A negative pressure weighing hood and control system

Abstract

The embodiment of the present specification provides a negative pressure weighing cover and a control system. The control system comprises a negative pressure weighing cover, a first air quality detection device group, a second air quality detection device group and a controller. The controller is used for controlling the first air quality detection device group to obtain first air quality detection data; controlling the second air quality detection device group to obtain second air quality detection data; determining a warning type in response to at least one of the first air quality detection data and the second air quality detection data being abnormal; adjusting the operation parameter of the negative pressure weighing cover based on the warning type; and sending the adjusted operation parameter to the processor of the negative pressure weighing cover to control the negative pressure weighing cover to work based on the adjusted operation parameter. The negative pressure weighing cover comprises at least one differential pressure sensor, a flow equalization film, a primary filter, a medium efficiency filter and a high efficiency filter.

Description

Technical Field

[0001] This manual relates to the field of pharmaceutical production equipment, and in particular to a negative pressure weighing hood and control system. Background Technology

[0002] A negative pressure weighing hood (or simply negative pressure weighing hood) is a localized purification device specifically designed for use in pharmaceutical, microbiological research, and scientific experiments. It provides a unidirectional airflow, with some clean air circulating within the work area and some being exhausted to nearby areas, creating negative pressure in the work area to purify the air within the fume hood and laboratory. Existing negative pressure weighing hood systems require professional personnel to adjust fan power and gas discharge rates during installation and use to meet user needs. If problems arise during use, they may not be resolved promptly, impacting work efficiency and effectiveness.

[0003] To address the aforementioned issues, CN214121400U provides a negative pressure weighing hood that effectively purifies and filters the air inside, thus minimizing the impact of exhaust gases on the external environment and ensuring the cleanliness of the air within the hood. However, it does not address how to monitor equipment operation in real time or how to automatically adjust operating parameters and provide timely warnings to personnel to ensure the purification effect of the negative pressure weighing hood.

[0004] Therefore, it is hoped that a negative pressure weighing hood and control system can be proposed to monitor air quality in a timely manner, accurately judge abnormal situations, and effectively adjust the operating parameters of the negative pressure weighing hood when abnormalities occur, so as to ensure that the purification work of the negative pressure weighing hood is carried out normally. Summary of the Invention

[0005] This specification provides one or more embodiments of a negative pressure weighing hood control system, comprising: a negative pressure weighing hood, a first air quality detection device group, a second air quality detection device group, and a controller. The controller is configured to: control the first air quality detection device group to acquire first air quality detection data, wherein the first air quality detection device group is deployed at at least one preset point inside the space to be purified; control the second air quality detection device group to acquire second air quality detection data, wherein the second air quality detection device group is deployed at at least one preset point around the space to be purified; respond to the first air quality detection data, wherein at least one of the second air quality detection data is abnormal, and determine a warning type; adjust the operating parameters of the negative pressure weighing hood based on the warning type, wherein the operating parameters include at least one of fan power and indoor gas exhaust volume; and send the adjusted operating parameters to the processor of the negative pressure weighing hood, wherein the processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters.

[0006] This specification provides one or more embodiments of a purification device, the device including at least one controller and at least one memory; the at least one memory is used to store computer instructions; the at least one controller is used to execute at least a portion of the computer instructions to: control a first air quality detection device group to acquire first air quality detection data; control a second air quality detection device group to acquire second air quality detection data; in response to an anomaly in at least one of the first air quality detection data and the second air quality detection data, determine a warning type; adjust the operating parameters of the negative pressure weighing hood based on the warning type; send the adjusted operating parameters to the processor of the negative pressure weighing hood, and the processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters.

[0007] This specification provides one or more embodiments of a computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the following: controlling a first air quality detection device group to acquire first air quality detection data; controlling a second air quality detection device group to acquire second air quality detection data; determining a warning type in response to an anomaly occurring in at least one of the first air quality detection data and the second air quality detection data; adjusting the operating parameters of the negative pressure weighing hood based on the warning type; and sending the adjusted operating parameters to the processor of the negative pressure weighing hood, wherein the processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters. Attached Figure Description

[0008] 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:

[0009] Figure 1 This is a schematic diagram of the negative pressure weighing hood control system according to some embodiments of this specification;

[0010] Figure 2 This is a structural schematic diagram of the negative pressure weighing hood shown in some embodiments of this specification;

[0011] Figure 3 This is an exemplary flowchart of a negative pressure weighing hood control method according to some embodiments of this specification;

[0012] Figure 4 This is a schematic diagram illustrating the operation of the negative pressure weighing hood based on adjusted operating parameters, according to other embodiments of this specification;

[0013] Figure 5This is a schematic diagram illustrating the adjustment of the operating parameters of the negative pressure weighing hood according to some embodiments of this specification. Detailed Implementation

[0014] 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.

[0015] 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.

[0016] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[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] Existing negative pressure weighing hoods require manual adjustment of fan power and gas discharge volume, which often cannot be adjusted in a timely manner based on actual usage or equipment malfunctions, resulting in low efficiency and affecting purification effectiveness. The CN214121400U provides a negative pressure weighing hood that can effectively filter exhaust gas and further filter recirculated gas, reducing cross-contamination and secondary pollution. However, it does not address how to monitor equipment operation in real time and adjust operating parameters promptly to ensure the purification effect of the negative pressure weighing hood.

[0019] Therefore, it is desirable to provide a negative pressure weighing hood and control system that can accurately and efficiently adjust parameters according to actual usage conditions, ensuring the stable and normal operation of the purification work and avoiding adverse effects on the health of staff from contaminated air leaks.

[0020] Figure 1 This is a schematic diagram of the negative pressure weighing hood control system according to some embodiments of this specification.

