Urban rail transit vehicle air conditioner adjusting system based on comfort big data analysis

Abstract

The invention provides a comfort-based big data analysis and adjustment system for an urban rail transit vehicle air conditioner, and relates to the technical field of data analysis and adjustment. Comprising a data acquisition module, a data analysis module, a control strategy module and a control execution module. The data acquisition module acquires related data of urban rail transit vehicles in real time; the data analysis module obtains the sendible temperature with the highest comfort at present; the control strategy module is used for constructing a control model based on a random forest and obtaining a real-time adjustment strategy; the control execution module adjusts the temperature, the humidity and the wind speed. The comfort level of passengers can be improved, personalized comfort adjustment is achieved, energy can be saved, consumption can be reduced, the operation efficiency can be improved, and environmental protection is facilitated. Meanwhile, through intelligent operation and maintenance, the maintenance cost can be reduced, and the reliability of the system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis and adjustment, and particularly to a comfort big data analysis and adjustment system for urban rail transit vehicle air conditioners. Background Art

[0002] Urban rail transit is an important means for modern cities to solve traffic congestion and improve travel efficiency. As a core component of it, rail transit vehicles have gone through a long development process and continuous innovation in technology. The air conditioning system of urban rail transit vehicles is a key device to ensure the comfort of passengers in the carriages. With the rapid development of urban rail transit, higher requirements are put forward for the performance, energy saving, reliability and intelligent level of the air conditioning system. The early rail transit vehicle air conditioning systems mainly adopted simple direct expansion refrigeration systems, and the refrigerants were mostly traditional refrigerants such as R22. The control methods were also relatively simple, mainly relying on manual adjustment. Due to the limitation of technical level, the early air conditioning systems had problems such as low refrigeration efficiency, high energy consumption and poor comfort.

[0003] The existing urban rail transit vehicle air conditioning systems usually rely on preset fixed parameters or simple temperature feedback for adjustment, lacking comprehensive consideration of complex environmental factors in the carriages, resulting in inaccurate air conditioning adjustment strategies, unable to dynamically adjust according to the actual situation, prone to over-cooling or over-heating, causing energy waste, and it is difficult to ensure the comfort of all passengers, with poor passenger experience. Summary of the Invention

[0004] The present invention provides a comfort big data analysis and adjustment system for urban rail transit vehicle air conditioners to solve the defects existing in the prior art.

[0005] The present invention provides a comfort big data analysis and adjustment system for urban rail transit vehicle air conditioners, including:

[0006] A data acquisition module, used for real-time acquisition of environmental data, passenger flow data and temperature loss data related to urban rail transit vehicles.

[0007] A data analysis module, used for preprocessing the environmental data, passenger flow data and temperature loss data to obtain preprocessed data, and constructing a prediction model based on multiple linear regression, inputting the preprocessed data, and outputting the body sensation temperature with the highest current comfort.

[0008] A control strategy module, used for constructing a control model based on random forest and optimizing the hyperparameters of the control model using a quantum-inspired optimization algorithm, inputting the preprocessed data and the body sensation temperature with the highest current comfort, and outputting the real-time adjustment strategy of the air conditioner.

[0009] A control execution module, configured to generate real-time control instructions according to real-time adjustment strategies and control an air conditioning system according to the real-time control instructions, so as to adjust temperature, humidity, and wind speed.

[0010] A feedback evaluation module, configured to monitor the temperature inside the carriage in real time and evaluate the effect of the real-time adjustment strategy.

[0011] According to an air conditioning adjustment system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the environmental data includes temperature data, humidity data, and wind speed inside and outside the carriage of the urban rail transit vehicle. The passenger flow data includes the real-time number of passengers and the real-time position distribution inside the carriage of the urban rail transit vehicle. The temperature loss data represents the amount of temperature loss inside the vehicle during a single route of the urban rail transit vehicle when it stops.

[0012] According to an air conditioning adjustment system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the calculation process of the temperature loss inside the vehicle includes:

[0013] Obtain the moment when the vehicle starts to stop and the moment when it restarts after the stop.

[0014] Install a plurality of high-precision temperature sensors inside the carriage, and use the position of each high-precision temperature sensor as a test point.

