A laboratory exhaust gas induced high-altitude jet fan control system

Abstract

This invention belongs to the field of fan control technology. It provides a laboratory exhaust gas-induced high-altitude jet fan control system, comprising: a multi-source data acquisition module for real-time acquisition of multi-dimensional time-series data related to laboratory exhaust gas emission safety, including fan operating parameters, building environment parameters, exhaust gas source equipment status parameters, and meteorological environment parameters; and a predictive maintenance and early warning module based on the multi-dimensional time-series data. By integrating multi-source data perception, chronic risk trend prediction, system vulnerability assessment based on digital twins, and graded resilience control strategies, a closed loop of "perception-prediction-assessment-decision-execution" is constructed. This achieves early identification, proactive early warning, and adaptive control of coupled risks between "equipment-building-environment-personnel," thereby enhancing the proactive safety capability to prevent toxic exhaust gases from entering the breathing zone of personnel.

Description

Technical Field

[0001] This invention belongs to the field of fan control technology, specifically a laboratory exhaust gas induced high-altitude jet fan control system. Background Technology

[0002] Laboratory exhaust gas induced high-altitude jet fan is a powerful fan specifically designed to forcibly transport harmful exhaust gases from the laboratory to high altitudes in the form of high-speed, concentrated, and directional jets for dilution and diffusion. Its core purpose is to ensure that pollutants are sufficiently diluted to below safe concentrations by the atmosphere before reaching the ground breathing zone through "high-altitude emission," thereby protecting the health of people around the laboratory. However, the control of laboratory-induced high-altitude jet fans generally adopts a threshold alarm mechanism based on the fan's own operating parameters (such as start / stop, current, and single-point wind speed). This is essentially a passive and isolated response control method, which has the following defects in actual operation: it cannot detect the chronic degradation of fan performance (such as impeller corrosion), changes in building pressure distribution, adverse meteorological conditions, and the synergistic effects of the source ventilation equipment status, resulting in complete failure to detect systemic coupling risks (such as backflow of exhaust gas due to building negative pressure imbalance or leakage through hidden channels); secondly, due to the lack of overall vulnerability assessment of "equipment-building-environment-personnel", the existing system can only alarm after obvious failure (such as fan shutdown) occurs, and cannot achieve early prediction and warning of risks; Therefore, the present invention provides a control system for a laboratory exhaust gas induced high-altitude jet fan. Summary of the Invention

[0003] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0004] The technical solution adopted by this invention to solve its technical problem is: a laboratory exhaust gas induced high-altitude jet fan control system, comprising: Multi-source data acquisition module: Real-time acquisition of multi-dimensional time-series data related to laboratory exhaust gas emission safety, including: fan operating parameters, building environment parameters, exhaust gas source equipment status parameters, and meteorological environment parameters; Predictive maintenance early warning module: Based on multi-dimensional time series data, the module uses a chronic risk trend prediction algorithm to perform long-term trend analysis on the core performance indicators of the laboratory jet fan system, identify whether the core performance indicators have reached the performance degradation early warning line, and generate a predictive maintenance early warning if they have. Vulnerability assessment module: It integrates multi-maintenance time-series data and predictive maintenance early warning, inputs them into the vulnerability assessment model, and outputs assessment indicators that reflect the comprehensive risk of current and future exhaust gas intrusion into the breathing zone of personnel; Among them, the vulnerability assessment model is a simulation prediction model based on the digital twin of the building and ventilation system; Control strategy execution module: Obtain the risk level corresponding to the assessment indicators, match and execute the corresponding dynamic control instructions.

[0005] The beneficial effects of this invention are as follows: This invention integrates multi-source data perception, chronic risk trend prediction, system vulnerability assessment based on digital twins, and hierarchical resilience control strategies to construct a closed loop of "perception-prediction-assessment-decision-execution," enabling early identification, forward-looking warning, and adaptive control of coupled risks in "equipment-building-environment-personnel," thereby enhancing the proactive safety capability to prevent toxic exhaust gases from entering the breathing zone of personnel. This invention uses a chronic risk trend prediction algorithm to perform long-term trend analysis on the core performance indicators of wind turbines. Before the equipment performance suffers a substantial failure, it can identify the chronic decline trend of efficiency in the early stage and output an early warning signal with a confidence level. This enables maintenance decisions to shift from experience-based judgment to data-based management, optimize the allocation of maintenance resources, and advance maintenance intervention points. This invention constructs a high-fidelity simulation model based on digital twins of building and ventilation systems, integrates multi-source real-time data and equipment performance degradation early warning, dynamically simulates the waste gas diffusion process, and outputs quantitative comprehensive risk indicators (such as area exposure ratio, concentration exceedance intensity, and system toughness degradation degree), thereby achieving real-time, quantitative, and forward-looking vulnerability assessment of systemic coupling risks. Attached Figure Description

[0006] The invention will now be further described with reference to the accompanying drawings.

