Workshop air purifier intelligent regulation and control method based on laser dust detection

Abstract

The invention relates to the technical field of air purification, in particular to a workshop air purifier intelligent regulation and control method based on laser dust detection, and the method comprises the steps: firstly obtaining particle size grading concentration data in real time through a laser detection device, and calculating a dynamic pollution index of each monitoring point in combination with a preset weight coefficient; a pollution core area and a diffusion trend are identified according to exponential distribution, an optimal air distribution scheme is generated based on the position of the core area and the concentration gradient, meanwhile, the purifier power and the filter screen mode are adjusted in a self-adaptive mode according to the concentration change rate and the target threshold value, and control parameters are optimized regularly based on an energy consumption efficiency model and the standard reaching time; according to the invention, the concentration data of PM10, PM2.5 and PM0.5 are obtained by grading in real time through the laser dust detection device, and the comprehensive hazard index of dust is accurately quantified in combination with a dynamic weight coefficient set by a respiratory deposition medical model, so that the problem that the particle size toxicity difference cannot be distinguished in the prior art is thoroughly solved.

Description

Technical Field

[0001] The present invention relates to the technical field of air purification, and in particular to an intelligent control method for a workshop air purifier based on laser dust detection. Background Art

[0002] Workshop air purification technology is a key link in industrial environmental health management. Especially in scenarios such as manufacturing and processing where dust pollution is severe, efficient and accurate air purification systems are crucial to protecting worker health and production safety. Currently, there are many air purification devices on the market, and their control methods mainly rely on traditional sensor detection and fixed operating modes. However, with the increasing complexity of the industrial environment, existing technologies still have obvious limitations in dynamic pollution response, energy consumption optimization and refined control, so more intelligent solutions are needed.

[0003] Most of the existing workshop air purification systems use a control strategy based on fixed threshold triggering, such as when PM 2.5 When the concentration exceeds the preset limit, purification is initiated. However, this method cannot distinguish the degree of harm and spatial distribution characteristics of dust particles of different sizes, for example, PM 0.5 (Ultrafine particles) have a much higher penetration rate into the human respiratory system than PM 10 However, traditional systems only use total mass concentration as the basis for regulation, resulting in irrational allocation of purification resources. This may lead to excessive processing of low-hazard large particles, but fail to effectively suppress the diffusion of highly toxic ultrafine particles. In addition, existing technologies usually adopt a uniform air supply mode, which makes it difficult to carry out targeted purification of the core pollution areas in the workshop, resulting in energy waste and low cleaning efficiency.

[0004] Therefore, in response to the above problems, the present invention proposes an intelligent control method for workshop air purifiers based on laser dust detection, which detects PM2.5 in real time by grading. 10 、PM 2.5 With PM 0.5 The concentration of pollutants is calculated by combining the calculation of dynamic pollution index and analysis of spatial diffusion to realize intelligent identification of pollution core areas and differentiated air volume distribution, thereby significantly reducing energy consumption while ensuring purification effect. Summary of the Invention

[0005] In order to overcome the problems of inaccurate dust hazard assessment and lack of spatial dynamic adaptability of purification strategies in the existing technology, the present invention proposes an intelligent control method for workshop air purifiers based on laser dust detection.

[0006] The technical solution of the present invention is: an intelligent control method for a workshop air purifier based on laser dust detection, comprising the following steps:

[0007] S1, through the laser dust detection device to obtain the particle size classification dust concentration data of multiple monitoring points in the workshop in real time, including PM 10 、PM 2.5 With PM 0.5 concentration;

[0008] S2, calculating the dynamic pollution index of each monitoring point based on the particle size classification data and a preset dust hazard weight coefficient;

[0009] S3, identifying the core areas and diffusion trends of pollution based on the spatial distribution of the dynamic pollution index;

[0010] S4, based on the location, diffusion trend and real-time concentration gradient of the pollution core area, generates the optimal air volume distribution plan and controls the output of differentiated air volumes from multiple air outlets of the purifier;

[0011] S5, based on the real-time dust concentration change rate and the target cleanliness threshold, adaptively adjusts the purifier operating power and filter working mode;

[0012] S6, every time a preset period is passed, the control parameters of steps S1-S5 are optimized according to the energy efficiency model and the time required for purification to reach the target.

