Metro ventilation system and method based on big data analysis

Abstract

The invention discloses a subway ventilation system and method based on big data analysis, relates to the technical field of ventilation management and control, and is used for dynamically adjusting the operation time of ventilation equipment so as to achieve the purposes of guaranteeing the comfort of passengers and saving energy. Comprising the steps of collecting station characteristics, the distance between stations and the duration time of a ventilation effect required by determining an optimal strategy for starting the ventilation equipment; according to the station characteristics, the stations are classified by using a clustering algorithm, and the importance of the stations is determined; the importance of the stations, the distance between the stations and the duration of the ventilation effect are comprehensively considered, a linear regression model is established, and the optimal strategy for starting ventilation equipment is predicted; the real-time temperature and the real-time relative humidity in the compartment are obtained, the comfort index is calculated through the Roseburg formula, and the comfort index serves as the real-time environment; and the real-time environment in the compartment and the importance of the station serve as input variables, and the running time of ventilation equipment is adjusted through a fuzzy logic control method.

Description

Technical Field

[0001] The present invention relates to the field of ventilation control technology, and more specifically, to a subway ventilation system and method based on big data analysis. Background Art

[0002] In the existing subway ventilation system, the ventilation equipment will start running in advance before the train arrives at the station to provide good ventilation during the train stop. After leaving the station, the ventilation equipment will stop running in time to save energy and reduce operating costs. However, the time it takes for the subway to reach the adjacent station is short, and the ventilation equipment needs to be turned on or off in advance every time it arrives and leaves the station. Frequent opening and closing of the ventilation equipment will lead to energy waste and unnecessary operating costs. Therefore, this application proposes a subway ventilation system based on big data analysis, which further optimizes when the ventilation equipment is turned on and off, and dynamically adjusts the operating time of the ventilation equipment to achieve the purpose of both ensuring passenger comfort and saving energy, thereby realizing the optimization and intelligent management of the subway ventilation system.

[0003] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a subway ventilation system and method based on big data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A subway ventilation system and method based on big data analysis, comprising the following steps: Step 1: Collect the station characteristics, distance between stations and duration of ventilation effect required to determine the best strategy for ventilation equipment activation; Step 2: Based on the characteristics of the stations, use the clustering algorithm to classify the stations and determine their importance; Step 3: Considering the importance of stations, the distance between stations and the duration of ventilation effect, a linear regression model was established to predict the optimal strategy for opening ventilation equipment; Step 4: Obtain the real-time temperature and real-time relative humidity in the vehicle cabin, calculate the comfort index using the Rosberg formula, and use the comfort index as the real-time environment; Step 5: Taking the real-time environment in the carriage and the importance of the station as input variables, the fuzzy logic control method is used to adjust the operation time of the ventilation equipment.

[0006] In a preferred embodiment, in step 2, a clustering algorithm is used to calculate the importance of the station, which specifically includes the following steps: S1: Collect the characteristic values ​​of the station; S2: Data preprocessing; standardization of eigenvalues; S3: Select the appropriate number of clusters; S4: Select K-means clustering algorithm for cluster analysis: randomly select k initial cluster centers, assign each sample to the cluster with the closest cluster center; then calculate the new center of each cluster as the new cluster center; repeat the two steps of assigning samples and updating centers until the cluster center no longer changes or the maximum number of iterations is reached. Assigning samples means assigning each sample to the cluster with the closest cluster center; updating centers means calculating the new center of each cluster as the new cluster center; Mark the randomly selected k initial cluster centers as μ1, μ2, ..., μk. For each sample, calculate its distance to each cluster center. The specific formula is ; In the formula Represents the distance between sample xi and cluster center μj; assigns it to the nearest cluster Cu (u=1, 2, 3), specifically ; For each cluster Cu, calculate its new cluster center μj, that is, the sample mean within the cluster, , where xi represents the i-th station, which contains the feature vector of all the features of the station; S5: Explain the clustering results; for each cluster, calculate the average value of each feature expressed as ; where u represents the index of the cluster and j represents the index of the feature; the specific formula is ; In the formula is the number of stations in cluster Cu, is the jth feature value of the qth station in cluster Cu; for each feature j, add the average value of the feature in a cluster to get the sum , and then calculate ; Where E represents the sum of the average values ​​of all features in the cluster, and m is the number of features; The importance of the station is evaluated by comparing the size of E; the sum of the average values ​​of all features in the first cluster is marked as E1, and so on, the sum of the average values ​​of all features in the second and third clusters are marked as E2 and E3. Among E1, E2, and E3, the maximum value indicates that the station in its corresponding cluster is important, the minimum value indicates that the station in its corresponding cluster is not important, and the middle value indicates that the importance of the station in its corresponding cluster is medium.