[0021] like Figure 1 As shown, the negative pressure weighing hood control system 100 may include a controller 110, a first air quality detection device group 120, a second air quality detection device group 130, and a negative pressure weighing hood 200.

[0022] Controller 110 refers to a device for processing information and / or data related to the negative pressure weighing hood control system 100. Controller 110 can execute program instructions based on this data, information, and / or processing results to perform one or more functions described in this specification. In some embodiments, controller 110 can be communicatively connected to a first air quality detection device group 120, a second air quality detection device group 130, and the negative pressure weighing hood 200.

[0023] In some embodiments, the controller 110 can be used to control the first air quality detection device group 120 to acquire first air quality detection data; control the second air quality detection device group 130 to acquire second air quality detection data; determine a warning type in response to an anomaly occurring in at least one of the first air quality detection data and the second air quality detection data; adjust the operating parameters of the negative pressure weighing hood 200 based on the warning type; and send the adjusted operating parameters to the processor 201 of the negative pressure weighing hood 200. More information about the controller 110 can be found in [link to relevant documentation]. Figures 3 to 5 Related descriptions.

[0024] In some embodiments, the controller 110 can perform more complex data calculations, information processing, etc., than the processor 201 of the negative pressure weighing hood 200.

[0025] The first air quality detection device group 120 refers to equipment or components used to acquire first air quality detection data. In some embodiments, the first air quality detection device group may include one or more first air quality detection devices. The first air quality detection device may include at least one of a dust particle counter, a dust sensor, etc. More information about first air quality detection data can be found at [link to relevant documentation]. Figure 3 And its related descriptions.

[0026] In some embodiments, the first air quality detection device group can be deployed at at least one preset point inside the space to be purified. The space to be purified refers to the internal area of ​​the negative pressure weighing hood 200 where air purification is required. The preset point refers to the pre-set installation location of the air quality detection device. In some embodiments, the preset point inside the space to be purified can be set at any location inside the space, for example, the preset point inside the space to be purified can be set at the middle / slightly above the middle / above the top inside the negative pressure weighing hood 200.

[0027] The second air quality detection device group 130 refers to equipment or components used to acquire second air quality detection data. In some embodiments, the second air quality detection device group may include one or more second air quality detection devices. The second air quality detection devices may include at least one of a dust particle counter, a dust sensor, etc. More information about second air quality detection data can be found at [link to relevant documentation]. Figure 3 And its related descriptions.

[0028] In some embodiments, the second air quality detection device group is deployed at at least one preset point around the space to be purified. In some embodiments, the preset points around the space to be purified can be set at any location around the space to be purified. For example, the preset points around the space to be purified can be set on the left / right side of the periphery of the negative pressure weighing hood 200.

[0029] The negative pressure weighing hood 200 refers to a local purification device used to provide a unidirectional airflow environment and filter air. For more information about the negative pressure weighing hood 200, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0030] When the negative pressure weighing hood 200 is in use, part of the airflow can circulate in the space to be purified, while the other part of the airflow is filtered by a high-efficiency filter and discharged from the negative pressure weighing hood 200. This creates a negative pressure inside the negative pressure weighing hood relative to the outside, thereby ensuring that dust and other particles in this area do not spread to the outside and protecting the external environment.

[0031] It should be noted that the above description of the negative pressure weighing hood control system 100 and its modules is for ease of description only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principle of this system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from this principle.

[0032] Figure 2 This is a structural schematic diagram of a negative pressure weighing hood according to some embodiments of this specification.

[0033] like Figure 2As shown, the negative pressure weighing hood 200 may include at least one differential pressure sensor 210, a flow equalization membrane 220, a primary filter 230, a medium-efficiency filter 240, a high-efficiency filter 250, and a processor 201.

[0034] Differential pressure sensor 210 refers to a device used to acquire pressure-related data.

[0035] In some embodiments, at least one differential pressure sensor 210 is configured to correspond one-to-one with a filtration device, and each differential pressure sensor is used to measure the pressure data of the corresponding filtration device. The filtration device can refer to the equipment in the negative pressure weighing hood that requires pressure detection, such as a flow equalization membrane, a pre-filter, a medium-efficiency filter, a high-efficiency filter, etc. More information on pressure data can be found in [link to relevant documentation]. Figure 4 And its related descriptions.

[0036] The flow equalization membrane 220 refers to a special membrane material that evenly delivers air into the space to be purified, such as ultrafiltration membranes and nanomembranes.

[0037] A pre-filter 230 refers to a filter that pre-filters polluted air. Examples include activated carbon filters. Pre-filters can remove large particulate dust particles from polluted air. Polluted air can refer to air with poor air quality, such as air with a cleanliness level below a preset air quality threshold. The preset air quality threshold can be set based on experience.

[0038] A medium-efficiency filter (240) refers to a filter that performs a secondary filtration on pre-filtered air. Examples include water vapor filters, special non-woven fabric or glass fiber filters, etc. Medium-efficiency filters can be used as pre-filters for high-efficiency filters to fully protect them.

[0039] HEPA filter 250 refers to a filter that performs final filtration on air that has already undergone secondary filtration. Examples include nanofiber filters.

[0040] Processor 201 refers to a device for processing information and / or data related to the negative pressure weighing hood. In some embodiments, processor 201 may upload data and / or information to controller 110, and may also execute one or more functions described herein in response to operating parameters sent by controller 110.

[0041] In some embodiments, the processor 201 can be used to control the negative pressure weighing hood 200 to operate with preset operating parameters; control at least one differential pressure sensor 210 to acquire at least one pressure data point based on a preset frequency, and upload at least one pressure data point to the controller 110; and, in response to receiving adjusted operating parameters sent by the controller, control the negative pressure weighing hood 200 to operate based on the adjusted operating parameters. More information regarding operating parameters, preset frequency, pressure data, adjusted operating parameters, etc., can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0042] In some embodiments, the negative pressure weighing hood 200 may further include a housing, a flow chamber, a platform, a fan, and a power distribution box (not shown in the figure). The fan may be a centrifugal fan or similar device, used to provide stable and adjustable negative pressure and airflow to ensure the purification effect of the negative pressure weighing hood.

