Intelligent fresh air handling unit self-adaptive environment regulation and control method and system based on Internet of Things

Abstract

The invention relates to the technical field of intelligent environment regulation and control, and particularly discloses an intelligent fresh air handling unit self-adaptive environment regulation and control method and system based on the Internet of Things. Temperature and humidity data are collected in real time through multi-source sensors deployed indoors and outdoors, and a temperature stability characteristic value is calculated through zero-sequence processing and fast Fourier transform; a humidity change rate characteristic value is extracted by combining first-order difference processing and Haar wavelet transform; the feature values are constructed into a comprehensive environment state feature vector, and the comprehensive environment state feature vector is input into a trained random forest model for environment regulation and control effect evaluation; according to the method, the sensing technology, signal analysis and machine learning prediction are fused, the sensing ability, the regulation and control precision and the self-adaptability of the system are improved, and the method is suitable for complex and changeable environment scenes and has good application prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent environment control, and particularly to an adaptive environment control method and system for an intelligent fresh air unit based on the Internet of Things. Background Art

[0002] With the rapid development of the Internet of Things and intelligent building technologies, indoor environment control systems are evolving towards intelligence and refinement. As an important device for improving indoor air quality and regulating temperature and humidity, fresh air systems are widely used in places such as residences, offices, hospitals, and data centers. Modern fresh air systems usually rely on sensor networks to collect indoor and outdoor environmental parameters, such as temperature and humidity, and perform operation control based on set thresholds or fixed strategies. In recent years, with the introduction of artificial intelligence and big data analysis technologies, data-driven environment control methods have gradually become a research hotspot, aiming to improve the adaptive ability and control efficiency of the system. Achieving real-time perception and intelligent decision-making of the environmental state through the combination of multi-source sensing, signal processing, and machine learning has become an important direction for the optimization and upgrade of the new generation of fresh air units.

[0003] The existing technologies have the following deficiencies: Although the current fresh air systems have a certain level of intelligence in terms of hardware configuration and basic control logic, there are still many problems in practical applications. First, most systems only rely on simple threshold judgment methods for control, lacking in-depth analysis of environmental change trends, and it is difficult to accurately identify the stability of temperature fluctuations and the characteristics of abnormal humidity changes, resulting in frequent response lags or misadjustments. Second, traditional methods often ignore the time series characteristics of environmental data and fail to effectively extract key feature information, restricting the improvement of control accuracy and prediction ability. In addition, existing control systems generally lack a dynamic adaptive mechanism and cannot flexibly adjust operation strategies according to factors such as seasonal changes and sudden weather changes, causing energy waste or a decline in user experience. Therefore, there is an urgent need for a new control method that can integrate multi-source sensing data, deep feature extraction, and intelligent prediction models to achieve efficient, stable, and intelligent management of indoor and outdoor environments. Summary of the Invention

[0004] The purpose of the present invention is to provide an adaptive environment control method and system for an intelligent fresh air unit based on the Internet of Things to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions: An adaptive environment control method for an intelligent fresh air unit based on the Internet of Things includes the following steps: S1: Real-time collect temperature data and humidity data through multi-source sensors deployed in indoor and outdoor environments; The multi-source sensors include: temperature sensors and humidity sensors; S2: Perform zero-sequence processing on the collected temperature data, construct a zero-sequence temperature sequence, and calculate the temperature stability characteristic value for evaluating the stability of the current ambient temperature fluctuation. S3: Perform first-order difference processing on the humidity data, construct a differential humidity sequence, and calculate the humidity change rate characteristic value for identifying whether there is a potential abnormality in the ambient humidity. S4: Construct a comprehensive environmental state characteristic vector from the temperature stability characteristic value and the humidity change rate characteristic value, and input it into the trained machine learning model for evaluating the environmental regulation effect. S5: Dynamically adjust the operating parameters of the fresh air unit according to the evaluation result to achieve adaptive regulation of the indoor and outdoor environment.

[0006] As a further solution of the present invention: The evaluation of the stability of the current ambient temperature fluctuation specifically includes: Collect temperature data in real time according to the time series through temperature sensors deployed in the indoor and outdoor environments, perform zero-sequence processing on the collected temperature data, construct a zero-sequence temperature sequence, calculate the temperature stability characteristic value according to the fluctuation degree of the zero-sequence temperature sequence, and judge whether the temperature stability characteristic value is greater than or equal to the preset threshold. If so, the current ambient temperature fluctuation is unstable; if not, the current ambient temperature fluctuation is stable.

