitoring, enhances the ability and response speed of security management, and ensures plant safety and operational efficiency.

[0095] S302: Based on the video data collection record, by analyzing the video data at the entrance, identifying the identity of the person entering and leaving and comparing it with the authorization information in the database, identifying the authorization status, and generating an identity authentication result;

[0096] In sub-step S302, the video data at the entrance is analyzed to identify the identity of the person entering and leaving and compare it with the authorization information in the database. In the process, facial recognition technology is used to capture the facial image in the video according to the formula Calculate facial feature matching scores and generate identity verification results;

[0097] In the formula, x i,c and i,c Represents the X and Y coordinates of the currently captured i-th facial feature point, x i,r and i,r Respectively represent the X and Y coordinates of the corresponding registered facial feature point in the database, n is the total number of feature points, and R is the facial feature matching score;

[0098] Detailed explanation of the formula and the process of formula calculation and derivation:

[0099] Assume that there are two feature point coordinates. The currently captured coordinates are (30, 45) and (35, 50). The corresponding coordinates registered in the database are (32, 47) and (34, 48). Calculate the facial feature matching score:

[0100]

[0101] R=1-1.75=0.25

[0102] The score shows that the matching score between facial features is 0.25, reflecting that there is a certain deviation in the facial recognition process, but the feature points are relatively close, and the calculation provides a data basis for identity authentication.

[0103] S303: Based on the identity authentication result, by analyzing the video data of multiple internal locations, identifying and recording the location information and movement trajectories of multiple persons, synchronously mapping them to the building information model, and generating person location tracking information;

[0104] In sub-step S303, video surveillance and location analysis technology is used to capture video through the internal camera system, and the multi-target tracking framework of the personnel tracking algorithm is applied to analyze the movement of personnel in the video, identify the individual's location information and action path, and the target data is processed by real-time video analysis software, such as Hikvision IVMS-5200, to ensure accurate tracking of each person's real-time location and movement trajectory. The generated personnel location tracking information is synchronized to the building information model and mapped using Autodesk Revit, which improves the real-time and accuracy of internal security monitoring, provides the security team with real-time and dynamic security management data, supports emergency response and accident investigation, and ensures the safety of personnel and safe operation of the factory.

[0105] See also Figure 5 Based on the personnel location tracking information, by analyzing the video data, analyzing personnel behavior in real time and monitoring the factory perimeter, detecting personnel intrusion and abnormal behavior, and generating perimeter security event records, the specific steps are:

[0106] S401: Based on the personnel location tracking information, use an image acquisition device to monitor the perimeter of the factory area in real time, map the location information to a building information model, and generate perimeter monitoring data;

[0107] In sub-step S401, cameras and infrared sensors are used to conduct all-weather real-time monitoring of the perimeter of the thermal power plant. They are deployed on walls, gates and multiple key entrances. The monitoring equipment transmits video data to the central monitoring system in real time through a fiber optic network. The video management software Genetec Security Center is used to process and store video data, synchronize the captured images with the building information model, and use geographic information system technology for location mapping to ensure that the viewing angle and location data of each camera accurately correspond to the geographic location in the model, increase the visualization of the perimeter security of the plant, and make security monitoring more intuitive. The perimeter monitoring data includes the field of view of each camera, the recording timestamp and the related event tags, which provides real-time data support for the security team and enhances the management and response capabilities of the perimeter security of the plant.

[0108] S402: Based on the perimeter monitoring data, analyzing the moving objects in the video, recording the moving path and speed of the objects, identifying abnormal behaviors and intrusion behaviors, calculating the degree of abnormality, and generating abnormal behavior detection results;

[0109] The specific formula for calculating the abnormality degree is:

[0110]

[0111] Among them, u and v represent the optical flow vector components in the horizontal and vertical directions, the numerical value represents the speed change, which is used to capture the motion state of the object in the picture, T represents the set speed threshold, and E represents the calculated speed anomaly index, which is used to determine whether it exceeds the threshold and identify potential abnormal behavior.

