A method and system for indoor ecological environment design based on digital twin

Abstract

The present invention relates to the field of digital twin simulation technology, specifically a method and system for indoor ecological environment design based on digital twin, comprising the following steps: collecting temperature to calculate hysteresis difference to generate thermal adaptation classification information, monitoring carbon dioxide and leaf area to estimate carbon dissipation ratio, judging ventilation rules to generate control labels, collecting stomatal conductance to adjust disturbance frequency, extracting water vapor pressure and transpiration to generate response labels, and deriving states to generate adjustment label sets. In the present invention, by collecting leaf and root temperature responses to calculate hysteresis difference, identifying thermal disturbance characteristics, extracting individual thermal adaptation differences, monitoring carbon dioxide concentration and leaf area, calculating carbon dissipation ratio to measure carbon metabolism efficiency, assisting ventilation decision-making, combining stomatal conductance and temperature feedback, controlling disturbance frequency to optimize, integrating water vapor pressure difference and transpiration rate, constructing multi-parameter response labels, integrating multi-source data to generate adjustment state labels, and improving ecological regulation capabilities.

Description

Technical Field

[0001] The present invention relates to the field of digital twin simulation technology, and in particular to a method and system for indoor ecological environment design based on digital twin. Background Art

[0002] The field of digital twin simulation technology includes virtual modeling, data-driven construction, dynamic interactive simulation, and real-time feedback updates for real-world physical systems. The core is to establish a digital mapping model of a physical entity by collecting information such as its structure, state, and behavior, and to achieve real-time collaboration between the physical and virtual on a unified platform. This field combines multi-source perception, modeling deduction, and timing control methods to support operational status monitoring, behavior prediction, and optimized regulation in complex environments such as cities, buildings, industries, and medical care. From a systemic perspective, digital twin simulation includes modules such as modeling methods, dynamic data fusion, three-dimensional scene restoration, and full-cycle simulation operations to serve the needs of intelligent management and precise decision support.

[0003] The digital twin-based indoor ecological environment design method and system involves capturing real-time data such as temperature, humidity, lighting, and air quality through environmental sensors during the construction of indoor space environments. This system then uses three-dimensional parametric modeling to reconstruct the indoor physical space and simulates thermal airflow and plant distribution on a digital platform. This system then integrates static parameters such as building orientation, material properties, and ventilation paths to construct a dynamic ecological feedback mechanism. This method also includes pattern learning and spatial regulation factor construction based on user behavior trajectories to adjust the parameters of the local indoor microenvironment and complete the design calculation process for spatial composition, ecological regulation strategies, and layout structures.

[0004] While existing technologies have achieved modeling and reconstruction of indoor physical spaces and the collection and feedback of basic environmental parameters, significant limitations remain in the ecological response dimension. Current approaches mostly focus on simple feedback from macro-indicators such as temperature, humidity, and air quality, ignoring the active response of plants as key biological factors and lacking in-depth analysis of the dynamic interactions between plant heat, carbon, and water. Ecological regulation pathways are often based on static parameters, failing to form a closed feedback loop, resulting in delayed or even mismatched regulatory strategies. For example, ventilation strategies are often triggered by temperature thresholds without considering the actual state of plant physiological behaviors such as stomatal opening and closing and photosynthetic rate, resulting in energy waste or a deterioration of the plant growth environment. Furthermore, existing systems generally lack multi-source data fusion mechanisms, making it impossible to effectively extract correlations between ecological parameters. This results in low feedback accuracy and poor adaptability of the regulatory systems, as well as significant lags in response to complex dynamic environments. This limits the depth and breadth of the systems' application in complex ecological spaces. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiment of the present invention provides a method and system for designing an indoor ecological environment based on digital twins. The technical solution is as follows:

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for designing an indoor ecological environment based on digital twins, comprising the following steps:

[0007] S1: Use thermal sensing components to obtain the leaf temperature and root temperature response time of indoor plants at multiple points in time, calculate the time difference and leaf temperature rise rate, and extract the thermal response hysteresis coefficient. Use linear discriminant analysis to generate thermal adaptability classification information in the digital twin.

[0008] S2: Obtaining the trend of carbon dioxide concentration changes over a continuous period of time and collecting the current leaf area through a gas sensor, calculating the carbon dissipation ratio in combination with a carbon flow rate estimation function, determining whether ventilation control rules are met based on the thermal adaptability classification information and the carbon dissipation ratio, and generating a ventilation control label;

[0009] S201: Collecting concentration data output by the carbon dioxide sensor over a continuous period of time and aligning it according to timestamps, extracting the direction of concentration changes within multiple time periods and analyzing the trend rate, calculating the change direction of the overall sequence after excluding discontinuous segments, and generating a carbon dioxide concentration change trend;

[0010] S202: Based on the carbon dioxide concentration change trend, synchronously collect the current leaf area image and count the leaf area, calculate the ratio between the leaf area carbon output and the total carbon release by using the carbon flow rate estimation function, and obtain the carbon dissipation ratio;

[0011] S203: comparing the carbon dissipation ratio and the thermal adaptability classification information to see whether the intervals of the carbon dissipation ratio in multiple time periods fall within the control boundaries of the corresponding sections of the classification information, identifying whether the rule determination items are met and marking them, thereby generating a ventilation control label;

[0012] S3: calling the ventilation control tag to activate the path switching mechanism, collecting the stomatal conductance state and leaf surface temperature, inputting the Penman-Monteith control function to adjust the air disturbance frequency, selecting the optimal air disturbance frequency, and generating a ventilation adjustment parameter group;

[0013] S4: Based on the ventilation adjustment parameter group, collecting the plant water vapor pressure difference change rate and transpiration change value and extracting the change characteristics to generate a transpiration response label;

[0014] S5: Based on the transpiration response label and carbon dissipation ratio and the thermal response hysteresis coefficient, the regulation path state is derived through a state transition graph model to generate a plant regulation state label set of the ecological environment feedback simulation platform;

[0015] S501: Based on the transpiration response tag, collecting and comparing the carbon dissipation ratios of the plant under multiple environmental adjustment conditions, calculating the carbon dissipation rates under the multiple adjustment conditions, and generating a carbon dissipation ratio variation range;

[0016] S502: Calculating the regulation path state through a state transition diagram model according to the carbon dissipation ratio variation range and the thermal response hysteresis coefficient, and deducing the state transition moment during the regulation process to obtain the regulation path state;

[0017] S503: Based on the correspondence between the regulation path state and the transpiration response label and the carbon dissipation ratio variation range, the thermal response hysteresis effect and the state of the plant under multiple regulation paths are compared to generate a plant regulation state label set of the ecological environment feedback simulation platform.

