Public place gas detection method based on gas chromatography

Abstract

The invention relates to the technical field of gas component detection, in particular to a public place gas detection method based on gas chromatography, which comprises the following steps: a mobile robot covers all areas of a public place according to a predetermined path, collects an air sample, and pretreats the collected gas sample through a filter or an adsorbent; a gas sample enters a detector after being separated by a gas chromatographic column, and harmful gas components are identified; according to the detected harmful gas concentration, combining historical data and a threshold value, calculating the danger level of each region, and carrying out danger level division on the region of the public place; according to the danger level, the system automatically selects and executes corresponding countermeasures; and the system records a historical data set of all countermeasures, and optimizes the countermeasures through a machine learning algorithm. According to the invention, full coverage, multi-area dynamic monitoring, accurate risk prediction and grading processing can be realized, and the response speed and the use effect of the system are improved.

Description

Technical Field

[0001] The invention relates to the technical field of gas component detection, and in particular to a gas chromatography-based method for detecting gas in public places. Background Art

[0002] With the rapid development of industrialization and urbanization, the air quality problem in public places has received increasing attention. Many public places, such as stations, shopping malls, hospitals, etc., are prone to accumulate various harmful gases due to dense crowds and complex ventilation conditions. The high concentration accumulation of these harmful gases will not only pollute the environment, but also pose a serious threat to human health. Therefore, how to efficiently and accurately detect harmful gases in public places and quickly take countermeasures has become an urgent problem to be solved.

[0003] Traditional hazardous gas detection systems usually use fixed sensors to monitor gas concentrations, but they have problems such as limited detection area, slow response speed, and high equipment deployment cost. In addition, many existing systems only provide basic detection and alarm functions, lack dynamic risk prediction based on changes in gas concentration and automated execution of emergency measures, which affects the system's response speed and usage effect. Summary of the invention

[0004] In order to overcome the shortcomings and deficiencies in the prior art, the purpose of the present invention is to provide a gas detection method for public places based on gas chromatography, which can achieve full coverage, multi-area dynamic monitoring, accurate risk prediction and graded processing, while also realizing automated response measures execution and self-learning and feedback optimization, thereby improving the response speed and use effect of the system.

[0005] The present invention is achieved through the following technical solutions:

[0006] In a first aspect, the present invention discloses a method for detecting gas in public places based on gas chromatography, which comprises the following steps:

[0007] S100. The mobile robot covers all areas of the public place according to a predetermined path, collects air samples, and pre-treats the collected gas samples through filters or adsorbents;

[0008] S200. The gas sample is separated by a gas chromatography column and enters a detector to identify harmful gas components;

[0009] S300. Calculate the danger level of each area based on the detected concentration of harmful gases, combined with historical data and thresholds, and divide the danger level of areas in public places;

[0010] S400. According to the danger level, the system automatically selects and executes corresponding countermeasures;

[0011] S500. The system records the historical data set of all response measures and optimizes the response measures through machine learning algorithms.

[0012] In combination with the first aspect, further, in step S100, the predetermined path P of the mobile robot i The calculation formula is:

[0013]

[0014] Among them, (x, y, z) is the coordinates of the robot in three-dimensional space, t is time, (x′, y′, z′) is the position where the robot may move next, f(x, y, z, t) is the path planning function that determines the sampling position of the robot at different time points, h(x′, y′, z′) is the heuristic function that estimates the cost from the current position to the target position, and g(x′, y′, z′) is the cost paid from the starting point to the current position.

[0015] In combination with the first aspect, further, the mathematical formula of h(x′,u′,z′) is expressed as:

[0016]

[0017] Among them, (x goal ,y goal ,z goal ) are the coordinates of the target point;

[0018] The mathematical formula of g(x′,y′,z′) is:

[0019]

[0020] Among them, dist(P i-1 ,P i ) is from point P i-1 To point P i The moving distance or time.

[0021] In combination with the first aspect, further, in step S100, the calculation formula for pre-processing the gas is:

[0022] V in =η p ×V s

[0023] Among them, V s is the volume of the gas sample collected, V in is the volume of gas injected into the gas chromatography column, η p is the pretreatment efficiency;

[0024] Pretreatment efficiency η p The calculation formula is:

[0025]

[0026] Among them, C post is the average gas concentration before historical pretreatment, C pre is the average gas concentration after historical preprocessing.

[0027] In combination with the first aspect, further, in step S200, the identification formula of the harmful gas component is:

[0028]

[0029] Among them, C i is the concentration of the i-th harmful gas, A i is the chromatographic peak area of ​​the i-th harmful gas, F i is the correction factor for the i-th harmful gas.

[0030] In combination with the first aspect, further, in step S300, the calculation formula for the danger level L of the area is:

[0031]

[0032] Among them, μ i is the historical average concentration of the i-th harmful gas, σ i is the standard deviation of the i-th harmful gas.

