Intelligent factory personnel positioning and safety warning method

Abstract

The application discloses a kind of intelligent factory personnel positioning and safety early warning method, comprising: by accurately identifying risk source and dividing direct, indirect risk sensing area, personnel route is planned with three-dimensional map annotation position and influence range, effectively avoid high-risk area, optimize path planning to make personnel away from potential danger, reduce exposure risk;Risk chain model is constructed to quantify risk transmission path and influence weight, combine real-time positioning to calculate path deviation value, based on the risk assessment model constructed can dynamically and accurately calculate risk value, so that risk assessment accuracy improves;When risk value is over threshold value, timely early warning, accident response time is shortened, greatly reduce the probability of accident, all-round guarantee personnel and equipment safety, build solid defense line for factory safety production.

Description

Technical Field

[0001] This invention relates to the field of positioning and early warning technology, and in particular to a method for personnel positioning and safety early warning in a smart factory. Background Technology

[0002] In traditional factory production environments, personnel safety management faces numerous challenges. On the one hand, factory environments are complex, with many hazardous areas and potential risk sources, making it difficult for manual patrols to accurately and in real-time pinpoint personnel locations and prevent them from entering high-risk areas. On the other hand, risk warning mechanisms are often lagging, relying heavily on human experience and lacking scientific basis and dynamic monitoring. With the development of factory automation and intelligence, the interaction between personnel and equipment increases, raising the complexity of risks. Therefore, there is an urgent need for a smart factory personnel positioning and safety warning method to achieve accurate personnel location and timely risk warnings, ensuring personnel safety and production stability.

[0003] Patent application number 202010641443.4 discloses a factory personnel positioning and safety early warning system, including a positioning information acquisition module, a three-dimensional management module, an information calculation module, a display module, an alarm management module, and a historical tracking module. The positioning information acquisition module can collect the location information of factory personnel in real time. Through the three-dimensional management module and the information calculation module, the system updates and calculates movement paths, mapping the location to a coordinate system to improve positioning accuracy. The system also promptly feeds back the calculated safety status of factory personnel to the display module, allowing the system to grasp the safety status of factory personnel immediately and provide safety reminders, effectively improving the effectiveness of safety management. In the event of a safety problem, the system can promptly issue alarms to factory personnel, minimizing human losses. Simultaneously, it can respond promptly to sudden safety issues, improving the utilization rate of various resources within the factory.

[0004] However, the actual factory environment is complex, with various risk sources widely distributed and interconnected. Yet, the zoning of risk impact areas is unclear, making it difficult to visually represent the direct and indirect effects of risk sources. This can lead to personnel unknowingly entering high-risk areas during work. Furthermore, the lack of systematic research into risk transmission patterns makes it impossible to accurately grasp the transmission paths and impact levels of risks across different areas and processes, hindering the construction of an effective risk assessment system. In terms of personnel path management, simplistic planning is insufficient, failing to monitor actual personnel movements in real time and failing to promptly detect deviations from safe routes. Once a risk occurs, the lack of a scientific early warning mechanism makes it difficult to issue timely alerts, prolonging the exposure of personnel and equipment to danger and increasing the probability and severity of accidents. Summary of the Invention

[0005] This application provides a method for intelligent factory personnel positioning and safety early warning, which accurately identifies risk areas, quantifies risk transmission, and provides real-time early warning.

[0006] This application provides a method for personnel location and safety early warning in smart factories, including:

[0007] S1 identifies the direct and indirect risk sensing zones of risk sources within the factory, marks their locations and impact ranges on a 3D map, and plans personnel work routes based on the locations of each risk sensing zone.

[0008] S2, define the risk transmission path and impact weight between risk sources to construct a risk chain model;

[0009] S3, real-time positioning and recording of personnel's actual path, generating key points of the path, and calculating the distance deviation between the actual path and the work route;

[0010] S4. Based on the relationship between the deviation value and the risk chain, construct a risk assessment model to calculate the risk value of the current risk chain; based on the risk chain model, identify the risk transmission path between risk sources and calculate the risk value of each path point on the transmission path; calculate the transmission attenuation coefficient and work fatigue coefficient on the transmission path to correct the risk value of the path point; use the transmission attenuation coefficient and work fatigue coefficient to calculate the risk delay coefficient of the corrected path point risk value.

