Method and system for monitoring concentration level and real-time exposure of multiple hazard factors of dressing plant

Abstract

The invention discloses a concentration level and real-time exposure monitoring method for multiple hazard factors of a dressing plant. The method comprises the following steps: firstly, acquiring multi-source data in a monitoring area; in order to realize accurate reconstruction and prediction of a hazard factor concentration field in a working space, a space-time prediction model based on graph structure learning is established, and a space-time change graph of a hazard substance concentration field in a monitoring area is obtained; in order to generate a space concentration field reflecting real distribution details of hazard factors, a thermodynamic diagram generation algorithm is constructed based on dynamic weight distribution, and a time-space continuous hazard concentration field and a thermodynamic distribution diagram in a monitoring area are generated; acquiring real-time moving tracks of workers in the monitoring area, performing space-time matching on the real-time moving tracks, the hazardous substance concentration field and the thermal distribution diagram, and further calculating to obtain individual accumulated exposure dose of each worker; and finally, performing mixed contact risk assessment and early warning and skin contact risk identification and early warning by using the individual cumulative exposure dose, and finally realizing real-time monitoring and early warning of the working risk of the worker.

Description

Technical Field

[0001] This invention belongs to the field of safety production technology in mineral processing plants, specifically a method and system for real-time monitoring of the concentration levels and exposure of multiple hazardous factors in mineral processing plants. Background Technology

[0002] Mineral processing plants simultaneously generate multiple sources of combined hazards during crushing, screening, and flotation processes, including silica dust (containing free SiO2) and volatile chemical toxins from mineral processing reagents, posing a severe occupational health challenge. However, existing monitoring technologies reveal deep-seated and systemic technical deficiencies in this complex exposure scenario, failing to meet the national strategic requirements for precise and dynamic prevention and control. These deficiencies are specifically manifested in the following key aspects: First, at the monitoring system level, current dust and chemical toxic substance monitoring systems are independent devices, making it impossible to correlate the distribution characteristics, concentration trends, and interactions of the two types of hazards in the same spatiotemporal dimension. Industry standards require assessments to cover "all possible routes of exposure," but fragmented systems cannot determine whether high-concentration dust areas are accompanied by volatile organic compound (VOC) exposure, nor can they identify the dual risks of dust dispersion and chemical leakage caused by equipment malfunctions. This results in a lack of data support for risk assessments in mixed exposure scenarios, failing to provide a scientific basis for the development of comprehensive protective measures.

[0003] Second, the lag in sampling patterns further exacerbates assessment bias. The existing system heavily relies on manual, timed inspections and intermittent sampling, creating significant blind spots for capturing transient high-risk events. For example, short-term exposure to extremely high concentrations caused by sudden leaks of mineral processing reagents or momentary equipment seal failures is often missed by routine sampling intervals due to its sudden and transient nature. This is especially true for new mineral processing reagents without PC-STEL (Permissible Short-Term Exposure Elasticity) limits, potentially leading to unknown risks such as acute irritation, central nervous system depression, or even acute poisoning for workers. Furthermore, for mobile workers performing routine inspections and equipment maintenance, the existing model cannot track individual movements and simultaneously record exposure concentrations in real time, relying solely on time-weighted average concentrations calculated from fixed points (C0). TWA It is difficult to quantify the cumulative exposure dose over the entire workday, which may significantly underestimate individual risk. Even for factors with PC-TWA (time-weighted average permissible concentration) but no PC-STEL, this model cannot identify the peak exposure period or confirm whether short-term exposure exceeds the multiple limit, rendering the peak exposure control mechanism determined by industry safety standards ineffective.

[0004] Third, the static and rigid nature of the assessment model leads to a severe disconnect from the actual production environment. The model's mean-based calculations ignore the dynamic impact of environmental parameters such as temperature, humidity, and wind speed on the diffusion of hazardous materials. High temperatures accelerate the volatilization of mineral processing reagents like xanthate and black powder, humidity alters dust agglomeration and settling patterns, and wind speed affects the aerosol diffusion range. Ignoring these variables causes the assessment results to deviate from actual risks. Furthermore, the model fails to integrate production load fluctuations such as ore processing volume and equipment operating load, failing to reflect the true risks of increased dust and reagent volatilization during high-load periods, resulting in delays in the allocation of protective resources and risk warnings. In mixed exposure assessments, while existing methods require individual assessments of each factor before determining interactions, combined toxicological data on dust and multiple organic solvents in mining scenarios are extremely scarce. In practice, formulas are often mechanically applied, failing to identify potential synergistic enhancement effects.

