Dust and Poison Detection Method and System Based on Safety Helmet

Abstract

The present invention discloses a dust and poison detection method and system based on a safety helmet, belonging to the technical field of dust and poison detection. It includes: integrating a dust and poison detection sensor into the safety helmet of an operator to collect the concentration of environmental target substances in real time; dividing the operation space into operation area monomers with equal volumes through three-dimensional modeling, and generating a monomer sample set at a time node by combining the dynamic density (the ratio of the number of people to the volume) in each monomer; constructing a three-dimensional melt model, quantifying the melt scale and calculating the concentration of the circular area, and characterizing the dust and poison flow state (diffusion, stillness or contraction) by comparing the concentration changes in adjacent areas; iteratively evaluating and predicting the step length based on the flow state set, and outputting the optimal prediction result. The present invention realizes the dynamic tracking and accurate prediction of the dust and poison diffusion trend in a three-dimensional space, effectively improves the monitoring coverage rate and real-time performance, and provides intelligent decision-making support for the safety protection of high-risk operation environments.

Description

Technical Field

[0001] The present invention relates to the technical field of dust and poison detection, and specifically to a dust and poison detection method and system based on a safety helmet. Background Art

[0002] In industrial production and high-risk working environments, dust and poison pollution is one of the key factors threatening the health and safety of workers. Real-time and accurate dust and poison concentration monitoring technology is of great significance for ensuring work safety and optimizing environmental management.

[0003] Currently, traditional dust and poison detection technologies mainly rely on fixed sensor networks. By deploying detection devices at key points in the working area, concentration collection and analysis in a static environment are achieved. However, such methods have significant limitations: First, fixed sensors are difficult to cover dynamic working scenarios, especially areas with strong personnel mobility, resulting in monitoring blind spots. Second, the existing technology lacks the ability to dynamically model the diffusion trend of dust and poison in three-dimensional space and cannot effectively reflect the impact of real-time changing factors such as personnel movement and equipment operation on the concentration distribution. In addition, existing systems mostly use data analysis at a single time node and do not combine the dynamic changes in personnel density in the working area, resulting in insufficient timeliness and accuracy of the prediction model. In particular, some existing solutions attempt to improve data collection efficiency by dividing the monitoring area and combining wireless transmission technology, but their area division methods are mostly two-dimensional planes or fixed volume units, without considering the synergistic effect of the distribution of workers in three-dimensional space on dust and poison diffusion. Other methods introduce cloud computing for data processing, but do not deeply integrate sensors with personnel-worn devices (such as safety helmets), resulting in a single data source and weak spatial correlation. In addition, existing prediction models are mostly based on linear regression of historical data and lack the fusion analysis of key parameters such as dynamic density gradient and melt scale quantization, making it difficult to accurately characterize the flow state and diffusion trend of dust and poison. Summary of the Invention

[0004] The purpose of the present invention is to provide a dust and poison detection method and system based on a safety helmet to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] A dust and poison detection system based on a safety helmet, the system includes: a data preparation module, a data preprocessing module, a data fitting module, and a data analysis module;

[0007] The data preparation module collects the concentration of the target substance in the environment through a dust and poison detection sensor and uploads it to the cloud detection center. The dust and poison detection sensor is installed in a safety helmet; by dividing the three-dimensional space of the operation site into individual operation area units, it receives the concentration of the target substance collected by the dust and poison sensor when the operator wears the safety helmet and works within the individual operation area unit.

[0008] The data preprocessing module obtains the dynamic density of the individual operation area unit by the ratio of the number of operators in the individual operation area unit to the volume of the individual operation area unit. Based on the dynamic density, it analyzes and generates a set of individual samples at a time node.

[0009] The data fitting module is used to construct a three-dimensional melt model. Based on the set of individual samples, it analyzes and quantifies the melt scale to generate a circular domain concentration.

[0010] The data analysis module analyzes and characterizes the flow state of the dust and poison based on the circular domain concentration. Based on the flow state, it analyzes and obtains the prediction step length.