[0018] As a further solution of the present invention, the thermal adaptability classification information includes the leaf temperature rise rate type, the root response delay level, and the time difference interval type; the ventilation control label includes the carbon dissipation judgment result, the thermal adaptability matching type, and the ventilation rule compliance status; the ventilation adjustment parameter group includes the disturbance frequency value, the stomatal conductance level, and the adjustment trigger threshold; the transpiration response label specifically includes the direction of water vapor pressure difference change, the transpiration change rate level, and the synchronous change corresponding status; the plant adjustment state label set specifically includes the adjustment path type, the state transition node, and the response coordination level.

[0019] As a further solution of the present invention, the following steps are used to obtain the response time of the leaf surface temperature and root temperature of indoor plants at multiple time points through a thermal sensing component, calculate the time difference and the leaf surface temperature rise rate, and extract the thermal response hysteresis coefficient. Then, the thermal adaptability classification information in the digital twin is generated through linear discriminant analysis:

[0020] S101: Continuous thermal sensing records of indoor plant leaf and root temperatures are obtained through a thermal sensing component and compared. The fluctuations and change slopes of the temperature values ​​in multiple intervals are identified and time periods are selected. The time offset lengths corresponding to the multiple time periods are calculated through time series differences to generate a thermal response time difference sequence.

[0021] S102: calling the thermal response time difference sequence to extract the continuous rising intervals of the leaf surface temperature at the same time, calculating and arranging the growth gradient of the temperature change trend corresponding to the slope of the time point, and generating a leaf surface temperature rise rate sequence;

[0022] S103: Based on the thermal response time difference sequence and the leaf surface temperature rise rate sequence, all samples are segmented according to the time difference interval and the temperature rise rate, and classification labels are set to generate thermal adaptability classification information.

[0023] As a further solution of the present invention, the ventilation control tag is called to activate the path switching mechanism, the stomatal conductance state and leaf surface temperature of the leaves are collected, the Penman-Monteith control function is input to adjust the air disturbance frequency, the optimal air disturbance frequency is selected, and the ventilation adjustment parameter group is generated in the following steps:

[0024] S301: activating a path switching mechanism based on the ventilation control tag, collecting a ventilation path switching signal corresponding to the tag state and recording a response state, identifying a starting moment when a plant state variable under the ventilation mechanism shifts, and obtaining a ventilation path response time point;

[0025] S302: collecting and aligning the leaf stomatal conductance state and leaf surface temperature data based on the ventilation path response time point, calculating the airflow disturbance frequency of the leaf surface temperature and stomatal conductance using a Penman-Monteith control function, and generating a disturbance frequency variation interval;

[0026] S303: Segment processing is performed on the disturbance frequency variation interval, the stomatal conductance variation amplitudes corresponding to multiple disturbance frequency segments are screened, the disturbance frequencies corresponding to the stomatal conductance segments that meet the stable range are recorded as target value intervals, and a ventilation adjustment parameter group is obtained.

[0027] As a further solution of the present invention, the airflow disturbance frequency of the leaf surface temperature and stomatal conductance is calculated by the Penman-Monteith control function. , using the formula:

[0028] ;

[0029] in, represents the measured value of leaf surface temperature, Represents the baseline value of canopy air temperature, represents the normalized baseline value of canopy temperature change, Representative The measured value of stomatal conductance at each sampling time point is represents the time series average of stomatal conductance, represents the normalized reference value of stomatal conductance level, represents the air density, represents the specific heat capacity of air at constant pressure, represents the latent heat coefficient of water vapor, Represents the saturated water vapor pressure difference between the leaf surface and the air. Represents the temperature gradient correction.

[0030] As a further solution of the present invention, based on the ventilation adjustment parameter group, the steps of collecting the plant water vapor pressure difference change rate and transpiration change value and extracting the change characteristics to generate the transpiration response label are specifically as follows:

[0031] S401: collecting the leaf surface temperature and the ambient air temperature under the ventilation operation state based on the ventilation adjustment parameter group, converting them into leaf surface water vapor pressure and air water vapor pressure respectively, calculating the difference between the leaf surface water vapor pressure and the air water vapor pressure, and generating a water vapor pressure difference value;

[0032] S402: Calculating the rate of change of the water vapor pressure difference value based on the time interval of the sampling points, collecting and recording the transpiration water loss of the plant under the ventilation state, calculating and integrating the value changes of adjacent sampling points in a continuous interval, and generating a transpiration change value sequence;

[0033] S403: According to the correspondence between the transpiration change value sequence and the water vapor pressure difference change rate in the time dimension, the change direction and change amplitude of the two indicators at each time point are extracted, and classification judgment is performed based on the consistency of the change direction to generate a transpiration response label.

[0034] As a further solution of the present invention, the state of the adjustment path is calculated by the state transition diagram model. , using the formula:

[0035] ;

[0036] in, Represents the instantaneous change in the carbon dissipation ratio of the mth state node, represents the thermal response hysteresis coefficient of the mth monitoring point, is the inertia compensation of the j-th transfer path, represents the weight coefficient of the kth time window, represents the correction factor for the pth heat conduction channel, is the environmental interference factor of the qth sampling period.