[0007] In a preferred embodiment, in step 3, the optimal strategy for opening the ventilation equipment is determined according to the importance of the station, the distance between the stations and the duration of the ventilation effect, including the following steps: G1: The ventilation equipment opening strategy is used as a binary variable, where 0 means opening the ventilation equipment every time a station is reached, and 1 means opening the ventilation equipment every other station; the distance between stations is marked as B, the duration of the ventilation effect is marked as t, and the average sum of all features in the cluster E is used to represent the importance of the station; G2: The importance of the station (E), the distance between stations (B) and the duration of the ventilation effect (t) are used as independent variables, and the ventilation equipment opening strategy is used as the dependent variable (0 or 1). A linear regression model is established; the expression of the model is: ; where β0, β1, β2, β3 are the coefficients of the model, is the error term, Y1 is the ventilation equipment opening strategy; G3: Model fitting; use the least squares method to estimate the coefficients in the model so that the model fits the actual observations as closely as possible; the coefficient estimation formula is ; In the formula, X is the independent variable matrix, which contains the independent variable value of each sample. The first column of the matrix X is usually a constant column with all 1s, which is used to represent the intercept term; Y is a vector containing the dependent variable value (0 or 1) of each sample. represents the transpose of matrix X, express The inverse matrix of , β is a vector containing all the coefficients in the linear model, including the coefficients of the intercept term and the independent variable; G4: Model evaluation: Use the F test to judge the entire linear regression model, that is, to determine whether the independent variables in the model as a whole have a significant impact on the dependent variable; the specific steps are as follows: G4.1: Calculate the F statistic ; Where SSR is the regression sum of squares, 3 refers to the number of independent variables, the number of independent variables in this embodiment is 3, SSE is the error sum of squares, and n is the sample size, i.e., n stations; G4.2: Find the F distribution table based on the F statistic and the degrees of freedom (n-3-1) and determine the p-value corresponding to the F statistic; the p-value is an indicator in statistical hypothesis testing, which indicates the probability of observing the statistic or a more extreme situation when the null hypothesis is true; G5: Model explanation; the value of the coefficient indicates the change in the dependent variable when the value of the independent variable increases by 1 unit; the positive and negative signs of the coefficient indicate the directional relationship between the independent variable and the dependent variable. If the coefficient is positive, it means that the increase in the independent variable is positively correlated with the increase in the dependent variable; if the coefficient is negative, it means that the increase in the independent variable is negatively correlated with the decrease in the dependent variable; G6: Model prediction: Use the established model to predict the optimal ventilation equipment opening strategy.

[0008] In a preferred embodiment, in step 4, the real-time environment in the compartment includes temperature, relative humidity, etc., and the real-time environment in the compartment is calculated as follows: D1: Collect data; use temperature sensors and relative humidity sensors to measure the temperature and relative humidity in the vehicle compartment in real time; D2: Calculation of comfort index: The comfort index is calculated according to the Rosberg formula. The specific formula is: ; Where T represents the real-time temperature in the car, RH represents the real-time relative humidity in the car and is expressed in percentage.

[0009] In a preferred embodiment, in step 5, the real-time environment in the carriage and the importance of the station are comprehensively analyzed to dynamically adjust the operation time of the ventilation equipment; the specific process is as follows: Firstly, the real-time environment in the carriage and the importance of the station are defined as input variables and divided into different fuzzy sets; The running time of ventilation equipment is defined as the output variable and divided into different fuzzy sets; Formulate fuzzy rules to describe the impact of the real-time environment in the carriage and the importance of the station on the operation time of the ventilation equipment; Fuzzy reasoning is performed based on fuzzy rules to dynamically adjust the operating time of ventilation equipment.