[0011] Furthermore, the data preparation module includes a data acquisition unit and a three-dimensional model unit;

[0012] The data acquisition unit collects the concentration of the target substance in the environment through a dust and poison detection sensor installed in a safety helmet. By setting a unique attribute code for each safety helmet and allocating data storage space to the cloud detection center based on the code attribute of the safety helmet, the data storage space is used to store the concentration of the target substance.

[0013] The three-dimensional model unit is used to divide the three-dimensional space of the operation site into several individual operation area units with equal volume. When the operator wears the safety helmet and works within the individual operation area unit, it instructs the dust and poison sensor on the safety helmet to collect the concentration of the target substance.

[0014] Furthermore, the data preprocessing module includes a dynamic density processing unit and a gradient processing unit;

[0015] The dynamic density processing unit is used to obtain the number of operators in each individual operation area unit, and the ratio of the number of operators in the individual operation area unit to the volume of the individual operation area unit is the dynamic density of the individual operation area unit.

[0016] The gradient processing unit is used to generate a set of individual samples at different time nodes. The set of individual samples records the dynamic density of different individual operation area units at the same time node. The gradient vector is formed by the spatial relationship between any two individual operation area units to generate a gradient set.

[0017] Furthermore, the data fitting module includes a melt fitting unit and a melt concentration processing unit;

[0018] The melt fitting unit is used to take the dynamic density as the centroid of the monomer sample set and fit the dynamic gradient to obtain the melt scale;

[0019] The melt concentration processing unit is used to take the melt scale as the radius and the monomer in the operation area as the center of the circle, retrieve the concentration of the target substance uploaded by each dust and poison detection sensor in the circle when the operator wears a safety helmet and works in the monomer in the operation area, and calculate the average value of the concentration of the target substance uploaded by each dust and poison detection sensor in the circle as the circle domain concentration.

[0020] Further, the data analysis module includes a fluid state marking unit and a dust and poison detection prediction unit;

[0021] The fluid state marking unit quantifies the flow state of the target substance when taking different monomers in the operation area as the center of the circle based on the circle domain concentration;

[0022] The dust and poison detection prediction unit is used to generate a set of flow states of different monomers in the operation area, and by means of iterative analysis, adjust the prediction step length, evaluate the prediction success probability at the prediction step length, and select and output the prediction step length corresponding to the maximum prediction success probability when the iteration stops.

[0023] A dust and poison detection method based on a safety helmet, the method includes the following steps:

[0024] Step S1: Collect the concentration of the target substance in the environment through the dust and poison detection sensor and upload it to the cloud detection center, and the dust and poison detection sensor is installed in the safety helmet; divide the three-dimensional space of the operation site into monomers in the operation area to receive the concentration of the target substance collected by the dust and poison sensor when the operator wears a safety helmet and works in the monomer in the operation area;

[0025] Step S2: Obtain the dynamic density of the monomer in the operation area by the ratio of the number of operators in the monomer in the operation area to the volume of the monomer in the operation area, and based on the dynamic density, analyze and generate a monomer sample set at a time node;

[0026] Step S3: Build a three-dimensional melt model, analyze and quantify the melt scale based on the monomer sample set to generate the circle domain concentration;

[0027] Step S4: Analyze and characterize the flow state of dust and poison based on the circle domain concentration, and analyze to obtain the prediction step length based on the flow state.

[0028] Further, the specific implementation process of step S1 includes:

[0029] The concentration of the target substance in the environment is collected by the dust and poison detection sensor installed in the safety helmet and uploaded to the cloud detection center through a wireless network; by setting a uniquely-identifiable code for each safety helmet and allocating data storage space to the cloud detection center according to the coding attribute of the safety helmet, the data storage space is used to store the concentration of the target substance.

