Risk quantification control method and system for intelligent safety production
By collecting environmental, equipment and personnel parameters in the power plant, using risk quantification models and GIS map display, the hierarchical control mechanism is triggered, and the precise quantification and real-time management of power plant production risks is solved, and efficient production safety control is achieved.
Patent Information
- Application Number
- CN202510564054.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-30
- Publication Date
- 2025-08-19
AI Technical Summary
It is difficult for the existing technology to achieve accurate quantitative control of production risks in power plants, especially under the influence of multi-dimensional equipment, environment and personnel factors. The traditional safety management model has problems such as inaccurate data collection, incomplete risk identification, and in real-time control measures.
By collecting the plant environment, equipment and personnel parameters, using the production risk quantitative model for risk quantitative analysis, and visually display based on the GIS map, triggering a hierarchical control mechanism, including electronic alarms, patrols and equipment interlocking protection measures.
It realizes accurate quantification and intelligent control of power plant production risks, improves the coverage dimensions of risk identification and the real-time response, and ensures the stable and safe operation of power plants.
Smart Images

Figure CN120509717A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power plant safety management, and in particular to a risk quantification control method and system for smart production safety. Background Art
[0002] In today's society, with the rapid development of industry, power plants, as important energy suppliers, are experiencing a continuous expansion in their production and operations. However, as the scale of power plant production expands, the number of equipment, process flows, and complexity of operational scenarios increase significantly. Traditional safety management models are gradually exposing shortcomings in terms of data collection accuracy, comprehensive risk identification, and real-time control measures. For example, limited staff resources make it difficult to refine safety management, with a significant amount of time consumed by repetitive daily tasks, making it difficult to conduct systematic risk analysis and preventative measures in a timely manner. Furthermore, safety management is limited by the traditional manual experience-based approach. Furthermore, power plant risk sources are dynamic and multi-dimensional, such as aging equipment, environmental changes, and human error. Relying solely on qualitative assessments makes it difficult to accurately identify high-risk areas, leading to blind spots in management and control.
[0003] Currently, in the field of power production safety, some companies have begun experimenting with introducing various information technologies to improve safety management. For example, some companies are leveraging the Internet of Things (IoT) to monitor equipment status in real time. Sensors collect operational data, providing preliminary early warnings of potential risks. Others are employing big data analytics to analyze historical safety data and identify patterns in the occurrence of safety incidents. Overall, however, these applications are still at a relatively nascent stage. Most systems only implement simple data collection and preliminary analysis capabilities, failing to establish a comprehensive system capable of fully controlling production risks.
[0004] Furthermore, achieving intelligent management and control of power plant production risks presents numerous challenges. Power plant production involves numerous complex equipment and process flows, with interconnectedness between different equipment and processes. The complex and ever-changing production environment of power plants, influenced by factors such as the external environment and equipment aging, can lead to changes in risk profiles at any time. This requires high levels of real-time and adaptable risk management, while manual approvals and on-site inspections are inefficient and cannot meet the rapid response requirements for high-risk operations. Furthermore, existing technical approaches have significant limitations when dealing with such complex and ever-changing situations, making it difficult for power plants to meet their needs for precise, quantitative control of production risks. Summary of the Invention
[0005] The present invention aims to provide a risk quantification control method and system for smart production safety, which can accurately quantify the production risks of power plants and perform visual intelligent management and control, with high real-time performance and reliability.
[0006] To achieve the above objectives, the present invention provides the following basic solutions.
[0007] Option 1
[0008] A risk quantification control method for smart production safety, comprising the following steps:
[0009] Step 1: Collect plant monitoring data and store it in a risk database; the plant monitoring data includes environmental parameters, equipment parameters, and personnel parameters;
[0010] Step 2: The production risk quantification model performs a risk quantification analysis based on the risk operations selected in the risk database, and outputs risk index values by region, which are then visualized by a visualization unit. The visualization unit is loaded with a plant layout diagram of the power plant, and the visualization unit displays the risk index values by region on the plant layout diagram.
[0011] Step 3: When the risk indicator value exceeds the threshold, the hierarchical control mechanism is triggered.
[0012] Furthermore, in step 1, the environmental parameters include temperature, humidity, wind speed, wind direction, air pressure, precipitation, dust concentration, and risk gas concentration; the equipment parameters include equipment operation data; and the personnel parameters include personnel duty records, personnel inspection records, personnel operation records, and personnel trajectory data.