[0043] Figure 3 This is an exemplary flowchart of a negative pressure weighing hood control method according to some embodiments of this specification. In some embodiments, process 300 may be executed by a controller. Figure 3 As shown, process 300 includes the following steps.

[0044] Step 310: Control the first air quality detection device group to acquire the first air quality detection data.

[0045] Air quality monitoring data refers to data obtained after analyzing and testing air. Examples include dust concentration and polluted air. Specifically, air quality monitoring data can refer to the air quality monitoring data inside the space to be purified.

[0046] In some embodiments, the first air quality detection data may consist of at least one first air quality detection sub-data. A first air quality detection sub-data may refer to air quality detection data obtained by a first air quality detection device. Further details regarding the space to be purified and the first air quality detection device group can be found in [link to relevant documentation]. Figure 1 And its related descriptions.

[0047] In some embodiments, the controller can acquire first air quality detection sub-data at corresponding preset points through first air quality detection devices deployed at multiple preset points within the space to be purified, either in real time or at preset time intervals, thereby acquiring first air quality detection data. The time for acquiring the first air quality detection data can be set according to actual needs.

[0048] Step 320: Control the second air quality detection device group to acquire the second air quality detection data.

[0049] The second air quality detection data can refer to the air quality detection data around the space to be purified. In some embodiments, the second air quality detection data may consist of at least one second air quality detection sub-data. A second air quality detection sub-data may refer to the air quality detection data obtained by a second air quality detection device. Further details regarding the second air quality detection device group can be found in [link to relevant documentation]. Figure 1 And its related descriptions.

[0050] In some embodiments, the controller can acquire second air quality detection sub-data at corresponding preset points through second air quality detection devices deployed at multiple preset points around the space to be purified, either in real time or at preset time intervals, thereby acquiring second air quality detection data. The time for acquiring the second air quality detection data can be set according to actual needs.

[0051] Step 330: In response to an anomaly in at least one of the first air quality monitoring data and the second air quality monitoring data, determine the warning type.

[0052] In some embodiments, the controller can determine whether the first air quality detection data and the second air quality detection data are abnormal in various ways. For example, the controller can compare the first air quality detection data and / or the second air quality detection data with a preset air quality threshold. If the first air quality detection data and / or the second air quality detection data exceed the preset air quality threshold, then it is determined that an abnormality has occurred in the first air quality detection data and / or the second air quality detection data.

[0053] Warning type can refer to the type of method used to issue a warning. Warning methods can include light warnings (such as illuminating a red warning light) and sound warnings (such as emitting a warning sound).

[0054] In some embodiments, the warning type may include a first warning type and a second warning type, etc. The first warning type may refer to the warning type corresponding to when the first air quality monitoring data is abnormal. The second warning type may refer to the warning type corresponding to when the first air quality monitoring data is normal and the second air quality monitoring data is abnormal. For more information on the first and second warning types, please refer to [link to relevant documentation]. Figure 5 And its related descriptions. Different warning types can correspond to different warning methods. For example, the first warning type can correspond to a light warning method, the second warning type can correspond to an audible warning method, and so on.

[0055] In some embodiments, the controller can determine the warning type in multiple ways. For example, the controller can determine the warning type using a first preset table. The first preset table records different abnormal situations and their corresponding warning types when the first air quality detection data and / or the second air quality detection data are abnormal. The first preset table can be preset based on historical data.

[0056] In some embodiments, the controller can determine the warning type as a first warning type and adjust the fan power and indoor gas exhaust volume accordingly; or determine the warning type as a second warning type and adjust the indoor gas exhaust volume accordingly. For detailed instructions, please refer to [link to relevant documentation]. Figure 5 .

[0057] Step 340: Adjust the operating parameters of the negative pressure weighing hood based on the warning type.

[0058] Operating parameters refer to the specific parameters of the negative pressure weighing hood during operation. For example, operating parameters may include fan power and indoor gas exhaust volume. Among them, fan power can refer to the operating power of the fan in the negative pressure weighing hood; indoor gas exhaust volume can refer to the volume of polluted air discharged from the space to be purified after being purified by the negative pressure weighing hood per unit time.

[0059] In some embodiments, the controller can adjust the operating parameters of the negative pressure weighing hood in various ways based on the warning type, and determine the adjusted operating parameters. For example, the controller can adjust the operating parameters of the negative pressure weighing hood based on the warning type using a second preset table, etc. The second preset table records different warning types and their corresponding methods for adjusting the operating parameters of the negative pressure weighing hood. The second preset table can be set based on experience. For example, the second preset table can specify that when the warning type is type a, the fan power in the operating parameters is reduced by b%.

[0060] Step 350: Send the adjusted operating parameters to the processor of the negative pressure weighing hood, and the processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters.

[0061] In some embodiments, the controller can generate corresponding control commands based on the adjusted operating parameters and send the control commands to the processor of the negative pressure weighing hood, so that the processor controls the negative pressure weighing hood to work based on the adjusted operating parameters.

[0062] In some embodiments, the processor of the negative pressure weighing hood can control the negative pressure weighing hood to operate based on adjusted operating parameters. For detailed instructions, please refer to [link to relevant documentation]. Figure 4 .