[0030] A three-dimensional space model of the work site is established, and the three-dimensional space of the work site is divided into several work area monomers with equal volumes. When the operator wears a safety helmet and works in the work area monomer, the cloud detection center receives in real time the concentration of the target substance collected by the dust and poison sensor on the safety helmet.

[0031] Further, the specific implementation process of step S2 includes:

[0032] Obtain the number of operators in each work area monomer, and the ratio of the number of operators in the work area monomer to the volume of the work area monomer is the dynamic density of the work area monomer, and upload the dynamic density to the cloud detection center;

[0033] At the t-th time node, a monomer sample set is generated, denoted as , where represents the dynamic density of the i-th work area monomer, and I represents the total number of work area monomers;

[0034] Select the dynamic density as the centroid of the monomer sample set , and collect all the dynamic gradients of the centroid at the t-th time node to form a gradient set, , where represents the gradient vector formed between the i-th work area monomer and the j-th work area monomer, represents the magnitude value of the gradient vector, that is, the dynamic gradient, and , represents the dynamic density of the j-th work area monomer.

[0035] Further, the specific implementation process of step S3 includes:

[0036] When taking the dynamic density as the centroid of the monomer sample set , fit the dynamic gradient, and calculate the melt scale of the i-th work area monomer. In the formula, represents the ceiling function;

[0037] With the melt scale Taking the melt scale [[ID=]] as the radius and the i-th single operation area as the center, retrieve from the cloud detection center the concentration of the target substance uploaded by each dust and poison detection sensor within the circle when the operator wears a safety helmet and works within the single operation area, and calculate the average value of the concentration of the target substance uploaded by each dust and poison detection sensor within the circle, which is denoted as the circle domain concentration with the i-th single operation area as the center 。

[0038] Further, the specific implementation process of step S4 includes:

[0039] Based on the circle domain concentration, quantify the flow state of the target substance with the i-th single operation area as the center ,if ,then let ,indicating that there is a diffusion trend in the i-th single operation area at the t-th time node. If ,then let ,indicating that there is a static behavior in the i-th single operation area at the t-th time node. If ,then let ,indicating that there is a contraction behavior in the i-th single operation area at the t-th time node, Indicating the area of the circle with the melt scale [[ID=]] as the radius and the i-th single operation area as the center , Indicating the area of the circle with the melt scale [[ID=]] as the radius and the i-th single operation area as the center , Indicating the circle domain concentration with the melt scale [[ID=]] as the radius and the i-th single operation area as the center;

[0040] Generate the flow state set of the i-th single operation area, denoted as ,T represents the current time node, initialize the prediction step length k, and evaluate the prediction success probability at the prediction step length k ;

[0041] In the formula, if ,then let ;

[0042] If ,then let ;

[0043] Let Perform iterative calculation of the prediction success probability, Stop iterating when ,L is a preset threshold, and select and output the prediction step length corresponding to the maximum prediction success probability when iterating stops.

[0044] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The dust and poison detection method and system based on a safety helmet provided by the present invention are used to solve the problems of insufficient three-dimensional space dynamic monitoring, poor data correlation, and low prediction model accuracy in the prior art. The technical solutions include: integrating dust and poison detection sensors into the safety helmets of operators, collecting the concentrations of environmental target substances in real time and uploading them to the cloud detection center; dividing the operation space into operation area monomers with equal volumes through three-dimensional modeling, and generating a monomer sample set at a time node by combining the dynamic density (the ratio of the number of people to the volume) in each monomer; constructing a three-dimensional melt model, quantifying the melt scale and calculating the concentration in the circular area, and characterizing the dust and poison flow state (diffusion, static or contraction) by comparing the concentration changes in adjacent areas; iteratively evaluating the prediction step based on the flow state set and outputting the optimal prediction result. Through dynamic density gradient analysis, three-dimensional melt modeling, and flow state quantification, the present invention realizes the dynamic tracking and accurate prediction of the dust and poison diffusion trend in three-dimensional space, effectively improves the monitoring coverage rate and real-time performance, and provides intelligent decision-making support for the safety protection of high-risk operation environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention.