[0013] Furthermore, the risk index values are divided into level 1 - low risk, level 2 - general risk, level 3 - greater risk, and level 4 - major risk; and the levels are calculated and confirmed according to the LEC evaluation method.
[0014] Furthermore, the visualization unit displays risk index values based on the GIS map, and represents the corresponding areas with four-color maps according to different risk levels; risk levels 1 to 4 correspond to blue, yellow, orange and red, respectively.
[0015] Furthermore, the hierarchical control mechanism includes: when the risk level is level 1, triggering an electronic alarm in the area; and displaying an alarm notification in the visualization unit;
[0016] When the risk level is level 2, electronic alarms are triggered in the area and adjacent areas; alarm notifications are displayed in the visualization unit and staff inspections are arranged in the area;
[0017] When the risk level reaches Level 3, electronic alarms are triggered within the area and adjacent areas. A pop-up alarm notification is displayed in the visualization unit, an emergency approval form is issued to the area manager, and professional safety officers are arranged for inspections.
[0018] When the risk level reaches Level 4, an electronic alarm for the entire area is triggered; a pop-up alarm notification is forcibly displayed in the visualization unit, an emergency management notification is sent to the area manager and professional safety officer, and automatic interlock protection of key equipment is activated.
[0019] Furthermore, in step 1, when collecting plant area monitoring data, the data is collected and stored by region.
[0020] Furthermore, the area division method includes: dividing the boiler area, steam turbine area, main transformer area, start-up and standby transformer area, fuel area, cooling tower area, desulfurization area, chemical water area, electrostatic precipitator area, hydrogen production station area, oil depot area, start-up boiler area, and urea solution preparation workshop area according to regional function.
[0021] Furthermore, an electronic fence is provided around each area; the visualization unit is also used to visually display the electronic fence and issue an early warning when the electronic fence detects an illegal intrusion.
[0022] Furthermore, the visualization unit also visualizes risk operation data based on personnel operation records.
[0023] Option 2
[0024] A risk quantification control system for smart production safety, used to implement a risk quantification control method for smart production safety as described in Solution 1; comprising a data acquisition module, a risk quantification module, and a risk control module;
[0025] The data acquisition module is used to collect factory monitoring data; the factory monitoring data includes environmental parameters, equipment parameters and personnel parameters;
[0026] The risk quantification module includes a production risk quantification model and a visualization unit. The production risk quantification model performs risk quantification analysis based on plant monitoring data and outputs risk index values by region, which are then visualized by the visualization unit. The visualization unit is loaded with a plant layout diagram of the power plant, and the visualization unit displays the risk index values by region on the plant layout diagram.
[0027] The risk control module is used to trigger a hierarchical management and control mechanism when the risk indicator value exceeds a threshold.
[0028] The working principle and advantages of the present invention are:
[0029] The present invention provides a risk quantification control method and system for smart production safety. Through information technology, it can accurately quantify the production risks of power plants and conduct intelligent management and control, with high real-time performance and reliability. It can also liberate the labor of some safety management personnel, allowing safety management work to be carried out more efficiently and orderly, thereby ensuring the stable and safe operation of power plants and providing a reliable energy supply for society.
[0030] Key points: This solution integrates risk quantification across three dimensions: equipment, environment, and personnel. It comprehensively considers multiple influencing factors, including equipment status, environmental factors, and human operations, enabling coordinated monitoring of the "man-machine-environment" trinity. This enables comprehensive capture of production risks within the plant, significantly improving risk identification coverage. Furthermore, this solution calculates, analyzes, and visualizes risk indicators for each region, enabling a graded response. By mapping risk indicator values to corresponding areas on the plant layout, a spatial visualization of safety risks is achieved. This GIS-based display facilitates management to quickly locate risk sources and assess the impact of adjacent areas. The implemented hierarchical control mechanism forms a four-tiered progressive response system. Through a response strategy of "regional isolation - adjacent linkage - global control," a gradient emergency response mechanism is established. Each risk level corresponds to a differentiated response package (alert scope, notification format, and task assignment). For example, Level 2 triggers the issuance of an inspection ticket, Level 3 adds an emergency approval process, and Level 4 initiates equipment interlocking protection. This ensures precise matching of response measures to risk severity, ensuring accurate and reliable response actions. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 This is a method flow diagram of a first embodiment of a risk quantification control method and system for smart production safety according to the present invention;
[0032] Figure 2 This is a schematic diagram of regional risk visualization of embodiment 1 of a risk quantification control method and system for smart production safety of the present invention. DETAILED DESCRIPTION
[0033] The following is a further detailed description through specific implementation methods:
[0034] Example 1
[0035] The embodiment is basically as shown in the attached Figure 1 As shown: A risk quantification control method for smart production safety, comprising the following steps:
[0036] Step 1: Collect plant monitoring data and store it in a risk database; the plant monitoring data includes environmental parameters, equipment parameters, and personnel parameters.