[0007] Figure 1 This is a modular architecture diagram of a laboratory exhaust gas induced high-altitude jet fan control system according to the present invention; Figure 2 This is a flowchart of the steps of a laboratory exhaust gas induced high-altitude jet fan control method according to the present invention; Figure 3 This is a front view of a laboratory exhaust gas induced high-altitude jet fan according to the present invention; Figure 4 This is a side view of a laboratory exhaust gas induced high-altitude jet fan according to the present invention. Detailed Implementation

[0008] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0009] Example 1

[0010] One of the core inventive points of this invention is that, in response to the shortcomings of the current technology, a laboratory exhaust gas-induced high-altitude jet fan control system is proposed. By integrating multi-source data sensing, equipment chronic risk trend prediction, system vulnerability dynamic assessment based on digital twins, and hierarchical resilience control strategies, a closed loop of "sensing-prediction-assessment-decision-execution" is constructed. This achieves forward-looking early warning and adaptive control of coupled risks of "equipment-building-environment-personnel", thereby improving the proactive safety capability to prevent toxic exhaust gases from entering the breathing zone of personnel. Please see Figure 1 As shown in the embodiment of the present invention, a laboratory exhaust gas induced high-altitude jet fan control system includes: Multi-source data acquisition module: Real-time acquisition of multi-dimensional time-series data related to laboratory exhaust gas emission safety. The multi-dimensional time-series data includes at least: fan operating parameters, building environment parameters, exhaust gas source equipment status parameters, and meteorological environment parameters. The multi-source data acquisition module is used to collect multi-dimensional time-series data related to laboratory exhaust gas emission safety in real time. Its execution process includes two stages: data acquisition and preprocessing. Fan operating parameters: acquired by sensors installed on the fan body for inducing high-altitude jet flow, including at least: real-time jet velocity at the fan outlet, operating current of the fan motor, frequency converter output frequency, fan bearing temperature and vibration amplitude. Building environment parameters: obtained through monitoring equipment deployed within the laboratory building, including at least: Key source status: real-time face velocity, operating window height, and exhaust valve opening of each laboratory fume hood and universal exhaust hood; Indoor safety environment: Concentration of volatile organic compounds, concentration of characteristic toxic gases, and pressure difference between the room and the corridor in the main operating area of ​​the laboratory and adjacent corridors; System pressure nodes: Static pressure values ​​at key nodes in the exhaust manifold; Status parameters of exhaust gas source equipment: obtained from laboratory environmental monitoring system or experimental equipment logs, used to correlate exhaust gas generation intensity, including start-stop status signals of experimental equipment involving the use of high-risk reagents, and occupancy status of fume hoods (such as infrared sensor signals). Meteorological environmental parameters: obtained through meteorological stations installed on the roof of buildings, including at least wind speed, wind direction, ambient temperature, relative humidity, and auxiliary wind speed monitoring data at a specific distance downwind of the building; The collected raw data is standardized to obtain standardized time-series data packets, including the following processing steps: Time synchronization and alignment: Aligning data streams with a uniform timestamp to ensure data time consistency; Outlier detection and cleaning: Statistical methods (such as the 3σ principle) are used to identify and remove abnormal data points caused by obvious sensor false alarms or communication errors; Missing value imputation: For time-series data missing due to short-term communication interruption, linear interpolation or forward filling method is used for reasonable imputation to ensure data continuity; Standardization and formatting: Normalize data of different dimensions (such as wind speed m / s, current A, concentration ppm) and convert them into a standard data format.