[0010] A subway ventilation system based on big data analysis, used to implement the above method, includes a data acquisition module, a cluster analysis module, a linear regression prediction module, a comfort calculation module and a fuzzy logic control module, and the modules are signal-connected; The data collection module is used to collect all data related to the ventilation strategy in real time, including station characteristics, the distance between stations, the duration of ventilation effects, and the real-time temperature and real-time relative humidity in the carriage; The cluster analysis module classifies stations based on their characteristics and divides them into different categories using clustering algorithms; The linear regression prediction module is used to establish a linear regression model to predict the optimal ventilation strategy for each station and output the opening time and duration of the ventilation equipment; The comfort calculation module is used to convert the real-time temperature and relative humidity in the cabin into a comfort index through the Rosseberg formula; The fuzzy logic control module is used to dynamically adjust the operation time of the ventilation equipment according to the real-time calculated comfort index and the importance of the station.

[0011] Technical effects and advantages of a subway ventilation system and method based on big data analysis of the present invention: The present invention establishes a model based on the importance of stations, the distance between stations, and the duration of ventilation effects, further predicts the best strategy for opening ventilation equipment, and comprehensively analyzes the importance of stations and the real-time environment in the carriage, thereby dynamically adjusting the operation time of ventilation equipment. This improves passenger comfort and saves energy, and realizes the optimization and intelligent management of subway ventilation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic diagram of the structure of a subway ventilation system based on big data analysis in the present invention; Figure 2 This is a flow chart of a subway ventilation method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] Example, Figure 1 A method for determining the optimal strategy for opening ventilation equipment and dynamically adjusting the operation time of ventilation equipment in a subway ventilation system based on big data analysis is given. Figure 2 As shown, the following steps are included: Step 1: Collect the station characteristics, distance between stations and duration of ventilation effect required to determine the best strategy for ventilation equipment activation.

[0015] Step 2: Based on the station characteristics, use clustering algorithm to classify the stations and determine the importance of the stations.

[0016] Step 3: Considering the importance of stations, the distance between stations and the duration of ventilation effect, a linear regression model was established to predict the optimal strategy for opening ventilation equipment.

[0017] Step 4: Get the real-time temperature and real-time relative humidity in the car, calculate the comfort index using the Rosseberg formula, and use the comfort index as the real-time environment.

[0018] Step 5: Taking the real-time environment in the carriage and the importance of the station as input variables, the fuzzy logic control method is used to adjust the operation time of the ventilation equipment.

[0019] Specifically, in step 1, for the acquisition of station features, the transfer situation is represented by other subway lines that each station can transfer to. For example, if a station can transfer to two other subway lines, the characteristic value of the transfer situation of the station is 2. The passenger flow is obtained through the gate system in the station. The importance of the station indicates the importance of the station, which is usually evaluated based on the station features. The acquisition of the characteristic value of a specific feature is mainly determined based on the professional knowledge in the relevant field and the actual situation. The objectivity of the characteristic value needs to be guaranteed, which will not be elaborated here.

[0020] The distance between stations can be measured using mapping tools or GIS software, or obtained directly from the line design drawings of the subway operating company.

[0021] As for the duration of the ventilation effect, specifically, the air flow rate inside the car is monitored in real time through an air velocity meter, and the time period when the air flow rate remains above the flow rate threshold is stipulated as the duration of the ventilation effect. For example, in the period between turning on the ventilation equipment and turning on the ventilation equipment next time, the air flow rate is above the flow rate threshold for t minutes, which means that the duration of the ventilation effect is t minutes. The setting of the flow rate threshold needs to be based on the standard of air flow rate, and is set according to the specific environment and actual needs, which will not be elaborated here. The duration of the ventilation effect refers to the time period between two adjacent times when the ventilation equipment is turned on, and the duration of the improvement effect on the internal environment of the subway car.