[0037] The environmental parameters include temperature, humidity, wind speed, wind direction, air pressure, precipitation, dust concentration, and risk gas concentration.
[0038] In this embodiment, the environmental parameters also include a comprehensive meteorological index, and the comprehensive meteorological index W is calculated based on temperature, humidity, and wind speed, W=0.6T+0.3H+0.1V; where T is temperature, H is humidity, and V is wind speed.
[0039] The equipment parameters include equipment operating data. In practical applications, the power plant equipment to be included in the collection scope can be selected based on actual monitoring and analysis needs and computing power levels. Preferably, the equipment parameters also include data that can reflect the structural status of the equipment, such as equipment vibration data and equipment surface temperature data, to facilitate timely detection of equipment operating risks.
[0040] The personnel parameters include personnel duty records, personnel inspection records, personnel operation records, and personnel trajectory data. Specifically, the personnel duty records include duty time, duty tasks, duty event records (recording any abnormal events that occurred during the duty period, such as equipment failures, alarm information, etc., including the time, location, specific phenomena, and initial treatment measures), and handover records (recording the handover content with the previous shift and the next shift, including equipment operating status, unfinished work tasks, pending issues, etc.).
[0041] The personnel inspection records include inspection time, inspection route, equipment inspection status, environmental inspection status, safety facility inspection status, problem and handling records (problems found and handling measures taken on site), etc.
[0042] The personnel operation records include operator information, operation project information (operation name, content, location, operation start and end time, etc.), operation process records (key steps in the operation process, operation methods, actual implementation status), safety facility implementation status, etc.
[0043] The personnel trajectory data includes personnel location information, movement trajectory records, stay time information, etc.
[0044] In this step, environmental parameters, equipment parameters, and personnel parameters are also temporally and spatially aligned for unified analysis.
[0045] Furthermore, plant monitoring data is collected and stored by area. These areas are divided by function into boiler area, turbine area, main transformer area, starter and standby transformer area, fuel area, cooling tower area, desulfurization area, chemical water area, electrostatic precipitator area, hydrogen production station area, oil depot area, start-up boiler area, and urea solution preparation workshop area. Furthermore, electronic fences are installed around each area to facilitate accurate regional management.
[0046] In actual applications, different area division methods can be selected according to the monitoring needs of the factory area.
[0047] In step 2, the production risk quantification model performs a risk quantification analysis based on the risk operation content selected in the risk database, and outputs risk index values by region, which are then visualized by a visualization unit; the visualization unit is loaded with a plant layout diagram of the power plant, and the visualization unit displays the risk index values by region on the plant layout diagram.
[0048] The risk indicator values are divided into Level 1 - low risk, Level 2 - general risk, Level 3 - greater risk, and Level 4 - major risk; and the levels are calculated and confirmed according to the LEC evaluation method.
[0049] The LEC evaluation method is a semi-quantitative assessment method for evaluating the hazardousness of operating conditions. It assigns values to three factors: the likelihood of an accident (L), the frequency of exposure to hazardous environments (E), and the potential consequences of an accident (C). It then calculates a hazard score (D) using the formula D = L × E × C to assess the hazardousness of the operating conditions. This method allows for a rapid assessment of the hazardousness of operating conditions.
[0050] In this embodiment, the production risk quantification model assigns values to the three factors L, E, and C.
[0051] The risk operation content and its associated plant area monitoring data are pre-set and selected according to actual needs.
[0052] like Figure 2 As shown, the visualization unit displays the risk index value based on the GIS map, and represents the corresponding area with a four-color map according to different risk levels; risk levels 1 to 4 correspond to blue, yellow, orange and red, respectively.
[0053] In this embodiment, the production risk quantification model provided includes a risk quantification unit and a weight adjustment unit.
[0054] The risk quantification unit analyzes the plant monitoring data based on the Monte Carlo risk assessment method and calculates the risk index. The weight adjustment unit is used to dynamically adjust the weights of the risk quantification unit analysis. When adjusting the weights, the weight adjustment unit first generates the initial weight ω based on the LSTM-Attention mechanism. _base ; Then, based on the plant monitoring data, the initial weight is temporarily modified through the event-driven model, where the modified value is Δω. Specifically, the weight value ω finally obtained by the weight adjustment unit is i =ω _final =a·ω _base+b·Δω; a+b=1.