[0063] When abnormal detection data is detected as described in some embodiments of this specification, the warning type is determined, and the operating parameters of the negative pressure weighing hood are adjusted and sent to the processor of the negative pressure weighing hood. The processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters. This allows for timely monitoring of air quality, accurate judgment of abnormal situations, and timely and effective adjustment of the operating parameters of the negative pressure weighing hood when abnormalities occur. This ensures the normal operation of the negative pressure weighing hood's purification function, avoids the impact of dust, reagents, etc. on the health of workers, and protects the safety of workers.

[0064] Figure 4 This is a schematic diagram illustrating the operation of the negative pressure weighing hood based on adjusted operating parameters, according to other embodiments of this specification.

[0065] In some embodiments, the processor can control the negative pressure weighing hood to operate with preset operating parameters; control at least one differential pressure sensor to acquire at least one pressure data 403 based on a preset frequency 406, and upload at least one pressure data 403 to the controller; and control the negative pressure weighing hood to operate based on the adjusted operating parameters sent by the controller in response to receiving the adjusted operating parameters.

[0066] The preset operating parameters can refer to the pre-set operating parameters of the negative pressure weighing hood. For example, preset fan power and preset indoor gas discharge rate. In some embodiments, the negative pressure weighing hood operates with preset operating parameters when it first starts working.

[0067] The preset frequency of 406 refers to the number of times the differential pressure sensor acquires pressure data from each filtration device per unit time. For more information on filtration devices, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0068] In some embodiments, the processor may determine the preset frequency 406 in a variety of ways. For example, the processor may determine the preset frequency 406 by obtaining user input.

[0069] Pressure data 403 can refer to data reflecting the pressure exerted on the filtration equipment. For example, pressure data 403 may include the pressure difference across the filtration equipment, the pressure exerted on the filtration equipment, etc.

[0070] Understandably, pressure data of 403 reflects the resistance experienced by the corresponding filtration equipment (such as a high-efficiency filter). The higher the pressure data, the greater the resistance. Higher resistance indicates more dust on the filtration equipment, requiring cleaning or replacement.

[0071] In some embodiments, the processor can acquire at least one pressure data 403 of each filter device corresponding to the differential pressure sensor in real time or at preset time intervals via at least one differential pressure sensor, and communicate with the controller to upload the at least one pressure data 403 to the controller. The time for acquiring the pressure data 403 can be set according to actual needs. More information on differential pressure sensors acquiring pressure data can be found in [link to relevant documentation]. Figure 2 And its related descriptions.

[0072] In some embodiments, the processor may, in response to receiving adjusted operating parameters sent by the controller, change the preset operating parameters to the adjusted operating parameters to operate the negative pressure weighing hood.

[0073] In some embodiments, the processor may, in response to receiving at least one pressure data 403 sent by the processor, determine whether at least one pressure data is abnormal 404; in response to at least one pressure data 403 being abnormal, issue an early warning 405; in response to at least one pressure data 403 being normal, predict the maintenance time of at least one filter device through a prediction model 430, and send the maintenance time of at least one filter device to the staff, wherein the prediction model 430 is a machine learning model.

[0074] In some embodiments, the processor can determine whether at least one pressure data 403 is abnormal in a variety of ways. For example, the processor can set a preset pressure data range based on experience, compare at least one pressure data with the preset pressure data range, and if a pressure data is not within the preset pressure data range, then the pressure data is determined to be abnormal.

[0075] In some embodiments, the processor may compare at least one pressure data 403 with a standard pressure threshold 402, and determine that at least one pressure data 403 is abnormal in response to at least one pressure data 403 being greater than the standard pressure threshold 402.

[0076] The standard pressure threshold 402 can refer to the highest pressure value at which the negative pressure weighing hood can operate normally, as preset. In some embodiments, different filtration devices have different standard pressure thresholds. In some embodiments, the standard pressure threshold 402 can be preset based on experience.

[0077] In some embodiments, the standard pressure threshold 402 may be related to the current fan power 401.

[0078] The current wind turbine power of 401 can refer to the wind turbine power at the current point in time.

[0079] In some embodiments, the processor can determine the current fan power 401 based on the current operating parameters of the negative pressure weighing hood.

[0080] In some embodiments, the processor may determine that the standard pressure threshold of the filter device i is the product of an adjustment coefficient and a preset standard pressure threshold of the filter device i, wherein the preset standard pressure threshold may refer to the aforementioned standard pressure threshold preset based on experience, and the adjustment coefficient may refer to a parameter used to adjust the preset standard pressure threshold. The adjustment coefficient may be different for different filter devices.

[0081] In some embodiments, the adjustment coefficient can be negatively correlated with the current wind turbine power 401; the larger the current wind turbine power 401, the smaller the adjustment coefficient.

[0082] Understandably, the higher the current fan power (401), the more staff expect to improve the purification effect of the space to be purified. This increases the workload of filtration equipment such as HEPA filters, making them more prone to malfunctions and unsatisfactory purification results. Therefore, the standard pressure threshold (402) can be appropriately lowered to reduce adverse effects.

[0083] The standard pressure threshold described in some embodiments of this specification can be related to the current fan power. When the purification load of the filtration equipment is large, the purification effect standard can be appropriately reduced to reduce the probability of malfunctions of the filtration equipment.

[0084] In some embodiments, the processor can compare at least one pressure data 403 with a standard pressure threshold 402, and if a pressure data exceeds the corresponding standard pressure threshold 402, then the pressure data is determined to be abnormal.

[0085] By comparing the responses described in some embodiments of this specification when at least one pressure data point is greater than the standard pressure threshold, an anomaly can be determined, and an accurate standard pressure threshold can be identified, enabling timely and efficient judgment of pressure data anomalies.

[0086] In some embodiments, the processor can issue a warning 405 in multiple ways. For example, the processor can issue a warning 405 based on the warning type and the warning method corresponding to that type. More information on warning types and warning methods can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0087] Maintenance time can refer to the predicted time when maintenance and adjustments to the filtration equipment are needed. For example, maintenance time can be expressed as the interval between the next maintenance time of the filtration equipment and the current time. For instance, the maintenance time for a pre-filter could be 3 days from the current time.