[0037] On the other hand, a digital twin-based indoor ecological environment design system is provided. The system is based on a digital twin-based indoor ecological environment design method. The system includes:

[0038] The thermal response module uses a thermal sensing component to obtain the response time of the indoor plant leaf surface temperature and root temperature at multiple time points, calculates the time difference and the leaf surface temperature rise rate, and extracts the thermal response hysteresis coefficient. Through linear discriminant analysis, it generates thermal adaptability classification information in the digital twin and transmits it to the carbon ventilation module;

[0039] The carbon ventilation module uses a gas sensor to obtain the trend of carbon dioxide concentration changes over a continuous period of time and collects the current leaf area, calculates the carbon dissipation ratio in combination with the carbon flow rate estimation function, determines whether the ventilation control rules are met based on the thermal adaptability classification information and the carbon dissipation ratio, generates a ventilation control label, and transmits it to the ventilation adjustment module;

[0040] The ventilation adjustment module calls the ventilation control tag to activate the path switching mechanism, collects the stomatal conductance state and leaf surface temperature, inputs the Penman-Monteith control function to adjust the air disturbance frequency, selects the optimal air disturbance frequency, generates a ventilation adjustment parameter group, and transmits it to the transpiration response module;

[0041] A transpiration response module collects plant water vapor pressure difference change rate and transpiration change value based on the ventilation adjustment parameter group and extracts change characteristics, generates a transpiration response label and transmits it to the state deduction module;

[0042] The state deduction module derives the regulation path state through a state transition diagram model based on the transpiration response label, carbon dissipation ratio and thermal response hysteresis coefficient, and generates a plant regulation state label set of the ecological environment feedback simulation platform.

[0043] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0044] By collecting plant leaf and root temperature responses at different time points and calculating their lagged differences, we can more accurately identify plant responses to environmental thermal perturbations and effectively extract microscopic differences in thermal adaptability among individual plants. Combined with gas sensors continuously monitoring carbon dioxide concentration and leaf area data, the carbon dissipation ratio calculation is introduced to further clarify the plant's carbon metabolism efficiency under a given photosynthetic intensity, providing multi-factor support for initiating ventilation control. After activating the path switching mechanism, an air disturbance frequency control model is constructed based on the plant's real-time stomatal conductance and temperature feedback, seeking a dynamic optimal value between evaporation and cooling. This allows for the dynamic generation of ventilation parameters that better meet plant needs. Combining the characteristics of plant transpiration rate changes with changes in vapor pressure difference, a multi-parameter transpiration response label is constructed, effectively incorporating water cycle feedback information. Finally, a state transition model is constructed to integrate and analyze these multi-source data, including thermal response, carbon exchange, and water regulation, to output a multi-label set reflecting the state of the plant's regulatory mechanism. This sequential processing logic effectively improves the real-time identification, response and regulation capabilities of indoor ecosystems, making the adaptive behavior of plants under multi-factor intervention quantifiable, predictable and intervention-able, thereby achieving more accurate ecological environment dynamic simulation and regulation strategy optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0047] Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0048] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0049] In the embodiments of the present invention, words such as "exemplarily" and "including" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0050] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0051] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0052] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0053] See also Figure 1 The present invention provides a technical solution, a method for designing an indoor ecological environment based on digital twins, comprising the following steps:

[0054] S1: Use thermal sensing components to obtain the leaf temperature and root temperature response time of indoor plants at multiple points in time, calculate the time difference and leaf temperature rise rate, and extract the thermal response hysteresis coefficient. Use linear discriminant analysis to generate thermal adaptability classification information in the digital twin.

[0055] S2: Obtaining the trend of carbon dioxide concentration changes over a continuous period of time and collecting the current leaf area through a gas sensor, calculating the carbon dissipation ratio in combination with a carbon flow rate estimation function, determining whether ventilation control rules are met based on the thermal adaptability classification information and the carbon dissipation ratio, and generating a ventilation control label;

[0056] S201: Collecting concentration data output by the carbon dioxide sensor over a continuous period of time and aligning it according to timestamps, extracting the direction of concentration changes within multiple time periods and analyzing the trend rate, calculating the change direction of the overall sequence after excluding discontinuous segments, and generating a carbon dioxide concentration change trend;

[0057] S202: Based on the carbon dioxide concentration change trend, synchronously collect the current leaf area image and count the leaf area, calculate the ratio between the leaf area carbon output and the total carbon release by using the carbon flow rate estimation function, and obtain the carbon dissipation ratio;

[0058] S203: comparing the carbon dissipation ratio and the thermal adaptability classification information to see whether the intervals of the carbon dissipation ratio in multiple time periods fall within the control boundaries of the corresponding sections of the classification information, identifying whether the rule determination items are met and marking them, thereby generating a ventilation control label;

[0059] S3: calling the ventilation control tag to activate the path switching mechanism, collecting the stomatal conductance state and leaf surface temperature, inputting the Penman-Monteith control function to adjust the air disturbance frequency, selecting the optimal air disturbance frequency, and generating a ventilation adjustment parameter group;

[0060] S4: Based on the ventilation adjustment parameter group, collecting the plant water vapor pressure difference change rate and transpiration change value and extracting the change characteristics to generate a transpiration response label;

[0061] S5: Based on the transpiration response label and carbon dissipation ratio and the thermal response hysteresis coefficient, the regulation path state is derived through a state transition graph model to generate a plant regulation state label set of the ecological environment feedback simulation platform;

[0062] S501: Based on the transpiration response tag, collecting and comparing the carbon dissipation ratios of the plant under multiple environmental adjustment conditions, calculating the carbon dissipation rates under the multiple adjustment conditions, and generating a carbon dissipation ratio variation range;

[0063] S502: Calculating the regulation path state through a state transition diagram model according to the carbon dissipation ratio variation range and the thermal response hysteresis coefficient, and deducing the state transition moment during the regulation process to obtain the regulation path state;

[0064] S503: Based on the correspondence between the regulation path state and the transpiration response label and the carbon dissipation ratio variation range, the thermal response hysteresis effect and the state of the plant under multiple regulation paths are compared to generate a plant regulation state label set for the ecological environment feedback simulation platform.

[0065] Thermal adaptability classification information includes leaf temperature rise rate type, root response delay level, and time difference interval type. Ventilation control labels include carbon dissipation judgment results, thermal adaptability matching type, and ventilation rule compliance status. The ventilation adjustment parameter group includes disturbance frequency value, stomatal conductance level, and adjustment trigger threshold. The transpiration response label specifically includes the direction of water vapor pressure difference change, transpiration change rate level, and synchronous change corresponding status. The plant regulation status label set specifically includes regulation path type, state transition node, and response coordination level.

