Laminar flow hood and purification system

Abstract

The embodiment of the present specification provides a laminar flow hood and a purification system. The laminar flow hood comprises an air extractor, a return air panel, at least one filter, an air inlet panel, an ultraviolet disinfection lamp, a uniform flow film, a curtain and a touch panel. The at least one filter comprises a first filter and a second filter. The purification system comprises the laminar flow hood, an air quality detection device, an image acquisition device, a memory and a general controller. The general controller is configured to: control the air quality detection device to obtain air quality detection data of at least one preset area; control the image acquisition device to acquire detection images of at least one worker; determine updated operation parameters of the laminar flow hood at at least one preset point based on the air quality detection data and the detection images; generate updated control instructions based on the updated operation parameters, and send the updated control instructions to the laminar flow hood at the at least one preset point and the memory.

Description

Technical Field

[0001] This manual relates to the field of air purification, and in particular to a laminar flow hood and purification system. Background Technology

[0002] A laminar flow hood is a modular purification unit that protects a defined area from dust and other air pollutants by maintaining a constant unidirectional filtered airflow, thus safeguarding product quality and personnel safety. Currently, most laminar flow hoods only execute preset parameters during operation and cannot adjust fan power, requiring manual adjustments when the environment changes. This low level of automation impacts efficiency and fails to meet user needs promptly.

[0003] To address the aforementioned issues, CN208205281U provides an automatically adjustable fresh air laminar flow hood that can detect air quality in real time using an air quality detection device and automatically adjust the fan speed based on the air quality. However, it does not address how to determine operating parameters such as fan power based on the detected air quality.

[0004] Therefore, it is desirable to provide a laminar flow hood and purification system that can help automatically adjust appropriate operating parameters (such as fan power) to improve work efficiency while saving energy and protecting the environment. Summary of the Invention

[0005] One embodiment of this specification provides a laminar flow hood, which includes an exhaust fan, a return air panel, at least one filter, an air inlet panel, an ultraviolet disinfection lamp, a flow equalization membrane, a curtain, and a touch panel. The at least one filter includes a first filter and a second filter. The exhaust fan is used to draw in air from at least one preset area and send it to the second filter for filtration. The return air panel is used to recover contaminated air from the at least one preset area. The first filter is used to filter the contaminated air to obtain first filtered air. The second filter is used to filter the first filtered air and / or air from the at least one preset area to obtain second filtered air and send it to the at least one preset area. The air inlet panel is used to draw in air from the at least one preset area. The ultraviolet disinfection lamp is used to disinfect the second filtered air. The flow equalization membrane is used to uniformly send the second filtered air into the at least one preset area. The curtain is used to purify the second filtered air within the at least one preset area. The touch panel is used by at least one operator to adjust the laminar flow hood.

[0006] One embodiment of this specification provides a purification system, which includes a laminar flow hood, an air quality detection device, an image acquisition device, a memory, and a main controller. The laminar flow hood and / or the air quality detection device are deployed at at least one preset location. The main controller is configured to: control the air quality detection device to acquire air quality detection data of at least one preset area and send it to the memory for storage, wherein the at least one preset area corresponds to the at least one preset location; control the image acquisition device to acquire detection images of at least one worker and send them to the memory for storage; determine updated operating parameters for the laminar flow hood at the at least one preset location based on the air quality detection data and the detection images, wherein the updated operating parameters include fan power; and generate an update control command based on the updated operating parameters and send the update control command to the laminar flow hood at the at least one preset location and the memory.

[0007] One embodiment of this specification provides a purification device, the device including at least one main controller and at least one memory; the at least one memory is used to store computer instructions; the at least one main controller is used to execute at least some of the computer instructions to: control an air quality detection device to acquire air quality detection data of at least one preset area and send it to the memory for storage, the at least one preset area corresponding to at least one preset location; control an image acquisition device to acquire detection images of at least one worker and send them to the memory for storage; based on the air quality detection data and the detection images, determine the updated operating parameters of the laminar flow hood at the at least one preset location, the updated operating parameters including fan power; based on the updated operating parameters, generate an update control command and send the update control command to the laminar flow hood at the at least one preset location and the memory.

[0008] One embodiment of this specification provides a computer-readable storage medium storing computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the following: controlling an air quality detection device to acquire air quality detection data for at least one preset area and sending it to a memory for storage, wherein the at least one preset area corresponds to at least one preset location; controlling an image acquisition device to acquire detection images of at least one worker and sending them to the memory for storage; determining updated operating parameters for the laminar flow hood at the at least one preset location based on the air quality detection data and the detection images, wherein the updated operating parameters include fan power; generating an update control command based on the updated operating parameters and sending the update control command to the laminar flow hood at the at least one preset location and the memory. Attached Figure Description

[0009] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is an exemplary schematic diagram of a laminar flow hood according to some embodiments of this specification;

[0011] Figure 2 These are exemplary schematic diagrams of purification systems shown in some embodiments of this specification;

[0012] Figure 3 This is an exemplary flowchart of purification according to some embodiments of this specification;

[0013] Figure 4 This is an exemplary flowchart illustrating the determination of updated operating parameters according to some embodiments of this specification;

[0014] Figure 5 This is an exemplary schematic diagram illustrating the determination of updated operating parameters based on a preset algorithm according to some embodiments of this specification. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0018] Currently, most laminar flow hoods only execute preset parameters during operation and cannot adjust fan power, etc. When the environment changes, manual adjustments are required, resulting in low intelligence. CN208205281U provides an automatically adjusting fresh air laminar flow hood that automatically adjusts the airflow based on air quality, but it does not address how to determine operating parameters such as fan power based on detected air quality, nor does it consider the impact of personnel movement within the area. When people move within the area, they cause airflow, altering the unidirectional airflow created by the laminar flow hood to some extent, affecting the purification effect. In this case, it is still necessary to adjust operating parameters such as fan power to mitigate the impact of personnel movement within the area.

[0019] Therefore, it is desirable to provide a laminar flow hood and purification system that can automatically adjust appropriate operating parameters (such as fan power) of the laminar flow hood based on air quality assessment results and the characteristics of people in the area, thereby improving work efficiency while saving energy and protecting the environment.

[0020] Figure 1 This is an exemplary schematic diagram of a laminar flow hood according to some embodiments of this specification.

