A fume hood variable air volume control method based on laboratory environment monitoring

Abstract

The application discloses a kind of based on laboratory environment monitoring's fume chamber variable air volume control method, it is related to control adjustment technical field, steps include: arrangement sensor and collect laboratory data;Establish the basic fluid dynamics model of laboratory gas flow and diffusion;Gas diffusion path prediction is carried out, and the optimized gas diffusion path is obtained;According to the optimized gas diffusion path adjustment laboratory wind speed, and the wind speed adjustment result is obtained;According to wind speed adjustment result carries out gas concentration control, and the wind speed control result is obtained;Based on wind speed control result combines safety threshold and realizes alarm and response mechanism, and the alarm information and wind speed data are obtained;Based on alarm information and wind speed data carries out wind speed optimization and fault diagnosis, and the optimization data are obtained;Based on optimization data generates environmental safety report and adjusts wind speed control strategy.The application improves the safety, efficiency and energy saving of laboratory fume chamber, provides more effective gas control solution for laboratory environment.

Description

Technical Field

[0001] This invention relates to the field of control and regulation technology, specifically to a method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring. Background Technology

[0002] Variable air volume (VAV) control methods for laboratory fume hoods are crucial for ensuring personnel safety, optimizing energy consumption, and improving the stability of the experimental environment. Traditional fume hood systems typically rely on fixed fan speed control or manual adjustment to address changes in the concentration of harmful gases within the laboratory. However, these traditional control methods often fail to respond in real-time to dynamic factors such as gas leaks, temperature and humidity variations in the experimental environment, leading to excessively high or low gas concentrations that compromise experimental safety and energy efficiency. Therefore, developing an intelligent fan speed regulation and control method based on laboratory environmental monitoring is of great significance.

[0003] Currently, some technologies attempt to control the airflow velocity of fume hoods using gas concentration sensors. However, most of these methods rely on simple threshold settings and single feedback control, failing to fully consider the complex impact of airflow velocity on gas diffusion and emission, and lacking accurate modeling of fluid dynamics and real-time data correction. Existing technologies generally suffer from the following two problems:

[0004] 1. Existing technologies have shortcomings in basic fluid dynamics models: Although existing technologies employ certain fluid dynamics models to simulate gas diffusion and flow within fume hoods, most models are overly simplified and fail to consider complex factors in the experimental environment (such as temperature and humidity, gas type, and wind speed variations), thus failing to accurately describe the impact of wind speed adjustments on gas concentration. Existing models often neglect the nonlinear relationship between airflow and gas diffusion, resulting in low accuracy in gas concentration prediction and an inability to achieve accurate, real-time control.

[0005] 2. Existing Kalman filter correction techniques have shortcomings: While existing techniques use Kalman filtering to correct the relationship between gas concentration and wind speed in experimental environments, most methods rely solely on simple linear assumptions, neglecting the impact of nonlinear dynamic changes on the system state. Furthermore, existing Kalman filter methods fail to integrate calculations from fundamental fluid dynamics models and gas diffusion models, resulting in inaccurate wind speed regulation after correction and an inability to dynamically adjust for changes in fluid and gas states. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a variable air volume control method for fume hoods based on laboratory environmental monitoring, in order to solve the problems mentioned in the background section.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, embodiments of the present invention provide a method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring, comprising the following steps:

[0009] S1. Deploy sensors and collect laboratory data;

[0010] S2. Establish a basic fluid dynamics model for gas flow and diffusion in the laboratory;

[0011] S3. Predict the gas diffusion path to obtain the optimized gas diffusion path;

[0012] S4. Adjust the laboratory wind speed according to the optimized gas diffusion path to obtain the wind speed adjustment result;

[0013] S5. Based on the wind speed adjustment results, control the gas concentration to obtain the wind speed control results;

[0014] S6. Based on the wind speed control results and safety thresholds, an alarm and response mechanism is implemented to obtain alarm information and wind speed data.

[0015] S7. Based on alarm information and wind speed data, perform wind speed optimization and fault diagnosis to obtain optimized data;

[0016] S8. Generate environmental safety reports and adjust wind speed control strategies based on optimized data.

[0017] To further optimize this technical solution, the types of sensors deployed and the laboratory data collected in step S1 include:

[0018] Temperature sensor, humidity sensor, pressure sensor, flow meter, gas sensor;

[0019] Airflow velocity, gas concentration, temperature, humidity, fluid density, gas type, air pressure, fluid viscosity, and diffusion coefficient.

[0020] To further optimize this technical solution, the step of establishing the fluid dynamics model in S2 includes:

[0021] Navier-Stokes Equation:

[0022] This equation describes the flow of air in space and time and is used to simulate gas flow processes.

