Intelligent micro-region gas circulation control method and system for a disinfection cabinet

Abstract

The present invention relates to the technical field of disinfection cabinet control, and discloses an intelligent micro-region gas circulation control method and system for a disinfection cabinet. The method includes obtaining disinfectant concentration data and air flow velocity data; performing regional state analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal region distribution map; performing air flow optimization based on the abnormal region distribution map to obtain optimized control parameters; generating a control instruction according to the optimized control parameters, and after the air flow circulation is stable, obtaining the gas circulation state; calculating the balance degree according to the gas circulation state to obtain the air flow balance degree; when the air flow balance degree is lower than a preset balance degree threshold, triggering secondary optimization to generate a secondary optimized distribution scheme. The present method has the following effects: The present method can improve the gas circulation control efficiency of local regions in the disinfection cabinet.

Description

Technical Field

[0001] The present invention relates to the technical field of disinfection cabinet control, and particularly to an intelligent micro-region gas circulation control method and system for a disinfection cabinet. Background Art

[0002] As an important device used in the household, medical, and catering industries, the main function of a disinfection cabinet is to sterilize and disinfect items through methods such as high temperature, ultraviolet light, or chemical gases. With the improvement of people's requirements for the quality of life and the increasingly strict hygiene standards, traditional disinfection methods are difficult to meet modern needs. Especially for different types of items, such as glassware, plastic products, and medical devices, they have different requirements for the disinfection environment, which has promoted the development of intelligent micro-region gas circulation control technology. This technology aims to precisely control the gas flow and temperature and humidity conditions in each region inside the disinfection cabinet to achieve the best disinfection effect while protecting the items from damage.

[0003] Existing disinfection cabinets adopt an integral gas circulation system, and its operation process is roughly as follows: First, the items to be disinfected are placed inside the disinfection cabinet, and the cabinet door is closed; then, according to the set disinfection mode, the corresponding program is started, including steps such as heating and injecting disinfection gas (such as ozone); during the disinfection process, the built-in fan promotes the overall circulation of the gas inside the cabinet to ensure the uniform distribution of the disinfection gas.

[0004] However, the entire disinfection process of the existing technical solutions depends on unified gas circulation and concentration settings, and it is impossible to flexibly adjust the disinfection conditions in each micro-region according to actual needs, resulting in the disinfection effect being affected or even the items being damaged in some regions due to excessive gas concentration or improper flow rate. Further, the global control strategy is also difficult to effectively identify and handle the emerging abnormal situations. For example, in a large disinfection space, problems such as excessive temperature and humidity or gas leakage may occur in a small area. If these problems are not discovered and solved in time, not only will the disinfection effect of this local area be reduced, but it may also lead to the imbalance of the internal environment of the entire disinfection cabinet. However, due to the effect of overall data averaging, these abnormalities in a small range are often masked and cannot be fully emphasized and processed in time. In summary, the global control strategy is difficult to identify abnormal regions, resulting in low control efficiency of gas circulation. Summary of the Invention

[0005] The present invention provides an intelligent micro-region gas circulation control method and system for a disinfection cabinet, in particular, to improve the gas circulation control efficiency of the disinfection cabinet.

[0006] In a first aspect, to solve the above technical problems, the present invention provides an intelligent micro-region gas circulation control method for a disinfection cabinet, including:

[0007] Obtain disinfectant concentration data and air flow velocity data;

[0008] Perform regional status analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal area distribution map;

[0009] Perform air flow optimization based on the abnormal area distribution map to obtain optimized control parameters;

[0010] Generate a control instruction according to the optimized control parameters. After the air flow circulation is stable, obtain the gas circulation status;

[0011] Perform equilibrium degree calculation based on the gas circulation status to obtain the air flow equilibrium degree;

[0012] When the air flow equilibrium degree is lower than a preset equilibrium degree threshold, trigger secondary optimization and generate a secondary optimized distribution plan.

[0013] In an alternative embodiment, the performing regional status analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal area distribution map includes:

[0014] Perform data cleaning on the disinfectant concentration data to obtain the cleaned cleaning concentration data;

[0015] Perform variance calculation on the cleaned cleaning concentration data to obtain the concentration deviation;

[0016] Mark the area where the concentration deviation is higher than a preset concentration deviation threshold as a concentration abnormal area;

[0017] Perform data cleaning on the air flow velocity data to obtain the cleaned cleaning flow velocity data;

[0018] Perform standard deviation calculation on the cleaned cleaning flow velocity data to obtain the air flow uniformity;

[0019] Mark the area where the air flow uniformity is lower than a preset uniformity standard value as a flow velocity abnormal area;

[0020] Mark the overlapping area of the concentration abnormal area and the flow velocity abnormal area as a comprehensive abnormal area;

[0021] Generate a heat map based on the concentration abnormal area, the flow velocity abnormal area and the comprehensive abnormal area to obtain the abnormal area distribution map.

[0022] In an alternative embodiment, the performing air flow optimization based on the abnormal area distribution map to obtain optimized control parameters includes:

[0023] Divide the abnormal area distribution map into grids according to a preset grid size to obtain micro areas;

[0024] Particle swarm optimization is performed on each of the micro-regions, including:

[0025] Initialize the particle swarm size, inertia weight, learning factor, and maximum number of iterations, where each particle represents a set of disinfection cabinet control parameters;

[0026] Randomly initialize the current position and current velocity of each particle;

[0027] Calculate the fitness based on the current position and the current velocity to obtain the current fitness of the current particle;

[0028] Update the individual optimal solution and the global optimal solution according to the current fitness;

[0029] Multiply the inertia weight by the current velocity to obtain the inertia term;

[0030] Calculate the cognitive term based on the learning factor, the individual optimal solution, and the current position;

[0031] Calculate the social term based on the learning factor, the global optimal solution, and the current position;

[0032] Perform weighted summation of the inertia term, the cognitive term, and the social term to obtain the updated velocity;

[0033] Calculate the updated position based on the updated velocity;

[0034] Use the updated velocity and the updated position as the current velocity and the current position respectively, repeat the iteration process, and record the number of iterations;

[0035] When the number of iterations reaches the maximum number of iterations, or fitness convergence is detected, complete the iteration process and output the global optimal solution as the optimized control parameter.

