An intelligent control method and related equipment for energy-saving ventilation system

Abstract

The present invention relates to an intelligent control method for an energy-saving ventilation system, comprising the following steps: obtaining indoor environmental parameters through preset sensors, and sorting the indoor environmental parameters to obtain sorting parameters; constructing a time series parameter curve based on the sorting parameters, and generating a time series parameter matrix according to the coordinates of points on the time series parameter curve; obtaining weather forecast data and indoor personnel density change data, and predicting the indoor environment based on the time series parameter matrix, weather forecast data and indoor personnel density change data through a preset multiple regression analysis algorithm to obtain a prediction result; if the indoor environment grade quality is not within a predetermined range, determining a corresponding ventilation intelligent control strategy according to the sorting parameters and the indoor environment grade quality; performing speed regulation and energy-saving control on the ventilation system based on the ventilation intelligent control strategy; solving the problems of low efficiency and slow response of traditional ventilation systems.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving ventilation, and in particular to an intelligent control method and related equipment for an energy-saving ventilation system. Background Art

[0002] With the acceleration of urbanization and the improvement of people's living standards, indoor air quality has become a major public health concern. Traditional ventilation systems often operate in a fixed mode, unable to make timely adjustments based on the actual indoor environmental conditions and changes in external conditions, resulting in the dual problems of energy waste and poor indoor air quality. Especially in densely populated office spaces, schools, and residential areas, rising concentrations of volatile organic compounds (VOCs), carbon dioxide (CO2), and particulate matter (PM) pollution directly affect people's comfort and health. In addition, the variability of weather conditions and the irregularity of indoor human activities make it difficult to achieve ideal energy savings and air purification effects through manual ventilation system adjustment. Summary of the Invention

[0003] The main purpose of the present invention is to provide an intelligent control method and related equipment for an energy-saving ventilation system to solve the technical problems of low efficiency and slow response of traditional ventilation systems.

[0004] To achieve the above object, the present invention provides an intelligent control method for an energy-saving ventilation system, comprising the following steps:

[0005] Acquire indoor environmental parameters through preset sensors and sort the indoor environmental parameters to obtain sorting parameters; wherein the indoor environmental parameters include VOCs concentration, CO2 concentration and particulate matter concentration;

[0006] Constructing a timing parameter curve based on the sorting parameters, and generating a timing parameter matrix according to the coordinates of points on the timing parameter curve;

[0007] Obtain weather forecast data and indoor occupant density change data, and predict the indoor environment based on the time series parameter matrix, weather forecast data, and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain a prediction result; wherein the prediction result includes the indoor environment grade quality;

[0008] If the indoor environment quality level is not within a predetermined range, determining a corresponding ventilation intelligent control strategy according to the sorting parameter and the indoor environment quality level;

[0009] Based on the intelligent ventilation control strategy, the ventilation system is controlled to adjust speed and save energy.

[0010] Furthermore, the indoor environment parameters are sorted to obtain sorting parameters, including:

[0011] Constructing a triangle shape based on the indoor environment parameters; wherein the indoor environment parameters are used as nodes on the triangle, and the mutual influence and dependency between the indoor environment parameters are used as sides of the triangle;

[0012] Obtaining corresponding side lengths based on the triangular shape; wherein each side length represents a concentration of a corresponding indoor environmental parameter;

[0013] Comparing the side lengths to obtain a first side length, a second side length, and a third side length; wherein the first side length is greater than the second side length, the second side length is greater than the third side length, and the first side length, the second side length, and the third side length change over time;

[0014] The indoor environment parameters are sorted based on the lengths of the first side length, the second side length, and the third side length to obtain a sorting parameter.

[0015] Furthermore, constructing a timing parameter curve based on the sorting parameters and generating a timing parameter matrix according to the coordinates of points on the timing parameter curve includes:

[0016] Fitting the temporal trend of the ranking parameters using a preset linear regression algorithm to obtain a time series parameter curve;

[0017] Extracting key data from the timing parameter curve to obtain key data features, and using the key data features as point coordinates on the timing parameter curve, wherein the key data features include abnormal values, peak values, and valley values;

[0018] A time series vector is constructed based on the point coordinates, and the time series vector is sorted from left to right according to preset labels to obtain a time series parameter matrix.

[0019] Furthermore, the indoor environment is predicted based on the time series parameter matrix, weather forecast data and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain prediction results, including:

[0020] Performing vector conversion on the weather forecast data to obtain a first conversion vector;

[0021] Performing vector transformation on the indoor personnel density change data to obtain a second transformation vector;

[0022] Extracting the main diagonal and the sub-diagonal of the timing parameter matrix respectively to obtain corresponding main diagonal elements and sub-diagonal elements;

[0023] Constructing a main diagonal vector and a sub-diagonal vector based on the main diagonal elements and the sub-diagonal elements;

[0024] Adding the diagonal vector to the first transformed vector to obtain a first vector;

[0025] Adding the secondary diagonal vector and the second transformed vector to obtain a second vector;

[0026] Taking the first vector as a column and the second vector as a row, multiplying the first vector by the second vector to obtain a multiplication matrix;

[0027] Adding the multiplication matrix and the timing parameter matrix to obtain an addition matrix;

[0028] The indoor environment is predicted based on the addition matrix using a preset multiple regression analysis algorithm to obtain a prediction result.

[0029] Furthermore, if the indoor environment quality level is not within a predetermined range, a corresponding intelligent ventilation control strategy is determined according to the sorting parameter and the indoor environment quality level, including:

[0030] If the indoor environment quality level is not within a predetermined range, a multi-dimensional analysis is performed on the indoor environment quality level that is not within the predetermined range to obtain multiple analysis results, and each of the analysis results is used as a first root node, and the sorting parameter is used as a second root node; wherein each of the analysis results includes temperature and humidity that are not within a predetermined threshold range;

[0031] Merging the first root node and the second root node to obtain a fused node;

[0032] Traversing the historical ideal environment states corresponding to the fusion nodes, taking the historical ideal environment states as leaf nodes, and constructing a search tree based on the root node and the leaf nodes;

[0033] Using a preset MCTS algorithm, based on the search tree, a control path is determined from the root node to the optimal leaf node; wherein the control path has multiple path nodes, each of which represents a control decision point, and the control decision point includes adjusting the fan speed, switching the air purification mode, and time scheduling;

[0034] Each of the control decision points is used as a corresponding ventilation intelligent control strategy.