[0033] In combination with the first aspect, further, in step S500, a linear regression model is used to optimize the countermeasures, and the historical data set includes the response time t response , Changes of harmful gas concentration over time C(t), Evaluation of effectiveness of countermeasures E effectiveness and the change of hazard level over time L(t);

[0034] The steps to build a linear regression model include:

[0035] Define a training function to optimize the countermeasures. The calculation formula of the training function is:

[0036]

[0037] in, is the effect of the countermeasures predicted by the model, W is the weight matrix of the model, X is the input variable matrix, and b is the bias;

[0038] Minimize the error between the predicted effect and the actual effect. The calculation formula is:

[0039]

[0040] Among them, Y is the effect of the original response measures;

[0041] Update the model parameters W and b by gradient descent:

[0042]

[0043] Among them, α is the learning rate, and is the gradient of the loss function with respect to W and b;

[0044] The updated model will be based on real-time data X real-time Make new coping strategies new , the formula is:

[0045] M new =W new ·X real-time +b new .

[0046] In a second aspect, the present invention further discloses a computer device, which includes a processor and a storage medium;

[0047] The storage medium is used to store instructions;

[0048] The processor is used to operate according to the instructions to execute the steps of the method described above.

[0049] Beneficial effects of the present invention:

[0050] 1. Full coverage, multi-region dynamic monitoring: This invention combines gas chromatography technology with mobile robots to achieve dynamic gas monitoring in different areas of public places. Compared with traditional fixed sensors, mobile robots can move flexibly over a large range and cover more monitoring points, effectively solving the problem of limited monitoring range of fixed sensors, and is particularly suitable for public places with dense traffic and complex areas.

[0051] 2. Accurate risk prediction and graded processing: The present invention detects the concentration of harmful gases in different areas in real time, uses mathematical models to conduct risk assessment and prediction, divides the regional hazard levels based on the risk prediction results, and automatically selects corresponding response measures, such as starting the ventilation system, triggering the alarm, or evacuating the crowd. This graded processing mechanism ensures that different hazard levels can get the most appropriate response measures, effectively avoiding unnecessary waste of resources and overreaction.

[0052] 3. Automated execution of response measures: The present invention not only has gas monitoring and risk assessment functions, but also integrates an automated execution module, which can automatically initiate corresponding response measures according to different hazard levels, such as ventilation, alarm, evacuation, etc. This automated execution function reduces the need for manual intervention and improves the response speed, which helps to respond quickly in times of crisis and ensure personnel safety.

[0053] 4. Self-learning and feedback optimization: The system has an intelligent feedback mechanism, which can continuously optimize future response strategies by recording and analyzing data during the execution process. Through the machine learning model, the system can self-optimize based on historical data, improve the prediction accuracy and response efficiency of future changes in harmful gas concentrations, and continuously improve the stability and intelligence level of the system in long-term operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0055] Figure 1 Flow chart of the detection method of the present invention. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0057] With the rapid development of industrialization and urbanization, the air quality problem in public places has received increasing attention. Many public places, such as stations, shopping malls, hospitals, etc., are prone to accumulate various harmful gases due to dense crowds and complex ventilation conditions. The high concentration accumulation of these harmful gases will not only pollute the environment, but also pose a serious threat to human health. Therefore, how to efficiently and accurately detect harmful gases in public places and quickly take countermeasures has become an urgent problem to be solved.

[0058] Traditional hazardous gas detection systems usually use fixed sensors to monitor gas concentrations, but they have problems such as limited detection area, slow response speed, and high equipment deployment cost. In addition, many existing systems only provide basic detection and alarm functions, lack dynamic risk prediction based on changes in gas concentration and automated execution of emergency measures, which affects the system's response speed and usage effect.

[0059] Example 1

[0060] In order to solve the above problems, this embodiment discloses a method for detecting gas in public places based on gas chromatography, which comprises the following steps:

[0061] S100. The mobile robot covers all areas of the public place according to a predetermined path, collects air samples, and pre-treats the collected gas samples through filters or adsorbents;

[0062] S200. The gas sample is separated by a gas chromatography column and enters a detector to identify harmful gas components;

[0063] S300. Calculate the danger level of each area based on the detected concentration of harmful gases, combined with historical data and thresholds, and divide the danger level of areas in public places;

[0064] S400. According to the danger level, the system automatically selects and executes corresponding countermeasures;

[0065] S500. The system records the historical data set of all response measures and optimizes the response measures through machine learning algorithms.

[0066] In this embodiment, according to the danger level, the system automatically selects and executes corresponding response measures, such as ventilation, alarm, or personnel evacuation; the response measures are preset in the system according to the actual situation and usage scenarios.