[0036] In an alternative embodiment, generating a control instruction according to the optimized control parameter, and after the air flow circulation is stable, obtaining the gas circulation state, includes:

[0037] Extract the air flow distribution ratio of each micro-region from the optimized control parameter;

[0038] Generate a control instruction set for the gas circulation device according to the air flow distribution ratio;

[0039] Drive the intake valve and the outlet valve of each micro-region according to the control instruction set, and record the gas deviation amount;

[0040] When the gas deviation amount is less than a preset stability threshold, it is determined that the air flow circulation is stable, and the gas circulation state is obtained;

[0041] The gas circulation state includes a disinfectant concentration value and an air flow velocity value.

[0042] In an optional embodiment, the calculating the balance degree according to the gas circulation state to obtain the airflow balance degree includes:

[0043] The airflow balance is calculated using the following formula:

[0044]

[0045] in, Indicates the airflow balance. represents the total number of micro-regions, Indicates the micro-area number, Indicates the The disinfectant concentration value of each micro area, Represents the average of the disinfectant concentration values of all micro-areas.

[0046] In an optional embodiment, when the airflow balance is lower than a preset balance threshold, a secondary optimization is triggered to generate a secondary optimized distribution plan, including:

[0047] Initialize the population according to the preset population size, where each individual gene sequence is a three-dimensional vector, including the three dimensions of fan speed, valve opening, and disinfectant cycle;

[0048] The fitness is calculated according to the following formula:

[0049]

[0050] in, represents fitness, Indicates the airflow balance. represents the normalization factor, Indicates the zero-proof constant;

[0051] Arrange the individuals in descending order according to their fitness, retain a preset proportion of individuals from large to small, and obtain the remaining individual population;

[0052] Performing arithmetic crossover and non-uniform mutation on the remaining individual population to obtain a new generation population, repeating the iterative process, and recording the number of iterations;

[0053] When the number of iterations reaches a preset upper limit of the number of iterations, a final population is obtained;

[0054] The individual gene sequence with the highest fitness in the final population is extracted, and after boundary verification, an allocation plan is output.

[0055] In an alternative embodiment, the fitness calculation based on the current position and the current speed to obtain the current fitness of the current particle includes:

[0056] Calculate the current fitness according to the following formula:

[0057]

[0058] Wherein, represents the current fitness, represents the maximum flow rate, represents the minimum flow rate, represents the average flow rate, represents the target concentration, represents the measured concentration, represents the normalized concentration, represents the comprehensive energy consumption, represents the normalized energy consumption, represents the index weight coefficient.

[0059] In a second aspect, the present invention provides an intelligent micro-region gas circulation control system for a disinfection cabinet, including:

[0060] A data acquisition module for acquiring disinfectant concentration data and air flow velocity data;

[0061] A region state module for performing region state analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal region distribution map;

[0062] An air flow optimization module for performing air flow optimization based on the abnormal region distribution map to obtain optimized control parameters;

[0063] A primary control module for generating a control instruction according to the optimized control parameters, and obtaining the gas circulation state after the air flow circulation is stable;

[0064] An equilibrium calculation module for performing equilibrium degree calculation based on the gas circulation state to obtain the air flow equilibrium degree;

[0065] A secondary optimization module for triggering secondary optimization and generating a secondary optimized distribution plan when the air flow equilibrium degree is lower than a preset equilibrium degree threshold.

[0066] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the intelligent micro-region gas circulation control method for the disinfection cabinet described in any one of the above.

[0067] Fourthly, the present invention also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent micro-region gas circulation control method of the disinfection cabinet described in any one of the above.

[0068] Compared with the prior art, the intelligent micro-region gas circulation control method of the disinfection cabinet of the present invention has the following beneficial effects:

[0069] (1) The process of obtaining the disinfectant concentration data and the air flow velocity data ensures a comprehensive understanding of the internal environment state of the disinfection cabinet. By installing high-precision sensors in the disinfection cabinet to monitor the disinfectant concentration and air flow velocity in real time, accurate data support is provided for subsequent analysis. This step not only improves the accuracy of data collection but also lays a foundation for achieving precise control, which helps to improve the disinfection effect.

[0070] (2) Analyze the regional state according to the disinfectant concentration data and the air flow velocity data to obtain an abnormal region distribution map. Calculate and process the disinfectant concentration and air flow velocity data using variance and standard deviation respectively to identify abnormal regions with insufficient disinfectant concentration or uneven air flow inside the disinfection cabinet. This method can quickly locate the problem areas, provide a clear direction for subsequent optimization control, and ensure that the ideal disinfection effect can be achieved in each corner. It improves the recognition efficiency and accuracy for local regions.

[0071] (3) Optimize the air flow according to the abnormal region distribution map to obtain optimized control parameters. Based on the identified abnormal region distribution map, the system automatically adjusts the working parameters (such as air speed, air direction, etc.) of the air supply device to improve the air flow distribution and eliminate the abnormal regions. This dynamic optimization mechanism can significantly improve the uniformity of the air flow, enabling the disinfectant to be evenly distributed throughout the disinfection cabinet, thereby improving the control efficiency of the overall air flow circulation.

