Air conditioner control method and system for optimizing thermal comfort of subway carriage

Abstract

The invention discloses an air conditioner control method and system for optimizing the thermal comfort of a subway carriage, and relates to the technical field of fluid simulation, and the method comprises the following steps: utilizing a subway carriage model established by AnsysFluent to carry out numerical simulation on an unoptimized subway carriage, and then carrying out error analysis with actual data so as to establish a more accurate carriage model. The method comprises the following steps: performing numerical simulation on subway carriage thermal environments under different stand mat densities, optimizing air supply parameters based on evaluation indexes such as related standard specifications and PMV, and classifying the stand mat densities according to an optimization result. The interval where the density of the standing seats in the carriages is located at the starting moment of each train is calculated in real time through a detection algorithm of the density of the standing seats in the carriages based on a space attention module of a self-adaptive receptor, and fuzzy PID control is adopted to replace a traditional switch to control a carriage air conditioning system. And adjusting the temperature in the carriage by linking the calculated standing position density category interval with a fuzzy PID controller.

Description

Technical Field

[0001] The present invention relates to the technical field of fluid simulation, and in particular to an air conditioning control method and system for optimizing thermal comfort in a subway car. Background Art

[0002] In the past three decades, my country's economic strength has been rapidly improved. Due to its safety and punctuality, the subway has become an important means of transportation for people to travel. The thermal comfort in the subway car is closely related to the air flow organization and standing density in the air-conditioned area of ​​the car. However, the setting of air-conditioning parameters in the current subway design specifications in my country is mainly for tunnels and station halls, and there is a lack of a clear design standard for subway car air-conditioning systems that can meet the thermal comfort requirements of passengers. At present, the setting of air-conditioning in the car mainly refers to the setting method of air-conditioning parameters of railway trains or is set separately according to experience in different regions. In view of the great difference between the environment of subway cars and long-distance trains, most of them are underground, except for ground lines and elevated lines. The environment in the car is relatively less affected by solar radiation and outdoor environment, but relatively more affected by tunnel temperature and standing density. The passenger ride time is relatively short, the passenger flow varies greatly, and the distance between stations is short. With the frequent opening and closing of the doors, the cold and heat inside and outside the car are constantly exchanged. The design standards for long-distance railway passenger cars may not be applicable to subway cars. At the same time, the frequently changing thermal environment in the carriage in a short period of time requires an air conditioning control system that can respond quickly. The combination of PID control and fuzzy control can well meet the above control requirements. Therefore, it is necessary to use fluid simulation to analyze the thermal environment of the subway carriage, and based on the regulatory requirements and passenger thermal comfort, the fuzzy PID controller can quickly and stably optimize the thermal environment of the carriage.

[0003] Therefore, the present invention provides an air conditioning control strategy for optimizing the thermal comfort of subway carriages, thereby achieving energy-saving and efficient optimization of the thermal environment of the carriages. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing traditional standing density monitoring method has poor adaptability, low data accuracy, and the problem of how to adapt to continuous door opening and closing to achieve real-time adjustment.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an air conditioning control method for optimizing the thermal comfort of a subway car, comprising using simulation analysis software to establish a subway car model with different standing seat densities. The established car model is meshed and converged. The thermal environment simulation parameters of the subway car under different standing seat densities are simulated under preset boundary conditions. The actual thermal environment parameters of the subway car when the standing seat density is 0 are measured, and the parameters are preprocessed. The error value between the simulation parameter and the actual parameter when the standing seat density is 0 is calculated. The error value is compared with the threshold error range. The thermal environment of the car under each standing seat density is analyzed to obtain an optimized car thermal environment. According to the optimization results, a detection algorithm based on a spatial attention module of an adaptive receptive field is used to dynamically classify the standing seat density in the subway car, and the interval of the standing seat density in the car at the start time of each station is calculated in real time. The standing seat density category interval obtained by linkage calculation is used to control the car air conditioning system by fuzzy PID, and the air conditioning system adjusts the temperature in the car through the actuator to perform corresponding actions to optimize the thermal comfort of the subway car.