[0066] See also Figure 1 The thermal sensing component is used to obtain the multi-point temperature of the indoor plant leaves and the root temperature response time, calculate the time difference and the leaf temperature rise rate, and extract the thermal response hysteresis coefficient. The linear discriminant analysis is used to judge and generate the thermal adaptability classification information in the digital twin. The specific steps are as follows:

[0067] S101: Continuous thermal sensing records of indoor plant leaf and root temperatures are obtained through a thermal sensing component and compared. The fluctuations and change slopes of the temperature values ​​in multiple intervals are identified and time periods are selected. The time offset lengths corresponding to the multiple time periods are calculated through time series differences to generate a thermal response time difference sequence.

[0068] Based on the leaf surface temperature collected by the thermal sensing component ( ) and root temperature ( ) data, recorded continuously for 48 hours with a sampling interval of 15 minutes, and divided the temperature data into preset intervals: low temperature interval (18-22℃), medium temperature interval (22-26℃), and high temperature interval (26-30℃). When the leaf surface temperature is in the same interval for three consecutive sampling points, it is marked as a stable period. When calculating the temperature change slope of adjacent periods, the ratio of the temperature difference between the beginning and the end of the period to the time difference is taken. In the period [09:00-11:00], the leaf surface temperature rises from 22.3℃ to 24.8℃, with a time difference of 120 minutes. The slope is calculated as , screen the periods with slope absolute values ​​greater than 0.015℃ / min as valid fluctuation segments, match the timestamps of the valid fluctuation segments of the leaf surface and the root system, and calculate the corresponding time offset by taking the difference between the start time of the leaf surface fluctuation segment and the start time of the most recent root fluctuation segment. If the leaf surface fluctuation segment starts at 09:00 and the corresponding root segment starts at 09:12, the time offset is 12 minutes, generating a sequence of 32 sets of time differences (see Table 1);

[0069] Table 1 Example of thermal response time difference

[0070]

[0071] As shown in Table 1, the time difference includes positive and negative values. Positive values ​​indicate that the root system responds laggingly, and negative values ​​indicate that the root system responds ahead of time. Statistics show that 82% of the time period differences are concentrated within the range of ±20 minutes.

[0072] S102: Calling the thermal response time difference sequence to extract the continuous rising intervals of the leaf surface temperature at the same time, calculating and arranging the growth gradient of the temperature change trend corresponding to the slope of the corresponding time point, and generating a leaf surface temperature rise rate sequence;

[0073] The time difference sequence in Table 1 was called to locate the continuous rising interval on the leaf temperature curve, which was defined as: the temperature increase of 5 consecutive sampling points exceeded 0.5℃ and the slope increased, including the temperature rising from 23.1℃ to 25.6℃ during the period [14:00-15:00]. The instantaneous slope of multiple time points was calculated. When , the three-point central difference method is used: ,when When, take 、 , the instantaneous slope is calculated , the growth gradient is calculated using the ratio of adjacent slopes, when 、 hour, , generating a sequence of 28 sets of gradient values, of which the gradient values ​​1.15-1.25 account for 64%.

[0074] S103: Based on the thermal response time difference sequence and the leaf surface temperature rise rate sequence, all samples are segmented according to the time difference interval and the temperature rise rate, and classification labels are set to generate thermal adaptability classification information;

[0075] The time difference is divided into three intervals: short time difference (<10min), medium time difference (10-20min), and long time difference (20min). The temperature rise rate is divided according to the gradient value: low growth rate (<1.1), medium growth rate (1.1-1.3), and high growth rate (1.3). The time difference interval and the growth rate interval are combined to form 9 classification labels, including a time difference of 15min (medium time difference) with a gradient of 1.25 (medium growth rate) marked as Class B2. When setting the classification weight, the samples that meet both the medium time difference and medium growth rate are given a benchmark weight. If the time difference exceeds 20 minutes, the weight adjustment coefficient , including a single sample time difference of 22 minutes, a gradient of 1.28, and calculation weights , through 325 groups of sample tests, thermal adaptability classification information including 6 key categories was generated, of which Class C1 (short time difference + high growth rate) accounted for 17.2%, and Class B2 (medium time difference + medium growth rate) accounted for 38.5%.

[0076] See also Figure 1The gas sensor is used to obtain the trend of carbon dioxide concentration changes over a continuous period of time and the current leaf area. The carbon dissipation ratio is calculated in combination with the carbon flow rate estimation function. Based on the thermal adaptability classification information and the carbon dissipation ratio, it is determined whether the ventilation control rules are met. The specific steps for generating ventilation control labels are as follows:

[0077] S201: Collecting concentration data output by the carbon dioxide sensor over a continuous period of time and aligning it according to timestamps, extracting the direction of concentration changes within multiple time periods and analyzing the trend rate, calculating the change direction of the overall sequence after excluding discontinuous segments, and generating a carbon dioxide concentration change trend;

[0078] The carbon dioxide sensor collects 72 hours of concentration data at 5-minute intervals. , linear interpolation correction is used for data points with timestamp deviation exceeding 30 seconds, and the trend rate is defined as the concentration change in the adjacent 15-minute window. When the data integrity in the window is less than 80%, it is marked as a discontinuous segment, including the missing of 3 data points in the [08:00-08:15] window (completeness 75%), then the segment is eliminated. When calculating the trend direction of the valid segment, the concentration difference between the beginning and the end of the window is taken. , represents the concentration at which the window ends, Represents the concentration at the start of the window. When marked as an upward trend, is a downward trend, and the rest are classified as stable. As shown in Table 2, among the 24 valid paragraphs, the upward trend accounts for 58.3%;

[0079] Table 2 Carbon dioxide concentration trend analysis

[0080]

[0081] As shown in Table 2, the trend rate is calculated as the absolute value , when paragraph 1 When the reference rate exceeds 0.3ppm / min, it is classified as a drastic change.

