Ventilation air conditioner air pipe cleaning control platform

Abstract

The invention discloses a ventilation air conditioner air pipe cleaning control platform which is characterized in that air pipe environment parameters and the inner wall pollution state are monitored in real time through a data acquisition module, a central processing unit is combined with an intelligent algorithm to generate a cleaning scheme and dispatch cleaning equipment, and a remote monitoring module supports real-time intervention and data visualization. And the storage database realizes historical data accumulation and strategy optimization. The problems that a traditional cleaning method is low in efficiency and poor in effect are solved, and the standardization and intelligence level of cleaning operation is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ventilation and air conditioning, and particularly to a ventilation and air conditioning duct cleaning control platform. Background Art

[0002] With the wide application of ventilation and air conditioning systems, the problem of the cleanliness inside their ducts has become increasingly prominent. During the operation of ventilation and air conditioning systems, particulate matter, microorganisms, etc. in indoor and outdoor air will continuously deposit or adhere inside the ducts. This will not only reduce the operation efficiency of the ventilation and air conditioning systems, increase energy consumption, but also have a serious impact on indoor air quality and threaten human health. For example, in places with extremely high air quality requirements such as hospitals and food processing plants, pollutants inside the ducts may cause serious problems such as cross-infection and food contamination.

[0003] Traditional ventilation and air conditioning duct cleaning methods have many drawbacks. On the one hand, the cleaning cycle and cleaning plan often rely on the personal experience of operation and maintenance personnel, lacking scientific basis and precise control and monitoring means. This makes the cleaning work either too frequent, resulting in waste of resources; or not timely enough, leading to the aggravation of pollution problems. On the other hand, during the cleaning operation process, due to poor information communication and non-standardized processes, the cleaning is often incomplete, making it difficult to achieve the ideal cleaning effect, and the cleaning efficiency is also relatively low.

[0004] Therefore, it is of great practical significance to develop a ventilation and air conditioning duct cleaning control platform that can accurately monitor the duct pollution situation, intelligently formulate cleaning plans, and efficiently execute cleaning operations. Summary of the Invention

[0005] The present invention aims to provide a ventilation and air conditioning duct cleaning control platform to solve problems existing in traditional duct cleaning methods such as relying on manual experience, inaccurate cleaning, and low efficiency, realize the intelligentization, standardization, and high efficiency of ventilation and air conditioning duct cleaning, improve the operation and maintenance management efficiency of ventilation and air conditioning systems, and ensure indoor air quality.

[0006] 2. To achieve the above object, the present application provides a ventilation and air-conditioning duct cleaning control platform, which is characterized by including a central processing unit. The central processing unit is connected to a data acquisition module, a cleaning execution module, a remote monitoring module, and a storage database, and the modules are electrically connected to each other; the central processing unit is built-in with a variety of intelligent analysis algorithms, and according to the environmental state parameters inside the duct, automatically generates a cleaning plan, schedules the cleaning process in real time, analyzes and feedbacks the cleaning effect, and continuously optimizes the best cleaning strategy according to the historical cleaning data; the data acquisition module is used to collect various environmental parameters inside the duct to provide data support for the control platform; the cleaning execution module is used to receive the instructions of the central processing unit and accurately execute the cleaning strategy; the remote monitoring module provides and sets a user operation interface for management personnel to remotely view the duct cleaning progress, real-time data, and historical cleaning records, and provides a remote operation intervention function; the storage database is used to store the basic information of the ventilation and air-conditioning duct system and the historical cleaning data of the ducts in each area; the intelligent algorithms integrated in the central processing unit include an image recognition algorithm, a pollution degree judgment algorithm, a cleaning plan generation algorithm, an equipment scheduling algorithm, and a cleaning strategy optimization algorithm.

[0007] Further, the image recognition algorithm analyzes the dust accumulation information in different areas by using image recognition technology according to the high-definition image of the inner wall of the duct provided by the data acquisition module. According to the gray-scale characteristics of the dust accumulation and the pre-established dust accumulation amount - gray-scale linear regression model, combined with parameters such as the duct diameter and the image shooting angle, the actual dust accumulation amount is calculated.