[0007] As a further solution of the present invention: The process of obtaining the temperature stability characteristic value is as follows: Obtain the temperature data collected in real time and integrate it into a temperature time series. Use a linear regression model to fit the trend term of the temperature time series, specifically, use the least squares method to perform a linear fit on the relationship between the time points and the corresponding temperature values to obtain the best fit straight line equation; then calculate the trend value corresponding to each time point according to the fit straight line equation, and subtract the corresponding trend value from the original temperature time series point by point to obtain the temperature fluctuation sequence after removing the linear trend, that is, the zero-sequence temperature sequence. Perform a fast Fourier transform on the temperature sequence after zero-sequence processing to obtain a frequency domain signal sequence. Determine the frequency resolution and divide the frequency range according to the sampling frequency and the number of data points, and set the target frequency range. Calculate the sum of the power spectral densities of the frequency components within the target frequency range to obtain the temperature stability characteristic value.

[0008] As a further solution of the present invention: The identification of whether there is a potential abnormality in the ambient humidity specifically includes: Humidity data is collected in real time according to a time series by humidity sensors deployed in indoor and outdoor environments. The humidity data is processed by first-order difference to construct a differential humidity sequence. According to the degree of change of the differential humidity sequence, the eigenvalue of the humidity change rate is calculated, and it is judged whether the eigenvalue of the humidity change rate is greater than or equal to a preset threshold. If so, there is a potential abnormality in the environmental humidity; if not, there is no potential abnormality in the environmental humidity.

[0009] As a further solution of the present invention: the process of obtaining the eigenvalue of the humidity change rate is as follows: Obtain the humidity data collected in real time and integrate it into a humidity time series. Perform first-order difference processing on the humidity time series, specifically by subtracting each humidity value in the humidity time series from the humidity value at its previous time point, that is, for the humidity difference between any two adjacent time points, integrate all the humidity differences to obtain a differential humidity sequence; Use Haar wavelet transform to analyze the differential humidity sequence, select Haar wavelet as the wavelet basis function, and perform multi-scale decomposition on the differential humidity sequence to generate a set of wavelet coefficients at different scales; According to the results of the Haar wavelet transform, sum up the squares of all wavelet coefficients at each scale to obtain the eigenvalue of the humidity change rate.

[0010] As a further solution of the present invention: constructing the temperature stability eigenvalue and the humidity change rate eigenvalue into a comprehensive environmental state feature vector and inputting it into a machine learning model specifically includes: Obtain the temperature stability eigenvalue and the humidity change rate eigenvalue of indoor and outdoor environments, construct the temperature stability eigenvalue and the humidity change rate eigenvalue into a comprehensive environmental state feature vector as the input of the machine learning model, and use minimizing the error between the predicted environmental regulation effect score and the actual environmental regulation effect score as the training objective to train the machine learning model. Output the environmental regulation effect score according to the trained machine learning model, and the machine learning model is a random forest model.

[0011] As a further solution of the present invention: the training process of the machine learning model is as follows: Taking the comprehensive environmental state feature vectors extracted within multiple sampling periods as input samples, and at the same time taking the actual environmental regulation effect scores within the corresponding time periods as target output labels, a training data set is constructed. A random forest model is used as the prediction model. The model consists of multiple decision trees. Training samples for each tree are generated from the training data set by the method of sampling with replacement, and the out-of-bag error is used to evaluate the generalization ability of the model. During the training process, minimizing the mean square error between the environmental regulation effect score predicted by the model and the actual score is used as the objective function. By optimizing the decision tree node splitting criterion and the number of decision trees in the forest, the prediction accuracy of the model is gradually improved. Finally, the trained random forest model can receive a new comprehensive environmental state feature vector as input and output the predicted value of the corresponding environmental regulation effect score.

[0012] As a further solution of the present invention: The evaluation of the environmental regulation effect specifically includes: Judging whether the environmental regulation effect score of the environmental regulation is greater than or equal to a preset threshold. If so, the environmental regulation effect is normal; if not, the environmental regulation effect is abnormal.