[0082] S202: Based on the trend of carbon dioxide concentration changes, the current leaf area image is synchronously collected and the leaf area is counted. The ratio between the carbon output of the leaf area and the total carbon release is calculated using the carbon flow rate estimation function to obtain the carbon dissipation ratio;

[0083] Use image recognition algorithm to count the number of pixels in the leaf area , through the calibration coefficient Convert to current area , when the image is parsed hour, , defining carbon output , where the gas flow rate Measured by wind speed sensor, time interval ,but , total carbon release Take the sensor cumulative value, when When the carbon dissipation ratio , after 12 sets of experiments, the ratio range was measured to be between 0.00012-0.00045.

[0084] S203: Based on the carbon dissipation ratio and the thermal adaptability classification information, compare whether the interval of the carbon dissipation ratio in multiple time periods falls within the control boundary of the section corresponding to the classification information, identify whether the rule judgment item is met and mark it, and generate a ventilation control label;

[0085] Set the control boundary to the carbon dissipation ratio range of thermal adaptability classification B2 [0.00035, 0.00045]. When the time difference parameter is obtained from the heat classification information of the time period , the judgment condition is and , trigger ventilation tag FLAG=1, weight coefficient Set the piecewise function: when the period ratio When the upper limit of the range is exceeded , within the interval , below the range , including when When the classification is C1, since the C1 benchmark interval is [0.00040, 0.00050], the calculation is , 37 ventilation control labels were generated in 89 detection periods.

[0086] See also Figure 1 , call the ventilation control tag to activate the path switching mechanism, collect the leaf stomatal conductance state and leaf surface temperature, input the Penman-Monteith control function to adjust the air disturbance frequency, select the optimal air disturbance frequency, and generate the ventilation adjustment parameter group in the following steps:

[0087] S301: Activate the path switching mechanism based on the ventilation control tag, collect the ventilation path switching signal corresponding to the tag state and record the response state, identify the starting time of the plant state variable transfer under the ventilation mechanism, and obtain the ventilation path response time point;

[0088] Based on the trigger signal of ventilation control tag FLAG=1, the voltage value of DO1 port of PLC controller is read through RS485 interface. When the voltage jumps from 0V to 24V, it is recorded as the time when the switching signal takes effect. , synchronously monitor leaf transpiration rate ,when When the increase of three consecutive sampling points exceeds 10%, it is determined as the starting point of state transfer , including when the switching signal takes effect When the leaf transpiration rate The sequence is [2.1, 2.3, 2.6], and the calculated increase sequence is [9.5%, 13.0%]. Since the increase in the second interval exceeds 10%, take , get 12 groups of response time differences ,As shown in Table 3, the time difference is concentrated in the range of 25-40 seconds;

[0089] Table 3 Ventilation response time record

[0090]

[0091] As shown in Table 3, the key distribution of system response delay is in the overlapping interval of equipment mechanical action time (20s) and plant physiological response time (5-15s).

[0092] S302: collecting and aligning leaf stomatal conductance state and leaf surface temperature data based on ventilation path response time points, calculating the airflow disturbance frequency of leaf surface temperature and stomatal conductance using a Penman-Monteith control function, and generating a disturbance frequency variation interval;

[0093] Stomatal conductance was collected every 30 seconds using an AP4 porometer. , and simultaneously measure the leaf surface temperature with a FLIRT540 infrared thermal imager , The leaf surface temperature is measured by a non-contact infrared thermal imager at a distance of 10 cm from the leaf surface, with a measurement accuracy of ±0.5°C. The FLIRT540 device measured a value of 301.65K in an environment of 28.5°C. It represents the baseline value of canopy air temperature, which is continuously monitored by a height-calibrated temperature and humidity sensor (SHT85) suspended in the middle of the plant canopy and recorded every 5 minutes. , The reference value for canopy temperature change is experimentally set to the optimum temperature for plant photosynthesis, 25°C (298.15K), and has been verified by 12 plant species. The stomatal conductance at the i-th sampling time point is measured using an AP4 porometer at three randomly selected locations on the underside of the leaf, taking the average value. This includes the third measurement value of 0.33 mol / m² / s. Represents the average value of the stomatal conductance time series. When n=5 and the measurement sequence is [0.32, 0.35, 0.38, 0.41, 0.39], it is calculated to be 0.37mol / m² / s. Represents the reference value of stomatal conductance level, which is set to 80% of the maximum stomatal conductance value of the tested plant. When the maximum value monitored is 0.5, it is taken as 0.4. Represents the air density, through the formula Calculated, where atmospheric pressure P = 101.325 kPa, air gas constant , the temperature T takes the measured value, Represents the specific heat capacity of air at constant pressure, set to 1005, and refer to the physical property parameter table under ISO standard atmospheric conditions (temperature 20°C, humidity 50%). Represents the latent heat coefficient of water vapor, which is 2.45MJ / kg and is determined based on the latent heat of vaporization of water at 25°C in international units. Represents the saturated water vapor pressure difference between the leaf surface and the air, calculated by Tetens formula: ,in is the current water vapor pressure of the air, , represents the measured value of leaf surface temperature, Represents the temperature gradient correction, take , substituting into the formula we get: ; This value indicates that the airflow disturbance frequency is at an extremely low level under this environmental condition.

[0094] S303: Segment processing is performed on the disturbance frequency variation interval, the stomatal conductance variation amplitudes corresponding to the multiple disturbance frequency segments are screened, and the disturbance frequencies corresponding to the stomatal conductance segments that meet the stable range are recorded as the target value interval to obtain the ventilation adjustment parameter group;

[0095] The air flow disturbance frequency Divided into three intervals: low frequency, medium frequency, and high frequency. The stable range is defined as the fluctuation rate of stomatal conductance. ,in represents the measured value of stomatal conductance, Represents the average value of stomatal conductance time series. (intermediate frequency) and corresponding When the volatility is 12%, it is marked as a valid target interval. When setting the target value boundary, the frequency range in which 8 out of 10 consecutive sampling points meet the volatility condition is selected. 18 groups of valid target values ​​are screened from 56 groups of data, and the mid-frequency range accounts for 72.2%. The ventilation adjustment parameter group is generated, including the target frequency mean. .