[0011] Predictive maintenance early warning module: Based on multi-dimensional time series data, the module uses a chronic risk trend prediction algorithm to perform long-term trend analysis on the core performance indicators of the laboratory jet fan system, identify whether the core performance indicators have reached the performance degradation early warning line, and generate a predictive maintenance early warning if they have. The predictive maintenance early warning module, based on multi-dimensional time-series data, uses a chronic risk trend prediction algorithm to conduct long-term trend analysis on the core performance indicators of the laboratory jet fan system. The specific execution process is as follows: Based on multidimensional time-series data, core performance indicators are calculated, including: dynamic performance coefficient and wind speed-frequency baseline curve offset. Furthermore, the calculation process of the dynamic efficiency coefficient is as follows: First, calculate the product of the fan operating current and the inverter output power, and then calculate the ratio of the real-time jet velocity at the fan outlet to the aforementioned product. The obtained ratio is the dynamic efficiency coefficient. It should be explained that the dynamic efficiency coefficient eliminates the normal changes in current caused by adjusting the air volume (changing the frequency). The long-term downward trend of this coefficient directly reflects the efficiency decline of the fan caused by impeller corrosion, fouling, or increased mechanical resistance. The calculation process of the wind speed-frequency reference curve offset is as follows: Under a fixed building back pressure condition, record the stable outlet wind speed corresponding to different frequency converter frequencies during historical normal periods to form a wind speed-frequency reference curve. The percentage deviation between the measured wind speed at the current frequency and the corresponding value on the reference curve is calculated in real time, which is the wind speed-frequency reference curve offset. It should be noted that an increasing trend in the offset of the wind speed-frequency reference curve indicates a degradation in system performance. Long-term trend analysis is performed based on the time series of the calculated dynamic efficiency coefficient and the offset of the wind speed-frequency reference curve to distinguish between short-term fluctuations and chronic decline. Further long-term trend analysis includes: moving average filtering analysis, trend slope analysis, and variability stability analysis; The variation stability analysis includes: dividing the time series of dynamic efficiency coefficients and the time series of wind speed-frequency baseline curve offset into continuous, non-overlapping data windows (e.g., weekly data as a data window), calculating the coefficient of variation of the data windows, and calculating the average coefficient of variation of the most recent M data windows as a confidence index for trend analysis. The coefficient of variation is the ratio of the standard deviation to the mean of the data within the data window, and is used to measure the degree of dispersion of the data relative to the mean. It should be noted that the higher the confidence index of trend analysis, the greater the discrete fluctuation of the data within the M data windows, and the lower the statistical certainty of the data based on moving average filtering and trend slope analysis. The moving average filtering analysis includes: performing moving average calculations on the time series of dynamic efficiency coefficients and the time series of wind speed-frequency reference curve offsets through a sliding time window (e.g., 30 days) to obtain the arithmetic mean of the data within each sliding time window, which is used as the filtered value at the center of the sliding time window. The smoothed trend line sequence of dynamic efficiency coefficients and the trend line sequence of wind speed-frequency reference curve offsets are then output. Trend slope analysis includes: preset analysis period, extract the smoothed dynamic efficiency coefficient trend line sequence and wind speed-frequency reference curve offset trend line sequence within the most recent analysis period, take time as independent variable, and take the smoothed dynamic efficiency coefficient trend line sequence and wind speed-frequency reference curve offset trend line sequence as dependent variable respectively, use the least squares method to perform linear regression, fit the corresponding straight line equation, and use it as the first straight line equation and the second straight line equation. Based on the fitted first and second line equations, the corresponding first trend slope and second trend slope are calculated respectively. A predictive maintenance early warning signal is generated when the following conditions are met simultaneously: Condition 1: The slope of the first trend is consistently negative and its absolute value is greater than the preset minimum significance slope, or the slope of the second trend (corresponding offset) is consistently positive and its absolute value is greater than the preset minimum significance slope. Condition 2: The moving average of the dynamic efficiency coefficient is lower than the corresponding dynamically set warning line, or the moving average of the wind speed-frequency reference curve offset is higher than the corresponding dynamically set warning line. It should be noted that the performance degradation warning line is set based on historical data. The performance degradation warning line includes the minimum significant slope corresponding to the first trend slope, the minimum significant slope corresponding to the second trend slope, the warning line corresponding to the moving average of the dynamic efficiency coefficient, and the warning line corresponding to the moving average of the wind speed-frequency reference curve offset. The setup process is as follows: Historical time-series data of core performance indicators (dynamic performance coefficient and wind speed-frequency baseline deviation) over a complete historical period (usually no less than 12 months) are extracted and analyzed. Moving average sequences are calculated as performance baselines, and fluctuation characteristics are statistically analyzed. The minimum significance slope threshold for the trend slopes of the two indicators is determined by analyzing the statistical distribution of historical trend slopes (taking the top 10% quantile of the absolute value). The warning line corresponding to the moving average of the two indicators is dynamically calculated and generated based on the historical baseline, offset by a certain multiple (usually 1.5 to 2.5 times) of the historical standard deviation in the direction of performance degradation. All warning thresholds can be updated periodically based on the latest long-term operating data to achieve adaptive adjustment. The confidence level of the output warning signal is determined based on trend analysis confidence indexes, including: If the confidence index is lower than the preset threshold, it will be marked as a high confidence warning, indicating that the trend judgment is reliable; If the confidence index is higher than the preset threshold, it will be marked as a low confidence warning. It is recommended to combine it with other means such as equipment inspection for comprehensive confirmation. Among them, the threshold setting is: by calculating the statistical distribution of the confidence index of the trend analysis of the system in each time window during the historical normal operation cycle (usually no less than 12 months), the preset threshold is set as the upper quantile value (75th percentile) of the historical distribution. It should be noted that the output of the predictive maintenance early warning signal includes: when triggered by the deteriorating trend of the dynamic efficiency coefficient or the wind speed-frequency reference curve deviation, the early warning category is defined as an efficiency degradation early warning, indicating that the root cause of the early warning is the performance degradation of the wind turbine equipment itself; the confidence level is directly adopted from the level result generated by the aforementioned confidence index based on trend analysis, and its value is either a high confidence warning or a low confidence warning, which is used to characterize the reliability of the data quality and trend judgment on which this early warning is based.