[0013] As a further solution of the present invention: Dynamically adjusting the operating parameters of the fresh air unit according to the evaluation results to achieve adaptive regulation of the indoor and outdoor environment specifically includes: If the effect of the environmental regulation is determined to be abnormal, the operating parameters of the fresh air unit need to be adjusted. According to the change trends of the temperature stability eigenvalue and the humidity change rate eigenvalue in the comprehensive environmental state feature vector, when the temperature stability eigenvalue is greater than or equal to the preset threshold, the air supply volume is increased to enhance the air circulation ability; when the humidity change rate eigenvalue is greater than or equal to the preset threshold, the dehumidification or humidification linkage mechanism is started, and the operating intensity of the filtration system is increased.

[0014] The intelligent fresh air unit adaptive environment regulation system based on the Internet of Things includes: A data acquisition module, which collects temperature data and humidity data in real time through multi-source sensors deployed in the indoor and outdoor environments; An environmental temperature evaluation module, which performs zero-sequence processing on the collected temperature data, constructs a zero-sequence temperature sequence, and calculates the temperature stability eigenvalue to evaluate the stability of the current environmental temperature fluctuation; An environmental humidity evaluation module, which performs first-order difference processing on the humidity data, constructs a difference humidity sequence, and calculates the humidity change rate eigenvalue to identify whether there is a potential abnormality in the environmental humidity; An environmental regulation effect evaluation module, which constructs the temperature stability eigenvalue and the humidity change rate eigenvalue into a comprehensive environmental state feature vector and inputs it into the trained machine learning model for environmental regulation effect evaluation; A fresh air unit adjustment module, which dynamically adjusts the operating parameters of the fresh air unit according to the evaluation result to achieve adaptive control of the indoor and outdoor environment.

[0015] Advantages of the present invention: (1) By adopting temperature and humidity sensors with high precision and strong anti-interference ability, the present invention can collect the temperature and humidity data in the indoor and outdoor environment in real time, and perform in-depth feature extraction on the original data based on advanced multi-dimensional signal processing technology. Specifically, for temperature data, first, a linear regression model is used to fit and subtract the trend term of the time series to construct a zero-sequence temperature series, and then the fast Fourier transform is combined to extract the frequency domain features and calculate the temperature stability eigenvalue, so as to realize the quantitative evaluation of the temperature fluctuation stability; for humidity data, the first-order difference processing is performed on the time series to remove the influence of the long-term trend, and the Haar wavelet transform is introduced for multi-scale decomposition to further extract the energy features at each scale, and finally the humidity change rate eigenvalue reflecting the severity of the short-term change of humidity is obtained. The above two key eigenvalues are fused into a representative comprehensive environmental state feature vector, which is used as an input variable and sent into the trained random forest model to predict the current environmental control effect score. The model takes the mean square error between the predicted score and the actual score as the objective function, and has good generalization ability and prediction accuracy. By comparing the prediction result with the set threshold, the system can intelligently judge whether the current environment is in the ideal control state, and dynamically adjust the operating parameters of the fresh air unit accordingly to achieve closed-loop adaptive environmental control. Compared with the traditional method, the present invention not only improves the perception ability and response speed to complex environmental changes, but also significantly enhances the intelligent level and decision-making reliability of the control system, truly realizing the leap and upgrade from "passive adjustment" to "active perception - accurate prediction - automatic optimization", and having significant technological progressiveness and application promotion value.

[0016] (2) The method proposed by the present invention breaks through the limitation of the traditional environmental control system's strong dependence on fixed operating conditions, and constructs an intelligent control mechanism with high adaptability and autonomous decision-making ability. This method is not only applicable to various indoor and outdoor environmental conditions, but also can dynamically identify the current environmental state according to complex external factors such as seasonal changes, day-night temperature differences, and sudden weather changes, and flexibly adjust the operating mode of the fresh air unit through an adaptive control strategy. For example, when the temperature fluctuates violently, the system automatically increases the air supply volume and air circulation efficiency based on the real-time evaluation results of the temperature stability characteristic value to suppress the phenomenon of heat accumulation or cold air retention; when the characteristic value of the humidity change rate exceeds the set threshold, the dehumidification or humidification linkage control is triggered, combined with the coordinated enhanced operation of the filtration system, to ensure that the indoor air quality and comfort are always at an ideal level. At the same time, relying on the trained random forest model, the system can predict the future short-term environmental change trend based on the fusion analysis of historical and real-time data, and perform intervention control in advance, thereby significantly improving the response speed and control accuracy. This model has good generalization ability and anti-interference ability, and can still maintain stable output performance in the case of noisy or abnormally fluctuating data, effectively avoiding misjudgment and adjustment lag problems. This system architecture that integrates environmental perception, intelligent prediction, and dynamic execution not only enhances the applicability and robustness of the equipment in various complex scenarios, but also provides a solid technical support for realizing a green, energy-saving, healthy, and comfortable indoor environment, and has broad application prospects and promotion value. Description of the Drawings

[0017] The present invention will be further described below with reference to the drawings.