[0021] like Figure 1 As shown, the laminar flow hood 100 may include an exhaust fan 110, a return air panel 120, at least one filter 130, an air inlet panel 140, an ultraviolet disinfection lamp 150, a flow equalization membrane 160, a curtain 170, and a touch panel 180.

[0022] The exhaust fan 110 can refer to a ventilation device that can be used for both blowing and drawing air. In some embodiments, the exhaust fan can be started at least half an hour before using the laminar flow hood to ensure that the indoor air reaches a stable clean state. In some embodiments, the exhaust fan can draw in air from at least one preset area from the return air panel, filter it through a second filter, and then distribute it to the preset area in a unidirectional laminar flow manner. The air outside the preset area can be outdoor air. For details regarding the second filter, please refer to the relevant description below.

[0023] The return air panel 120 may refer to a device or component used to recycle contaminated air from at least one preset area. In some embodiments, a clean unidirectional flow can blow contaminated air from the work area into the return air panel. After being purified by a first filter in the return air panel, the contaminated air is circulated to the top of the laminar flow hood, purified by a second filter, and then blown into the preset area. This cycle is repeated to maintain the cleanliness of the preset area.

[0024] Filter 130 may refer to a device for filtering polluted air and / or outdoor air drawn in by an exhaust fan. In some embodiments, at least one filter may include a first filter 131 and a second filter 132.

[0025] The first filter 131 can refer to a filter used to filter polluted air and obtain first filtered air. In some embodiments, the first filter can be a pre-filter or medium-efficiency filter, such as an activated carbon filter, a water vapor filter module, etc. Polluted air can refer to air with a cleanliness level lower than that required for a preset area. First filtered air can refer to air after the polluted air has been filtered by the first filter to remove large particulate dust particles.

[0026] The second filter 132 may refer to a filter used to filter the first filtered air and / or air outside at least one preset area, to obtain the second filtered air and deliver it to at least one preset area. In some embodiments, the second filter may be a high-efficiency filter, such as a nanofiber filter. The second filtered air may refer to air whose cleanliness meets the requirements of the preset area.

[0027] The air intake panel 140 may refer to a device or component used to draw in air from at least one preset area. In some embodiments, in order to maintain a positive pressure environment within the preset area of ​​the laminar flow hood, the air intake panel may simultaneously draw in outdoor air to compensate for the pressure loss in the return air duct. The unidirectional laminar flow clean environment not only purifies the local environment but also creates a positive pressure environment to prevent dust particles and the like from entering the preset area.

[0028] The ultraviolet disinfection lamp 150 can refer to a device that uses the principle of ultraviolet sterilization for disinfection. In some embodiments, the ultraviolet disinfection lamp can be used for disinfection of a second filtered air. In some embodiments, the ultraviolet disinfection lamp and the exhaust fan can be electrically connected to an external power supply and an external control device via a wiring harness.

[0029] The uniform flow membrane 160 can refer to a special membrane material used to uniformly deliver the second filtered air into at least one preset area, such as an ultrafiltration membrane or a nanomembrane.

[0030] Curtain 170 can refer to a device used to purify a second filtered air within at least one preset area.

[0031] The touch panel 180 can refer to a device used by at least one worker to adjust the laminar flow hood. For example, at least one worker can manually adjust the power of the exhaust fan, etc., via the touch panel 180.

[0032] In some embodiments, the laminar flow hood 100 may also include a microprocessor (not shown) and at least one dirt detection device (not shown).

[0033] A microprocessor can refer to a device or component used to process data and / or information obtained from a laminar flow hood. Based on this data, information, and / or processing results, the microprocessor can execute program instructions to perform one or more functions described in this specification. For example, the microprocessor can control the laminar flow hood to operate with preset operating parameters; control at least one fouling detection device to acquire fouling characteristics of at least one filter at a preset frequency and upload the fouling characteristics to a central controller; and, in response to receiving an update control command from the central controller, control the laminar flow hood to operate with updated operating parameters. Further details about microprocessors can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0034] A dirt detection device can refer to a device or component used to obtain dirt accumulation characteristics of at least one filter. In some embodiments, the dirt detection device may be located inside the filter, and the number of dirt detection devices may correspond one-to-one with the number of filters.

[0035] In some embodiments, the laminar flow hood may further include a housing, PVC panels, an optical camera, etc. The housing may include the laminar flow hood body, an air inlet, a purification flange, a dust filter, purification ducts, maintenance doors, a motor, an air intake duct, and connecting hoses. The PVC panels can increase the cleanliness and purification effect within the preset area.

[0036] Figure 2 This is an exemplary schematic diagram of a purification system according to some embodiments of this specification.

[0037] like Figure 2 As shown, the purification system 200 may include a laminar flow hood 100 deployed at at least one preset location, an air quality detection device 210 deployed at at least one preset location, an image acquisition device 220, a memory 230, and a main controller 240.

[0038] A laminar flow hood 100 can refer to a device used to provide a unidirectional airflow environment and filter air. In some embodiments, a laminar flow hood may include one or more, each deployed at at least one preset location. A preset location may refer to a pre-defined installation position of the laminar flow hood and air quality detection device. For example, the preset location can be set anywhere indoors. More information about laminar flow hoods can be found at [link to relevant documentation]. Figure 1 And its related descriptions.

[0039] Air quality detection device 210 can refer to a device or component used to acquire air quality detection data. For example, the air quality detection device may include at least one of a dust particle counter, a dust sensor, etc. In some embodiments, the air quality detection device may be deployed at at least one preset point in a plurality of predefined preset areas. For example, the air quality detection device may be deployed at a preset point in the middle / slightly above the middle / above the middle of a preset area. In some embodiments, the preset point where the air quality detection device is deployed is not higher than the preset point where the laminar flow hood is deployed. More information about preset areas can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0040] Image acquisition device 220 can refer to a device or component used to acquire inspection images of at least one worker. For example, image acquisition device may include a digital camera, a video camera, or other device capable of acquiring images.

[0041] The memory 230 may store data and / or information related to the purification system 200. For example, the memory 230 may store air quality detection data obtained from air quality detection devices, image acquisition devices, and microprocessors, as well as detection images of personnel and update control commands. In some embodiments, the memory may include a mass storage device, a removable memory, a volatile read-write memory, a read-only memory (ROM), or any combination thereof.

[0042] The main controller 240 refers to the controller used to process information and / or data related to the purification system 200. Based on this data, information, and / or processing results, the main controller 240 can execute program instructions to perform one or more functions described in this specification. In some embodiments, the main controller 240 may be communicatively connected to the laminar flow hood 100, the air quality detection device 210, the image acquisition device 220, and the memory 230. More information about the main controller 240 can be found in [link to relevant documentation]. Figures 3 to 5 Related descriptions.

