A laboratory ventilation energy-saving automatic control method and system

Abstract

The present invention relates to the field of ventilation control technology, and in particular to a laboratory ventilation energy-saving automatic control method and system, which obtain laboratory pollutant concentration data and laboratory ventilation volume data in each time period, obtain the ventilation demand degree and ventilation efficiency characteristics of each time period, combine the ventilation demand degree and ventilation efficiency characteristics, obtain the dynamic change characteristics of air quality data in each time period, cluster based on the dynamic change characteristics of air quality data in each time period, obtain the matching degree according to the difference between the dynamic change characteristics of air quality data of the current time period and each historical time period in the same cluster, obtain the ventilation demand according to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster, and accurately obtain the ventilation demand that should be needed at present, so as to avoid misjudging the demand due to the fluctuation of a single monitoring parameter.

Description

Technical Field

[0001] The invention relates to the technical field of ventilation control, and in particular to a laboratory ventilation energy-saving automatic control method and system. Background Art

[0002] The purpose of laboratory ventilation system is to achieve air circulation in the laboratory to maintain a safe, healthy and comfortable working environment. However, in some experimental environments that require strict gas quality control, the energy consumption of laboratory ventilation system is usually high. Traditional ventilation systems mostly rely on manual control or timing control, and cannot adjust the ventilation intensity and time in real time according to actual needs. Turning on ventilation equipment for a long time will lead to a lot of energy waste. At present, intelligent and automated ventilation energy-saving control systems are gradually developing, which can automatically adjust the working state of ventilation equipment according to the real-time environmental parameters in the laboratory, achieving the dual effects of energy saving and improving comfort.

[0003] In the existing technology, laboratory ventilation design usually adopts a fixed air exchange rate or a simple adjustment method based on preset parameters to meet the laboratory air quality and safety requirements. However, due to the dynamic and diverse laboratory environment, ventilation requirements often change due to factors such as personnel activities, experimental operations or equipment operation, which may cause the control system to respond lag, unable to adjust the ventilation volume in time, or overshoot the ventilation volume, resulting in energy waste and unnecessary air disturbance, which in turn affects the experimental accuracy and indoor environmental stability. Summary of the invention

[0004] In order to solve the technical problem that the existing laboratory ventilation demand acquisition method is not reliable, the purpose of the present invention is to provide a laboratory ventilation energy-saving automatic control method and system, and the technical solution adopted is as follows:

[0005] In a first aspect of the present invention, a laboratory ventilation energy-saving automatic control method is provided, comprising:

[0006] Acquire laboratory pollutant concentration data and laboratory ventilation volume data for each time period; each time period includes a current time period and multiple historical time periods;

[0007] Based on the laboratory pollutant concentration data of each time period, the ventilation demand degree of each time period is obtained;

[0008] According to the pollutant concentration decrease amplitude in the pollutant concentration decrease section in the laboratory pollutant concentration data of each time period, and the corresponding time range and its corresponding laboratory ventilation volume data, the ventilation efficiency characteristics of each time period are obtained;

[0009] Combining the ventilation demand degree and ventilation efficiency characteristics, the dynamic change characteristics of air quality data in each time period are obtained;

[0010] Clustering is performed based on the dynamic change characteristics of air quality data in each time period, and the matching degree is obtained according to the difference in the dynamic change characteristics of air quality data in the current time period and each historical time period in the same cluster;

[0011] The ventilation demand is obtained according to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster.

[0012] In an exemplary embodiment, obtaining the ventilation requirement level for each time period based on the laboratory pollutant concentration data for each time period includes:

[0013] According to the data fluctuation of the laboratory pollutant concentration data in each time period, the pollutant concentration variation characteristics of each time period are obtained; the pollutant concentration variation characteristics represent the fluctuation degree of the pollutant concentration;

[0014] According to the pollutant concentration change rate at each sampling moment in the laboratory pollutant concentration data of each time period, the pollution persistence characteristics of each time period are obtained; the pollution persistence characteristics represent the speed of change of the pollutant concentration;

[0015] The ventilation requirement degree for each time period is obtained according to the pollutant concentration variation characteristics and the pollution persistence characteristics in each time period; the ventilation requirement degree is proportional to the pollutant concentration variation characteristics and the pollution persistence characteristics.

[0016] In an exemplary embodiment, the process of acquiring the pollutant concentration variation characteristics in each time period includes:

[0017] Obtain the pollutant concentration range of laboratory pollutant concentration data for each time period;

[0018] Obtaining target pollutant concentrations higher than a preset pollutant concentration reference value in the laboratory pollutant concentration data for each time period, and obtaining the concentration difference between each target pollutant concentration and the preset pollutant concentration reference value;

[0019] Based on the pollutant concentration extremes and the concentration differences in each time period, the pollutant concentration variation characteristics in each time period are obtained; the pollutant concentration variation characteristics are proportional to the pollutant concentration extremes and the concentration differences.

[0020] In an exemplary embodiment, the process of obtaining the pollutant concentration decreasing section includes:

[0021] Perform curve fitting on laboratory pollutant concentration data and obtain the extreme points;

[0022] The laboratory pollutant concentration data is segmented according to each extreme point, and the data segment with the starting point as the maximum value and the ending point as the minimum value is taken as the pollutant concentration decreasing segment.