[0015] When the vehicle starts to stop, record the initial temperature values of each measurement point inside the carriage through the sensors.

[0016] When the vehicle restarts after the stop, measure the temperature values of each point inside the carriage again, subtract the initial temperature value from the temperature value at the end to obtain the temperature change amount of each measurement point.

[0017] Comprehensively calculate the overall temperature loss of the vehicle during the stop according to the temperature change amounts of each measurement point and their position weights inside the carriage.

[0018] According to an air conditioning adjustment system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the preprocessing process includes: screening, cleaning, and calibrating the environmental data to remove outliers and noise. Statistically analyzing and classifying the passenger flow data, and dividing the passenger flow into peak periods and off-peak periods according to different time periods and carriage positions. Correcting and converting the temperature loss data.

[0019] According to an air conditioning adjustment system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the process of constructing a prediction model based on multiple linear regression includes:

[0020] Collect historical environmental data, historical passenger flow data, and historical temperature loss data related to urban rail transit vehicles, and perform preprocessing to obtain historical preprocessed data.

[0021] The historical preprocessed data is randomly divided into training set and test set.

[0022] Initialize the regression coefficients of the prediction model based on multiple linear regression.

[0023] The prediction model is trained using the training set, the regression coefficient of the prediction model is optimized by minimizing the mean square error, and the gradient descent algorithm is used to update the regression coefficient.

[0024] The performance of the trained prediction model is evaluated using the test set, and the evaluation indicators are calculated, including mean square error, mean absolute error, and determination coefficient.

[0025] Repeat the training and performance evaluation of the prediction model, retain the prediction model regression coefficients that meet the test accuracy, and obtain the prediction model.

[0026] According to an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis provided by the present invention, the process of constructing a control model based on random forest includes:

[0027] Collect preprocessed data and the corresponding currently most comfortable perceived temperature, establish a sample set, extract and transform features from the data in the sample set, and establish a feature set. Feature extraction and transformation include: binning and discretizing continuous features and one-hot encoding categorical features.

[0028] The importance and relevance of each feature in the feature set are evaluated, and the key features that have a significant impact on predicting the real-time adjustment strategy of air conditioning are screened out.

[0029] Set the number of decision trees in the random forest, randomly extract features from the feature set, and build each decision tree. Set initial parameters for each decision tree, including the maximum depth and the minimum number of leaf node samples.

[0030] A preset proportion of sample data is randomly extracted from the sample set as training data. For each node of the decision tree, the information gain and Gini index are calculated based on the selected features to determine the best partitioning features and partitioning points, and the node data is divided into subsets. The partitioning process is repeated to gradually grow the decision tree. When the preset stop condition is reached, the further splitting of the node is stopped, and a control model based on random forest is obtained.

[0031] According to an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis provided by the present invention, the process of optimizing the hyperparameters of the control model using a quantum heuristic optimization algorithm includes:

[0032] The number of decision trees, the depth of the tree, and the ratio of feature selection are taken as the hyperparameter combinations that need to be optimized.

[0033] Randomly generate a set of initial qubit states, where the qubit states represent the initial conjecture of hyperparameters.

[0034] Measure the qubits to obtain a set of classical hyperparameter combinations as the current solution.

[0035] Apply the measured hyperparameter combinations to the control model of the deep forest, and use the accuracy rate and mean square error to evaluate the performance of the model under the hyperparameter combinations to obtain the fitness value.

[0036] According to the fitness value, use the update rule of the quantum-inspired optimization algorithm to adjust the probability amplitude of the qubits.

[0037] Repeat the steps of measurement, fitness evaluation, and qubit update until the preset number of iterations is reached, and obtain the hyperparameter combination with the optimal fitness value.

[0038] According to an air-conditioning regulation system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the control execution module includes an instruction generation unit, an instruction transmission unit, and an execution control unit. The instruction generation unit is used to formulate real-time control instructions related to temperature, humidity, and wind speed regulation according to the real-time adjustment strategy, and the real-time control instructions include control parameters and instruction formats. The instruction transmission unit is used to ensure the timeliness and accuracy of the real-time control instructions during the transmission process. The execution control unit is used to control the relevant devices in the air-conditioning system according to the real-time control instructions.