[0043] In some embodiments, the main controller 240 can control the air quality detection device to acquire air quality detection data for at least one preset area and send it to a memory for storage, wherein the at least one preset area corresponds to at least one preset location; control the image acquisition device to acquire detection images of at least one worker and send them to the memory for storage; determine updated operating parameters for the laminar flow hood at at least one preset location based on the air quality detection data and detection images, wherein the updated operating parameters include fan power; generate an update control command based on the updated operating parameters, and send the update control command to the laminar flow hood at at least one preset location and the memory. Further details can be found in [link to relevant documentation]. Figure 3 Related descriptions.

[0044] It should be noted that the above description of the purification system 200 and its modules is for convenience only and should not be construed as limiting this specification to the scope of the illustrated embodiments. It is understood that those skilled in the art, after understanding the principles of this system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles.

[0045] Figure 3 This is an exemplary flowchart of purification according to some embodiments of this specification. In some embodiments, process 300 may be executed by a central controller. Figure 3 As shown, process 300 includes the following steps:

[0046] Step 310: Obtain air quality detection data for at least one preset area and send it to the memory for storage.

[0047] Air quality monitoring data refers to data obtained after analyzing and detecting air. For example, air quality monitoring data can include dust concentration, polluted air, etc., in at least one preset area.

[0048] A preset area can refer to an indoor area where air quality testing is required. In some embodiments, the preset area can be pre-set manually. In some embodiments, at least one preset area can correspond one-to-one with at least one preset point; more information about preset points can be found here. Figure 2 And its related descriptions.

[0049] In some embodiments, the central controller can acquire air quality monitoring data for corresponding preset areas in real time or at preset time intervals using air quality monitoring devices deployed at different preset locations. Further details regarding the air quality monitoring devices can be found in [link to relevant documentation]. Figure 2 And related descriptions. The time for acquiring air quality monitoring data can be set according to actual needs.

[0050] In some embodiments, the central controller can send the acquired air quality detection data to a memory for storage. Further details regarding the memory can be found in [link to relevant documentation]. Figure 2 And its related descriptions.

[0051] Step 320: Acquire an inspection image of at least one worker and send it to the memory for storage.

[0052] A detection image refers to an image that includes the features of at least one worker. In some embodiments, the features of at least one worker may include information such as the number, location, status, and movement of the workers. In some embodiments, the number of detection images may be one or more. A single detection image can reflect static information such as the number and location of workers, while multiple detection images at different points in time can reflect dynamic information such as the movement distance and direction of the workers.

[0053] In some embodiments, the central controller may use an image acquisition device to take at least one image of at least one worker in real time or at preset time intervals, thereby acquiring at least one detection image of at least one worker. Further details regarding the image acquisition device can be found in [link to relevant documentation]. Figure 2 And its related descriptions.

[0054] In some embodiments, the central controller can send the detected images of at least one worker to a memory for storage.

[0055] Step 330: Based on air quality monitoring data and images, determine the updated operating parameters of the laminar flow hood at at least one preset location. More information about preset locations can be found at [link to relevant documentation]. Figure 2 And its related descriptions.

[0056] Updating operating parameters can refer to the operating parameters adopted after the laminar flow hood has been adjusted. For example, updated operating parameters may include wind speed, fan power, etc. In some embodiments, updated operating parameters may include updated operating parameters of laminar flow hoods deployed at different preset locations, and the updated operating parameters of different laminar flow hoods may be the same or different.

[0057] In some embodiments, the main controller can determine the updated operating parameters of the laminar flow hood at at least one preset location in a variety of ways. For example, the main controller can determine the updated operating parameters based on air quality monitoring data and images, using a preset table or similar method. For instance, the preset table may specify that the higher the air quality reflected in the air quality monitoring data, the fewer the number of workers reflected in the images, and the shorter the movement distance, the lower the fan power required for updating the operating parameters.

[0058] In some embodiments, the main controller can determine updated operating parameters for at least one preset laminar flow hood based on a first negative index and a second negative index. For more details, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0059] In some embodiments, the main controller can determine updated operating parameters based on a preset algorithm; for more details, please refer to [link to relevant documentation]. Figure 5 And its related descriptions.

[0060] Step 340: Based on the updated operating parameters, generate an update control command and send the update control command to at least one preset laminar flow hood and memory.

[0061] An update control command is a control command corresponding to updating operating parameters. In some embodiments, the update control command can be used to control at least one pre-set laminar flow hood to update its operating parameters.

[0062] In some embodiments, the main controller may generate corresponding update control instructions based on the updated operating parameters, and send the update control instructions to at least one preset laminar flow hood and memory, so that the laminar flow hood operates with the updated operating parameters.

[0063] In some embodiments, the main controller can generate updated operating parameters in real time or at preset time intervals, thereby ensuring that the laminar flow hoods at preset locations operate with updated operating parameters in a timely manner after environmental changes.

[0064] By using acquired air quality monitoring data and images to determine updated operating parameters, the system can better meet actual needs and automatically adjust appropriate parameters without manual intervention. This approach can improve work efficiency while saving energy and protecting the environment.

[0065] In some embodiments, the microprocessor can control the laminar flow hood to operate with preset operating parameters; control at least one dirt detection device to acquire dirt accumulation characteristics of at least one filter at a preset frequency and upload the dirt accumulation characteristics to the main controller; and, in response to receiving an update control command from the main controller, control the laminar flow hood to operate with updated operating parameters. More information about the microprocessor, laminar flow hood, dirt detection device, at least one filter, and main controller can be found in [link to relevant documentation]. Figure 1 , 2 And its related descriptions.

[0066] Preset operating parameters can refer to the pre-set operating parameters of the laminar flow shield. For example, preset initial operating parameters. In some embodiments, the preset operating parameters of laminar flow shields deployed at different preset locations can be the same or different. In some embodiments, the laminar flow shield initially operates with preset operating parameters.

[0067] The preset frequency can refer to the number of times the dirt detection device acquires the dirt accumulation characteristics of the filter per unit time. For example, the preset frequency could be 6 times / hour. In some embodiments, the preset frequency can be set manually based on air quality. For example, the higher the air quality, the lower the preset frequency can be set.