[0112] formula:

[0113]

[0114] Detailed explanation of the formula and the process of formula calculation and derivation:

[0115] The formula is used to calculate the degree of abnormal motion of the target object in the video. When the result is greater than 0, it indicates that the behavior of the object may be abnormal;

[0116] Parameter meaning and setting value:

[0117] u is the difference in the horizontal moving speed of the target object between two consecutive video frames. Assume that in the monitored video, an object moves 15 pixels horizontally from one frame to the next;

[0118] v is the difference in the vertical moving speed of the target object between two consecutive video frames. Assume that in the monitored video, the same object moves 10 pixels in the vertical direction;

[0119] T is the speed threshold set based on historical data, which is used to define what speed changes are considered abnormal. Assume that T is 20 pixels / frame;

[0120] Substitute the parameters into the formula for calculation:

[0121]

[0122] E=18.03-20

[0123] E=-1.97

[0124] The result -1.97 indicates that the behavior of the target object is not abnormal under the currently set threshold, and the movement speed does not exceed the preset abnormal behavior threshold T. The result is used to judge the safety status of the factory perimeter.

[0125] S403: Based on the abnormal behavior detection result, according to the location and time information of the abnormal behavior and the intrusion behavior, match the warning information content and send it to the management personnel to generate a perimeter security event record;

[0126] In sub-step S403, based on the abnormal behavior detection results, the event management system SAPEventManagement is used to match events and generate warning information. Based on the type, location and time information of the abnormal behavior, appropriate alarm content is selected from the preset alarm template and sent to the corresponding management personnel. The process involves real-time data processing and communication technology to ensure that all key information can be conveyed to the security team that needs to respond in the shortest time. The generated perimeter security event record records the details of each warning, including the cause, time, location and measures taken, which improves the management efficiency and handling speed of perimeter security incidents and ensures the overall safety of the factory.

[0127] See also Figure 6 Based on the perimeter security event records, the behavior of personnel inside the thermal power plant is analyzed using video data, risk behaviors are identified and mapped to the building information model, and the steps for generating behavior analysis results are as follows:

[0128] S501: Based on the perimeter safety event record, by analyzing the video data inside the thermal power plant, identifying and recording the safety equipment wearing status of the operators, including recording the identity and location information of the personnel who are not wearing safety helmets, and generating safety equipment inspection results;

[0129] In sub-step S501, the activities of operators in the thermal power plant are analyzed through a high-resolution video surveillance system, with a focus on checking whether the operators are wearing safety equipment. The deep learning model YOLO is used to detect safety helmets. The system scans each operator in the video in real time and automatically identifies whether they are wearing safety helmets. People who are not wearing safety helmets are marked and their specific locations and identity information are recorded. The database MySQL is used to save the target inspection results, including the identity, location information and timestamp of the people not wearing safety helmets. The generated safety equipment inspection results generate a record for each video inspection cycle to ensure the effectiveness and timeliness of the safety inspection, and provide basic data support for subsequent violation inspections and safety audits.

[0130] S502: Based on the safety equipment inspection results, analyze the video data to identify illegal operation behaviors, including entering a prohibited operation area, using unauthorized tools and equipment, and violating operating procedures, record the time and location of the violation, and generate a violation record;

[0131] In sub-step S502, based on the results of the safety equipment inspection, video data analysis is used to identify potential violations of operators, and the video analysis software IBM Watson Video Analytics is used to detect entering restricted areas and irregular operations. Combined with computer vision technology and deep learning algorithms, unauthorized operations are automatically marked, including unauthorized entry into restricted areas, use of unapproved equipment, and non-compliant operations. During the analysis process, an anomaly detection algorithm is used to monitor and identify each operation in real time, record the specific time, location and identity of the operator of the violation, and store the target data in the violation record generated in the database, providing a basis for subsequent safety management and violation review.

[0132] S503: According to the violation record, the location data and identity data of the violator are input into the building information model to generate a behavior analysis result;

[0133] In sub-step S503, the location information and identity information of the violators are integrated into the building information model using the generated violation records. Autodesk Revit and Navisworks are used to update the model, and the recorded data is synchronously mapped with the building model. The spatial location of the personnel behavior is analyzed and visualized to form a behavior analysis result. The result helps managers identify concentrated areas of high-frequency violations and provides an optimization basis for subsequent safety management. The generated behavior analysis results contain the information of each violator, the activity path in the factory, and related violation incidents, which enhances the comprehensive control capability of on-site operations and contributes to effective risk prevention and personnel management.