[0012] This module uses a chronic risk trend prediction algorithm to identify the chronic decline trend of wind turbine efficiency in the early stages before the wind turbine performance suffers a substantial failure, thus significantly advancing the maintenance intervention point and transforming passive response into proactive defense. The output warning signals come with clear evidence of performance degradation (trend slope, horizontal deviation) and confidence level, enabling maintenance decisions to shift from experience-based judgment to data-driven management and optimize the allocation of maintenance resources. This provides input to the vulnerability assessment model, enabling the calculation of system security risks to fully consider the performance degradation of the equipment itself, thereby improving the accuracy and foresight of the overall risk assessment.

[0013] Vulnerability assessment module: It integrates multi-maintenance time-series data and predictive maintenance early warning, inputs them into the vulnerability assessment model, and outputs assessment indicators that reflect the comprehensive risk of current and future exhaust gas intrusion into the breathing zone of personnel; Among them, the vulnerability assessment model is a simulation prediction model based on the digital twin of the building and ventilation system; The process of constructing the vulnerability assessment model is as follows: Based on the building information model of the target laboratory, the ventilation system design drawings, and the factory performance curve of the induced high-altitude jet fan, a static digital twin containing the three-dimensional geometry of the building, the topology of the ventilation network, and the equipment parameters is constructed in the simulation platform. After the system installation and commissioning are completed or after major overhaul, under typical operating conditions (such as design air volume and normal meteorological conditions), the multi-source data acquisition module is called to collect a set of benchmark operating data (including pressure difference in various areas of the building, static pressure in the exhaust duct, and velocity field of the roof jet). By iteratively adjusting the local drag coefficient and boundary condition parameters in the digital twin, the error between the simulation output and the above-mentioned benchmark measured data is brought to a preset range (such as ±5%), thereby completing the initial calibration of the model and establishing a high-fidelity simulation benchmark that can accurately reflect the system design performance. The real-time input vector acquisition process for the vulnerability assessment model is as follows: Acquire standardized time-series data packets from the multi-source data acquisition module, as well as predictive maintenance warning signals and their associated confidence levels from the predictive maintenance warning module; Furthermore, the input processing of predictive maintenance early warning signals includes: analyzing the signal; if it is an efficiency degradation early warning, then based on the confidence level (high confidence warning or low confidence warning), the performance retention coefficient is calculated based on the current moving average of the dynamic efficiency coefficient, the corresponding performance degradation early warning line value, and the historical health benchmark value. Then, the benchmark maximum jet velocity of the wind turbine in the vulnerability assessment model is reduced by multiplying the benchmark maximum jet velocity with the performance retention coefficient to obtain the equipment equivalent performance parameters used in this simulation. The performance retention coefficient is calculated as follows: First, the difference between the current moving average of the dynamic performance coefficient and the corresponding performance degradation warning line value is calculated. Then, the difference between the historical health benchmark value and the corresponding performance degradation warning line value is calculated. Finally, the two differences are compared to obtain the performance retention coefficient. Key real-time parameters are extracted from the data packets to form an environmental state vector, including: real-time differential pressure sequence of key areas of the building, static pressure of the exhaust duct, roof wind speed, wind direction angle, and real-time total exhaust