[0068] Debris characteristics can refer to features associated with dirt accumulation on a filter. For example, debris characteristics may include the area and size of the accumulated dirt. In some embodiments, a microprocessor may acquire debris characteristics of at least one filter at a preset frequency via a dirt detection device and upload the debris characteristics to a central controller.

[0069] In some embodiments, the main controller can determine updated operating parameters for at least one preset laminar flow hood based on fouling characteristics, air quality detection data, and detection images, using a preset table. For example, the preset table may specify that the more fouling reflected in the filter, the worse the air quality and / or the reduced filter purification capacity in the historical preset area, and the main controller can accordingly increase the fan power in the updated operating parameters.

[0070] In some embodiments, the main controller may generate an update control command based on the updated operating parameters and send the update control command to at least one laminar flow hood and memory at a preset location.

[0071] In some embodiments, the microprocessor can control the laminar flow shield to update its operating parameters after receiving an update operation instruction from the main controller.

[0072] By uploading fouling characteristics to the central controller via a microprocessor, and determining updated operating parameters based on these characteristics, the accuracy of the determined updated operating parameters can be improved, which is beneficial to ensuring the purification effect of the laminar flow hood.

[0073] It should be noted that the above description of the process is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the process under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0074] Figure 4 This is an exemplary flowchart illustrating the determination and updating of operating parameters according to some embodiments of this specification. In some embodiments, process 400 may be executed by a central controller. Figure 4 As shown, process 400 includes the following steps:

[0075] Step 410: Determine the indoor air quality assessment results based on the air quality detection data.

[0076] For more information on air quality monitoring data, please refer to [link / reference]. Figure 3 Related descriptions.

[0077] An air quality assessment result refers to the assessment result of indoor air quality. For example, an air quality assessment result could be the assessment result of air quality monitoring data for at least one preset area. Indoor can refer to an enclosed space that includes at least one preset area.

[0078] In some embodiments, the central controller can determine the indoor air quality assessment result based on air quality monitoring data through various methods. For example, the central controller can perform modeling or use various data analysis algorithms, such as regression analysis and discriminant analysis, to analyze and process the air quality monitoring data to obtain the air quality assessment result.

[0079] In some embodiments, the air quality assessment results may include a first assessment result and a second assessment result.

[0080] The first assessment result is the assessment result of the air quality of each preset area.

[0081] The first evaluation result can be determined in a variety of ways. In some embodiments, the central controller can determine the first evaluation result by performing a weighted summation based on the difference between the air quality detection data (dust concentration) and the concentration threshold of each preset area and a first weight.

[0082] The primary weight can be related to the number of people in the preset area or the functional zoning of the preset area. Functional zoning refers to the division of the interior according to its function; for example, functional zoning can include work areas, rest areas, and passageways.

[0083] In some embodiments, the more people in the preset area, and the more the preset area belongs to the work area, the greater the corresponding first weight.

[0084] A concentration threshold refers to the maximum allowable dust concentration in a preset area. Different preset areas have different purification requirements, and therefore different concentration thresholds. For example, workbench areas or preset areas with a high number of people have higher purification requirements and correspondingly lower concentration thresholds. Conversely, other preset areas have lower purification requirements and correspondingly higher concentration thresholds. Concentration thresholds can be values ​​determined based on experiments or experience.

[0085] In some embodiments, the central controller can reasonably consider the layout of each preset area to improve the comprehensiveness of air quality assessment and the accuracy of the first assessment results.

[0086] The second assessment result is the assessment result of the overall indoor air quality difference.

[0087] The second evaluation result can be determined in several ways. In some embodiments, the main controller can determine the second evaluation result based on the air quality detection data of each preset area and its neighboring preset areas. For example, the main controller can calculate the difference between the air quality detection data of each preset area and its neighboring areas, where the neighboring areas of a preset area can be preset areas that have a specified adjacency relationship with the preset area. The second evaluation result is determined by a weighted sum based on a second weight for each difference. The second weight can refer to the weight corresponding to the difference.

[0088] The second weight can be related to the rate of change of air quality monitoring data between two adjacent preset areas. For example, the greater the rate of change, the greater the second weight. The rate of change can be the ratio of the change in air quality monitoring data of an adjacent preset area relative to the corresponding preset area to the air quality monitoring data of the preset area. For example, if the dust concentration in an adjacent preset area is 'a' and the dust concentration in the preset area is 'b', then the rate of change is (ab) / b. By assigning a higher second weight to the difference between two adjacent preset areas with a higher rate of change, the second evaluation result can better reflect the purification differences between adjacent preset areas.

[0089] Specifying an adjacency relationship refers to the adjacency between any preset area and at least one other preset area. The specified adjacency relationship is related to the combined shape of all preset areas. For example, when all preset areas are arranged in a "line" shape, specifying an adjacency relationship means that a preset area directly adjacent to a specified side of the preset area, such as its right side, is considered an adjacency area. As another example, when all preset areas are arranged in a "grid" shape, specifying an adjacency relationship means that a preset area directly adjacent to a specified side of the preset area is considered an adjacency area. The specified side can be different for each preset area.

[0090] By assessing the differences in overall indoor air quality, the differences between adjacent preset areas can be taken into account, which helps to reduce the purification differences between adjacent preset areas and improve the overall uniformity of indoor purification.

[0091] Step 420: Based on the air quality assessment results, determine a first negative index, which is related to the air quality of at least one preset area.

[0092] The First Negative Index is a metric used to characterize the adverse health effects of air quality on workers. A higher First Negative Index indicates greater health risks and a higher likelihood of negative impacts. In some embodiments, the First Negative Index is related to the air quality of at least one preset area. For example, the worse the air quality in at least one preset area, the higher the First Negative Index; conversely, the better the air quality in at least one preset area, the lower the First Negative Index.

[0093] The first negative index can be determined in several ways. For example, the overall controller can directly determine the first negative index based on the first assessment result and / or the second assessment result.

[0094] In some embodiments, the overall controller may determine a first negative index by weighted summation based on a first evaluation result and a second evaluation result.

[0095] The weights for the weighted summation can be the third weight of the first evaluation result and the fourth weight of the second evaluation result. The third and fourth weights are obtained by system default or manual preset.

[0096] The first negative index is determined by combining the results of the first and second assessments. This allows for a comprehensive consideration of the air quality in each area and the differences in air quality between adjacent areas, improving the accuracy of the determined first negative index. This facilitates subsequent adjustments to the operating parameters of the laminar flow hood, thereby enhancing the rationality and balance of the indoor purification effect.