[0008] Further, the dust amount - gray-scale linear regression model is constructed in the following way, specifically as follows:

[0009] S1, Gray-scale feature extraction: After graying the image of the inner wall of the duct, the average gray-scale value G within the ROI (region of interest) is selected as the feature parameter, and the gray-scale value range is [0, 255], where 0 is pure black and 255 is pure white;

[0010] S2, Dust accumulation thickness calibration: Through laboratory calibration, a linear relationship between the gray-scale value and the dust accumulation thickness h, unit: mm, is established: h = a·G + b + ∈, where a and b are calibration coefficients obtained by least squares fitting, and ∈ is the noise term;

[0011] S3, Geometric conversion model: Combining the image shooting angle θ, the dust accumulation thickness is converted into the actual dust accumulation amount M: M = ρ·h·cosθ·10 4 , unit: g / m 2 ; where ρ is the dust accumulation density, unit: g / cm 3 .

[0012] Further, the pollution degree judgment algorithm synthesizes the data detected by each sensor, sampling data, and image recognition results, sets different threshold ranges corresponding to different pollution levels according to the dust accumulation amount and the number of microbial colonies, analyzes the characteristics such as the coverage area, thickness, and distribution uniformity of the dirt by combining image recognition technology, and at the same time considers the influence of temperature and humidity on the nature of the dirt, and accurately determines the pollution level of the air duct in multiple dimensions.

[0013] Further, in the pollution degree judgment algorithm, a fuzzy logic dynamic threshold adjustment model is introduced to automatically correct the thresholds of the dust accumulation amount and the number of microbial colonies according to the real-time temperature and humidity (T, H). The specific steps are as follows:

[0014] First, define the input and output variables: the input temperature T ranges from 10°C to 40°C, and the relative humidity H ranges from 30% to 90%; the output: the threshold correction coefficient kd of the dust accumulation amount and the threshold correction coefficient km of the number of microbial colonies, with the range: 0.8 to 1.2;

[0015] Second, design the fuzzy rules: when T increases and H increases, the dirt viscosity increases, and the dust is more likely to adhere, so the threshold is decreased; when T decreases and H decreases, the dirt is easy to fall off, so the threshold is increased;

[0016] Finally, calculate the dynamic threshold: the corrected threshold = the basic threshold × kd × km.

[0017] Further, the cleaning plan generation algorithm determines the cleaning liquid composition and spraying amount based on the pollution degree judgment result and combines the air duct material, and sets the brush head rotation speed and moving speed according to the dirt adhesion force and the air duct shape; the equipment scheduling algorithm formulates a preliminary operation sequence based on the pipe network layout, the pollution degree of each section of the air duct, and the cleaning equipment position, monitors the running state and progress of the equipment in real time during the cleaning process, and dynamically adjusts the operation sequence and time allocation according to the actual situation.

[0018] Further, the cleaning strategy optimization algorithm regularly retrieves the historical cleaning records of a specific area from the storage database, uses data analysis technology to compare the best cleaning strategies corresponding to different pollution levels, pollutant properties, etc., and dynamically adjusts and optimizes the strategy in combination with the real-time feedback data during the current cleaning process.

[0019] Further, determining the cleaning liquid composition and spraying amount in combination with the air duct material is specifically as follows. Based on the pollution level L, where mild L = 1, moderate L = 2, severe L = 3, and the corrosion resistance coefficient c of the air duct material, where stainless steel = 1.0, galvanized sheet = 0.8, glass = 0.6, establish the spraying amount Q calculation formula: Q = Q0·L·c, where Q0 is the basic spraying amount.

[0020] Further, the rotation speed and moving speed of the brush head are set according to the dirt adhesion force and the shape of the air duct. Specifically, the rotation speed n of the brush head is based on the dirt adhesion force F, and F is evaluated by the difficulty of dirt peeling in image recognition: n = n0 + k·F. (Where n0 is the basic rotation speed, k is the correction coefficient, which is related to the pipe material and humidity, usually taking a value of 1 - 10, with the unit of rpm·m 2 / N). Among them, n0 is the basic rotation speed; the moving speed v is determined in combination with the duct bending degree α: v = v0·(1 - α / 180), where v0 is the basic speed of the straight section.