[0023] ;

[0024] in:

[0025] Fluid density, in units of kg / m³, is affected by laboratory ambient temperature and pressure and is calculated based on data obtained in S1;

[0026] : Airflow velocity vector, in m / s, measured by a flow meter, such as a top-spinning sphere gas flow meter;

[0027] : Rate of change of velocity over time;

[0028] Gas pressure gradient, measured in Pa / m, represents the rate of change of pressure in space and is obtained by a pressure sensor.

[0029] Fluid viscosity, in Pa·s, is obtained by consulting relevant literature based on the type of gas measured by the gas sensor.

[0030] The second spatial derivative of the velocity field;

[0031] Representation: External force, obtained through measurement, used to represent gravity and surface friction.

[0032] Solving the equation, we get:

[0033] The velocity field v(x,t) of the airflow in the laboratory represents the magnitude and direction of the airflow velocity at each point x and at each time t;

[0034] The pressure field p(x,t) represents the magnitude of the gas pressure at each point x and at each time t.

[0035] By analyzing the speed and direction of airflow and the magnitude of gas pressure, the diffusion path of the gas can be determined, thereby simulating the gas flow process.

[0036] Diffusion-convection equations:

[0037] This equation is used to describe the propagation and diffusion behavior of gases in fluids;

[0038] ;

[0039] in:

[0040] Gas concentration, measured in mg / m³, represents the gas concentration at spatial location (x, y, z) and time t, and is obtained by a gas sensor.

[0041] The gas concentration gradient represents the change in gas concentration in space, and its magnitude is equal to the rate of change of gas concentration.

[0042] Gas diffusion coefficient, in meters (m). 2 / s, estimated based on the type of gas measured by the gas sensor and environmental factors;

[0043] The Laplace operator for gas concentration describes the second-order rate of change of gas concentration in space, reflecting how gas flows from a high-concentration region to a low-concentration region through diffusion.

[0044] Solving the equations yields the temporal and spatial distribution of gas concentration in the laboratory. By observing changes in gas concentration, the diffusion path of the gas is determined; the greater the gas concentration gradient, the faster the gas diffusion.

[0045] To further optimize this technical solution, the step of predicting the gas diffusion path in S3 includes:

[0046] Input real-time environmental data;

[0047] Using the fluid dynamics model established in step S2, predict the diffusion path and concentration distribution of the gas in the laboratory;

[0048] The Kalman filter technique is used to correct the model's prediction results.

[0049] To further optimize this technical solution, the steps for correcting the prediction results using the Kalman filtering technique include:

[0050] System state model:

[0051] The system state model describes how the current system state is calculated;

[0052] ;

[0053] in:

[0054] System status, including gas concentration, wind speed, fluid velocity, and diffusion coefficient;

[0055] The state transition matrix represents the dynamic change from the previous state to the current state. It is calculated by combining the Navier-Stokes equations and the diffusion-convection equations with the gas diffusion process in the laboratory, reflecting the influence of laboratory air flow, gas diffusion, temperature and humidity on gas diffusion.

[0056] : Control matrix, representing the effect of control inputs on the system state;

[0057] The wind speed adjustment is controlled in real time by the laboratory's wind speed control system and is affected by temperature and humidity.

[0058] Process noise represents the uncertainty and external disturbances in the model; set according to the results.

[0059] Observation equation:

[0060] Data from temperature, humidity, and gas sensors is used in the system status update process;

[0061] ;

[0062] in:

[0063] Observations are real-time measurement data obtained through sensors.

[0064] The observation matrix describes the system state, such as gas concentration and wind speed, and the relationship between these and the observed values. It also adjusts the predicted gas concentration based on changes in temperature and humidity.

[0065] Observation noise represents the measurement error of the sensor and should be adjusted according to the actual situation.

[0066] Kalman filter prediction steps:

[0067] Through the state transition matrix and control matrix Make a prediction and output the system state at the next moment.

[0068] ;

[0069] in:

[0070] The predicted system state includes gas concentration, wind speed, and diffusion coefficient.

[0071] State estimate from the previous moment;

[0072] Kalman filter update steps:

[0073] By fusing the prediction results with the actual observation data, a more accurate state estimate can be obtained;

[0074] ;

[0075] Updated system state estimate;

[0076] Kalman gain is a weighted measure of the difference between predicted and observed values.

[0077] : Residual, set according to the gas diffusion path calculated by the diffusion-convection equation and the influence of temperature and humidity on the diffusion coefficient, represents the difference between the actual observed value and the predicted value;

[0078] Covariance update:

[0079] Reflecting the uncertainty of system state estimation, the confidence level obtained by updating the covariance matrix is ​​used to gradually improve prediction accuracy, and the decision to continue optimization is made based on the confidence level.