[0035] Furthermore, a multi-dimensional analysis is performed on the indoor environment quality that is not within the predetermined range to obtain multiple analysis results, including:

[0036] Using a preset multi-dimensional analysis algorithm, various indicators are marked for the indoor environmental quality levels that are not within the predetermined range to identify abnormal indoor environmental areas;

[0037] Obtaining an abnormal area distribution map based on the abnormal environmental area;

[0038] Performing dimensionality reduction processing on the abnormal area distribution map to extract key factors; wherein the key factors are key factors affecting indoor environmental quality;

[0039] The key factors are grouped to obtain multiple analysis results; wherein the multiple analysis results are different types of environmental problem patterns, and the environmental problem patterns include abnormal temperature, abnormal humidity, excessive microorganisms and pollutants, and abnormal air quality.

[0040] Furthermore, the ventilation system is speed-regulated and energy-saving controlled based on the intelligent ventilation control strategy, including:

[0041] Acquire a layout structure of the ventilation system, and construct a network diagram based on the layout structure;

[0042] The network graph is matrix constructed using a preset distributed optimization algorithm to obtain an adjacent matrix; wherein the adjacent matrix is ​​the connection relationship between the structures of the ventilation systems;

[0043] Performing matrix construction on the network graph to obtain an in-degree matrix; wherein the in-degree matrix is ​​the number of connections of each structure;

[0044] Obtaining a Laplacian matrix based on the adjacency matrix and the in-degree matrix;

[0045] Performing distributed optimization on the control decision points based on the Laplace matrix to obtain a global optimization target of the intelligent control strategy of the ventilation system; wherein the control decision points are used as the intelligent control strategy of the ventilation system;

[0046] Based on the global optimization goal, the ventilation system is controlled to adjust speed and save energy, and indoor environmental quality and energy consumption data are obtained;

[0047] If the indoor environment quality and energy consumption data deviate from the preset range, the adaptive adjustment mechanism is triggered to perform speed regulation and energy-saving control on the ventilation system until the indoor environment quality and energy consumption data are within the preset range.

[0048] The present invention also provides an intelligent control device for an energy-saving ventilation system, comprising:

[0049] A sorting module is used to obtain indoor environmental parameters through preset sensors and sort the indoor environmental parameters to obtain sorting parameters; wherein the indoor environmental parameters include VOCs concentration, CO2 concentration and particulate matter concentration;

[0050] A construction module, configured to construct a timing parameter curve based on the sorting parameters, and generate a timing parameter matrix according to the coordinates of points on the timing parameter curve;

[0051] A prediction module is configured to obtain weather forecast data and indoor occupant density change data, and predict the indoor environment based on the time series parameter matrix, weather forecast data, and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain a prediction result; wherein the prediction result includes the indoor environment quality grade;

[0052] an obtaining module, configured to determine a corresponding intelligent ventilation control strategy according to the sorting parameter and the indoor environment quality level if the indoor environment quality level is not within a predetermined range;

[0053] The control module is used to perform speed regulation and energy-saving control on the ventilation system based on the ventilation intelligent control strategy.

[0054] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0055] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0056] The intelligent control method of the energy-saving ventilation system provided by the present invention includes the following steps: obtaining indoor environmental parameters through preset sensors, and sorting the indoor environmental parameters to obtain sorting parameters; constructing a time series parameter curve based on the sorting parameters, and generating a time series parameter matrix according to the point coordinates on the time series parameter curve; obtaining weather forecast data and indoor personnel density change data, and predicting the indoor environment based on the time series parameter matrix, weather forecast data and indoor personnel density change data through a preset multiple regression analysis algorithm to obtain a prediction result; if the indoor environment grade quality is not within a predetermined range, determining the corresponding ventilation intelligent control strategy according to the sorting parameters and the indoor environment grade quality; performing speed regulation and energy-saving control on the ventilation system based on the ventilation intelligent control strategy; through the above-mentioned technical solution, the problems of low efficiency and slow response of traditional ventilation systems are solved, and the ventilation rate can be automatically adjusted according to the real-time status and future change trends of the indoor environment, effectively controlling the indoor pollutant concentration, and ensuring the beneficial effect of indoor air quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a schematic diagram of the steps of an intelligent control method for an energy-saving ventilation system according to an embodiment of the present invention;

[0058] Figure 2 This is a structural block diagram of an intelligent control device for an energy-saving ventilation system according to an embodiment of the present invention;

[0059] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0060] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0062] like Figure 1 As shown, Figure 1 This is a schematic diagram of the steps of an intelligent control method for an energy-saving ventilation system in one embodiment of the present invention;

[0063] In one embodiment of the present invention, a method for intelligently controlling an energy-saving ventilation system is provided, comprising the following steps:

[0064] Step S1, obtaining indoor environmental parameters through preset sensors, and sorting the indoor environmental parameters to obtain sorting parameters; wherein the indoor environmental parameters include VOCs concentration, CO2 concentration and particulate matter concentration.

[0065] Specifically, at the initial stage of implementing this intelligent control method for energy-saving ventilation systems, the primary task is to accurately assess the current status of indoor air quality so that appropriate measures can be taken. This process involves several key steps: Deploying Preset Sensors: The system installs a series of pre-defined, high-sensitivity sensors at strategic locations indoors. These sensors are specifically designed to monitor specific indoor environmental parameters and serve as the foundation for technical implementation. Each sensor corresponds to a specific environmental indicator or category, ensuring comprehensive and accurate data collection. Collecting Indoor Environmental Parameters: The sensors continuously monitor and record three key indicators: VOC (volatile organic compound) concentrations, CO2 (carbon dioxide) concentrations, and particulate matter (typically referring to smaller suspended particles such as PM2.5 and PM10). VOC concentrations reflect the level of harmful gases released by new indoor decoration materials and cleaning agents; CO2 concentrations are a key indicator of indoor ventilation efficiency and the impact of respiratory activity; and particulate matter concentrations measure the concentration of suspended particles such as dust and smoke in the air, which is closely related to respiratory health. Parameter Sorting: The collected data is then organized and sorted according to specific rules. The purpose of sorting is to identify the environmental issues that currently require the most attention, that is, which parameter readings are outside the normal or ideal range, or which parameters have the most significant changing trends. This sorting may be based on the absolute values ​​of the parameters, or on the degree of their deviation from safety or comfort standards. Generate sorting parameters: After sorting, the resulting sequence is called a "sorting parameter." This process is actually a summary and prioritization of the raw data, providing a clear basis for subsequent analysis and decision-making. For example, if the VOCs concentration is found to be abnormally high, then in the subsequent control strategy, reducing the VOCs concentration will be given a higher priority. In summary, through this series of meticulous operations, the system can accurately and in real time grasp the specific conditions of indoor air quality, laying a solid data foundation for the formulation and implementation of subsequent intelligent control strategies.