[0018] Figure 1 is a flowchart of the method for adaptively controlling the environment of an intelligent fresh air unit based on the Internet of Things according to the present invention; Figure 2 is a flowchart of the system for adaptively controlling the environment of an intelligent fresh air unit based on the Internet of Things according to the present invention. Detailed Embodiment

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] Please refer to Figure 1 as shown, the present invention is a method for adaptively controlling the environment of an intelligent fresh air unit based on the Internet of Things, including the following steps: S1: Real-time collect temperature data and humidity data through multi-source sensors deployed in indoor and outdoor environments; The multi-source sensor includes: a temperature sensor and a humidity sensor; S2: Perform zero-sequence processing on the collected temperature data, construct a zero-sequence temperature sequence, and calculate the temperature stability characteristic value to evaluate the stability of the current ambient temperature fluctuation; S3: Perform first-order difference processing on the humidity data, construct a differential humidity sequence, and calculate the humidity change rate characteristic value to identify whether there is a potential abnormality in the ambient humidity; S4: Construct a comprehensive environmental state characteristic vector from the temperature stability characteristic value and the humidity change rate characteristic value, and input it into the trained machine learning model for evaluating the environmental control effect; S5: Dynamically adjust the operating parameters of the fresh air unit according to the evaluation results to achieve adaptive control of the indoor and outdoor environment.

[0021] In S1, through the multi-source sensors deployed in the indoor and outdoor environments, temperature data and humidity data are collected in real time, specifically including: The multi-source sensor includes, but is not limited to, a temperature sensor and a humidity sensor. The temperature sensor is used to collect air temperature information at indoor and outdoor locations, and the humidity sensor is used to synchronously obtain the relative humidity value in the air. Each sensor is distributed in different areas according to a preset spatial layout to ensure that the collected data is representative and consistent, so as to comprehensively reflect the current environmental state.

[0022] Each sensor establishes a connection with the central control module through the Internet of Things communication protocol to achieve periodic uploading and centralized processing of temperature and humidity data. The sensor device has high precision and anti-interference characteristics, and the sampling frequency can be dynamically adjusted according to actual needs to adapt to the data update rate requirements in different application scenarios. The collected original temperature and humidity data respectively form time series and are transmitted to the subsequent data processing module to provide basic data support for constructing the zero-sequence temperature sequence, the differential humidity sequence, and extracting the temperature stability characteristic value and the humidity change rate characteristic value.

[0023] In S2, perform zero-sequence processing on the collected temperature data, construct a zero-sequence temperature sequence, and calculate the temperature stability characteristic value to evaluate the stability of the current ambient temperature fluctuation, specifically including: Through the temperature sensors deployed in the indoor and outdoor environments, collect temperature data in real time according to the time series, perform zero-sequence processing on the collected temperature data, construct a zero-sequence temperature sequence, calculate the temperature stability characteristic value according to the fluctuation degree of the zero-sequence temperature sequence, and judge whether the temperature stability characteristic value is greater than or equal to the preset threshold. If so, the current ambient temperature fluctuation is unstable; if not, the current ambient temperature fluctuation is stable; The process of obtaining the temperature stability characteristic value is: Obtain the temperature data collected in real time and integrate it into a temperature time series. Use a linear regression model to fit the trend term of the temperature time series. Specifically, use the least squares method to perform a linear fit on the relationship between time points and corresponding temperature values to obtain the best fit straight-line equation. Then, calculate the trend value corresponding to each time point according to the fit straight-line equation and subtract the corresponding trend value from the original temperature time series point by point, so as to obtain the temperature fluctuation series after removing the linear trend, that is, the zero-sequence temperature series. Finally, perform a stationarity test on the zero-sequence temperature series. If it meets the preset trendless standard, output it as the basic data for subsequent frequency-domain analysis and temperature stability evaluation; otherwise, readjust the fitting model parameters or use a higher-order trend fitting method for reprocessing until a zero-sequence temperature series that meets the requirements is obtained. Perform a fast Fourier transform on the temperature series after zero-sequence processing to obtain a frequency-domain signal series. Determine the frequency resolution according to the sampling frequency and the number of data points. And divide the frequency interval, where represents the number of data points, represents the sampling frequency, and set the target frequency range , where represents the low-frequency cut-off frequency, represents the high-frequency cut-off frequency, corresponding to the index range in the frequency-domain signal , where, , ; Calculate the sum of the power spectral densities of each frequency component within the target frequency range to obtain the temperature stability characteristic value. The calculation expression is: ; In the formula, represents the temperature stability characteristic value, represents the number of frequency components, represents the th absolute value of the amplitude of the frequency component.