[0023] In an exemplary embodiment, according to the pollutant concentration decrease amplitude of the pollutant concentration decrease segment in the laboratory pollutant concentration data of each time period, and the corresponding time range and the corresponding laboratory ventilation volume data, the ventilation efficiency characteristics of each time period are obtained, including:

[0024] According to the pollutant concentration decrease amplitude of the pollutant concentration decrease segment in the laboratory pollutant concentration data of each time period, and the corresponding time range and its corresponding laboratory ventilation volume data, the corresponding action relationship between the pollutant concentration and the ventilation volume in each time period, as well as the overall corresponding action relationship between the pollutant concentration and the ventilation volume are obtained;

[0025] According to the difference between the corresponding relationship between the pollutant concentration and the ventilation volume in each time period and the overall corresponding relationship between the pollutant concentration and the ventilation volume, the ventilation efficiency characteristics of each time period are obtained.

[0026] In an exemplary embodiment, the calculation formula for the corresponding relationship between the pollutant concentration and the ventilation volume in each time period is as follows:

[0027] ;

[0028] Among them, i represents the i-th time period, represents the corresponding relationship between the pollutant concentration and the ventilation volume in the i-th time period, M represents the number of pollutant concentration decrease segments in the laboratory pollutant concentration data in the i-th time period, and m represents the m-th pollutant concentration decrease segment in the laboratory pollutant concentration data in the i-th time period. It represents the decrease in the pollution concentration of the mth pollutant concentration decrease segment in the laboratory pollutant concentration data of the i-th time period, It represents the total ventilation volume in the time range corresponding to the mth pollutant concentration drop segment in the laboratory pollutant concentration data of the i-th time period; It represents the length of time corresponding to the time range of the mth pollutant concentration decline segment in the laboratory pollutant concentration data of the i-th time period; Represents an exponential function with the natural constant e as the base.

[0029] In an exemplary embodiment, the calculation formula for the overall corresponding relationship between pollutant concentration and ventilation volume is as follows:

[0030] ;

[0031] in, It represents the overall corresponding relationship between pollutant concentration and ventilation volume, and I represents the number of time periods.

[0032] In an exemplary embodiment, clustering is performed based on the dynamic change characteristics of air quality data in each time period, including:

[0033] Based on the differences in the dynamic change characteristics of air quality data in different time periods, preliminary clustering is performed;

[0034] The CURE clustering algorithm is used to cluster the preliminary clustering results again, wherein the clustering scaling factor of each time period is obtained from the dynamic change characteristics of the air quality data of each time period.

[0035] In an exemplary embodiment, the ventilation demand is obtained according to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster, including:

[0036] The ventilation demand is calculated as follows:

[0037] ;

[0038] in, represents the ventilation demand, J represents the number of historical time periods in the same cluster as the current time period, j represents the jth historical time period in the same cluster as the current time period, Indicates the matching degree between the current time period and the jth historical time period in the same cluster. Represents the total ventilation volume of the jth historical time period in the same cluster as the current time period.

[0039] In the second aspect of the present invention, a laboratory ventilation energy-saving automatic control system is provided, comprising: a memory and a processor; the memory is connected to the processor; the memory is used to store program instructions; the processor is used to implement the above-mentioned laboratory ventilation energy-saving automatic control method when the program instructions are executed.

[0040] The present invention has the following beneficial effects: the present invention analyzes laboratory pollutant concentration data and laboratory ventilation volume data of a current time period and a plurality of historical time periods, extracts the variation law of laboratory parameters by analyzing the historical data, helps to grasp the dynamic characteristics of ventilation demand under different experimental conditions, finds abnormal ventilation demand variation patterns that may cause overshoot or lag, optimizes the control logic, and can ensure the accuracy of obtaining subsequent ventilation demand; according to the laboratory pollutant concentration data and laboratory ventilation volume data of each time period, obtains the dynamic variation characteristics of air quality data of each time period, thereby completing the clustering of the dynamic variation characteristics of air quality data of each time period, distinguishes different situations by clustering, reduces the interference of mixed data, and provides clear demand categories for the ventilation system by clustering results, which helps to quickly adjust the ventilation strategy in a complex environment; according to the difference in the dynamic variation characteristics of air quality data of the current time period and each historical time period in the same cluster, obtains the matching degree, and finally predicts the ventilation demand according to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster, and can accurately obtain the ventilation demand that should be needed at present, avoiding misjudgment of demand due to fluctuation of a single monitoring parameter. The present invention is essentially a ventilation demand prediction method, which is used to obtain the ventilation demand and judge the actual ventilation demand of the current laboratory. In the subsequent ventilation control based on the ventilation demand, the response speed can be improved, the ventilation system can be adjusted in advance, and response lag can be avoided. The stability and efficiency of the ventilation system are improved, and a more scientific target setting basis is provided for the automatic controller, reducing the trial and error adjustment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of a laboratory ventilation energy-saving automatic control method provided by one embodiment of the present invention;

[0042] Figure 2 is a flow chart for obtaining the degree of ventilation requirement provided by an embodiment of the present invention;

[0043] Figure 3 is a flow chart for obtaining pollutant concentration variation characteristics provided by an embodiment of the present invention;

[0044] Figure 4 is a schematic diagram of a curve showing a change in pollutant concentration over time provided by an embodiment of the present invention;

[0045] Figure 5 It is a flow chart for obtaining a pollutant concentration decreasing section provided by an embodiment of the present invention;