[0134] See also Figure 7 According to the behavior analysis results, the use process of work tickets and operation tickets is monitored in real time. By tracking the status and location of the two tickets, operation deviations and behavior risks are identified, and the steps for generating safety control monitoring records are as follows:

[0135] S601: Based on the behavior analysis results, the usage of the work ticket and the operation ticket is tracked in real time, the issuance and usage status of the two tickets are recorded, and a ticket usage tracking record is generated;

[0136] In sub-step S601, the work tickets and operation tickets of the thermal power plant are tracked through the real-time monitoring system. The system uses radio frequency identification technology to record the issuance and use status of each ticket. The status of the ticket includes the allocation of the ticket, the authorized person, the use time and the use location information. The target information is transmitted to the central database through the RFID tag for recording and storage. The management system SAPPM is used to manage and monitor the circulation process of all tickets, update the use status of each ticket in real time, and store the use records in categories. The generated ticket use tracking record lists the full life cycle information of each ticket, including the use trajectory and current status in the factory, providing data support for tracing usage and improving the transparency of ticket management.

[0137] S602: Analyze the ticket usage tracking record, identify the usage of the two tickets that does not meet the safety standards by real-time tracking the location and usage information of the two tickets, and generate an operation deviation analysis result;

[0138] In sub-step S602, by analyzing the ticket usage tracking records, it is detected in real time whether the usage of the two tickets meets the safety standards. The data analysis tool Tableau is used to analyze and visualize the location, usage duration and operator information of the tickets. Combined with the safety standards configured by the rule engine Drools, the ticket usage situations with operational deviations are identified. The rule engine compares the ticket usage process one by one to screen whether the usage operation meets the safety specifications, including whether it is returned on time and whether it is used in the specified area. The generated operational deviation analysis results describe the deviation, including the time, place and related ticket information of the deviation, providing traceable data support for factory safety management and analyzing safety hazards.

[0139] S603: According to the operation deviation analysis results, identify and record the operation deviation and behavior risks, send warning information to the management personnel, and generate security control monitoring records;

[0140] In sub-step S603, based on the results of the operational deviation analysis, the deviation behaviors that lead to operational risks are identified and recorded, and early warning information is sent to management personnel through the behavior monitoring module. The system combines the data management platform Splunk to conduct risk level assessment on the deviation behaviors. The system analyzes the severity of the deviation, including the frequency of the behavior, the areas involved and the type of deviation. Through the early warning mechanism, the information is automatically pushed to the management terminal to provide timely safety warnings for management personnel. The generated safety management and control monitoring records include records of deviation events, risk level assessment results and response measures. Recommendations improve the safety management capabilities of thermal power plants and the effectiveness of risk prevention mechanisms, ensuring efficient operation and safety management of the plant.

[0141] See also Figure 8A multi-dimensional safety control system for a thermal power plant is provided. The multi-dimensional safety control system for a thermal power plant is used to execute the multi-dimensional safety control method for a thermal power plant. The system includes:

[0142] The model building module uses the location information of the thermal power plant, the building CAD drawings and the internal structure scanning data to identify and extract the spatial location information of the facility, build a building information model, enter the location data, and generate the structural information mapping results;

[0143] The data integration module collects the location information of multiple IoT sensors based on the structural information mapping result and inputs it into the building information model, and monitors the operating status of multiple devices in real time to generate device status monitoring records;

[0144] The identity authentication module performs facial recognition verification on the in-and-out personnel through the image acquisition device based on the equipment status monitoring record, and tracks the position of the personnel in the building information model in real time to generate the personnel access permission status;

[0145] The behavior monitoring module monitors the personnel behavior and perimeter security in the factory area in real time based on the personnel access rights status, identifies abnormal behavior, and performs risk assessment to record the location, personnel identity, and time information of risk events, and generates perimeter and behavior security information;

[0146] Based on the perimeter and behavioral security information, the security audit module tracks and reviews the use of work tickets and operation tickets in real time, evaluates the compliance of operations, identifies operational deviations and behavioral risks, and generates security management and control monitoring records.