[0021] Further, the remote monitoring module is built - in with an alarm and notification function. When severe pollution in the air duct is detected, it will remotely notify the management staff. When there are faults in the cleaning equipment or abnormal cleaning progress, it will immediately send an alarm notification to the management staff, and display various real - time information during the air duct cleaning process through the display screen. The management staff can manually adjust the cleaning plan parameters and control the operation of the equipment.

[0022] Beneficial effects

[0023] Improve the cleaning accuracy: By the data acquisition module, the environmental parameters inside the air duct are collected in real - time and comprehensively. Combining with the intelligent algorithm of the central processing unit, it can accurately judge the pollution degree of the air duct, thus formulating a highly targeted cleaning plan, avoiding the blindness of traditional cleaning methods, and greatly improving the cleaning accuracy.

[0024] Enhance the cleaning efficiency: The intelligent devices of the cleaning execution module can efficiently execute the cleaning tasks according to the instructions of the central processing unit. The equipment scheduling algorithm ensures the orderly progress of the cleaning work, reduces the cleaning time, and improves the cleaning efficiency.

[0025] Realize intelligent management: The remote monitoring module facilitates the management staff to remotely monitor and operate. The storage database provides data support for intelligent analysis and strategy optimization. The entire platform realizes the intelligent management of the ventilation and air - conditioning air duct cleaning, reduces the labor cost, and improves the management efficiency. Brief description of the drawings

[0026] Figure 1 It is a schematic diagram of the connection relationship between each module in the present invention. Specific implementation manners

[0027] The following combines the drawings and embodiments to further describe in detail the specific implementation manners of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0028] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups.

[0029] For the sake of simplicity of the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product as a whole. In addition, for the sake of simplicity and easy understanding of the drawings, among the parts with the same structure or function in some figures, only one of them is schematically shown, or only one of them is labeled. In this article, "one" not only means "only this one", but also means the situation of "more than one".

[0030] It should be further understood that the term "and / or" used in the specification and the appended claims of this application refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0031] In the embodiments shown in the drawings, the indication of directions (such as up, down, left, right, front and back) is used to explain that the structures and movements of various components of the present invention are not absolute but relative. When these components are in the positions shown in the drawings, these explanations are appropriate. If the descriptions of the positions of these components change, the indication of these directions also changes accordingly.

[0032] In addition, in the description of this application, the terms "first", "second", etc. are only used for distinguishing descriptions, and cannot be understood as indicating or implying relative importance.

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the specific embodiments of the present invention will be described below with reference to the accompanying drawings.

[0034] As Figure 1 shown, the present invention provides a ventilation and air-conditioning duct cleaning control platform, which includes a central processing unit, a data acquisition module, a cleaning execution module, a remote monitoring module and a storage database. Among them, the modules are electrically connected to each other;

[0035] The data acquisition module includes three parts: a variety of sensors, microbial sampling detection and image recognition. Among them, the sensors include temperature and humidity, pressure, wind speed, particulate matter sensors, etc., which are used to record the corresponding environmental parameters in the pipeline air flow; the total number of bacteria, the total number of fungi, the total number of β-hemolytic streptococci in the ventilation and air-conditioning pipeline air flow and the total number of bacteria and fungi on the duct wall are measured by the culture method; the images inside the duct are captured by high-definition photography, and then the intelligent image analysis algorithm in the central processing unit is used to obtain the information of the dust accumulation amount on the inner wall.

[0036] The central processing unit incorporates a variety of intelligent analysis algorithms, including image recognition algorithms, pollution level judgment algorithms, cleaning plan generation algorithms, equipment scheduling algorithms, and cleaning strategy optimization algorithms.