[0080] To further optimize this technical solution, the step of adjusting the laboratory wind speed in S4 includes:

[0081] Real-time monitoring of environmental data via sensors;

[0082] The gas concentration is calculated and judged based on the automated control algorithm;

[0083] Based on the judgment results, the wind speed is automatically adjusted through the wind speed regulation system.

[0084] To further optimize this technical solution, the gas concentration control step in S5 includes:

[0085] Relationship between gas concentration and wind speed:

[0086] Changes in wind speed directly affect the diffusion rate of gases. The higher the wind speed, the lower the gas concentration. If the wind speed is too low, the gas will stagnate and the gas concentration will increase.

[0087] ;

[0088] in:

[0089] Gas concentration, obtained through a gas sensor;

[0090] Air velocity, obtained through a flow meter;

[0091] The diffusion coefficient of a gas is estimated based on the type of gas measured by a gas sensor and environmental factors.

[0092] By adjusting the wind speed, the airflow velocity is changed. This changes the diffusion rate of the gas concentration, thus adjusting the gas concentration.

[0093] The goal of wind speed regulation:

[0094] Real-time adjustment: The wind speed is adjusted in real time based on the data monitored by the gas concentration sensor;

[0095] Feedback control: By combining gas concentration data provided by sensors and using feedback control algorithms, the gas concentration in the laboratory is optimized by real-time monitoring and adjustment of wind speed;

[0096] Control process:

[0097] Sensor monitoring: The gas concentration inside the fume hood is continuously monitored by a gas concentration sensor, and fluctuations in the gas concentration are fed back to the control system via sensor signals;

[0098] Concentration vs. Safety Threshold Comparison: The real-time monitored gas concentration is compared with the set safety concentration threshold to determine whether it exceeds the limit;

[0099] Wind speed regulation strategy: The system dynamically adjusts the wind speed according to the degree to which the gas concentration deviates from the safe threshold;

[0100] Adjustment strategy:

[0101] Fuzzy control: The wind speed is adjusted based on the deviation of the gas concentration from the safety threshold and the rate of change of the error, using fuzzy control rules.

[0102] To further optimize this technical solution, the method for implementing the alarm and response mechanism in S6 includes:

[0103] Set safety thresholds; determine gas concentration to trigger alarms and take emergency measures.

[0104] To further optimize this technical solution, the method for wind speed optimization and fault diagnosis in S7 includes:

[0105] By using machine learning algorithms, the relationship between different gas leakage scenarios and wind speed regulation can be learned, and future wind speed regulation strategies can be optimized.

[0106] To further optimize this technical solution, the environmental safety report in S8 includes:

[0107] Based on the optimized data, a detailed laboratory gas environment safety report is generated, including gas concentration change trends, historical wind speed adjustment records, alarm information, and emergency response measures. This allows laboratory managers to optimize wind speed adjustment strategies and improve the system's intelligence level based on the detailed environmental safety report.

[0108] Compared with the prior art, the present invention provides a variable air volume control method for fume hoods based on laboratory environmental monitoring, which has the following beneficial effects:

[0109] This variable air volume (VAV) control method for fume hoods based on laboratory environmental monitoring accurately predicts and adjusts gas concentration and airflow changes in the laboratory environment through data acquisition and monitoring control, combined with advanced fundamental fluid dynamics models (such as the Navier-Stokes equations and diffusion-convection equations) and Kalman filtering correction technology. Based on accurate modeling of airflow and gas diffusion, this method dynamically adjusts the airflow by real-time monitoring of environmental parameters (such as gas concentration, temperature, and humidity) to ensure that the gas concentration remains within a safe range. Simultaneously, by using Kalman filtering to correct real-time data, the system state can be adjusted promptly, optimizing the airflow adjustment strategy and improving the system's response speed and accuracy. This intelligent adjustment mechanism significantly improves the safety, efficiency, and energy efficiency of laboratory fume hoods, providing a more stable and reliable gas control solution for laboratory environments. Attached Figure Description

[0110] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0111] Figure 1 This is a flowchart illustrating a variable air volume control method for fume hoods based on laboratory environmental monitoring proposed in this invention.

[0112] Figure 2 This is a schematic diagram of the basic fluid dynamics model of the variable air volume control method for fume hoods based on laboratory environmental monitoring proposed in this invention.

[0113] Figure 3 This is a flowchart illustrating the Kalman filter model of a fume hood variable air volume control method based on laboratory environmental monitoring proposed in this invention.

[0114] Figure 4 This is a flowchart illustrating the machine learning algorithm for a fume hood variable air volume control method based on laboratory environmental monitoring proposed in this invention. Detailed Implementation

[0115] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0116] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0117] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0118] Example 1:

[0119] Reference Figures 1-4 This is the first embodiment of the present invention, which provides a method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring, including the following steps:

[0120] S1. Deploy sensors and collect laboratory data.