[0046] Figure 6 It is a clustering flow chart based on the dynamic change characteristics of air quality data in each time period provided by an embodiment of the present invention;

[0047] Figure 7 It is a control principle diagram of a ventilation system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0049] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0050] Laboratory ventilation demand is mainly affected by factors such as air quality, pollutant concentration and personnel activities. The ventilation control system needs to adjust the ventilation volume in real time according to the dynamic changes of laboratory parameters to ensure the freshness, safety and comfort of indoor air. At present, when the laboratory is ventilated, the laboratory environment is usually dynamically affected by multiple factors, resulting in dynamic changes in ventilation demand. When the ventilation system fails to perceive and adapt to these dynamic changes in real time, it often causes the response lag of the ventilation system. Ventilation is often controlled by pollutants or air quality data exceeding a certain standard, which may cause energy waste caused by system lag or overshoot and instability of the experimental environment. Therefore, it is necessary to analyze the relevant data of laboratory historical ventilation, combine the real-time monitoring data to predict the ventilation demand, so as to dynamically adjust the ventilation volume, optimize energy efficiency, and ensure air quality and experimental safety at the same time. Based on this, the present invention provides a laboratory ventilation energy-saving automatic control method, by analyzing the changes in various parameters of the laboratory in historical data, judging the dynamic change characteristics corresponding to different ventilation demands, thereby clustering, dividing the data of different ventilation demands, matching according to the current real-time monitored laboratory data, and predicting the ventilation demand of the laboratory. In the subsequent process, the ventilation demand will be used as the setting target of the ventilation system controller to improve the energy efficiency optimization and real-time response capability of the laboratory ventilation system.

[0051] like Figure 1 As shown, the present embodiment provides a laboratory ventilation energy-saving automatic control method comprising the following steps:

[0052] Step 1: Obtain laboratory pollutant concentration data and laboratory ventilation volume data for each time period.

[0053] A pollutant concentration sensor is installed at a certain detection position in the laboratory to detect the laboratory's pollutant concentration data. It should be understood that the type of pollutant detected is determined by the specific situation of the laboratory. Different laboratories need to focus on different types of pollutants due to the different types of experiments they undertake. For example, some laboratories have higher requirements for dust-free, so the pollutant they focus on is dust concentration, such as PM2.5 concentration, and the pollutant concentration sensor is a PM2.5 concentration sensor; some laboratories are more sensitive to carbon dioxide, so the pollutant they focus on is carbon dioxide concentration, and the pollutant concentration sensor is a carbon dioxide concentration sensor.

[0054] A ventilation volume detection device is also provided at the ventilation system of the laboratory to detect the laboratory ventilation volume data, specifically the laboratory ventilation volume within a certain time period. It should be understood that the ventilation volume is a cumulative volume, and can be obtained in the following manner: obtain the ventilation volume per unit time on the time sequence, the ventilation volume per unit time is the ventilation volume per unit time period, and then integrate the ventilation volume per unit time of a certain time length, and the result obtained is the ventilation volume of the time length. The ventilation volume per unit time period can be calculated by the wind speed in the ventilation duct and the cross-sectional area of ​​the ventilation duct.

[0055] Multiple time periods are preset, including the current time period and multiple historical time periods. The end time of the current time period is the current time. The number of historical time periods is set according to actual needs. The length of each time period is set according to actual needs, such as 1 hour. In addition, the data sampling frequency is set according to actual needs, such as collecting data once every 10 seconds.

[0056] The laboratory pollutant concentration data and laboratory ventilation volume data of each time period are obtained. The laboratory pollutant concentration data is a time series data set, which is composed of laboratory pollutant concentrations at multiple sampling times.

[0057] In an exemplary embodiment, the laboratory pollutant concentration data and laboratory ventilation volume data can also be pre-cleaned to remove some obvious outliers that do not conform to the actual situation. The data of different dimensions can also be normalized and scaled to a uniform range.

[0058] Step 2: Based on the laboratory pollutant concentration data for each time period, obtain the ventilation requirement for each time period.

[0059] Analyzing the changes in pollutant concentrations in the laboratory is the key to ensuring air quality and experimental safety. Pollutant concentrations will change dynamically due to experimental operations, personnel activities, and equipment operation. If they cannot be controlled in time, they may have an adverse effect on the health of experimental personnel and the experimental environment. According to the changes in laboratory pollutant concentrations, ventilation needs can be classified. When high-risk experiments produce polluted gases, the ventilation needs are higher. Therefore, the changes in pollutant concentrations can reflect the ventilation needs of the laboratory. Then, based on the laboratory pollutant concentration data of each time period, the degree of ventilation needs in each time period can be obtained.

[0060] In an exemplary embodiment, Figure 2 As shown, a specific process for obtaining the degree of ventilation requirement is given as follows:

[0061] Step 2-1: According to the data fluctuation of the laboratory pollutant concentration data in each time period, the pollutant concentration change characteristics of each time period are obtained.

[0062] For the convenience of explanation, the current time period and any one of the multiple historical time periods are set as the target time period.

[0063] According to the data fluctuation of the laboratory pollutant concentration data in the target time period, the pollutant concentration variation characteristics of the target time period are obtained, and the pollutant concentration variation characteristics represent the fluctuation degree of the pollutant concentration in the target time period.