[0046] Figure 1 It is a schematic diagram of the steps of the dust and poison detection method based on a safety helmet of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] In the first embodiment: A dust and poison detection system based on a safety helmet is provided. The system includes: a data preparation module, a data preprocessing module, a data fitting module, and a data analysis module;

[0049] The data preparation module collects the concentration of the target substance in the environment through a dust and poison detection sensor and uploads it to the cloud detection center. The dust and poison detection sensor is installed in the safety helmet; by dividing the three-dimensional space of the operation site into operation area monomers, it receives the concentration of the target substance collected by the dust and poison sensor when the operator wears the safety helmet and works in the operation area monomer.

[0050] Among them, the data preparation module includes a data collection unit and a three-dimensional model unit;

[0051] The data acquisition unit collects the concentration of the target substance in the environment through the dust and poison detection sensors installed in the safety helmets. By setting a uniquely-identifying code for each safety helmet and based on the coded attributes of the safety helmets, data storage spaces are allocated to the cloud detection center, and the data storage spaces are used to store the concentration of the target substance.

[0052] The three-dimensional model unit is used to divide the three-dimensional space of the work site into several work area monomers with equal volumes. When the workers wear safety helmets and work within the work area monomers, the dust and poison sensors on the safety helmets are instructed to collect the concentration of the target substance.

[0053] The data preprocessing module obtains the dynamic density of the work area monomer by the ratio of the number of workers in the work area monomer to the volume of the work area monomer. Based on the dynamic density, it analyzes and generates a monomer sample set at a time node.

[0054] Among them, the data preprocessing module includes a dynamic density processing unit and a gradient processing unit.

[0055] The dynamic density processing unit is used to obtain the number of workers in each work area monomer, and the ratio of the number of workers in the work area monomer to the volume of the work area monomer is the dynamic density of the work area monomer.

[0056] The gradient processing unit is used to generate a monomer sample set at different time nodes. The dynamic densities of different work area monomers at the same time node are recorded in the monomer sample set, and a gradient vector is formed by the spatial relationship between any two work area monomers to generate a gradient set.

[0057] The data fitting module is used to construct a three-dimensional melt model, analyze and quantify the melt scale based on the monomer sample set to generate the circular domain concentration.

[0058] Among them, the data fitting module includes a melt fitting unit and a melt concentration processing unit.

[0059] The melt fitting unit is used to take the dynamic density as the centroid of the monomer sample set and fit the dynamic gradient to obtain the melt scale.

[0060] The melt concentration processing unit is used to take the melt scale as the radius and the work area monomer as the center of the circle, retrieve the concentration of the target substance uploaded by each dust and poison detection sensor within the circle when the worker wears a safety helmet and works within the work area monomer, and calculate the mean value of the concentration of the target substance uploaded by each dust and poison detection sensor within the circle as the circular domain concentration.

[0061] The data analysis module analyzes and characterizes the flow state of the dust and poison based on the circular domain concentration, and analyzes and obtains the prediction step length based on the flow state.

[0062] Among them, the data analysis module includes a fluid state marking unit and a dust and poison detection and prediction unit;

[0063] The fluid state marking unit quantifies the flow state of the target object when the center of the circle is the single body of different working areas based on the concentration in the circular area;

[0064] The dust and poison detection and prediction unit is used to generate a set of flow states of the single body of different working areas, and by means of iterative analysis, adjust the prediction step length, evaluate the prediction success probability at the prediction step length, and select and output the prediction step length corresponding to the maximum prediction success probability when the iteration stops.