[0039] According to an air-conditioning regulation system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the feedback evaluation module includes a temperature monitoring unit and a strategy effect evaluation unit. The temperature monitoring unit is used to measure the temperature data inside the carriages of urban rail transit vehicles in real time according to the sensor devices. The strategy effect evaluation unit is used to evaluate and analyze the actual effect of the real-time adjustment strategy.

[0040] According to an air-conditioning regulation system for urban rail transit vehicles based on comfort big data analysis provided by the present invention, the feedback evaluation module further includes a data feedback unit. The data feedback unit is used to feedback the evaluation information to the control strategy module when the actual effect is lower than the preset effect threshold, so as to optimize and improve the control model and adjustment strategy.

[0041] The present invention has at least the following technical effects:

[0042] The air conditioner for urban rail transit vehicles provided by the present invention is based on a comfort big data analysis and adjustment system. By collecting environmental data, passenger flow data, and temperature loss data in real time and combining with a prediction model based on multiple linear regression, it can accurately predict the body temperature with the highest current comfort. The air conditioning system can dynamically adjust the temperature, humidity, and wind speed according to the actual situation inside the carriage, providing passengers with a personalized comfortable experience. By constructing a control model based on random forest and using a quantum-inspired optimization algorithm to optimize the model hyperparameters, precise control of the air conditioning system can be achieved, effectively reducing temperature fluctuations and maintaining the stability of the temperature inside the carriage, thereby improving the comfort of passengers and dynamically adjusting the cooling capacity and ventilation volume according to actual needs to avoid unnecessary energy consumption. Traditional air conditioning systems often overcool or overheat, causing energy waste. The present invention can avoid overcooling or overheating and achieve energy conservation and consumption reduction by collecting data in real time and using a prediction model to determine the optimal body temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0044] Figure 1 It is a schematic structural diagram of the air conditioner for urban rail transit vehicles based on the comfort big data analysis and adjustment system provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0046] The following will be combined with Figure 1 Describe the air conditioner for urban rail transit vehicles based on the comfort big data analysis and adjustment system of the present invention.

[0047] Figure 1 It is a schematic structural diagram of the air conditioner for urban rail transit vehicles based on the comfort big data analysis and adjustment system provided by the embodiment of the present invention.

[0048] As Figure 1As shown in the figure, the air conditioner for urban rail transit vehicles provided by the embodiment of the present invention is based on a comfort big data analysis and adjustment system, and includes a data acquisition module, a data analysis module, a control strategy module, a control execution module, and a feedback evaluation module.

[0049] The data acquisition module is used to collect in real time the environmental data, passenger flow data, and temperature loss data related to urban rail transit vehicles.

[0050] The environmental data includes the temperature data, humidity data, and wind speed inside and outside the carriages of urban rail transit vehicles. The passenger flow data includes the real-time number of passengers and the real-time position distribution inside the carriages of urban rail transit vehicles. The temperature loss data represents the amount of temperature loss inside the vehicle during a single route of urban rail transit vehicles when docking.

[0051] The calculation process of the temperature loss amount inside the vehicle includes:

[0052] Obtain the moment when the vehicle starts to dock and the moment when it restarts after the docking ends.

[0053] Install a plurality of high-precision temperature sensors inside the carriage, and use the position of each high-precision temperature sensor as a test point.

[0054] When the vehicle starts to dock, record the initial temperature values of each measurement point inside the carriage through the sensors.

[0055] When the vehicle restarts after the docking ends, measure the temperature values of each point inside the carriage again, subtract the initial temperature value from the temperature value at the end to obtain the temperature change amount of each measurement point.

[0056] Based on the temperature change amounts of each measurement point and their position weights inside the carriage, comprehensively calculate the overall temperature loss amount of the vehicle during docking.