[0097] Step 430: In response to the first negative index meeting a preset condition, a second negative index is determined based on the detected image. The second negative index is related to the working conditions of at least one worker.

[0098] The preset conditions are the criteria used to determine whether a second negative index needs to be calculated. For example, preset conditions could include the first negative index being greater than an index threshold. The index threshold can be a system default value or a manually preset value.

[0099] In some embodiments, the exponential threshold can be negatively correlated with the buildup characteristics. The more buildup the buildup characteristics indicate, the smaller the exponential threshold.

[0100] For more information on the characteristics of scale buildup, please refer to [link / reference]. Figure 3 Related descriptions.

[0101] In some embodiments, the master controller can determine the corresponding exponential threshold by weighted summation of the fouling characteristics of multiple filters.

[0102] In some embodiments, the main controller can preset the correspondence between the fouling characteristics of multiple filters and the index threshold, and determine the index threshold by looking up a table.

[0103] The more dirt buildup, the worse the filter's purification capacity, indicating that the indoor air quality (e.g., in a factory or workshop) has historically been poor or that a lot of dust has been generated, and the corresponding working environment is also more dangerous. Therefore, determining the index threshold corresponding to the first negative index through dirt buildup characteristics is beneficial for timely updating the laminar flow hood's operating parameters, thereby improving the purification effect on the indoor environment.

[0104] The second negative index is data used to reflect the impact of staff performance on the effectiveness of purification. In some embodiments, the second negative index is related to the performance of at least one staff member. For example, the more staff members who are on the move, the larger the second negative index.

[0105] Work status is data used to reflect the movement of indoor staff.

[0106] In some embodiments, in response to a first negative index meeting a preset condition, the central controller can determine the number of workers currently in a moving state based on multiple sequentially detected images within the current time period, and determine a corresponding second negative index based on this number. Different numbers correspond to different second negative indices. The larger the number of workers in a moving state, the larger the second negative index. The current time period refers to the time period from a certain point in the past to the current point.

[0107] For more information on image detection, please refer to [link / reference]. Figure 3 Related descriptions.

[0108] In some embodiments, the central controller may determine the motion characteristics of at least one worker based on the detected image; and determine a second negative index based on the detected image and the motion characteristics using an index determination model, wherein the index determination model is a machine learning model.

[0109] Motion characteristics are information related to the movement of staff. For example, motion characteristics may include the direction, distance, and speed of movement. It should be noted that motion characteristics can roughly reflect the impact of staff movement on the purification effect, and may not involve the staff's specific posture.

[0110] In some embodiments, the central controller can identify the motion characteristics of workers (e.g., one or more workers) based on multiple detected images in chronological order within the current time period using a moving object detection algorithm. For example, the moving object detection algorithm may include intra-frame differencing algorithms, background differencing algorithms, optical flow algorithms, or combinations thereof.

[0111] In some embodiments, the main controller may determine motion features based on a first detection image at a first time point and a second detection image at a second time point.

[0112] The first detection image refers to the detection image captured at the first time point.

[0113] The second detection image refers to the detection image captured at the second time point.

[0114] The first time point and the second time point refer to two different shooting moments. For example, there can be a preset time interval between the second time point and the first time point. The preset time interval can be a system default value or a manually set value. The first time point can be a time point that precedes the second time point.

[0115] The first detection image and the second detection image can also be two adjacent frames that are consecutive in time.

[0116] In some embodiments, the main controller can perform differential operations on the first detection image and the second detection image, subtract the corresponding pixels of the different images to obtain a differential image, and determine motion features based on the differential image.

[0117] In some embodiments, the main controller can determine the target worker and a first reference point based on the first detection image. The first reference point can be a human body position that is relatively easy to capture, such as the head or shoulders. In the second detection image, a second reference point of the target worker can be determined. The second reference point is at the same position as the first reference point. The movement direction, movement distance, and movement speed of the target worker can be calculated based on the first reference point and the second reference point.

[0118] In some embodiments, the main controller can determine the direction from the first reference point to the second reference point as the movement direction of the target worker.

[0119] In some embodiments, the central controller can determine the movement distance of the target worker based on the distance from the first reference point to the second reference point. For example, the central controller can determine the movement distance of the target worker by multiplying the distance from the first reference point to the second reference point by a conversion factor. The conversion factor is an empirically preset factor used to convert pixel distances within the image into actual median distances.

[0120] In some embodiments, the conversion factor is related to the installation location of the image acquisition device and the indoor spatial layout.

[0121] In some embodiments, the central controller may determine the movement speed of the target worker based on the quotient of the movement distance and the time interval between the first time point and the second time point.

[0122] The target worker can refer to any worker who is in a moving state in the first detection image.

[0123] Because the images acquired by the imaging device are continuous, if the staff in the room do not move, the changes between the detected images are very slight; if the staff move, there will be obvious changes between the detected images.

[0124] In some embodiments, the time points may also include a third time point, a fourth time point, etc., where the third time point and the fourth time point are adjacent time points after the second time point. The main controller can determine the motion characteristics of the staff based on the detection images corresponding to the first time point, the second time point, the third time point, the fourth time point, etc.

[0125] In some embodiments of this specification, determining the motion characteristics of at least one worker by calculating from at least two frames of images at at least two time points can improve the accuracy of the determined motion characteristics, which is beneficial to improving the accuracy of the subsequently determined second negative index. Calculating from at least two frames of images at at least two time points can reduce computational complexity, enabling the system to adapt to various dynamic environments and improving its robustness.

[0126] An index determination model is a model used to determine the second negative index. An index determination model can be a neural network model or another machine learning model.

[0127] In some embodiments, the index determination model includes an image feature extraction layer and a negative index prediction layer. The overall controller can determine an image feature vector based on at least one detected image using the image feature extraction layer; and determine a second negative index based on the image feature vector, motion features of at least one worker, operational data, and worker data using the negative index prediction layer.

[0128] The movement characteristics of staff can reflect the impact of staff walking (large movements) on the purification effect, while the image feature vector corresponding to the detected image can reflect the impact of staff operating posture (small movements) on the purification effect, such as whether the staff's operation is in violation of regulations, etc. Considering both of these factors at the same time can improve the accuracy of model prediction.

[0129] An image feature extraction layer can be used to extract feature vectors from a detection image. In some embodiments, the image feature extraction layer can be a machine learning model such as a convolutional neural network model. The input to the image feature extraction layer may include at least one detection image, and the output may include an image feature vector.