[0024] It should be noted that: In the present invention, temperature data is collected in real time by temperature sensors deployed in indoor and outdoor environments, and a linear regression model is used to fit the trend term of the original temperature time series. After obtaining the best fitting line using the least squares method, the trend term is subtracted point by point, thereby constructing a zero-sequence temperature series that removes the influence of the long-term trend. Further, a fast Fourier transform is performed on the zero-sequence temperature series to obtain its frequency-domain signal distribution, and a target frequency band within a specific frequency range is set. By summing the power spectral densities of each frequency component within this frequency band, a quantitative index, the temperature stability eigenvalue, which reflects the stability of temperature fluctuations, is calculated. By comparing the temperature stability eigenvalue with a preset threshold, it is possible to accurately determine whether the current ambient temperature is in a stable state, thereby providing a scientific basis for subsequent regulation decisions. This technical solution effectively solves the technical defects of traditional methods that are difficult to distinguish short-term fluctuations from long-term trends and cannot quantitatively evaluate temperature stability, and has the advantages of high data processing accuracy, objective and reliable evaluation results, and strong adaptability, reflecting the significant progress and innovative value of the present invention in the fields of environmental perception and intelligent regulation.

[0025] In S3, first-order difference processing is performed on the humidity data to construct a difference humidity sequence, and the humidity change rate eigenvalue is calculated to identify whether there is a potential anomaly in the environmental humidity, specifically including: Humidity data is collected in real time according to the time series by humidity sensors deployed in indoor and outdoor environments. First-order difference processing is performed on the humidity data to construct a difference humidity sequence. According to the degree of change of the difference humidity sequence, the humidity change rate eigenvalue is calculated. It is judged whether the humidity change rate eigenvalue is greater than or equal to the preset threshold. If so, there is a potential anomaly in the environmental humidity. If not, there is no potential anomaly in the environmental humidity; The humidity data collected in real time is obtained and integrated into a humidity time series. First-order difference processing is performed on the humidity time series, specifically by subtracting each humidity value in the humidity time series from its previous time point humidity value, that is, for the humidity difference between any two adjacent time points, all humidity differences are integrated to obtain a difference humidity sequence; The Haar wavelet transform is used to analyze the difference humidity sequence. The Haar wavelet is selected as the wavelet basis function, and the difference humidity sequence is decomposed at multiple scales to generate a set of wavelet coefficients at different scales. The Haar wavelet transform is a simple form of discrete wavelet transform, which realizes multi-level signal representation by recursively decomposing the signal into approximation and detail parts; According to the result of the Haar wavelet transform, the sum of the energies of the wavelet coefficients within the selected scale range is calculated as the humidity change rate eigenvalue. Specifically, the sum of the squares of all wavelet coefficients at each scale is accumulated to obtain the humidity change rate eigenvalue. For example, in the first-level decomposition, the energy sum of the detail coefficients is calculated, and the approximation coefficients are further decomposed and the energy is calculated until the predetermined decomposition level is reached; Finally, the calculated humidity change rate eigenvalue is output for subsequent quantitative analysis and monitoring of environmental humidity changes. This process can not only effectively capture the short-term fluctuation characteristics in humidity data, but also focus on the change characteristics of different periods by adjusting the decomposition level of Haar wavelet transform, thereby providing a more accurate evaluation of the humidity change rate eigenvalue.