[0022] Specifically, in step 2, a clustering algorithm is used to calculate the importance of the station, which specifically includes the following steps: S1: Collect the characteristic values ​​of the station. The characteristic value is the data describing a certain characteristic of the station, such as geographical location, transfer situation, passenger flow, etc., to form a characteristic matrix. Assume that there are n stations in a subway line, and each station has m characteristics, then there is a characteristic matrix X, represents the jth eigenvalue of the ith station. A sample is a vector containing all eigenvalues. Each sample represents a station and contains a vector of all the features of the station. That is, each sample is an m-dimensional feature vector, where m is the number of features.

[0023] S2: Data preprocessing. Standardize the eigenvalues ​​to ensure that they have the same scale and dimension. A common method is to subtract the mean from each eigenvalue and then divide it by its standard deviation so that its mean is 0 and its standard deviation is 1. The specific formula is ; In the formula is the standardized eigenvalue, x is the original eigenvalue, α is the mean of the feature, is the standard deviation of the feature.

[0024] S3: Select an appropriate number of clusters. The number of clusters indicates how many clusters or groups the data will be divided into when using a clustering algorithm. Selecting an appropriate number of clusters is a very important step in cluster analysis, which directly affects the quality and interpretability of the final clustering results. According to this implementation case, the importance of the station is divided into three levels, namely, high, medium and low, corresponding to important, medium and unimportant. Therefore, the number of clusters is determined to be 3. By selecting the number of clusters as 3, the expected three clusters are obtained, each cluster representing a level of importance. At the same time, further adjustments are made through the elbow rule or silhouette coefficient, which will not be described in detail in this article.

[0025] S4: Select a clustering algorithm and apply it. Common clustering algorithms include K-means clustering, hierarchical clustering, density clustering, etc. Based on the characteristic data of the station, this application uses K-means clustering as an example. The advantages of this algorithm are that it is simple, easy to understand and implement, and can be used for large-scale data sets.

[0026] Randomly select k initial cluster centers and assign each sample to the cluster with the closest cluster center. Then calculate the new center of each cluster (i.e., the mean of the samples within the cluster) as the new cluster center. Repeat the two steps of assigning samples and updating centers until the cluster center no longer changes or the maximum number of iterations is reached. Assigning samples means assigning each sample to the cluster with the closest cluster center. Updating centers means calculating the new center of each cluster (i.e., the mean of the samples within the cluster) as the new cluster center.

[0027] Mark the randomly selected k initial cluster centers as μ1, μ2..., μk. For each sample, calculate its distance to each cluster center. The specific formula is ; In the formula Represents the distance between sample xi and cluster center μj. Assign it to the nearest cluster Cu (u=1, 2, 3), specifically For each cluster Cu, calculate its new cluster center μj, that is, the sample mean within the cluster, , where xi represents the i-th station, which is the feature vector containing all the features of the station.

[0028] S5: Explain the clustering results. For each cluster, calculate the average value of each feature expressed as ; where u represents the index of the cluster and j represents the index of the feature. The specific formula is ; In the formula is the number of stations in cluster Cu, is the jth feature value of the qth station in cluster Cu. For each feature j, add up the average values ​​of the feature in a cluster to get the sum , and then calculate ; Where E represents the sum of the average values ​​of all features in the cluster, and m is the number of features.

[0029] The importance of the station is evaluated by comparing the size of E. The sum of the average values ​​of all features in the first cluster is marked as E1, and so on. The sum of the average values ​​of all features in the second and third clusters are marked as E2 and E3. Among E1, E2, and E3, the maximum value indicates that the station in its corresponding cluster is important, the minimum value indicates that the station in its corresponding cluster is not important, and the middle value indicates that the importance of the station in its corresponding cluster is medium.

[0030] Specifically, in step 3, the best strategy for turning on the ventilation equipment is determined mainly based on the importance of the station, the distance between the stations, and the duration of the ventilation effect. The default strategy for turning on the ventilation equipment is that the subway turns on the ventilation equipment every time it arrives at a station, and the adjusted strategy for turning on the ventilation equipment is to turn on the ventilation equipment at intervals of one station. It should be noted that the strategy for turning on the ventilation equipment in this embodiment is only used as an example. In fact, the adjusted strategy for turning on the ventilation equipment can also be to turn on the ventilation equipment at intervals of two or more stations. The specific situation is subject to actual needs and is not limited here.