[0096] See also Figure 1 Based on the ventilation adjustment parameter group, the steps of collecting the plant water vapor pressure difference change rate and transpiration change value and extracting the change characteristics to generate the transpiration response label are as follows:

[0097] S401: collecting the leaf surface temperature and the ambient air temperature under the ventilation operation state based on the ventilation adjustment parameter group, converting them into leaf surface water vapor pressure and air water vapor pressure respectively, calculating the difference between the leaf surface water vapor pressure and the air water vapor pressure, and generating a water vapor pressure difference value;

[0098] Target frequency based on ventilation parameter set Settings, Represents the measured value of leaf surface temperature, using PT1000 platinum resistance temperature sensor to collect leaf surface temperature at 1 minute intervals (unit: °C) and canopy air temperature , when measured When the leaf saturated water vapor pressure is calculated by Tetens formula , and the relative humidity of the air is measured using the HMP155 humidity sensor , calculate the current water vapor pressure of the air ( hour ), Represents the air saturated water vapor pressure, water vapor pressure difference ,6 hours of continuous data collection generated 48 sets of difference records (see Table 4);

[0099] Table 4 Water vapor pressure difference value record table

[0100]

[0101] As shown in Table 4, the vapor pressure difference value increases during the noon period due to the increase in leaf temperature.

[0102] S402: Calculate the rate of change of the difference in water vapor pressure difference based on the time interval of the sampling points, collect and record the transpiration water loss of plants under ventilation conditions, calculate and integrate the value changes of adjacent sampling points in a continuous interval, and generate a transpiration change value sequence;

[0103] Set the sampling interval , calculate the rate of change of water vapor pressure difference , when the water vapor pressure during 09:00-09:05 When the water vapor pressure difference increases from 1.52kPa to 1.68kPa, the rate of change of the water vapor pressure difference , and simultaneously measure transpiration using the weighing method (Unit: g), the weight of the container is reduced from 502.3g to 501.7g, then , integrating 24 sets of data to generate a sequence, where the maximum rate of change is Corresponding transpiration changes .

[0104] S403: Based on the correspondence between the transpiration change value sequence and the water vapor pressure difference change rate in the time dimension, the change direction and change amplitude of the two indicators at each time point are extracted, and classification judgment is performed based on the consistency of the change direction to generate a transpiration response label;

[0105] Define the consistency rule of change direction: and When it is marked as a positive response, and is a negative response, and the rest are abnormal responses. Represents the rate of change of the water vapor pressure difference, and the amplitude matching condition is set to , Represents the change in transpiration. 、 When the ratio If the conditions are met, they are marked as Class A labels. 87 valid labels are generated in 132 sets of data, of which Class A accounts for 63.2% and Class C (abnormal response) accounts for 11.5%.

[0106] See also Figure 1 Based on the transpiration response label and carbon dissipation ratio and the thermal response hysteresis coefficient, the regulation path state is derived through the state transition graph model, and the steps of generating the plant regulation state label set of the ecological environment feedback simulation platform are as follows:

[0107] S501: Based on the transpiration response tag, collect and compare the carbon dissipation ratios of the plant under multiple environmental adjustment conditions, calculate the carbon dissipation rates under the multiple adjustment conditions, and generate a carbon dissipation ratio variation range;

[0108] Based on the environmental data corresponding to the Class A transpiration response tags (accounting for 63.2%), the carbon dissipation ratio was measured every 15 minutes using the LI-6400XT photosynthetic meter under three conditions: temperature set at 25°C / humidity 60%, 28°C / humidity 50%, and 22°C / humidity 70%. When the temperature rises from 25℃ to 28℃, the carbon dissipation ratio Calculate the carbon dissipation rate from 0.00038 to 0.00043 , obtained during 72 hours of monitoring The fluctuation range is [0.00032, 0.00047], and as shown in Table 5, it reaches its peak during the noon period.

[0109] Table 5 Carbon dissipation ratio change table

[0110]

[0111] As shown in Table 5, condition 2 (high temperature and low humidity) leads to an increase of 15.8% in the upper bound of the carbon dissipation ratio.

[0112] S502: Calculate the regulation path state through a state transition diagram model based on the carbon dissipation ratio variation range and the thermal response hysteresis coefficient, and deduce the state transition moment during the regulation process to obtain the regulation path state;

[0113] Select the thermal response hysteresis coefficient, Represents the instantaneous change of the carbon dissipation ratio of the mth state node, through the two adjacent sampling points The carbon dissipation ratio at 09:00 is obtained by subtracting the absolute value. 09:15 ,but , The thermal response hysteresis coefficient of the mth monitoring point is measured by the time difference from the start of ventilation to the beginning of leaf temperature change, including the detection of leaf temperature rise at 8 minutes after ventilation is started. , Represents the inertia compensation of the jth transfer path, which is set to 10%-15% of the hysteresis coefficient according to the equipment mass. When using a stainless steel air valve (mass 12kg), ,like but , Represents the weight coefficient of the kth time window. The time period weight is divided according to the light intensity. The setting principle is: photosynthetically active radiation > 800 hours (noon) , 400-800 (morning / afternoon) , <400 (morning and evening) , Represents the correction factor for the pth heat conduction channel, set according to the pipe material: Copper pipe: (thermal conductivity 401W / mK), Represents the environmental interference factor of the qth sampling period, through the wind speed fluctuation rate (Unit: %) converted to , when the anemometer measures a 10-minute average wind speed of 2.5m / s and a fluctuation range of 2.3-2.7m / s, ,but Substitute into the formula to calculate: , which is lower than the threshold of 0.0005 and is determined to be a stable transfer path.

[0114] S503: Based on the correspondence between the regulation path state and the transpiration response label and the carbon dissipation ratio variation range, the thermal response hysteresis effect and the state of the plant under multiple regulation paths are compared to generate a plant regulation state label set for the ecological environment feedback simulation platform;

[0115] Define status label rules: When the path status If the transpiration label is Class A, it is marked as S1 (Excellent). The label class B is S2 (good), and the rest are S3 (to be optimized). Among the 18 groups of data under condition 2, the S1 status accounts for 66.7% (corresponding to The average value is 0.00029), and the S3 state only appears in the carbon dissipation ratio And during the period when the wind speed fluctuation is >8%, the plant regulation state label set of the ecological environment feedback simulation platform is generated.