[0072] (4) Generate control instructions according to the optimized control parameters. After the air flow circulation is stable, obtain the gas circulation state. Generate specific control instructions using the optimized control parameters and send them to the control system of the disinfection cabinet for execution. After a period of time, when the air flow circulation tends to be stable, collect the gas circulation state data again to evaluate the current air flow condition. This process ensures the effective implementation of the optimization measures and provides a basis for further adjustment.

[0073] (5) Calculate the balance degree according to the gas circulation state to obtain the air flow balance degree. Through a detailed analysis of the gas circulation state data, calculate the air flow balance degree index, which quantitatively represents the uniformity of the air flow inside the disinfection cabinet. This step helps to objectively evaluate the current air flow distribution situation and provides a scientific basis for judging whether further optimization is needed.

[0074] (6) When the air flow balance degree is lower than the preset balance degree threshold, secondary optimization is triggered to generate an allocated scheme after secondary optimization. If the calculated air flow balance degree does not meet the preset standard, the system will start the secondary optimization process to readjust the parameters of the air supply device until the requirements are met. Through multiple rounds of iterative optimization, this method ensures the uniformity and stability of the air flow, and finally realizes the consistency of the disinfection effects in each micro-region inside the disinfection cabinet, improving the disinfection quality and efficiency.

[0075] In summary, through a series of precise data acquisition, analysis, and control steps, the present invention realizes the intelligent management of the air flow inside the disinfection cabinet, not only improving the disinfection effect, but also enhancing the reliability and adaptability of the system, and is particularly suitable for occasions with high requirements for disinfection quality. Description of the Drawings

[0076] Figure 1 is a schematic flow chart of an intelligent micro-region gas circulation control method for a disinfection cabinet provided by the first embodiment of the present invention;

[0077] Figure 2 is a schematic structural diagram of an intelligent micro-region gas circulation control system for a disinfection cabinet provided by the second embodiment of the present invention. Detailed Embodiments

[0078] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0079] Referring to Figure 1 , the first embodiment of the present invention provides an intelligent micro-region gas circulation control method for a disinfection cabinet, including the following steps:

[0080] S11, obtaining the disinfection agent concentration data and the air flow velocity data;

[0081] S12, performing regional state analysis according to the disinfection agent concentration data and the air flow velocity data to obtain an abnormal region distribution map;

[0082] S13, performing air flow optimization according to the abnormal region distribution map to obtain optimized control parameters;

[0083] S14, generating a control instruction according to the optimized control parameters, and obtaining the gas circulation state after the air flow circulation is stable;

[0084] S15. Calculate the balance degree based on the gas circulation state to obtain the air flow balance degree.

[0085] S16. When the air flow balance degree is lower than the preset balance degree threshold, trigger secondary optimization to generate a redistributed plan after secondary optimization.

[0086] In step S11, obtain the disinfectant concentration data and the air flow velocity data.

[0087] In one implementation, the disinfectant concentration data is collected in real time by electrochemical sensors or infrared spectroscopy sensors distributed on the top, bottom, and side walls of the disinfection cabinet, and the concentration unit is ppm. The air flow velocity data is obtained by hot-wire anemometers or ultrasonic velocity meters installed at the inlet, outlet, and key micro-regions of the circulation duct, and the velocity unit is uniformly m / s (meters per second). After analog-to-digital conversion, the two types of data are transmitted to the main control module through the CAN bus or RS-485 communication protocol, stored as a structured data table indexed by time stamps, and recorded in CSV format with the spatial coordinates, concentration values (accurate to 0.1 ppm), wind speed values (accurate to 0.01 m / s), and acquisition times (millisecond-level accuracy) of each sensor node. At the same time, the CRC checksum is used to ensure the integrity of data transmission, and all numerical values are accompanied by unit identifiers to avoid the risk of dimension confusion.

[0088] In step S12, perform regional state analysis based on the disinfectant concentration data and the air flow velocity data to obtain a distribution map of abnormal regions.

[0089] In one implementation, perform data cleaning on the disinfectant concentration data to obtain the cleaned concentration data after cleaning.

[0090] Calculate the variance based on the cleaned concentration data to obtain the concentration deviation.

[0091] Mark the regions where the concentration deviation is higher than the preset concentration deviation threshold as concentration abnormal regions.

[0092] Perform data cleaning on the air flow velocity data to obtain the cleaned flow velocity data after cleaning.

[0093] Calculate the standard deviation based on the cleaned flow velocity data to obtain the air flow uniformity.

[0094] Mark the regions where the air flow uniformity is lower than the preset uniformity standard value as flow velocity abnormal regions.

[0095] Mark the overlapping regions of the concentration abnormal regions and the flow velocity abnormal regions as comprehensive abnormal regions.

[0096] A thermal map is generated according to the concentration abnormal area, the velocity abnormal area and the comprehensive abnormal area to obtain an abnormal area distribution map.

[0097] In one embodiment, during data cleaning, the disinfectant concentration data is first subjected to sliding average filtering (with a window width set to 5 sampling points) to eliminate sensor noise, and outliers are identified through a binning method: the 5%-95% percentile interval of the concentration data is calculated, and data points outside this range are eliminated. At the same time, zero-value sequences with a duration of more than 3 seconds are marked as sensor failure states; for the airflow velocity data, a median filter (with a window width of 3 points) is applied to suppress pulse interference, combined with physical constraint filtering (such as when the flow rate exceeds the maximum design value of the circulation system of 3m / s, it is considered an abnormality), and cubic spline interpolation is used to fill in single-point missing points caused by sensor jitter; both types of data are normalized after preprocessing (the concentration value is mapped to a dynamic range of 0-50ppm, and the flow rate value is mapped to the interval of 0-2.5m / s), and finally, the concentration and flow rate data sets are aligned at the millisecond level through a timestamp synchronization module, and the sampling time deviation is compensated by linear interpolation. The cleaned data is stored in a relational database with version control, and the original data and the cleaned data are bidirectionally traceable through the MD5 checksum.