[0121] In this embodiment, sensor devices are first deployed in key areas of the laboratory. These sensors will continuously collect environmental data, providing real-time environmental data for subsequent fluid dynamics modeling, gas diffusion path prediction, and wind speed regulation.

[0122] Furthermore, the types of sensors that can be deployed include:

[0123] Temperature sensor: used to monitor laboratory temperature;

[0124] Humidity sensor: used to monitor humidity in the laboratory;

[0125] Pressure sensor: used to monitor laboratory air pressure;

[0126] Flow meter: used to monitor airflow velocity in the laboratory;

[0127] Gas sensors: used to monitor the concentration and type of gases in the laboratory.

[0128] Furthermore, the collected laboratory data includes:

[0129] Airflow velocity, gas concentration, temperature, humidity, fluid density, gas type, gas pressure, fluid viscosity, and diffusion coefficient (by analyzing the types of gases in the laboratory using gas sensors and experimental procedures, and by consulting laboratory data, data on fluid viscosity and diffusion coefficient can be obtained).

[0130] S2. Establish a basic fluid dynamics model for gas flow and diffusion in the laboratory.

[0131] In this embodiment, the steps for establishing the fluid dynamics model include:

[0132] Navier-Stokes Equation:

[0133] This equation describes the flow of air in space and time and is used to simulate gas flow and fluid dynamics processes.

[0134] ;

[0135] in:

[0136] Fluid density, in units of kg / m³, is affected by laboratory ambient temperature and pressure and is calculated based on data obtained in S1;

[0137] : Airflow velocity vector, in m / s, measured by a flow meter, such as a top-spinning sphere gas flow meter;

[0138] : Rate of change of velocity over time;

[0139] Gas pressure gradient, measured in Pa / m, represents the rate of change of pressure in space and is obtained by a pressure sensor.

[0140] Fluid viscosity, in Pa·s, is obtained by consulting relevant literature based on the type of gas measured by the gas sensor.

[0141] The second spatial derivative of the velocity field;

[0142] Representation: External force, obtained through measurement, used to represent gravity and surface friction.

[0143] Solving the equation, we get:

[0144] The velocity field v(x,t) of the airflow in the laboratory represents the magnitude and direction of the airflow velocity at each point x and at each time t;

[0145] The pressure field p(x,t) represents the magnitude of the gas pressure at each point x and at each time t.

[0146] By analyzing the speed and direction of airflow and the magnitude of gas pressure, the diffusion path of the gas can be determined, thereby simulating the gas flow process.

[0147] Diffusion-convection equations:

[0148] This equation combines the processes of gas diffusion and convection to describe the propagation and diffusion behavior of gas in fluids. In a laboratory environment, the effects of gas diffusion and convection jointly influence the concentration distribution of the gas.

[0149] ;

[0150] in:

[0151] Gas concentration, measured in mg / m³, represents the gas concentration at spatial location (x, y, z) and time t, and is obtained by a gas sensor.

[0152] The gas concentration gradient represents the change in gas concentration in space, and its magnitude is equal to the rate of change of gas concentration.

[0153] Gas diffusion coefficient, in meters (m) 2 / s, estimated based on the type of gas measured by the gas sensor and environmental factors;

[0154] The Laplace operator for gas concentration describes the second-order rate of change of gas concentration in space, reflecting how gas flows from a high-concentration region to a low-concentration region through diffusion.

[0155] Solving the equation yields the temporal and spatial distribution of gas concentration within the laboratory. This equation simulates the gas propagation process under the influence of wind speed and diffusion. By observing changes in gas concentration, the diffusion path is determined; a larger concentration gradient indicates faster diffusion. Combining the results with the Navier-Stokes equations allows for a detailed understanding of the interaction between airflow and gas diffusion, simulating gas flow characteristics and diffusion paths, predicting potential gas leak areas and their concentration changes, optimizing wind speed adjustments, and ensuring that gas emissions do not pose a hazard to personnel within the laboratory.

[0156] S3. Predict the gas diffusion path to obtain the optimized gas diffusion path.

[0157] In this embodiment, the steps for predicting gas diffusion paths include:

[0158] Input real-time environmental data, such as gas concentration, wind speed, fluid velocity, diffusion coefficient, etc.

[0159] Using the fluid dynamics model established in step S2, predict the diffusion path and concentration distribution of gas in the laboratory: based on the input data, simulate the flow characteristics and diffusion path of the gas, and predict the area where the gas may leak and the changes in concentration.

[0160] Kalman filtering technology is used to correct the model's prediction results: the model's prediction results are corrected in real time, the prediction of gas diffusion paths is optimized to make them more realistic, and the accuracy of laboratory environmental safety is improved.