volume calculated by summing the opening of exhaust valves of all fume hoods; The simulation process is executed based on real-time input vectors and a vulnerability assessment model. Using real-time parameters as boundary conditions, computational fluid dynamics and pollutant diffusion simulation are run to simulate the diffusion process of exhaust gas from the emission outlet to the periphery of the building, and output the pollutant concentration distribution field at the height of the breathing zone (1.5-1.8m). In the pollutant concentration distribution field, identify all grids with concentrations exceeding the preset safety limit, calculate the total area of ​​the exceeding area and the maximum concentration exceeding ratio (the ratio of the maximum value in the pollutant concentration distribution field to the preset safety limit), and simultaneously overlay building BIM information to determine whether the exceeding area overlaps with the preset densely populated area or fresh air intake. In the vulnerability assessment model, a preset extreme adverse disturbance condition is automatically applied (e.g., simulating a calm wind with the roof wind speed dropping to 0.5 m / s and the wind direction perpendicular to the main facade of the building), and the system's performance in response to this disturbance is simulated under the design baseline performance and the current equivalent performance. Using the effective height of emissions under the design baseline as a reference, the effective height under the current equivalent performance is calculated, and then the rate of decrease in immunity due to performance degradation is obtained; The difference between the effective emission height under the design baseline and the effective height under the current equivalent performance is calculated, and the ratio of the difference to the effective emission height under the design baseline is the disturbance immunity reduction rate. The process of calculating the comprehensive risk value is as follows: Calculate the ratio of the area exceeding the standard to the total area of ​​the assessment area as the area exposure ratio; Logarithmic transformation of the maximum concentration exceedance ratio smooths out extreme values, yielding the transformed maximum concentration exceedance ratio. The transformation formula is as follows: ;in, This represents the maximum concentration exceeding the standard ratio after conversion. The percentage of the maximum concentration exceeding the standard; The geometric mean method was used to calculate the comprehensive risk value, which involved multiplying the three core risk components—area exposure rate, concentration exceedance intensity, and system resilience attenuation—and then taking the cube root of the product to obtain the comprehensive risk value. It should be noted that a very small positive constant (e.g., ...) is added to the calculation of the system's resilience degradation. This ensures that the mathematical calculations remain valid when the system's resilience degradation is zero. The inherent characteristic of the geometric mean method is that when any one of the three values ​​increases significantly, the final comprehensive risk value will be directly and significantly increased. This naturally reflects the weakest link effect among risk factors, that is, the overall risk level is dominated by the weakest link, which is consistent with the inherent coupling law of safety risks in complex systems.

[0014] This module integrates predictive maintenance warnings (such as equipment efficiency degradation) and predicts future risk performance under adverse conditions based on digital twin simulation, enabling early identification and forward-looking assessment of potential risks and significantly advancing the safety defense line. Based on Building Information Modeling (BIM) and ventilation system design, a calibrable digital twin is constructed, and combined with real-time equipment performance data (dynamically reducing fan capacity through performance retention factors), the model can reflect the actual and potentially degraded operating status of the system with high fidelity, thus improving the accuracy of risk assessment. By integrating multi-source data, digital twin simulation, and dynamic performance evaluation, a real-time, quantitative, and forward-looking vulnerability assessment of systemic coupling risks in laboratory exhaust gas high-altitude emission control is conducted.