[0011] S5 issues a risk warning when the risk value exceeds the safety threshold.

[0012] Preferably, in step S4, the calculation of the corrected path point risk value includes: ,in, It is the conduction attenuation coefficient. (p,s) is the Euclidean distance between path point p and risk source s, and β is the medium attenuation coefficient; It is the work fatigue coefficient. t is the working time (hours), and δ is the fatigue growth coefficient; This is the original risk value.

[0013] Preferably, the original risk value includes: ,in, The influence weight of the k-th risk chain path. Let be the risk transmission probability of the k-th path, and m be the number of associated paths.

[0014] Preferably, the direct risk sensing zone and the indirect risk sensing zone specifically include: the direct risk sensing zone is centered on the risk source, with a radius of... A spherical or cylindrical area where personnel entering will directly face high risk; direct risk sensing zone = The indirect risk sensing zone is centered on the risk source, with a radius of... spherical or cylindrical regions, and Indirect risk sensing zone = , Coordinates of the risk source.

[0015] Preferably, the method further includes: using the conduction attenuation coefficient and the working fatigue coefficient to calculate the risk delay coefficient of the corrected path point risk value to adjust the timeliness of the risk assessment, the calculation formula being: , It is the time delay factor.

[0016] Preferably, the path points include: the risk values ​​of the starting point, intermediate node, and ending point in the risk transmission path; the risk transmission path is a risk chain relationship composed of each path from the starting point of the source risk to the ending point of the risk source's propagation range.

[0017] Preferably, in step S41, identifying the risk transmission path between risk sources further includes:

[0018] 1A. Collect historical risk transmission path records of the risk type at each path point, group them according to risk type, and establish a risk type database;

[0019] 1B sets a risk value threshold for each waypoint and dynamically calculates the risk value of each waypoint within the group in real time;

[0020] 1C: When the risk value of a path point within a group exceeds a threshold, analyze the trend of risk value changes of the path point and trigger the group adjustment mechanism.

[0021] 1D regroups path points whose risk values ​​exceed the threshold with path points that have the same risk value change trend.

[0022] Preferably, establishing the risk type database specifically involves: collecting risk transmission path data from historical records, grouping path points with the same risk type into a group, and assigning a unique identifier to each group; creating a database to store information about risk type groups, and the database should contain group identifiers, risk type descriptions, and a list of path points within the group.

[0023] Preferably, the triggering grouping adjustment mechanism includes: real-time monitoring of the risk value of each path point within the group; comparing the real-time risk value of each path point with a pre-set risk value threshold; marking the path point as an over-threshold path point when its real-time risk value exceeds the set threshold; collecting risk value data of over-threshold path points over a past window period to form a time series dataset; and using time... Establish a linear regression model with as the independent variable and hazard R as the dependent variable. The regression coefficients a and b are calculated using methods such as least squares. Based on the results of the risk value change trend analysis, the conditions for triggering grouping adjustments are set. When the triggering conditions are met, the grouping adjustment process is started immediately.

[0024] Preferably, the regrouping specifically includes: selecting path points with the same risk value change trend from all path points with risk values ​​exceeding the threshold; removing the selected path points from the original group and regrouping them into a new group; and updating the relevant information in the risk type database.

[0025] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0026] By accurately identifying risk sources within the factory and delineating direct and indirect risk sensing zones, the system enables visual labeling and path planning on a 3D map, effectively avoiding high-risk areas and optimizing personnel work routes. Simultaneously, a risk chain model is constructed to quantify risk transmission paths and impact weights. Combined with real-time positioning technology, personnel path deviation values ​​are calculated, and a risk assessment model is built to dynamically calculate the current risk value, providing timely warnings when risks exceed thresholds. This solution comprehensively enhances the intelligence and precision of factory safety management, effectively ensuring the safety of personnel and equipment and reducing accident risks.