[0064] In an exemplary embodiment, Figure 3 As shown in FIG. 1 , the process of obtaining the pollutant concentration variation characteristics in the target time period includes:

[0065] Step 2-1-1: Obtain the pollutant concentration range of the laboratory pollutant concentration data for the target time period.

[0066] The maximum pollutant concentration value and the minimum pollutant concentration value in the laboratory pollutant concentration data of the target time period are obtained, and the difference between the maximum pollutant concentration value and the minimum pollutant concentration value is the pollutant concentration range.

[0067] Step 2-1-2: Obtain target pollutant concentrations that are higher than preset pollutant concentration reference values ​​in the laboratory pollutant concentration data for the target time period, and obtain the concentration difference between each target pollutant concentration and the preset pollutant concentration reference value.

[0068] A pollutant concentration reference value is preset, and the preset pollutant concentration reference value represents the standard line of pollutant concentration. The pollutant concentration above the standard line is an excessively high pollutant concentration, which is an abnormal pollutant concentration. The specific value of the preset pollutant concentration reference value is set according to actual judgment needs.

[0069] The pollutant concentrations in the laboratory pollutant concentration data of the target time period that are higher than the preset pollutant concentration reference value are obtained, and the pollutant concentrations that are higher than the preset pollutant concentration reference value are defined as target pollutant concentrations.

[0070] Then, the concentration difference between each target pollutant concentration and a preset pollutant concentration reference value is obtained, specifically, the absolute value of the concentration difference.

[0071] Step 2-1-3: Based on the pollutant concentration range and concentration difference in the target time period, obtain the pollutant concentration change characteristics in the target time period.

[0072] The pollutant concentration range characterizes the range length of the laboratory pollutant concentration data in the target time period, representing the fluctuation range of air quality pollution. The larger the pollutant concentration range, the stronger the pollutant concentration change characteristics. Therefore, the pollutant concentration change characteristics are proportional to the pollutant concentration range. The concentration difference is the distance between the target pollutant concentration and the preset pollutant concentration baseline value. The larger the concentration difference, the stronger the pollutant concentration change characteristics. Therefore, the pollutant concentration change characteristics are proportional to the concentration difference.

[0073] In an exemplary embodiment, the calculation formula for the pollutant concentration variation characteristic is given as follows:

[0074] ;

[0075] Among them, i represents the i-th time period, It represents the pollutant concentration variation characteristics in the i-th time period, and the pollutant concentration variation characteristics represent the pollution degree of the air quality in the corresponding time period; It represents the extreme value of pollutant concentration in the i-th time period; represents the number of target pollutant concentrations in the laboratory pollutant concentration data for the i-th time period; represents the first time period in the laboratory pollutant concentration data The value of the target pollutant concentration; Indicates the preset pollutant concentration baseline value.

[0076] represents the first time period in the laboratory pollutant concentration data The concentration difference between the target pollutant concentration and the preset pollutant concentration baseline value.

[0077] It represents the average value of the concentration difference between the target pollutant concentration in the laboratory pollutant concentration data of the i-th time period and the preset pollutant concentration benchmark value, characterizing the overall difference and representing the laboratory air pollution situation in the i-th time period.

[0078] Step 2-2: Based on the pollutant concentration change rate at each sampling moment in the laboratory pollutant concentration data of each time period, the pollution persistence characteristics of each time period are obtained.

[0079] During the laboratory ventilation process, if the pollutant concentration shows an upward trend over time, the ventilation system will be started after exceeding the preset pollutant concentration baseline value. After ventilation, the pollutant concentration will temporarily drop. As the experimental time changes, the pollutant concentration will gradually increase. This is a period of high ventilation demand, and ventilation at a higher wind speed must be maintained at all times. Figure 4 It is a schematic diagram of the curve of pollutant concentration changing with time, with the horizontal axis being time and the vertical axis being pollutant concentration.

[0080] According to the change of laboratory pollutant concentration data over time, if there are repeated fluctuations, it means that the corresponding time period is a period of high ventilation demand. Therefore, it is necessary to obtain the pollution persistence characteristics of the target time period based on the pollutant concentration change rate at each sampling time in the laboratory pollutant concentration data of the target time period. The pollution persistence characteristics characterize the speed of change of pollutant concentration.

[0081] In an exemplary embodiment, the calculation formula of the pollution persistence characteristic is given as follows:

[0082] ;

[0083] in, represents the pollution persistence characteristics of the i-th time period; represents the number of pollutant concentrations in the laboratory pollutant concentration data for the i-th time period; represents the laboratory pollutant concentration data in the i-th time period. The value of the pollutant concentration; represents the laboratory pollutant concentration data in the i-th time period. The value of the pollutant concentration; express and The time interval between them. Since the pollutant concentration is obtained according to a fixed sampling frequency, the time interval between two adjacent pollutant concentrations remains unchanged, which is the time interval between two adjacent sampling moments.

[0084] represents the laboratory pollutant concentration data in the i-th time period. The pollutant concentration is the same as the laboratory pollutant concentration data in the i-th time period. The rate of change of pollutant concentration for a pollutant concentration.

[0085] It represents the average value of the pollutant concentration change rate in the laboratory pollutant concentration data in the i-th time period, and characterizes the overall situation of the pollutant concentration change rate.

[0086] Step 2-3: Based on the pollutant concentration change characteristics and pollution persistence characteristics in each time period, the ventilation demand degree in each time period is obtained.