[0057] In this embodiment, by collecting environmental data, passenger flow data, and temperature loss data in real time, a multi-dimensional and high-resolution data foundation can be provided, which provides a reliable basis for subsequent data analysis and intelligent control. Traditional air-conditioning control systems often rely only on a single temperature sensor and cannot fully consider the actual feelings of passengers. The rich data collected by this module can more comprehensively reflect the comfort conditions inside the carriage. For example, when the passenger flow is large, the human body will emit heat, resulting in an increase in the carriage temperature; when the doors are frequently opened and closed, the cold air loss accelerates, resulting in temperature fluctuations in the carriage. These factors will all affect the comfort of passengers. By collecting this data, the system can more accurately judge the actual comfort conditions inside the carriage and make more refined adjustments accordingly. The real-time collection feature can ensure that the system can respond in a timely manner to changes in the carriage environment and avoid inaccurate control caused by data lag. Through high-precision data collection, this module lays a solid foundation for building an accurate prediction model and an effective control strategy, ultimately improving the passenger experience.

[0058] The data analysis module is used to preprocess the environmental data, passenger flow data, and temperature loss data to obtain preprocessed data, and build a prediction model based on multiple linear regression. Input the preprocessed data and output the body sensation temperature with the highest current comfort level.

[0059] The process of preprocessing includes: screening, cleaning, and calibrating the environmental data to remove outliers and noise. Statistically analyzing and classifying the passenger flow data, and dividing the passenger flow into peak periods and off-peak periods according to different time periods and carriage positions. Correcting and transforming the temperature loss data.

[0060] The process of building a prediction model based on multiple linear regression includes:

[0061] Collect historical environmental data, historical passenger flow data, and historical temperature loss data related to urban rail transit vehicles, and perform preprocessing to obtain historical preprocessed data.

[0062] Randomly divide the historical preprocessed data into a training set and a test set.

[0063] Initialize the regression coefficients of the prediction model based on multiple linear regression.

[0064] Use the training set to train the prediction model, optimize the regression coefficients of the prediction model by minimizing the mean square error, and update the regression coefficients using the gradient descent algorithm.

[0065] Use the test set to evaluate the performance of the trained prediction model, calculate the evaluation metrics, and the evaluation metrics include mean square error, mean absolute error, and coefficient of determination.

[0066] The prediction model is repeatedly trained and its performance is evaluated, and the regression coefficients of the prediction model that meet the test accuracy are retained to obtain the prediction model.

[0067] In this embodiment, the data analysis module mines the key factors affecting passenger comfort from the massive data and uses these factors to predict the body sensation temperature that can most improve passenger comfort at present. This module first preprocesses the data obtained by the data acquisition module to eliminate noise and outliers and ensure the quality of the data. Then, based on the multiple linear regression model, the relationships between environmental data, passenger flow data, temperature loss data, and passenger comfort are established. The advantage of the multiple linear regression model is that it is simple, easy to understand and implement, and can quickly establish a prediction model. By inputting the preprocessed data, this model can predict the body sensation temperature at which passengers feel most comfortable in the current environment. Among them, the body sensation temperature is not a simple fixed value, but is dynamically adjusted according to the actual situation in the carriage, which better meets the personalized needs of passengers. Compared with the traditional fixed temperature setting, the body sensation temperature target provided by this module can more accurately reflect the actual feelings of passengers. For example, when the passenger flow is large, the model will predict a relatively low body sensation temperature to offset the heat dissipated by the human body and keep the carriage cool. This personalized comfort target can significantly improve the passenger experience.

[0068] The control strategy module is used to construct a control model based on the random forest and optimize the hyperparameters of the control model using the quantum-inspired optimization algorithm, input the preprocessed data and the body sensation temperature with the highest current comfort level, and output the real-time adjustment strategy of the air conditioner.

[0069] The process of constructing a control model based on the random forest includes:

[0070] Collect the preprocessed data and the corresponding body sensation temperature with the highest current comfort level, establish a sample set, perform feature extraction and transformation on the data in the sample set, and establish a feature set. The feature extraction and transformation include: binning and discretizing continuous features and performing one-hot encoding on categorical features.

[0071] Evaluate the importance and relevance of each feature in the feature set, and screen out the key features that have a significant impact on predicting the real-time adjustment strategy of the air conditioner.

[0072] Set the number of decision trees in the random forest, randomly extract features from the feature set, and construct each decision tree. Set the initial parameters for each decision tree, and the initial parameters include the maximum depth and the minimum number of samples in the leaf nodes.