[0027] This solution identifies risk transmission paths and quantifies risk values ​​at path points using a risk chain model. It then calculates a transmission attenuation coefficient by combining the medium attenuation coefficient and environmental correction factor, reflecting the natural attenuation of risk along the transmission path. Simultaneously, it introduces a fatigue growth coefficient and working hours to calculate a work fatigue coefficient, quantifying the impact of personnel fatigue on risk perception. Finally, it calculates a risk delay coefficient using a time delay factor, path length, and movement speed, dynamically adjusting the timeliness of risk assessment. This comprehensive approach, integrating physical attenuation, human factors, and dynamic time delay, achieves accurate quantification and real-time early warning of risk transmission, enhancing the scientific rigor and effectiveness of safety management.

[0028] By grouping path points with similar risk characteristics or correlations, centralized risk management and precise monitoring are achieved, which helps optimize resource allocation and improve resource utilization efficiency. Simultaneously, risk trend prediction and early warning based on grouping enable the development of targeted strategies and coordinated prevention and control, effectively improving the accuracy of risk management, enhancing risk response capabilities, and reducing losses caused by risks. Systematic management of risk information is achieved, enabling accurate identification and dynamic monitoring of risks, timely adjustment of groupings to adapt to risk changes, effectively improving the efficiency and accuracy of risk response, reducing risk losses, and ensuring stable factory operation.

[0029] By deeply analyzing historical risk data and accurately simulating risk propagation, it is possible to predict the trajectory of risks at key points in the path of risk, enabling early risk warnings. Compared to traditional methods, it avoids a passive approach to risk response, allowing for advance deployment of pre-planned adjustments and measures, significantly improving the timeliness and proactivity of risk response. Furthermore, it can accurately pinpoint risk propagation paths and key nodes, rationally allocate resources, optimize risk management strategies, and effectively reduce the damage caused by risks. Attached Figure Description

[0030] Figure 1 This is a flowchart illustrating a method for personnel location and safety early warning in a smart factory according to an embodiment of the present invention. Detailed Implementation

[0031] To facilitate understanding of the present invention, a more complete description of this application will be given below with reference to the accompanying drawings, which illustrate preferred embodiments of the invention. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to enable a more thorough and complete understanding of the disclosure of the present invention.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention; the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0033] Example 1: Figure 1 This is a flowchart illustrating a method for intelligent factory personnel positioning and safety early warning according to an embodiment of the present invention.

[0034] like Figure 1 As shown, a method for personnel location and safety early warning in a smart factory includes the following steps:

[0035] S1 identifies the direct and indirect risk sensing zones of risk sources within the factory, marks their locations and impact ranges on a 3D map, and plans personnel work routes based on the locations of each risk sensing zone.

[0036] Among them, the direct risk sensing zone is centered on the risk source and has a radius of... A spherical or cylindrical area (e.g., 1-3 meters) poses a high risk to personnel entering this area; the direct risk sensing zone = The indirect risk sensing zone is centered on the risk source, with a radius of... A spherical or cylindrical area (e.g., 5-10 meters) and Although personnel do not directly enter, they may face potential risks due to proximity; this is the indirect risk sensing zone. , For the coordinates of the risk source, These represent the coordinates of any location in three-dimensional space, i.e., the location of the observation point or the person. The specific area is further defined based on the actual application scenario.

[0037] Specifically, the process involves traversing the entire factory area to identify all potential risk sources, such as high-temperature equipment, high-pressure areas, and toxic chemical storage areas. The type, location, and risk level of each risk source are recorded, and criteria for delineating direct and indirect risk sensing zones are determined. Using 3D modeling software or GIS tools, risk sources and their sensing zone boundaries are marked on a 3D map, creating a visualized risk map.

[0038] Based on a 3D risk map, a path planning algorithm is used to plan personnel work routes, ensuring that the routes avoid directly risk-aware zones and minimize the time spent in indirectly risk-aware zones. Considering personnel task requirements (such as material handling and equipment maintenance), the routes are optimized to balance efficiency and safety, generating the optimal work route. Taking the A* algorithm as an example, the shortest path from the starting point S to the ending point G is found, avoiding directly risk-aware zones. The heuristic function is defined as f(n) = g(n) + h(n), where g(n) is the actual cost from the starting point to node n, and h(n) is the estimated cost from node n to the ending point (e.g., Euclidean distance). The constraint is that path nodes must not be located within directly risk-aware zones. The goal is to minimize the path length L and the exposure time T in indirectly risk-aware zones. The formula is as follows: ,in, and Let be the weighting coefficient, satisfying .