[0130] Image feature vectors can refer to data that reflects the characteristics of a detected image. For example, image feature vectors may include data reflecting the operational posture of a worker in the detected image.

[0131] The negative index prediction layer can be used to obtain a second negative index. In some embodiments, the image feature extraction layer can be a machine learning model such as a neural network model. The input to the negative index prediction layer may include an image feature vector, motion features of at least one worker, operational data, and worker data, and the output may include a second negative index.

[0132] Operational data refers to the types of operations performed by staff within the premises where the purification system is installed. For example, operational data may include key procedures and working hours for a particular process. Staff data refers to data related to the staff themselves; for example, staff data may include worker qualifications, skill level, length of service, and job responsibilities.

[0133] In some embodiments, the exponential determination model can be obtained through joint training.

[0134] In some embodiments, an exemplary joint training process includes: inputting a first training sample into an initial image feature extraction layer to obtain an initial image feature vector output by the initial image feature extraction layer; inputting the output of the initial image feature extraction layer, motion features of at least one worker, operation data, and worker data into an initial negative index prediction layer to obtain an initial second negative index; constructing a loss function based on the output of the initial negative index prediction layer and a first label, while simultaneously updating the parameters of the initial image feature extraction layer and the initial negative index prediction layer, until a preset condition is met, and training is complete. The preset condition may be that the loss function is less than a threshold, convergence, or the training period reaches a threshold.

[0135] The first training sample for joint training may include multiple sets of samples, each set of samples may include at least one sample detection image, at least one sample worker's motion features, sample operation data, and sample worker data. The first label may include a second negative index corresponding to the first training sample.

[0136] The first training sample can be obtained based on historical cleanup data, and the first label can be obtained based on the central controller or manual annotation. For example, the central controller can pre-store multiple target detection images in the database. These target detection images can be images of staff violating regulations. The controller obtains the maximum similarity between at least one sample detection image and the target detection image. Based on the motion characteristics of at least one sample staff member, it calculates the difference between the motion speed and a speed threshold, and obtains the corresponding negative degree through a pre-defined correspondence. The maximum similarity and the negative degree are then summed, and the sum is used as the first label. Here, the speed threshold can refer to a threshold condition for the staff member's motion speed, which can be a system default or a manually set value. The negative degree can refer to the degree of negative impact of the motion on the cleanup effect.

[0137] By setting the index determination model as an image feature extraction layer and a negative index prediction layer, and processing the corresponding data through different layers, the data processing efficiency and prediction accuracy can be further improved.

[0138] The movement of staff can affect the purification effect. By using an index prediction model to analyze the detection images and motion characteristics, accurate data analysis can be performed to obtain a second negative index, which improves the efficiency and accuracy of data processing. This is beneficial for further improving the accuracy of subsequent updated operating parameters, reducing the impact of staff movement on the purification effect, and thus ensuring the air purification effect.

[0139] Step 440: Determine the updated operating parameters based on the first negative index and the second negative index.

[0140] Updated operating parameters can be determined in several ways. In some embodiments, the main controller can obtain the closest or identical historical first negative index and historical second negative index from historical purification data based on the first negative index and the second negative index, and determine the historical updated operating parameters corresponding to the historical first negative index and historical second negative index as the updated operating parameters.

[0141] In some embodiments, the main controller may determine the updated operating parameters based on a first negative index and a second negative index, through a preset correspondence.

[0142] In some embodiments, the main controller can preset the correspondence between the first negative index, the second negative index, and the adjustment amount, and determine the updated operating parameters based on the adjustment amount and the current operating parameters. The current operating parameters refer to the operating parameters of the purification system at the current moment.

[0143] In some embodiments, the adjustment amounts of the multiple laminar flow hood parameters may be the same or different.

[0144] By using the first and second negative indices to determine and update operating parameters, the air purification effect can be guaranteed without affecting the work efficiency of staff.

[0145] By determining the first and second negative indices through air quality monitoring data and images, updated operating parameters can be determined. This allows for analysis of factors influencing air purification effectiveness from multiple perspectives, such as dust levels and staff working conditions, thereby improving the accuracy of the determined updated operating parameters and ensuring purification results.

[0146] Figure 5 This is an exemplary schematic diagram illustrating the determination of updated operating parameters based on a preset algorithm according to some embodiments of this specification.

[0147] In some embodiments, the main controller may determine updated operating parameters based on a preset algorithm, wherein the preset algorithm includes: generating at least one candidate parameter scheme 521 based on preset operating parameters 510; determining estimated detection data 540 for at least one preset area through an evaluation model 530 based on at least one of the candidate parameter scheme 521, a regional image 522 of at least one preset area, an air quality assessment result 523, and motion characteristics of at least one worker 524, wherein the evaluation model is a machine learning model; determining a target parameter scheme 550 that meets preset conditions based on at least one candidate parameter scheme 521 and the estimated detection data 540 of at least one preset area; and determining updated operating parameters 560 based on the target parameter scheme.

[0148] For more information on preset operating parameters, please refer to [link / reference]. Figure 3 The relevant description. For more information on air quality assessment results, please refer to... Figure 4 Related descriptions.

[0149] A candidate parameter scheme refers to one or more operating parameters that are to be determined as the target parameter scheme. For example, a candidate parameter scheme may include the operating parameters of the laminar flow hoods at all preset locations.

[0150] Candidate parameter schemes can be determined in various ways. In some embodiments, the main controller can directly determine the preset operating parameters of each laminar flow hood as candidate parameter schemes.

[0151] In some embodiments, the main controller may generate at least one candidate parameter scheme based on preset operating parameters and the movement direction of at least one worker.

[0152] The direction of movement refers to the direction in which a worker moves within a workplace. In some embodiments, the direction of movement may refer to moving from one preset area to another, etc. In some embodiments, the direction of movement may also include the worker's current position relative to their initial position.

[0153] In some embodiments, the main controller can improve the preset operating parameters of the laminar flow hoods during the movement of workers based on their movement direction, and determine candidate parameter schemes based on the improved preset operating parameters. For example, there are four laminar flow hoods configured indoors, corresponding to four preset points, used for five preset areas. Assuming that workers are moving between preset area 1 and preset area 2, the purification of preset areas 1 and 2 is mainly handled by laminar flow hood 100-1. The main controller can improve the operating parameters of the corresponding laminar flow hood 100-1 to improve the purification effect of preset areas 1 and 2. It should be noted that, for ease of distinction, one or more laminar flow hoods and preset areas are exemplified by 1, 2, etc.

