Fume hood parameter configuration management method based on big data

Abstract

The invention discloses a ventilation cabinet parameter configuration management method based on big data, and relates to the technical field of big data processing, and the method comprises the following steps: collecting historical data of a ventilation cabinet; performing parameter analysis on the historical data; performing performance prediction on a parameter analysis result; performing configuration optimization on the prediction result; setting parameters according to an optimal configuration result; carrying out equipment calibration according to a parameter setting result; and performing system health assessment according to a calibration result. According to the method, by introducing multi-dimensional real-time data acquisition, a health assessment algorithm and a self-adaptive real-time feedback mechanism, the problems of feedback lag and inaccurate health assessment in the prior art are solved. And an intelligent algorithm is utilized to comprehensively analyze the operation state of the equipment, and adjustment is made in time, so that accurate prediction and optimal management of the performance of the equipment are realized. And through a data-driven feedback mechanism, the operation efficiency of the equipment is remarkably improved, and the safety and the stability of the equipment are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and specifically provides a method for managing the parameter configuration of a fume hood based on big data. Background Art

[0002] With the increasing demand for the use of fume hoods in laboratory and industrial environments, the management and optimization of their operating states have become the key to improving laboratory safety, equipment efficiency, and energy consumption levels. The health assessment method is a key technology for predicting and evaluating the health state of fume hoods. It collects data on fume hoods through sensor data, and then conducts a health assessment on the collected data.

[0003] In the prior art, the health assessment algorithm lacks comprehensiveness and accuracy: traditional equipment health assessment methods usually rely on experience or single sensor data, and do not fully consider environmental factors, maintenance history, and the cumulative effects of long-term equipment operation. This results in often inaccurate assessment results and insufficient predictive ability, especially in key applications such as aging and wear prediction and remaining life prediction, lacking sufficient data support and dynamic optimization ability. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method for managing the parameter configuration of a fume hood based on big data to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a method for managing the parameter configuration of a fume hood based on big data, including the following steps: S1. Collect historical data of the fume hood; The historical data is obtained through a sensor network and Internet of Things technology; S2. Conduct parameter analysis on the historical data; The obtained historical data is deeply analyzed to obtain a parameter analysis result; S3. Conduct performance prediction on the parameter analysis result; After obtaining the parameter analysis result, perform performance prediction on the fume hood data of the parameter analysis result to obtain a prediction result; S4. Conduct configuration optimization on the prediction result; According to the prediction result, conduct configuration optimization on the various data of the fume hood to obtain an optimized configuration result; S5. Set parameters according to the optimized configuration result; By inputting the optimized configuration result into an automatic control system, the system automatically adjusts the parameters to obtain a parameter setting result; S6. Calibrate the device according to the parameter setting result; Further calibrate the parameters based on the parameter setting result and the response of the device to obtain a calibration result; S7. Conduct a system health assessment according to the calibration result; Evaluate the overall operating health status of the fume hood through a health assessment algorithm based on the calibration result.

[0006] To further optimize this technical solution, in step S6, the response of the device includes: Use a real-time feedback mechanism to continuously monitor the actual operating condition of the fume hood through sensors and compare it with the parameter setting result.

[0007] To further optimize this technical solution, the real-time feedback mechanism includes: Real-time data collection, continuously collect key data through installed sensors and monitoring devices; Deviation analysis and comparison; Automatic adjustment and optimization, automatically adjust device parameters based on the deviation analysis result; Real-time alarm and manual intervention mechanism, trigger an alarm for manual intervention when automatic adjustment cannot solve the problem; Optimization loop and dynamic adjustment, continuously adjust device parameters to improve device operation; Visualization and report generation, generate visualization charts for reference.

[0008] To further optimize this technical solution, the deviation analysis and comparison includes: Collect the real-time data and send it into the deviation analysis system. The system determines whether the set parameter data is available by comparing the deviation value between the real-time data and the set parameter data; Compare the deviation value with the threshold set by the system. If the deviation value exceeds the threshold, the system will mark the anomaly and record the deviation source.