[0073] Randomly select a preset proportion of sample data from the sample set as training data. For each node of the decision tree, calculate the information gain and Gini index based on the selected features to determine the best splitting feature and splitting point, and divide the node data into subsets. Repeat the splitting process to gradually grow the decision tree. When the preset stopping condition is reached, stop the further splitting of the node.

[0074] Repeat the above steps to construct multiple decision trees and obtain a control model based on a random forest.

[0075] The process of using a quantum-inspired optimization algorithm to optimize the hyperparameters of the control model includes:

[0076] Take the number of decision trees, the depth of the trees, and the proportion of feature selection as the hyperparameter combination to be optimized.

[0077] Randomly generate an initial set of qubit states, where the qubit states represent the initial conjectures of the hyperparameters.

[0078] Measure the qubits to obtain a set of classical hyperparameter combinations as the current solution.

[0079] Apply the measured hyperparameter combination to the control model of the deep forest and use the accuracy rate and mean squared error to evaluate the performance of the model under the hyperparameter combination to obtain the fitness value.

[0080] According to the fitness value, use the update rule of the quantum-inspired optimization algorithm to adjust the probability amplitudes of the qubits.

[0081] Repeat the steps of measurement, fitness evaluation, and qubit update until the preset number of iterations is reached to obtain the hyperparameter combination with the optimal fitness value.

[0082] In this embodiment, the control strategy module can intelligently generate a real-time adjustment strategy for the air-conditioning system according to the comfort objectives provided by the data analysis module, so as to achieve precise control of the temperature, humidity and wind speed in the car cabin. This module uses the random forest algorithm to build a control model. Compared with the traditional linear model, the random forest can better handle non-linear relationships and adapt to the complex car cabin environment. The advantage of the random forest algorithm lies in its strong generalization ability and robustness, which can effectively cope with various changes in the car cabin environment. To further improve the performance of the control model, this module also uses the quantum-inspired optimization algorithm to optimize the hyperparameters of the random forest. The quantum-inspired optimization algorithm has the advantages of strong global search ability and fast convergence speed, and can quickly find the optimal combination of hyperparameters to improve the accuracy of the control model. By inputting the preprocessed data and the current body sensation temperature with the highest comfort level, this module can output the real-time adjustment strategy of the air-conditioning system, including the adjustment schemes for temperature, humidity and wind speed. This strategy is based on big data analysis and intelligent optimization algorithms, and can more accurately grasp the comfort conditions in the car cabin and achieve precise control of the air-conditioning system.

[0083] The control execution module is used to generate real-time control instructions according to the real-time adjustment strategy and control the air-conditioning system according to the real-time control instructions to achieve the adjustment of temperature, humidity and wind speed.

[0084] The control execution module includes an instruction generation unit, an instruction transmission unit and an execution control unit. The instruction generation unit is used to formulate real-time control instructions related to the adjustment of temperature, humidity and wind speed according to the real-time adjustment strategy. The real-time control instructions include control parameters and instruction formats. The instruction transmission unit is used to ensure the timeliness and accuracy of the real-time control instructions during the transmission process. The execution control unit is used to control the relevant equipment in the air-conditioning system according to the real-time control instructions.

[0085] In this embodiment, the instruction generation unit parses the real-time adjustment strategy output by the control strategy module. The real-time adjustment strategy contains information in multiple dimensions, including: target temperature, target humidity, wind speed level, fresh air ratio, and the adjustment range of the compressor speed. Define the specific meanings and value ranges of the parameters in the real-time adjustment strategy. After the strategy is parsed, the information in the strategy needs to be mapped to specific air conditioner control parameters. For example, map the target temperature to the set value of the chilled water temperature of the chiller, and map the wind speed level to the set value of the speed of the supply fan. This mapping process requires a full understanding of the control characteristics and parameter ranges of the air conditioner system to ensure that the generated control parameters are within the safe operating range of the system. To enable the air conditioner system to correctly identify and execute control instructions, the instruction generation unit needs to encapsulate the control parameters according to a predefined instruction format. The instruction format may include: start bit, device address, control parameter type, control parameter value, check bit, end bit, etc. Different air conditioner systems may adopt different instruction formats, and the instruction generation unit needs to be able to flexibly adapt to various instruction formats.