[0087] The greater the change characteristics of pollutant concentration in the laboratory and the greater the pollution persistence characteristics, the higher the concentration of air pollution in the laboratory is for a long time. At this time, the laboratory has a high ventilation demand and needs to respond quickly to increase ventilation volume to reduce pollution concentration. Then, according to the change characteristics of pollutant concentration and the pollution persistence characteristics in the target time period, the ventilation demand degree in the target time period is obtained, and the ventilation demand degree is proportional to the change characteristics of pollutant concentration and the pollution persistence characteristics.

[0088] In an exemplary embodiment, the calculation formula for the degree of ventilation requirement is given as follows:

[0089] ;

[0090] in, represents the degree of ventilation demand in the i-th time period, Represents a normalization function. The normalization method in this embodiment is selected according to actual needs, for example: normalization can adopt the maximum and minimum value normalization method, or the following common methods: , It represents the processing object, and exp represents the exponential function with the natural constant e as the base.

[0091] By adopting the above method, the ventilation demand degree in each time period is obtained.

[0092] Step 3: According to the pollutant concentration decrease amplitude in the pollutant concentration decrease segment in the laboratory pollutant concentration data of each time period, as well as the corresponding time range and its corresponding laboratory ventilation volume data, the ventilation efficiency characteristics of each time period are obtained.

[0093] The ventilation efficiency in the laboratory is reflected in the change of pollutant concentration with the ventilation volume. If the pollutant concentration decreases rapidly with the increase of ventilation volume, it means that the ventilation efficiency is high. Therefore, when ventilating the laboratory, the ventilation efficiency needs to be considered to facilitate the subsequent acquisition of the relationship between pollutant concentration and ventilation volume based on the decrease in pollutant concentration and the change in ventilation volume.

[0094] In an exemplary embodiment, it is first necessary to obtain the pollutant concentration decrease segment in the laboratory pollutant concentration data of the target time period, such as Figure 5 As shown, including:

[0095] Step 3-1: Perform curve fitting on the laboratory pollutant concentration data of the target time period and obtain the extreme points, which include the maximum and minimum values.

[0096] Step 3-2: Segment the laboratory pollutant concentration data of the target time period with each extreme point, and take the data segment with the starting point as the maximum value and the ending point as the minimum value as the pollutant concentration decrease segment. Among them, each extreme point is used as a segmentation point to divide the laboratory pollutant concentration data into multiple data segments, among which some data points have the starting point as the maximum value and the ending point as the minimum value. Therefore, the data segment with the starting point as the maximum value and the ending point as the minimum value is taken as the pollutant concentration decrease segment. The pollutant concentration in the pollutant concentration decrease segment shows a monotonically decreasing change. Moreover, since the laboratory pollutant concentration data is time series data, after obtaining each pollutant concentration decrease segment of the target time period, the time range corresponding to each pollutant concentration decrease segment, that is, the time period, is also obtained.

[0097] Then, according to the pollutant concentration decrease amplitude of the pollutant concentration decrease segment in the laboratory pollutant concentration data of the target time period, and the corresponding time range and its corresponding laboratory ventilation volume data, the ventilation efficiency characteristics of the target time period are obtained. In an exemplary embodiment, a specific acquisition process of the ventilation efficiency characteristics is given as follows:

[0098] Step 3-3: Based on the pollutant concentration decrease amplitude in the pollutant concentration decrease segment in the laboratory pollutant concentration data of each time period, as well as the corresponding time range and its corresponding laboratory ventilation volume data, obtain the corresponding relationship between the pollutant concentration and the ventilation volume in each time period, as well as the overall corresponding relationship between the pollutant concentration and the ventilation volume.

[0099] In an exemplary embodiment, the calculation formula for the corresponding relationship between pollutant concentration and ventilation volume is as follows:

[0100] ;

[0101] in, represents the corresponding relationship between the pollutant concentration and the ventilation volume in the i-th time period, M represents the number of pollutant concentration decrease segments in the laboratory pollutant concentration data in the i-th time period, and m represents the m-th pollutant concentration decrease segment in the laboratory pollutant concentration data in the i-th time period. It represents the decrease in the pollution concentration of the mth pollutant concentration decrease segment in the laboratory pollutant concentration data of the i-th time period, It represents the total ventilation volume in the time range corresponding to the mth pollutant concentration drop segment in the laboratory pollutant concentration data of the i-th time period; It represents the time length of the time range corresponding to the mth pollutant concentration decline segment in the laboratory pollutant concentration data of the ith time period, that is, the time interval between the start and end times of the mth pollutant concentration decline segment, that is, the pollutant concentration decline duration.

[0102] The decrease in pollutant concentration in the mth pollutant concentration decrease segment in the laboratory pollutant concentration data in the i-th time period The method for obtaining may be: obtaining the maximum pollutant concentration and the minimum pollutant concentration in the mth pollutant concentration decrease segment, and calculating the difference between the maximum pollutant concentration and the minimum pollutant concentration as the decrease range of the pollution concentration.

[0103] The total ventilation volume for the time range corresponding to the mth pollutant concentration drop segment in the laboratory pollutant concentration data for the i-th time period The method of obtaining can be: obtain the ventilation volume per unit time length in the time range corresponding to the mth pollutant concentration decrease segment, and then multiply it by the time length of the time range corresponding to the mth pollutant concentration decrease segment to obtain the total ventilation volume , or directly obtain the total ventilation volume of the mth pollutant concentration reduction section through the ventilation volume detection equipment.