[0013] Preferably, the laser dust detection device includes a laser scattering module, a multi-channel particle size analysis module and a wireless transmission module, wherein the laser scattering module emits a laser beam and receives the particle scattering signal, and the multi-channel particle size analysis module analyzes the scattered signal into PM in real time. 10 、PM 2.5 With PM 0.5 The wireless transmission module sends the graded concentration data to the central controller.

[0014] As an example, the calculation formula of the dynamic pollution index in step S2 is: PI = α × C (PM 10 )+β×C(PM 2.5 )+γ×C(PM 0.5 ), where C(PM 10 )、C(PM 2.5 )、C(PM 0.5 ) represent the PM measured in real time by the laser dust detection device 10 、PM 2.5 With PM 0.5 The mass concentration value of , where the weight coefficients satisfy β>γ>α, β is 0.5-0.6, γ is 0.3-0.4, and α is 0.1-0.2. This coefficient combination is set based on respiratory system deposition experimental data.

[0015] Preferably, the identification of the pollution core area in step S3 simulates the spatial distribution of dust through a Gaussian diffusion model. When the dynamic pollution index of a monitoring point exceeds 120% of the average dynamic pollution index value of the area for three consecutive sampling cycles, the area within a radius of 2 meters from the point is marked as the pollution core area.

[0016] Preferably, the air volume distribution scheme of step S4 needs to meet the following requirements: the air volume distribution in the pollution core area shall not be less than 60% of the total air volume, and the remaining areas shall be distributed according to the gradient from the boundary of the core area, and the air volume shall be reduced by 10% for every additional meter of distance until the basic air volume maintenance value of 10% of the total air volume is reached.

[0017] As an example, the filter working mode switching rule in step S5 is as follows: when PM 2.5 The concentration change rate exceeds 5 μg / m 3 / min, the high-voltage electrostatic adsorption module is activated to deal with sudden pollution; when PM 0.5 When the concentration is higher than 30% of the total dust concentration for 5 minutes, it switches to HEPA filtration mode to capture ultrafine particles.

[0018] Preferably, the energy efficiency model of step S6 is: η = (ΔC×V) / (P×t), where ΔC is the average concentration reduction value at the monitoring point, V is the workshop volume, P is the real-time power consumption of the purifier, t is the time taken to reach the target cleanliness, and the optimization goal is to maximize η while ensuring t≤T_max, and T_max is the preset maximum purification time.

[0019] Preferably, the method also includes a pre-start strategy: the system obtains the start and stop status signals of the workshop production equipment in real time, and after detecting the equipment start signal, increases the purifier power to 80% of the peak power 10 minutes in advance to form a negative pressure protection barrier.

[0020] Preferably, the method is provided with a safety interlock mechanism. When the PI value of any monitoring point exceeds 150% of the OSHA dust exposure limit, the emergency fresh air system on the top of the workshop is automatically triggered to ventilate at a rate of 15m / min. 3 The air flow is injected into the area and the infrared sound and light alarm is activated at the same time.

[0021] As a preferred method, the weight coefficients α, β, and γ are dynamically updated through a machine learning model. Based on the LSTM machine learning model, historical dust concentration data, the frequency of respiratory abnormalities reported by the worker health monitoring system, and data from the ambient humidity sensor are used as training sets to generate optimized weight coefficients and overwrite the original parameters.

[0022] Beneficial effects of the present invention:

[0023] 1. The present invention uses a laser dust detection device to obtain PM in real time by grading 10 、PM 2.5 With PM 0.5 The concentration data, combined with the dynamic weight coefficient (β>γ>α) set by the respiratory deposition medical model, accurately quantifies the comprehensive hazard index of dust, completely solving the problem of the inability to distinguish the toxicity differences of particle size in existing technologies.