[0009] To further optimize this technical solution, in step S7, the health assessment algorithm includes: Construction of the device health index; Establish a multiple regression model for aging and wear prediction; Fault risk prediction and early warning; Health assessment and decision support.

[0010] To further optimize this technical solution, the construction of the device health index includes: The health index is a key indicator for comprehensively evaluating the health status of the equipment. The health index is a key indicator for comprehensively evaluating the health status of the equipment. It scores the health status of the fume hood based on the fan speed data, vibration data, energy efficiency data, air flow data, temperature data, humidity data in the calibration results, as well as historical maintenance and failure data.

[0011] To further optimize this technical solution, the multiple regression model includes: Establishing a regression model; Estimation of regression coefficients; Model evaluation and verification.

[0012] To further optimize this technical solution, the steps for establishing the regression model include: Selecting independent variables and a dependent variable. In this model, the dependent variable is the aging progress and wear degree, and the independent variables include: Vibration data: vibration amplitude, frequency; Temperature and humidity data: temperature and humidity values in the environment where the equipment is located; Energy efficiency data: energy efficiency decline rate; Operating status: operating time of the equipment.

[0013] Regression model: ; Where, is the dependent variable, including aging progress and wear degree; is the constant term, set artificially; is the regression coefficient, indicating the influence degree of each independent variable on the aging progress; are the independent variables, including vibration data, temperature and humidity data, energy efficiency data, operating status; is the error term, set artificially.

[0014] To further optimize this technical solution, the estimation of the regression coefficients includes: Using the ordinary least squares method (OLS) to estimate the regression coefficients. OLS minimizes the sum of squared errors, The formula is: ; Where, is the sample size; is the actual value, obtained by real-time collection through multi-source sensors; is the predicted value, that is .

[0015] Further optimize this technical solution. The model evaluation and verification include: Three methods: R-squared : Represents the proportion of the variance explained by the model in the total variance. The closer the value is to 1, the better the fitting degree of the model to the data; Mean Squared Error MSE: Measures the difference between the predicted value and the actual value of the model. The smaller the value, the better; Root Mean Squared Error RMSE: Is the square root of MSE and is commonly used to evaluate the accuracy of regression models.

[0016] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of a method for managing the parameter configuration of a fume hood based on big data as described in the first aspect of the present invention are implemented.

[0017] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program instructions are executed by the processor, the steps of a method for managing the parameter configuration of a fume hood based on big data as described in the first aspect of the present invention are implemented.

[0018] Compared with the prior art, the present invention provides a method for managing the parameter configuration of a fume hood based on big data, having the following beneficial effects: This method for managing the parameter configuration of a fume hood based on big data overcomes the problems of lagging feedback and inaccurate health assessment in the prior art by introducing multi-dimensional real-time data collection, a health assessment algorithm, and an adaptive real-time feedback mechanism.

[0019] This method comprehensively analyzes the operating state of the device by using intelligent algorithms through real-time monitoring of multiple factors such as temperature and humidity, air flow, vibration, and energy efficiency, and makes timely adjustments, achieving precise prediction and optimized management of the device performance.

[0020] Through a data-driven feedback mechanism, the operating efficiency of the device is significantly improved, energy waste is reduced, and the service life of the device is effectively extended, ensuring the safety and stability of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 This is a schematic flow chart of a method for managing the parameter configuration of a fume hood based on big data proposed by the present invention; Figure 2 This is a flowchart of the real-time feedback mechanism of a method for managing the parameter configuration of a fume hood based on big data proposed by the present invention; Figure 3 This is a flowchart of the multiple regression model of a method for managing the parameter configuration of a fume hood based on big data proposed by the present invention. Specific embodiments

[0023] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0024] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0025] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments.

[0026] Embodiment 1: Referring to Figures 1 to 3 , this is the first embodiment of the present invention. This embodiment provides a method for managing the parameter configuration of a fume hood based on big data, including the following steps: S1. Collect historical data of the fume hood; The historical data is obtained through a sensor network and Internet of Things technology. Before configuring the parameters of the fume hood, it is first necessary to collect and organize its usage historical data.