[0066] Step S2: constructing a timing parameter curve based on the sorting parameters, and generating a timing parameter matrix according to the coordinates of the points on the timing parameter curve.

[0067] Specifically, after obtaining the ranking of indoor environmental parameters, constructing time-series parameter curves and generating a time-series parameter matrix are key steps for further analyzing and predicting indoor environmental trends. This process involves the following steps: Constructing the time-series parameter curves: Based on the ranked parameters, we treat the VOCs, CO2, and particulate matter concentrations at each monitoring moment as time series data. This means that each environmental parameter becomes a time-varying curve, with the horizontal axis representing time (e.g., hours or minutes) and the vertical axis representing the corresponding concentration value. Using these continuous monitoring data points, we plot three independent time-series curves, each showing the temporal trends of VOCs, CO2, and particulate matter concentrations. This visualization not only intuitively displays the instantaneous state of each parameter but also reveals its dynamic patterns over time. Generating the time-series parameter matrix: A time-series parameter matrix is ​​a structured data representation that organizes the data points on the aforementioned curves in a matrix format. In this matrix, each row represents a specific monitoring time point, and each column corresponds to an environmental parameter (VOCs, CO2, or particulate matter concentration). The value of each cell is the measured value of the corresponding environmental parameter at that point in time. For example, the first row and second column of the matrix stores the CO2 concentration value at the first monitoring time point. In this way, the entire matrix fully records the status of all key parameters at all monitoring moments. In this way, the time series parameter matrix not only facilitates data storage and management but also provides a directly usable dataset for subsequent statistical analysis, pattern recognition, anomaly detection, and the establishment of predictive models. It enables multi-dimensional data comparison and complex time series analysis, which is crucial for optimizing indoor environmental control strategies, predicting future environmental trends, and developing efficient control plans.

[0068] Step S3, obtaining weather forecast data and indoor occupant density change data, and using a preset multiple regression analysis algorithm to predict the indoor environment based on the time series parameter matrix, weather forecast data and indoor occupant density change data to obtain a prediction result; wherein the prediction result includes the indoor environment grade quality.

[0069] Specifically, to predict the indoor environmental quality level, we adopted a comprehensive analytical approach, combining a time-series parameter matrix, weather forecast data, and indoor occupancy density data. This was achieved using a pre-defined multiple regression analysis algorithm. The following are detailed implementation steps and explanations: Data Integration: Time-series parameter matrix: First, we have a time-series parameter matrix constructed based on historical monitoring data. This matrix contains the temporal changes in key indoor environmental parameters (such as VOC concentrations, CO2 concentrations, and particulate matter concentrations). Weather forecast data: This data includes, but is not limited to, external meteorological conditions such as temperature, humidity, and wind speed. These factors indirectly affect the indoor environment, for example by affecting the building's heat exchange efficiency and the effectiveness of the fresh air system. Indoor occupancy density data: Human activity is a key factor affecting indoor air quality. Increases or decreases in occupancy density directly affect environmental parameters such as CO2 concentration, temperature, and humidity. Multiple regression analysis is a statistical method used to study the relationship between multiple independent variables (here, time-series parameters, weather factors, and occupancy density) and a dependent variable (indoor environmental quality level). Our pre-defined algorithm model attempts to identify any linear or nonlinear relationships between these variables. Through algorithm training, the model learns how indoor environmental quality levels change under different conditions, such as how high humidity and high occupancy density work together to increase CO2 concentrations, thereby affecting environmental quality levels. After model training is complete and its accuracy verified, the model is fed with the latest weather forecast data and predicted changes in indoor occupancy density. Based on this input data, the model calculates the expected quality level of the indoor environment for a specific time period in the future. Indoor environmental quality levels can typically be quantified into different grades, such as "excellent," "good," "fair," and "poor." These grades are based on preset standards, such as the internationally recognized Air Quality Index (AQI) or custom indoor environmental health indicators. In summary, this approach allows us to comprehensively consider multiple influencing factors and make relatively accurate predictions about the future state of the indoor environment.

[0070] Step S4: If the indoor environment quality level is not within a predetermined range, a corresponding intelligent ventilation control strategy is determined according to the sorting parameter and the indoor environment quality level.

[0071] Specifically, when the monitored indoor environmental quality deviates from our preset ideal range, the system will take immediate action to ensure the indoor environment is comfortable and healthy. This response mechanism operates based on two core elements: sorting parameters and the current indoor environmental quality. The following is a detailed explanation:

[0072] Identify the problem: First, through continuous monitoring, the system detects that indoor environmental quality (such as VOC concentrations, CO2 concentrations, and particulate matter concentrations) is not maintained within preset health or comfort standards. This indicates poor air quality, which is adversely affecting occupant health or work efficiency. Analyze the ranking parameters: Next, the system reviews the previously constructed ranking parameters, which reveal the relative importance and urgency of different environmental factors. For example, if VOC concentrations are abnormally high and ranked high, this indicates that the top priority is to reduce harmful gas emissions. Strategy Matching: Based on the current indoor environmental quality level and ranking parameters, the system intelligently matches the most appropriate ventilation control strategy. Strategy formulation takes into account the severity and urgency of the problem, ensuring that the measures taken are targeted to address the issue. For example, if CO2 concentrations are excessively high and associated with increased indoor occupancy density, the system decides to increase the fresh air volume and adjust the wind speed to accelerate air exchange, while also optimizing the air conditioning system's operating mode to save energy. Execute Intelligent Control: Once the appropriate control strategy is determined, the system automatically adjusts the ventilation system's operating parameters, such as adjusting fan speed, switching air purification modes, and even adjusting the amount of fresh air introduced based on the weather forecast, to quickly restore the indoor environment to its ideal state. In short, this step demonstrates the system's dynamic responsiveness to indoor environmental quality. By analyzing the current environmental status and historical data, it intelligently selects and implements the most appropriate control strategy, ensuring a consistently healthy and comfortable indoor environment.