[0039] For example, a high-temperature device (such as a furnace) located at coordinates (10, 20, 5) is identified as having a high risk level. The radius of the direct risk sensing zone is also considered. =3 meters, radius of indirect risk sensing zone =8 meters. Starting point S=(0,0,0), ending point G=(20,30,0). Using the A* algorithm, plan the path, avoiding the direct risk sensing zone, generating the following path node sequence: (0,0,0)→(5,10,0)→(15,25,0)→(20,30,0). Verify whether the path nodes are located within the direct risk sensing zone: (Safety). Calculate the path length L = 15 + 10 + 5 = 30 meters. Calculate the exposure time T in the indirect risk sensing zone (assuming a personnel speed of 1 m / s): The shortest distance between the path from node (5,10,0) to (15,25,0) and the boundary of the indirect risk sensing zone is 8. 7.07 ≈ 0.93 meters (exposure time T = 10 seconds). Optimize the objective function min(0.6). 30 + 0.4 10) = 22.

[0040] S2 defines the risk transmission path and impact weight between risk sources to construct a risk chain model.

[0041] Specifically, based on factory layout, technological processes, and historical accident data, the potential correlations between risk sources (such as physical proximity, upstream / downstream processes, energy / material transfer, etc.) are analyzed to identify triggering conditions that may lead to risk transmission (such as high-temperature equipment failure causing fires in adjacent areas, chemical leaks spreading to downstream areas, etc.). Based on the correlations between risk sources, risk transmission paths are defined, i.e., the possible paths by which risk can be transmitted from one risk source to another. These risk transmission paths are then marked on a 3D risk map, including the starting point, ending point, intermediate nodes (such as equipment, pipelines, vents, etc.), and direction of transmission.

[0042] Based on factors such as the intensity, frequency, and duration of risk transmission paths, an influence weight is assigned to each path. The analytic hierarchy process (AHP) or historical data analysis is used to quantify the influence weight. Weight values ​​typically range from 0 to 1, with larger values ​​indicating a higher probability or degree of risk transmission. Risk sources, their transmission paths, and influence weights are integrated into a risk chain model. The model is represented by a directed graph, where nodes represent risk sources, edges represent risk transmission paths, and edge weights represent influence weights. The completeness and rationality of the risk chain model are verified to ensure that all key risk transmission paths are covered.

[0043] S3, real-time positioning and recording of personnel's actual path, generating key points of the path, and calculating the distance deviation between the actual path and the work route.

[0044] Specifically, high-precision positioning equipment is installed within the factory to ensure coverage of all work areas. Personnel are equipped with positioning tags, and location data is uploaded to a positioning server in real time. The positioning server records the personnel's location coordinates at fixed time intervals (1 second). This generates time-series data, and the location data is filtered to eliminate noise and outliers, thereby improving path accuracy.

[0045] Based on path change features (abrupt direction, speed changes, and stop points), key points of the path are extracted, and a key point sequence is generated. ,in Load the pre-planned work route from the 3D risk map, representing it as a sequence of line segments. ,in A line segment is defined by its starting point and ending point.

[0046] For each actual path key point Calculate its route to work shortest distance Distance deviation values ​​can be calculated using the average distance deviation (the average of the shortest distances from all critical points to the work route) and the maximum distance deviation (the maximum of the shortest distances from all critical points to the work route). The appropriate distance deviation value should be selected as the evaluation indicator based on safety management requirements.

[0047] S4. Based on the relationship between the deviation value and the risk chain, construct a risk assessment model to calculate the risk value of the current risk chain.

[0048] Specifically, based on historical data, a correlation is established between path deviation values ​​and the probability of risk transmission in the risk chain, determining the risk level (low, medium, or high risk) corresponding to the deviation value range, and mapping it to the risk transmission path in the risk chain. Using the path deviation value as input, combined with the influence weights in the risk chain model, a risk assessment model is constructed. The model can employ a weighted method to calculate the current risk value. Considering the impact weights and risk transmission probabilities of all associated risk chain paths, the calculation formula is as follows: ,in, The influence weight of the k-th risk chain path. The risk transmission probability (and deviation value) for the k-th path (related), m is the number of associated paths, It is the path deviation value corresponding to the k-th risk chain path.