[0027] In this embodiment, the historical data includes information such as the operating status of the fume hood, maintenance records, air flow changes, and energy consumption levels. These historical data can be obtained in real time through an integrated sensor network and Internet of Things technology. The sensors monitor the operating conditions of the fume hood, such as air flow velocity, filter status, exhaust port pressure, etc., and at the same time, the intelligent system stores and analyzes the historical data. These historical data provide a decision-making basis for subsequent optimization of the fume hood performance and configuration parameters. The collection of historical data should not only focus on the status of the equipment itself, but also consider external environmental factors, such as the operating status of the building ventilation system, the impact of weather changes on ventilation requirements, etc. These factors may all affect the performance requirements of the fume hood (temperature and humidity, vibration data).

[0028] S2. Conduct parameter analysis on the historical data.

[0029] The obtained historical data is deeply analyzed through statistical analysis and machine learning models to obtain the parameter analysis results.

[0030] In this embodiment, the collected historical data can be deeply analyzed through statistical analysis and machine learning models. In this step, statistical methods such as regression analysis and clustering analysis are used to process the historical data to find the key factors affecting the operating efficiency, air flow, energy consumption, etc. of the fume hood. This analysis can help us identify which factors have the greatest impact on the efficiency and safety of the fume hood under different environments and working conditions, and then refine and optimize the configuration parameters of the fume hood. For example, using a regression model to evaluate the relationship between the temperature, humidity and air flow inside and outside the fume hood, and predicting the optimal wind speed and energy efficiency configuration of the fume hood under different environmental conditions. At this time, the parameter analysis results can be obtained, that is, the optimal wind speed and energy efficiency configuration of the fume hood. In addition, by combining the change trend of historical data, potential failure points of the equipment can be predicted, and the fume hood configuration can be adjusted in advance or maintenance can be arranged.

[0031] S3. Conduct performance prediction on the parameter analysis results.

[0032] After obtaining the parameter analysis results, a prediction model in machine learning is used for prediction to obtain the prediction results.

[0033] In this embodiment, the random forest algorithm is used to predict the future performance of the fume hood. Based on the historical data and parameter analysis results, the model can predict the optimal operating parameters required by the fume hood under different workloads and different environmental factors. For example, in the case of relatively serious air pollution, the fume hood may require a higher wind speed or a stronger filtration system. At this time, the prediction model can predict this change in advance and make a response. In addition, the model can also simulate the energy consumption changes in different situations to help users optimize power consumption and reduce unnecessary resource waste.

[0034] The random forest algorithm is an ensemble learning method that performs regression prediction by constructing multiple decision trees. Each decision tree is trained based on a different subset of samples and makes predictions during the test phase. The final prediction result is the average of the output results of all decision trees, thereby improving the robustness and accuracy of the model. Its advantage is that it can capture complex non-linear relationships between input features.

[0035] Model formula: The prediction formula consists of the outputs of all decision trees: ; where is the number of decision trees.

[0036] is the prediction result of the th tree.

[0037] are the input features.

[0038] is the average predicted value, that is, the prediction result obtained by using the prediction model in machine learning.

[0039] Implementation steps: Collect and clean historical data.

[0040] Divide the dataset into a training set and a test set.

[0041] Use the random forest algorithm to train the model (such as RandomForestRegressor).

[0042] Evaluate the model performance and make predictions.

[0043] S4. Optimize the configuration of the prediction results; According to the prediction results, perform configuration optimization through an optimization algorithm to obtain the optimized configuration results; In this embodiment, the prediction results are input into the optimization algorithm for further configuration adjustment. The goals of configuration optimization include improving the working efficiency of the fume hood, reducing energy consumption, and extending the service life of the equipment, etc. By optimizing the prediction results output by the model, we can adjust parameters such as the wind speed, air flow rate, and filter replacement cycle of the equipment, so that the fume hood maintains the best working state under different working conditions. For example, in the case of predicting high energy consumption, the power consumption can be reduced by optimizing the wind speed and ventilation time, and at this time, the optimized configuration results, that is, the wind speed and ventilation time, can be obtained. In this process, optimization methods such as genetic algorithms can be used.