[0161] Furthermore, the step of correcting the prediction results using the Kalman filtering technique includes:

[0162] System state model:

[0163] The core of the Kalman filter model is the prediction and updating of system states, such as gas concentration and wind speed. The system state model describes how the current system state is calculated.

[0164] ;

[0165] in:

[0166] System status, including gas concentration, wind speed, fluid velocity, and diffusion coefficient;

[0167] The state transition matrix represents the dynamic change from the previous state to the current state. It is calculated by combining the Navier-Stokes equations and the diffusion-convection equations with the gas diffusion process in the laboratory, reflecting the influence of laboratory air flow, gas diffusion, temperature and humidity on gas diffusion.

[0168] : Control matrix, representing the effect of control inputs on the system state;

[0169] The wind speed adjustment is controlled in real time by the laboratory's wind speed control system and is affected by temperature and humidity.

[0170] Process noise represents the uncertainty and external disturbances in the model; set according to the results.

[0171] The effects of temperature and humidity on the system:

[0172] ;

[0173] Temperature, obtained through a temperature sensor;

[0174] Humidity, obtained through a humidity sensor;

[0175] Reference wind speed, i.e., wind speed under reference conditions;

[0176] , , : Adjustment coefficient, adjust automatically based on the results;

[0177] Observation equation:

[0178] The observation equation links the system state with the sensor's observation data. Through the observation equation using Kalman filtering, temperature, humidity, and gas concentration data are applied to the system state update process.

[0179] ;

[0180] in:

[0181] Observations are real-time measurement data obtained through sensors.

[0182] The observation matrix describes the system state, such as gas concentration and wind speed, and the relationship between these and the observed values. It also adjusts the predicted gas concentration based on changes in temperature and humidity.

[0183] Observation noise represents the measurement error of the sensor and should be adjusted according to the actual situation.

[0184] The effects of temperature and humidity:

[0185] Temperature and humidity affect gas diffusion velocity D and wind speed. The change in gas concentration is directly affected by the observation matrix in the observation equation. It will dynamically adjust according to temperature and humidity to ensure that the predicted gas concentration matches the actual measured value;

[0186] Kalman filter prediction steps:

[0187] Predict the system state at the next time step using the state transition matrix and the control input matrix;

[0188] ;

[0189] in:

[0190] The predicted system state includes gas concentration, wind speed, and diffusion coefficient.

[0191] State estimate from the previous moment;

[0192] Application of diffusion-convection equations in the prediction phase:

[0193] In the prediction phase, the solution to the diffusion-convection equation (the gas diffusion path and concentration distribution) affects the prediction of the system state. Changes in temperature and humidity affect the gas diffusion model, and thus affect the concentration prediction.

[0194] Kalman filter update steps:

[0195] By fusing the prediction results with the actual observation data, a more accurate state estimate can be obtained;

[0196] ;

[0197] in:

[0198] Updated system state estimate;

[0199] Kalman gain is a weighted measure of the difference between predicted and observed values.

[0200] : Residual, set according to the gas diffusion path calculated by the diffusion-convection equation and the influence of temperature and humidity on the diffusion coefficient, represents the difference between the actual observed value and the predicted value;

[0201] Relationship between diffusion-convection equations and Kalman gain:

[0202] The gas diffusion path calculated using the diffusion-convection equation and the influence of temperature and humidity on the diffusion coefficient determine the residuals in the Kalman filter. If the gas concentration is significantly affected by changes in temperature and humidity, the Kalman gain will be dynamically adjusted to optimize the concentration estimation.

[0203] Covariance update:

[0204] Reflecting the uncertainty of system state estimation, the prediction accuracy is gradually improved by updating the covariance matrix, and the decision to continue optimization is made based on the confidence level.

[0205] ;

[0206] The updated covariance matrix represents the confidence level of the current state estimate.

[0207] : The covariance matrix in the prediction stage, representing the confidence level of the predicted values.

[0208] The relationship between temperature, humidity and covariance matrix:

[0209] Temperature and humidity affect the diffusion coefficient and wind speed, thus influencing the diffusion path and flow characteristics of gas concentration. During covariance update, changes in temperature and humidity affect the estimation uncertainty through dynamic adjustments to the diffusion coefficient and wind speed, optimizing the accuracy of state estimation and improving prediction accuracy.

[0210] S4. Adjust the laboratory wind speed according to the optimized gas diffusion path to obtain the wind speed adjustment result.

[0211] In this embodiment, the step of adjusting the laboratory wind speed includes:

[0212] Real-time monitoring of environmental data via sensors: Based on the gas diffusion path optimized in step S3, the wind speed in the laboratory is adjusted according to the real-time monitoring data.

[0213] The gas concentration is calculated and judged based on the automated control algorithm: the gas concentration in the laboratory is calculated based on real-time monitored environmental data and it is judged whether the concentration exceeds the standard.