[0055] When analyzing the plant monitoring data, the risk quantification unit includes the following steps:
[0056] Traverse the plant monitoring data, identify risk factors, build a Monte Carlo indicator system based on the risk factors, and then calculate the risk indicators.
[0057] Step 3: When the risk indicator value exceeds the threshold, the hierarchical control mechanism is triggered.
[0058] Specifically, the hierarchical control mechanism includes: when the risk level is level 1, triggering an electronic alarm in the area; and displaying an alarm notification in the visualization unit;
[0059] When the risk level is level 2, electronic alarms are triggered in the area and adjacent areas; alarm notifications are displayed in the visualization unit and staff inspections are arranged in the area;
[0060] When the risk level reaches Level 3, electronic alarms are triggered within the area and adjacent areas. A pop-up alarm notification is displayed in the visualization unit, an emergency approval form is issued to the area manager, and professional safety officers are arranged for inspections.
[0061] When the risk level reaches Level 4, an electronic alarm for the entire area is triggered; a pop-up alarm notification is forcibly displayed in the visualization unit, an emergency management notification is sent to the area manager and professional safety officer, and automatic interlock protection of key equipment is activated.
[0062] In this embodiment, the visualization unit is further used to visualize the electronic fence and issue an early warning when the electronic fence detects illegal intrusion.
[0063] The visualization unit also visualizes risk operation data based on personnel operation records.
[0064] This embodiment provides a risk quantification control method and system for smart production safety, which can accurately quantify the production risks of power plants and perform visual intelligent management and control, and has high real-time, reliability and intuitiveness.
[0065] Example 2
[0066] A risk quantification control method for smart production safety is improved as follows based on the first embodiment.
[0067] When the risk quantification unit outputs the risk index, it is calculated according to the following formula:
[0068]
[0069] Among them, R total is the risk index value; ωi are the dynamic weights of the equipment dimension, environment dimension, and personnel dimension, corresponding to ω1, ω2, and ω3 respectively; μ if is the membership value of the jth indicator in the i-th dimension; α ij is the indicator experience coefficient; β is the Monte Carlo risk correction coefficient; R monte_carlo is the Monte Carlo simulation function.
[0070] The β is based on ω i Perform adaptive correction; and the correction satisfies: β = 0.2 + 0.05 × max (ω1, ω2, ω3); ω1, ω2, ω3 are the dynamic weights of the equipment dimension, environment dimension, and personnel dimension respectively.
[0071] The weight adjustment unit is also provided with an exponential decay function; the exponential decay function is used to adjust the reference weights of the weight adjustment unit and the risk quantification unit to the historical data; the exponential decay function is set to ω t =ω0·e -λt ; In the formula, ω0 is the initial reference weight of the weight adjustment unit or risk quantification unit for historical data; t is the time parameter; λ is the proportional coefficient.
[0072] Here, by setting an exponential decay function, the reference weight of historical data can be dynamically reduced over time, allowing the production risk quantification model to pay more attention to recent data, more accurately capture the dynamic changes of data, and suppress noise interference in historical data, which helps to improve the accuracy and scientific nature of model decisions.
[0073] The triggering events of the event-driven model include: abnormal data or abnormal data fluctuations or abnormal operating conditions in the plant monitoring data; the abnormal operating conditions include: equipment is in the maintenance and running-in period, and personnel are in the job change and running-in period.
[0074] Specifically, when the triggering event is an abnormal operating condition—equipment undergoing maintenance and run-in—the weight of the corresponding equipment dimension is reduced; when the triggering event is an abnormal operating condition—personnel undergoing job change and run-in—the weight of the corresponding personnel dimension is reduced. The reduction ratio is set based on empirical values.
[0075] When the trigger event is abnormal data or abnormal data fluctuation, the weight of the corresponding dimension is increased based on the data category (environmental parameters, equipment parameters, or personnel parameters) to which the abnormal data or abnormal data fluctuation belongs. The increase ratio is proportional to the degree of abnormality of the abnormal data or abnormal data fluctuation.
[0076] The weight adjustment unit is further provided with an intervention interface, which is used to visually display the weight distribution and allow the user to adjust the weight within a limited range. In this embodiment, the limited range can be pre-set based on expert experience.