[0024] 2. Based on the pollution core area and concentration gradient data identified by the Gaussian diffusion model, the present invention dynamically generates a differentiated air volume distribution plan, in which the core area accounts for ≥60% of the air volume, and the air volume decreases by 10% for every additional meter of distance, thereby achieving targeted purification of the space. Compared with the traditional uniform air supply mode, the cleaning efficiency of the pollution core area is improved by 40-50% under the same energy consumption, while also reducing the energy waste caused by ineffective air supply in the edge areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 What is shown is a schematic diagram of the workflow of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0027] See also Figure 1 The present invention provides an embodiment: a method for intelligently controlling a workshop air purifier based on laser dust detection, comprising the following steps:

[0028] S1, through the laser dust detection device to obtain the particle size classification dust concentration data of multiple monitoring points in the workshop in real time, including PM 10 、PM 2.5 With PM 0.5 concentration;

[0029] S2, calculating the dynamic pollution index of each monitoring point based on the particle size classification data and a preset dust hazard weight coefficient;

[0030] S3, identifying the core areas and diffusion trends of pollution based on the spatial distribution of the dynamic pollution index;

[0031] S4, based on the location, diffusion trend and real-time concentration gradient of the pollution core area, generates the optimal air volume distribution plan and controls the output of differentiated air volumes from multiple air outlets of the purifier;

[0032] S5, based on the real-time dust concentration change rate and the target cleanliness threshold, adaptively adjusts the purifier operating power and filter working mode;

[0033] S6, every time a preset period is passed, the control parameters of steps S1-S5 are optimized according to the energy efficiency model and the time required for purification to reach the target.

[0034] The present invention uses a laser dust detection device to obtain PM in real time 10 、PM 2.5 With PM 0.5 The pollution index is dynamically calculated based on the graded concentration data of the system, combined with the preset dust hazard weight coefficient, to accurately identify the core pollution area and its diffusion trend, and generate the optimal air volume distribution plan based on this to achieve differentiated air supply control. At the same time, the purification power and filter working mode are adaptively adjusted based on the real-time concentration change rate, and a closed-loop control is formed through periodic iterative optimization, ultimately achieving a significant improvement in purification efficiency and reduced energy consumption.

[0035] The embodiments of the present invention are described below, specifically:

[0036] At least four distributed laser dust detection devices are deployed in the workshop. Each device includes a laser scattering module, a multi-channel particle size analysis module and a LoRa wireless transmission module. The laser scattering module uses a 650nm wavelength laser source to receive particle scattering signals at a 30-degree scattering angle, and converts the light intensity signal into particle size distribution data through Mie scattering theory. The multi-channel particle size analysis module has a built-in three-channel threshold processor corresponding to PM 10 (>0.5μm and ≤10μm), PM 2.5 (>0.3μm and ≤2.5μm) and PM 0.5 The real-time concentration of particles (≤0.5μm) is calculated with a sampling frequency of 1 time per second. All detection devices transmit data to the central controller via the LoRa self-organizing network.

[0037] After receiving the data from each monitoring point, the central controller performs the calculation of the dynamic pollution index (PI): according to the respiratory system deposition medical model, the weight coefficient α is set to 0.15 (PM 10 ), β=0.55(PM 2.5 ),γ=0.30(PM 0.5 ), according to the formula PI = 0.15 × C (PM 10 )+0.55×C(PM 2.5 )+0.30×C(PM 0.5) Generate the PI value of each point. The Gaussian plume diffusion model is used to identify the core pollution area. A two-dimensional grid is established with the monitoring point as the coordinate origin. The grid accuracy is 0.5m×0.5m. At the same time, real-time wind speed and direction data are input to calculate the concentration distribution of each grid point. When the PI value of a monitoring point exceeds 120% of the average PI value of the area with a radius of 5m for three consecutive times (with an interval of 10 seconds), the point is marked as a core pollution source point, and a circular target area with a radius of 2 meters is generated with this point as the center.