[0104] Represents the change of pollutant concentration with ventilation in the laboratory pollutant concentration data of the i-th time period.

[0105] In an exemplary embodiment, the overall corresponding relationship between the pollutant concentration and the ventilation volume is obtained by using the above-mentioned method of obtaining the corresponding relationship between the pollutant concentration and the ventilation volume in each time period, and the formula is as follows:

[0106] ;

[0107] in, It represents the overall corresponding relationship between pollutant concentration and ventilation volume, and I represents the number of time periods.

[0108] Step 3-4: Based on the difference between the corresponding relationship between the pollutant concentration and the ventilation volume in each time period and the overall corresponding relationship between the pollutant concentration and the ventilation volume, the ventilation efficiency characteristics of each time period are obtained.

[0109] In laboratory ventilation control, if the ventilation efficiency in the laboratory is poor due to other factors such as environmental factors, the ventilation demand should also be increased to accelerate the replacement of air pollutants. Therefore, when the change of pollutant concentration with ventilation volume in the laboratory pollutant concentration data of the target time period is lower than the overall change, that is, if the corresponding relationship between pollutant concentration and ventilation volume in the target time period is lower than the overall corresponding relationship between pollutant concentration and ventilation volume, the ventilation efficiency of the target time period is low, and its ventilation demand should be increased.

[0110] Then, by obtaining the corresponding relationship between the pollutant concentration and the ventilation volume in each time period and the difference between the overall corresponding relationship between the pollutant concentration and the ventilation volume, the ventilation efficiency characteristics of each time period are obtained. In an exemplary embodiment, the calculation formula of the ventilation efficiency characteristics is as follows:

[0111] ;

[0112] in, Represents the ventilation efficiency characteristics of the i-th time period.

[0113] Step 4: Combine the ventilation demand degree and ventilation efficiency characteristics to obtain the dynamic change characteristics of air quality data in each time period.

[0114] The air quality and environmental parameters in the laboratory will show complex dynamic changes due to factors such as experimental operation, equipment operation and personnel activities, which directly affect the ventilation demand. If the dynamic change characteristics of laboratory pollutant concentration data in the laboratory are ignored, the ventilation system may be difficult to adjust in time, resulting in a decrease in air quality or energy waste. Analyzing the dynamic change characteristics of laboratory pollutant concentration data is the basis for achieving precise ventilation control. By analyzing the dynamic change characteristics of laboratory pollutant concentration data, the fluctuation pattern of parameters such as pollutant concentration can be identified, providing a basis for predicting ventilation demand, thereby improving the response speed, stability and energy efficiency optimization level of the ventilation system. Therefore, the dynamic change characteristics of air quality data in the target time period are obtained by combining the ventilation demand degree and ventilation efficiency characteristics of the target time period. The higher the ventilation demand degree, the higher the dynamic change characteristics of air quality data, and the lower the ventilation efficiency characteristics, the higher the dynamic change characteristics of air quality data.

[0115] In an exemplary embodiment, the calculation formula for the dynamic change characteristic of air quality data is as follows:

[0116] ;

[0117] in, Represents the dynamic change characteristics of air quality data in the i-th time period.

[0118] By adopting the above process, the dynamic change characteristics of the air quality data in each time period are obtained.

[0119] Step 5: Clustering is performed based on the dynamic change characteristics of the air quality data in each time period, and the matching degree is obtained according to the difference in the dynamic change characteristics of the air quality data in the current time period and each historical time period in the same cluster.

[0120] In laboratory ventilation scenarios, the dynamic characteristics of ventilation-related data may be complex and show different changing patterns at different times and in different situations. Through cluster analysis, laboratory pollutant concentration data can be grouped according to similar needs, thus providing a more accurate reference for real-time prediction. CURE clustering can divide complex dynamic characteristics into different ventilation demand patterns and use them to predict ventilation demand, thereby identifying potential patterns of ventilation demand under different conditions in the laboratory and helping the system respond to dynamic changes in the environment more accurately.

[0121] In an exemplary embodiment, the specific implementation process of clustering based on the dynamic change characteristics of air quality data in each time period is given as follows: Figure 6 As shown, including:

[0122] Step 5-1: Perform preliminary clustering based on the differences in the dynamic change characteristics of air quality data in different time periods.

[0123] Take each time period as a clustering data point, obtain the difference between the dynamic change characteristics of the air quality data of any two time periods, which can be the absolute value of the difference, and use the difference as a distance rule for preliminary clustering. It should be understood that the preliminary clustering adopts the existing commonly used clustering methods, such as hierarchical clustering, K-means algorithm, DBSCAN algorithm, etc. If the K-means algorithm is used, it is necessary to determine the K value.

[0124] Step 5-2: Use the CURE clustering algorithm to cluster the preliminary clustering results again.

[0125] In a laboratory environment, pollutant concentrations, personnel activities, and equipment operating conditions may fluctuate dramatically or be relatively stable over time, and ventilation requirements vary significantly in different time periods. By adjusting the scaling factor, the degree of compression of representative points to the cluster center during the clustering process can be controlled, so that the clustering results can retain the characteristics of abnormal changes while avoiding the interference of noise data, thereby improving the accuracy of clustering.

