Urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis

Abstract

The present invention provides an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis, which relates to the field of data analysis and adjustment technology. It includes a data acquisition module, a data analysis module, a control strategy module and a control execution module. The data acquisition module collects relevant data of urban rail transit vehicles in real time; the data analysis module obtains the currently most comfortable perceived temperature; the control strategy module is used to construct a control model based on random forests to obtain real-time adjustment strategies; and the control execution module realizes the adjustment of temperature, humidity and wind speed. The present invention can not only improve the comfort of passengers and realize personalized comfort adjustment, but also save energy and reduce consumption, improve operational efficiency, and is beneficial to environmental protection. At the same time, through intelligent operation and maintenance, maintenance costs can be reduced and system reliability can be improved.

Description

Technical Field

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

[0002] Urban rail transit is a crucial means of alleviating traffic congestion and improving travel efficiency in modern cities. Rail transit vehicles, as a core component of these vehicles, have undergone a long history of development and continuous technological innovation. Urban rail transit vehicle air conditioning systems are crucial for ensuring passenger comfort. The rapid development of urban rail transit has placed higher demands on the performance, energy efficiency, reliability, and intelligence of air conditioning systems. Early rail transit vehicle air conditioning systems primarily utilized simple direct expansion refrigeration systems, using traditional refrigerants such as R22. Control methods were also relatively simple, relying primarily on manual adjustment. Due to technological limitations, these early air conditioning systems suffered from low cooling efficiency, high energy consumption, and poor comfort.

[0003] Existing urban rail transit vehicle air-conditioning systems typically rely on preset fixed parameters or simple temperature feedback for adjustment. They lack comprehensive consideration of complex environmental factors within the vehicle cabin, resulting in inaccurate air-conditioning adjustment strategies and an inability to dynamically adjust according to actual conditions. This can easily lead to over-cooling or over-heating, resulting in energy waste, making it difficult to ensure the comfort of all passengers and resulting in a poor passenger experience. Summary of the Invention

[0004] The present invention provides an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis, which is used to solve the defects existing in the prior art.

[0005] The present invention provides an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis, comprising:

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

[0007] The data analysis module is used to preprocess environmental data, passenger flow data and temperature loss data to obtain preprocessed data, and to build a prediction model based on multiple linear regression. The preprocessed data is input and the currently most comfortable perceived temperature is output.

[0008] The control strategy module is used to build a control model based on random forests and optimize the hyperparameters of the control model using a quantum-inspired optimization algorithm. It inputs preprocessed data and the currently most comfortable perceived temperature and outputs a real-time air conditioning adjustment strategy.

[0009] 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.

[0010] The feedback evaluation module is used to monitor the temperature inside the vehicle in real time and evaluate the effectiveness of the real-time adjustment strategy.

[0011] According to the present invention, a system for analyzing and regulating air conditioning in urban rail transit vehicles based on big data comfort analysis is provided. Environmental data includes temperature, humidity, and wind speed data inside and outside the urban rail transit vehicle compartment. Passenger flow data includes the real-time number of passengers and their location distribution within the urban rail transit vehicle compartment. Temperature loss data represents the amount of internal temperature loss during stops on a single urban rail transit route.

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

[0013] Get the time when the vehicle starts to stop and the time when it ends to restart.

[0014] Multiple high-precision temperature sensors are installed inside the carriage, and the location of each high-precision temperature sensor is used as a test point.

[0015] When the vehicle stops, the initial temperature values ​​of each measuring point in the vehicle compartment are recorded by sensors.

[0016] When the vehicle is restarted after stopping, the temperature value of each point in the car is measured again, and the initial temperature value is subtracted from the ending temperature value to obtain the temperature change of each measuring point.

[0017] Based on the temperature change of each measurement point and its position weight in the vehicle compartment, the overall temperature loss of the vehicle during the parking period is calculated comprehensively.

[0018] According to the present invention, a system for analyzing and adjusting air conditioning in urban rail transit vehicles based on comfort big data is provided. The preprocessing process includes: filtering, cleaning, and calibrating environmental data to remove outliers and noise; collecting statistics and classifying passenger flow data; dividing passenger flow into peak and off-peak periods based on different time periods and car locations; and correcting and converting temperature loss data.