[0065] Please refer to Figure 1 , in the second embodiment: Provide a dust and poison detection method based on a safety helmet for application in the first embodiment above. This method includes the following steps:

[0066] Step S1: Collect the concentration of the target object in the environment through a dust and poison detection sensor and upload it to the cloud detection center. The dust and poison detection sensor is installed in the safety helmet; divide the three-dimensional space of the working site into single bodies of working areas, and receive the concentration of the target object collected by the dust and poison sensor when the operator wears the safety helmet and works in the single body of the working area;

[0067] Exemplarily, collect the concentration of the target object in the environment through a dust and poison detection sensor installed in the safety helmet and upload it to the cloud detection center through a wireless network; set a uniquely attributed code for each safety helmet, and allocate data storage space to the cloud detection center through the coding attribute of the safety helmet. The data storage space is used to store the concentration of the target object;

[0068] Establish a three-dimensional space model of the working site, divide the three-dimensional space of the working site into several single bodies of working areas with equal volumes. When the operator wears the safety helmet and works in the single body of the working area, the cloud detection center receives the concentration of the target object collected by the dust and poison sensor on the safety helmet in real time.

[0069] Step S2: Obtain the dynamic density of the single body of the working area by the ratio of the number of operators in the single body of the working area to the volume of the single body of the working area. Based on the dynamic density, analyze and generate a set of single body samples at a time node;

[0070] Exemplarily, obtain the number of operators in each single body of the working area, and the ratio of the number of operators in the single body of the working area to the volume of the single body of the working area is the dynamic density of the single body of the working area. Upload the dynamic density to the cloud detection center;

[0071] At the t-th time node, generate a set of single body samples, denoted as , where represents the dynamic density of the i-th single operation area unit, and I represents the total number of single operation area units;

[0072] Select the dynamic density as the centroid of the single unit sample set , and collect all the dynamic gradients of the centroid at the t-th time node to form a gradient set, , where, represents the gradient vector formed between the i-th single operation area unit and the j-th single operation area unit, represents the magnitude value of the gradient vector, that is, the dynamic gradient, and , represents the dynamic density of the j-th single operation area unit.

[0073] Step S3: Construct a three-dimensional melt model, analyze and quantify the melt scale based on the single unit sample set to generate the circular domain concentration;

[0074] Exemplarily, when taking the dynamic density as the centroid of the single unit sample set , fit the dynamic gradient, and calculate the melt scale of the i-th single operation area unit. In the formula, represents the ceiling function;

[0075] Taking the melt scale as the radius and the i-th single operation area unit as the center, retrieve the target substance concentration uploaded by each dust and poison detection sensor within the circle when the operator wears a safety helmet and works within the single operation area unit from the cloud detection center, and calculate the average value of the target substance concentration uploaded by each dust and poison detection sensor within the circle, denoted as the circular domain concentration when taking the i-th single operation area unit as the center .

[0076] Step S4: Analyze and characterize the flow state of dust and poison based on the circular domain concentration, and analyze and obtain the prediction step size based on the flow state;

[0077] Exemplarily, quantify the flow state of the target substance when taking the i-th single operation area unit as the center based on the circular domain concentration , if , then let , indicating that there is a diffusion trend in the i-th single operation area unit at the t-th time node. If , then let , indicating that there is a static behavior in the i-th single operation area unit at the t-th time node. If , then let , indicating that there is a contraction behavior in the i-th single operation area unit at the t-th time node, represents the melt scale The area of a circle with the \(i\)-th single operation area as the center and a radius of denotes the melt scale The area of a circle with the \(i\)-th single operation area as the center and a radius of denotes the melt scale is the concentration of the circular domain with the \(i\)-th single operation area as the center and a radius of

[0078] Generate the flow state set of the \(i\)-th single operation area, denoted as , \(T\) represents the current time node, initialize the prediction step length \(k\), and evaluate the prediction success probability at the prediction step length \(k\) ;

[0079] In the formula, if , then let ;

[0080] If , then let ;

[0081] Let Perform iterative calculation of the prediction success probability, The iteration stops when , \(L\) is a preset threshold, and when the iteration stops, select and output the prediction step length corresponding to the maximum prediction success probability;

[0082] On the one hand, after selecting the most appropriate prediction step length \(k\), if the current time node is \(T\), and there is a stationary behavior of a single operation area at the current time node, then it can be predicted that the single operation area after \(T + k\) steps is a stationary behavior;

[0083] On the other hand, if it is planned to predict the state behavior of a single operation area at the \(H\)-th time node, the most appropriate prediction step length \(k\) can be combined, and through the backward method for inverse simulation, the time node of the inverse simulation is \((H - T) / k\).