[0086] After the execution control unit receives the control instruction sent by the instruction transmission unit, it first needs to parse the instruction to extract the control parameters and the type of control instruction. The execution control unit needs to have the ability to drive various devices in the air conditioner system. These devices may include: Chiller: used to provide a cold source, controlling its chilled water temperature and flow rate. Supply fan: used to send cold or hot air into the carriage, controlling its speed and air volume. Return air valve: used to adjust the return air volume, controlling the air circulation in the carriage. Fresh air valve: used to adjust the fresh air volume, improving the air quality in the carriage. Humidifier / dehumidifier: used to adjust the humidity in the carriage.

[0087] To ensure the accuracy and stability of control, the execution control unit usually adopts a closed-loop control method. For example, the temperature in the carriage can be monitored in real time through a temperature sensor, and the actual temperature is compared with the target temperature. According to the deviation, the chilled water temperature of the chiller is adjusted to achieve precise control of the carriage temperature.

[0088] The feedback evaluation module is used to monitor the temperature in the carriage in real time and evaluate the effect of the real-time adjustment strategy.

[0089] The feedback evaluation module includes a temperature monitoring unit, a strategy effect evaluation unit, and a data feedback unit. The temperature monitoring unit is used to measure the temperature data in the carriage of an urban rail transit vehicle in real time according to sensor devices. The strategy effect evaluation unit is used to evaluate and analyze the actual effect of the real-time adjustment strategy. The data feedback unit is used to feedback the evaluation information to the control strategy module when the actual effect is lower than the preset effect threshold, so as to optimize and improve the control model and adjustment strategy.

[0090] In this embodiment, the core of the temperature monitoring unit lies in the deployment of the sensor network. It is necessary to strategically arrange multiple high-precision temperature sensors inside the carriage to cover different areas of the carriage, including the area near the door, the middle of the carriage, both ends of the carriage, and the area near the ventilation opening. The multi-point deployment can more comprehensively reflect the temperature distribution inside the carriage and avoid deviations caused by the limitation of the sensor position. At the same time, in order to ensure the accuracy and reliability of the data, the temperature monitoring unit uses high-precision and fast-response temperature sensors.

[0091] The policy effect evaluation unit compares the real-time temperature data transmitted by the temperature monitoring unit with the ideal temperature data predicted by the control strategy module, including the uniformity of the temperature distribution and the rate of temperature change. The policy effect evaluation unit calculates comfort indexes based on the temperature data, including: mean radiant temperature, predicted mean vote, predicted percentage dissatisfied, and temperature uniformity index. The mean radiant temperature takes into account the radiant heat transfer between the human body and the surrounding environment and can better reflect the real feelings of the human body. The predicted mean vote comprehensively considers comfort indexes such as temperature, humidity, wind speed, activity intensity, and clothing insulation. The predicted percentage dissatisfied predicts the proportion of people who are dissatisfied with the environment. The temperature uniformity index evaluates the degree of uniformity of the temperature distribution inside the carriage.

[0092] The policy effect evaluation unit needs to preset a set of evaluation criteria for judging whether the actual effect of the air conditioning system meets the expectations. The evaluation criteria can be adjusted according to different operation requirements. For example, during peak hours, the comfort requirements can be appropriately reduced to ensure the stable operation of the system; while during off-peak hours, the comfort requirements can be increased to provide a better experience for passengers.

[0093] The data feedback unit preset an effect threshold for judging whether the actual effect of the air conditioning system needs to be improved. The effect threshold can be set according to different comfort indexes. When the policy effect evaluation unit determines that the actual effect of the air conditioning system is lower than the preset effect threshold, the data feedback unit will generate feedback information. The feedback information needs to include a problem description, data support, and improvement suggestions. The problem description is used to describe in detail the problems existing in the system, such as too high temperature, uneven temperature distribution, etc. The data support is used to provide data supporting the problem description, such as real-time temperature data, comfort indexes, etc. The improvement suggestions are used to put forward improvement suggestions for the problems, such as adjusting the cooling capacity, adjusting the ventilation strategy, etc. These suggestions can be based on preset rules or automatically generated through machine learning algorithms.