[0019] According to the urban rail transit vehicle air conditioning adjustment system 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] Historical environmental data, historical passenger flow data, and historical temperature loss data related to urban rail transit vehicles are collected and preprocessed to obtain historical preprocessed data.

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

[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 regression coefficient is updated using the gradient descent algorithm.

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

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

[0026] According to the present invention, an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis is provided, and 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 performing one-hot encoding on categorical features.

[0028] The importance and relevance of each feature in the feature set are evaluated, and key features with 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 construct each decision tree. Set initial parameters for each decision tree, including the maximum depth and 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 in the decision tree, information gain and Gini index are calculated based on the selected features to determine the optimal partitioning features and points. The node data is then divided into subsets, and the partitioning process is repeated to gradually grow the decision tree. When the preset stopping condition is reached, further node splitting is stopped, resulting in a control model based on random forest.

[0031] According to the present invention, an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis is provided. 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 trees, and the ratio of feature selection are taken as the hyperparameter combinations that need to be optimized.

[0033] An initial set of qubit states is randomly generated, where the qubit states represent initial guesses for the hyperparameters.

[0034] The qubit is measured and a set of classical hyperparameter combinations is obtained as the current solution.

[0035] The measured hyperparameter combination is applied to the control model of the deep forest, and the performance of the model under the hyperparameter combination is evaluated using accuracy and mean square error to obtain the fitness value.

[0036] Based on the fitness value, the probability amplitude of the qubit is adjusted using the update rule of the quantum-inspired optimization algorithm.

[0037] 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.

[0038] According to the present invention, a system for adjusting air conditioning in urban rail transit vehicles based on big data comfort analysis is provided. The control execution module includes a command generation unit, a command transmission unit, and an execution control unit. The command generation unit is used to formulate real-time control commands related to temperature, humidity, and wind speed adjustment based on real-time adjustment strategies. The real-time control commands include control parameters and a command format. The command transmission unit is used to ensure the timeliness and accuracy of the real-time control commands during transmission. The execution control unit is used to control the relevant equipment in the air conditioning system according to the real-time control commands.

[0039] According to the present invention, a system for adjusting air conditioning in urban rail transit vehicles based on big data comfort analysis includes a feedback evaluation module comprising a temperature monitoring unit and a strategy effectiveness evaluation unit. The temperature monitoring unit is configured to measure temperature data within the urban rail transit vehicle compartment in real time using a sensor device. The strategy effectiveness evaluation unit is configured to evaluate and analyze the actual effectiveness of the real-time adjustment strategy.

[0040] In an urban rail transit vehicle air conditioning adjustment system based on big data comfort analysis, the feedback evaluation module further includes a data feedback unit. This unit is configured to provide feedback to the control strategy module when the actual performance falls below a preset performance threshold, thereby optimizing and improving the control model and adjustment strategy.

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

[0042] The urban rail transit vehicle air conditioning 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 it with a prediction model based on multiple linear regression, it can accurately predict the current most comfortable perceived temperature. The air-conditioning system can dynamically adjust the temperature, humidity and wind speed according to the actual situation in the car to provide passengers with a personalized comfort experience. By constructing a control model based on random forests and using a quantum heuristic optimization algorithm to optimize the model hyperparameters, it is possible to achieve precise control of the air-conditioning system, effectively reduce temperature fluctuations, maintain the temperature stability in the car, thereby improving passenger comfort, and dynamically adjust the cooling and ventilation capacity according to actual needs to avoid unnecessary energy consumption. Traditional air-conditioning systems often over-cool or over-heat, resulting in energy waste. The present invention collects data in real time and uses a prediction model to determine the optimal perceived temperature, which can avoid excessive cooling or heating and achieve energy saving and consumption reduction. 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 briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 It is a structural diagram of the urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] The following combination Figure 1 The present invention describes an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis.

[0047] Figure 1 It is a structural diagram of the urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis provided by an embodiment of the present invention.

[0048] like Figure 1As shown, the urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis provided by the embodiment of the present invention 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 real-time environmental data, passenger flow data and temperature loss data related to urban rail transit vehicles.