[0005] In summary, existing occupational hazard monitoring technologies in mineral processing plants suffer from systemic defects, resulting in a large amount of fragmented, untimely data that is detached from the actual environment and production dynamics, ignores key exposure pathways, and causes risk assessments to deviate significantly from real-world scenarios. These technologies are unable to effectively identify instantaneous high risks, quantify mobile exposures, or assess the complex effects of mixtures. This technological state makes it difficult to protect workers from health damage caused by pneumoconiosis, acute and chronic poisoning, and mixed exposures. Therefore, developing a monitoring system that integrates real-time wide-area sensing, multi-factor dynamic correlation analysis, comprehensive assessment of multi-pathway exposures, and intelligent proactive early warning has become an urgent technological requirement to overcome current occupational health protection bottlenecks and achieve inherent safety. Summary of the Invention

[0006] To address the problems existing in the prior art, this invention provides a method and system for real-time monitoring of the concentration levels and exposure of multiple hazardous factors in a mineral processing plant, which can effectively solve the problems existing in the prior art.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is: a method for real-time exposure monitoring of multiple hazardous factors in a mineral processing plant, comprising the following steps: Step 1: Acquire multi-source data: Deploy various sensing units at the required locations in the ore dressing plant to form a spatiotemporally synchronized data acquisition network, thereby continuously acquiring spatiotemporally synchronized multi-source data; Step 2: Spatiotemporal prediction of hazardous fields and heat maps within space: Constructing a spatiotemporal reconstruction model of the hazard field: Establishing a spatiotemporal prediction model based on graph structure learning. This model abstracts the monitoring area into a dynamic graph structure and uses the multi-source data from step one to predict the spatiotemporal variation map of the hazard concentration field within the monitoring area. Establishing a high-precision heat map: A heat map generation algorithm is constructed based on dynamic weight allocation. This algorithm calculates the attention weight of each point in space through a self-constructed feature mapping network. It uses the data obtained in step one to perform high-precision spatial interpolation on the spatiotemporal change map formed in step one, thereby generating a spatiotemporally continuous hazardous substance concentration field and thermal distribution map within the monitoring area for subsequent assessment of individual exposure concentration. Step 3: Individual Exposure Concentration Assessment and Early Warning S1. Calculation of individual cumulative exposure dose: Obtain the real-time movement trajectory of the staff in the monitoring area and match it with the spatiotemporally continuous hazardous substance concentration field and thermal distribution map in the monitoring area in step two to calculate the individual cumulative exposure dose of each staff member. S2. Mixed Exposure Risk Assessment and Early Warning: Based on the individual cumulative exposure dose obtained in step S1, the Mixed Exposure Ratio (MCR) is calculated to assess the combined health risk when multiple hazard factors are exposed simultaneously, including additive and synergistic effects; if the MCR is greater than a set threshold, an early warning is issued. S3. Skin contact risk identification and early warning: Mark high-risk areas (such as drug addition points) on the GIS map of the monitoring area; match the real-time movement trajectory of the staff obtained in step S1 with the high-risk areas, determine whether there is a skin contact risk based on the matching results, and issue an early warning.

[0008] Furthermore, the multi-source data in step one includes dust concentration, H2S concentration, SO2 concentration, TVOC concentration, temperature, relative humidity, wind speed, and wind direction.

[0009] Furthermore, the steps are as follows: Constructing a spacetime graph structure: in: The graph is a set of nodes, each node corresponds to a deployed sensor unit, and the node attributes include its geographical coordinates and time-series concentration monitoring data; For real-time wind field data (wind direction) Wind speed The directed edges constructed are used to characterize the propagation path of pollutants under the influence of wind fields; For adaptive adjacency matrix, ,in, The angle between the wind direction vector and the line connecting node i to node j is the angle between the vector and the line connecting node i to node j. This design enables the model to adapt to changes in wind speed and direction and accurately capture pollutant transport characteristics. Based on the above graph structure, the concentration field is predicted through the following multi-layer spatiotemporal convolution operation: in: The normalized adjacency matrix; This represents the adjacency matrix after adding self-connections; For the first The node feature matrix of the layer; The model's parameter matrix is ​​to be trained. By stacking multiple convolutional operations, the spatiotemporal reconstruction model of the hazard field can deeply integrate spatial and temporal features to achieve accurate prediction of the concentration field of hazardous substances; and the output of the spatiotemporal reconstruction model of the hazard field can be any point within the monitoring area within a future period. Predicted concentration values .