[0094] In summary, this embodiment provides an air-conditioning regulation system for urban rail transit vehicles based on comfort big data analysis. By collecting environmental data, passenger flow data, and temperature loss data in real time and combining with a prediction model based on multiple linear regression, it can accurately predict the body temperature with the highest current comfort level. The air-conditioning system can dynamically adjust the temperature, humidity, and wind speed according to the actual situation inside the carriage, providing passengers with a personalized comfortable experience. By constructing a control model based on random forest and using a quantum-inspired optimization algorithm to optimize the model hyperparameters, precise control of the air-conditioning system can be achieved, effectively reducing temperature fluctuations and maintaining the stability of the temperature inside the carriage, thereby improving the comfort of passengers, and dynamically adjusting the cooling capacity and ventilation volume according to actual needs to avoid unnecessary energy consumption. Traditional air-conditioning systems often overcool or overheat, resulting in energy waste. This embodiment can avoid overcooling or overheating and achieve energy conservation and consumption reduction by collecting data in real time and using a prediction model to determine the optimal body temperature.

[0095] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0096] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An air-conditioning regulation system for urban rail transit vehicles based on comfort big data analysis, characterized in that, Including: A data acquisition module for real-time acquisition of environmental data, passenger flow data, and temperature loss data related to urban rail transit vehicles; A data analysis module for preprocessing the environmental data, passenger flow data, and temperature loss data to obtain preprocessed data, constructing a prediction model based on multiple linear regression, inputting the preprocessed data, and outputting the body sensation temperature with the highest current comfort level; A control strategy module for constructing a control model based on random forest and optimizing the hyperparameters of the control model using a quantum-inspired optimization algorithm, inputting the preprocessed data and the body sensation temperature with the highest current comfort level, and outputting an air-conditioning real-time adjustment strategy; A control execution module for generating real-time control instructions according to the real-time adjustment strategy and controlling the air-conditioning system according to the real-time control instructions to achieve the adjustment of temperature, humidity, and wind speed; A feedback evaluation module for real-time monitoring of the temperature inside the carriage and evaluating the effect of the real-time adjustment strategy.

2. The air conditioner for urban rail transit vehicles based on comfort big data analysis and adjustment system according to claim 1, characterized in that The environmental data includes temperature data, humidity data, and wind speed inside and outside the carriage of urban rail transit vehicles; the passenger flow data includes the real-time number of passengers and the real-time position distribution inside the carriage of urban rail transit vehicles; the temperature loss data represents the amount of temperature loss inside the vehicle during a single route of urban rail transit vehicles when docking.

3. The air conditioner for urban rail transit vehicles based on the comfort big data analysis and adjustment system according to claim 2, characterized in that, The calculation process of the temperature loss inside the vehicle includes: Obtaining the moment when the vehicle starts to dock and the moment when it restarts after docking; Installing multiple high-precision temperature sensors inside the carriage and taking the position of each high-precision temperature sensor as a test point; At the beginning of vehicle docking, recording the initial temperature values of each measurement point inside the carriage through the sensors; When the vehicle restarts after docking, measuring the temperature values of each point inside the carriage again, subtracting the initial temperature value from the temperature value at the end to obtain the temperature change amount of each measurement point; Comprehensively calculating the overall temperature loss amount of the vehicle during docking according to the temperature change amounts of each measurement point and their position weights inside the carriage.

4. The air conditioner for urban rail transit vehicles based on comfort big data analysis regulation system according to claim 1, characterized in that, The process of the preprocessing includes: screening, cleaning, and calibrating the environmental data to remove outliers and noise; statistically analyzing and classifying the passenger flow data, and dividing the passenger flow into peak periods and off-peak periods according to different time periods and carriage positions; correcting and transforming the temperature loss data.