[0049] Based on the deviation value of the actual path, query the associated risk chain path and its impact weight, calculate the current risk value, and consider the amplification effect of the deviation value on the probability of risk transmission.

[0050] Among them, the path deviation value D is related to the probability of risk transmission in the risk chain. The relationship is as follows:

[0051]

[0052] It should be noted that the threshold and probability value can be adjusted according to actual needs.

[0053] For example, assuming the actual path deviation is D = 1.2 meters, the risk transmission probability can be obtained based on the mapping relationship. =0.3, assuming two risk chain paths are associated, with influence weights of respectively. =0.6 and =0.4, the probability of risk transmission is 0.4. Calculate the current risk value =0.6×0.3+0.4×0.3=0.18+0.12=0.3.

[0054] S5 issues a risk warning when the risk value exceeds the safety threshold.

[0055] The technical solutions described in the embodiments of this application above have at least the following technical effects or advantages:

[0056] By accurately identifying risk sources within the factory and delineating direct and indirect risk sensing zones, the system enables visual labeling and path planning on a 3D map, effectively avoiding high-risk areas and optimizing personnel work routes. Simultaneously, a risk chain model is constructed to quantify risk transmission paths and impact weights. Combined with real-time positioning technology, personnel path deviation values ​​are calculated, and a risk assessment model is built to dynamically calculate the current risk value, providing timely warnings when risks exceed thresholds. This solution comprehensively enhances the intelligence and precision of factory safety management, effectively ensuring the safety of personnel and equipment and reducing accident risks.

[0057] Example 2: In Example 1, the risk value calculation for the risk transmission path relied solely on the initial risk superposition at a single path point, failing to fully consider the impact of medium attenuation, dynamic environmental changes, and personnel operational status on risk perception during the transmission process. However, the attenuation characteristics of different transmission media (such as air and liquids) vary significantly, and real-time fluctuations in environmental conditions (such as ventilation efficiency and temperature) can lead to changes in the intensity of risk transmission. Simultaneously, fatigue after prolonged work reduces personnel's ability to cope with risks, resulting in a lag in risk perception. If a uniform initial risk value calculation model is still used, it will inevitably fail to accurately reflect the dynamic characteristics of risk transmission, causing bias in risk assessment and delays in early warning. To more accurately quantify the attenuation effect and the influence of human factors during risk transmission, it is necessary to simultaneously introduce a medium attenuation coefficient, an environmental correction factor, and a work fatigue coefficient to dynamically correct the risk value at the path point, thereby improving the real-time performance and accuracy of risk assessment.

[0058] In some embodiments, the current risk value is calculated, and step S4 further includes:

[0059] S41, based on the risk chain model, identifies the risk transmission path between risk sources and calculates the risk value of each path point on the transmission path.

[0060] The risk transmission path also includes each path consisting of a starting point (source of risk), an ending point (end of the risk source's propagation range), and intermediate nodes (equipment, pipelines, ventilation openings, etc. involved in the middle); the path points are the risk values ​​of the starting point, intermediate nodes, and ending point in the risk transmission path.

[0061] S42, calculate the conduction attenuation coefficient and working fatigue coefficient on the conduction path, and correct the path point risk value.

[0062] The conduction attenuation coefficient represents the degree of risk attenuation along the conduction path, and its calculation formula is: , (p,s) is the Euclidean distance between path point p and risk source s, and β is the medium attenuation coefficient (preset according to the type of conductive medium, such as air=0.1, liquid=0.05). It is an environmental correction factor (dynamically adjusted based on ventilation, temperature, etc., ranging from 0.8 to 1.2).

[0063] The work fatigue coefficient represents the degree to which an employee's perception and ability to cope with risks declines after prolonged work. The calculation formula is: t is the working time (hours), and δ is the fatigue growth coefficient (based on the preset working intensity, high intensity = 0.3, medium intensity = 0.2, low intensity = 0.1).

[0064] The formula for adjusting the path point risk value is: .

[0065] S43, calculate the risk delay coefficient of the corrected path point risk value using the conduction attenuation coefficient and the working fatigue coefficient.