[0031] The specific analysis process is as follows: G1: The ventilation equipment opening strategy is used as a binary variable, where 0 means turning on the ventilation equipment every time a station is reached, and 1 means turning on the ventilation equipment every other station. The distance between stations is marked as B, the duration of the ventilation effect is marked as t, and the average sum E of all features in the cluster is used to represent the importance of the station. In the linear regression model, a sample refers to an observed data point, and each data point represents an observation unit (such as a station). In this embodiment, each sample contains relevant information about a station, including the importance of the station, the distance between stations, the duration of the ventilation effect, and the corresponding ventilation equipment opening strategy.

[0032] G2: Take the importance of the station (E), the distance between stations (B) and the duration of the ventilation effect (t) as independent variables, and the ventilation equipment opening strategy as the dependent variable (0 or 1), and establish a linear regression model. The expression of the model is ; where β0, β1, β2, β3 are the coefficients of the model, is the error term, and Y1 is the ventilation equipment opening strategy.

[0033] G3: Model fitting. Use the least squares method to estimate the coefficients in the model so that the model fits the actual observations as closely as possible. The coefficient estimation formula is ; In the formula, X is the independent variable matrix, which contains the independent variable value of each sample. The first column of the matrix X is usually a constant column with all 1s, which is used to represent the intercept term. Y is a vector containing the dependent variable value (0 or 1) of each sample. represents the transpose of matrix X, express The inverse matrix of β is a vector containing all the coefficients in the linear model, including the intercept term and the coefficients of the independent variable. By calculating the formula, the best coefficient estimate is obtained, thus establishing a linear regression model to predict and explain the dependent variable Y.

[0034] G4: Model evaluation. Use the F test to judge the entire linear regression model, that is, to determine whether the independent variables in the model as a whole have a significant impact on the dependent variable. The specific steps are as follows: G4.1: Calculate the F statistic ; Where SSR is the regression sum of squares, 3 refers to the number of independent variables, the number of independent variables in this embodiment is 3, SSE is the error sum of squares, and n is the sample size, i.e., n stations.

[0035] G4.2: Find the F distribution table based on the F statistic and the degrees of freedom (n-3-1) and determine the p-value corresponding to the F statistic. The p-value is an indicator in statistical hypothesis testing, which indicates the probability of observing the statistic (F statistic) or a more extreme situation when the null hypothesis is true.

[0036] The p-value is compared with the pre-set significance level (using the common significance level of 0.05). If the p-value is less than the significance level, the entire model is considered significant; conversely, if the p-value is greater than or equal to the significance level, the entire model is considered insignificant.

[0037] G5: Model explanation. The numerical value of the coefficient indicates the change in the dependent variable when the value of the independent variable increases by 1 unit; the positive and negative signs of the coefficient indicate the directional relationship between the independent variable and the dependent variable. If the coefficient is positive, it means that the increase in the independent variable is positively correlated with the increase in the dependent variable; if the coefficient is negative, it means that the increase in the independent variable is negatively correlated with the decrease in the dependent variable.

[0038] G6: Model prediction. Use the established model to predict the optimal ventilation equipment opening strategy.

[0039] It should be noted that the model should be adjusted and optimized according to the results of model evaluation and actual needs, such as trying different combinations of independent variables.

[0040] Specifically, in step 4, the real-time environment in the car includes temperature, relative humidity, etc. The real-time environment in the car is calculated as follows: D1: Collect data. Use temperature sensors and relative humidity sensors to measure the temperature and relative humidity in the car in real time. The temperature is in degrees Celsius. Relative humidity refers to the ratio of the water vapor content in the air at a certain temperature to the maximum possible water vapor content in the air at that temperature, usually expressed as a percentage.