[0037] The image recognition algorithm obtains the image of the inner wall of the air duct through the image acquisition camera. It converts the color image into a grayscale image through grayscale processing, uses a filtering algorithm to remove noise interference in the image, adopts an edge detection algorithm to identify the contour of the inner wall of the air duct, and determines the effective analysis area. For the dust accumulation area, according to the gray-scale characteristics of the dust accumulation and the pre-established dust accumulation amount-gray scale linear regression model, the dust accumulation thickness of different areas is calculated. Then, combined with parameters such as the diameter of the air duct and the image shooting angle, through geometric calculation, the dust accumulation thickness is converted into the actual dust accumulation amount. The image recognition algorithm can identify the dust accumulation area on the inner wall of the air duct and accurately calculate the dust accumulation thickness of different areas based on the gray-scale characteristics of the dust accumulation and the pre-established dust accumulation amount-gray scale linear regression model.

[0038] Construct a dust accumulation amount-gray scale linear regression model as follows:

[0039] S1, Gray-scale feature extraction: After grayscale processing the image of the inner wall of the air duct, select the average gray value G within the ROI (region of interest) as the feature parameter, and the gray value range is [0, 255] (0 is pure black, 255 is pure white).

[0040] S2, Dust accumulation thickness calibration: Through laboratory calibration, establish a linear relationship between the gray value and the dust accumulation thickness h (unit: mm): h = a·G + b + ∈, where a and b are calibration coefficients obtained by least squares fitting, and ∈ is the noise term.

[0041] S3, Geometric conversion model: Combine the image shooting angle θ to convert the dust accumulation thickness into the actual dust accumulation amount M: M = ρ·h·cosθ·10 4 , unit: g / m 2 ; where ρ is the dust accumulation density, unit: g / cm 3 .

[0042] The above construction of the dust accumulation amount-gray scale linear regression model can quantify the dust accumulation amount with high precision: directly associate the image gray value with the dust accumulation thickness through the linear regression model, and combine geometric parameter correction to reduce the measurement error of the dust accumulation amount from ±20% of the traditional manual estimation to ±5%, providing accurate data support for pollution level judgment; 2. Enhanced robustness: Introduce the noise term ∈ and the angle compensation factor cosθ to reduce the influence of uneven illumination and shooting angle deviation during image acquisition on the measurement results, and is applicable to complex air duct environments (such as elbows, variable diameter sections).

[0043] Pollution level judgment algorithm, which integrates the data of various sensors, microbial sampling and detection, and image recognition results. According to the dust accumulation amount and the number of microbial colonies, three threshold ranges are set from less to more, corresponding to mild pollution, moderate pollution and severe pollution levels respectively. According to the "Cleaning Specification for Air Conditioning and Ventilation Systems" (GB 19210-2019) and actual engineering data, for the dust accumulation amount (unit: g / m 2 ) and the number of microbial colonies (unit: CFU / m 2 , taking the total number of bacteria as an example), the following three-level basic thresholds are set:

[0044]

[0045]

[0046] Combined with image recognition technology, analyze the characteristics of the dirt coverage area, thickness and distribution uniformity, etc., and at the same time consider the influence of temperature and humidity on the dirt properties to accurately determine the duct pollution level in multiple dimensions.

[0047] In the pollution level judgment algorithm, a fuzzy logic dynamic threshold adjustment model is introduced to automatically correct the thresholds of the dust accumulation amount and the number of microbial colonies according to the real-time temperature and humidity (T, H). The specific steps are as follows:

[0048] Define input and output variables:

[0049] 1. Input: Temperature T (range: 10°C to 40°C), relative humidity H (range: 30% to 90%);

[0050] 2. Output: Dust accumulation amount threshold correction coefficient kd, microbial colony number threshold correction coefficient km (range: 0.8 to 1.2).

[0051] Fuzzy rule design:

[0052] 1. When T increases and H increases (such as in a high-temperature and high-humidity environment), the dirt viscosity increases, and dust is more likely to adhere, reducing the threshold (kd < 1, km < 1);

[0053] 2. When T decreases and H decreases (such as in a low-temperature and dry environment), the dirt is easy to fall off, increasing the threshold

[0054] (kd > 1, km > 1).