[0050] Environmental data includes temperature, humidity, and wind speed inside and outside urban rail transit vehicles. Passenger flow data includes the real-time number of passengers and their location distribution within urban rail transit vehicles. Temperature loss data represents the amount of temperature loss inside urban rail transit vehicles during stops on a single route.

[0051] The calculation process of the vehicle's internal temperature loss includes:

[0052] Get the time when the vehicle starts to stop and the time when it ends to restart.

[0053] Multiple high-precision temperature sensors are installed inside the carriage, and the location of each high-precision temperature sensor is used as a test point.

[0054] When the vehicle stops, the initial temperature values ​​of each measuring point in the vehicle compartment are recorded by sensors.

[0055] When the vehicle is restarted after stopping, the temperature value of each point in the car is measured again, and the initial temperature value is subtracted from the ending temperature value to obtain the temperature change of each measuring point.

[0056] Based on the temperature change of each measurement point and its position weight in the vehicle compartment, the overall temperature loss of the vehicle during the parking period is calculated comprehensively.

[0057] In this embodiment, real-time collection of environmental data, passenger flow data, and temperature loss data provides a multi-dimensional, high-resolution data foundation, providing a reliable basis for subsequent data analysis and intelligent control. Traditional air conditioning control systems often rely solely on a single temperature sensor, failing to fully consider passengers' actual experience. The rich data collected by this module can more comprehensively reflect the comfort conditions within the vehicle cabin. For example, during periods of high passenger flow, human bodies dissipate heat, causing the cabin temperature to rise. Frequent door opening and closing accelerates cold air loss, leading to temperature fluctuations. These factors can affect passenger comfort. By collecting this data, the system can more accurately determine the actual comfort conditions within the cabin and make more precise adjustments accordingly. The real-time data collection feature ensures that the system can promptly respond to changes in the cabin environment, avoiding inaccurate control due to data lag. Through high-precision data collection, this module lays a solid foundation for building accurate predictive models and effective control strategies, ultimately enhancing the passenger experience.

[0058] The data analysis module is used to preprocess environmental data, passenger flow data and temperature loss data to obtain preprocessed data, and to build a prediction model based on multiple linear regression. The preprocessed data is input and the currently most comfortable perceived temperature is output.

[0059] The preprocessing process includes filtering, cleaning, and calibrating environmental data to remove outliers and noise. Passenger flow data is statistically analyzed and categorized into peak and off-peak periods based on time periods and carriage locations. Temperature loss data is also corrected and converted.

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

[0061] Historical environmental data, historical passenger flow data, and historical temperature loss data related to urban rail transit vehicles are collected and preprocessed to obtain historical preprocessed data.

[0062] The historical preprocessed data is randomly divided into training and test sets.

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

[0064] 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 regression coefficient is updated using the gradient descent algorithm.

[0065] The performance of the trained prediction model is evaluated using the test set, and evaluation indicators are calculated, including mean square error, mean absolute error, and coefficient of determination.

[0066] Repeat the training and performance evaluation of the prediction model, retain the prediction model regression coefficient that meets the test accuracy, and obtain the prediction model.

[0067] In this embodiment, the data analysis module extracts key factors influencing passenger comfort from massive amounts of data and uses these factors to predict the current perceived temperature that best enhances passenger comfort. This module first preprocesses the data acquired by the data acquisition module to eliminate noise and outliers, ensuring data quality. Then, based on a multivariate linear regression model, it establishes relationships between environmental data, passenger flow data, temperature loss data, and passenger comfort. The advantages of the multivariate linear regression model lie in its simplicity, ease of understanding, and implementation, enabling rapid creation of a predictive model. By inputting the preprocessed data, the model predicts the perceived temperature that passengers find most comfortable under the current circumstances. The perceived temperature is not a simple fixed value; it dynamically adjusts based on the actual conditions within the vehicle, better meeting the individual needs of passengers. Compared to traditional fixed temperature settings, the perceived temperature targets provided by this module more accurately reflect passengers' actual experiences. For example, when passenger flow is high, the model predicts a relatively low perceived temperature to offset heat dissipated by human bodies and maintain a cool cabin. This personalized comfort target can significantly enhance the passenger experience.