[0073] Step S5: performing speed regulation and energy-saving control on the ventilation system based on the intelligent ventilation control strategy.

[0074] Specifically, after identifying that the indoor environmental quality level falls outside the predetermined range and determining the corresponding intelligent ventilation control strategy, the system enters the execution phase, implementing speed regulation and energy-saving control of the ventilation system based on these strategies. This process unfolds as follows: Strategy Interpretation and Translation: First, the system analyzes the determined intelligent control strategy and translates it into specific operational instructions. For example, if the strategy indicates the need for increased ventilation to reduce CO2 concentrations, the system interprets this as requiring increased fresh air intake and / or increased fan speed to accelerate air circulation. Dynamic Speed ​​Regulation: Based on the strategy, the fans and other controllable components (such as dampers and valves) in the ventilation system are dynamically adjusted. Speed ​​regulation not only takes into account the need to correct the current environmental problem but also considers energy efficiency, ensuring that energy consumption is minimized while improving indoor air quality. For example, if only minor adjustments are required to maintain the indoor environment, the system will select a lower energy consumption mode for the fan. Real-Time Monitoring and Feedback Adjustment: During the adjustment process, the system continuously monitors changes in environmental parameters such as CO2 concentrations, VOCs concentrations, and particulate matter concentrations, as well as the energy consumption of the ventilation system. Through real-time data analysis, the system can instantly evaluate the effectiveness of control strategies and make further adjustments based on environmental response and energy efficiency, ensuring precise and effective control measures. Energy-saving optimization: While maintaining indoor environmental quality, the system also utilizes predictive algorithms and optimization models to explore more energy-efficient control paths. For example, based on weather forecast data, the system will increase the proportion of natural ventilation and reduce the use of mechanical ventilation when outdoor air quality is good and temperature is suitable, thereby achieving energy conservation and emission reduction. Automatic balancing: The entire control process strives for the optimal balance between indoor environmental quality and energy efficiency, ensuring a healthy, comfortable, and environmentally friendly indoor environment at all times. Through continuous self-learning and strategy optimization, the ventilation system can more intelligently adapt to varying environmental conditions and usage requirements. In summary, speed-adjusted energy-saving control based on the described intelligent ventilation control strategy is a highly dynamic, feedback-driven process that integrates environmental monitoring, data analysis, intelligent decision-making, and execution optimization. It aims to efficiently and automatically manage the indoor environment while maximizing energy efficiency.

[0075] In a specific embodiment, the indoor environment parameters are sorted to obtain sorting parameters, including:

[0076] Constructing a triangle shape based on the indoor environment parameters; wherein the indoor environment parameters are used as nodes on the triangle, and the mutual influence and dependency between the indoor environment parameters are used as sides of the triangle;

[0077] Obtaining corresponding side lengths based on the triangular shape; wherein each side length represents a concentration of a corresponding indoor environmental parameter;

[0078] Comparing the side lengths to obtain a first side length, a second side length, and a third side length; wherein the first side length is greater than the second side length, the second side length is greater than the third side length, and the first side length, the second side length, and the third side length change over time;

[0079] The indoor environment parameters are sorted based on the lengths of the first side length, the second side length, and the third side length to obtain a sorting parameter.

[0080] Specifically, this embodiment introduces a novel method for sorting indoor environmental parameters to intuitively identify and prioritize those factors that have the greatest impact on indoor environmental quality. The following is a detailed explanation of this process:

[0081] Constructing a triangle model: First, map the indoor environmental parameters of interest (e.g., VOCs concentration, CO2 concentration, and particulate matter concentration) to the three vertices of a triangle. Each parameter, as an independent node, represents a key indicator for monitoring. The sides of the triangle symbolize the mutual influence and dependency between these parameters. While the specific influence mechanisms are not elaborated here, it can be understood as how they interact in the comprehensive impact on indoor environmental quality.

[0082] Side Length to Concentration Mapping: In this model, the lengths of the triangle sides are given new meaning, representing the concentration level of their corresponding indoor environmental parameters. This means that longer sides indicate higher concentrations of that parameter, and vice versa. This method converts abstract concentration values ​​into intuitive geometric dimensions, facilitating intuitive comparison of the relative importance of various parameters.

[0083] Side Length Sorting: By directly comparing the lengths of the three sides of a triangle, the first side (longest), second side (second longest), and third side (shortest) are determined. This ranking naturally reflects which parameter concentration is highest, second lowest, and lowest at a given point in time. It is important to note that these side lengths (and thus parameter concentrations) are dynamic. Over time, indoor environmental parameter concentrations will fluctuate, requiring the ranking parameters to be updated accordingly.

[0084] Dynamic Parameter Sorting: Indoor environmental parameters are ranked in real time based on the lengths of the first, second, and third sides to identify the parameters that require the most attention in the current environment. This ranking strategy directly reflects the current criticality of the indoor environment, guiding subsequent control and improvement measures, prioritizing the highest concentrations and ultimately improving the overall indoor environmental quality.

[0085] In summary, this method constructs an intuitive triangle model, associates the concentration of indoor environmental parameters with the side length, and uses the intuitive comparison of side lengths to achieve parameter sorting. Based on this, the indoor environmental control strategy is dynamically adjusted and optimized to ensure that the indoor environment always maintains an ideal health and comfort level.

[0086] In a specific embodiment, constructing a timing parameter curve based on the sorting parameters and generating a timing parameter matrix according to the coordinates of points on the timing parameter curve includes:

[0087] Fitting the temporal trend of the ranking parameters using a preset linear regression algorithm to obtain a time series parameter curve;

[0088] Extracting key data from the timing parameter curve to obtain key data features, and using the key data features as point coordinates on the timing parameter curve, wherein the key data features include abnormal values, peak values, and valley values;

[0089] A time series vector is constructed based on the point coordinates, and the time series vector is sorted from left to right according to preset labels to obtain a time series parameter matrix.