[0066] Specifically, the risk delay coefficient is used to adjust the timeliness of risk assessment. The calculation formula is as follows: , It is the time delay factor (related to path length and personnel movement speed, unit: seconds / meter). Example: If personnel movement speed v = 1 meter / second and path length L = 20 meters, then τ = L / v = 20 seconds.

[0067] The technical solutions described in the embodiments of this application above have at least the following technical effects or advantages:

[0068] This solution identifies risk transmission paths and quantifies risk values ​​at path points using a risk chain model. It then calculates a transmission attenuation coefficient by combining the medium attenuation coefficient and environmental correction factor, reflecting the natural attenuation of risk along the transmission path. Simultaneously, it introduces a fatigue growth coefficient and working hours to calculate a work fatigue coefficient, quantifying the impact of personnel fatigue on risk perception. Finally, it calculates a risk delay coefficient using a time delay factor, path length, and movement speed, dynamically adjusting the timeliness of risk assessment. This comprehensive approach, integrating physical attenuation, human factors, and dynamic time delay, achieves accurate quantification and real-time early warning of risk transmission, enhancing the scientific rigor and effectiveness of safety management.

[0069] Example 3: In Example 2, the grouping and monitoring of path points for risk management was primarily based on a fixed risk level classification standard for initial grouping, and a unified response strategy was adopted for all path points within the group when a risk occurred. However, in reality, the risk transmission mechanisms and impact ranges of different path points vary significantly, making it difficult to accurately capture the dynamic changes in risk at each path point using a fixed grouping method. Furthermore, when facing complex and ever-changing risk scenarios, failing to fully consider the key factor of risk value change trends and relying solely on whether the risk value exceeds a threshold to trigger the response mechanism can easily lead to misjudgments or delayed responses, resulting in poor risk management effectiveness. To more effectively address complex risk environments, achieve precise dynamic management of risk path points, and improve the accuracy and timeliness of risk response, this example proposes a path point grouping and dynamic adjustment method based on risk type and change trends, namely Example 3.

[0070] In some embodiments, step S41, identifying the risk transmission path between risk sources, further includes:

[0071] 1A. Collect historical risk transmission path records of the risk type at each path point, group them according to risk type, and establish a risk type database.

[0072] Specifically, risk transmission path data is collected from historical records. This data should include relevant information for each path point, such as path point identification, occurrence time, and risk description. The risk descriptions for each path point are then analyzed, and risks are classified into different types based on factors such as the nature of the risk, its source, and its scope of impact.

[0073] Group waypoints with the same risk type together and assign a unique identifier to each group. Create a database to store information about risk type groupings. The database should contain fields such as group identifier, risk type description, and a list of waypoints within the group.

[0074] 1B sets a risk value threshold for each waypoint and dynamically calculates the risk value of each waypoint within the group in real time.

[0075] This can be set by referring to historical risk value data.

[0076] 1C: When the risk value of a path point within a group exceeds a threshold, analyze the trend of risk value changes of the path point and trigger the group adjustment mechanism.

[0077] Specifically, the risk value of each path point within the group is continuously monitored in real time. The real-time risk value of each path point is compared with a pre-set risk value threshold. When the real-time risk value of a path point exceeds its set threshold, the path point is marked as an over-threshold path point.

[0078] Collect risk value data for path points exceeding the threshold over a past window period (e.g., 6 hours, 12 hours; the specific time length can be determined based on requirements and risk characteristics), forming a time series dataset. For example, recording the risk value of this path point once a day yields a data series containing risk values ​​at multiple time points. (Based on time...) Establish a linear regression model with as the independent variable and hazard R as the dependent variable. The regression coefficients a and b are calculated using methods such as the least squares method. If the regression coefficient a > 0, it indicates that the risk value is increasing over time; if a < 0, it indicates that the risk value is decreasing over time.

[0079] Based on the results of the risk value trend analysis, conditions are set to trigger grouping adjustments. For example, when the risk value shows a continuous upward trend (the regression coefficient α in the linear regression analysis is greater than 0 and reaches a certain significance level), the grouping adjustment mechanism is triggered. Once the triggering conditions are met, the grouping adjustment process is immediately initiated.

[0080] 1D regroups path points whose risk values ​​exceed the threshold with path points that have the same risk value change trend.