[0026] It should be noted that: in the present invention, humidity data is collected in real time through humidity sensors deployed in indoor and outdoor environments, and a humidity time series is constructed; subsequently, first-order difference processing is performed on it to eliminate the influence of long-term trends and highlight short-term fluctuation characteristics, forming a differential humidity series; further, Haar wavelet transform is used to perform multi-scale decomposition on the differential humidity series, extract wavelet coefficients at different frequency scales, and calculate the humidity change rate eigenvalue by accumulating the sum of the squares of wavelet coefficients at each scale, so as to realize the quantitative evaluation of the severity of humidity changes. By comparing the humidity change rate eigenvalue with a preset threshold, it is possible to effectively judge whether there are abnormal humidity fluctuations in the current environment, and thus provide a basis for subsequent regulation strategies. This technical solution not only improves the sensitivity and accuracy of humidity anomaly recognition, but also utilizes the multi-resolution analysis ability of Haar wavelet transform to achieve a fine description of different periodic fluctuation characteristics, with advantages such as fast response speed, low computational complexity, and strong adaptability, significantly enhancing the ability of the existing environmental monitoring system to identify humidity abnormal states, reflecting the substantial progress and innovation of the present invention in the field of intelligent environmental perception and regulation technology.

[0027] In S4, the temperature stability eigenvalue and the humidity change rate eigenvalue are constructed into a comprehensive environmental state feature vector and input into the trained machine learning model for environmental regulation effect evaluation, specifically including: Obtain the temperature stability eigenvalue and the humidity change rate eigenvalue of indoor and outdoor environments, construct the temperature stability eigenvalue and the humidity change rate eigenvalue into a comprehensive environmental state feature vector as the input of the machine learning model, take minimizing the error between the predicted environmental regulation effect score and the actual environmental regulation effect score as the training objective, train the machine learning model, and output the environmental regulation effect score according to the trained machine learning model. The machine learning model is a random forest model; Taking the comprehensive environmental state feature vectors extracted within multiple sampling periods as input samples, and at the same time taking the actual environmental regulation effect scores within the corresponding time periods as target output labels, a training data set is constructed. A random forest model is used as the prediction model. The model consists of multiple decision trees. Each tree's training samples are generated from the training data set by the method of sampling with replacement, and the out-of-bag error is used to evaluate the generalization ability of the model. During the training process, minimizing the mean square error between the environmental regulation effect score predicted by the model and the actual score is used as the objective function. By optimizing the decision tree node splitting criterion and the number of decision trees in the forest, the prediction accuracy of the model is gradually improved. Finally, the trained random forest model can receive a new comprehensive environmental state feature vector as input and output the predicted value of the corresponding environmental regulation effect score.

[0028] The evaluation of the environmental regulation effect specifically includes: Judging whether the environmental regulation effect score of the environmental regulation is greater than or equal to a preset threshold. If so, the environmental regulation effect is normal; if not, the environmental regulation effect is abnormal.

[0029] In S5, according to the evaluation results, the operating parameters of the fresh air unit are dynamically adjusted to achieve adaptive regulation of the indoor and outdoor environment, which specifically includes: If the effect of the environmental regulation is determined to be abnormal, the operating parameters of the fresh air unit need to be adjusted. According to the change trends of the temperature stability eigenvalue and the humidity change rate eigenvalue in the comprehensive environmental state feature vector, when the temperature stability eigenvalue is greater than or equal to the preset threshold, the air supply volume is increased to enhance the air circulation ability; when the humidity change rate eigenvalue is greater than or equal to the preset threshold, the dehumidification or humidification linkage mechanism is started, and the operating intensity of the filtration system is increased; through the above adaptive regulation strategy, the indoor environment is restored to a stable and comfortable state as soon as possible, so as to achieve intelligent and refined fresh air regulation based on real-time environment perception.

[0030] Please refer to Figure 2 As shown, the intelligent fresh air unit adaptive environment regulation system based on the Internet of Things includes: A data acquisition module, which collects temperature data and humidity data in real time through multi-source sensors deployed in the indoor and outdoor environments; An environmental temperature evaluation module, which performs zero-sequence processing on the collected temperature data, constructs a zero-sequence temperature sequence, and calculates the temperature stability eigenvalue to evaluate the stability of the current environmental temperature fluctuation; An environmental humidity evaluation module, which performs first-order difference processing on the humidity data, constructs a differential humidity sequence, and calculates the humidity change rate eigenvalue to identify whether there are potential abnormalities in the environmental humidity; An environmental control effect evaluation module, which constructs a comprehensive environmental state feature vector from the temperature stability eigenvalue and the humidity change rate eigenvalue, and inputs it into a trained machine learning model for environmental control effect evaluation; A fresh air unit adjustment module, which dynamically adjusts the operating parameters of the fresh air unit according to the evaluation results to achieve adaptive control of the indoor and outdoor environment.