[0041] D2: Calculation of comfort index. The comfort index is an index that comprehensively considers the impact of temperature and humidity on human sensation. The most common comfort index is the Temperature Humidity Index (THI). The calculation formula of the temperature and humidity index is usually based on the values ​​of temperature and humidity. A common calculation method is to use temperature and relative humidity. There are specific formulas such as the Rosenberg formula ; Where T represents the real-time temperature in the car, RH represents the real-time relative humidity in the car and is expressed in percentage.

[0042] The higher the value of the comfort index (THI), the higher the degree of discomfort felt by the human body, and the lower the comfort level, the worse the real-time environment in the vehicle cabin is considered to be. Conversely, the lower the value of the comfort index (THI), the lower the degree of discomfort felt by the human body, and the higher the comfort level, the better the real-time environment in the vehicle cabin is considered to be.

[0043] It should be noted that different regions and seasons may require different temperature and humidity index calculation formulas, and corresponding adjustments need to be made. The specific impact of climatic conditions on the human body and actual conditions shall prevail, and no limitation is made here.

[0044] Specifically, in step 5, the real-time environment in the carriage and the importance of the station are comprehensively analyzed to dynamically adjust the operation time of the ventilation equipment. The specific process is as follows: First, the real-time environment in the carriage and the importance of the station are defined as input variables and divided into different fuzzy sets. For example, "Bad", "Medium", and "Good" are for the real-time environment in the carriage, and "Low", "Medium", and "High" are for the importance of the station.

[0045] The operating time of the ventilation equipment is defined as the output variable and divided into different fuzzy sets, such as "Decrease", "Unchanged", and "Increase". For the operating time of the ventilation equipment, "Decrease" means reducing the operating time of the ventilation equipment, "Unchanged" means that the operating time of the ventilation equipment remains unchanged, and "Increase" means increasing the operating time of the ventilation equipment.

[0046] Fuzzy rules are formulated to describe the impact of the real-time environment in the carriage and the importance of the station on the operation time of the ventilation equipment. The definition of the rules is based on the professional knowledge of the industry or obtained through data analysis and experiments. For example, the real-time environment is marked as η, the importance of the station is marked as A, and the operation time of the ventilation equipment is represented by R. Then it can be defined as: Rule1: IF (η is Good) AND (A is Low) THEN(R is Decrease) Rule2: IF (η is Bad) AND (A is High) THEN(R is Increase) ...... Perform fuzzy reasoning based on fuzzy rules to dynamically adjust the operating time of ventilation equipment. It should be noted that the division of fuzzy sets is adjusted according to actual conditions. For instance, this embodiment takes three fuzzy sets as an example. In fact, the real-time environment in the car, the importance of the station and the operating time of the ventilation equipment can be divided into more than three sets, so as to more conveniently dynamically adjust the operating time of the ventilation equipment.

[0047] Furthermore, for the judgment of whether the real-time environment inside the carriage is bad, medium, or good, the comfort index threshold is set according to the actual situation for judgment. For example, the most comfortable temperature for the human body is generally between 20 and 25 degrees Celsius, and the relative humidity is generally between 40% and 60%. Therefore, by calculating when -6.8≤THI≤4, the real-time environment inside the carriage is marked as "Good"; for the judgment of the importance of the station is low, medium, or high, as in step 2, the judgment is made according to the size of E. If E1>E2>E3, the importance of the station in the cluster represented by E1 is marked as "High", etc., which will not be elaborated here.

[0048] The present invention mainly establishes a model based on the importance of stations, the distance between stations, and the duration of ventilation effects, further predicts the best strategy for opening ventilation equipment, and comprehensively analyzes the importance of stations and the real-time environment in the carriage, so as to dynamically adjust the operation time of ventilation equipment. It improves passenger comfort and saves energy, and realizes the optimization and intelligent management of subway ventilation systems.