[0055] Typical rules are as follows:

[0056] Temperature Humidity kd km High High 0.8 0.9 Medium Medium 1.0 1.0 Low Low 1.2 1.1

[0057] Dynamic threshold calculation: Corrected threshold = Basic threshold × kd × km.

[0058] By correcting the thresholds in real time based on temperature and humidity, we can avoid misjudgments of traditional fixed thresholds in extreme environments (for example, dust accumulation in a high-humidity environment is actually more harmful but the fixed threshold has not been adjusted), thereby improving the accuracy of pollution level judgment. In addition, the pollution threshold is automatically lowered in high-temperature and high-humidity scenarios (such as air-conditioning systems in summer), triggering cleaning tasks in advance to prevent the growth of microorganisms and the adhesion and solidification of dirt, reducing the difficulty of subsequent cleaning.

[0059] Cleaning plan generation algorithm: Based on the contamination level, the cleaning fluid spray rate is determined according to the duct material. The brush head rotation speed and movement speed are set based on the dirt adhesion and duct shape. For heavily contaminated ducts made of corrosion-resistant materials, the cleaning fluid spray rate is increased. For strong dirt adhesion, the brush head rotation speed is increased and the movement speed is reduced. For complex duct shapes, the brush head movement path and speed are dynamically adjusted.

[0060] The amount of cleaning fluid sprayed is determined according to the material of the air duct. Specifically, based on the pollution level L (mild = 1, moderate = 2, severe = 3) and the corrosion resistance coefficient c of the air duct material (values: stainless steel = 1.0, galvanized sheet = 0.8, fiberglass = 0.6), the spraying amount Q (unit: L / min) calculation formula is established: Q = Q0·L·c, where Q0 is the basic spraying amount.

[0061] The brush head speed and movement speed are set according to the dirt adhesion and duct shape. Specifically, the brush head speed n (unit: rpm) is set according to the dirt adhesion F (assessed by the difficulty of dirt removal in image recognition, with a value of 0 to 100 N / m 2 ), F is evaluated by the difficulty of dirt removal in image recognition: n = n0 + k·F. (where n0 is the basic speed (preset to 200 rpm), and k is a correction factor that is related to the pipe material and humidity, usually ranging from 1 to 10, and the unit is rpm·m 2 / N) where n0 is the basic rotation speed; the moving speed v (unit: m / min) is determined in combination with the duct curvature α (elbow angle, value: 0°~90°): v=v0·(1-α / 180), and v0 is the basic speed of the straight segment (preset to 5m / min).

[0062] Through the linkage calculation of multiple factors such as pollution level, material, dirt characteristics and duct shape, the amount of cleaning fluid used is reduced and the life of the brush head is extended; the moving speed is automatically reduced in the elbow section (such as v = 2.5m / min for 90° elbow) to ensure full contact between the brush head and the pipe wall, and the cleaning coverage rate is increased from 80% of the traditional method to 98%.

[0063] Equipment scheduling algorithm: Starting from the overall perspective of the pipe network, based on the pipe network layout, the pollution degree of each section of the air duct, and the location of the cleaning equipment, a preliminary operation sequence is formulated, and the cleaning of the equipment closest to the severely polluted area is prioritized. During the cleaning process, the operating status and progress of the equipment are monitored in real time, and the operation sequence and time allocation are dynamically adjusted according to the actual situation to ensure high efficiency and orderliness.

[0064] Cleaning strategy optimization algorithm: Regularly retrieve the historical cleaning records of the air ducts in a specific area from the storage database, including the pollution type during each cleaning, the adopted cleaning plan, and the final cleaning effect evaluation data. Using data analysis techniques, compare the cleaning effects of different cleaning plans under the same or similar pollution types to find the best combination of cleaning plans. At the same time, combined with the real-time feedback data during the current cleaning process, such as the real-time change trend of the dust concentration and the dirt removal situation shown in the images during the cleaning process, the optimization strategy is dynamically adjusted. If it is found during the cleaning process that the actual dirt removal speed is slower than expected, the algorithm will automatically retrieve the handling methods for similar situations in the historical data and fine-tune the current cleaning plan, such as appropriately increasing the spraying amount of the cleaning liquid or adjusting the rotation speed of the brush head, to continuously optimize the cleaning strategy.