[0068] The control strategy module is used to build a control model based on random forest and use a quantum-inspired optimization algorithm to optimize the hyperparameters of the control model. It inputs preprocessed data and the currently most comfortable perceived temperature, and outputs a real-time air conditioning adjustment strategy.

[0069] The process of building a random forest-based control model includes:

[0070] 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 performing one-hot encoding on categorical features.

[0071] The importance and relevance of each feature in the feature set are evaluated, and key features with significant impact on predicting the real-time adjustment strategy of air conditioning are screened out.

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

[0073] A preset proportion of sample data is randomly extracted from the sample set as training data. For each node in the decision tree, the information gain and Gini index are calculated based on the selected features to determine the optimal splitting features and points. The node data is then divided into subsets, and the partitioning process is repeated to gradually grow the decision tree. When the preset stopping condition is reached, further node splitting stops.

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

[0075] The process of optimizing the hyperparameters of the control model using a quantum-inspired optimization algorithm involves:

[0076] The number of decision trees, the depth of the trees, and the ratio of feature selection are taken as the hyperparameter combinations that need to be optimized.

[0077] An initial set of qubit states is randomly generated, where the qubit states represent initial guesses for the hyperparameters.

[0078] The qubit is measured and a set of classical hyperparameter combinations is obtained as the current solution.

[0079] The measured hyperparameter combination is applied to the control model of the deep forest, and the performance of the model under the hyperparameter combination is evaluated using accuracy and mean square error to obtain the fitness value.

[0080] Based on the fitness value, the probability amplitude of the qubit is adjusted using the update rule of the quantum-inspired optimization algorithm.

[0081] 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.

[0082] In this embodiment, the control strategy module intelligently generates real-time adjustment strategies for the air conditioning system based on the comfort targets provided by the data analysis module, achieving precise control of cabin temperature, humidity, and wind speed. This module uses the random forest algorithm to construct the control model. Compared to traditional linear models, random forests are better able to handle nonlinear relationships and adapt to complex cabin environments. The advantages of the random forest algorithm lie in its strong generalization and robustness, effectively adapting to various changes in the cabin environment. To further improve the performance of the control model, the module also uses a quantum-inspired optimization algorithm to optimize the hyperparameters of the random forest algorithm. Quantum-inspired optimization algorithms offer strong global search capabilities and fast convergence, enabling rapid identification of optimal hyperparameter combinations and improving the accuracy of the control model. By inputting preprocessed data and the current most comfortable perceived temperature, the module outputs a real-time adjustment strategy for the air conditioning system, including temperature, humidity, and wind speed control plans. This strategy, based on big data analysis and intelligent optimization algorithms, more accurately assesses cabin comfort conditions and enables 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 a command generation unit, a command transmission unit, and an execution control unit. The command generation unit is responsible for formulating real-time control commands related to temperature, humidity, and air speed adjustment based on the real-time adjustment strategy. Real-time control commands include control parameters and command formats. The command transmission unit ensures the timeliness and accuracy of real-time control commands during transmission. The execution control unit is responsible for controlling the relevant equipment in the air conditioning system according to the real-time control commands.

[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 from multiple dimensions, including target temperature, target humidity, wind speed level, fresh air ratio, and compressor speed adjustment range. The specific meaning and value range of each parameter in the real-time adjustment strategy must be clarified. After the strategy is parsed, the information in the strategy needs to be mapped into specific air conditioning control parameters. For example, the target temperature can be mapped to the chiller's outlet water temperature setpoint, and the wind speed level can be mapped to the blower's speed setpoint. This mapping process requires a thorough understanding of the air conditioning system's control characteristics and parameter ranges to ensure that the generated control parameters are within the system's safe operating range. To enable the air conditioning system to correctly identify and execute control commands, the instruction generation unit must encapsulate the control parameters according to a predefined instruction format. The instruction format may include: a start bit, a device address, a control parameter type, a control parameter value, a check bit, an end bit, etc. Different air conditioning systems may use different instruction formats, and the instruction generation unit must 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 and extract the control parameters and control instruction type. The execution control unit needs to have the ability to drive various devices in the air-conditioning system. These devices may include: Chiller: used to provide a cold source and control its outlet water temperature and flow. Blower: used to deliver cold or hot air into the car, controlling its speed and air volume. Return air valve: used to adjust the return air volume and control the air circulation in the car. Fresh air valve: used to adjust the fresh air volume and improve the air quality in the car. Humidifier / dehumidifier: used to adjust the humidity in the car.