[0044] S5. Set parameters according to the optimized configuration results; By inputting the optimized configuration results into the automatic control system, the system automatically adjusts the parameters to obtain the parameter setting results. In this embodiment, the fume hood is equipped with a built-in automatic control system when it leaves the factory. Using this automatic control system, the optimized configuration results are directly transmitted to the fume hood equipment, and the system will automatically adjust the operating parameters of the equipment, including air velocity, air flow rate, temperature and humidity adjustment, filter working status, etc. These adjusted data are the parameter setting results. The system can achieve these adjustments through a preset control program and ensure that the equipment always maintains the optimal configuration state during operation. For example, automatically adjust the speed of the fan or automatically turn on or off the exhaust system according to the air quality detection value. This process can greatly reduce manual intervention compared with the prior art and improve the automation and intelligence level of the system.

[0045] S6. Calibrate the equipment according to the parameter setting results. According to the parameter setting results and the response of the equipment, further calibrate the parameters to obtain the calibration results.

[0046] Use a real-time feedback mechanism to continuously monitor the actual operating conditions of the fume hood through sensors and compare them with the preset configuration parameters. If a deviation is found, the system will automatically adjust the relevant parameters to ensure that the equipment operates as expected. Through this innovative step, the equipment can self-correct during operation, improve the accuracy of equipment operation, and avoid energy consumption waste or equipment damage caused by deviations.

[0047] The real-time feedback mechanism includes: Real-time data collection and monitoring. Based on the sensors and monitoring equipment already installed on the equipment, the real-time feedback mechanism will continuously collect and process the key data of the parameter setting results. In this embodiment, these key data include: Operating status: Continuously monitor the on / off status, operating mode, operating time, etc. of the equipment to ensure that the equipment works according to the predetermined plan.

[0048] Air flow rate change: Continuously monitor the air flow rate, especially the deviation between the actual flow rate and the set flow rate, and continuously record the deviation.

[0049] Energy consumption level: Track the real-time energy consumption of the equipment, monitor the power demand and energy efficiency level, and ensure that the energy consumption is within the optimized range.

[0050] Maintenance records: Record the operating conditions and maintenance history of the equipment, including equipment failure rate, maintenance cycle, and any abnormal events.

[0051] Temperature and humidity data: Continuously monitor the impact of ambient temperature and humidity on the operation of the equipment to avoid the performance of the equipment being affected by too high or too low temperature and humidity.

[0052] These key data are transmitted in real time through integrated Internet of Things (IoT) technologies, using communication protocols such as the MQTT protocol or LoRaWAN to obtain real-time data, and then transmitting these real-time data to the cloud platform or local control system for storage and processing.

[0053] Deviation analysis and comparison. Collect the real-time data and send it to the deviation analysis system. The system determines whether the set parameter data is available by comparing the deviation value between the real-time data and the set parameter data. Deviation calculation method: ; where is the deviation value; is the set value; is the real-time value; Compare the deviation value with the threshold set by the system. If the deviation value exceeds the threshold, the system will mark the abnormality and record the source of the deviation.

[0054] In this embodiment, after the real-time data is collected, the system will compare it with the preset optimization goal, analyze whether there is a deviation and generate feedback information. For example, the actual value of the air flow may have a large deviation from the set value, the energy consumption level may exceed the reasonable range, or the operating state does not match the expectation.

[0055] Automatic adjustment and optimization.

[0056] In this embodiment, based on the deviation analysis result, the system automatically adjusts the device parameters to achieve the optimization goal. For example: Fan speed adjustment: According to the deviation of the air flow, automatically adjust the fan speed to ensure that the flow rate is within the set range.

[0057] Air flow regulation: The system will automatically adjust the flow valve in the fume hood to avoid low energy efficiency caused by excessive flow rate changes.

[0058] Energy consumption optimization: When the energy consumption exceeds the preset target value, the system will take energy-saving measures according to the demand, such as adjusting the fan mode or deactivating non-critical functions.

[0059] Temperature and humidity regulation: When the temperature or humidity deviates from the set range, the system will start devices such as air conditioners or humidifiers / dehumidifiers to ensure that the device operates under suitable environmental conditions.