[0090] Specifically, this embodiment further enhances the complexity of indoor environmental parameter analysis by introducing time series analysis to capture the temporal trends and key features of these parameters. The following is a detailed explanation: Constructing a time series parameter curve: First, a preset linear regression algorithm is used to mathematically fit the temporal trends of the previously obtained ranking parameters (i.e., indoor environmental parameters sorted by concentration). Linear regression is a statistical method that predicts the relationship between one or more independent variables (here, time) and a dependent variable (the values ​​of the ranking parameters), thereby generating one or more smooth curves reflecting the temporal trends of the parameters. This step helps understand how each parameter rises, falls, or remains stable over time. Key data feature extraction: From the generated time series parameter curve, data points of particular significance, known as key data features, are identified and extracted. These features typically include, but are not limited to, outliers (measured values ​​that deviate from the normal range), peaks (maximum values ​​of the parameters over a period of time), and valleys (minimum values). The coordinates of these points on the curve mark important turning points or abnormal events in the indoor environmental state, which are particularly important for in-depth analysis and early warning systems. Constructing and Sorting Time Series Vectors: Next, the extracted coordinates of key data feature points are converted into time series vectors, with each vector element representing a feature value at a specific moment. These vectors contain key information about the evolution of the indoor environment over time. These time series vectors are then sorted from left to right according to pre-defined labeling rules (by chronological order, parameter type, or other logic) to form a time series parameter matrix. This matrix structure facilitates observation and analysis of state changes of different parameters at different moments, as well as potential connections between them. In summary, by constructing time series parameter curves and matrices, this solution not only provides a macroscopic view of the dynamic changes in indoor environmental parameters, but also enhances understanding and response capabilities to detailed environmental changes by identifying and sorting key feature points, providing powerful data support for environmental monitoring, fault diagnosis, and optimization and control.

[0091] In a specific embodiment, a preset multiple regression analysis algorithm is used to predict the indoor environment based on the time series parameter matrix, weather forecast data, and indoor occupant density change data to obtain prediction results, including:

[0092] Performing vector conversion on the weather forecast data to obtain a first conversion vector;

[0093] Performing vector transformation on the indoor personnel density change data to obtain a second transformation vector;

[0094] Extracting the main diagonal and the sub-diagonal of the timing parameter matrix respectively to obtain corresponding main diagonal elements and sub-diagonal elements;

[0095] Constructing a main diagonal vector and a sub-diagonal vector based on the main diagonal elements and the sub-diagonal elements;

[0096] Adding the diagonal vector to the first transformed vector to obtain a first vector;

[0097] Adding the secondary diagonal vector and the second transformed vector to obtain a second vector;

[0098] Taking the first vector as a column and the second vector as a row, multiplying the first vector by the second vector to obtain a multiplication matrix;

[0099] Adding the multiplication matrix and the timing parameter matrix to obtain an addition matrix;

[0100] The indoor environment is predicted based on the addition matrix using a preset multiple regression analysis algorithm to obtain a prediction result.

[0101] Specifically, the solution describes in detail the process of using a multivariate regression analysis algorithm combined with multi-source data to predict indoor environmental changes. The specific steps are as follows:

[0102] Weather forecast data vectorization: First, the weather forecast data is converted into a first conversion vector in numerical form. This step involves encoding meteorological factors such as temperature and humidity into continuous or discrete values ​​to facilitate subsequent calculations.

[0103] Vectorization of indoor occupant density change data: Similarly, the temporal change data of indoor occupant density is also converted into a second transformation vector. This includes the number of people recorded at different time points, forming a time series vector reflecting density fluctuations.

[0104] Timing parameter matrix processing:

[0105] Extracting Diagonal Elements: The time series parameter matrix contains information about the time-varying changes of multiple parameters. Extract the elements on the main diagonal and sub-diagonal lines to form main diagonal vectors and sub-diagonal vectors, respectively. This step aims to extract specific patterns or trends in the matrix, such as direct serial correlation and cross-serial correlation of time series.

[0106] Constructing the prediction model input:

[0107] Constructing a vector combination: Add the main diagonal vector to the first transformed vector to generate a first vector that accounts for environmental parameter trends and external weather influences. Add the secondary diagonal vector to the second transformed vector to form a second vector that accounts for the influence of changes in population density. This step integrates information from different dimensions and prepares input for the multiple regression analysis.

[0108] Matrix operations:

[0109] Constructing a multiplication matrix: Performing matrix multiplication generates a new matrix by using the first vector as the columns and the second vector as the rows. This step aims to model the interaction between two different dimensional features (environmental parameter trends + weather impact, and changes in population density).

[0110] Combine with the original time series parameter matrix: Add the obtained multiplication matrix to the original time series parameter matrix. The resulting summation matrix integrates historical data trends, external factors, and interaction effects.

[0111] Multiple regression analysis prediction:

[0112] Finally, a pre-defined multiple regression analysis algorithm is used to perform a prediction based on the constructed additive matrix. Multiple regression analysis predicts the future state of the indoor environment by analyzing the relationship between multiple independent variables (here, including the combined effects of historical parameter trends, weather influences, and changes in occupancy density) and dependent variables (indoor environmental indicators such as temperature and CO2 concentration). The resulting predictions can provide a basis for applications such as environmental control and energy management.

[0113] The entire process aims to improve the accuracy of predicting indoor environmental changes through highly structured data processing and complex statistical modeling, while taking into account the interaction of multiple internal and external factors.

[0114] In a specific embodiment, if the indoor environment quality level is not within a predetermined range, determining a corresponding intelligent ventilation control strategy according to the sorting parameter and the indoor environment quality level includes:

[0115] If the indoor environment quality level is not within a predetermined range, a multi-dimensional analysis is performed on the indoor environment quality level that is not within the predetermined range to obtain multiple analysis results, and each of the analysis results is used as a first root node, and the sorting parameter is used as a second root node; wherein each of the analysis results includes temperature and humidity that are not within a predetermined threshold range;

[0116] Merging the first root node and the second root node to obtain a fused node;

[0117] Traversing the historical ideal environment states corresponding to the fusion nodes, taking the historical ideal environment states as leaf nodes, and constructing a search tree based on the root node and the leaf nodes;

[0118] Using a preset MCTS algorithm, based on the search tree, a control path is determined from the root node to the optimal leaf node; wherein the control path has multiple path nodes, each of which represents a control decision point, and the control decision point includes adjusting the fan speed, switching the air purification mode, and time scheduling;

[0119] Each of the control decision points is used as a corresponding ventilation intelligent control strategy.