[0038] Generate an air volume distribution plan based on the target area location of the pollution core, and the total air volume is based on the maximum air volume of the purifier, 8000m 3 / h is the benchmark, and 60% of the wind volume is distributed in the target area, that is, 4800m 3 / h, and the rest of the area is allocated according to the gradient of the distance from the target area boundary - for every 1 meter increase in distance, the wind volume decreases by 10%, for example, 4320m is allocated at 1m away from the target area. 3 / h, 3888m3 is distributed at 2m 3 / h, maintain a minimum of 10% of the basic air volume, i.e. 800m 3 / h. The executive layer controls the multi-air outlet electric dampers through the CAN bus, and the opening of each damper is linearly adjusted according to the target air volume.

[0039] The filter system includes a high-voltage electrostatic adsorption module and a HEPA filter module. 2.5 Concentration change rate ≥5μg / m 3 / min and last for 2 minutes, the electrostatic adsorption module is activated and a high voltage electric field of 18kV is applied to capture charged particles. 0.5 When the concentration accounts for ≥30% of the total dust concentration and lasts for 5 minutes, it switches to HEPA mode and enables the 0.3μm pore size filter paper to intercept ultrafine particles. The two modes can be operated in combination.

[0040] Establish the energy efficiency model η=(ΔC×V) / (P×t), where ΔC is the average concentration reduction value of all monitoring points (μg / m 3 ), V is the workshop volume (e.g. 2000m 3 ), P is the real-time power of the purifier (kW), and t is the time taken to reduce the current concentration to the target cleanliness level, for example, 2.5 Reduced to 35 μg / m 3 The following process takes 12 minutes. The system performs an optimization iteration every 15 minutes. While ensuring that t ≤ 20 minutes, it adjusts the fan speed, air valve opening, and filter mode combination to solve for the parameter group corresponding to the maximum value of η and updates it to the control system.

[0041] The Modbus-RTU protocol is used to collect PLC status signals from workshop production equipment in real time. When a device startup signal is detected, the central controller immediately triggers the pre-start program. The purifier increases its power to 80% of its peak power within 10 seconds, the fan speed increases to 80Hz, and the air valve fully opens to form a negative pressure barrier. This state is maintained for 10 minutes. If the dust concentration does not exceed the standard, it automatically switches to optimization mode.

[0042] At the same time, the system sets the OSHA dust exposure limit (PM 2.5 =500 μg / m 3 ) as the safety threshold, i.e. 750 μg / m 3 When the PI value of any monitoring point exceeds the limit, the central controller immediately executes a three-level response: when the limit is exceeded for 30 seconds, the first-level response is triggered, activating the infrared sound and light alarm in the polluted area; when the limit is exceeded for 60 seconds, the second-level response starts the fresh air system on the top of the workshop, with a speed of 15m 3 / min flow rate to inject filtered fresh air; when the limit is exceeded for 90 seconds, the third-level response will force the shutdown of the nearest production equipment and send an alarm to the management terminal.

[0043] The present invention constructs an LSTM neural network model. The input layer contains three types of data: historical dust concentration calculated every seven days, the number of respiratory discomfort events reported by workers' health bracelets once a day, and environmental humidity sensor data collected every 10 minutes. The output layer generates optimized weight coefficients α', β', and γ'. The model is trained once a quarter, and the parameters are updated with the goal of maximizing the correlation coefficient between the frequency of actual health events and the predicted PI value. The new coefficients overwrite the original parameters after confirmation by engineers, thereby achieving model optimization.