[0065] The cleaning execution module consists of multiple remotely controllable cleaning robots or cleaning equipment with intelligent drives. They receive instructions from the central processing unit and accurately execute the cleaning tasks according to the preset information such as the rotation speed, angle, cleaning liquid spraying flow rate, equipment moving speed, and moving path of the brush head.

[0066] The remote control terminal is built-in with alarm and notification functions. When severe pollution in the air duct is detected, it will remotely notify the management personnel. When the cleaning equipment fails or the cleaning progress is abnormal, it will immediately send an alarm notification to the management personnel. In addition, through the display screen, various real-time information during the air duct cleaning process is displayed, including the operating status of the equipment and the real-time data of the pollutants in the air duct. The management personnel can manually adjust the parameters of the cleaning plan and control the operation of the equipment.

[0067] The storage database can store a large amount of various data related to the ventilation and air-conditioning air duct system. It includes the basic information of the air ducts, such as the pipe diameter, length, material, installation location, and orientation, and also covers the detailed historical cleaning records of the air ducts in each area, including the cleaning time, cleaning plan, pollution data before and after cleaning, and cleaning effect evaluation each time.

[0068] The above has introduced the technical solution provided by the present invention for patents in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention for patents. The description of the above embodiments is only used to help understand the method and its core idea of the present invention for patents; at the same time, for those of ordinary skill in the art, according to the idea of the present invention for patents, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation on the present invention for patents.

Claims

1. A cleaning control platform for ventilation and air-conditioning air ducts, characterized in that, It includes a central processing unit, which is connected with a data acquisition module, a cleaning execution module, a remote monitoring module and a storage database, and the modules are electrically connected to each other; the central processing unit is built-in with a variety of intelligent analysis algorithms, which automatically generate a cleaning plan according to the environmental state parameters in the air duct, schedule the cleaning process in real time, analyze and feedback the cleaning effect, and continuously optimize the best cleaning strategy according to the historical cleaning data; the data acquisition module is used to collect various environmental parameters in the air duct to provide data support for the control platform; the cleaning execution module is used to receive the instructions of the central processing unit and accurately execute the cleaning strategy; the remote monitoring module provides and sets a user operation interface for the management personnel to remotely view the air duct cleaning progress, real-time data and historical cleaning records, and provides a remote operation intervention function; the storage database is used to store the basic information of the ventilation and air-conditioning air duct system and the historical cleaning data of the air ducts in each area; the intelligent algorithms integrated in the central processing unit include an image recognition algorithm, a pollution degree judgment algorithm, a cleaning plan generation algorithm, an equipment scheduling algorithm and a cleaning strategy optimization algorithm.

2. The ventilation and air-conditioning duct cleaning control platform according to claim 1, wherein The image recognition algorithm analyzes the dust accumulation information in different areas according to the high-definition image of the inner wall of the air duct provided by the data acquisition module by using image recognition technology, and calculates the actual dust accumulation amount according to the gray-scale characteristics of the dust accumulation and the pre-established dust accumulation amount-gray scale linear regression model, combined with parameters such as the pipe diameter of the air duct and the image shooting angle.

3. The ventilation and air-conditioning duct cleaning control platform according to claim 2, characterized in that, The dust accumulation amount-gray scale linear regression model is constructed in the following way, specifically as follows: S1, gray-scale feature extraction: After graying the image of the inner wall of the air duct, select the average gray value G in the ROI (region of interest) as the feature parameter, and the gray value range is [0, 255], where 0 is pure black and 255 is pure white; S2, dust accumulation thickness calibration: Through laboratory calibration, establish a linear relationship between the gray value and the dust accumulation thickness h, unit: mm: h = a·G + b + ∈, where a and b are calibration coefficients obtained by least squares fitting, and ∈ is the noise term; S3, Geometric transformation model: Combining the image shooting angle θ, convert the dust thickness into the actual dust amount M: M = ρ·h·cosθ·10 4 , unit: g / m 2 ; where ρ is the dust density, unit: g / cm 3 .