[0007] As a preferred solution of the air conditioning control method for optimizing the thermal comfort of subway cars described in the present invention, wherein: the use of simulation analysis software to establish subway car models with different standing seat densities includes modeling according to the actual length, width and height of the car, the size and distribution of the doors and windows, and the shape of the vehicle, taking a 1 / 2 symmetrical structure for grid division and numerical simulation, and establishing the standing seat density according to the standing-to-sitting ratio People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 There are seven carriage models in total.

[0008] Among them, the standing density refers to the average number of standing passengers in the subway car, which is the area of ​​the ground minus the area occupied by the infrastructure. It is used to characterize the degree of crowding of people and cars under the standing density, and is expressed as:

[0009]

[0010] Where C is the density of standing seats for passengers in the subway car, which is a positive integer. N is the number of standing passengers in the subway car. X is the floor area of ​​the subway car minus the area occupied by infrastructure.

[0011] As a preferred solution of the air conditioning control method for optimizing thermal comfort of subway cars according to the present invention, the thermal environment simulation parameters of the subway car under different seat densities are simulated under preset boundary conditions, including adopting the RNG k-ε model and component transport in the turbulence model, and using the standard wall function for calculation, and the turbulent kinetic energy and dissipation rate of the RNG k-ε turbulence model are expressed as:

[0012]

[0013] Among them, μ eff is the effective viscosity coefficient, G k is the term for the turbulent kinetic energy generated by the mean velocity gradient, is the air density, α k , α ε is the reciprocal of the effective Prandtl number of k and ε, C 1ε , C 2ε is an empirical constant, C 1ε =1.42, C 2ε =1.68.

[0014] The RNG k-ε turbulence model is selected together with the law of conservation of mass, law of conservation of momentum and law of conservation of energy to form the control model. The tensor form is:

[0015] Continuity equation:

[0016]

[0017] Momentum is expressed as:

[0018]

[0019] Energy is expressed as:

[0020]

[0021] The component transport is expressed as:

[0022]

[0023] Among them, u i Represents the velocity component, where i = 1, 2, 3, representing the x, y, and z directions respectively. i 、x j represents the spatial position coordinates, P represents pressure, T represents fluid temperature, g represents gravitational acceleration, C p represents the specific heat at constant pressure, ρ represents the fluid density, C represents the local concentration of the fluid, Re represents the Reynolds number, Sc represents the Schmidt number, Q represents the incidence rate of the defined pollutant source term, and L 0 represents the characteristic length, C 0 Indicates a very positive concentration.

[0024] As a preferred scheme of the air conditioning control method for optimizing thermal comfort of subway cars described in the present invention, the thermal environment simulation parameters include supply air speed, return air speed, return air temperature, average car temperature, average car wind speed, and car temperature and car wind speed at different heights.

[0025] As a preferred solution of the air conditioning control method for optimizing thermal comfort of subway cars described in the present invention, the comparison of the error value with the threshold error range includes re-gridding and convergence processing the established car model when the error value exceeds the threshold error range.

[0026] When the error value does not exceed the threshold error range, the thermal environment of the carriage under various seat densities is analyzed to obtain the optimized thermal environment of the carriage.

[0027] As a preferred solution of the air conditioning control method for optimizing thermal comfort of subway cars described in the present invention, the detection algorithm based on the spatial attention module of the adaptive receptive field for dynamically classifying the standing seat density in the subway car includes using the SKSAM-ResNet algorithm to detect the standing seat density in the subway car in real time, and embedding the series combination of the adaptive receptive field attention module in front and the spatial attention module in the back into the backbone network ResNet-50 model. The adaptive receptive field module and the spatial attention module replace the 3×3 convolution kernel in ResNet-50. At the start time of the train at each station, the standing seat density in the car is calculated in real time, and the air supply parameters are dynamically adjusted to ensure that the thermal environment in the car is always in the best state.