[0044] The present invention can also be equipped with an industrial touch screen to display the PI value heat map of each monitoring point, the purifier operation status and energy efficiency curve in real time. At the same time, the system pushes data such as dust concentration exceeding the standard event and equipment pre-start record to the cloud platform. Maintenance personnel can remotely adjust the target cleanliness threshold through the mobile APP, such as PM 2.5 The standard is 35 μg / m 3 Changed to 25 μg / m 3 , after modification, the system automatically re-optimizes the control parameters.

[0045] Furthermore, the present invention provides an embodiment of a risk scenario of sudden aluminum powder explosion in a metal grinding workshop:

[0046] In the case of sudden ventilation system failure in the aluminum alloy wheel polishing workshop, the aluminum powder (PM 2.5 70%) concentration increased from 200 μg / m 3 Soared sharply to 1500μg / m3 , approaching the lower explosion limit concentration of aluminum powder. At the same time, the visibility in the working area dropped sharply to below 1 meter, posing a major explosion risk and the risk of acute aluminum pneumoconiosis poisoning for workers.

[0047] Conventional fixed threshold purification systems need to wait until the concentration reaches a preset 1000 μg / m 3 There is a delay window of at least 3 minutes before the response is initiated, and the uniform air supply mode adopted cannot quickly suppress the core pollution area, resulting in the continuous accumulation of high concentrations of aluminum powder. The system cannot link the production equipment to an emergency shutdown, making it impossible to eliminate major safety hazards in time.

[0048] The laser dust detection device used in the present invention monitors PM in real time. 2.5 Concentration change rate up to 300μg / m 3 / min, far exceeding 5μg / m 3 / min preset threshold, the central controller immediately implements a three-level emergency response: first, the 18kV high-voltage electrostatic module is activated to quickly absorb the charged aluminum powder; second, based on the Gaussian diffusion model, the radius of 2 meters from the grinder is locked as the core target area, thereby dynamically allocating 85% of the total air volume (6800m 3 / h) for purification, and at the same time forcibly cut off the power supply of the grinder, and start the fresh air system on the top of the workshop at 20m 3 Fresh air is injected at a flow rate of / min, and the system simultaneously triggers sound and light alarms and evacuates personnel. All data is uploaded to the factory safety monitoring platform in real time.

[0049] After using the present invention, the system will be PM in the core area within 2 minutes and 10 seconds. 2.5 Concentration from 1500 μg / m 3 Suppressed to 480 μg / m 3 The response speed is 4 times faster than that of traditional solutions, and the area with explosion risk is reduced by 80% through targeted air supply. The present invention avoids accidents through the equipment linkage mechanism.

[0050] Furthermore, the present invention provides an embodiment for enriching ultrafine particles in a high humidity environment of a paint spraying workshop:

[0051] In the automobile paint shop, the ambient humidity is continuously higher than 80%, and the PM in the water-based paint mist 0.5 It accounts for as much as 45%, which is much higher than the 20% in normal environments. At the same time, high humidity causes the HEPA filter to be quickly blocked due to condensation of water vapor.

[0052] The traditional solution causes optical sensors to misjudge due to humidity interference, and the detection value is more than 30% lower than the actual concentration, and it is unable to accurately identify PM 0.5The change in the proportion of air pollution causes the purification system to continue to operate inefficiently and continue to use the HEPA mode, which accelerates the scrapping of the filter.

[0053] The existing purification system relies on a single wavelength (such as 650nm) laser detection, which cannot effectively distinguish between water mist and particulate matter signals, resulting in PM 0.5 The concentration was seriously underestimated. At the same time, the system still forced the use of HEPA filtration according to a fixed pattern. The filter quickly became saturated in a high humidity environment, causing the filter replacement frequency to increase by 3 times and the operating cost to surge.