[0098] In a specific embodiment, for the disinfectant concentration data (5 micro-area values after cleaning: 12.3ppm, 14.8ppm, 11.5ppm, 13.2ppm, 25.6ppm), the calculated mean μ=15.48ppm and the variance σ²=28.7ppm² were set according to the GB / T 18883-2022 standard as the concentration deviation threshold of 1.5 times the standard deviation (8.04ppm). The concentration deviation of area 5 reached 10.12ppm (25.6ppm), triggering an abnormal flag. For the airflow velocity data (measurement point values after cleaning: 1.8m / s, 1.9m / s, 2.0m / s, 2.1m / s, 0.5m / s), its standard deviation σ=0.62m / s (μ=1.66m / s) resulted in a coefficient of variation CV=0.37, which is significantly higher than ISO The uniformity exceeds the Level II standard (CV≤0.25) specified in 5801:2017, especially the low-speed airflow of 0.5m / s in area 5, which is the main reason for the uniformity exceeding the standard.

[0099] In one implementation, the process of generating the abnormal area distribution map includes the following steps: First, based on the concentration detection data, the concentration abnormal areas deviating from the mean by 1.5 times the standard deviation (such as >8.04 ppm in the example) are screened out through variance calculation, and at the same time, the flow velocity abnormal areas are identified according to the standard deviation and coefficient of variation of the air flow velocity (such as CV>0.25); Subsequently, through spatial overlay analysis, the two types of abnormal areas are overlaid on the vector layer of the geographic information system (the GeoPandas library in Python can be used), and the spatial intersection is extracted as the comprehensive abnormal area; Finally, using the heat map visualization technology, in Python's Matplotlib, different color codings are assigned to the three types of abnormal areas respectively (such as red gradient for concentration abnormality, blue gradient for flow velocity abnormality, and purple for comprehensive abnormality), a heat distribution map with transparency overlay effect is generated, and the spatial coordinate grid and legend description are embedded, and finally output as a high-resolution vector map or an interactive Web map (implemented by Leaflet.js).

[0100] In step S13, the air flow is optimized according to the abnormal area distribution map to obtain the optimized control parameters.

[0101] In one implementation, the abnormal area distribution map is divided into grids according to a preset grid size to obtain micro areas;

[0102] Particle swarm optimization is performed on each of the micro areas, including:

[0103] Initialize the particle swarm size, inertia weight, learning factor, and maximum number of iterations, where each particle represents a set of disinfection cabinet control parameters;

[0104] Randomly initialize the current position and current velocity of each particle;

[0105] Calculate the fitness according to the current position and the current velocity to obtain the current fitness of the current particle;

[0106] Update the individual optimal solution and the global optimal solution according to the current fitness;

[0107] Multiply the inertia weight by the current velocity to obtain the inertia term;

[0108] Calculate the cognitive term according to the learning factor, the individual optimal solution, and the current position;

[0109] Calculate the social term according to the learning factor, the global optimal solution, and the current position;

[0110] Perform weighted summation on the inertia term, the cognitive term, and the social term to obtain the updated velocity;

[0111] Calculate the update position based on the update speed;

[0112] Use the update speed and the update position as the current speed and the current position respectively, repeat the iteration process, and record the number of iterations;

[0113] When the number of iterations reaches the maximum number of iterations, or fitness convergence is detected, complete the iteration process, and output the global optimal solution as the optimized control parameter.

[0114] It should be noted that in the grid division implementation of the disinfection cabinet air flow optimization, taking the typical disinfection cavity size of 2.4m×1.8m as an example, the uniform grid division method can be adopted: preset the grid size as 0.3m×0.3m, divide the cavity longitudinally into 8 columns (2.4m / 0.3m), and transversely into 6 rows (1.8m / 0.3m) to form 48 rectangular micro-regions (numbered G01 - G48). The physical coordinate range corresponding to each grid is, for example, the G15 grid corresponding to the X-axis region of 1.2 - 1.5m and the Y-axis region of 0.6 - 0.9m. When dividing, give priority to equidistant cutting along the length and width directions of the cavity. If the size of the boundary region is less than 0.3m (such as the remaining 0.2m in the end grid), then extend it to the adjacent grid for merging processing to ensure full coverage without gaps. During anomaly detection, if a certain micro-region simultaneously satisfies the flow velocity standard deviation ≥ 0.15m / s and the concentration deviation ≥ 8ppm, it is marked as an abnormal grid. For example, if the G22 grid measures a flow velocity fluctuation of 0.18m / s and a concentration deviation from the target value of 12ppm, then trigger the particle swarm optimization process of this grid.

[0115] In one implementation, calculate the current fitness according to the following formula:

[0116]

[0117] where, represents the current fitness, represents the maximum flow velocity, represents the minimum flow velocity, represents the average flow velocity, represents the target concentration, represents the measured concentration, represents the normalized concentration, represents the comprehensive energy consumption, represents the normalized energy consumption, represents the index weight coefficient.