[0084] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0085] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A dust and toxicity detection method based on a safety helmet, characterized in that: The method comprises the following steps: Step S1: The concentration of target objects in the environment is collected by a dust and toxicity detection sensor and uploaded to the cloud detection center. The dust and toxicity detection sensor is installed in a safety helmet. The three-dimensional space of the work site is divided into working area monomers to receive the target object concentration collected by the dust and toxicity sensor when the worker wears a safety helmet and works in the working area monomer; Step S2: The dynamic density of the monomer in the operating area is obtained by the ratio of the number of operators in the monomer in the operating area to the volume of the monomer in the operating area. Based on the dynamic density, a monomer sample set at a time node is analyzed and generated; Step S3: construct a three-dimensional melt model, analyze and quantify the melt scale based on the monomer sample set to generate a circular domain concentration; Step S4: Analyze and characterize the flow state of dust and poison based on the circular concentration, and obtain the predicted step length based on the flow state; The specific implementation process of step S2 includes: The number of operators in each operating area is obtained, and the ratio of the number of operators in the operating area to the volume of the operating area is the dynamic density of the operating area, and the dynamic density is uploaded to the cloud detection center; At the tth time node, a monomer sample set is generated, denoted as ,in, represents the dynamic density of the monomer in the i-th operation area, and I represents the total number of monomers in the operation area; Select Dynamic Density Single sample set The centroid of , and collect all dynamic gradients of the centroid at the tth time node to form a gradient set, ,in, represents the gradient vector between the i-th operating area monomer and the j-th operating area monomer, represents the magnitude of the gradient vector, i.e. the dynamic gradient, and , represents the dynamic density of the monomer in the jth operating area; The specific implementation process of step S3 includes: Dynamic density Single sample set When the centroid of the i-th operation area is reached, the dynamic gradient is fitted to calculate the melting scale of the monomer in the i-th operation area. , where It represents the rounding function; Integral Scale As the radius, with the i-th working area monomer as the center, the target concentration uploaded by each dust and toxic detection sensor in the circle when the operator wears a safety helmet and works in the working area monomer is retrieved from the cloud detection center, and the average value of the target concentration uploaded by each dust and toxic detection sensor in the circle is obtained, which is recorded as the circle concentration with the i-th working area monomer as the center ; The specific implementation process of step S4 includes: Based on the circle concentration, quantify the flow state of the target object when the i-th operating area monomer is the center of the circle ,like , then let , indicating that at the tth time node, the monomer in the i-th operation area has a diffusion trend. , then let , indicating that at the tth time node, the i-th operating area monomer has a stationary behavior. , then let , indicating that at the tth time node, the i-th operating area monomer has a shrinking behavior, In terms of melt size is the radius, and the area of ​​the circle with the i-th operating area monomer as the center, In terms of melt size is the radius, and the area of ​​the circle with the i-th operating area monomer as the center, In terms of melt size is the radius, and the concentration of the circle with the monomer in the i-th operating area as the center; Generate the flow state set of the i-th operating area monomer, denoted as , T represents the current time node, initialize the prediction step length k, and evaluate the prediction success probability under the prediction step length k ; In the formula, if , then let ; like , then let ; make Perform iterative calculation of prediction success probability, The iteration stops when , L is the preset threshold, and the prediction step corresponding to the maximum prediction success probability is selected and output when the iteration stops.