[0015] Control strategy execution module: Obtains the risk level corresponding to the assessment indicators, matches and executes the corresponding dynamic control instructions; The execution process of the control strategy execution module is as follows: Obtain a comprehensive risk value and map the corresponding risk level based on the state classification threshold; The status classification thresholds include early warning thresholds and emergency thresholds, which divide the risk level into normal monitoring status, enhanced control status, and emergency avoidance status. The early warning thresholds and emergency thresholds are set based on long-term (usually no less than 12 months) historical operating data of the system, statistically analyzing the distribution characteristics of the comprehensive risk value under typical safe operating conditions. The early warning thresholds are set in the high percentile range of the distribution (such as the 85th-90th percentile) to identify early signals of performance degradation or increased risk. The emergency thresholds are mainly based on the requirements of safety regulations for personnel exposure limits. Extreme adverse scenarios are simulated through digital twin simulation to deduce the critical risk value that can cause the concentration of respiratory zone to exceed the standard instantaneously, and the thresholds are calibrated and determined in combination with expert experience. If the overall risk value is less than or equal to the warning threshold, the current operational risk is determined to be controllable, and the system is in a normal monitoring state. Regular data monitoring can continue. If the overall risk value is greater than the warning threshold and less than or equal to the emergency threshold, the current operational risk is determined to be increased, and an enhanced control command is activated to strengthen the control status. If the overall risk value is greater than the emergency threshold, the current operation is determined to be at high risk, and an emergency evacuation state is activated to prioritize personnel safety. For the aforementioned enhanced control and emergency evacuation states, the preset control command set includes at least: Under enhanced regulation: the core objectives are to improve system emission capacity, suppress source risks, and balance building pressures; Execution logic: Fan lifting instruction: Increase the output frequency of the inverter of the induced high-altitude jet fan to increase the jet velocity and effective discharge height; Source linkage command: Send an increased risk signal to the laboratory environment monitoring system, which can automatically execute: issue audible and visual alerts for fume hoods that are not in an effective ventilation state; push a pause suggestion to the operator interface for ongoing high-risk experimental operations that can be safely paused; Pressure compensation instruction: Fine-tune the airflow of the laboratory make-up air system to stabilize or restore the negative pressure gradient in critical areas; Confidence weighting: If the confidence level of the predictive maintenance warning that triggers this state is low, it will be automatically suggested to enhance it to a dialog box that requires manual confirmation, and the wind turbine upgrade range will be based on a conservative value; In an emergency evacuation situation: the core objective is to immediately stop the spread of risk and ensure the safety of personnel; Execution logic: Fan limit operation command: Control the fan frequency converter to operate at the highest permissible safe frequency or rated power; Source intervention command: Send the highest priority command to all related laboratory environmental monitoring systems, requiring immediate execution of the preset safety shutdown or maximum exhaust mode; Personnel alarm and evacuation guidance: Automatically triggers building-level audible and visual alarms, and pushes emergency warnings and evacuation guidance through public broadcasts, displays and mobile terminals. It can also be linked with the access control system to release escape routes. Background emergency notification: Automatically sends emergency notifications containing risk indicators and actions already performed to a pre-defined list of safety responsible persons.

[0016] Example 2

[0017] Based on the same inventive concept as the laboratory exhaust gas induced high-altitude jet fan control system in the foregoing embodiments, such as Figure 2 As shown, this application provides a method for controlling a laboratory exhaust gas induced high-altitude jet fan, specifically including the following steps: Step 1: Real-time collection of multi-dimensional time-series data related to laboratory exhaust gas emission safety. The multi-dimensional time-series data should include at least: fan operating parameters, building environment parameters, exhaust gas source equipment status parameters, and meteorological environment parameters. Step 2: Based on multi-dimensional time series data, a long-term trend analysis of the core performance indicators of the laboratory jet fan system is conducted using a chronic risk trend prediction algorithm to identify whether the core performance indicators have reached the performance degradation warning line. If they have, a predictive maintenance warning is generated. Step 3: Integrate multi-maintenance time-series data and predictive maintenance early warnings, input them into the vulnerability assessment model, and output assessment indicators that reflect the comprehensive risk of current and future exhaust gas intrusion into the breathing zone of personnel; Among them, the vulnerability assessment model is a simulation prediction model based on the digital twin of the building and ventilation system; Step 4: Obtain the risk level corresponding to the assessment indicators, match and execute the corresponding dynamic control instructions.