[0028] As a preferred solution of the air conditioning control method for optimizing the thermal comfort of subway cars described in the present invention, the fuzzy PID control car air conditioning system is used, and the air conditioning system adjusts the temperature in the car through the actuator to perform corresponding actions, including monitoring the interval in which the standing density at the time of vehicle start-up is located, and taking the optimized average temperature in the car after simulation under the interval as the set value, comparing the air temperature in the car measured by the sensor with the set value, and obtaining the temperature deviation e and the deviation change rate ec of the air in the car as the input variables of the controller, and then obtaining the output through the fuzzification, reasoning and defuzzification process. The controller gives different PID parameters in real time according to different situations and expert experience, so as to meet the control requirements of the train car under different car thermal environments, optimize the system temperature control, and make the car thermal environment comfortable.

[0029] Another object of the present invention is to provide an air-conditioning control system for optimizing thermal comfort in subway cars. The detection algorithm of standing density in subway cars through a spatial attention module based on an adaptive receptive field is highly flexible and can adapt to changes in passenger distribution in real time, thereby solving the problem that the current traditional standing density monitoring technology requires a lot of time to design filters that can extract features that meet specific scene characteristics, and cannot be flexibly adjusted and is difficult to adapt to passenger distribution.

[0030] As a preferred solution of the air-conditioning control system for optimizing thermal comfort of subway cars described in the present invention, it includes: a first processing module, a first acquisition module, a second processing module, a second acquisition module, a third processing module, a third acquisition module, and a fourth processing module.

[0031] The first processing module is used to use simulation analysis software to establish a car model of a subway car with different standing density, divide the model into grids and perform algorithm convergence processing, and simulate the thermal environment simulation parameters of the subway car under preset boundary conditions using the obtained car model.

[0032] The first acquisition module is used to measure the actual parameters of the thermal environment of the subway car when the standing density is 0.

[0033] The second processing module is used to perform parameter preprocessing to eliminate measurement errors, calculate the error value between the simulated parameters and the actual parameters of the subway car when the standing density is 0, and when the error value exceeds the threshold error, send an instruction to the first processing module. When the error value does not exceed the threshold error, analyze the thermal environment of the car under each standing seat density to obtain the optimized car thermal environment, and classify the standing seat density according to the optimization result.

[0034] The second acquisition module is used to monitor the passenger distribution in the car in real time through a distributed sensor network and dynamically adjust the monitoring range according to the actual passenger distribution based on the detection algorithm of the standing seat density in the subway car of the spatial attention module of adaptive perception, and calculate the standing seat density in the car at the start time of each station in real time.

[0035] The third processing module is used to identify the category interval of the standing seat density and the optimized average temperature in the rear compartment obtained by simulation in the interval according to the obtained standing seat density.

[0036] The third acquisition module is used to measure the air temperature in the carriage at the time of train start through a sensor.

[0037] The fourth processing module is used to link the calculated standing density category interval with the fuzzy PID controller, and use the optimized average temperature in the car after simulation under this interval as the set value. The air temperature in the car measured by the sensor is compared with the set value to obtain the temperature deviation e and the deviation change rate ec of the air in the car. The output obtained by the input controller after calculation acts on the train air-conditioning system. The air-conditioning system performs corresponding actions through the actuator to adjust the temperature in the car and optimize the thermal comfort of the subway car.

[0038] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of an air conditioning control method for optimizing thermal comfort in a subway car.

[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an air-conditioning control method for optimizing thermal comfort in a subway car.