[0118] It should be noted that in the fitness calculation formula, the units and physical meanings of the parameters are as follows: the units of the maximum flow velocity, minimum flow velocity, and average flow velocity are meters per second (m / s), the units of the target concentration and measured concentration are ppm, the normalization value is 1 ppm for dimensional normalization, the unit of the comprehensive energy consumption is watt-hour (Wh), and the normalized energy consumption value is 100 watt-hours for dimensional normalization. The weight coefficient is a unitless proportionality factor (which can take values of 0.4, 0.3, 0.3 and satisfy the sum of 1). The fitness function is the core evaluation index of the optimization objective in the particle swarm algorithm. Its role is to guide the particle swarm to search for the optimal solution in the parameter space by quantifying the comprehensive performance of flow velocity uniformity, concentration control accuracy, and energy consumption efficiency. For example, when a set of control parameters results in small flow velocity fluctuations (the first term approaches 0), low concentration deviation (the second term approaches 0), and low energy consumption (the third term approaches 0), the fitness value f will be minimized. At this time, the parameter combination corresponding to this particle is the optimization direction, and the algorithm iteratively makes the population gradually converge to the global optimal solution.

[0119] It should be noted that in the particle swarm optimization implementation of the disinfection cabinet control parameters, the algorithm parameters are first set: the particle swarm size is taken as 20 - 50 (such as 30), the inertia weight w ∈ [0.4, 1.2] (typical value 0.8), the individual and social learning factors are taken as 1.5 and 2.0 respectively, and the maximum number of iterations is set to 100 times; each particle is encoded by a three-dimensional vector, representing the wind speed (0.5 - 3.0 m / s), wind direction (0 - 360°), and injection volume (50 - 200 ml / min) respectively. For example, the initial parameters of the randomly generated particle B are [2.1 m / s, 45°, 180 ml / min], and its velocity vector is initialized as [-0.1 m / s, +15°, -10 ml / min].

[0120] It should be noted that in each iteration, dynamic simulation is carried out using CFD (Computational Fluid Dynamics) software: ANSYS Fluent is used to establish a three-dimensional disinfection chamber model (size 2.4m×1.8m×1.2m), set the multiphase flow coupling (air-disinfectant mixture) and k-epsilon turbulence model, and simulate the airflow field distribution through a transient solver (time step 0.1 second). The parameter combination of each particle (such as [2.3m / s, 75°, 170ml / min]) is input as a boundary condition, and the software automatically outputs the extreme values of the flow velocity, concentration, and total system power consumption in each micro-region; among them, the wind speed is controlled by the inlet velocity boundary condition, the concentration is calculated through the component transport model, and the energy consumption is based on the integral of the fan power curve, all of which are automatically calculated within the simulation software. After the simulation data is extracted by a Python script, it is substituted into the fitness formula for calculation (such as f = 0.445), and the particle update logic is triggered. For example, when the simulation parameters of COMSOL Multiphysics are [2.2m / s, 90°, 180ml / min], through the post-processing module, it is detected that the standard deviation of the flow velocity of the G22 grid is 0.12m / s (lower than the threshold of 0.15m / s), and the concentration deviation is 6ppm (meeting the standard), then this parameter combination is marked as a candidate optimal solution. The entire simulation process runs in parallel on the HPC cluster, and the single iteration takes about 3 minutes (based on 480,000 grids and 32 CPU cores). The final output parameters are transmitted to the virtual PLC through the OPC UA protocol for verification. The obtained flow velocity, concentration, and power consumption data are then substituted into the fitness formula (the smaller the value, the better) for calculation; in the update rule, if the fitness of particle C at the 20th iteration is 0.38, which is better than its historical best of 0.42, then the parameter [2.3m / s, 75°, 170ml / min] is updated to the individual best. At the same time, if this value is lower than the global best of 0.40, then the global best is replaced.

[0121] It should be noted that the formula for the cognitive term is:

[0122]

[0123] Among them, represents the cognitive term, represents the individual learning factor, represents a random number, represents the individual optimal solution, represents the current position;

[0124] The formula for the social term is:

[0125]

[0126] Among them, represents the social term, represents the social learning factor, Represents a random number, Represents the global optimal solution, Represents the current position.

[0127] It should be noted that the random number takes values from 0 to 1 to prevent premature convergence.

[0128] It should be noted that in the particle swarm optimization algorithm, the velocity update is achieved by integrating three factors: First, retain the original motion trend of the particle (inertia term, weight 0.6), second, introduce the attraction of the particle's own historical best position (cognitive term, weight 1), and finally, superimpose the guiding effect of the global optimal position of the group (social term, weight 1).

[0129] It should be noted that in the particle swarm optimization algorithm, the calculation of the new position is achieved by vectorially superimposing the updated velocity vector with the current position. Specifically, the position update of each particle can be decomposed into the following steps: First, algebraically add the current parameter value (such as the wind speed value in the disinfection cabinet case) to the velocity increment of the corresponding dimension (i.e., the component of the velocity vector in that dimension). For example, when the current wind speed is 2.0 m / s and the velocity increment is +0.3 m / s, the new position wind speed is updated to 2.3 m / s; Second, in the multi-dimensional parameter space, such addition operations are independently performed for each dimension (such as wind speed, temperature, disinfection time, etc.) to form a new parameter combination; Finally, the system will detect whether the new position exceeds the preset parameter range (such as the wind speed is limited between 0.5 - 3.0 m / s). If it exceeds, the boundary handling mechanism will be triggered - for example, when 3.2 m / s is calculated, it is directly truncated to 3.0 m / s (hard boundary) or reflected back to 2.8 m / s according to the exceeding ratio (soft boundary). This process ensures that the movement of particles in the solution space follows both the dynamic laws and meets the engineering feasibility through the step-by-step superposition of parameter dimensions and boundary constraints.