[0060] The automatic adjustment mechanism can continuously and dynamically optimize the device operation based on real-time feedback data, historical trends, and the set optimization goals.

[0061] In this embodiment, when the deviation analysis detects that the device operation parameters deviate from the predetermined target, the system will automatically start an adjustment mechanism to optimize the device configuration and ensure that it is always in the best operating state.

[0062] Real-time alarm and manual intervention mechanism. In this embodiment, when the automatic adjustment cannot effectively solve the problem, the system will trigger an alarm and notify the operator for manual intervention. If the real-time monitoring system detects that the deviation exceeds the predetermined threshold and the automatic adjustment fails to effectively solve the problem, the system will issue an alarm. The alarm can be notified to relevant personnel in a timely manner in the form of text messages, emails or APP push notifications. Common types of alarms include: Airflow alarm: When the airflow deviation is too large and cannot be restored through automatic adjustment, the system will alarm.

[0063] Abnormal energy consumption alarm: If the device energy consumption continues to be high, the system will prompt to check the energy efficiency status of the device.

[0064] Device failure alarm: If the system detects device abnormalities (such as sensor failures, fan not running, etc.), the system will immediately alarm.

[0065] Temperature and humidity alarm: If the temperature and humidity exceed the set threshold (such as temperature exceeding 30°C or humidity exceeding 80%), the system will alarm and prompt the risk that may affect the device operation.

[0066] The alarm information will be accompanied by relevant data and recommended intervention measures to help the operator take corresponding repair or adjustment actions in a timely manner.

[0067] Optimization loop and dynamic adjustment. In this embodiment, based on real-time feedback and alarm results, the system will enter an optimization loop and continuously adjust to maintain the optimal operating state.

[0068] The real-time feedback mechanism not only makes adjustments every time a deviation occurs, but also continuously improves the device operation through the optimization loop. The optimization loop is divided into the following steps: Obtain the latest real-time data: including air flow, energy consumption, device operation status, etc.

[0069] Analysis and comparison: Compare the new real-time data with the data after the last optimization to evaluate the effect of the last adjustment.

[0070] Adjustment and optimization: If it is found that the device operation does not reach the optimization target, the system will automatically make fine adjustments.

[0071] Evaluation and feedback: By evaluating the effect of the new adjustment, determine whether the optimization target is reached and decide whether to continue the adjustment.

[0072] This optimization loop will continue to ensure that the system can cope with environmental changes and device performance fluctuations and always maintain the optimal operating state.

[0073] Visualization and report generation. Based on real-time data collection, adjustment, and optimization, the system will generate visualization reports to help decision-makers track the long-term operating status of the equipment.

[0074] To facilitate operators and managers to promptly grasp the operating conditions of the equipment, the system will generate and display charts and trend graphs of key performance indicators (KPIs) in real time. For example: Airflow: Displays the real-time change trend of the flow rate and the comparison with the set value.

[0075] Energy consumption level: Displays the energy efficiency performance of the equipment and compares it with the preset target.

[0076] Equipment status: Displays the real-time operating status of the equipment, including whether it is in normal operation and whether maintenance is required, etc.

[0077] Temperature and humidity trend: Displays the real-time changes in temperature and humidity and their impact on the operating status of the equipment, helping decision-makers adjust environmental conditions to optimize equipment performance.

[0078] The system will also automatically generate regular reports summarizing the fan speed, energy efficiency performance, maintenance records, airflow, temperature, humidity, and vibration frequency of the equipment, and these data are the calibration results.

[0079] S7. Conduct system health assessment based on the calibration results; According to the calibration results, evaluate the overall operating health status of the fume hood through a health assessment algorithm.

[0080] The health assessment algorithm includes: Construction of equipment health index.

[0081] The health index (HI) is a key indicator for comprehensively evaluating the health status of the equipment, considering the operating status, wear, energy efficiency, and environmental conditions of the equipment.