[0049] The present invention also includes a subway ventilation system based on big data analysis, which is used to implement the above method, including a data acquisition module, a cluster analysis module, a linear regression prediction module, a comfort calculation module and a fuzzy logic control module, and the modules are signal-connected; The data collection module is used to collect all data related to the ventilation strategy in real time, including station characteristics, the distance between stations, the duration of ventilation effects, and the real-time temperature and real-time relative humidity in the carriage; The cluster analysis module classifies stations based on their characteristics and divides them into different categories using clustering algorithms; The linear regression prediction module is used to establish a linear regression model to predict the optimal ventilation strategy for each station and output the opening time and duration of the ventilation equipment; The comfort calculation module is used to convert the real-time temperature and relative humidity in the cabin into a comfort index through the Rosseberg formula; The fuzzy logic control module is used to dynamically adjust the operation time of the ventilation equipment according to the real-time calculated comfort index and the importance of the station.

[0050] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0051] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0052] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0053] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0054] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0055] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A subway ventilation method based on big data analysis, characterized in that: The steps include: Step 1: Collect the station characteristics, distance between stations and duration of ventilation effect required to determine the best strategy for ventilation equipment activation; Step 2: Based on the characteristics of the stations, use the clustering algorithm to classify the stations and determine their importance; Step 3: Considering the importance of stations, the distance between stations and the duration of ventilation effect, a linear regression model was established to predict the optimal strategy for opening ventilation equipment; Step 4: Obtain the real-time temperature and real-time relative humidity in the vehicle cabin, calculate the comfort index using the Rosberg formula, and use the comfort index as the real-time environment; Step 5: Taking the real-time environment in the carriage and the importance of the station as input variables, the fuzzy logic control method is used to adjust the operation time of the ventilation equipment.

2. A subway ventilation method based on big data analysis according to claim 1, characterized in that: In step 2, a clustering algorithm is used to calculate the importance of the station, which includes the following steps: S1: Collect the characteristic values ​​of the station; S2: Data preprocessing; standardization of eigenvalues; S3: Select the appropriate number of clusters; S4: Select K-means clustering algorithm for cluster analysis: randomly select k initial cluster centers, assign each sample to the cluster with the closest cluster center; then calculate the new center of each cluster as the new cluster center; repeat the two steps of assigning samples and updating centers until the cluster center no longer changes or the maximum number of iterations is reached. Assigning samples means assigning each sample to the cluster with the closest cluster center; updating centers means calculating the new center of each cluster as the new cluster center; Mark the randomly selected k initial cluster centers as μ1, μ2, ..., μk. For each sample, calculate its distance to each cluster center. The specific formula is ; In the formula Represents the distance between sample xi and cluster center μj; assigns it to the nearest cluster Cu (u=1, 2, 3), specifically ; For each cluster Cu, calculate its new cluster center μj, that is, the sample mean within the cluster, , where xi represents the i-th station, which contains the feature vector of all the features of the station; S5: Explain the clustering results; for each cluster, calculate the average value of each feature expressed as ; where u represents the index of the cluster and j represents the index of the feature; the specific formula is ; In the formula is the number of stations in cluster Cu, is the jth feature value of the qth station in cluster Cu; for each feature j, add the average value of the feature in a cluster to get the sum , and then calculate ; Where E represents the sum of the average values ​​of all features in the cluster, and m is the number of features; The importance of the station is evaluated by comparing the size of E; the sum of the average values ​​of all features in the first cluster is marked as E1, and so on, the sum of the average values ​​of all features in the second and third clusters are marked as E2 and E3. Among E1, E2, and E3, the maximum value indicates that the station in its corresponding cluster is important, the minimum value indicates that the station in its corresponding cluster is not important, and the middle value indicates that the importance of the station in its corresponding cluster is medium.