[0130] In step S14, a control instruction is generated according to the optimization control parameter. After the air flow circulation is stable, the gas circulation state is obtained.

[0131] In one implementation, the air flow distribution ratio of each micro-region is extracted from the optimization control parameter;

[0132] A control instruction set for the gas circulation device is generated according to the air flow distribution ratio;

[0133] Each intake valve and exhaust valve of each micro-region is driven according to the control instruction set, and the gas deviation amount is recorded;

[0134] When the gas deviation amount is less than the preset stability threshold, it is determined that the air flow circulation is stable, and the gas circulation state is obtained;

[0135] Wherein the gas circulation state includes the disinfectant concentration value and the air flow velocity value.

[0136] It should be noted that the optimized control parameters are encoded by a three-dimensional vector, representing wind speed (0.5 - 3.0 m / s), wind direction (0 - 360°), and injection volume (50 - 200 ml / min) respectively. A control instruction set including valve opening degrees, time sequences, etc. is generated, and then the intake valves and exhaust valves of each micro-region are driven to perform dynamic regulation. After the valves act, the system monitors the gas distribution deviation amounts (such as pressure difference, flow rate difference, etc.) of each region in real time. When the deviation amount is lower than the preset stability threshold (for example, ±5% relative error) for 3 consecutive sampling periods, it is determined that the air flow circulation reaches a stable state. At this time, the measured values of the disinfectant concentration sensor and the wind speed sensor are synchronously collected to form gas circulation state data including the spatial concentration gradient distribution and the real-time flow rate matrix, providing input for subsequent disinfection efficacy evaluation. When the deviation amount exceeds the stability threshold for more than 50 sampling periods, it is determined that the air flow cannot reach a stable state, and data is re-collected and the control parameters are optimized.

[0137] It should be noted that the three-dimensional vector (wind speed, wind direction, injection volume) of the optimized control parameters generates a specific control instruction set through the following logic: First, the wind speed parameter (0.5 - 3.0 m / s) is mapped and converted into a fan speed instruction. For example, the speed of the fan motor is controlled through a PWM (pulse width modulation) signal to ensure that the actual wind speed matches the optimized value; the wind direction parameter (0 - 360°) drives the air deflector motor to adjust the angle, converting the abstract angle value into a mechanical displacement amount (such as 0° corresponding to the horizontal direction and 90° corresponding to vertically upward), and dynamically adjusting the opening degrees of the intake / exhaust valves of each region in combination with the air flow distribution ratio (such as when the wind direction of a certain region needs to be biased downward, the angle of the lower-layer air deflector and the opening degree of the intake valve are linked). The injection volume parameter (50 - 200 ml / min) controls the opening / closing time sequence and pulse width of the solenoid valve of the injector, converting the flow rate requirement into a duty cycle instruction of the valve. On this basis, the system further generates a time sequence table for the valve actions according to the disinfection task stages (such as pre-disinfection, main circulation, homogenization stage). For example, in the homogenization stage, the exhaust valves in the high-concentration regions are preferentially opened to balance the distribution, and at the same time, the execution order and duration of each instruction are recorded. Finally, it is integrated into a complete control instruction set including valve opening ratios, motor angle values, solenoid valve pulse parameters, and execution time sequences, ensuring that the hardware device can accurately execute the optimized air flow and concentration regulation strategy.

[0138] In step S15, the air flow balance degree is calculated according to the gas circulation state to obtain the air flow balance degree.

[0139] In one implementation, the air flow balance degree is calculated by the following formula:

[0140]

[0141] Among them, Indicates the air flow balance degree, Indicates the total number of micro - regions, Indicates the micro - region number, Indicates the disinfectant concentration value of the nth micro - region, Indicates the average value of the disinfectant concentration values of all micro - regions.

[0142] It should be noted that the calculation process of the air flow balance degree is based on the real - time monitoring data of each micro - region: First, obtain the measured value of the current disinfectant concentration through the concentration sensors distributed in each micro - region, and perform arithmetic averaging on the concentration values of all micro - regions (the total number is determined by the number of disinfection partitions preset by the system) to obtain the reference concentration level; Subsequently, square and sum the deviation between the concentration value of each partition and the average value, divide the sum by the total number of partitions to obtain the variance characterization quantity of the concentration dispersion degree, and take the square root of the variance to obtain the standard deviation of the concentration distribution; Finally, divide the standard deviation by the average concentration value to obtain the dimensionless air flow balance degree index. The smaller this value is, the more uniform the concentration distribution in each region. When it is lower than 0.15, it is considered to reach an excellent equilibrium state.

[0143] In step S16, when the air flow balance degree is lower than the preset balance degree threshold, secondary optimization is triggered to generate an optimized distribution plan after secondary optimization.

[0144] In one implementation, initialize the population according to the preset population quantity, where each individual gene sequence is a three - dimensional vector, including three dimensions: fan rotation speed, air valve opening degree, and disinfectant cycle;

[0145] Calculate the fitness according to the following formula:

[0146]

[0147] Where, Indicates the fitness, Indicates the air flow balance degree, Indicates the normalization factor, Indicates the anti - zero constant;

[0148] Arrange in descending order according to the magnitude of the fitness, and retain individuals with a preset proportion from large to small to obtain the remaining individual population;

[0149] Perform arithmetic crossover and non - uniform mutation on the remaining individual population to obtain a new generation of population, repeat the iterative process, and record the number of iterations;

[0150] When the number of iterations reaches the preset iteration upper limit, obtain the final population;

[0151] Extract the individual gene sequence with the highest fitness in the final population, and after boundary verification, output the distribution plan.