[0081] Specifically, among all path points whose risk values ​​exceed a threshold, path points with the same trend of risk value change are selected. These selected path points are then removed from their original groups and regrouped into a new group. Simultaneously, the relevant information in the risk type database is updated.

[0082] The technical solutions described in the embodiments of this application above have at least the following technical effects or advantages:

[0083] By grouping path points with similar risk characteristics or correlations, centralized risk management and precise monitoring are achieved, which helps optimize resource allocation and improve resource utilization efficiency. Simultaneously, risk trend prediction and early warning based on grouping enable the development of targeted strategies and coordinated prevention and control, effectively improving the accuracy of risk management, enhancing risk response capabilities, and reducing losses caused by risks. Systematic management of risk information is achieved, enabling accurate identification and dynamic monitoring of risks, timely adjustment of groupings to adapt to risk changes, effectively improving the efficiency and accuracy of risk response, reducing risk losses, and ensuring stable factory operation.

[0084] Example 4: In Example 3, the risk monitoring and grouping adjustment of path points mainly relied on comparing the current risk value with a fixed threshold to trigger the response mechanism, and the grouping adjustment was relatively lagging. However, actual risk propagation is a dynamic and complex process, with significant differences in the speed, scope, and impact of risk propagation between different path points. Judging solely based on the current risk value and the fixed threshold makes it difficult to accurately capture early signs of risk propagation and predict risk trends in advance, resulting in untimely grouping adjustments and a passive risk response. Furthermore, because the time characteristics of risk propagation are not fully considered, the delayed effect of different path points in the risk propagation process is ignored, making risk warnings inaccurate. To more effectively cope with complex and ever-changing risk environments, predict risks in advance, optimize grouping adjustment strategies, and improve the timeliness and accuracy of risk response, this example further optimizes the risk value change trend of path points.

[0085] In some embodiments, step 1C, analyzing the trend of risk value changes at path points, further includes:

[0086] By collecting historical risk value change trends of path points, a risk propagation model is constructed. Based on the risk propagation model, the risk value change trends of different path points are simulated and predicted to obtain the risk propagation time of each path point. Based on different risk propagation times, a corresponding risk delay coefficient is injected into each path point to predict the grouping in advance and make grouping preparation adjustments.

[0087] Specifically, the risk value trends of historical path points are categorized and cleaned to remove noise and outliers. The risk value data is then standardized. Based on the characteristics of risk propagation and a complex network model, path points are treated as nodes in the network, and the connections between path points are considered as edges, thus constructing a risk propagation network. By analyzing historical risk propagation events, the probability of risk propagating from one path point to another under different conditions, as well as the degree of risk attenuation during the propagation process, are determined.

[0088] Different initial risk scenarios are set, such as different initial risk values ​​at certain critical path points, to simulate various possible risk outbreaks. The simulation time step and total duration are determined; the time step can be set according to the speed and accuracy requirements of risk propagation, such as hourly or daily. The constructed risk propagation model is used to run the simulation, calculating the risk value change trend and risk propagation process at each path point within each time step. The risk value of each path point at different time steps is recorded to obtain time-series data of risk propagation. Based on the simulated risk propagation time-series data, the risk propagation time of each path point under different initial risk scenarios is calculated, and a corresponding delay coefficient is calculated for each path point. The risk value of each path point is obtained in advance based on the delay coefficient, enabling early risk warnings.

[0089] The technical solutions described in the embodiments of this application above have at least the following technical effects or advantages:

[0090] By deeply analyzing historical risk data and accurately simulating risk propagation, it is possible to predict the trajectory of risks at key points in the path of risk, enabling early risk warnings. Compared to traditional methods, it avoids a passive approach to risk response, allowing for advance deployment of pre-planned adjustments and measures, significantly improving the timeliness and proactivity of risk response. Furthermore, it can accurately pinpoint risk propagation paths and key nodes, rationally allocate resources, optimize risk management strategies, and effectively reduce the damage caused by risks.