[0120] Specifically, when the indoor environmental quality is detected to have deviated from the preset ideal range, the system adopts a set of detailed and dynamic strategies to optimize the indoor environment. The specific process is as follows:

[0121] First, an in-depth, multi-dimensional analysis of substandard indoor environmental quality levels is conducted, focusing primarily on whether temperature and humidity exceed predefined thresholds. These exceeding thresholds are considered "first-root nodes," reflecting the specific issues within the current indoor environment. Furthermore, "ranking parameters" are introduced as "second-root nodes." These ranking parameters, including factors such as urgency, scope of impact, or cost of improvement, further guide the decision-making process. This approach establishes a foundational framework for problem identification and prioritization. The first-root node (problem characteristics, such as abnormal temperature or humidity) is fused with the second-root node (ranking parameters) to form a "fused node" that comprehensively considers the severity and urgency of the problem. This node reflects the environmental conditions and control priorities that require simultaneous consideration. The system then traverses the historical database for ideal environmental states that match the current fused node and sets these ideal states as "leaf nodes." Based on this, a search tree is constructed based on the root node (the fusion of problem and priority) and the leaf nodes (the ideal states). This tree represents the exploration space of all possible paths from the current undesirable environmental state to the target ideal state. The Monte Carlo Tree Search (MCTS) algorithm explores this search tree, finding the optimal path from the fusion node (i.e., the current problem state) to a specific leaf node (i.e., the ideal environmental state). MCTS simulates a large number of random paths and continuously updates path evaluations based on the simulation results, ultimately locating paths that are more likely to reach the target state. In this process, each "path node" on the path represents a specific control decision point, such as adjusting fan speed, selecting an air purification mode, or setting a time schedule—all of which directly impact actions that improve the indoor environment. Ultimately, based on the optimal path determined by the MCTS algorithm, each selected path node is transformed into an actual intelligent ventilation control strategy. These strategies directly guide actual operations, such as adjusting equipment parameters to quickly restore the indoor environment to the ideal state, ensuring comfort and health for residents or workers. In summary, through meticulous problem analysis, policy prioritization, construction of a search tree for optimized paths, and intelligent decision-making algorithms, this solution achieves efficient and precise control of non-ideal indoor environments, thereby maintaining indoor environmental quality within a predetermined range.

[0122] In a specific embodiment, a multi-dimensional analysis is performed on the indoor environment quality that is not within the predetermined range to obtain multiple analysis results, including:

[0123] Using a preset multi-dimensional analysis algorithm, various indicators are marked for the indoor environmental quality levels that are not within the predetermined range to identify abnormal indoor environmental areas;

[0124] Obtaining an abnormal area distribution map based on the abnormal environmental area;

[0125] Performing dimensionality reduction processing on the abnormal area distribution map to extract key factors; wherein the key factors are key factors affecting indoor environmental quality;

[0126] The key factors are grouped to obtain multiple analysis results; wherein the multiple analysis results are different types of environmental problem patterns, and the environmental problem patterns include abnormal temperature, abnormal humidity, excessive microorganisms and pollutants, and abnormal air quality.

[0127] Specifically, this step involves a complex and structured series of analytical processes designed to accurately identify and categorize problem areas within the indoor environment and their root causes, enabling targeted improvement measures to be implemented. The details are as follows: First, a pre-defined multi-dimensional analysis algorithm is used to comprehensively scan areas of the indoor environment that do not meet standard requirements. This analysis goes beyond simple temperature and humidity measurements to encompass multiple indicators related to environmental quality, such as light intensity, air circulation, and hazardous substance concentrations. Through this algorithmic processing, the system identifies areas and indicators that deviate from normal ranges, effectively identifying abnormal areas within the indoor environment. Based on the abnormal data identified in the first step, the system generates a distribution map of abnormal areas. This map visually displays the distribution of environmental quality issues at various locations within the room, allowing maintenance personnel to clearly identify problem areas and provide clear guidance for subsequent on-site inspections and maintenance. Because the raw data contains a large number of variables, the abnormal area distribution map undergoes dimensionality reduction to more efficiently understand and process this information. This process uses mathematical methods to reduce the complexity of the data while retaining the most critical information. After dimensionality reduction, the few decisive factors influencing indoor environmental quality can be more clearly identified. These extracted factors are known as "key factors." These key factors are further categorized and summarized into several typical environmental problem patterns. For example, if the key factor points to a temperature control system failure or the influence of external temperature, it is classified as "temperature anomaly"; if it is related to air moisture content or water leakage, it is classified as "humidity anomaly"; if bacteria, viruses, or harmful chemicals exceed the standard, it is classified as "microorganisms and pollutants exceed the standard"; and if air quality monitoring indicators fail to meet standards, it is defined as "air quality anomaly." This grouping simplifies complex and diverse abnormal situations into a few easy-to-understand and actionable categories. In short, this solution uses advanced data analysis technology to transform complex indoor environmental issues into a series of actionable analytical results, laying a solid foundation for the subsequent implementation of precise intelligent control strategies.

[0128] In a specific embodiment, speed regulation and energy-saving control of the ventilation system is performed based on the ventilation intelligent control strategy, including:

[0129] Acquire a layout structure of the ventilation system, and construct a network diagram based on the layout structure;

[0130] The network graph is matrix constructed using a preset distributed optimization algorithm to obtain an adjacent matrix; wherein the adjacent matrix is ​​the connection relationship between the structures of the ventilation systems;

[0131] Performing matrix construction on the network graph to obtain an in-degree matrix; wherein the in-degree matrix is ​​the number of connections of each structure;

[0132] Obtaining a Laplacian matrix based on the adjacency matrix and the in-degree matrix;

[0133] Performing distributed optimization on the control decision points based on the Laplace matrix to obtain a global optimization target of the intelligent control strategy of the ventilation system; wherein the control decision points are used as the intelligent control strategy of the ventilation system;

[0134] Based on the global optimization goal, the ventilation system is controlled to adjust speed and save energy, and indoor environmental quality and energy consumption data are obtained;

[0135] If the indoor environment quality and energy consumption data deviate from the preset range, the adaptive adjustment mechanism is triggered to perform speed regulation and energy-saving control on the ventilation system until the indoor environment quality and energy consumption data are within the preset range.