4. The ventilation and air-conditioning duct cleaning control platform according to claim 1, wherein The pollution degree judgment algorithm comprehensively combines various sensors, sampling detection data and image recognition results, sets different threshold ranges corresponding to different pollution levels according to the dust accumulation amount and the number of microbial colonies, analyzes the characteristics such as the coverage area, thickness and distribution uniformity of the dirt by combining image recognition technology, and at the same time considers the influence of temperature and humidity on the nature of the dirt to accurately determine the air duct pollution level in multiple dimensions.

5. The ventilation and air conditioning duct cleaning control platform according to claim 4, wherein In the pollution degree judgment algorithm, a fuzzy logic dynamic threshold adjustment model is introduced to automatically correct the thresholds of the dust accumulation amount and the number of microbial colonies according to the real-time temperature and humidity (T, H). The specific steps are as follows: First, define the input and output variables: input temperature T, range 10°C to 40°C, relative humidity H, range 30% to 90%; output: dust accumulation amount threshold correction coefficient kd, microbial colony number threshold correction coefficient km, range: 0.8 to 1.2; Secondly, fuzzy rule design: When T increases and H increases, the dirt viscosity increases and the dust is more likely to adhere, so the threshold is reduced; when T decreases and H decreases, the dirt is easy to fall off, so the threshold is increased; Final dynamic threshold calculation: Revised threshold = Basic threshold × kd × km.

6. The ventilation and air-conditioning duct cleaning control platform according to claim 1, characterized in that, The cleaning solution generation algorithm determines the cleaning liquid composition and spraying volume based on the pollution degree judgment result and in combination with the duct material, and sets the brush head rotation speed and moving speed according to the dirt adhesion and duct shape; the equipment scheduling algorithm formulates a preliminary operation sequence based on the pipe network layout, the pollution degree of each section of the duct, and the cleaning equipment location, monitors the equipment operation status and progress in real time during the cleaning process, and dynamically adjusts the operation sequence and time allocation according to the actual situation.

7. The ventilation and air-conditioning duct cleaning control platform according to claim 2, characterized in that, The cleaning strategy optimization algorithm regularly retrieves the historical cleaning records of a specific area from the storage database, uses data analysis techniques to compare the best cleaning strategies corresponding to different pollution levels, pollutant properties, etc., and dynamically adjusts and optimizes the strategy in combination with the data real-time feedback during the current cleaning process.

8. The ventilation and air-conditioning duct cleaning control platform according to claim 6, characterized in that, Determining the cleaning liquid composition and spraying volume in combination with the duct material specifically means that based on the pollution level L, where mild L = 1, moderate L = 2, severe L = 3, and the corrosion resistance coefficient c of the duct material, where stainless steel = 1.0, galvanized sheet = 0.8, glass = 0.6, a calculation formula for the spraying volume Q is established: Q = Q0·L·c, where Q0 is the basic spraying volume.

9. The ventilation and air-conditioning duct cleaning control platform according to claim 6, characterized in that, Set the brush head rotation speed and moving speed according to the dirt adhesion and the shape of the air duct. Specifically, the brush head rotation speed n is based on the dirt adhesion F, and F is evaluated by the difficulty of dirt peeling in image recognition: n = n0 + k·F. (where n0 is the base rotation speed, k is the correction coefficient, related to the pipe material and humidity, usually taking a value of 1 to 10, unit: rpm·m 2 / N). Among them, n0 is the base rotation speed; the moving speed v is determined in combination with the duct curvature α: v = v0·(1 - α / 180), where v0 is the base speed in the straight section.

10. The ventilation and air - conditioning duct cleaning control platform according to claim 1, wherein, The remote monitoring module has an alarm and notification function built-in. When serious pollution in the duct is detected, it will remotely notify the management personnel. When there are faults in the cleaning equipment or abnormal cleaning progress, it will immediately send an alarm notification to the management personnel, display various real-time information during the duct cleaning process through the display screen, and the management personnel can manually adjust the cleaning plan parameters and control the operation of the equipment.

Images