[0116] See also Figure 2 A digital twin-based indoor ecological environment design system is provided. The digital twin-based indoor ecological environment design system is used to execute the above-mentioned digital twin-based indoor ecological environment design method. The system includes:

[0117] The thermal response module uses a thermal sensing component to obtain the response time of the indoor plant leaf surface temperature and root temperature at multiple time points, calculates the time difference and the leaf surface temperature rise rate, and extracts the thermal response hysteresis coefficient. Through linear discriminant analysis, it generates thermal adaptability classification information in the digital twin and transmits it to the carbon ventilation module;

[0118] The carbon ventilation module uses gas sensors to obtain the trend of carbon dioxide concentration changes over a continuous period of time and collects the current leaf area. It then calculates the carbon dissipation ratio using a carbon flow rate estimation function. Based on the thermal adaptability classification information and the carbon dissipation ratio, it determines whether the ventilation control rules are met, generates a ventilation control label, and transmits it to the ventilation regulation module.

[0119] The ventilation control module calls the ventilation control tag to activate the path switching mechanism, collects the stomatal conductance state and leaf surface temperature, inputs the Penman-Monteith control function to adjust the air disturbance frequency, selects the optimal air disturbance frequency, generates a ventilation control parameter group, and passes it to the transpiration response module;

[0120] The transpiration response module collects the plant water vapor pressure difference change rate and transpiration change value based on the ventilation adjustment parameter group, extracts the change characteristics, generates the transpiration response label and passes it to the state deduction module;

[0121] The state deduction module, based on the transpiration response label, carbon dissipation ratio and thermal response hysteresis coefficient, derives the regulation path state through the state transition graph model and generates the plant regulation state label set of the ecological environment feedback simulation platform.

[0122] It should be understood that the term "and / or" in this document simply describes an association between related objects, indicating that three possible relationships exist, including A and / or B. This can mean: A exists alone, A and B exist simultaneously, or B exists alone. A and B can be singular or plural. Furthermore, the character " / " in this document generally indicates an "or" relationship between the related objects, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0123] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0124] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use multiple methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0126] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. Including, the device embodiments described above are merely illustrative, including, the division of units, which is only a logical function division, and there may be other division methods in actual implementation, including that multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The indoor ecological environment design method based on digital twin is characterized by: The method comprises: S1: Use thermal sensing components to obtain the leaf temperature and root temperature response time of indoor plants at multiple points in time, calculate the time difference and leaf temperature rise rate, and extract the thermal response hysteresis coefficient. Use linear discriminant analysis to generate thermal adaptability classification information in the digital twin. S2: Obtaining the trend of carbon dioxide concentration changes over a continuous period of time and collecting the current leaf area through a gas sensor, calculating the carbon dissipation ratio in combination with a carbon flow rate estimation function, determining whether ventilation control rules are met based on the thermal adaptability classification information and the carbon dissipation ratio, and generating a ventilation control label; S201: Collecting concentration data output by the carbon dioxide sensor over a continuous period of time and aligning it according to timestamps, extracting the direction of concentration changes within multiple time periods and analyzing the trend rate, calculating the change direction of the overall sequence after excluding discontinuous segments, and generating a carbon dioxide concentration change trend; S202: Based on the carbon dioxide concentration change trend, synchronously collect the current leaf area image and count the leaf area, calculate the ratio between the leaf area carbon output and the total carbon release by using the carbon flow rate estimation function, and obtain the carbon dissipation ratio; S203: comparing the carbon dissipation ratio and the thermal adaptability classification information to see whether the intervals of the carbon dissipation ratio in multiple time periods fall within the control boundaries of the corresponding sections of the classification information, identifying whether the rule determination items are met and marking them, thereby generating a ventilation control label; S3: calling the ventilation control tag to activate the path switching mechanism, collecting the stomatal conductance state and leaf surface temperature, inputting the Penman-Monteith control function to adjust the air disturbance frequency, selecting the optimal air disturbance frequency, and generating a ventilation adjustment parameter group; S4: Based on the ventilation adjustment parameter group, collecting the plant water vapor pressure difference change rate and transpiration change value and extracting the change characteristics to generate a transpiration response label; S5: Based on the transpiration response label and carbon dissipation ratio and the thermal response hysteresis coefficient, the regulation path state is derived through a state transition graph model to generate a plant regulation state label set of the ecological environment feedback simulation platform; S501: Based on the transpiration response tag, collecting and comparing the carbon dissipation ratios of the plant under multiple environmental adjustment conditions, calculating the carbon dissipation rates under the multiple adjustment conditions, and generating a carbon dissipation ratio variation range; S502: Calculating the regulation path state through a state transition diagram model according to the carbon dissipation ratio variation range and the thermal response hysteresis coefficient, and deducing the state transition moment during the regulation process to obtain the regulation path state; S503: Based on the correspondence between the regulation path state and the transpiration response label and the carbon dissipation ratio variation range, the thermal response hysteresis effect and the state of the plant under multiple regulation paths are compared to generate a plant regulation state label set of the ecological environment feedback simulation platform.

2. The indoor ecological environment design method based on digital twin according to claim 1 is characterized in that: The thermal adaptability classification information includes the leaf temperature rise rate type, the root response delay level, and the time difference interval type; the ventilation control label includes the carbon dissipation judgment result, the thermal adaptability matching type, and the ventilation rule compliance status; the ventilation adjustment parameter group includes the disturbance frequency value, the stomatal conductance level, and the adjustment trigger threshold; the transpiration response label specifically includes the direction of water vapor pressure difference change, the transpiration change rate level, and the corresponding state of synchronous change; the plant adjustment state label set specifically includes the adjustment path type, the state transition node, and the response coordination level.