[0077] In this embodiment, the risk index value ranges from 0 to 100; when the risk index value is in the range of 0 to 30, the risk level is level 1; when the risk index value is in the range of 31 to 60, the risk level is level 2; when the risk index value is in the range of 61 to 85, the risk level is level 3; when the risk index value is in the range of 86 to 100, the risk level is level 4.
[0078] This embodiment provides a risk quantification control method and system for smart production safety. It selects a Monte Carlo risk assessment method to perform risk indicator analysis, which can assign a probability distribution to uncertain risk factors in the power plant environment (such as equipment failure probability, maintenance time, probability of human operation error, etc.). Then, through a large number of simulation calculations, the possible value range of the risk indicator is obtained, which can make the risk assessment results closer to the actual situation and can more comprehensively cover various possible risk situations, thereby achieving a higher quantitative reliability.
[0079] Secondly, this solution offers high risk quantification accuracy and adaptability to the dynamically changing power plant production environment. Specifically, this solution features a weight adjustment unit, based on a dual data-driven and event-driven model (LSTM-Attention mechanism and event-driven model). This unit dynamically adjusts the analytical weights for equipment, environment, and personnel based on real-time plant changes. Furthermore, the analytical weights, acting as multiplicative factors in the risk formula, directly amplify or reduce the risk contribution of each dimension, enabling dynamic regulation of the risk quantification formula. This ensures that the risk quantification results respond to real-time plant operating conditions and adapt to the dynamically changing power plant production environment, resulting in high risk quantification adaptability and accuracy.
[0080] Example 3
[0081] A risk quantification control method for smart production safety is improved as follows based on the first embodiment.
[0082] When the risk level is 1-2, a risk evolution analysis is also conducted to pre-check whether the current risk level has an increasing trend, so as to arrange risk management work reasonably. The specific steps include the following:
[0083] Based on the dynamic Bayesian network, a time-varying causal graph is constructed. The nodes of the time-varying causal graph are set as equipment parameters, environmental parameters, and personnel parameters. The edge weights of the time-varying causal graph represent the causal strength.
[0084] Based on the time-varying causal diagram, the temporal causal relationship between risk factors is confirmed.
[0085] According to the temporal causal relationship, the influence of nodes is quantified based on the PageRank algorithm to locate the risk diffusion point.
[0086] Calculate the contribution gradient of each dimension of data to risk changes, and set the reference weight of each dimension of data based on the contribution gradient. Use the LSTM network to refer to the data of each dimension in the past 24 hours to predict the next risk rapid change moment and risk indicators of the risk diffusion point.
[0087] If the risk level corresponding to the predicted risk indicator is 3 to 4, it means that the current risk level has an increasing trend and risk management needs to be completed before the next risk rapid change moment.
[0088] When the risk level is 3 to 4, the same method can be used to conduct risk evolution analysis to obtain the moment of rapid risk change so as to complete risk control in a timely manner.
[0089] This embodiment provides a risk quantification control method and system for smart production safety. Based on the current risk level determination results, it can further analyze the risk evolution, allowing for the development of response plans in advance to prevent risks from evolving into accidents. It can also guide the optimization of risk management plans.
[0090] Example 4
[0091] A risk quantification control method for smart production safety is improved as follows based on the first embodiment.
[0092] The production risk quantification model also includes a local risk calculation unit, which is used to calculate the spatial correlation risk value of the plant equipment group based on the plant monitoring data. When the risk quantification unit outputs the risk index, it also adds the spatial correlation risk value.
[0093] In this embodiment, the local risk calculation unit captures and calculates the spatial correlation risk of the equipment group based on the graph neural network. Specifically, the local risk calculation unit first regards each device as a node in the graph, defines the edge according to the spatial position relationship, physical connection relationship or functional dependency relationship between the devices, and sets the weight of the edge according to the degree of association between the devices to construct the equipment graph structure. For example, edges can be established between adjacent devices, devices connected by pipes or lines, and devices with upstream and downstream relationships in the same production process. The edge weights between devices that are close to each other can be set higher. Preferably, the edge weights can also be dynamically adjusted according to factors such as the frequency of interaction between devices and the degree of mutual influence.
[0094] Then, based on the graph neural network (graph convolutional network GCN is selected here), the spatial correlation risk of the device group is calculated.
[0095] This embodiment provides a risk quantification control method and system for smart production safety. Compared to existing risk quantification solutions, which often focus only on the status of individual devices when analyzing equipment-related risks, while ignoring the interactions between devices, this solution specifically addresses these interactions, utilizing graph neural networks to treat the device cluster as a whole while also considering the spatial correlation information between multiple devices. This enables a more comprehensive and accurate assessment of the risk status of the device cluster, avoiding risk misjudgments caused by ignoring the connections between devices.