3. The subway ventilation method based on big data analysis according to claim 2 is characterized in that: In step 3, the optimal strategy for opening the ventilation equipment is determined based on the importance of the station, the distance between the stations, and the duration of the ventilation effect, including the following steps: G1: The ventilation equipment opening strategy is used as a binary variable, where 0 means opening the ventilation equipment every time a station is reached, and 1 means opening the ventilation equipment every other station; the distance between stations is marked as B, the duration of the ventilation effect is marked as t, and the average sum of all features in the cluster E is used to represent the importance of the station; G2: Taking the importance of the station (E), the distance between stations (B) and the duration of the ventilation effect (t) as independent variables and the ventilation equipment opening strategy as the dependent variable, a linear regression model is established; the expression of the model is ; where β0, β1, β2, β3 are the coefficients of the model, is the error term, Y1 is the ventilation equipment opening strategy; G3: Model fitting; use the least squares method to estimate the coefficients in the model so that the model fits the actual observations as closely as possible; the coefficient estimation formula is ; In the formula, X is the independent variable matrix, which contains the independent variable values ​​of each sample. The first column of the matrix X is usually a constant column with all 1s, which is used to represent the intercept term; Y is a vector, which contains the dependent variable values ​​of each sample. represents the transpose of matrix X, express The inverse matrix of , β is a vector containing all the coefficients in the linear model, including the coefficients of the intercept term and the independent variable; G4: Model evaluation: Use the F test to judge the entire linear regression model, that is, to determine whether the independent variables in the model as a whole have a significant impact on the dependent variable; the specific steps are as follows: G4.1: Calculate the F statistic ; Where SSR is the regression sum of squares, 3 refers to the number of independent variables, the number of independent variables in this embodiment is 3, SSE is the error sum of squares, and n is the sample size, i.e., n stations; G4.2: Find the F distribution table based on the F statistic and the degrees of freedom (n-3-1) and determine the p-value corresponding to the F statistic; the p-value is an indicator in statistical hypothesis testing, which indicates the probability of observing the statistic or a more extreme situation when the null hypothesis is true; G5: Model explanation; the value of the coefficient indicates the change in the dependent variable when the value of the independent variable increases by 1 unit; the positive and negative signs of the coefficient indicate the directional relationship between the independent variable and the dependent variable. If the coefficient is positive, it means that the increase in the independent variable is positively correlated with the increase in the dependent variable; if the coefficient is negative, it means that the increase in the independent variable is negatively correlated with the decrease in the dependent variable; G6: Model prediction: Use the established model to predict the optimal ventilation equipment opening strategy.

4. A subway ventilation method based on big data analysis according to claim 3, characterized in that ； In step 4, the real-time environment in the car includes temperature, relative humidity, etc. The real-time environment in the car is calculated as follows: D1: Collect data; use temperature sensors and relative humidity sensors to measure the temperature and relative humidity in the vehicle compartment in real time; D2: Calculation of comfort index: The comfort index is calculated according to the Rosberg formula. The specific formula is: ; Where T represents the real-time temperature in the car, RH represents the real-time relative humidity in the car and is expressed in percentage.

5. The subway ventilation method based on big data analysis according to claim 4 is characterized in that: In step 5, the real-time environment in the carriage and the importance of the station are comprehensively analyzed to dynamically adjust the operation time of the ventilation equipment; the specific process is as follows: Firstly, the real-time environment in the carriage and the importance of the station are defined as input variables and divided into different fuzzy sets; The running time of ventilation equipment is defined as the output variable and divided into different fuzzy sets; Formulate fuzzy rules to describe the impact of the real-time environment in the carriage and the importance of the station on the operation time of the ventilation equipment; Fuzzy reasoning is performed based on fuzzy rules to dynamically adjust the operating time of ventilation equipment.

6. A subway ventilation system based on big data analysis, used to implement the subway ventilation method based on big data analysis as described in any one of claims 1 to 5, characterized in that: It includes data acquisition module, cluster analysis module, linear regression prediction module, comfort calculation module and fuzzy logic control module, and the signal connections between the modules; The data collection module is used to collect all data related to the ventilation strategy in real time, including station characteristics, the distance between stations, the duration of ventilation effects, and the real-time temperature and real-time relative humidity in the carriage; The cluster analysis module classifies stations based on their characteristics and divides them into different categories using clustering algorithms; The linear regression prediction module is used to establish a linear regression model to predict the optimal ventilation strategy for each station and output the opening time and duration of the ventilation equipment; The comfort calculation module is used to convert the real-time temperature and relative humidity in the cabin into a comfort index through the Rosseberg formula; The fuzzy logic control module is used to dynamically adjust the operation time of the ventilation equipment according to the real-time calculated comfort index and the importance of the station.

Images