[0154] By obtaining the movement direction of the staff, the candidate parameter schemes can be made more targeted, which is conducive to improving the accuracy of the target parameter schemes determined in the future.

[0155] A region image refers to an image of a preset area. For example, a region image may include environmental information within the preset area, the location information of the preset area indoors, etc. In some embodiments, when there are no staff members in the preset area, the main controller can acquire a region image of at least one preset area through an image acquisition device.

[0156] Predicted monitoring data refers to the air quality monitoring data of the predicted candidate parameter operation scheme.

[0157] The evaluation model can be used to predict air quality monitoring data after the purification system operates based on candidate parameter schemes. In some embodiments, the evaluation model can be a machine learning model such as a neural network model.

[0158] In some embodiments, the evaluation model can be trained using a large number of second training samples with second labels. In some embodiments, training can be performed based on the second training samples using various methods. For example, training can be performed using gradient descent.

[0159] In some embodiments, each training sample in the second training sample may include a regional image of at least one sample preset area, at least one sample parameter scheme, sample air quality assessment results, and at least one sample worker motion characteristics. The second training sample can be obtained from historical data.

[0160] In some embodiments, the second label is the actual detection data of at least one preset area corresponding to the second training sample. The second label can be determined by the central controller or manually. For example, it can be determined as the second label based on air quality detection data adjusted according to sample parameter schemes during actual historical purification processes.

[0161] In some embodiments, the evaluation model may include a spatial feature extraction layer and a detection data prediction layer. The main controller may determine spatial feature vectors based on regional images of at least one preset area through the spatial feature extraction layer; and determine estimated detection data for at least one preset area through the detection data prediction layer based on at least one candidate parameter scheme, the spatial feature vectors, air quality assessment results, and the motion characteristics of at least one worker.

[0162] The spatial feature extraction layer can be used to obtain feature vectors of a region image within a preset area. In some embodiments, the spatial feature extraction layer can be a convolutional neural network model, etc.

[0163] In some embodiments, the input to the spatial feature extraction layer may include a region image of at least one preset region, and the output may include a spatial feature vector. Further details regarding the region image of at least one preset region can be found in [link to relevant documentation]. Figure 5 The above description.

[0164] Spatial feature vectors can refer to data that reflects the characteristics of a region's image. For example, spatial feature vectors may include data reflecting the environment within a predetermined region of the image.

[0165] The detection data prediction layer can be used to predict estimated detection data for at least one preset region. In some embodiments, the detection data prediction layer can be a deep neural network model, etc.

[0166] In some embodiments, the input to the detection data prediction layer may include at least one candidate parameter scheme, a spatial feature vector, air quality assessment results, and at least one worker's motion characteristics; the output may include estimated detection data for at least one preset area. Further explanation of the at least one candidate parameter scheme and spatial feature vector can be found in [link to relevant documentation]. Figure 5 The above description is relevant. Further details regarding air quality assessment results and the movement characteristics of at least one worker can be found in [link to relevant documentation]. Figure 4 Related descriptions.

[0167] In some embodiments, the evaluation model can also be obtained through joint training using a large number of second training samples with second labels. The joint training method for the evaluation model is similar to that for the exponential determination model; see [link to relevant documentation]. Figure 4 The relevant description in the document.

[0168] By dividing the evaluation model into a spatial feature extraction layer and a detection data prediction layer, with each layer being independent of the others, the complex problem is decomposed into several smaller, easier-to-handle problems, thereby improving computational efficiency and the accuracy of the predicted detection data.

[0169] The target parameter scheme refers to the scheme that includes the final operating parameters used for each laminar flow hood.

[0170] In some embodiments, the main controller may determine a first negative index based on the estimated detection data of at least one preset area, wherein the preset condition is that the estimated first negative index is less than an index threshold.

[0171] For more information on exponential thresholds, see [link to relevant documentation]. Figure 4 Related descriptions.

[0172] The first negative index is the first negative index of the predicted detection data.

[0173] In some embodiments, the central controller can be based on Figure 4 The estimated first negative index is determined in a similar way to the method used to determine the first negative index in China.

[0174] In some embodiments, the main controller may select the corresponding predicted detection data that meets the preset conditions from the candidate parameter schemes and determine it as the target parameter scheme.

[0175] It should be noted that when multiple candidate parameter schemes meet the preset conditions, the overall controller can select the candidate parameter scheme with the smallest estimated first negative index and determine it as the target parameter scheme.

[0176] By determining whether the estimated detection data meets the preset conditions, a target parameter scheme that is more in line with the actual situation can be selected, thereby improving the air purification effect.

[0177] In some embodiments, the main controller determines the operating parameters included in the target parameter scheme as the updated operating parameters for different laminar flow hoods based on the target parameter scheme.

[0178] The preset algorithm comprehensively considers factors such as the regional image of the preset area, the air quality assessment results, and the movement characteristics of at least one worker, making the determined updated operating parameters more accurate, which can quickly reach the purification requirements and further improve the purification efficiency.

[0179] This specification provides a purification device in some embodiments, the device including at least one main controller and at least one memory; the at least one memory is used to store computer instructions; the at least one main controller is used to execute at least some of the computer instructions to: control an air quality detection device to acquire air quality detection data of at least one preset area and send it to the memory for storage, the at least one preset area corresponding to at least one preset location; control an image acquisition device to acquire detection images of at least one worker and send them to the memory for storage; based on the air quality detection data and the detection images, determine the updated operating parameters of the laminar flow hood at the at least one preset location, the updated operating parameters including fan power; based on the updated operating parameters, generate an update control command and send the update control command to the laminar flow hood at the at least one preset location and the memory.

[0180] Some embodiments of this specification provide a computer-readable storage medium storing computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the following: controlling an air quality detection device to acquire air quality detection data for at least one preset area and sending it to a memory for storage, wherein the at least one preset area corresponds to at least one preset location; controlling an image acquisition device to acquire detection images of at least one worker and sending them to the memory for storage; determining updated operating parameters for the laminar flow hood at the at least one preset location based on the air quality detection data and the detection images, wherein the updated operating parameters include fan power; generating an update control command based on the updated operating parameters and sending the update control command to the laminar flow hood at the at least one preset location and the memory.