[0147] 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. A multi-dimensional safety control method for a thermal power plant, characterized in that: The following steps are involved: Based on the location information of the thermal power plant, the building CAD drawings are analyzed and the internal structure of the thermal power plant is scanned to identify the facility elements and spatial location information, build a building information model, and generate a model construction record; Based on the model construction record, the location information of the IoT sensor is collected and input into the building information model, and the health status of multiple devices is monitored in real time to generate device safety status information; Based on the equipment safety status information, real-time video information inside the thermal power plant is collected, the identity and authorization status of people entering and leaving the plant are verified in real time, and the location information of multiple people is synchronized into the information model to generate personnel location tracking information; Based on the personnel location tracking information, by analyzing the video data, analyzing personnel behavior in real time and monitoring the factory perimeter, detecting personnel intrusion and abnormal behavior, and generating perimeter security event records; Based on the perimeter security event records, the behaviors of personnel inside the thermal power plant are analyzed using video data, risk behaviors are identified and mapped to the building information model, and behavior analysis results are generated; Based on the behavioral analysis results, the use process of work tickets and operation tickets is monitored in real time. By tracking the status and location of the two tickets, operational deviations and behavioral risks are identified, and safety management and control monitoring records are generated.

2. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: The model construction record includes building structure information, facility space configuration data, and location information mapping records; the equipment safety status information includes equipment operation data sets, sensor location information, and sensor data input records to the building information model; the personnel location tracking information includes employee identity recognition results, personnel location coordinate information, and personnel movement trajectory diagrams; the perimeter security event records include alarm triggering events, location information of the event, and time information of the event; the behavior analysis results include identified risk behavior type information, personnel identification information, and the area where the behavior occurs; the security management and control monitoring records include two-ticket status tracking records, deviation operation identification records, and operator identity information verification records.

3. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: Based on the location information of the thermal power plant, the steps of analyzing the architectural CAD drawings and scanning the internal structure of the thermal power plant, identifying the facility elements and spatial location information, building the building information model, and generating the model construction record are as follows: Based on the location information of the thermal power plant, the structural design data in the architectural CAD drawings is analyzed, the spatial layout and various key structural elements are identified, and the internal structure data set is generated; Based on the internal structure data set, a three-dimensional scan is performed on the internal structure of the thermal power plant, quality enhancement and feature extraction are performed on the scanned image, location information of multiple key facility elements is identified and annotated, and facility element positioning data is generated; Based on the facility element positioning data, a building information model of the thermal power plant is constructed, and the location data is mapped into the model, the equipment location information in the model is synchronized and corrected, and a model construction record is generated.

4. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: Based on the model construction record, the location information of the IoT sensor is collected and input into the building information model, and the health status of multiple devices is monitored in real time to generate the device safety status information. Specifically, the steps are as follows: Based on the model construction record, the location information of multiple IoT sensors inside the thermal power plant is collected, the type information of the sensors is recorded, and a sensor configuration list is generated; According to the sensor configuration list, multiple sensors are mapped into a building information model, and monitoring data of the sensors are received in real time to generate a real-time sensor data stream; The real-time sensor data stream is analyzed to monitor various operating parameters of multiple key equipment inside the thermal power plant, including temperature, pressure and power, and the health status of multiple equipment is evaluated and input into the building information model to generate equipment safety status information.

5. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: Based on the equipment safety status information, real-time video information inside the thermal power plant is collected, the identity and authorization status of the personnel entering and leaving the plant are verified in real time, and the location information of multiple personnel is synchronized to the information model. The steps for generating personnel location tracking information are as follows: Based on the equipment safety status information, using image acquisition equipment, real-time video information of multiple locations of the thermal power plant, including multiple key locations at the entrance and inside, is collected to generate video data acquisition records; Based on the video data collection record, by analyzing the video data at the entrance, identifying the identity of the person entering and leaving and comparing it with the authorization information in the database, identifying the authorization status, and generating an identity authentication result; Based on the identity authentication result, the video data of multiple internal locations are analyzed to identify and record the location information and movement trajectories of multiple personnel, and synchronously map them to the building information model to generate personnel location tracking information.

6. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: Based on the personnel location tracking information, by analyzing the video data, analyzing personnel behavior in real time and monitoring the factory perimeter, detecting personnel intrusion and abnormal behavior, and generating perimeter security event records are specifically as follows: Based on the personnel location tracking information, the perimeter of the factory area is monitored in real time using an image acquisition device, and the location information is mapped to a building information model to generate perimeter monitoring data; Based on the perimeter monitoring data, analyzing the moving objects in the video, recording the moving path and speed of the objects, identifying abnormal behaviors and intrusion behaviors, calculating the degree of abnormality, and generating abnormal behavior detection results; Based on the abnormal behavior detection results, the warning information content is matched and sent to the management personnel according to the location and time information of the abnormal behavior and the intrusion behavior, and a perimeter security event record is generated.

7. The multi-dimensional safety control method for a thermal power plant according to claim 6 is characterized in that: The specific formula for calculating the abnormality degree is: Among them, u and v represent the optical flow vector components in the horizontal and vertical directions, the numerical value represents the speed change, which is used to capture the motion state of the object in the picture, T represents the set speed threshold, and E represents the calculated speed anomaly index, which is used to determine whether it exceeds the threshold and identify potential abnormal behavior.

8. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: Based on the perimeter security event records, the behavior of personnel inside the thermal power plant is analyzed using video data, risk behaviors are identified and mapped to the building information model, and the steps for generating behavior analysis results are as follows: Based on the perimeter safety event record, by analyzing the video data inside the thermal power plant, the safety equipment wearing status of the operators is identified and recorded, including the identity and location information of the personnel who are not wearing safety helmets, and the safety equipment inspection results are generated; Based on the safety equipment inspection results, analyze the video data to identify illegal operating behaviors, including entering prohibited operating areas, using unauthorized tools and equipment, and violating operating procedures, record the time and location of the violation, and generate a record of the violation; According to the violation records, the location data and identity data of the violators are input into the building information model to generate behavior analysis results.

9. The multi-dimensional safety control method for a thermal power plant according to claim 1 is characterized in that: According to the behavior analysis results, the use process of work tickets and operation tickets is monitored in real time. By tracking the status and location of the two tickets, operation deviations and behavior risks are identified, and the steps for generating safety control monitoring records are as follows: Based on the behavior analysis results, the use of work tickets and operation tickets is tracked in real time, the issuance and use status of the two tickets are recorded, and the ticket use tracking record is generated; Analyze the ticket usage tracking records, identify the usage of the two tickets that does not meet the safety standards by real-time tracking of the location and usage information of the two tickets, and generate operation deviation analysis results; Based on the operational deviation analysis results, operational deviations and behavioral risks are identified and recorded, and early warning information is sent to management personnel to generate safety management and control monitoring records.

10. A multi-dimensional safety control system for a thermal power plant, characterized in that: According to the multi-dimensional safety management and control method for a thermal power plant according to any one of claims 1 to 9, the system comprises: The model building module uses the location information of the thermal power plant, the building CAD drawings and the internal structure scanning data to identify and extract the spatial location information of the facility, build a building information model, enter the location data, and generate the structural information mapping results; The data integration module collects the location information of multiple IoT sensors based on the structural information mapping result and inputs it into the building information model, and monitors the operating status of multiple devices in real time to generate device status monitoring records; The identity authentication module performs facial recognition verification on the in-and-out personnel through the image acquisition device based on the equipment status monitoring record, and tracks the position of the personnel in the building information model in real time to generate the personnel access permission status; The behavior monitoring module monitors the personnel behavior and perimeter security in the factory area in real time based on the personnel access rights status, identifies abnormal behavior, and performs risk assessment to record the location, personnel identity, and time information of risk events, and generates perimeter and behavior security information; Based on the perimeter and behavioral security information, the security audit module tracks and reviews the use of work tickets and operation tickets in real time, evaluates the compliance of operations, identifies operational deviations and behavioral risks, and generates security management and control monitoring records.

Images