[0082] Health index formula: ; Where, : Fan speed health degree, reflecting the deviation of the fan speed from the set value; : Vibration health degree, based on the data of vibration sensors, evaluating the wear condition of components; : Energy efficiency health degree, reflecting the energy efficiency performance of the equipment; : Airflow health degree, reflecting the deviation of the actual flow rate from the set flow rate; : Maintain health, considering the historical failure and maintenance records of the equipment; : Temperature health, considering the impact of the equipment's working environment temperature on its operation; : Humidity health, evaluating the impact of the humidity in the equipment's environment on the equipment's health; : Weight coefficient, set according to the equipment characteristics and operation requirements; : Health index.

[0083] Establish a multiple regression model for aging and wear prediction. The multiple regression model includes: Problem definition and goal setting. Goal: Through the multiple regression model combined with various factors such as vibration data, temperature and humidity, and energy efficiency, predict the process of equipment aging and wear, so as to help managers reasonably arrange maintenance plans and optimize resource allocation. Prediction goals: The aging progress of the equipment (e.g., aging speed, remaining service life) and the degree of wear (e.g., component wear rate, failure probability).

[0084] Data collection and preprocessing. The multiple regression model relies on multiple input variables, which come from the equipment's real-time monitoring system. The key data sources involved include: Vibration data: Collect vibration data through installed acceleration sensors and analyze information such as vibration amplitude and frequency.

[0085] Temperature and humidity data: Temperature and humidity sensors record the temperature and humidity changes in the equipment's operating environment, especially when the equipment load is high (such as fan speed, air flow adjustment).

[0086] Energy efficiency data: The power consumption, efficiency, etc. of the equipment, usually from the equipment's energy efficiency monitoring module.

[0087] Operating status data: Such as equipment switch status, running time, etc.

[0088] Data preprocessing: Missing value processing: Fill or delete missing values, using mean filling or interpolation method.

[0089] Standardization: Standardize data with different dimensions so that they can be compared on the same scale (such as using z-score standardization).

[0090] Outlier detection: Identify and process outliers to avoid their excessive impact on the regression model.

[0091] Establish a regression model. Select independent variables and dependent variables. In this model, the dependent variables are aging progress and degree of wear, and the independent variables include: Vibration data: vibration amplitude, frequency; Temperature and humidity data: temperature and humidity values of the environment where the device is located; Energy efficiency data: energy efficiency decline rate; Operating status: operating time of the device.

[0092] Regression model: ; Among them, is the dependent variable, including aging progress and wear degree, is the constant term, set artificially; is the regression coefficient, indicating the influence degree of each independent variable on the aging progress; is the independent variable, including vibration data, temperature and humidity data, energy efficiency data, operating status; (other relevant independent variables can be added) is the error term, set artificially.

[0093] Regression coefficient estimation and model training. Use the ordinary least squares method OLS to estimate the regression coefficient. OLS is to minimize the sum of squared errors, The formula is: ; Among them, is the sample size; is the actual value, obtained by real-time collection through multi-source sensors; is the predicted value, that is ; The model training process includes: Data division: Divide the historical data into a training set and a test set, usually divided according to the ratio of 70% training set and 30% test set.

[0094] Model training: Solve the regression coefficient on the training set by the ordinary least squares method.

[0095] Evaluation and adjustment: Use the test set to verify the performance of the model and adjust the model according to the results (for example, remove some irrelevant features).

[0096] Model evaluation and verification. Three evaluation formulas: ; Among them, is the proportion of variance in the total variance; ; Among them, is the difference between the predicted value and the actual value; is the square root of, which evaluates the accuracy of the regression model.

[0097] Prediction and practical application. Once the regression model is trained and verified to be effective, it can be used to predict the aging progress and wear degree of the device in real time. In practical applications, the model can predict the aging of the device based on real-time monitoring data (such as vibration, temperature and humidity, and energy efficiency).

[0098] In this implementation, the specific application scenarios are as follows: Prediction of aging speed: Predict the aging speed of each component of the device to help arrange timely maintenance and component replacement.

[0099] Prediction of remaining service life: Combine historical data and prediction results to evaluate the remaining service life of the device for early planning of replacement or maintenance.

[0100] Analysis of energy efficiency decline: Predict the energy efficiency decline speed of the device and optimize the operation strategy according to the prediction results.