[0091] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for personnel positioning and safety early warning in a smart factory, characterized in that, include: S1, identify the direct and indirect risk sensing zones of risk sources within the factory, mark their locations and impact ranges on a 3D map, and plan personnel work routes based on the locations of each risk sensing zone; wherein, the direct and indirect risk sensing zones specifically include: the direct risk sensing zone is centered on the risk source, with a radius of... A spherical or cylindrical area where personnel entering will directly face high risk; direct risk sensing zone = The indirect risk sensing zone is centered on the risk source, with a radius of... spherical or cylindrical regions, and Indirect risk sensing zone = , For the coordinates of the risk source, Represents the coordinates of any position in three-dimensional space; S2, define the risk transmission path and impact weight between risk sources to construct a risk chain model; S3, real-time positioning and recording of personnel's actual path, generating key points of the path, and calculating the distance deviation between the actual path and the work route; S4. Establish the correlation between path deviation value and risk transmission probability based on historical data. Construct a risk assessment model based on the correlation and the influence weights in the risk chain model. Calculate the risk value of the current risk chain using the risk assessment model. Based on the risk chain model, identify the risk transmission path between risk sources and calculate the risk value of each path point. Calculate the transmission attenuation coefficient and work fatigue coefficient on the transmission path to correct the path point risk value. Calculate the risk delay coefficient of the corrected path point risk value using the transmission attenuation coefficient and work fatigue coefficient. Identifying the risk transmission path between risk sources also includes: collecting historical risk transmission path records of the risk type of each path point, grouping them according to risk type, and establishing risk categories. The system employs a database model; it sets risk thresholds for each path point and dynamically calculates the risk value of each path point within a group in real time; when the risk value of a path point within a group exceeds the threshold, it analyzes the trend of risk value changes and triggers a grouping adjustment mechanism; it regroups path points with risk values ​​exceeding the threshold with path points having the same risk value change trend; the triggering of the grouping adjustment mechanism includes: real-time monitoring of the risk value of each path point within the group, comparing the real-time risk value of each path point with a pre-set risk threshold, and marking a path point as an over-threshold path point when its real-time risk value exceeds the set threshold; collecting risk value data of over-threshold path points over a past window period to form a time series dataset; and using time... Establish a linear regression model with as the independent variable and hazard R as the dependent variable. The regression systems a and b are calculated using the least squares method. Based on the results of the risk value change trend analysis, the conditions for triggering grouping adjustments are set. When the triggering conditions are met, the grouping adjustment process is immediately initiated. S5: A risk warning is issued when the risk value of the current risk chain exceeds the safety threshold.

2. The intelligent factory personnel positioning and safety early warning method as described in claim 1, characterized in that, In step S4, the calculation of the corrected path point risk value includes: ,in, It is the conduction attenuation coefficient. , (p,s) is the Euclidean distance between path point p and risk source s, and β is the medium attenuation coefficient. It is an environmental correction factor; It is the work fatigue coefficient. t is the working time, and δ is the fatigue growth coefficient; This is the original risk value.

3. The intelligent factory personnel positioning and safety early warning method as described in claim 2, characterized in that, The original risk value includes: ,in, The influence weight of the k-th risk chain path. Let m be the risk propagation probability of the k-th path, and m be the number of associated paths. It is the path deviation value corresponding to the k-th risk chain path.

4. The intelligent factory personnel positioning and safety early warning method as described in claim 1, characterized in that, The formula for calculating the risk delay coefficient of the corrected path point risk value along the propagation path using the conduction attenuation coefficient and the working fatigue coefficient is as follows: , It is the time delay factor. It is the conduction attenuation coefficient. It is the work fatigue coefficient.

5. The intelligent factory personnel positioning and safety early warning method as described in claim 2, characterized in that, The path points include: the risk values ​​of the starting point, intermediate nodes, and ending point in the risk transmission path; the risk transmission path is a risk chain relationship composed of each path from the starting point of the source risk to the ending point of the risk source's propagation range.

6. The intelligent factory personnel positioning and safety early warning method as described in claim 1, characterized in that, The establishment of the risk type database specifically involves: collecting risk transmission path data from historical records, grouping path points with the same risk type into a group, and assigning a unique identifier to each group; creating a database to store information about risk type groups, which should include group identifiers, risk type descriptions, and a list of path points within the group.

7. The intelligent factory personnel positioning and safety early warning method as described in claim 1, characterized in that, The regrouping specifically includes: selecting path points with the same risk value change trend from all path points with risk values ​​exceeding the threshold; removing the selected path points from the original group and regrouping them into a new group; and updating the relevant information in the risk type database.

Images