[0088] "Staff" can refer to personnel working within the space to be cleaned. More information about spaces to be cleaned can be found here. Figure 1 And its related descriptions.

[0089] The prediction model 430 can be a model for predicting the maintenance time of the filtration device. In some embodiments, the prediction model 430 can be a machine learning model with a custom structure as described below, or it can be a machine learning model with other structures, such as a recurrent neural network (RNN) model.

[0090] In some embodiments, the prediction model 430 may include a feature extraction layer 420 and a maintenance time prediction layer 440.

[0091] The feature extraction layer 420 can be used to determine the usage feature vector 431 of the filtering device. The input to the feature extraction layer 420 may include historical usage data 410 of the filtering device i, and the output may include the usage feature vector 431 of the filtering device i. In some embodiments, the feature extraction layer 420 may be a neural network (NN) model.

[0092] Historical usage data 410 can refer to data related to the usage of the filtration equipment over a historical period. For example, historical usage data 410 may include maintenance data and service life of the filtration equipment. Maintenance data can refer to data reflecting the maintenance status of the filtration equipment. For example, maintenance data may include maintenance frequency and number of maintenance visits.

[0093] In some embodiments, the processor can determine the historical usage data 410 of the filter device i in a variety of ways. For example, the processor can obtain the historical usage data 410 of the filter device i through a storage device inside or outside the negative pressure weighing hood control system.

[0094] The maintenance time prediction layer 440 can be used to determine the maintenance time 450 of the filter equipment. The input to the maintenance time prediction layer 440 may include a pressure data sequence 432 of the filter equipment i at multiple time points and a usage feature vector 431 of the filter equipment i. The output may include the maintenance time 450 of the filter equipment i. The maintenance time prediction layer 440 can be a Long Short-Term Memory (LSTM) network model.

[0095] Pressure data sequence 432 can refer to a sequence of pressure data 403 at one or more time points. For information on pressure data and its acquisition methods, please refer to the aforementioned related explanations.

[0096] In some embodiments, the feature extraction layer 420 and the maintenance time prediction layer 440 can be jointly trained and acquired. In some embodiments, the first training samples for joint training include historical usage data of the sample filtering device, pressure data sequences of the sample filtering device at multiple time points, and the first label is the actual maintenance time of the sample filtering device. The first training samples can be obtained from historical data, and the first label can be obtained from annotation.

[0097] During training, historical usage data of the sample filtering device is input into the feature extraction layer to obtain the usage feature vector output by the feature extraction layer. The usage feature vector is then input into the maintenance time prediction layer to obtain the maintenance time of the sample filtering device output by the maintenance time prediction layer.

[0098] A loss function is constructed based on the first label and the maintenance time of the sample filtering device, and the parameters of the feature extraction layer and the maintenance time prediction layer are updated synchronously. Through parameter updates, the trained feature extraction layer 420 and maintenance time prediction layer 440 are obtained.

[0099] The prediction model described in some embodiments of this specification may include the use of a feature extraction layer and a maintenance time prediction layer, which can comprehensively consider various factors affecting the maintenance time of filtration equipment and their correlations, making the maintenance time determination process accurate and efficient.

[0100] In some embodiments, the processor can send the determined maintenance time 450 of at least one filter device to the staff's terminal device via a network for the staff to view and process.

[0101] The embodiments described in this specification enable the system to determine whether at least one pressure data point is abnormal. In response to abnormal pressure data, an early warning is issued. In response to normal pressure data, a predictive model is used to predict the maintenance time of at least one filtration device and send it to the staff. By monitoring abnormal pressure data in real time, the actual usage of the filtration device can be determined, making it easier for staff to detect and handle abnormalities in a timely manner. In addition, it can predict maintenance times that are consistent with reality, allowing staff to make advance arrangements for the maintenance of the filtration device and reduce the probability of safety accidents such as toxic gas leaks.

[0102] The negative pressure weighing hood described in some embodiments of this specification operates with preset operating parameters. The differential pressure sensor acquires pressure data based on a preset frequency and uploads it to the controller. In response to the adjusted operating parameters, the negative pressure weighing hood is controlled to operate. Accurate pressure data can be monitored in real time, which facilitates subsequent abnormal handling by the staff. In addition, the operating parameters of the negative pressure weighing hood can be adjusted in real time according to the usage situation to ensure the smooth progress of gas purification.

[0103] Figure 5This is a schematic diagram illustrating the adjustment of the operating parameters of the negative pressure weighing hood according to some embodiments of this specification.

[0104] In some embodiments, the controller can determine whether the first air quality detection data 534 and the second air quality detection data 572 are abnormal; in response to the first air quality detection data 534 being abnormal, the controller determines the warning type as the first warning type, issues the first warning, and adjusts the fan power and indoor gas exhaust volume; in response to the first air quality detection data 534 being normal and the second air quality detection data 572 being abnormal, the controller determines the warning type as the second warning type, issues the second warning, and adjusts the indoor gas exhaust volume.

[0105] In some embodiments, the controller can determine whether the first air quality detection data 534 and the second air quality detection data 572 are abnormal through various methods. For specific determination methods, please refer to [link / reference needed]. Figure 2 The relevant explanations in the document will not be repeated here.

[0106] In some embodiments, when any first air quality detection sub-data in the first air quality detection data 534 exceeds a first threshold, the controller can determine that the first air quality detection data 534 is abnormal; when any second air quality detection sub-data in the second air quality detection data 572 exceeds a second threshold, the controller can determine that the second air quality detection data 572 is abnormal. More information about the first and second air quality detection sub-data can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0107] The first threshold can refer to a standard value used to measure whether the first air quality detection data 534 is abnormal. The second threshold can refer to a standard value used to measure whether the second air quality detection data 572 is abnormal. The first threshold and the second threshold can be preset based on experience. The first threshold and the second threshold can be the same or different.