[0101] Model optimization and iteration. As more device data accumulates, the regression model can be retrained and optimized regularly to improve the prediction accuracy. By introducing more independent variables (such as vibration mode, component type, load condition, etc.), the generalization ability and accuracy of the model will continue to improve.

[0102] Influence of temperature and humidity and model adjustment. Increasing temperature and humidity may change the regression coefficients of the model.

[0103] High-temperature environment: Excessive temperature will accelerate the aging of the device, such as the accelerated insulation aging of the fan motor. At this time, the regression coefficient (the influence of temperature on the aging progress) will be larger.

[0104] High-humidity environment: Excessive humidity may cause corrosion or frosting of the electrical components inside the device, and the humidity coefficient has a greater impact on wear prediction.

[0105] Therefore, the temperature and humidity coefficients of the model need to be adjusted and optimized according to the changes in actual data.

[0106] Fault risk prediction and early warning. Combine temperature and humidity, vibration, and other health data to optimize the fault risk prediction and early warning mechanism. Fault risk prediction combines the device health index, historical maintenance records, and external environment data. Through machine learning algorithms (such as random forest, support vector machine (SVM)), potential faults of the device can be predicted and early warnings can be issued in advance.

[0107] In a prediction model, temperature, humidity, and vibration data can help identify early signals of equipment failures: Excessive temperature may indicate overheating of the fan or electrical faults.

[0108] Abnormal vibration is usually associated with loose components, wear, or other faults.

[0109] Excessive humidity may cause problems such as electrical short circuits and filter blockages.

[0110] Based on this data, a fault risk scoring model is constructed to help predict the probability of equipment failure and issue early warnings.

[0111] Health assessment and decision support. The health assessment results are fed back into the system to help optimize the equipment maintenance and operation strategies. The health assessment results will be presented through a visual interface for operation and maintenance personnel to make decisions. The impact of temperature, humidity, and vibration data will be included in the report to provide comprehensive health assessment results: Current health status: Determine whether the equipment is healthy through HI and whether immediate inspection or repair is required.

[0112] Aging prediction: Combine the prediction of the impact of temperature and humidity to provide the aging trend of the equipment and the possible failure time.

[0113] Environmental impact: Analyze the impact of temperature and humidity on the equipment and recommend appropriate adjustment of environmental conditions (such as ventilation or air conditioning adjustment) to optimize equipment operation.

[0114] Health assessment feedback and system optimization. The results of the health assessment are fed back into the system, and the operation and maintenance strategies of the equipment are optimized through a feedback mechanism. The feedback mechanism dynamically optimizes the equipment operation according to the health assessment results. For example, if the temperature and humidity are high, the system may adjust the fan speed or start the environmental control system to reduce the temperature or humidity. The system will also adjust the equipment maintenance plan according to the health assessment results to ensure that the equipment operates in an optimal state.

[0115] Example Two: This embodiment also provides a computer device applicable to a method for managing the parameter configuration of a fume hood based on big data, 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 implement a method for managing the parameter configuration of a fume hood based on big data as proposed in the above embodiment.

[0116] This embodiment also provides a storage medium with a computer program stored thereon, and when the program is executed by the processor, it implements a method for managing the parameter configuration of a fume hood based on big data as proposed in the above embodiment.

[0117] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0118] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drive, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk, or optical disc, etc., which can store program codes.

[0119] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0120] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0121] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A fume hood parameter configuration management method based on big data, characterized in that: The following steps are involved: S1. Collect historical data of fume hoods; Historical data is obtained through sensor networks and IoT technologies; S2. Parameter analysis of historical data; Conduct in-depth analysis on the acquired historical data to obtain parameter analysis results; S3. Predict performance based on parameter analysis results; After obtaining the parameter analysis results, the performance of the fume hood data of the parameter analysis results is predicted to obtain the prediction results; S4, optimizing the configuration of the prediction results; According to the prediction results, various data of the fume hood are optimized to obtain the optimized configuration results; S5. Setting parameters according to the optimization configuration results; By inputting the optimization configuration results into the automatic control system, the system automatically adjusts the parameters to obtain the parameter setting results; S6. Calibrate the equipment according to the parameter setting results; According to the parameter setting results and the response of the equipment, the parameters are further calibrated to obtain the calibration results; S7. Perform system health assessment based on the calibration results; Based on the calibration results, the overall operational health of the fume hood is evaluated through the health assessment algorithm.