[0087] To ensure control accuracy and stability, the control unit typically employs closed-loop control. For example, a temperature sensor can monitor the cabin temperature in real time, compare the actual temperature with the target temperature, and adjust the chiller's outlet water temperature based on the deviation, thereby achieving precise control of the cabin temperature.

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

[0089] The feedback evaluation module includes a temperature monitoring unit, a strategy effectiveness evaluation unit, and a data feedback unit. The temperature monitoring unit is used to measure the temperature inside urban rail transit vehicles in real time using sensors. The strategy effectiveness evaluation unit is used to evaluate and analyze the actual effectiveness of real-time adjustment strategies. When the actual effectiveness falls below a preset threshold, the data feedback unit is used to provide feedback to the control strategy module 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 a sensor network. Multiple high-precision temperature sensors are strategically placed throughout the vehicle cabin, covering different areas, including near the doors, the center of the cabin, the ends, and near the vents. This multi-point deployment provides a more comprehensive picture of the temperature distribution within the cabin, avoiding deviations caused by limited sensor placement. Furthermore, to ensure data accuracy and reliability, the temperature monitoring unit utilizes high-precision, fast-response temperature sensors.

[0091] The strategy effectiveness 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 temperature distribution and the rate of temperature change. The strategy effectiveness evaluation unit calculates comfort indicators based on the temperature data, including: average radiant temperature, predicted average evaluation, predicted dissatisfaction rate, and temperature uniformity index. The average radiant temperature takes into account the radiation heat exchange between the human body and the surrounding environment and better reflects the human body's true feelings. The predicted average evaluation is a comfort index that comprehensively considers temperature, humidity, wind speed, activity intensity, and clothing warmth. The predicted dissatisfaction rate predicts the proportion of people who are dissatisfied with the environment. The temperature uniformity index evaluates the uniformity of temperature distribution in the vehicle cabin.

[0092] The strategy effectiveness evaluation unit requires a pre-defined set of evaluation criteria to determine whether the air conditioning system's actual performance meets expectations. These criteria can be adjusted to suit different operational needs. For example, during peak hours, comfort requirements can be appropriately lowered to ensure stable system operation; during off-peak hours, comfort requirements can be increased to provide a better passenger experience.

[0093] The data feedback unit pre-sets an effect threshold to determine whether the actual effect of the air-conditioning system needs to be improved. The effect threshold can be set according to different comfort indicators. When the strategy 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 the problems existing in the system in detail, such as excessive temperature, uneven temperature distribution, etc. Data support is used to provide data to support the problem description, such as real-time temperature data, comfort indicators, etc. Improvement suggestions are used to make improvement suggestions for the problem, such as adjusting the cooling capacity, adjusting the ventilation strategy, etc. These suggestions can be based on preset rules or automatically generated by machine learning algorithms.

[0094] In summary, this embodiment provides an urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis. By real-time collection of environmental data, passenger flow data and temperature loss data, and combined with a prediction model based on multiple linear regression, it can accurately predict the current most comfortable perceived temperature. The air-conditioning system can dynamically adjust the temperature, humidity and wind speed according to the actual situation in the car to provide passengers with a personalized comfort experience. By constructing a control model based on random forests and using a quantum-inspired optimization algorithm to optimize the model hyperparameters, it is possible to achieve precise control of the air-conditioning system, effectively reduce temperature fluctuations, maintain the stability of the temperature in the car, thereby improving passenger comfort, and dynamically adjust the cooling and ventilation capacity according to actual needs to avoid unnecessary energy consumption. Traditional air-conditioning systems often over-cool or over-heat, resulting in energy waste. This embodiment collects data in real time and uses a prediction model to determine the optimal perceived temperature, which can avoid over-cooling or heating and achieve energy saving and consumption reduction.