[0031] The working principle of the present invention: The present invention collects indoor and outdoor temperature and humidity data through multi-source sensors, and combines signal processing and machine learning technologies to achieve real-time perception and precise control of the environmental state. The method includes five core steps: collecting environmental parameters in real time according to the preset spatial layout and sampling frequency through temperature sensors and humidity sensors deployed indoors and outdoors to form a representative temperature and humidity time series; performing zero-sequence processing on the temperature data, using a linear regression model to remove the trend term, constructing a zero-sequence temperature series, and extracting frequency domain features through fast Fourier transform to calculate the temperature stability eigenvalue for judging whether the current environmental temperature is stable; performing first-order difference processing on the humidity data, constructing a difference humidity series, and performing multi-scale decomposition using Haar wavelet transform to calculate the humidity change rate eigenvalue to identify whether there is abnormal humidity fluctuation; constructing the above two eigenvalues into a comprehensive environmental state feature vector, inputting it into a trained random forest model to predict the environmental control effect score and evaluate the effectiveness of the current control strategy; dynamically adjusting the operating parameters of the fresh air unit according to the score results to achieve closed-loop adaptive control based on environmental state perception. The present invention improves the intelligent level and response ability of the control system by introducing high-precision data collection, time-frequency analysis and machine learning prediction mechanisms, solves the problem of poor adaptability of traditional fresh air systems to complex environmental changes, and has good application prospects and promotion value.

[0032] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0033] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0034] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0035] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0036] The above has described in detail one embodiment of the present invention, but the content is only a preferred embodiment of the present invention and should not be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. An adaptive environmental control method for intelligent fresh air units based on the Internet of Things, characterized in that: The following steps are involved: S1: Real-time temperature and humidity data are collected through multi-source sensors deployed in indoor and outdoor environments; The multi-source sensor includes: a temperature sensor and a humidity sensor; S2: Perform zero-sequence processing on the collected temperature data, construct a zero-sequence temperature sequence, and calculate the temperature stability characteristic value to evaluate the stability of the current ambient temperature fluctuation; S3: Perform first-order difference processing on the humidity data, construct a differential humidity sequence, and calculate the characteristic value of the humidity change rate to identify whether there is a potential anomaly in the ambient humidity; S4: The temperature stability eigenvalue and the humidity change rate eigenvalue are constructed into a comprehensive environmental state eigenvector, which is input into the trained machine learning model to evaluate the environmental control effect; S5: Dynamically adjust the operating parameters of the fresh air unit according to the evaluation results to achieve adaptive control of the indoor and outdoor environment.

2. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 1 is characterized in that: The evaluation of the stability of the current ambient temperature fluctuation specifically includes: By deploying temperature sensors in indoor and outdoor environments, temperature data is collected in real time according to the time series, and the collected temperature data is processed by zero sequence to construct a zero sequence temperature sequence. According to the fluctuation degree of the zero sequence temperature sequence, the temperature stability characteristic value is calculated to determine whether the temperature stability characteristic value is greater than or equal to the preset threshold. If so, the current ambient temperature fluctuation is unstable, if not, the current ambient temperature fluctuation is stable.

3. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 2 is characterized in that: The process of obtaining the temperature stability characteristic value is as follows: The real-time collected temperature data is obtained and integrated into a temperature time series. The linear regression model is used to fit the trend term of the temperature time series. Specifically, the relationship between the time point and the corresponding temperature value is fitted by the least square method to obtain the best fitting straight line equation; then the trend value corresponding to each time point is calculated according to the fitting straight line equation, and the corresponding trend value is subtracted point by point from the original temperature time series, so as to obtain the temperature fluctuation sequence after removing the linear trend, that is, the zero-sequence temperature sequence; Perform fast Fourier transform on the temperature sequence after zero-sequence processing to obtain a frequency domain signal sequence. According to the sampling frequency and the number of data points, the frequency resolution is determined and the frequency interval is divided to set the target frequency range. The sum of the power spectral density of each frequency component within the target frequency range is calculated to obtain the temperature stability characteristic value.

4. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 1 is characterized in that: The step of identifying whether there is a potential abnormality in the ambient humidity specifically includes: By deploying humidity sensors in indoor and outdoor environments, humidity data is collected in real time according to the time series, and the humidity data is processed by first-order difference to construct a differential humidity sequence. According to the degree of change of the differential humidity sequence, the characteristic value of the humidity change rate is calculated to determine whether the characteristic value of the humidity change rate is greater than or equal to the preset threshold. If so, there is a potential anomaly in the ambient humidity. If not, there is no potential anomaly in the ambient humidity.

5. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 4 is characterized in that: The process of obtaining the characteristic value of the humidity change rate is as follows: Obtain the real-time collected humidity data and integrate it into a humidity time series. Perform first-order difference processing on the humidity time series, specifically, subtract the humidity value of the previous time point from each humidity value in the humidity time series, that is, for the humidity difference between any two adjacent time points, integrate all humidity differences to obtain a differential humidity series; The differential humidity sequence is analyzed by using Haar wavelet transform, and Haar wavelet is selected as the wavelet basis function. The differential humidity sequence is decomposed into multiple scales to generate a set of wavelet coefficients at different scales. According to the results of Haar wavelet transform, the sum of squares of all wavelet coefficients at each scale is accumulated to obtain the characteristic value of humidity change rate.

6. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 1 is characterized in that: The temperature stability characteristic value and the humidity change rate characteristic value are constructed into a comprehensive environmental state characteristic vector and input into the machine learning model, specifically including: The temperature stability characteristic values ​​and humidity change rate characteristic values ​​indoors and outdoors are obtained, and the temperature stability characteristic values ​​and the humidity change rate characteristic values ​​are constructed into a comprehensive environmental state characteristic vector as the input of the machine learning model. The machine learning model is trained with minimizing the error between the predicted environmental control effect score and the actual environmental control effect score as the training goal, and the environmental control effect score is output according to the trained machine learning model. The machine learning model is a random forest model.

7. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 6 is characterized in that: The training process of the machine learning model is: The comprehensive environmental state feature vectors extracted within multiple sampling periods are taken as input samples, and the actual environmental regulation effect scores within the corresponding time period are taken as the target output labels to construct a training data set. The random forest model is used as the prediction model. The model consists of multiple decision trees. The training samples of each tree are generated from the training data set through the replacement sampling method, and the out-of-bag error is used to evaluate the generalization ability of the model. During the training process, the objective function is to minimize the mean square error between the environmental regulation effect score predicted by the model and the actual score. By optimizing the decision tree node splitting criterion and the number of decision trees in the forest, the model prediction accuracy is gradually improved. Finally, the random forest model after training can receive the new comprehensive environmental state feature vector as input and output the corresponding environmental regulation effect score prediction value.

8. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 1 is characterized in that: The environmental regulation effect evaluation specifically includes: Determine whether the environmental control effect score of the environmental control is greater than or equal to a preset threshold. If so, the environmental control effect is normal; if not, the environmental control effect is abnormal.

9. The method for adaptive environmental control of intelligent fresh air units based on the Internet of Things according to claim 1 is characterized in that: The dynamic adjustment of the operating parameters of the fresh air unit according to the evaluation results to achieve adaptive control of the indoor and outdoor environment specifically includes: If the effect of environmental control is judged to be abnormal, the operating parameters of the fresh air unit need to be adjusted according to the changing trends of the temperature stability eigenvalue and the humidity change rate eigenvalue in the comprehensive environmental state eigenvector. When the temperature stability eigenvalue is greater than or equal to the preset threshold, the air supply volume is increased to enhance the air circulation capacity. When the humidity change rate eigenvalue is greater than or equal to the preset threshold, the dehumidification or humidification linkage mechanism is started, and the operating intensity of the filtration system is increased.

10. The intelligent fresh air unit adaptive environmental control system based on the Internet of Things is characterized by: The method for adaptive environmental control of an intelligent fresh air unit based on the Internet of Things as claimed in any one of claims 1 to 9 comprises: A data acquisition module, wherein the data acquisition module collects temperature data and humidity data in real time through multi-source sensors deployed in indoor and outdoor environments; An ambient temperature evaluation module, which performs zero-sequence processing on the collected temperature data, constructs a zero-sequence temperature sequence, and calculates a temperature stability characteristic value for evaluating the stability of the current ambient temperature fluctuation; An environmental humidity assessment module, which performs first-order difference processing on humidity data, constructs a differential humidity sequence, and calculates a characteristic value of the humidity change rate to identify whether there is a potential anomaly in the environmental humidity; An environmental control effect evaluation module, which constructs a comprehensive environmental state feature vector from the temperature stability feature value and the humidity change rate feature value, and inputs the vector into a trained machine learning model to evaluate the environmental control effect; The fresh air unit adjustment module dynamically adjusts the fresh air unit operating parameters according to the evaluation results to achieve adaptive control of the indoor and outdoor environment.

Images