[0040] Beneficial effects of the present invention: The present invention provides an air conditioning control strategy for optimizing the thermal comfort of subway cars. The subway car is taken as the research object, and Ansys Fluent is used to establish a subway car model under different standing seat densities. The subway car under different standing seat densities that have not been optimized is numerically simulated, and then the error analysis is performed with the actual thermal environment parameters, so as to establish a more accurate and more precise model. The detection algorithm of the standing seat density in the subway car based on the spatial attention module of the adaptive sensor is used to calculate the interval of the standing seat density in the car at the start time of each station in real time, and the fuzzy PID controller is linked to adjust the temperature in the car, so as to obtain a more comfortable and energy-saving car thermal environment. The Ansys Fluent software analysis system has the advantages of advanced numerical calculation methods, high calculation accuracy, good convergence and not prone to errors, which can help us perform calculations and analysis more quickly and accurately with the least workload. Using Ansys Fluent software to perform numerical simulation of the flow field in the car can obtain more accurate numerical results. The optimization scheme of the thermal environment of the carriage under different standing seat densities is based on comprehensive considerations such as relevant design specifications, PMV indicators that comprehensively reflect human thermal comfort, and air distribution characteristics. Compared with the traditional single temperature indicator as the control basis for subway carriage air conditioning, it can better meet the thermal comfort of passengers. Since the local features between different standing seat densities are similar, and the network is greatly affected by local features when detecting the standing seat density interval, based on the distribution characteristics of passengers under different standing seat densities, the spatial attention module that can suppress features unrelated to the standing seat density and the attention module with adaptive receptive field that can reduce the interference of local features on the judgment of standing seat density in the carriage are connected in series and embedded in the RseNet network, which can more accurately calculate the standing seat density in the carriage. The detection algorithm of the standing seat density in the subway carriage based on the spatial attention module with adaptive receptive field is highly flexible and can adapt to changes in passenger distribution in real time. At the same time, the distributed sensor network has a wide coverage, which can effectively reduce blind spots, dynamically adjust the classification standards according to actual conditions, and improve data accuracy. However, the traditional standing seat density monitoring method has fixed sensor positions, cannot be flexibly adjusted, has poor adaptability, may have monitoring blind spots, is difficult to adjust in real time, and has low data accuracy. Fuzzy PID control can meet the requirements of real-time adjustment of controller parameters, and can well adapt to the complex and changeable characteristics of the thermal environment of subway cars, realize stable control of the car air conditioning system, and reduce unnecessary energy consumption. The present invention has achieved better results in flexibility, control stability and energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0042] Figure 1 An overall flow chart of an air conditioning control method for optimizing thermal comfort in a subway car provided in the first embodiment of the present invention.

[0043] Figure 2 A schematic diagram of a module of an air conditioning control system for optimizing thermal comfort in a subway car provided in a third embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0045] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides an air conditioning control method for optimizing thermal comfort in a subway car, comprising:

[0046] S1: Use simulation analysis software to build subway car models with different standing seat densities.

[0047] Furthermore, simulation analysis software is used to establish subway car models with different standing density, including modeling based on the actual length, width and height of the car, the size and distribution of doors and windows, and the shape of the vehicle, taking the 1 / 2 symmetrical structure for meshing and numerical simulation, and establishing the standing density according to the standing-to-sitting ratio. People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 There are seven carriage models in total.

[0048] Among them, the standing density refers to the average number of standing passengers in the subway car, which is the area of ​​the ground minus the area occupied by the infrastructure. It is used to characterize the degree of crowding of people and cars under the standing density, and is expressed as:

[0049]

[0050] Where C is the density of standing seats for passengers in the subway car, which is a positive integer. N is the number of standing passengers in the subway car. X is the floor area of ​​the subway car minus the area occupied by infrastructure.

[0051] S2: Mesh division and convergence processing are performed on the established carriage model.

[0052] Furthermore, the unstructured grid is used to divide the model into different grid accuracies at different locations of the car model, and the grids of the air supply and return vents on the top of the car and the air outlets on the side of the car are encrypted.

[0053] S3: Simulate the thermal environment parameters of the subway car with different standing density under the preset boundary conditions.

[0054] Furthermore, the thermal environment simulation parameters of the subway car with different seat densities are simulated under the preset boundary conditions, including the RNG k-ε model and component transport in the turbulence model, and the standard wall function is used for calculation. The turbulent kinetic energy and dissipation rate of the RNG k-ε turbulence model are expressed as:

[0055]

[0056] Among them, μ eff is the effective viscosity coefficient, G k is the term for the turbulent kinetic energy generated by the mean velocity gradient, is the air density, α k , α ε is the reciprocal of the effective Prandtl number of k and ε, C 1ε , C 2ε is an empirical constant, C 1ε =1.42, C 2ε =1.68. In the simulation of the thermal environment in the car, the movement of the fluid must comply with the basic conservation laws including the law of conservation of mass, the law of conservation of momentum and the law of conservation of energy. The turbulent flow state of the air supply and return process must comply with the turbulent transport equation. At the same time, the flow involves the mixing or interaction of different components, and the system must also comply with the component conservation law.