[0126] In the CURE clustering algorithm, the clustering scaling factor of each time period is obtained by the dynamic change characteristics of the air quality data in each time period. The clustering scaling factor is adjusted to dynamically adjust to the changing characteristics of the laboratory environment. In an exemplary embodiment, the clustering scaling factor is calculated as follows:

[0127] ;

[0128] in, represents the clustering scaling factor of the laboratory pollutant concentration data in the i-th time period; Represents the initial scaling factor, usually set to 0.3.

[0129] It means that the clustering scaling factor is adjusted according to the dynamic change characteristics of the air quality in the laboratory, so that reducing the scaling factor will reduce the dynamic change characteristics of the air quality data to a certain extent, making the clustering more sensitive and suitable for situations where the dynamic air quality fluctuates greatly. The adjusted clustering scaling factor is applied to the CURE clustering process.

[0130] It should be understood that, as another implementation, only the above-mentioned preliminary clustering process may be performed, and subsequent processing may be performed according to the preliminary clustering result.

[0131] In order to achieve accurate ventilation control in laboratory environments, it is necessary to predict ventilation demand to ensure that energy use is optimized, energy waste is reduced, and the stability and comfort of the laboratory environment are maintained while meeting laboratory safety and air quality. By clustering laboratory pollutant concentration data, the typical patterns and changing laws of ventilation demand under different environmental conditions can be identified, so that similar demand scenarios can be grouped. Clustering reflects the relationship between ventilation demand and various environmental factors. Based on the clustering results, ventilation demand in similar situations in the future can be predicted.

[0132] Cluster analysis can group laboratories according to similar air quality characteristics, so that laboratories in the same cluster have similar air quality change patterns and similar ventilation requirements. Through clustering, the cluster in which the current time period is located is obtained, and then the historical time periods in the same cluster as the current time period are obtained. The same cluster represents similar dynamic changes in air quality, so the possible ventilation requirements in the future can be inferred from similar air change patterns.

[0133] Obtain the matching degree between the current time period and each historical time period in the same cluster. The matching degree can be understood as the correlation degree. In an exemplary embodiment, the calculation formula of the matching degree is as follows:

[0134]

[0135] Among them, j represents the jth historical time period in the same cluster as the current time period. Indicates the matching degree between the current time period and the jth historical time period in the same cluster. Indicates the dynamic change characteristics of air quality data in the current time period. Represents the dynamic change characteristics of air quality data in the jth historical time period in the same cluster as the current time period.

[0136] It indicates the difference between the dynamic change characteristics of air quality data in the current time period and the jth historical time period in the same cluster. The smaller the difference, the higher the consistency of the dynamic change characteristics of air quality data, the higher the matching degree, and the more reference significance the data of the jth historical time period has.

[0137] Step 6: According to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster, the ventilation demand is obtained.

[0138] The ventilation demand is calculated as follows:

[0139] ;

[0140] in, represents the ventilation demand, J represents the number of historical time periods in the same cluster as the current time period, Represents the total ventilation volume of the jth historical time period in the same cluster as the current time period.

[0141] It means that the ventilation volume of historical data is weighted averaged according to the matching degree of dynamic changes in air quality. The higher the matching degree of the data segment, the more reference value the corresponding ventilation volume has.

[0142] The ventilation demand is a predicted quantity, which is used as the total ventilation volume for the next time period of the current time period. The ventilation system can be controlled according to the ventilation demand.

[0143] In an exemplary embodiment, Figure 7 As shown, Figure 7 The predicted value and target parameter in are the ventilation demand. The ventilation demand is input into the PID control system of the ventilation system as the set target. The PID control system adjusts the wind speed, air volume, fan load and other related parameters based on the ventilation demand to ensure that the ventilation system can respond to environmental changes in real time and maintain the optimal working state. During the adjustment of the ventilation system, the real-time monitoring system will continuously feedback the changes in various parameters in the laboratory. The feedback data will be input into the PID control system again for comparison with the ventilation demand to ensure that the adjusted settings achieve the desired effect. If there is a deviation or change, the PID control system will make a secondary adjustment based on the new data, continuously optimize the response to the ventilation demand, so as to avoid overshoot or lag, and ultimately achieve the goals of energy saving and optimization, and ensure the stability of the laboratory environment and energy efficiency.

[0144] This embodiment also provides a laboratory ventilation energy-saving automatic control system, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-mentioned laboratory ventilation energy-saving automatic control method embodiment when the program instructions are executed.