[0214] Based on the judgment results, the wind speed is automatically adjusted through the wind speed regulation system: when the gas concentration exceeds the standard in certain areas, the system automatically adjusts the wind speed to increase the ventilation volume, thereby accelerating the emission of gas.

[0215] By adjusting the wind speed, the gas concentration in the laboratory is kept within a safe range to prevent gas from accumulating in local areas.

[0216] S5. Based on the wind speed adjustment results, gas concentration is controlled to obtain the wind speed control results.

[0217] In this embodiment, the steps for controlling gas concentration include:

[0218] Relationship between gas concentration and wind speed:

[0219] Changes in wind speed directly affect the diffusion rate of gases. The higher the wind speed, the lower the gas concentration. If the wind speed is too low, the gas will stagnate and the gas concentration will increase.

[0220] ;

[0221] in:

[0222] Gas concentration, obtained through a gas sensor;

[0223] Air velocity, obtained through a flow meter;

[0224] The diffusion coefficient of a gas is estimated based on the type of gas measured by a gas sensor and environmental factors.

[0225] By adjusting the wind speed, the airflow velocity is changed. This changes the diffusion rate of the gas concentration, thus adjusting the gas concentration.

[0226] Temperature and humidity affect the diffusion coefficient and wind speed, which in turn affect the diffusion path and flow characteristics of gas concentration. By dynamically adjusting these parameters through Kalman filtering, the prediction of diffusion path and concentration distribution can be optimized.

[0227] The goal of wind speed regulation:

[0228] Real-time adjustment: The wind speed is adjusted in real time based on the data monitored by the gas concentration sensor;

[0229] Feedback control: By combining gas concentration data provided by sensors and using feedback control algorithms, the gas concentration in the laboratory is optimized by real-time monitoring and adjustment of wind speed;

[0230] Control process:

[0231] Sensor monitoring: The gas concentration inside the fume hood is continuously monitored by a gas concentration sensor, and fluctuations in the gas concentration are fed back to the control system via sensor signals;

[0232] Concentration vs. Safety Threshold Comparison: The real-time monitored gas concentration is compared with the set safety concentration threshold to determine whether it exceeds the limit;

[0233] Wind speed regulation strategy: The system dynamically adjusts the wind speed according to the degree to which the gas concentration deviates from the safe threshold;

[0234] Adjustment strategy:

[0235] Fuzzy control: The fuzzy control rules are used to adjust the wind speed based on the deviation between the gas concentration and the safety threshold and the rate of change of the error. For example, when the gas concentration is high, the wind speed increases, and when the gas concentration is low and stable, the wind speed decreases.

[0236] By using gas concentration control methods, the fume hood speed can be automatically adjusted to maintain a safe laboratory environment when the gas concentration changes.

[0237] S6. Based on the wind speed control results and safety thresholds, an alarm and response mechanism is implemented to obtain alarm information and wind speed data.

[0238] In this embodiment, the method for implementing the alarm and response mechanism includes:

[0239] Set safety thresholds; determine gas concentration to trigger alarms and take emergency measures.

[0240] The safety threshold represents the acceptable upper limit for various harmful gases in a laboratory environment. After adjusting the fan speed, the system will determine whether the preset safety threshold has been exceeded based on the gas concentration data. If the gas concentration exceeds the safety threshold, the system will trigger a safety alarm and immediately take emergency measures, such as further increasing the fan speed or shutting down some experimental equipment, to avoid a safety accident.

[0241] During wind speed adjustment, the system automatically adjusts based on the deviation between gas concentration and safety threshold, and triggers an alarm mechanism through an algorithm. By combining the relationship between wind speed adjustment and gas concentration changes in step S5, the system's response to excessive gas concentrations in the laboratory is optimized.

[0242] The alarm mechanism formula is as follows:

[0243] ;

[0244] in:

[0245] C(t) is the gas concentration;

[0246] C threshold It is a preset safety threshold.

[0247] S7. Based on alarm information and wind speed data, perform wind speed optimization and fault diagnosis to obtain optimized data.

[0248] In this embodiment, the method for wind speed optimization and fault diagnosis includes:

[0249] By using machine learning algorithms, the relationship between different gas leakage scenarios and wind speed regulation can be learned, and future wind speed regulation strategies can be optimized.

[0250] By using data analysis and fault diagnosis, the system's ability to cope with laboratory gas diffusion and wind speed regulation can be improved, and system performance can be optimized.

[0251] The machine learning steps are as follows:

[0252] Regression analysis: Establish the relationship between gas concentration and wind speed adjustment, and train a regression model based on historical data to predict the required wind speed adjustment value under different gas leakage conditions;

[0253] Support Vector Machine Regression (SVR): Models nonlinear relationships and optimizes wind speed regulation. Factors such as gas concentration, temperature, and humidity are input into the SVR model, and the optimal wind speed regulation is output.