[0010] Furthermore, the steps are as follows: The formula for spatial difference is: in: Let be the concentration value of the i-th sensor at time t; Let (x, y) be the Euclidean distance from the point to be interpolated (x, y) to sensor i. To construct the Gaussian radial basis function kernel, Attention weights The following was obtained through calculation using a self-constructed multilayer perceptron: MLP stands for Multilayer Perceptron, and its input feature vector includes distance d. i Wind direction angle θ i Wind speed v w Multidimensional environmental parameters including temperature (T) and relative humidity (RH); After performing the above calculations at different times, a spatiotemporally continuous hazardous substance concentration field and thermal distribution map of the monitoring area are obtained. This is used for subsequent assessment of individual exposure concentrations.

[0011] Furthermore, the specific calculation process of step S1 is as follows: Trajectory-concentration field fusion: This integrates the real-time movement trajectories of staff. With hazardous substance concentration field and thermal distribution map Spatiotemporal matching was performed to obtain the real-time exposure concentration of individuals. ; Time-weighted average concentration calculation: In the formula, To calculate the time-weighted average concentration, the above formula is used, and the data processing center automatically calculates and updates the concentration for each staff shift at a rate of seconds. , The total exposure time is used to obtain the individual cumulative exposure dose for each worker.

[0012] Furthermore, the formula for calculating the mixing contact ratio in step S2 is as follows: In the formula, MCR is the mixed contact ratio, and the threshold is set to 1. When MCR > 1, an early warning is triggered.

[0013] Furthermore, the specific matching process in step S3 is as follows: when the real-time trajectory of the staff member shows the time spent in the high-risk area... And the concentration in this area When a skin contact risk is identified, an early warning is issued, where concentration C represents the real-time concentration of a certain occupational hazard factor in the area, PC-C TWA These are occupational health exposure limits.

[0014] The monitoring system for the above-mentioned mineral processing plant's multi-hazard concentration levels and real-time exposure monitoring method includes a data processing center and dust sensing units, chemical toxic substance sensing units, and environmental parameter sensing units deployed within the monitoring area. These multiple sensing units form a spatiotemporally synchronized data acquisition network and are all connected to the data processing center. The sensing data is fed back to the data processing center for analysis and processing, followed by individual risk assessment and early warning. The dust sensing unit monitors the dust concentration at its location; the chemical toxic substance sensing unit monitors the H2S, SO2, and TVOC concentrations at its location; and the environmental parameter sensing unit monitors the temperature, relative humidity, wind speed, and wind direction at its location.

[0015] Compared with existing technologies, this invention first establishes a spatiotemporally synchronized data acquisition network within the monitoring area to continuously acquire spatiotemporally synchronized multi-source data. To achieve accurate reconstruction and prediction of the concentration field of hazardous factors in the work space, this invention establishes a spatiotemporal prediction model based on graph structure learning. This model abstracts the monitoring area into a dynamic graph structure and uses multi-source data to predict the spatiotemporal variation map of the hazardous concentration field within the monitoring area. To generate a spatial concentration field that reflects the true distribution details of hazardous factors, this invention constructs a heat map generation algorithm based on dynamic weight allocation. This algorithm calculates the attention weight of each point in space through a self-constructed feature mapping network and uses multi-source data to perform high-precision spatial interpolation on the formed spatiotemporal variation map, thereby generating a spatiotemporally continuous hazardous concentration field and heat map within the monitoring area for subsequent individual exposure concentration assessment. Next, the real-time movement trajectory of workers within the monitoring area is acquired and spatiotemporally matched with the hazardous concentration field and heat map to calculate the individual cumulative exposure dose of each worker. Finally, the individual cumulative exposure dose is used to conduct mixed exposure risk assessment and early warning, and skin contact risk identification and early warning, respectively. As can be seen from the above process, the present invention integrates real-time wide-area perception, multi-factor dynamic correlation analysis, multi-path exposure comprehensive assessment and intelligent proactive early warning to form a monitoring system, thereby realizing real-time monitoring and early warning of work risks for staff and ensuring their personal health. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall process of the present invention. Detailed Implementation

[0017] The present invention will be further described below.