[0145] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0146] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A laboratory ventilation energy-saving automatic control method, characterized in that: include: Acquire laboratory pollutant concentration data and laboratory ventilation volume data for each time period; each time period includes a current time period and multiple historical time periods; Based on the laboratory pollutant concentration data of each time period, the ventilation demand degree of each time period is obtained; According to the pollutant concentration decrease amplitude of the pollutant concentration decrease segment in the laboratory pollutant concentration data of each time period, and the corresponding time range and its corresponding laboratory ventilation volume data, the ventilation efficiency characteristics of each time period are obtained; Combining the ventilation demand degree and ventilation efficiency characteristics, the dynamic change characteristics of air quality data in each time period are obtained; Clustering is performed based on the dynamic change characteristics of air quality data in each time period, and the matching degree is obtained according to the difference in the dynamic change characteristics of air quality data in the current time period and each historical time period in the same cluster; According to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster, the ventilation demand is obtained; The degree of ventilation demand in each time period is obtained, including: According to the data fluctuation of the laboratory pollutant concentration data in each time period, the pollutant concentration variation characteristics of each time period are obtained; the pollutant concentration variation characteristics represent the fluctuation degree of the pollutant concentration; According to the pollutant concentration change rate at each sampling moment in the laboratory pollutant concentration data of each time period, the pollution persistence characteristics of each time period are obtained; the pollution persistence characteristics represent the speed of change of the pollutant concentration; According to the pollutant concentration change characteristics and pollution persistence characteristics in each time period, the ventilation demand degree in each time period is obtained; the ventilation demand degree is proportional to the pollutant concentration change characteristics and pollution persistence characteristics; Acquisition of ventilation efficiency characteristics for each time period, including: According to the pollutant concentration decrease amplitude of the pollutant concentration decrease segment in the laboratory pollutant concentration data of each time period, and the corresponding time range and its corresponding laboratory ventilation volume data, the corresponding action relationship between the pollutant concentration and the ventilation volume in each time period, as well as the overall corresponding action relationship between the pollutant concentration and the ventilation volume are obtained; According to the difference between the corresponding relationship between the pollutant concentration and the ventilation volume in each time period and the overall corresponding relationship between the pollutant concentration and the ventilation volume, the ventilation efficiency characteristics of each time period are obtained.

2. A laboratory ventilation energy-saving automatic control method as claimed in claim 1, characterized in that: The process of obtaining the pollutant concentration variation characteristics in each time period includes: Obtain the pollutant concentration range of laboratory pollutant concentration data for each time period; Obtaining target pollutant concentrations higher than a preset pollutant concentration reference value in the laboratory pollutant concentration data for each time period, and obtaining the concentration difference between each target pollutant concentration and the preset pollutant concentration reference value; Based on the pollutant concentration extremes and the concentration differences in each time period, a pollutant concentration variation characteristic in each time period is obtained; the pollutant concentration variation characteristic is proportional to the pollutant concentration extremes and the concentration differences; The process of obtaining the pollution persistence characteristics of each time period includes: ； in, represents the pollution persistence characteristics of the i-th time period; represents the number of pollutant concentrations in the laboratory pollutant concentration data for the i-th time period; represents the first time period in the laboratory pollutant concentration data The value of the pollutant concentration; represents the first time period in the laboratory pollutant concentration data The value of the pollutant concentration; express and The time interval between.

3. A laboratory ventilation energy-saving automatic control method as claimed in claim 1, characterized in that: The process of obtaining the pollutant concentration decreasing section includes: Perform curve fitting on laboratory pollutant concentration data and obtain the extreme points; The laboratory pollutant concentration data is segmented according to each extreme point, and the data segment with the starting point as the maximum value and the ending point as the minimum value is taken as the pollutant concentration decreasing segment.

4. A laboratory ventilation energy-saving automatic control method as claimed in claim 1, characterized in that: The calculation formula for the corresponding relationship between pollutant concentration and ventilation volume in each time period is as follows: ； Among them, i represents the i-th time period, represents the corresponding relationship between the pollutant concentration and the ventilation volume in the i-th time period, M represents the number of pollutant concentration decrease segments in the laboratory pollutant concentration data in the i-th time period, and m represents the m-th pollutant concentration decrease segment in the laboratory pollutant concentration data in the i-th time period. It represents the decrease in the pollution concentration of the mth pollutant concentration decrease segment in the laboratory pollutant concentration data of the i-th time period, It represents the total ventilation volume in the time range corresponding to the mth pollutant concentration drop segment in the laboratory pollutant concentration data of the i-th time period; It represents the length of time corresponding to the time range of the mth pollutant concentration decline segment in the laboratory pollutant concentration data of the i-th time period; Represents an exponential function with the natural constant e as the base.

5. A laboratory ventilation energy-saving automatic control method as claimed in claim 4, characterized in that: The calculation formula for the overall corresponding relationship between pollutant concentration and ventilation volume is as follows: ； in, It represents the overall corresponding relationship between pollutant concentration and ventilation volume, and I represents the number of time periods.

6. A laboratory ventilation energy saving automatic control method as claimed in claim 1, characterized in that: Clustering is performed based on the dynamic change characteristics of air quality data in each time period, including: Based on the differences in the dynamic change characteristics of air quality data in different time periods, preliminary clustering is performed; The CURE clustering algorithm is used to cluster the preliminary clustering results again, wherein the clustering scaling factor of each time period is obtained from the dynamic change characteristics of the air quality data of each time period.

7. A laboratory ventilation energy saving automatic control method as claimed in claim 1, characterized in that: According to the matching degree and the laboratory ventilation volume data of each historical time period in the same cluster, the ventilation demand is obtained, including: The ventilation demand is calculated as follows: ； in, represents the ventilation demand, J represents the number of historical time periods in the same cluster as the current time period, j represents the jth historical time period in the same cluster as the current time period, Indicates the matching degree between the current time period and the jth historical time period in the same cluster. Represents the total ventilation volume of the jth historical time period in the same cluster as the current time period.

8. A laboratory ventilation energy-saving automatic control system, characterized in that it includes: Memory and processor; The memory is connected to the processor; The memory is used to store program instructions; The processor is used to implement the laboratory ventilation energy-saving automatic control method according to any one of claims 1 to 7 when the program instructions are executed.

Images