[0254] Cluster analysis (K-means): Identifies different gas leak patterns and optimizes wind speed regulation strategies. Through clustering algorithms, it automatically discovers the distribution patterns of gas concentration and wind speed in different gas leak scenarios. It can be used to identify common gas leak types and design different wind speed regulation strategies for these types.

[0255] Principal Component Analysis (PCA): Dimensionality reduction, extraction of key influencing factors, and improvement of regulation efficiency. By analyzing variables such as gas concentration, temperature, humidity, and wind speed, PCA identifies the principal components affecting gas diffusion, thereby simplifying model input and improving wind speed regulation efficiency.

[0256] Anomaly detection: Real-time fault diagnosis ensures normal system operation. By training models to identify "normal" wind speed adjustment patterns in historical data, an alarm will be triggered once abnormal data (such as a sudden drop in wind speed or a sharp increase in gas concentration) is detected.

[0257] S8. Generate environmental safety reports and adjust wind speed control strategies based on optimized data.

[0258] In this embodiment, a detailed laboratory gas environment safety report is generated based on the optimization data from step S7. The report includes gas concentration change trends, historical wind speed adjustment records, alarm information, and emergency response measures. Furthermore, based on historical data and optimization results, the wind speed control strategy is adjusted to further improve the system's safety and response speed.

[0259] Example 2:

[0260] This embodiment also provides a computer device applicable to a variable air volume control method for fume hoods based on laboratory environmental monitoring, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the variable air volume control method for fume hoods based on laboratory environmental monitoring as proposed in the above embodiment.

[0261] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a variable air volume control method for fume hoods based on laboratory environmental monitoring as proposed in the above embodiments.

[0262] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0263] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0264] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0265] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0266] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0267] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring, characterized in that, Includes the following steps: S1. Deploy sensors and collect laboratory data; S2. Establish a basic fluid dynamics model for gas flow and diffusion in the laboratory; S3. Predict the gas diffusion path to obtain the optimized gas diffusion path; The steps for predicting gas diffusion paths include: Input real-time environmental data; Using the fluid dynamics model established in step S2, predict the diffusion path and concentration distribution of the gas in the laboratory; Kalman filtering is used to correct the model's prediction results; The Kalman filtering technique includes: System state model: The system state model describes how the current system state is calculated; ； in: System status, including gas concentration, wind speed, fluid velocity, and diffusion coefficient; The state transition matrix represents the dynamic change from the previous state to the current state. It is calculated by combining the Navier-Stokes equations and the diffusion-convection equations with the gas diffusion process in the laboratory, reflecting the influence of laboratory air flow, gas diffusion, temperature and humidity on gas diffusion. : Control matrix, representing the effect of control inputs on the system state; The wind speed adjustment is controlled in real time by the laboratory's wind speed control system and is affected by temperature and humidity. Process noise represents the uncertainty and external disturbances in the model; set according to the results. Observation equation: Data from temperature, humidity, and gas sensors is used in the system status update process; ； in: Observations are real-time measurement data obtained through sensors. The observation matrix describes the system state, including gas concentration, wind speed, and the relationship between these and the observed values. It also adjusts the predicted gas concentration based on changes in temperature and humidity. Observation noise represents the measurement error of the sensor and should be adjusted according to the actual situation. Kalman filter prediction steps: Through the state transition matrix and control matrix Make a prediction and output the system state at the next moment. ； in: The predicted system state includes gas concentration, wind speed, and diffusion coefficient. State estimate from the previous moment; Kalman filter update steps: By fusing the prediction results with the actual observation data, a more accurate state estimate can be obtained; ； in: Updated system state estimate; Kalman gain is a weighted measure of the difference between predicted and observed values. : Residual, set according to the gas diffusion path calculated by the diffusion-convection equation and the influence of temperature and humidity on the diffusion coefficient, represents the difference between the actual observed value and the predicted value; Covariance update: Reflecting the uncertainty of system state estimation, the confidence level obtained by updating the covariance matrix is ​​used to gradually improve the prediction accuracy, and the decision to continue optimization is made based on the confidence level. S4. Adjust the laboratory wind speed according to the optimized gas diffusion path to obtain the wind speed adjustment result; S5. Based on the wind speed adjustment results, control the gas concentration to obtain the wind speed control results; S6. Based on the wind speed control results and safety thresholds, an alarm and response mechanism is implemented to obtain alarm information and wind speed data. S7. Based on alarm information and wind speed data, perform wind speed optimization and fault diagnosis to obtain optimized data; S8. Generate environmental safety reports and adjust wind speed control strategies based on optimized data.