[0018] like Figure 1 As shown, a method for real-time exposure monitoring of multiple hazard factors in a mineral processing plant includes the following steps: Step 1: Acquire multi-source data: Deploy various sensing units at the required locations in the ore dressing plant to form a spatiotemporally synchronized data acquisition network, thereby continuously acquiring spatiotemporally synchronized multi-source data, including dust concentration, H2S concentration, SO2 concentration, TVOC concentration, temperature, relative humidity, wind speed, and wind direction.

[0019] Step 2: Spatiotemporal prediction of hazardous fields and heat maps within space: Constructing a spatiotemporal reconstruction model of the hazard field: A spatiotemporal prediction model based on graph structure learning is established. This model abstracts the monitoring area into a dynamic graph structure. Using the multi-source data from step one, the spatiotemporal variation map of the hazard concentration field within the monitoring area is predicted, specifically: Constructing a spacetime graph structure: in: The graph is a set of nodes, each node corresponds to a deployed sensor unit, and the node attributes include its geographical coordinates and time-series concentration monitoring data; For real-time wind field data (wind direction) Wind speed The directed edges constructed are used to characterize the propagation path of pollutants under the influence of wind fields; For adaptive adjacency matrix, ,in, The angle between the wind direction vector and the line connecting node i to node j is the angle between the vector and the line connecting node i to node j. This design enables the model to adapt to changes in wind speed and direction and accurately capture pollutant transport characteristics. Based on the above graph structure, the concentration field is predicted through the following multi-layer spatiotemporal convolution operation: in: The normalized adjacency matrix; This represents the adjacency matrix after adding self-connections; For the first The node feature matrix of the layer; The model's parameter matrix is ​​to be trained. By stacking multiple convolutional operations, the spatiotemporal reconstruction model of the hazard field can deeply integrate spatial and temporal features to achieve accurate prediction of the concentration field of hazardous substances; and the output of the spatiotemporal reconstruction model of the hazard field can be any point within the monitoring area within a future period. Predicted concentration values .

[0020] Establishing a high-precision heatmap: A heatmap generation algorithm based on dynamic weight allocation is constructed. This algorithm calculates the attention weights of each point in space through a self-constructed feature mapping network, and performs high-precision spatial interpolation on the spatiotemporal change map formed in step one using the data obtained in step one, thereby generating a spatiotemporally continuous hazardous substance concentration field and thermal distribution map within the monitoring area for subsequent assessment of individual exposure concentrations. Specifically: The formula for spatial difference is: in: Let be the concentration value of the i-th sensor at time t; Let (x, y) be the Euclidean distance from the point to be interpolated (x, y) to sensor i. To construct the Gaussian radial basis function kernel, Attention weights The following was obtained through calculation using a self-constructed multilayer perceptron: MLP stands for Multilayer Perceptron, and its input feature vector includes distance d. i Wind direction angle θ i Wind speed v w Multidimensional environmental parameters including temperature (T) and relative humidity (RH); After performing the above calculations at different times, a spatiotemporally continuous hazardous substance concentration field and thermal distribution map of the monitoring area are obtained. This is used for subsequent assessment of individual exposure concentrations.

[0021] Step 3: Individual Exposure Concentration Assessment and Early Warning S1. Calculation of Individual Cumulative Exposure Dose: Obtain the real-time movement trajectory of workers within the monitoring area and match it with the spatiotemporally continuous hazardous substance concentration field and thermal distribution map within the monitoring area from step two. Then, calculate the individual cumulative exposure dose of each worker. The specific calculation process is as follows: Trajectory-concentration field fusion: This integrates the real-time movement trajectories of staff. With hazardous substance concentration field and thermal distribution map Spatiotemporal matching was performed to obtain the real-time exposure concentration of individuals. ; Time-weighted average concentration calculation: In the formula, To calculate the time-weighted average concentration, the above formula is used, and the data processing center automatically calculates and updates the concentration for each staff shift at a rate of seconds. , The total exposure time is used to obtain the individual cumulative exposure dose for each worker.

[0022] S2. Combined Exposure Risk Assessment and Early Warning: Based on the individual cumulative exposure dose obtained in step S1, the combined exposure ratio (MCR) is calculated to assess the combined health risk when multiple hazard factors are exposed simultaneously, including additive and synergistic effects. If the combined exposure ratio exceeds a set threshold, an early warning is issued. The formula for calculating the combined exposure ratio is as follows: In the formula, MCR is the mixed contact ratio, and the threshold is set to 1. When MCR > 1, an early warning is triggered.