[0108] In some embodiments, the controller can sequentially compare the first air quality detection sub-data in the first air quality detection data 534 with a first threshold. If there is a first air quality detection sub-data exceeding the first threshold, the controller can determine that the first air quality detection data 534 is abnormal. The specific method by which the controller determines whether the second air quality detection data 572 is abnormal can refer to the aforementioned method for determining whether the first air quality detection data is abnormal.

[0109] The embodiments described in this specification, which use a first threshold and a second threshold to determine whether corresponding air quality detection data is abnormal, allow for setting separate thresholds for the two types of air quality detection data. This makes the determination of abnormal air quality detection data more targeted and more in line with actual conditions.

[0110] In some embodiments, in response to an anomaly in the first air quality detection data 534, the controller can determine that the warning type is a first warning type and issue a first warning; more information about the first warning type and the first warning can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0111] In some embodiments, in response to an abnormality in the first air quality detection data 534, the controller can adjust the fan power and indoor gas exhaust volume in various ways. For example, the controller can adjust the fan power and indoor gas exhaust volume using a third preset table, etc. The third preset table can specify the adjustment methods for the fan power and indoor gas exhaust volume when the first air quality detection data is abnormal and the second air quality detection data is normal; the third preset table can be set based on experience. For example, the third preset table can specify that when the first air quality detection data is abnormal and the second air quality detection data is abnormal, the fan power is increased by c% and the indoor gas exhaust volume is decreased by d%.

[0112] Understandably, when the first air quality reading (534) is abnormal, it's necessary to increase fan power to enhance purification. However, this might accelerate air circulation, causing more polluted gases to accumulate faster in the area below the space to be purified, increasing leakage and potentially causing the second air quality reading to change from normal to abnormal or worsen. Therefore, when adjusting fan power, it's necessary to predict the impact of this adjustment on the outdoor second air quality reading to determine the appropriate adjustment process for indoor gas emissions.

[0113] In some embodiments, the controller may generate at least one candidate fan power 532; based on the at least one candidate fan power 532, determine the target fan power 571 and the adjusted second air quality detection data 590 corresponding to the target fan power 571 by means of an evaluation model 530; and adjust the indoor gas exhaust volume based on the adjusted second air quality detection data 590.

[0114] The candidate turbine power 532 can refer to the available turbine power.

[0115] In some embodiments, the controller can generate at least one candidate wind turbine power 532 in various ways. For example, the controller can randomly generate multiple candidate wind turbine powers 532 without exceeding a preset range of the current wind turbine power (e.g., floating upwards by 20%). The preset range can be set based on experience. More information about the current wind turbine power can be found in [reference needed]. Figure 4 And its related descriptions.

[0116] The evaluation model 530 can be a model that predicts the adjusted second air quality detection data 590. In some embodiments, the evaluation model 530 can be a machine learning model with a custom structure as described below, or it can be a machine learning model with other structures, such as a Convolutional Neural Network (CNN) model, an NN model, an RNN model, etc.

[0117] In some embodiments, the evaluation model 530 may include a spatial feature extraction layer 520, a first prediction layer 540, a wind turbine power determination layer 560, and a second prediction layer 580.

[0118] The spatial feature extraction layer 520 can be used to determine the spatial feature vector 531 of the space to be cleaned. The input to the spatial feature extraction layer 520 may include the image 510 of the space to be cleaned, and the output may include the spatial feature vector 531. In some embodiments, the spatial feature extraction layer 520 may be a CNN model.

[0119] The controller can acquire images 510 of the space to be cleaned in a variety of ways. For example, the controller can acquire images 510 of the space to be cleaned through internal or external storage devices.

[0120] The spatial feature vector 531 can refer to feature information related to the space to be cleaned. For example, the spatial feature vector 531 can be [V,S,H], where V represents the volume of the space to be cleaned, S represents the surface area of ​​the space to be cleaned, and H represents the height of the space to be cleaned.

[0121] The first prediction layer 540 can be used to determine the adjusted first air quality detection data 550. The inputs to the first prediction layer 540 may include the first air quality detection data 534, pressure data 403, at least one candidate fan power 532, and a spatial feature vector 531. The output may include the adjusted first air quality detection data 550 corresponding to the candidate fan power 532. In some embodiments, the first prediction layer 540 can be an neural network model. More information about pressure data 403 can be found in [link to relevant documentation]. Figure 4 And its related descriptions.

[0122] The fan power determination layer 560 can be used to determine the target fan power 571. The input to the fan power determination layer 560 may include multiple candidate fan powers 532 and corresponding adjusted first air quality detection data 550, and the output may include the target fan power 571. The target fan power 571 may refer to the finally determined fan power. In some embodiments, the fan power determination layer 560 does not participate in model training, but only processes and selects data. For example, the fan power determination layer 560 may use the candidate fan powers that make the adjusted first air quality detection data 550 normal as the target fan power 571.

[0123] The wind turbine power determination layer 560 can be determined based on empirical presets or user input.

[0124] The second prediction layer 580 can be used to determine the adjusted second air quality detection data 590. The inputs to the second prediction layer 580 may include first air quality detection data 534, second air quality detection data 572, and a target fan power 571, and the output may include the adjusted second air quality detection data 590. In some embodiments, the second prediction layer 580 can be an neural network (NN) model.