2. The method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The types of sensors deployed and the laboratory data collected in S1 include: Temperature sensor, humidity sensor, pressure sensor, flow meter, gas sensor; Airflow velocity, gas concentration, temperature, humidity, fluid density, gas type, gas pressure, fluid viscosity, and diffusion coefficient.

3. The method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The fluid dynamics model in S2 includes: Navier-Stokes Equation: This equation describes the flow of air in space and time and is used to simulate gas flow processes. ； in: ：流体密度，单位为 ，受实验室环境温度和压力影响，根据S1中获得的数据计算获得； : Airflow velocity vector, in m / s, measured by an up-spinning sphere gas velocity meter; : Rate of change of velocity over time; Gas pressure gradient, measured in Pa / m, represents the rate of change of pressure in space and is obtained by a pressure sensor. Fluid viscosity, in Pa·s, is obtained by consulting relevant literature based on the type of gas measured by the gas sensor. The second spatial derivative of the velocity field; Representation: External force, obtained through measurement, used to represent gravity and surface friction. Solving the equation, we get: The velocity field v(x,t) of the airflow in the laboratory represents the magnitude and direction of the airflow velocity at each point x and at each time t; The pressure field p(x,t) represents the magnitude of the gas pressure at each point x and at each time t. By analyzing the speed and direction of airflow and the magnitude of gas pressure, the diffusion path of the gas can be determined, thereby simulating the gas flow process. Diffusion-convection equations: This equation is used to describe the propagation and diffusion behavior of gases in fluids; ； in: ：气体浓度，单位为 ，表示空间位置(x,y,z)和时间t上的气体浓度，通过气体传感器测得； Gas concentration gradient: This represents the variation of gas concentration in space, and its magnitude is equal to the rate of change of gas concentration. Gas diffusion coefficient, in meters (m) 2 / s, estimated based on the type of gas measured by the gas sensor and environmental factors; The Laplace operator for gas concentration describes the second-order rate of change of gas concentration in space, reflecting how gas flows from a high-concentration region to a low-concentration region through diffusion. Solving the equations yields the temporal and spatial distribution of gas concentration in the laboratory. By observing changes in gas concentration, the diffusion path of the gas is determined; the greater the gas concentration gradient, the faster the gas diffusion.

4. The method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The steps for adjusting the laboratory wind speed in S4 include: Real-time monitoring of environmental data via sensors; The gas concentration is calculated and judged based on the automated control algorithm; Based on the judgment results, the wind speed is automatically adjusted through the wind speed regulation system.

5. The method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The gas concentration control in S5 includes: Relationship between gas concentration and wind speed: Changes in wind speed directly affect the diffusion rate of gases. The higher the wind speed, the lower the gas concentration. If the wind speed is too low, the gas will stagnate and the gas concentration will increase. ； in: Gas concentration, obtained through a gas sensor; Air velocity, obtained through a flow meter; The diffusion coefficient of a gas is estimated based on the type of gas measured by a gas sensor and environmental factors. By adjusting the wind speed, the airflow velocity is changed. This changes the diffusion rate of the gas concentration, thus adjusting the gas concentration. The goal of wind speed regulation: Real-time adjustment: The wind speed is adjusted in real time based on the data monitored by the gas concentration sensor; Feedback control: By combining gas concentration data provided by sensors and using feedback control algorithms, the gas concentration in the laboratory is optimized by real-time monitoring and adjustment of wind speed; Control process: Sensor monitoring: The gas concentration inside the fume hood is continuously monitored by a gas concentration sensor, and fluctuations in the gas concentration are fed back to the control system via sensor signals; Concentration vs. Safety Threshold Comparison: The real-time monitored gas concentration is compared with the set safety concentration threshold to determine whether it exceeds the limit; Wind speed regulation strategy: The system dynamically adjusts the wind speed according to the degree to which the gas concentration deviates from the safe threshold; Adjustment strategy: Fuzzy control: The wind speed is adjusted based on the deviation of the gas concentration from the safety threshold and the rate of change of the error, using fuzzy control rules.

6. The method for variable air volume control of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The methods for implementing the alarm and response mechanism in S6 include: Set safety thresholds; determine gas concentration to trigger alarms and take emergency measures.

7. The method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The methods for wind speed optimization and fault diagnosis in S7 include: By using machine learning algorithms, the relationship between different gas leakage scenarios and wind speed regulation can be learned, and future wind speed regulation strategies can be optimized.

8. The method for controlling the variable air volume of a fume hood based on laboratory environmental monitoring according to claim 1, characterized in that, The environmental safety report in S8 includes: Based on the optimized data, a detailed laboratory gas environment safety report is generated, including gas concentration change trends, historical wind speed adjustment records, alarm information, and emergency response measures, enabling laboratory managers to optimize wind speed adjustment strategies based on the detailed environmental safety report.

Images