[0136] Specifically, this solution is a highly integrated intelligent control strategy that aims to improve indoor environmental quality while achieving effective energy conservation through fine management and optimization of the ventilation system. Its core steps and principles are as follows: Analysis of the ventilation system layout structure: First, collect and analyze the physical layout information of the ventilation system, including the location of each vent, air duct, fan and other components and how they are connected to each other. This link is the basis for building the subsequent network model. Construct a network diagram: Use the actual layout structure of the ventilation system to establish a graphical network model. Each node represents a component in the system (such as a fan or air outlet), and the edge represents the airflow connection between components. Adjacency matrix: Through a preset algorithm, the network diagram is converted into a mathematical adjacency matrix. The matrix clearly shows the direct connection status between the components in the system and provides a mathematical framework for understanding the system structure. In-degree matrix: Further construct the in-degree matrix, which records how many edges point to each node, that is, it reflects the "receiving" relationship of each part in the ventilation system, which helps to evaluate the role of each part in the overall flow. Application of Laplace matrix:

[0137] Combining the adjacency matrix and the in-degree matrix, the Laplace matrix is ​​calculated. In graph theory, the Laplace matrix is ​​an important tool for describing network structures. It effectively reflects the relationships between nodes in a system and the overall connectivity of the system, making it crucial for subsequent optimization calculations. Using the Laplace matrix as a foundation, a distributed optimization algorithm is used to globally optimize the control decision points (i.e., controllable nodes in the ventilation system, such as fan speed). The goal is to find a control strategy that ensures that indoor environmental quality (such as temperature, humidity, and air quality) meets standards while minimizing energy consumption. This step forms an intelligent control strategy, ensuring that the actions of each control decision point serve the optimal goal of the entire system. The resulting intelligent control strategy is implemented to dynamically adjust ventilation system operating parameters, such as fan speed, to achieve the established indoor environmental quality targets and monitor energy consumption in real time. If the monitored indoor environmental quality or energy consumption data deviates from the pre-defined acceptable range, the system automatically triggers an adaptive adjustment mechanism to fine-tune the control strategy until all indicators return to the ideal range. This closed-loop control process ensures efficient and stable system operation while maximizing energy efficiency. In summary, this solution achieves intelligent management of ventilation systems through highly integrated algorithms and data analysis, which not only improves the comfort of living or working spaces, but also significantly improves the economy and sustainability of energy use.

[0138] The above describes the intelligent control method of the energy-saving ventilation system in the embodiment of the present invention. The following describes the intelligent control device of the energy-saving ventilation system in the embodiment of the present invention. Figure 2 An embodiment of the intelligent control device of the energy-saving ventilation system in the embodiment of the present invention includes:

[0139] The sorting module 21 is used to obtain indoor environmental parameters through preset sensors and sort the indoor environmental parameters to obtain sorting parameters; wherein the indoor environmental parameters include VOCs concentration, CO2 concentration and particulate matter concentration;

[0140] A construction module 22 is configured to construct a timing parameter curve based on the sorting parameters, and generate a timing parameter matrix according to the coordinates of points on the timing parameter curve;

[0141] The prediction module 23 is configured to obtain weather forecast data and indoor occupant density change data, and to predict the indoor environment based on the time series parameter matrix, weather forecast data, and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain a prediction result; wherein the prediction result includes the indoor environment quality grade;

[0142] an obtaining module 24 for determining a corresponding intelligent ventilation control strategy according to the sorting parameter and the indoor environment quality level if the indoor environment quality level is not within a predetermined range;

[0143] The control module 25 is used to perform speed regulation and energy-saving control on the ventilation system based on the ventilation intelligent control strategy.

[0144] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0145] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0146] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0147] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0148] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0149] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0150] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent control method for an energy-saving ventilation system, characterized in that: The following steps are involved: Acquire indoor environmental parameters through preset sensors and sort the indoor environmental parameters to obtain sorting parameters; wherein the indoor environmental parameters include VOCs concentration, CO2 concentration and particulate matter concentration; Constructing a timing parameter curve based on the sorting parameters, and generating a timing parameter matrix according to the coordinates of points on the timing parameter curve; Obtain weather forecast data and indoor occupant density change data, and predict the indoor environment based on the time series parameter matrix, weather forecast data, and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain a prediction result; wherein the prediction result includes the indoor environment quality grade; If the indoor environment quality level is not within a predetermined range, determining a corresponding ventilation intelligent control strategy according to the sorting parameter and the indoor environment quality level; Performing speed regulation and energy-saving control on the ventilation system based on the ventilation intelligent control strategy; If the indoor environment quality level is not within a predetermined range, determining a corresponding intelligent ventilation control strategy according to the sorting parameter and the indoor environment quality level, including: If the indoor environment quality level is not within a predetermined range, a multi-dimensional analysis is performed on the indoor environment quality level that is not within the predetermined range to obtain multiple analysis results, and each of the analysis results is used as a first root node, and the sorting parameter is used as a second root node; wherein each of the analysis results includes temperature and humidity that are not within a predetermined threshold range; Merging the first root node and the second root node to obtain a fused node; Traversing the historical ideal environment states corresponding to the fusion nodes, taking the historical ideal environment states as leaf nodes, and constructing a search tree based on the root node and the leaf nodes; Using a preset MCTS algorithm, based on the search tree, a control path is determined from the root node to the optimal leaf node; wherein the control path has multiple path nodes, each of which represents a control decision point, and the control decision point includes adjusting the fan speed, switching the air purification mode, and time scheduling; Taking each of the control decision points as a corresponding ventilation intelligent control strategy; The ventilation system is controlled to adjust speed and save energy based on the intelligent ventilation control strategy, including: Acquire a layout structure of the ventilation system, and construct a network diagram based on the layout structure; The network graph is matrix constructed using a preset distributed optimization algorithm to obtain an adjacent matrix; wherein the adjacent matrix is ​​the connection relationship between the structures of the ventilation systems; Performing matrix construction on the network graph to obtain an in-degree matrix; wherein the in-degree matrix is ​​the number of connections of each structure; Obtaining a Laplacian matrix based on the adjacency matrix and the in-degree matrix; Performing distributed optimization on the control decision points based on the Laplace matrix to obtain a global optimization target of the intelligent control strategy of the ventilation system; wherein the control decision points are used as the intelligent control strategy of the ventilation system; Based on the global optimization goal, the ventilation system is controlled to adjust speed and save energy, and indoor environmental quality and energy consumption data are obtained; If the indoor environment quality and energy consumption data deviate from the preset range, the adaptive adjustment mechanism is triggered to perform speed regulation and energy-saving control on the ventilation system until the indoor environment quality and energy consumption data are within the preset range.