[0057] The RNG k-ε turbulence model is selected together with the law of conservation of mass, law of conservation of momentum and law of conservation of energy to form the control model. The tensor form is:

[0058] Continuity equation:

[0059]

[0060] Momentum is expressed as:

[0061]

[0062] Energy is expressed as:

[0063]

[0064] The component transport is expressed as:

[0065]

[0066] Among them, u i Represents the velocity component, where i = 1, 2, 3, representing the x, y, and z directions respectively. i 、x j represents the spatial position coordinates, P represents pressure, T represents fluid temperature, g represents gravitational acceleration, C p represents the specific heat at constant pressure, ρ represents the fluid density, C represents the local concentration of the fluid, Re represents the Reynolds number, Sc represents the Schmidt number, Q represents the incidence rate of the defined pollutant source term, and L 0 represents the characteristic length, C 0 Indicates a very positive concentration.

[0067] It should be noted that the boundary conditions include the velocity inlet boundary for the air supply port and the pressure outlet boundary for the air exhaust port.

[0068] S4: Measure the actual parameters of the thermal environment of the subway car when the standing density is 0, and perform parameter preprocessing.

[0069] Furthermore, TES1365 and testo410-1 were used to measure the actual temperature data at four sections of 0.1m, 0.5m, 1.2m, and 1.7m in height and at the air outlet of the subway car of Shanghai Metro Line 5.

[0070] S5: Calculate the error value between the simulation parameter and the actual parameter when the standing density is 0.

[0071] Furthermore, the measured data were compared with the simulated calculated values ​​when the standing density was 0 people / m2, the supply air temperature was 20°C, and the supply air speed was 1m / s. The errors were all less than 2%.

[0072] S6: Compare the error value with the threshold error range.

[0073] Furthermore, comparing the error value with the threshold error range includes re-gridding and re-converging the established vehicle compartment model when the error value exceeds the threshold error range.

[0074] When the error value does not exceed the threshold error range, the thermal environment of the carriage under various seat densities is analyzed to obtain the optimized thermal environment of the carriage.

[0075] S7: Analyze the thermal environment of the carriage at various seat densities to obtain an optimized thermal environment of the carriage.

[0076] Furthermore, according to the analysis results, the thermal environment parameters obtained based on the simulation are compared with the existing relevant standards and design specifications. At the same time, targeted adjustments are made to the parts that do not meet the thermal comfort requirements in the comprehensive thermal comfort evaluation and the air distribution characteristic indicators, so as to optimize the air distribution system and obtain an optimized cabin thermal environment.

[0077] S8: According to the optimization results, a detection algorithm based on the spatial attention module of adaptive receptive field is used to dynamically classify the standing seat density in the subway car, and the interval of the standing seat density in the car at the start time of each station is calculated in real time.

[0078] Furthermore, a detection algorithm based on the spatial attention module of adaptive receptive field is used to dynamically classify the standing seat density in the subway car, including using the SKSAM-ResNet algorithm to detect the standing seat density in the subway car in real time, and embedding the series combination of the adaptive receptive field attention module in front and the spatial attention module in the back into the backbone network ResNet-50 model. The adaptive receptive field module and the spatial attention module replace the 3×3 convolution kernel in ResNet-50. At the start of the train at each station, the standing seat density in the car is calculated in real time, and the air supply parameters are dynamically adjusted to ensure that the thermal environment in the car is always in the best state.

[0079] S9: The standing seat density category interval obtained by linkage calculation adopts fuzzy PID to control the car air conditioning system. The air conditioning system adjusts the temperature in the car through the actuator to perform corresponding actions and optimize the thermal comfort of the subway car.