2. A fume hood parameter configuration management method based on big data according to claim 1, characterized in that: In step S6, the response of the device includes: Utilizing the real-time feedback mechanism, the actual operating status of the fume hood is monitored in real time through sensors, real-time data is obtained, and compared with the parameter setting results.

3. A fume hood parameter configuration management method based on big data according to claim 2, characterized in that: The real-time feedback mechanism includes six parts: Real-time data collection, through installed sensors and monitoring equipment to continuously collect key data; Deviation analysis and comparison; Automatic adjustment and optimization: Automatically adjust equipment parameters based on deviation analysis results; Real-time alarm and manual intervention mechanism: when automatic adjustment cannot solve the problem, an alarm is triggered and manual intervention is performed; Optimize circulation and dynamic adjustment, and constantly adjust equipment parameters to improve equipment operation; Visualization and report generation, generate visual charts for reference.

4. A fume hood parameter configuration management method based on big data according to claim 3, characterized in that: The deviation analysis and comparison includes: The real-time data is collected and sent to the deviation analysis system. The system determines whether the set parameter data is available by comparing the deviation value between the real-time data and the set parameter data. The deviation value is then compared with the threshold set by the system. If the deviation value exceeds the threshold, the system will mark the anomaly and record the source of the deviation.

5. The method for fume hood parameter configuration management based on big data according to claim 1, characterized in that: In step S7, the health assessment algorithm includes: Equipment health index construction; Establish a multivariate regression model for aging and wear prediction; Failure risk prediction and early warning: predict potential failures of fume hoods based on equipment health index, historical maintenance records, aging and wear prediction results, and provide early warnings for these failures; Health assessment and decision support; provide visual charts for reference of operation and maintenance personnel.

6. A fume hood parameter configuration management method based on big data according to claim 5, characterized in that: The device health index construction includes: The health index is a key indicator for comprehensively evaluating the health status of the equipment. It scores the health status of the fume hood based on the fume hood's fan speed data, vibration data, energy efficiency data, air flow data, temperature data, humidity data, and historical maintenance and failure data in the calibration results.

7. A fume hood parameter configuration management method based on big data according to claim 5, characterized in that: The multiple regression model includes the following steps: Build regression models; Regression coefficient estimation; Model evaluation and validation.

8. A fume hood parameter configuration management method based on big data according to claim 7, characterized in that: The steps of establishing the regression model include: Select independent and dependent variables. In this model, the dependent variables are aging progress and wear and tear, while the independent variables include: Vibration data: vibration amplitude, frequency; Temperature and humidity data: temperature and humidity values ​​of the environment where the device is located; Energy efficiency data: rate of energy efficiency decline; Running status: the running time of the equipment; Regression Model: ； in, is the dependent variable, including the aging progress and the degree of wear, is a constant term; is the regression coefficient, which indicates the degree of influence of each independent variable on the progress of aging; are independent variables, including vibration data, temperature and humidity data, energy efficiency data, and operating status; It is the error term, which is the error caused by unpredictable factors in data collection.

9. A fume hood parameter configuration management method based on big data according to claim 7, characterized in that: The regression coefficient estimation and model training include: The least squares method OLS is used to estimate the regression coefficients. OLS minimizes the sum of squared errors. The formula is: ； in, is the sample size; It is the actual value, which is collected in real time by multi-source sensors; is the predicted value, that is .

10. A fume hood parameter configuration management method based on big data according to claim 7, characterized in that: The model evaluation and verification includes three methods: R-squared : Indicates the proportion of the variance explained by the model to the total variance. The closer the value is to 1, the better the model fits the data; Mean square error (MSE): measures the difference between the model's predicted value and the actual value; Root mean square error (RMSE): is the square root of MSE and is used to evaluate the accuracy of the regression model.

Images