[0023] S3. Skin Contact Risk Identification and Early Warning: Mark high-risk areas (such as drug application points) on the GIS map of the monitored area; and match the real-time movement trajectory of staff obtained in step S1 with the high-risk areas. Specifically, when the staff's real-time trajectory shows the time they spent in the high-risk area... And the concentration in this area When a skin contact risk is identified, an early warning is issued, where concentration C represents the real-time concentration of a certain occupational hazard factor in the area, PC-C TWA These are occupational health exposure limits.

[0024] The monitoring system for the concentration levels of multiple hazardous factors and real-time exposure monitoring methods in the above-mentioned ore dressing plant includes a data processing center and dust sensing units, chemical toxic substance sensing units, and environmental parameter sensing units deployed in the monitoring area. The multiple sensing units form a spatiotemporally synchronized data acquisition network and are all connected to the data processing center. The sensing data is fed back to the data processing center for analysis and processing, and then used for individual risk assessment and early warning. The dust sensing unit is used to monitor the dust concentration at its location. In this embodiment, a laser dust sensor based on the Mie scattering principle is used, with a built-in dynamic temperature and humidity compensation algorithm to effectively overcome interference from high humidity environments and achieve accurate measurement within the range of 0.1-1000 mg / m³ (accuracy ±5%).

[0025] The chemical toxic substance sensing unit is used to monitor the concentrations of H2S, SO2, and TVOC at the location. In this embodiment, an integrated array sensor is used, including a high-sensitivity electrochemical sensor (for inorganic gases such as H2S and SO2) and a broad-spectrum photoionization detector (PID, range 0.1-2000ppm, for volatile organic compounds such as TVOC), to achieve ppb-level trace monitoring of characteristic components and decomposition products of mineral processing reagents.

[0026] The environmental parameter sensing unit is used to monitor the temperature, relative humidity, wind speed, and wind direction at its location. This embodiment employs synchronously embedded digital temperature and humidity sensors and ultrasonic wind speed and direction sensors to accurately quantify the real-time disturbance effects of environmental dynamic parameters (temperature T, relative humidity RH, wind speed WS, wind direction WD) on pollutant diffusion, deposition, and volatilization. Each deployed node outputs a multi-dimensional synchronous data stream {dust concentration, toxic substance concentration, temperature, humidity, wind speed, wind direction} with a unified timestamp and geographic coordinates, laying the foundation for subsequent fusion analysis.

[0027] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for real-time monitoring of concentration levels and exposure to multiple hazardous factors in a mineral processing plant, characterized in that, Includes the following steps: Step 1: Acquire multi-source data: Deploy various sensing units at the required locations in the ore dressing plant to form a spatiotemporally synchronized data acquisition network, thereby continuously acquiring spatiotemporally synchronized multi-source data; Step 2: Spatiotemporal prediction of hazardous fields and heat maps within space: Constructing a spatiotemporal reconstruction model of the hazard field: Establishing a spatiotemporal prediction model based on graph structure learning. This model abstracts the monitoring area into a dynamic graph structure and uses the multi-source data from step one to predict the spatiotemporal variation map of the hazard concentration field within the monitoring area. Establishing a high-precision heat map: A heat map generation algorithm is constructed based on dynamic weight allocation. This algorithm calculates the attention weight of each point in space through a self-constructed feature mapping network. It uses the data obtained in step one to perform high-precision spatial interpolation on the spatiotemporal change map formed in step one, thereby generating a spatiotemporally continuous hazardous substance concentration field and thermal distribution map within the monitoring area for subsequent assessment of individual exposure concentration. Step 3: Individual Exposure Concentration Assessment and Early Warning S1. Calculation of individual cumulative exposure dose: Obtain the real-time movement trajectory of the staff in the monitoring area and match it with the spatiotemporally continuous hazardous substance concentration field and thermal distribution map in the monitoring area in step two to calculate the individual cumulative exposure dose of each staff member. S2. Risk assessment and early warning of mixed exposure: Based on the individual cumulative exposure dose obtained in step S1, the mixed exposure ratio is calculated to assess the combined health risk when multiple hazard factors are exposed at the same time. If the mixed exposure ratio is greater than the set threshold, an early warning will be issued. S3. Skin contact risk identification and early warning: Mark high-risk areas on the GIS map of the monitoring area; The real-time movement trajectory of the staff obtained in step S1 is matched with the high-risk area. Based on the matching results, it is determined whether there is a risk of skin contact and an early warning is issued.