[0125] In some embodiments, the spatial feature extraction layer 520, the first prediction layer 540, and the second prediction layer 580 can be jointly trained. In some embodiments, the second training samples for joint training include an image of the sample space to be purified, sample first air quality detection data, sample pressure data, sample candidate fan power, and sample second air quality detection data, with the first label being the actual adjusted second air quality detection data corresponding to the sample data. The second training samples can be obtained based on historical data, and the second label can be obtained based on annotations.

[0126] During training, an image of the space to be cleaned is input into the spatial feature extraction layer to obtain a spatial feature vector output by the spatial feature extraction layer. This spatial feature vector, along with the sample's first air quality detection data, sample pressure data, and sample candidate fan power, is input into the first prediction layer to obtain adjusted first air quality detection data output by the first prediction layer. The sample candidate fan power and the adjusted first air quality detection data are then used by a fan power determination layer to determine the target fan power. The determined target fan power, along with the sample's first air quality detection data and sample's second air quality detection data, are input into the second prediction layer to obtain adjusted second air quality detection data.

[0127] A loss function is constructed based on the second label and the adjusted second air quality detection data, and the parameters of the spatial feature extraction layer, the first prediction layer, and the second prediction layer are updated synchronously. Through parameter updates, the trained spatial feature extraction layer 520, the first prediction layer 540, and the second prediction layer 580 are obtained.

[0128] The evaluation model described in some embodiments of this specification may include a spatial feature extraction layer, a first prediction layer, a wind turbine power determination layer, and a second prediction layer. This can refine the acquisition process of the adjusted second air quality detection data, making the determination process more efficient and accurate. Joint training can also reduce the difficulty of collecting training samples.

[0129] In some embodiments, the controller can determine whether the adjusted second air quality detection data 590 is abnormal. If it is normal, there is no need to adjust the indoor gas exhaust volume; if it is abnormal, the controller adjusts the indoor gas exhaust volume according to the method described later based on the correspondence to determine the adjustment amount. The specific method for determining abnormality can refer to the aforementioned method for determining whether the second air quality detection data is abnormal based on a second threshold.

[0130] By generating candidate fan power as described in some embodiments of this specification, and through an evaluation model, the target fan power and the corresponding adjusted second air quality detection data are determined. The indoor gas exhaust volume is then adjusted, taking into account the impact of adjusting the fan power on the second air quality detection data, thus avoiding safety hazards such as leakage of polluted gas.

[0131] In some embodiments, in response to the first air quality detection data 534 being normal and the second air quality detection data 572 being abnormal, the controller can determine that the warning type is a second warning type and issue a second warning; more information about the second warning type and the second warning can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0132] In some embodiments, in response to the first air quality detection data 534 being normal and the second air quality detection data 572 being abnormal, the controller can adjust the indoor gas emission rate in various ways. For example, the controller can adjust the indoor gas emission rate through a fourth preset table, etc. The fourth preset table can specify that the more severe the abnormality of the second air quality detection data (such as the more second air quality detection sub-data exceeding the second threshold), the more serious the situation of polluted air leakage, and the controller can increase the indoor gas emission rate accordingly.

[0133] In some embodiments, the controller can determine the degree of dispersion of pollutants in response to a first air quality detection data 534 being normal and a second air quality detection data 572 being abnormal; determine an adjustment amount for the indoor gas emission rate based on a preset correspondence; adjust the indoor gas emission rate based on the adjustment amount; and determine the adjusted indoor gas emission rate. More information about pollutants can be found at [link to relevant documentation]. Figure 2 And its related descriptions.

[0134] The degree of diffusion can refer to a parameter that characterizes the diffusion of a gas.

[0135] In some embodiments, the controller can determine the degree of diffusion of polluting gases in a variety of ways. For example, the controller can calculate and determine the degree of diffusion of polluting gases using formula (1):

[0136]

[0137] Where D represents the degree of diffusion of polluting gas, m represents the number of second air quality detection sub-data points in the second air quality detection data that exceed the second threshold, i represents the i-th second air quality detection sub-data point, q(i) represents the value of the i-th second air quality detection sub-data point in the second air quality detection data that exceeds the second threshold, and q' represents the second threshold.

[0138] A preset correspondence can refer to the relationship between the pre-set diffusion level of polluted gases and the adjustment amount of indoor gas emissions. Preset correspondences can be set based on experience.

[0139] In some embodiments, the controller can directly calculate the adjustment amount of indoor gas discharge based on the degree of diffusion of polluted gas and a preset correspondence.

[0140] In some embodiments, the controller may determine an output threshold based on the worker's physical condition; and determine an adjustment amount based on the output threshold.

[0141] Physical condition can refer to the health status of staff. For example, a staff member's physical condition can include their healthy state or their disease state. Among these, disease state can include the type of disease, such as respiratory diseases or surgical diseases.

[0142] In some embodiments, the controller can determine the worker's physical condition in a variety of ways. For example, the controller can determine the worker's physical condition by acquiring input information from the worker.

[0143] The emission threshold can refer to the standard threshold for indoor gas emission.

[0144] In some embodiments, the controller can determine the discharge threshold based on the worker's physical condition using various methods. For example, the controller can determine the discharge threshold based on the worker's physical condition using a preset data lookup table. The preset data lookup table can include different physical conditions and their corresponding discharge thresholds. The preset data lookup table can be preset based on historical data.

[0145] For example, when a worker has an illness, the corresponding discharge threshold in the preset data lookup table is reduced. In some embodiments, the degree of reduction in the discharge threshold is related to the type of illness and the number of workers affected. For instance, the greater the reduction in the discharge threshold when the worker has a respiratory illness, the greater the reduction in the discharge threshold; the more workers affected, the greater the reduction in the discharge threshold. The specific value of the discharge threshold reduction can be set based on experience.

[0146] In some embodiments, the adjusted indoor gas exhaust volume can be the sum of the indoor gas exhaust volume and the adjustment amount. The adjusted indoor gas exhaust volume should not exceed the exhaust volume threshold.