[0096] The above is only an embodiment of the present invention. Common knowledge such as the specific structure and characteristics of the scheme is not described in detail here. Ordinary technicians in the relevant field are aware of all common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the guidance of this application. Some typical well-known structures or well-known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several variations and improvements can be made, which should also be regarded as the scope of protection of the present invention. These will not affect the effect of the implementation of the present invention and the practicality of the patent.
Claims
1. A risk quantification control method for smart production safety, characterized in that: The following steps are involved: Step 1: Collect plant monitoring data and store it in the risk database; The plant monitoring data includes environmental parameters, equipment parameters and personnel parameters; Step 2: The production risk quantification model performs a risk quantification analysis based on the risk operations selected in the risk database, and outputs risk index values by region, which are then visualized by a visualization unit. The visualization unit is loaded with a plant layout diagram of the power plant, and the visualization unit displays the risk index values by region on the plant layout diagram. Step 3: When the risk indicator value exceeds the threshold, the hierarchical control mechanism is triggered.
2. The risk quantification control method for smart production safety according to claim 1, characterized in that: In step 1, the environmental parameters include temperature, humidity, wind speed, wind direction, air pressure, precipitation, dust concentration, and risk gas concentration; the equipment parameters include equipment operation data; and the personnel parameters include personnel duty records, personnel inspection records, personnel operation records, and personnel trajectory data.
3. The risk quantification control method for smart production safety according to claim 1, characterized in that: The risk indicator values are divided into Level 1 - low risk, Level 2 - general risk, Level 3 - greater risk, and Level 4 - major risk; and the levels are calculated and confirmed according to the LEC evaluation method.
4. The risk quantification control method for smart production safety according to claim 3, characterized in that: The visualization unit displays risk index values based on the GIS map, and represents the corresponding areas with four-color maps according to different risk levels; risk levels 1 to 4 correspond to blue, yellow, orange and red, respectively.
5. The risk quantification control method for smart production safety according to claim 3, characterized in that: The hierarchical control mechanism includes: when the risk level is level 1, triggering an electronic alarm in the area; and displaying an alarm notification in the visualization unit; When the risk level is level 2, electronic alarms are triggered in the area and adjacent areas; alarm notifications are displayed in the visualization unit and staff inspections are arranged in the area; When the risk level reaches Level 3, electronic alarms are triggered within the area and adjacent areas. A pop-up alarm notification is displayed in the visualization unit, an emergency approval form is issued to the area manager, and professional safety officers are arranged for inspections. When the risk level reaches Level 4, an electronic alarm for the entire area is triggered; a pop-up alarm notification is forcibly displayed in the visualization unit, an emergency management notification is sent to the area manager and professional safety officer, and automatic interlock protection of key equipment is activated.
6. The risk quantification control method for smart production safety according to claim 1, characterized in that: In step 1, when collecting plant monitoring data, the data is collected and stored by region.
7. The risk quantification control method for smart production safety according to claim 1, characterized in that: The areas are divided into the following ways: boiler area, steam turbine area, main transformer area, start-up and standby transformer area, fuel area, cooling tower area, desulfurization area, chemical water area, electrostatic precipitator area, hydrogen production station area, oil depot area, start-up boiler area, and urea solution preparation workshop area according to regional functions.
8. The risk quantification control method for smart production safety according to claim 1, characterized in that: An electronic fence is set up around each area; the visualization unit is also used to visually display the electronic fence and issue an early warning prompt when the electronic fence detects illegal intrusion.
9. The risk quantification control method for smart production safety according to claim 1, characterized in that: The visualization unit also visualizes risk operation data based on personnel operation records.
10. A risk quantification control system for smart production safety, characterized in that: Used to execute a risk quantification control method for smart production safety according to any one of claims 1 to 9; Including data acquisition module, risk quantification module and risk control module; The data acquisition module is used to collect factory monitoring data and store it in the risk database; The plant monitoring data includes environmental parameters, equipment parameters and personnel parameters; The risk quantification module includes a production risk quantification model and a visualization unit. The production risk quantification model performs risk quantification analysis based on the risk operation content selected in the risk database, outputs risk index values by region, and then displays them visually by the visualization unit. The visualization unit is loaded with a plant layout diagram of the power plant, and the visualization unit displays the risk index values by region on the plant layout diagram. The risk control module is used to trigger a hierarchical management and control mechanism when the risk indicator value exceeds a threshold.