2. The dust and toxicity detection method based on a safety helmet according to claim 1, characterized in that: The specific implementation process of step S1 includes: The dust and toxicity detection sensor installed in the helmet collects the target concentration in the environment and uploads it to the cloud detection center through a wireless network; a code with unique attributes is set for each helmet, and data storage space is allocated to the cloud detection center according to the coding attributes of the helmet, and the data storage space is used to store the target concentration; A three-dimensional spatial model of the work site is established, and the three-dimensional space of the work site is divided into several work area units of equal volume. When the workers wear safety helmets and work in the work area units, the cloud detection center receives the target object concentration collected by the dust and toxic sensors on the safety helmets in real time.

3. A dust and toxicity detection system based on a safety helmet, executing the dust and toxicity detection method according to claim 1, characterized in that: The system comprises: a data preparation module, a data preprocessing module, a data fitting module and a data analysis module; The data preparation module collects the target concentration in the environment through a dust and toxicity detection sensor and uploads it to the cloud detection center. The dust and toxicity detection sensor is installed in a safety helmet. The three-dimensional space of the work site is divided into work area monomers to receive the target concentration collected by the dust and toxicity sensor when the operator wears a safety helmet and works in the work area monomer. The data preprocessing module obtains the dynamic density of the operating area monomer by the ratio of the number of operators in the operating area monomer to the volume of the operating area monomer, and analyzes and generates a monomer sample set at a time node based on the dynamic density; The data fitting module is used to construct a three-dimensional melt model, analyze and quantify the melt scale based on the monomer sample set to generate a circular domain concentration; The data analysis module analyzes and characterizes the flow state of dust and toxic substances based on the circular domain concentration, and obtains the predicted step length based on the flow state analysis.

4. The dust and toxicity detection system based on a hard hat according to claim 3 is characterized in that: The data preparation module includes a data acquisition unit and a three-dimensional model unit; The data acquisition unit collects the target concentration in the environment through the dust and toxicity detection sensor installed in the safety helmet, sets a code with unique attributes for each safety helmet, and allocates data storage space to the cloud detection center according to the coding attributes of the safety helmet, and the data storage space is used to store the target concentration; The three-dimensional model unit is used to divide the three-dimensional space of the work site into a number of work area monomers of equal volume. When the workers wear safety helmets and work in the work area monomers, they instruct the dust and toxic sensors on the safety helmets to collect the target object concentration.

5. The dust and toxicity detection system based on a hard hat according to claim 4 is characterized in that: The data preprocessing module includes a dynamic density processing unit and a gradient processing unit; The dynamic density processing unit is used to obtain the number of operators in each operating area monomer, and the ratio of the number of operators in the operating area monomer to the volume of the operating area monomer is the dynamic density of the operating area monomer; The gradient processing unit is used to generate a monomer sample set at different time nodes. The monomer sample set records the dynamic density of monomers in different operating areas at the same time node. The spatial relationship between any two operating area monomers constitutes a gradient vector to generate a gradient set.

6. The dust and toxicity detection system based on a hard hat according to claim 5 is characterized in that: The data fitting module includes a melt fitting unit and a melt concentration processing unit; The melt fitting unit is used to take the dynamic density as the centroid of the monomer sample set and fit the dynamic gradient to obtain the melt scale; The melt concentration processing unit is used to use the melt scale as the radius and the working area monomer as the center of the circle, retrieve the target object concentration uploaded by each dust and toxic detection sensor in the circle when the operator wears a safety helmet and works in the working area monomer, and obtain the average of the target object concentration uploaded by each dust and toxic detection sensor in the circle as the circular domain concentration.

7. The dust and toxicity detection system based on a hard hat according to claim 6, characterized in that: The data analysis module includes a fluid state marking unit and a dust and toxicity detection prediction unit; The fluid state marking unit quantifies the flow state of the target object when the monomers in different operation areas are taken as the center of the circle based on the circle domain concentration; The dust and toxicity detection prediction unit is used to generate a set of flow states of monomers in different operating areas, and adjust the prediction step length through iterative analysis, evaluate the prediction success probability under the prediction step length, and select and output the prediction step length corresponding to the maximum prediction success probability when the iteration stops.

Images