[0067] Further, in step S100, the predetermined path P of the mobile robot i The calculation formula is:

[0068]

[0069] Among them, (x, y, z) is the coordinates of the robot in three-dimensional space, t is time, (x′, y′, z′) is the position where the robot may move next, f(x, y, z, t) is the path planning function that determines the sampling position of the robot at different time points, h(x′, y′, z′) is the heuristic function that estimates the cost from the current position to the target position, and g(x′, y′, z′) is the cost paid from the starting point to the current position.

[0070] The path planning formula determines the next position of the robot by minimizing the sum of the estimated cost h(x′, y′, z′) from the current position to the goal position and the actual cost g(x′, y′, z′) from the starting position to the current position.

[0071] Furthermore, the mathematical formula of h(x′,y′,z′) is expressed as:

[0072]

[0073] Among them, (x goal ,y goal ,z goal ) are the coordinates of the target point;

[0074] The mathematical formula of g(x′,y′,z′) is:

[0075]

[0076] Among them, dist(P i-1 ,P i ) is from point P i-1 To point P i The moving distance or time.

[0077] In path planning, the robot gradually approaches the target point by moving. When the robot is at the position (x′, y′, z′) at a certain moment, the h(x′, y′, z′) in the formula calculates the distance from the current position (x′, y′, z′) to the target point (x goal ,y goal ,z goal ). This distance is usually used to evaluate the optimality of the path, and the robot will choose the direction with the smallest path cost to move.

[0078] Furthermore, in step S100, the calculation formula for pre-processing the gas is:

[0079] V in =η p ×V s

[0080] Among them, V s is the volume of the gas sample collected, V in is the volume of gas injected into the gas chromatography column, η p is the pretreatment efficiency;

[0081] Pretreatment efficiency η p The calculation formula is:

[0082]

[0083] Among them, C post is the average gas concentration before historical pretreatment, C pre is the average gas concentration after historical preprocessing.

[0084] Furthermore, in step S200, the identification formula of the harmful gas component is:

[0085]

[0086] Among them, C i is the concentration of the i-th harmful gas, A i is the chromatographic peak area of ​​the i-th harmful gas, F i is the correction factor for the i-th harmful gas.

[0087] Furthermore, in step S300, the calculation formula for the danger level L of the area is:

[0088]

[0089] Among them, μ i is the historical average concentration of the i-th harmful gas, σ i is the standard deviation of the i-th harmful gas.

[0090] Furthermore, in step S500, a linear regression model is used to optimize the countermeasures, and the historical data set includes the response time t of the countermeasures. response , Changes of harmful gas concentration over time C(t), Evaluation of effectiveness of countermeasures E effectiveness and the change of hazard level over time L(t);

[0091] The steps to build a linear regression model include:

[0092] Define a training function to optimize the countermeasures. The calculation formula of the training function is:

[0093]

[0094] in, is the effect of the countermeasures predicted by the model, W is the weight matrix of the model, X is the input variable matrix, and b is the bias;

[0095] Minimize the error between the predicted effect and the actual effect. The calculation formula is:

[0096]

[0097] Among them, Y is the effect of the original response measures;

[0098] Update the model parameters W and b by gradient descent:

[0099]

[0100] Among them, α is the learning rate, and is the gradient of the loss function with respect to W and b;

[0101] The updated model will be based on real-time data X real-time Make new coping strategies new , the formula is:

[0102] M new =W new ·X real-time +b new .

[0103] Here is an example, assuming an input variable matrix W is the weight matrix obtained by training the machine learning model b is set to 5.

[0104] Then the calculation process of Y is:

[0105]

[0106] Predicted effectiveness of countermeasures It can be understood as the efficiency score of the response measures performed by the system under current conditions.

[0107] The system can use this prediction result Select the appropriate response. If the response is high, it means that the response is effective and the system may only start the ventilation system; If the risk is lower, a more severe alarm or even evacuation may be necessary. For example: Activate ventilation system; Activate the alarm; People evacuated.

[0108] Example 2

[0109] This embodiment provides a computer device, including a processor and a storage medium;

[0110] The storage medium is used to store instructions;

[0111] The processor is used to operate according to the instructions to execute the steps of any method described in Example 1.

[0112] Example 3

[0113] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

[0114] In summary, the gas chromatography-based public place gas detection method, electronic device and storage medium provided by the present invention have the following effects:

[0115] 1. Full coverage, multi-region dynamic monitoring: This invention combines gas chromatography technology with mobile robots to achieve dynamic gas monitoring in different areas of public places. Compared with traditional fixed sensors, mobile robots can move flexibly over a large range and cover more monitoring points, effectively solving the problem of limited monitoring range of fixed sensors, and is particularly suitable for public places with dense traffic and complex areas.