2. The method for monitoring the concentration levels and real-time exposure of multiple hazardous factors in a mineral processing plant according to claim 1, characterized in that, The multi-source data in step one includes dust concentration, H2S concentration, SO2 concentration, TVOC concentration, temperature, relative humidity, wind speed, and wind direction.

3. The method for monitoring the concentration levels and real-time exposure of multiple hazardous factors in a mineral processing plant according to claim 1, characterized in that, The specific steps are as follows: Constructing a spacetime graph structure: in: The graph is a set of nodes, each node corresponds to a deployed sensor unit, and the node attributes include its geographical coordinates and time-series concentration monitoring data; Directed edges constructed for real-time wind field data are used to characterize the propagation path of pollutants under the influence of wind field. For adaptive adjacency matrix, ,in, The angle between the wind direction vector and the line connecting node i to node j; Based on the above graph structure, the concentration field is predicted through the following multi-layer spatiotemporal convolution operation: in: The normalized adjacency matrix; This represents the adjacency matrix after adding self-connections; For the first The node feature matrix of the layer; The model's parameter matrix is ​​to be trained. By stacking multiple convolutional operations, the spatiotemporal reconstruction model of the hazard field can deeply integrate spatial and temporal features to achieve accurate prediction of the concentration field of hazardous substances; and the output of the spatiotemporal reconstruction model of the hazard field can be any point within the monitoring area within a future period. Predicted concentration values .

4. The method for monitoring the concentration levels and real-time exposure of multiple hazardous factors in a mineral processing plant according to claim 1, characterized in that, The specific steps are as follows: The formula for spatial interpolation is: in: Let be the concentration value of the i-th sensor at time t; Let (x, y) be the Euclidean distance from the point to be interpolated (x, y) to sensor i. To construct the Gaussian radial basis function kernel, Attention weights The results were obtained through calculations using a self-constructed multilayer perceptron: MLP stands for Multilayer Perceptron, and its input feature vector includes distance d. i Wind direction angle θ i Wind speed v w Multidimensional environmental parameters including temperature (T) and relative humidity (RH); After performing the above calculations at different times, a spatiotemporally continuous hazardous substance concentration field and thermal distribution map of the monitoring area are obtained. This is used for subsequent assessment of individual exposure concentrations.

5. The method for monitoring the concentration levels and real-time exposure of multiple hazardous factors in a mineral processing plant according to claim 4, characterized in that, The specific calculation process for step S1 is as follows: Trajectory-concentration field fusion: This integrates the real-time movement trajectories of staff. With hazardous substance concentration field and thermal distribution map Spatiotemporal matching was performed to obtain the real-time exposure concentration of individuals. ; Time-weighted average concentration calculation: In the formula, To calculate the time-weighted average concentration, the above formula is used, and the data processing center automatically calculates and updates the concentration for each staff shift at a rate of seconds. , The total exposure time is used to obtain the individual cumulative exposure dose for each worker.

6. The method for monitoring the concentration levels and real-time exposure of multiple hazardous factors in a mineral processing plant according to claim 1, characterized in that, The formula for calculating the mixing contact ratio in step S2 is as follows: In the formula, MCR is the mixed contact ratio, and the threshold is set to 1. When MCR > 1, an early warning is triggered.

7. The method for monitoring the concentration levels and real-time exposure of multiple hazardous factors in a mineral processing plant according to claim 5, characterized in that, The specific matching process in step S3 is as follows: when the real-time trajectory of the staff member shows the time spent in the high-risk area... And the concentration in this area When a skin contact risk is identified, an early warning is issued, where concentration C represents the real-time concentration of a certain occupational hazard factor in the area, PC-C TWA These are occupational health exposure limits.

8. A monitoring system utilizing the multi-hazard factor concentration level and real-time exposure monitoring method for a mineral processing plant according to any one of claims 1 to 7, characterized in that, It includes a data processing center and dust sensing units, chemical toxic substance sensing units, and environmental parameter sensing units deployed in the monitoring area. The various sensing units form a spatiotemporally synchronized data acquisition network and are all connected to the data processing center. The sensing data is fed back to the data processing center for analysis and processing, and then used for individual risk assessment and early warning. The dust sensing unit is used to monitor the dust concentration at its location; The chemical toxic substance sensing unit is used to monitor the concentrations of H2S, SO2, and TVOC at the location. The environmental parameter sensing unit is used to monitor the temperature, relative humidity, wind speed, and wind direction of the location.

Images