[0018] Example 3

[0019] Based on the foregoing embodiments, such as Figure 3 and Figure 4 As shown, this application also provides a laboratory exhaust gas induced high-altitude jet fan, comprising: The fan body includes an induced jet fan body, a drive motor, a frequency converter, and a fan mounting base; the frequency converter is electrically connected to the drive motor and is used to adjust the fan speed and jet velocity. It also includes: an integrated sensing unit, fixedly installed at key locations on the fan body and adjacent air ducts, for real-time acquisition of fan operating parameters and local environmental parameters; the integrated sensing unit includes at least: A wind speed sensor installed at the fan outlet is used to measure the real-time jet velocity. A current sensor connected in series in the power supply circuit of the drive motor is used to measure the motor's operating current; Vibration sensors installed in the fan bearing housing are used to monitor the vibration amplitude of the fan. Temperature sensors installed on the fan bearings and motor housing are used to monitor operating temperature; Static pressure probes installed at the fan inlet or near key nodes of the exhaust manifold are used to monitor the system static pressure.

[0020] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A control system for a laboratory exhaust gas induced high-altitude jet fan, characterized in that: include: Multi-source data acquisition module: Real-time acquisition of multi-dimensional time-series data related to laboratory exhaust gas emission safety, including: fan operating parameters, building environment parameters, exhaust gas source equipment status parameters, and meteorological environment parameters; Predictive maintenance early warning module: Based on multi-dimensional time series data, the module uses a chronic risk trend prediction algorithm to perform long-term trend analysis on the core performance indicators of the laboratory jet fan system, identify whether the core performance indicators have reached the performance degradation early warning line, and generate a predictive maintenance early warning if they have. Vulnerability assessment module: It integrates multi-maintenance time-series data and predictive maintenance early warning, inputs them into the vulnerability assessment model, and outputs assessment indicators that reflect the comprehensive risk of current and future exhaust gas intrusion into the breathing zone of personnel; Among them, the vulnerability assessment model is a simulation prediction model based on the digital twin of the building and ventilation system; Control strategy execution module: Obtain the risk level corresponding to the assessment indicators, match and execute the corresponding dynamic control instructions.

2. The laboratory exhaust gas induced high-altitude jet fan control system according to claim 1, characterized in that: The predictive maintenance early warning module includes: Based on multidimensional time-series data, core performance indicators are calculated, including: dynamic performance coefficient and wind speed-frequency baseline curve offset. Long-term trend analysis was performed on the time series of the calculated dynamic efficiency coefficient and the offset of the wind speed-frequency reference curve, including: moving average filtering analysis, trend slope analysis, and variability stability analysis. The predictive maintenance early warning signal is generated when the following conditions are met simultaneously: The trend slope of the dynamic efficiency coefficient is consistently negative and its absolute value is greater than the preset minimum significant slope, or the trend slope of the wind speed-frequency reference curve offset is consistently positive and its absolute value is greater than the preset minimum significant slope. The moving average of the dynamic efficiency coefficient is lower than the corresponding dynamically set warning line, or the moving average of the wind speed-frequency reference curve offset is higher than the corresponding dynamically set warning line.

3. The laboratory exhaust gas induced high-altitude jet fan control system according to claim 2, characterized in that: The calculation process for the dynamic efficiency coefficient and the wind speed-frequency reference curve offset is as follows: Calculate the product of the fan operating current and the inverter output power, and then calculate the ratio of the real-time jet velocity at the fan outlet to the aforementioned product. The resulting ratio is the dynamic efficiency coefficient. Under fixed building back pressure conditions, the stable outlet wind speed corresponding to different inverter frequencies during normal historical periods was recorded to form a wind speed-frequency reference curve. The percentage deviation between the measured wind speed at the current frequency and the corresponding value on the reference curve is calculated in real time, which is the wind speed-frequency reference curve offset.

4. The laboratory exhaust gas induced high-altitude jet fan control system according to claim 2, characterized in that: The process of the variation stability analysis is as follows: The time series of dynamic efficiency coefficients and the time series of wind speed-frequency reference curve offset are divided into continuous and non-overlapping data windows. The coefficient of variation of the data windows is calculated, and the average coefficient of variation of the most recent M data windows is calculated as the confidence index for trend analysis. The confidence level of the output warning signal is determined based on the confidence index of trend analysis.