[0116] 2. Accurate risk prediction and graded processing: The present invention detects the concentration of harmful gases in different areas in real time, uses mathematical models to conduct risk assessment and prediction, divides the regional hazard levels based on the risk prediction results, and automatically selects corresponding response measures, such as starting the ventilation system, triggering the alarm, or evacuating the crowd. This graded processing mechanism ensures that different hazard levels can get the most appropriate response measures, effectively avoiding unnecessary waste of resources and overreaction.

[0117] 3. Automated execution of response measures: The present invention not only has gas monitoring and risk assessment functions, but also integrates an automated execution module, which can automatically initiate corresponding response measures according to different hazard levels, such as ventilation, alarm, evacuation, etc. This automated execution function reduces the need for manual intervention and improves the response speed, which helps to respond quickly in times of crisis and ensure personnel safety.

[0118] 4. Self-learning and feedback optimization: The system has an intelligent feedback mechanism, which can continuously optimize future response strategies by recording and analyzing data during the execution process. Through the machine learning model, the system can self-optimize based on historical data, improve the prediction accuracy and response efficiency of future changes in harmful gas concentrations, and continuously improve the stability and intelligence level of the system in long-term operation.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solution of the present invention.

Claims

1. A method for detecting gas in public places based on gas chromatography, characterized in that: The following steps are involved: S100. The mobile robot covers all areas of the public place according to a predetermined path, collects air samples, and pre-treats the collected gas samples through filters or adsorbents; S200. The gas sample is separated by a gas chromatography column and enters a detector to identify harmful gas components; S300. Calculate the danger level of each area based on the detected concentration of harmful gases, combined with historical data and thresholds, and divide the danger level of areas in public places; S400. According to the danger level, the system automatically selects and executes corresponding countermeasures; S500. The system records the historical data set of all response measures and optimizes the response measures through machine learning algorithms.

2. A method for detecting gas in public places based on gas chromatography according to claim 1, characterized in that: In step S100, the predetermined path P of the mobile robot is i The calculation formula is: Among them, (x, y, z) are the coordinates of the robot in three-dimensional space, t is the time, (x ′ ,y ′ ,z ′ ) is the possible next move position of the robot, f(x,y,z,t) is the path planning function that determines the sampling position of the robot at different time points, h(x ′ ,y ′ ,z ′ ) is a heuristic function that estimates the cost from the current position to the target position, g(x ′ ,y ′ ,z ′ ) is the cost paid from the starting point to the current position.

3. A method for detecting gas in public places based on gas chromatography according to claim 2, characterized in that: h(x ′ ,y ′ ,z ′ ) is expressed as: Among them, (x goal ,y goal ,z goal ) are the coordinates of the target point; g(x ′ ,y ′ ,z ′ ) is expressed as: Among them, dist(P i-1 ,P i ) is from point P i-1 To point P i The moving distance or time.

4. A method for detecting gas in public places based on gas chromatography according to claim 1, characterized in that: In step S100, the calculation formula for pre-processing the gas is: V in =the p ×V s Among them, V s is the volume of the gas sample collected, V in is the volume of gas injected into the gas chromatography column, η p is the pretreatment efficiency; Pretreatment efficiency η p The calculation formula is: Among them, C post is the average gas concentration before historical pretreatment, C pre is the average gas concentration after historical preprocessing.

5. A method for detecting gas in public places based on gas chromatography according to claim 4, characterized in that: In step S200, the identification formula of harmful gas components is: Among them, C i is the concentration of the i-th harmful gas, A i is the chromatographic peak area of ​​the i-th harmful gas, F i is the correction factor for the i-th harmful gas.

6. A method for detecting gas in public places based on gas chromatography according to claim 5, characterized in that: In step S300, the calculation formula for the danger level L of the area is: Among them, μ i is the historical average concentration of the i-th harmful gas, σ i is the standard deviation of the i-th harmful gas.

7. A method for detecting gas in public places based on gas chromatography according to claim 1, characterized in that: In step S500, a linear regression model is used to optimize the countermeasures, and the historical data set includes the response time t response , Changes of harmful gas concentration over time C(t), Evaluation of effectiveness of countermeasures E effectiveness and the change of hazard level over time L(t); The steps to build a linear regression model include: Define a training function to optimize the countermeasures. The calculation formula of the training function is: in, is the effect of the countermeasures predicted by the model, W is the weight matrix of the model, X is the input variable matrix, and b is the bias; Minimize the error between the predicted effect and the actual effect. The calculation formula is: Among them, Y is the effect of the original response measures; Update the model parameters W and b by gradient descent: Among them, α is the learning rate, and is the gradient of the loss function with respect to W and b; The updated model will be based on real-time data X real-time Make new coping strategies new , the formula is: M new =W new ·X real-time +b new 。

Images