[0054] The present invention uses a laser dust detection device, which activates a dual-wavelength compensation algorithm (650nm+1550nm) and uses the difference in the absorption characteristics of water molecules at 1550nm wavelength to eliminate humidity interference signals, thereby accurately restoring PM 0.5 The central controller triggers the filter switching logic based on the corrected data, shuts down the HEPA module that is prone to clogging, and switches to high-voltage electrostatic adsorption mode. By increasing the electric field strength, it breaks through the water film on the surface of the particles, thereby improving the capture efficiency. In the calculation of the dynamic pollution index, the LSTM model automatically converts PM2.5 into PM2.5 based on historical humidity data and worker health feedback. 0.5 The weight coefficient γ was increased from 0.30 to 0.35, so that the system prioritizes processing ultrafine particles.

[0055] After using the present invention, PM 0.5 The purification efficiency increased from 68% to 92%, the filter replacement cycle was extended from 7 days to 21 days, and the overall energy consumption of the system decreased by 18%, perfectly adapting to the special needs of high-humidity paint workshops.

[0056] Furthermore, the present invention provides an embodiment for the dynamic migration of multiple pollution sources in a welding workshop:

[0057] In a large hull welding workshop, six welding machines operate at the same time and move frequently, causing the high-concentration pollution core area of ​​welding smoke to migrate in real time with the changes in welding points.

[0058] Traditional fixed purification systems are unable to track dynamic pollution sources, resulting in a purification delay of more than 5 minutes in the area 5 meters away from the welding machine, causing workers to be exposed to diffused high-concentration welding smoke for a long time.

[0059] The existing purification system adopts a static air outlet layout, and the air supply direction and air volume distribution cannot be adjusted as the location of the pollution source changes, resulting in a mismatch between the purified airflow and the pollution diffusion path. At the same time, the uniform air supply pattern causes more than 70% of the air volume to be wasted in low-pollution areas, and the purification efficiency in the core area is less than 50%.

[0060] The laser dust detection device of the present invention collects PM at each monitoring point at 1 second intervals. 2.5The central controller updates the pollution source coordinates every 30 seconds based on the Gaussian plume diffusion model, dynamically marks the mobile core area, and distributes 65% of the total air volume (5200m 3 / h) to the center of the circle. The air volume in the edge areas decreases by 10% for every meter away, ensuring concentration gradient control along the pollution diffusion path. The welder PLC position signal is acquired in real time via the Modbus-RTU protocol. Ten seconds before the welder moves, the adjacent clean air outlet is pre-activated to 80% power, forming a pilot negative pressure barrier. Simultaneously, an energy efficiency model dynamically optimizes the combination of fan speed and air valve opening, reducing the system's additional energy consumption by 25% when tracking mobile pollution sources.

[0061] After using the present invention, the air volume redistribution can be completed within 90 seconds after the pollution source moves, and the PM on the moving track can be 2.5 The concentration was always controlled at 50 μg / m 3 Compared with traditional systems, the purification efficiency of the core area is increased to 88%, the delayed exposure time of the edge area is shortened to less than 1 minute, and the overall energy consumption is reduced by 22%.

[0062] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the present invention may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An intelligent control method for workshop air purifiers based on laser dust detection, characterized in that: The following steps are included: S1, through the laser dust detection device to obtain the particle size classification dust concentration data of multiple monitoring points in the workshop in real time, including PM 10 、PM 2.5 With PM 0.5 concentration; S2, calculating the dynamic pollution index of each monitoring point based on the particle size classification data and a preset dust hazard weight coefficient; S3, identifying the core areas and diffusion trends of pollution based on the spatial distribution of the dynamic pollution index; S4, based on the location, diffusion trend and real-time concentration gradient of the pollution core area, generates the optimal air volume distribution plan and controls the output of differentiated air volumes from multiple air outlets of the purifier; S5, based on the real-time dust concentration change rate and the target cleanliness threshold, adaptively adjusts the purifier operating power and filter working mode; S6, every time a preset period is passed, the control parameters of steps S1-S5 are optimized according to the energy efficiency model and the time required for purification to reach the target.