[0095] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[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, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain 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, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis, characterized in that: include: Data acquisition module, used to collect real-time environmental data, passenger flow data and temperature loss data related to urban rail transit vehicles; A data analysis module is used to pre-process the environmental data, passenger flow data, and temperature loss data to obtain pre-processed data, and to construct a prediction model based on multiple linear regression, input the pre-processed data, and output the currently most comfortable body temperature; A control strategy module is used to construct a control model based on random forests, optimize the hyperparameters of the control model using a quantum-inspired optimization algorithm, input the preprocessed data and the currently most comfortable perceived temperature, and output a real-time air conditioning adjustment strategy; A control execution module, configured 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 adjust the temperature, humidity and wind speed; A feedback evaluation module, configured to monitor the temperature in the vehicle compartment in real time and evaluate the effectiveness of the real-time adjustment strategy; The environmental data includes temperature data, humidity data, and wind speed inside and outside the urban rail transit vehicle compartment; the passenger flow data includes the real-time number of passengers and real-time location distribution inside the urban rail transit vehicle compartment; the temperature loss data represents the temperature loss inside the vehicle when the urban rail transit vehicle stops on a single route; The calculation process of the vehicle internal temperature loss includes: Get the time when the vehicle starts to stop and the time when it ends to restart; Installing multiple high-precision temperature sensors inside the carriage, with the position of each high-precision temperature sensor serving as a test point; When the vehicle stops, the initial temperature value of each measuring point in the vehicle compartment is recorded by the sensor; When the vehicle is restarted after stopping, the temperature value of each point in the car is measured again, and the initial temperature value is subtracted from the final temperature value to obtain the temperature change of each measuring point; Based on the temperature change of each measurement point and its position weight in the vehicle compartment, the overall temperature loss of the vehicle during the parking period is calculated comprehensively.

2. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 1 is characterized in that: The preprocessing process includes: screening, cleaning and calibrating the environmental data to remove outliers and noise; counting and classifying the passenger flow data to divide the passenger flow into peak period and off-peak period according to different time periods and carriage positions; and correcting and converting the temperature loss data.

3. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 1 is characterized in that: The process of building a prediction model based on multiple linear regression includes: Collect historical environmental data, historical passenger flow data, and historical temperature loss data related to urban rail transit vehicles, and pre-process them to obtain historical pre-processed data; Randomly dividing the historical preprocessed data into a training set and a test set; Initialize the regression coefficients of the prediction model based on multiple linear regression; Using the training set to train the prediction model, optimizing the regression coefficient of the prediction model by minimizing the mean square error, and updating the regression coefficient using a gradient descent algorithm; Using the test set to evaluate the performance of the trained prediction model, and calculating evaluation indicators, the evaluation indicators include mean square error, mean absolute error and determination coefficient; The prediction model is repeatedly trained and evaluated for performance, and the prediction model regression coefficients that meet the test accuracy are retained to obtain a prediction model.

4. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 1 is characterized in that: The process of building a random forest-based control model includes: Collect preprocessed data and the corresponding currently most comfortable perceived temperature to establish a sample set, perform feature extraction and conversion on the data in the sample set to establish a feature set, wherein the feature extraction and conversion includes: 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; Setting the number of decision trees in the random forest, randomly extracting features from the feature set, and constructing each decision tree; setting initial parameters for each decision tree, including the maximum depth and the 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 optimal 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 a preset stopping condition is reached, further splitting of the node is stopped to obtain a control model based on random forest.

5. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 1 is 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 trees, 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; adjusting the probability amplitude of the qubit using an update rule of a quantum-inspired optimization algorithm according to the fitness value; 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.

6. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 1 is 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.

7. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 1 is 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 inside the urban rail transit vehicle compartment in real time based on the sensor equipment; the strategy effect evaluation unit is used to evaluate and analyze the actual effect of the real-time adjustment strategy.

8. The urban rail transit vehicle air conditioning adjustment system based on comfort big data analysis according to claim 7 is characterized in that: The feedback evaluation module further includes a data feedback unit; the data feedback unit is configured to feed back evaluation information to the control strategy module when the actual effect is lower than a preset effect threshold, so as to optimize and improve the control model and adjustment strategy.

Images