2. The intelligent control method for energy-saving ventilation system according to claim 1, characterized in that: Sorting the indoor environment parameters to obtain sorting parameters includes: Constructing a triangle shape based on the indoor environment parameters; wherein the indoor environment parameters are used as nodes on the triangle, and the mutual influence and dependency between the indoor environment parameters are used as sides of the triangle; Obtaining corresponding side lengths based on the triangular shape; wherein each side length represents a concentration of a corresponding indoor environmental parameter; Comparing the side lengths to obtain a first side length, a second side length, and a third side length; wherein the first side length is greater than the second side length, the second side length is greater than the third side length, and the first side length, the second side length, and the third side length change over time; The indoor environment parameters are sorted based on the lengths of the first side length, the second side length, and the third side length to obtain a sorting parameter.

3. The intelligent control method for energy-saving ventilation system according to claim 1, characterized in that: Constructing a timing parameter curve based on the sorting parameters, and generating a timing parameter matrix according to the coordinates of points on the timing parameter curve, including: Fitting the temporal trend of the ranking parameters using a preset linear regression algorithm to obtain a time series parameter curve; Extracting key data from the timing parameter curve to obtain key data features, and using the key data features as point coordinates on the timing parameter curve, wherein the key data features include abnormal values, peak values, and valley values; A time series vector is constructed based on the point coordinates, and the time series vector is sorted from left to right according to preset labels to obtain a time series parameter matrix.

4. The intelligent control method for energy-saving ventilation system according to claim 1, characterized in that: The indoor environment is predicted based on the time series parameter matrix, weather forecast data, and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain prediction results, including: Performing vector conversion on the weather forecast data to obtain a first conversion vector; Performing vector transformation on the indoor personnel density change data to obtain a second transformation vector; Extracting the main diagonal and the sub-diagonal of the timing parameter matrix respectively to obtain corresponding main diagonal elements and sub-diagonal elements; Constructing a main diagonal vector and a sub-diagonal vector based on the main diagonal elements and the sub-diagonal elements; Adding the diagonal vector to the first transformed vector to obtain a first vector; Adding the secondary diagonal vector and the second transformed vector to obtain a second vector; Taking the first vector as a column and the second vector as a row, multiplying the first vector by the second vector to obtain a multiplication matrix; Adding the multiplication matrix and the timing parameter matrix to obtain an addition matrix; The indoor environment is predicted based on the addition matrix using a preset multiple regression analysis algorithm to obtain a prediction result.

5. The intelligent control method for energy-saving ventilation system according to claim 1, characterized in that: A multi-dimensional analysis is performed on the indoor environment quality that is not within the predetermined range to obtain multiple analysis results, including: Using a preset multi-dimensional analysis algorithm, various indicators are marked for the indoor environmental quality levels that are not within the predetermined range to identify abnormal indoor environmental areas; Obtaining an abnormal area distribution map based on the abnormal environmental area; Performing dimensionality reduction processing on the abnormal area distribution map to extract key factors; wherein the key factors are key factors affecting indoor environmental quality; The key factors are grouped to obtain multiple analysis results; wherein the multiple analysis results are different types of environmental problem patterns, and the environmental problem patterns include abnormal temperature, abnormal humidity, excessive microorganisms and pollutants, and abnormal air quality.

6. An intelligent control device for an energy-saving ventilation system, characterized in that: include: A sorting module is used to obtain indoor environmental parameters through preset sensors and sort the indoor environmental parameters to obtain sorting parameters; wherein the indoor environmental parameters include VOCs concentration, CO2 concentration and particulate matter concentration; A construction module, configured to construct a timing parameter curve based on the sorting parameters, and generate a timing parameter matrix according to the coordinates of points on the timing parameter curve; A prediction module is configured to obtain weather forecast data and indoor occupant density change data, and predict the indoor environment based on the time series parameter matrix, weather forecast data, and indoor occupant density change data using a preset multiple regression analysis algorithm to obtain a prediction result; wherein the prediction result includes the indoor environment quality grade; an obtaining module, configured to determine a corresponding intelligent ventilation control strategy according to the sorting parameter and the indoor environment quality level if the indoor environment quality level is not within a predetermined range; A control module, configured to perform speed regulation and energy-saving control on the ventilation system based on the ventilation intelligent control strategy; If the indoor environment quality level is not within a predetermined range, determining a corresponding intelligent ventilation control strategy according to the sorting parameter and the indoor environment quality level, including: If the indoor environment quality level is not within a predetermined range, a multi-dimensional analysis is performed on the indoor environment quality level that is not within the predetermined range to obtain multiple analysis results, and each of the analysis results is used as a first root node, and the sorting parameter is used as a second root node; wherein each of the analysis results includes temperature and humidity that are not within a predetermined threshold range; Merging the first root node and the second root node to obtain a fused node; Traversing the historical ideal environment states corresponding to the fusion nodes, taking the historical ideal environment states as leaf nodes, and constructing a search tree based on the root node and the leaf nodes; Using a preset MCTS algorithm, based on the search tree, a control path is determined from the root node to the optimal leaf node; wherein the control path has multiple path nodes, each of which represents a control decision point, and the control decision point includes adjusting the fan speed, switching the air purification mode, and time scheduling; Taking each of the control decision points as a corresponding ventilation intelligent control strategy; The ventilation system is controlled to adjust speed and save energy based on the intelligent ventilation control strategy, including: Acquire a layout structure of the ventilation system, and construct a network diagram based on the layout structure; The network graph is matrix constructed using a preset distributed optimization algorithm to obtain an adjacent matrix; wherein the adjacent matrix is ​​the connection relationship between the structures of the ventilation systems; Performing matrix construction on the network graph to obtain an in-degree matrix; wherein the in-degree matrix is ​​the number of connections of each structure; Obtaining a Laplacian matrix based on the adjacency matrix and the in-degree matrix; Performing distributed optimization on the control decision points based on the Laplace matrix to obtain a global optimization target of the intelligent control strategy of the ventilation system; wherein the control decision points are used as the intelligent control strategy of the ventilation system; Based on the global optimization goal, the ventilation system is controlled to adjust speed and save energy, and indoor environmental quality and energy consumption data are obtained; If the indoor environment quality and energy consumption data deviate from the preset range, the adaptive adjustment mechanism is triggered to perform speed regulation and energy-saving control on the ventilation system until the indoor environment quality and energy consumption data are within the preset range.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images