5. The air conditioning based on comfort big data analysis and adjustment system for urban rail transit vehicles according to claim 1, wherein, The process of constructing a prediction model based on multiple linear regression includes: Collecting historical environmental data, historical passenger flow data, and historical temperature loss data related to urban rail transit vehicles and performing preprocessing to obtain historical preprocessed data; Randomly dividing the historical preprocessed data into a training set and a test set; Initializing the regression coefficients of a prediction model based on multiple linear regression; Training the prediction model using the training set, optimizing the regression coefficients of the prediction model by minimizing the mean square error, and updating the regression coefficients using the gradient descent algorithm; Performing performance evaluation on the trained prediction model using the test set and calculating evaluation metrics, where the evaluation metrics include mean square error, mean absolute error, and coefficient of determination; The prediction model is repeatedly trained and performance evaluated, and the prediction model regression coefficients that meet the test accuracy are retained to obtain a prediction model.

6. The air conditioner for urban rail transit vehicles based on the comfort big data analysis and adjustment system according to claim 1, wherein, The process of building a random forest-based control model includes: Collect preprocessed data and the corresponding currently most comfortable body temperature, establish a sample set, extract and transform the data in the sample set, and establish a feature set. The feature extraction and transformation include: binning and discretizing continuous features and performing one-hot encoding on categorical features; Evaluate the importance and relevance of each feature in the feature set, and select key features that have a significant impact on predicting the real-time adjustment strategy of the air conditioner; The number of decision trees in the random forest is set, and features are randomly extracted from the feature set to construct each decision tree; initial parameters are set for each decision tree, and the initial parameters include a maximum depth and a minimum number of leaf node samples; A preset proportion of sample data is randomly extracted from the sample set as training data; for each node of the decision tree, information gain and Gini index are calculated based on the selected features to determine the best partitioning features and partitioning points, the node data is divided into subsets, and the partitioning process is repeated to gradually grow the decision tree; when the preset stopping condition is reached, further splitting of the node is stopped to obtain a control model based on random forest.

7. The air conditioner for urban rail transit vehicles based on comfort big data analysis and adjustment system according to claim 1, characterized in that, The process of optimizing the hyperparameters of the control model using a quantum-inspired optimization algorithm includes: The number of decision trees, the depth of the tree, and the ratio of feature selection are taken as the hyperparameter combinations that need to be optimized; randomly generating an initial set of qubit states, the qubit states representing initial guesses for the hyperparameters; Measure the qubits and obtain a set of classical hyperparameter combinations as the current solution; Apply the measured hyperparameter combination to the control model of the deep forest, and use the accuracy and mean square error to evaluate the performance of the model under the hyperparameter combination to obtain the fitness value; According to the fitness value, adjusting the probability amplitude of the qubit using an update rule of a quantum heuristic optimization algorithm; The steps of measurement, fitness evaluation, and qubit update are repeated until the preset number of iterations is reached, and the hyperparameter combination with the optimal fitness value is obtained.

8. The air conditioner for urban rail transit vehicles based on comfort big data analysis and adjustment system according to claim 1, characterized in that, The control execution module includes an instruction generation unit, an instruction transmission unit and an execution control unit; the instruction generation unit is used to formulate real-time control instructions related to temperature, humidity and wind speed adjustment according to the real-time adjustment strategy, and the real-time control instructions include control parameters and instruction formats; the instruction transmission unit is used to ensure the timeliness and accuracy of the real-time control instructions during the transmission process; the execution control unit is used to control the relevant equipment in the air-conditioning system according to the real-time control instructions.

9. The air conditioner for urban rail transit vehicles based on comfort big data analysis and adjustment system according to claim 1, characterized in that, The feedback evaluation module includes a temperature monitoring unit and a strategy effect evaluation unit; the temperature monitoring unit is used to measure the temperature data in the urban rail transit vehicle compartment in real time according to the sensor equipment; the strategy effect evaluation unit is used to evaluate and analyze the actual effect of the real-time adjustment strategy.

10. The air conditioner for urban rail transit vehicles based on comfort big data analysis and adjustment system according to claim 9, characterized in that, The feedback evaluation module further includes a data feedback unit; the data feedback unit is used to feedback the evaluation information to the control strategy module when the actual effect is lower than the preset effect threshold, so as to optimize and improve the control model and the adjustment strategy.

Images