[0181] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0182] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A purification system, characterized in that, The purification system includes a laminar flow hood, an air quality detection device, an image acquisition device, a memory, and a main controller. The laminar flow hood and / or the air quality detection device are deployed at at least one preset location. The main controller is configured as follows: The air quality detection device is controlled to acquire air quality detection data of at least one preset area and send it to the memory for storage, wherein the at least one preset area corresponds to the at least one preset point. The image acquisition device is controlled to acquire detection images of at least one worker and send them to the memory for storage; Based on the air quality detection data, an indoor air quality assessment result is determined; the air quality assessment result includes a first assessment result and a second assessment result; the first assessment result is an assessment of the air quality of the at least one preset area; the second assessment result is an assessment of the overall indoor air quality differences. Based on the first assessment results and the second assessment results, a first negative index is determined; the first negative index represents data on how air quality is detrimental to the health of workers and causes adverse effects. In response to the first negative index being greater than an index threshold, a second negative index is determined based on the detected image, the second negative index being related to the working condition of the at least one worker; Based on the first negative index and the second negative index, the updated operating parameters of the laminar flow hood at the at least one preset point are determined, and the updated operating parameters include the fan power. Based on the updated operating parameters, an update control command is generated and sent to the laminar flow hood at the at least one preset point and the memory. The laminar flow hood includes an exhaust fan, a return air panel, at least one filter, an air inlet panel, an ultraviolet disinfection lamp, a flow equalization membrane, a curtain, a touch panel, a microprocessor, at least one dirt detection device, and a PVC board. The at least one filter includes a first filter and a second filter. The exhaust fan is used to draw in air from outside the at least one preset area and send it to the second filter for filtration; The return air panel is used to recycle polluted air from at least one preset area; The first filter is used to filter the polluted air and obtain first filtered air; The second filter is used to filter the first filtered air and / or air outside the at least one preset area, to obtain the second filtered air and send it into the at least one preset area; The air intake panel is used to draw in air from outside the at least one preset area; The ultraviolet disinfection lamp is used for disinfection of the second filtered air; The uniform flow membrane is used to uniformly deliver the second filtered air into the at least one preset area; The curtain is used to purify the second filtered air within the at least one preset area; The touch panel is used by at least one worker to adjust the laminar flow hood.

2. The purification system as described in claim 1, characterized in that, The microprocessor is configured to: The laminar flow shroud is controlled to operate with preset operating parameters; The system controls at least one dirt detection device to acquire dirt accumulation characteristics of at least one filter at a preset frequency and uploads the dirt accumulation characteristics to the main controller; the dirt accumulation characteristics include the area and size of dirt accumulation. In response to receiving the update control command sent by the main controller, the laminar flow hood is controlled to operate with the updated operating parameters; The PVC board is used to increase the cleanliness and purification effect within the at least one preset area.

3. The purification system as described in claim 1, characterized in that, The main controller is also configured to: Based on the detected image, the motion characteristics of the at least one worker are determined; Based on the detected image and the motion features, the second negative index is determined by an index determination model, wherein the index determination model is a machine learning model.

4. The purification system as described in claim 1, characterized in that, The main controller is also configured to: The updated operating parameters are determined based on a preset algorithm, wherein the preset algorithm includes: Based on preset operating parameters, generate at least one candidate parameter scheme; Based on at least one of the at least one candidate parameter scheme, the regional image of the at least one preset area, the air quality assessment result, and the motion characteristics of the at least one worker, the estimated detection data of the at least one preset area is determined by an evaluation model, wherein the evaluation model is a machine learning model. Based on the at least one candidate parameter scheme and the estimated detection data, a target parameter scheme that meets the preset conditions is determined. Based on the target parameter scheme, the updated operating parameters are determined.

5. A purification device, characterized in that, The device includes at least one main controller and at least one memory; The at least one memory is used to store computer instructions; The at least one central controller is configured to execute at least a portion of the instructions in the computer instructions to achieve: The air quality detection device is controlled to acquire air quality detection data of at least one preset area and send it to a memory for storage, wherein the at least one preset area corresponds to at least one preset point. The image acquisition device is controlled to acquire detection images of at least one worker and send them to the memory for storage; Based on the air quality detection data, an indoor air quality assessment result is determined; the air quality assessment result includes a first assessment result and a second assessment result; the first assessment result is an assessment of the air quality of the at least one preset area; the second assessment result is an assessment of the overall indoor air quality differences. Based on the first assessment results and the second assessment results, a first negative index is determined; the first negative index represents data on how air quality is detrimental to the health of workers and causes adverse effects. In response to the first negative index being greater than an index threshold, a second negative index is determined based on the detected image, the second negative index being related to the working condition of the at least one worker; Based on the first negative index and the second negative index, the updated operating parameters of the laminar flow hood at the at least one preset point are determined. The updated operating parameters include the fan power. The laminar flow hood includes an exhaust fan, a return air panel, at least one filter, an air inlet panel, an ultraviolet disinfection lamp, a flow equalization membrane, a curtain, a touch panel, a microprocessor, at least one dirt detection device, and a PVC board. Based on the updated operating parameters, an update control command is generated and sent to the laminar flow hood at the at least one preset point and the memory.

6. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes them: The air quality detection device is controlled to acquire air quality detection data of at least one preset area and send it to a memory for storage, wherein the at least one preset area corresponds to at least one preset point. The image acquisition device is controlled to acquire detection images of at least one worker and send them to the memory for storage; Based on the air quality detection data, an indoor air quality assessment result is determined; the air quality assessment result includes a first assessment result and a second assessment result; the first assessment result is an assessment of the air quality of the at least one preset area; the second assessment result is an assessment of the overall indoor air quality differences. Based on the first assessment results and the second assessment results, a first negative index is determined; the first negative index represents data on how air quality is detrimental to the health of workers and causes adverse effects. In response to the first negative index being greater than an index threshold, a second negative index is determined based on the detected image, the second negative index being related to the working condition of the at least one worker; Based on the first negative index and the second negative index, the updated operating parameters of the laminar flow hood at the at least one preset point are determined. The updated operating parameters include the fan power. The laminar flow hood includes an exhaust fan, a return air panel, at least one filter, an air inlet panel, an ultraviolet disinfection lamp, a flow equalization membrane, a curtain, a touch panel, a microprocessor, at least one dirt detection device, and a PVC board. Based on the updated operating parameters, an update control command is generated and sent to the laminar flow hood at the at least one preset point and the memory.

Images