[0152] It should be noted that during population initialization, the system randomly generates three-dimensional parameter combinations according to the preset feasible range: for example, the value range of the fan speed dimension is 30% - 100% (such as individual A taking 75% corresponding to medium-speed operation), the air valve opening dimension is randomly generated between 20% - 80% (such as individual B setting 60% to reserve adjustment margin), and the disinfectant spraying period dimension is limited to the range of 120 - 600 seconds (such as individual C configuring 300 seconds to balance continuous disinfection and energy consumption). This design avoids the risk of shutdown by restricting the minimum fan speed, limits the upper limit of the air valve opening to prevent air flow overshoot, and at the same time ensures that the disinfection interval meets the air treatment requirements specified in GB / T 18883 - 2022, ensuring both the diversity of the initial population and meeting the boundary conditions for the safe operation of the equipment. The population size is set to 100.

[0153] It should be noted that the value of the anti-removal zero constant is 10^-5, a dimensionless constant. The value of the normalization factor is 1.5, dimensionless. The fitness is dimensionless. The air flow balance degree is dimensionless. The upper limit of the number of iterations is set to 100 times.

[0154] It should be noted that during the population iteration optimization process, the collaborative execution of arithmetic crossover and non-uniform mutation follows the following engineerable operation chain: First, use the tournament selection method to select the top 30% of high-quality individuals with the highest fitness from the parental population as the crossover base group, and perform a convex combination operation on the three-dimensional gene vectors (fan speed, air valve opening, disinfection period) of each pair of parental individuals (such as the offspring individual rc = αrf + (1 - α)rm, where α is a dynamic weight coefficient between [0.3, 0.7], rc represents the offspring gene vector, rf represents the paternal gene vector, and rm represents the maternal gene vector); Subsequently, perform non-uniform Gaussian mutation on the offspring generated by crossover - apply a normal perturbation with a standard deviation σ = 2% in the fan speed dimension (ensuring that the speed fluctuation does not exceed the safety margin of ±5%), and the air valve opening accepts a step change of ±8% - ±15% according to the probability inversely proportional to the fitness (the mutation amplitude of individuals with low fitness is larger); After each round of iteration, eliminate illegal individuals that violate the lower limit of the disinfection period (<120s) or fan overclocking (>100%) through the Pareto front analysis method, and finally generate a new generation of population with both inheritance and diversity until the number of iterations reaches the preset 50 generations or the optimal fitness fluctuates continuously for 5 generations < 0.1% to terminate the optimization.

[0155] It should be noted that during the implementation of boundary verification, static range truncation is performed on the three-dimensional parameters (such as the fan speed is forcibly limited to the range of 30% - 100%, if 115% exists in the gene sequence, it is corrected to 100% and an overlimit alarm is triggered).

[0156] In summary, the present invention discloses an intelligent micro-region gas circulation control method for a disinfection cabinet. By monitoring local abnormal regions of the disinfection cabinet, the particle swarm optimization algorithm is first used to optimize control parameters, and software simulation is used to monitor the results. For the second optimization, actual measurement data is combined, and the genetic algorithm is used to optimize control parameters to improve the control efficiency of gas circulation.

[0157] Referring Figure 2 , the second embodiment of the present invention provides an intelligent micro-region gas circulation control system for a disinfection cabinet, including:

[0158] A data acquisition module for acquiring disinfectant concentration data and air flow velocity data;

[0159] A region status module for performing region status analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal region distribution map;

[0160] An air flow optimization module for optimizing the air flow based on the abnormal region distribution map to obtain optimized control parameters;

[0161] A primary control module for generating a control instruction based on the optimized control parameters, and after the air flow circulation is stable, obtaining the gas circulation status;

[0162] An equilibrium calculation module for calculating the equilibrium degree based on the gas circulation status to obtain the air flow equilibrium degree;

[0163] A secondary optimization module for triggering secondary optimization and generating a secondary optimized allocation scheme when the air flow equilibrium degree is lower than a preset equilibrium degree threshold.

[0164] It should be noted that the intelligent micro-region gas circulation control system for a disinfection cabinet provided in the embodiment of the present invention is used to execute all the process steps of the intelligent micro-region gas circulation control method for a disinfection cabinet in the above embodiment. The working principles and beneficial effects of the two correspond one by one, so they will not be elaborated here.

[0165] The embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in the above embodiments of the intelligent micro-region gas circulation control method for a disinfection cabinet are implemented, such as Figure 1 the step S11 shown. Or, when the processor executes the computer program, the functions of each module / unit in the above device embodiments are implemented, such as the data acquisition module.

[0166] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0167] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than those described above, or combine some components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0168] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and lines.

[0169] The memory can be used to store the computer program and / or module. By running or executing the computer program and / or module stored in the memory, and invoking the data stored in the memory, the processor can implement various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0170] Among them, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0171] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0172] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent micro-region gas circulation control method for a disinfection cabinet, characterized in that, Including: Obtain disinfectant concentration data and air flow velocity data; Perform regional status analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal area distribution map; Perform air flow optimization based on the abnormal area distribution map to obtain optimized control parameters; Generate a control instruction according to the optimized control parameters. After the air flow circulation is stable, obtain the gas circulation status; Perform equilibrium degree calculation according to the gas circulation status to obtain the air flow equilibrium degree; When the air flow equilibrium degree is lower than a preset equilibrium degree threshold, trigger secondary optimization and generate a secondary optimized distribution plan; Among them, when the air flow equilibrium degree is lower than a preset equilibrium degree threshold, trigger secondary optimization and generate a secondary optimized distribution plan, including: Initialize the population according to a preset population quantity, where each individual gene sequence is a three-dimensional vector, including three dimensions: fan speed, air valve opening degree, and disinfectant cycle; Calculate the fitness according to the following formula: Among them, represents fitness, represents air flow balance, represents a normalization factor, represents a zero-elimination constant; Arrange in descending order according to the magnitude of the fitness, and retain individuals with a preset proportion from largest to smallest to obtain the remaining individual population; Perform arithmetic crossover and non-uniform mutation on the remaining individual population to obtain a new generation population, repeat the iterative process, and record the number of iterations; When the number of iterations reaches the preset iteration upper limit, obtain the final population; Extract the individual gene sequence with the highest fitness in the final population, and after boundary verification, output the distribution plan.