3. The indoor ecological environment design method based on digital twin according to claim 1 is characterized in that: The thermal sensing component is used to obtain the leaf temperature and root temperature response time of indoor plants at multiple points in time. The time difference and leaf temperature rise rate are calculated, and the thermal response hysteresis coefficient is extracted. The linear discriminant analysis is used to determine the thermal adaptability classification information in the digital twin. The specific steps are as follows: S101: Continuous thermal sensing records of indoor plant leaf and root temperatures are obtained through a thermal sensing component and compared. The fluctuations and change slopes of the temperature values ​​in multiple intervals are identified and time periods are selected. The time offset lengths corresponding to the multiple time periods are calculated through time series differences to generate a thermal response time difference sequence. S102: calling the thermal response time difference sequence to extract the continuous rising intervals of the leaf surface temperature at the same time, calculating and arranging the growth gradient of the temperature change trend corresponding to the slope of the time point, and generating a leaf surface temperature rise rate sequence; S103: Based on the thermal response time difference sequence and the leaf surface temperature rise rate sequence, all samples are segmented according to the time difference interval and the temperature rise rate, and classification labels are set to generate thermal adaptability classification information.

4. The indoor ecological environment design method based on digital twin according to claim 1 is characterized in that: The ventilation control tag is called to activate the path switching mechanism, the stomatal conductance state and leaf surface temperature are collected, the Penman-Monteith control function is input to adjust the air disturbance frequency, the optimal air disturbance frequency is selected, and the ventilation adjustment parameter group is generated as follows: S301: activating a path switching mechanism based on the ventilation control tag, collecting a ventilation path switching signal corresponding to the tag state and recording a response state, identifying a starting moment when a plant state variable under the ventilation mechanism shifts, and obtaining a ventilation path response time point; S302: collecting and aligning the leaf stomatal conductance state and leaf surface temperature data based on the ventilation path response time point, calculating the airflow disturbance frequency of the leaf surface temperature and stomatal conductance using a Penman-Monteith control function, and generating a disturbance frequency variation interval; S303: Segment processing is performed on the disturbance frequency variation interval, the stomatal conductance variation amplitudes corresponding to multiple disturbance frequency segments are screened, the disturbance frequencies corresponding to the stomatal conductance segments that meet the stable range are recorded as target value intervals, and a ventilation adjustment parameter group is obtained.

5. The indoor ecological environment design method based on digital twin according to claim 4 is characterized in that: The airflow disturbance frequency of leaf surface temperature and stomatal conductance is calculated by the Penman-Monteith control function , using the formula: ； in, represents the measured value of leaf surface temperature, Represents the baseline value of canopy air temperature, represents the normalized baseline value of canopy temperature change, Representative The measured value of stomatal conductance at each sampling time point is represents the time series average of stomatal conductance, represents the normalized reference value of stomatal conductance level, represents the air density, represents the specific heat capacity of air at constant pressure, represents the latent heat coefficient of water vapor, Represents the saturated water vapor pressure difference between the leaf surface and the air. Represents the temperature gradient correction.

6. The indoor ecological environment design method based on digital twin according to claim 1 is characterized in that: Based on the ventilation adjustment parameter group, the steps of collecting the plant water vapor pressure difference change rate and transpiration change value and extracting the change characteristics to generate the transpiration response label are specifically as follows: S401: collecting the leaf surface temperature and the ambient air temperature under the ventilation operation state based on the ventilation adjustment parameter group, converting them into leaf surface water vapor pressure and air water vapor pressure respectively, calculating the difference between the leaf surface water vapor pressure and the air water vapor pressure, and generating a water vapor pressure difference value; S402: Calculating the rate of change of the water vapor pressure difference value based on the time interval of the sampling points, collecting and recording the transpiration water loss of the plant under the ventilation state, calculating and integrating the value changes of adjacent sampling points in a continuous interval, and generating a transpiration change value sequence; S403: According to the correspondence between the transpiration change value sequence and the water vapor pressure difference change rate in the time dimension, the change direction and change amplitude of the two indicators at each time point are extracted, and classification judgment is performed based on the consistency of the change direction to generate a transpiration response label.

7. The indoor ecological environment design method based on digital twin according to claim 1 is characterized in that: The state of the adjustment path is calculated by the state transition diagram model , using the formula: ； in, Represents the instantaneous change in the carbon dissipation ratio of the mth state node, represents the thermal response hysteresis coefficient of the mth monitoring point, is the inertia compensation of the j-th transfer path, represents the weight coefficient of the kth time window, represents the correction factor for the pth heat conduction channel, is the environmental interference factor of the qth sampling period.

8. An indoor ecological environment design system based on digital twins, characterized by: The system is used to implement the indoor ecological environment design method based on digital twins according to any one of claims 1 to 7, and the system includes: The thermal response module uses a thermal sensing component to obtain the response time of the indoor plant leaf surface temperature and root temperature at multiple time points, calculates the time difference and the leaf surface temperature rise rate, and extracts the thermal response hysteresis coefficient. Through linear discriminant analysis, it generates thermal adaptability classification information in the digital twin and transmits it to the carbon ventilation module; The carbon ventilation module uses a gas sensor to obtain the trend of carbon dioxide concentration changes over a continuous period of time and collects the current leaf area, calculates the carbon dissipation ratio in combination with the carbon flow rate estimation function, determines whether the ventilation control rules are met based on the thermal adaptability classification information and the carbon dissipation ratio, generates a ventilation control label, and transmits it to the ventilation adjustment module; The ventilation adjustment module calls the ventilation control tag to activate the path switching mechanism, collects the stomatal conductance state and leaf surface temperature, inputs the Penman-Monteith control function to adjust the air disturbance frequency, selects the optimal air disturbance frequency, generates a ventilation adjustment parameter group, and transmits it to the transpiration response module; A transpiration response module collects plant water vapor pressure difference change rate and transpiration change value based on the ventilation adjustment parameter group and extracts change characteristics, generates a transpiration response label and transmits it to the state deduction module; The state deduction module derives the regulation path state through a state transition diagram model based on the transpiration response label, carbon dissipation ratio and thermal response hysteresis coefficient, and generates a plant regulation state label set of the ecological environment feedback simulation platform.

Images