5. A laboratory exhaust gas induced high-altitude jet fan control system according to claim 2, characterized in that: The process of moving average filtering analysis and trend slope analysis is as follows: The dynamic efficiency coefficient time series and the wind speed-frequency reference curve offset time series are calculated by moving average through a sliding time window. The arithmetic mean of the data within each sliding time window is obtained and used as the filtered value at the center of the sliding time window. The smoothed dynamic efficiency coefficient trend line series and wind speed-frequency reference curve offset trend line series are output respectively. The analysis period is preset, and the smoothed dynamic efficiency coefficient trend line sequence and wind speed-frequency baseline curve offset trend line sequence are extracted within the most recent analysis period. With time as the independent variable and the smoothed dynamic efficiency coefficient trend line sequence and wind speed-frequency baseline curve offset trend line sequence as the dependent variable, the least squares method is used to perform linear regression to fit the corresponding straight line equation, which is used as the first and second straight line equations. Based on the fitted first and second line equations, the corresponding first trend slope and second trend slope are calculated respectively.

6. The laboratory exhaust gas induced high-altitude jet fan control system according to claim 1, characterized in that: The process of building and running a vulnerability assessment model includes: Based on the building information model of the target laboratory, the ventilation system design drawings, and the factory performance curve of the induced high-altitude jet fan, a static digital twin containing the three-dimensional geometry of the building, the topology of the ventilation network, and the equipment parameters is constructed. Under typical system operating conditions, a set of benchmark operating data is collected. By iteratively adjusting the local drag coefficient and boundary condition parameters in the digital twin, the error between the simulation output and the benchmark measured data is brought to a preset range, thus completing the initial calibration of the model. Using real-time collected multidimensional time-series data and predictive maintenance early warning as input, computational fluid dynamics and pollutant diffusion simulation are run to simulate the waste gas diffusion process and output the pollutant concentration distribution field at the height of the personnel breathing zone.

7. The laboratory exhaust gas induced high-altitude jet fan control system according to claim 1, characterized in that: The input acquisition process for the vulnerability assessment model is as follows: When the warning signal is an efficiency degradation warning, the performance retention coefficient is calculated based on the confidence level, the current moving average of the dynamic efficiency coefficient, the corresponding performance degradation warning line value and the historical health benchmark value. The performance retention coefficient is then used to reduce the benchmark maximum jet velocity of the wind turbine to obtain the equipment equivalent performance parameters for simulation. The real-time pressure difference of key areas of the building, static pressure of the exhaust duct, wind speed and direction on the roof, and real-time total exhaust volume are extracted from the data packet to form an environmental state vector.

8. The laboratory exhaust gas induced high-altitude jet fan control system according to claim 1, characterized in that: The execution process of the vulnerability assessment model is as follows: Using the environmental state vector as the real-time boundary condition, computational fluid dynamics and pollutant diffusion simulation are run to simulate the diffusion process of exhaust gas from the emission outlet to the periphery of the building, and output the pollutant concentration distribution field at the height of the breathing zone of people. Based on the concentration distribution field, identify areas with excessive concentration, calculate the area of ​​the excessive area and the maximum concentration exceeding the standard, and combine building information to determine whether it overlaps with densely populated areas or fresh air intakes. Simultaneously, preset extreme adverse disturbance conditions are automatically applied to simulate the system's response under current performance and calculate the rate of decrease in immunity caused by performance degradation.

9. A laboratory exhaust gas induced high-altitude jet fan control system according to claim 1, characterized in that: The assessment indicator reflecting the overall risk of current and future exhaust gas intrusion into the breathing zone of personnel is the overall risk value; The calculation of the comprehensive risk value is as follows: based on the pollutant concentration distribution field, the ratio of the area of ​​the area exceeding the standard to the total area of ​​the assessment area is calculated as the area exposure ratio; Logarithmically transform the maximum concentration exceedance ratio to obtain the transformed concentration exceedance intensity; The geometric mean method was used to calculate the comprehensive risk value by integrating the area exposure ratio, the intensity of concentration exceeding the standard after conversion, and the system toughness attenuation.

10. A laboratory exhaust gas induced high-altitude jet fan control system according to claim 1, characterized in that: The process of obtaining the risk level corresponding to the assessment indicators is as follows: If the overall risk value is less than or equal to the warning threshold, the current operational risk is determined to be controllable, and the system is in a normal monitoring state. If the overall risk value is greater than the warning threshold and less than or equal to the emergency threshold, the current operational risk is determined to be increased, and the control status is strengthened. If the overall risk value is greater than the emergency threshold, the current operation is determined to be facing a high risk and is placed in an emergency avoidance state.

Images