[0147] In some embodiments, the controller can determine the adjustment amount in various ways based on an exhaust volume threshold. For example, the controller can calculate the difference between the exhaust volume threshold and the indoor gas exhaust volume as the adjustment amount.

[0148] The embodiments described in this specification allow for the determination of emission thresholds and adjustment amounts based on the physical condition of staff. This enables timely adjustments to the indoor gas emission volume according to the staff's health status, preventing breathing problems caused by excessive indoor gas emission and reduced air pressure, and thus improving the user experience.

[0149] In some embodiments, the controller can add the adjustment amount to the indoor gas discharge amount to obtain the adjusted indoor gas discharge amount.

[0150] By determining the degree of diffusion of polluting gases through some embodiments of this specification, and based on a preset correspondence, determining the adjustment amount of indoor gas emission, indoor air pollution can be monitored in real time, and effective adjustments can be made to avoid air pollution.

[0151] By using the methods described in some embodiments of this specification to determine the abnormality of the first air quality detection data and the second air quality detection data, the warning type is determined to be the first warning type, and the fan power and / or indoor gas exhaust volume are adjusted. Different treatment methods can be implemented for different pollution conditions inside and outside the space to be purified, making the abnormal adjustment results more accurate.

[0152] Some embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the negative pressure weighing hood control method as described in any of the above embodiments.

[0153] 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.

[0154] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0155] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0156] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0157] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0158] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0159] 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 negative pressure weighing hood control system, characterized in that, The system includes: a negative pressure weighing hood, a first air quality detection device group, a second air quality detection device group, and a controller; The controller is used for: Control the first air quality detection device group to acquire the first air quality detection data. The first air quality detection device group is deployed at at least one preset point inside the space to be purified. Control the second air quality detection device group to acquire second air quality detection data. The second air quality detection device group is deployed at at least one preset point around the space to be purified. In response to an anomaly in at least one of the first air quality monitoring data and the second air quality monitoring data, a warning type is determined; Adjusting the operating parameters of the negative pressure weighing hood based on the aforementioned warning type includes: Determine whether the first air quality detection data and the second air quality detection data are abnormal; In response to the abnormality of the first air quality detection data, the warning type is determined to be the first warning type, a first warning is issued, and the fan power and indoor gas exhaust volume are adjusted, the adjustment including: Generate at least one candidate wind turbine power; Based on the power of at least one candidate wind turbine, the target wind turbine power and the adjusted second air quality detection data corresponding to the target wind turbine power are determined by an evaluation model, wherein the evaluation model is a machine learning model; Based on the adjusted second air quality detection data, the indoor gas exhaust volume is adjusted. In response to the first air quality detection data being normal and the second air quality detection data being abnormal, the warning type is determined to be the second warning type, a second warning is issued, and the indoor gas emission rate is adjusted. The adjusted operating parameters are sent to the processor of the negative pressure weighing hood, and the processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters.

2. The system according to claim 1, characterized in that, The negative pressure weighing hood includes at least one differential pressure sensor, a flow equalization membrane, a pre-filter, a medium-efficiency filter, and a high-efficiency filter. The at least one differential pressure sensor is configured to correspond one-to-one with the flow equalization membrane, the pre-filter, the medium-efficiency filter, and the high-efficiency filter. The processor is used for: The negative pressure weighing hood is controlled to operate with preset operating parameters; The controller controls the at least one differential pressure sensor to acquire at least one pressure data point based on a preset frequency, and uploads the at least one pressure data point to the controller. In response to receiving the adjusted operating parameters sent by the controller, the negative pressure weighing hood is controlled to operate based on the adjusted operating parameters.

3. The system according to claim 2, characterized in that, The processor is further used for: In response to receiving the at least one pressure data sent by the processor, determine whether the at least one pressure data is abnormal; An alert is issued in response to at least one abnormal pressure data point; In response to the at least one pressure data being normal, the maintenance time of at least one filter device is predicted using a predictive model, and the maintenance time of the at least one filter device is sent to the staff. The predictive model is a machine learning model.

4. A method for controlling a negative pressure weighing hood, characterized in that, The method is executed by a negative pressure weighing hood control system, the system including a negative pressure weighing hood, a first air quality detection device group, a second air quality detection device group, and a controller, the method including: Control the first air quality detection device group to acquire the first air quality detection data. The first air quality detection device group is deployed at at least one preset point inside the space to be purified. Control the second air quality detection device group to acquire second air quality detection data. The second air quality detection device group is deployed at at least one preset point around the space to be purified. In response to an anomaly in at least one of the first air quality monitoring data and the second air quality monitoring data, a warning type is determined; Adjusting the operating parameters of the negative pressure weighing hood based on the aforementioned warning type includes: Determine whether the first air quality detection data and the second air quality detection data are abnormal; In response to the abnormality of the first air quality detection data, the warning type is determined to be the first warning type, a first warning is issued, and the fan power and indoor gas exhaust volume are adjusted, the adjustment including: Generate at least one candidate wind turbine power; Based on the power of at least one candidate wind turbine, the target wind turbine power and the adjusted second air quality detection data corresponding to the target wind turbine power are determined by an evaluation model, wherein the evaluation model is a machine learning model; Based on the adjusted second air quality detection data, the indoor gas exhaust volume is adjusted. In response to the first air quality detection data being normal and the second air quality detection data being abnormal, the warning type is determined to be the second warning type, a second warning is issued, and the indoor gas emission rate is adjusted. The adjusted operating parameters are sent to the processor of the negative pressure weighing hood, and the processor controls the negative pressure weighing hood to operate based on the adjusted operating parameters.

5. 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 the negative pressure weighing hood control method as described in claim 4.

Images