2. The intelligent micro-region gas circulation control method of the disinfection cabinet according to claim 1, characterized in that Perform regional status analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal area distribution map, including: Perform data cleaning on the disinfectant concentration data to obtain the cleaned cleaning concentration data; Perform variance calculation on the cleaned cleaning concentration data to obtain the concentration deviation; Mark the area where the concentration deviation is higher than the preset concentration deviation threshold as the concentration abnormal area; Perform data cleaning on the air flow velocity data to obtain the cleaned cleaning flow velocity data; Perform standard deviation calculation on the cleaned cleaning flow velocity data to obtain the air flow uniformity; Mark the area where the air flow uniformity is lower than the preset uniformity standard value as the flow velocity abnormal area; Mark the overlapping area of the concentration abnormal area and the flow velocity abnormal area as the comprehensive abnormal area; Generate a heat map according to the concentration abnormal area, the flow velocity abnormal area, and the comprehensive abnormal area to obtain the abnormal area distribution map.

3. The intelligent micro-region gas circulation control method of the disinfection cabinet according to claim 1, characterized in that, The performing air flow optimization according to the abnormal area distribution map to obtain optimized control parameters includes: Divide the abnormal area distribution map into grids according to a preset grid size to obtain micro areas; Perform particle swarm optimization on each of the micro areas, including: Initialize the particle swarm size, inertia weight, learning factor, and maximum number of iterations, where each particle represents a set of disinfection cabinet control parameters; Randomly initialize the current position and current speed of each particle; Perform fitness calculation according to the current position and the current speed to obtain the current fitness of the current particle; Update the individual optimal solution and the global optimal solution according to the current fitness; Multiply the inertia weight by the current speed to obtain the inertia term; Calculate the cognitive term based on the learning factor, the individual optimal solution, and the current position; Calculate the social term based on the learning factor, the global optimal solution, and the current position; Perform weighted summation based on the inertia term, the cognitive term, and the social term to obtain the updated velocity; Calculate the updated position based on the updated velocity; Take the updated velocity and the updated position as the current velocity and the current position respectively, repeat the iterative process, and record the number of iterations; When the number of iterations reaches the maximum number of iterations or fitness convergence is detected, complete the iterative process and output the global optimal solution as the optimized control parameter.

4. The intelligent micro-region gas circulation control method of the disinfection cabinet according to claim 1, wherein Generate a control instruction based on the optimized control parameter. After the air flow circulation stabilizes, obtain the gas circulation state, including: Extract the air flow distribution ratio of each micro-region from the optimized control parameter; Generate a control instruction set for the gas circulation device according to the air flow distribution ratio; Drive the intake valve and the exhaust valve of each micro-region according to the control instruction set and record the gas deviation amount; When the gas deviation amount is less than the preset stability threshold, it is determined that the air flow circulation is stable and the gas circulation state is obtained; Wherein the gas circulation state includes the disinfectant concentration value and the air flow velocity value.

5. The intelligent micro-region gas circulation control method of the disinfection cabinet according to claim 1, characterized in that, Perform an equilibrium degree calculation based on the gas circulation state to obtain the air flow equilibrium degree, including: Calculate the air flow equilibrium degree through the following formula: Among them, represents the air flow uniformity, represents the total number of micro-regions, represents the micro-region number, represents the disinfectant concentration value of the th micro-region, and represents the average value of the disinfectant concentration values of all micro-regions.

6. The intelligent micro-region gas circulation control method of the disinfection cabinet according to claim 3, wherein Perform a fitness calculation based on the current position and the current velocity to obtain the current fitness of the current particle, including: Calculate the current fitness according to the following formula: Among them, represents the current fitness, represents the maximum flow rate, represents the minimum flow rate, represents the average flow rate, represents the target concentration, represents the measured concentration, represents the normalized concentration, represents the comprehensive energy consumption, represents the normalized energy consumption, represents the index weight coefficient.

7. An intelligent micro-region gas circulation control system for a disinfection cabinet, which is used to implement the intelligent micro-region gas circulation control method for a disinfection cabinet as described in any one of claims 1 to 6, characterized in that, Include: A data acquisition module for acquiring disinfectant concentration data and air flow velocity data; A regional state module for performing regional state analysis based on the disinfectant concentration data and the air flow velocity data to obtain an abnormal region distribution map; An air flow optimization module for performing air flow optimization based on the abnormal region distribution map to obtain an optimized control parameter; A primary control module for generating a control instruction based on the optimized control parameter and obtaining the gas circulation state after the air flow circulation stabilizes; An equilibrium calculation module for performing an equilibrium degree calculation based on the gas circulation state to obtain the air flow equilibrium degree; A secondary optimization module for triggering secondary optimization and generating a secondary optimized distribution plan when the air flow equilibrium degree is lower than the preset equilibrium degree threshold.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the intelligent micro-region gas circulation control method of the disinfection cabinet according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the intelligent micro-region gas circulation control method of the disinfection cabinet according to any one of claims 1 to 6.

Images