2. The intelligent control method for workshop air purifiers based on laser dust detection according to claim 1 is characterized in that: The laser dust detection device includes a laser scattering module, a multi-channel particle size analysis module and a wireless transmission module, wherein the laser scattering module emits a laser beam and receives the particle scattering signal, and the multi-channel particle size analysis module analyzes the scattered signal into PM in real time. 10 、PM 2.5 With PM 0.5 The wireless transmission module sends the graded concentration data to the central controller.

3. The intelligent control method for workshop air purifiers based on laser dust detection according to claim 1 is characterized in that: The calculation formula of the dynamic pollution index in step S2 is: PI = α × C (PM 10 )+β×C(PM 2.5 )+γ×C(PM 0.5 ), where C(PM 10 )、C(PM 2.5 )、C(PM 0.5 ) represent the PM measured in real time by the laser dust detection device 10 、PM 2.5 With PM 0.5 The mass concentration value of , where the weight coefficients satisfy β>γ>α, β is 0.5-0.6, γ is 0.3-0.4, and α is 0.1-0.

2. This coefficient combination is set based on respiratory system deposition experimental data.

4. The intelligent control method for workshop air purifiers based on laser dust detection according to claim 1 is characterized in that: The identification of the pollution core area in step S3 simulates the spatial distribution of dust through the Gaussian diffusion model. When the dynamic pollution index of a monitoring point exceeds 120% of the average dynamic pollution index value of the area for three consecutive sampling periods, the area within a radius of 2 meters from the point is marked as the pollution core area.

5. The intelligent control method for workshop air purifier based on laser dust detection according to claim 1 is characterized in that: The air volume distribution scheme of step S4 must meet the following requirements: the air volume distribution in the pollution core area shall not be less than 60% of the total air volume, and the air volume distribution in the remaining areas shall be based on the gradient from the boundary of the core area, with the air volume decreasing by 10% for every additional meter of distance until the basic air volume maintenance value of 10% of the total air volume is reached.

6. The intelligent control method for workshop air purifier based on laser dust detection according to claim 1 is characterized in that: The filter working mode switching rule in step S5 is specifically as follows: 2.5 The concentration change rate exceeds 5 μg / m 3 / min, the high-voltage electrostatic adsorption module is activated to deal with sudden pollution; when PM 0.5 When the concentration is higher than 30% of the total dust concentration for 5 minutes, it switches to HEPA filtration mode to capture ultrafine particles.

7. The intelligent control method for workshop air purifier based on laser dust detection according to claim 1 is characterized in that: The energy efficiency model of step S6 is: η = (ΔC × V) / (P × t), where ΔC is the average concentration reduction value at the monitoring point, V is the workshop volume, P is the real-time power consumption of the purifier, and t is the time taken to reach the target cleanliness. The optimization goal is to maximize η while ensuring t ≤ T_max, and T_max is the preset maximum purification time.

8. The intelligent control method for workshop air purifier based on laser dust detection according to claim 1 is characterized in that: The method also includes a pre-start strategy: the system obtains the start and stop status signals of the workshop production equipment in real time, and after detecting the equipment start signal, increases the purifier power to 80% of the peak power 10 minutes in advance to form a negative pressure protection barrier.

9. The intelligent control method for workshop air purifiers based on laser dust detection according to claim 1 is characterized in that: The method is provided with a safety interlock mechanism. When the PI value of any monitoring point exceeds 150% of the OSHA dust exposure limit, the emergency fresh air system on the top of the workshop is automatically triggered to ventilate at a rate of 15m / min. 3 The air flow is injected into the area and the infrared sound and light alarm is activated at the same time.

10. The intelligent control method for workshop air purifiers based on laser dust detection according to any one of claims 1 to 9, characterized in that: The weight coefficients α, β, and γ are dynamically updated through the machine learning model. Based on the LSTM machine learning model, historical dust concentration data, the frequency of respiratory abnormalities reported by the worker health monitoring system, and data from the ambient humidity sensor are used as the training set to generate optimized weight coefficients and overwrite the original parameters.

Images