[0080] Furthermore, a fuzzy PID control system is used to control the air conditioning system in the carriage. The air conditioning system adjusts the temperature in the carriage through the actuator to perform corresponding actions, including monitoring the interval of standing density at the time of vehicle start-up, and taking the optimized average temperature in the carriage after simulation in the interval as the set value. The air temperature in the carriage measured by the sensor is compared with the set value to obtain the temperature deviation e and the deviation change rate ec of the air in the carriage as the input variables of the controller, and then the output is obtained through the fuzzification, reasoning and defuzzification process. The controller gives different PID parameters in real time according to different situations and expert experience to meet the control needs of the train carriage in different thermal environments, so as to optimize the system temperature control and keep the thermal environment in the carriage comfortable.

[0081] Example 2, an embodiment of the present invention, provides an air conditioning control method for optimizing thermal comfort in subway cars. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0082] First, taking the example of the density of standing seats in the carriage of the present invention being 0, 1, and 2 as an example, typical cross-sections and typical fluid state points near the human body are selected for thermal comfort analysis, wherein the fluid state points avoid points on the human body. The specific selection method is as follows: four cross-sections in the X-axis direction are selected: X = 2.122m, 4.510m, 6.593m, and 8.431m, and monitoring points are selected in each cross-section respectively. The heights from the floor of the car are selected along the height direction of the car (Y axis) at 0.1m, 0.5m, 1.2m, and 1.7m, which correspond to the positions of the passengers' feet, knees, heads when sitting and standing, etc., and points near the sitting and standing passengers are selected along the width direction of the car (Z axis): z = -0.815m, -1.785m, and a total of 32 monitoring points are selected for thermal comfort point evaluation. The evaluation is based on the allowable air velocity range in the human comfort zone clearly stated in the American industry standard ASHRAE 55-2010: For operating temperatures greater than or equal to 25.5°C, the upper limit of the air velocity is 0.8m / s. For operating temperatures less than or equal to 22.5°C, the upper limit of the air velocity is 0.15m / s to avoid the discomfort of cold wind. For operating temperatures above 22.5 and below 25.5, the upper limit of the air velocity V and the air temperature ta should satisfy the following formula:

[0083] V=50.49-4.4047ta+0.096425ta 2

[0084] The FLUENT software was used to solve the calculation, read the temperature and velocity values ​​of 32 points, and counted the number of monitoring points that met thermal comfort under each condition. Table 1 counts the number of monitoring points that met thermal comfort under two air supply conditions: standing density of 0, 1, 2, air supply temperature of 22℃, air supply velocity of 1.5m / s, and air supply temperature of 20℃, air supply velocity of 1.0m / s.

[0085] Table 1 Number of monitoring points that meet thermal comfort requirements when the air supply temperature is 22°C and the air supply speed is 1.5m / s

[0086] Standing density (person / m2) 0 1 2 Number of points that meet thermal comfort requirements 25 23 17

[0087] Table 2 Number of monitoring points that meet thermal comfort requirements when the air supply temperature is 20℃ and the air supply speed is 1.0m / s

[0088] Standing density (person / m2) 0 1 2 Number of points that meet thermal comfort requirements 16 19 24

[0089] From the data in Table 2, it can be seen that when the standing density is 0 and 1, the monitoring points that meet the thermal comfort condition are the air supply temperature of 22℃ and the air supply speed of 1.5m / s. When the standing density is 2, the monitoring points that meet the thermal comfort condition are the air supply temperature of 22℃ and the air supply speed of 1.5m / s. At the same time, comparing the two air supply conditions, when the standing density is 0 and 1, the air supply temperature of 22℃ is both energy-saving and comfortable. When the standing density is 2, the air supply condition is adjusted from the air supply temperature of 22℃ and the air supply speed of 1.5m / s to the air supply temperature of 22℃ and the air supply speed of 1.5m / s, and the number of thermal comfort points increases from 53.13% to 75%. It can be seen that real-time adjustment of the air supply state with the change of the standing density in the car is very important for thermal comfort and reducing energy consumption in the car.

[0090] Ansys Fluent is used to simulate and analyze the velocity field and temperature field of the car model, and the car model under different seat density is optimized according to the analysis results. By simulating the thermal environment of the car when the seat density is 0, and performing error analysis with the actual thermal environment parameters of the car when the seat density is 0, the data is reprocessed to reduce the error between the simulation and the actual measurement. A relative error threshold is set according to the data reprocessing results. When the error analysis result exceeds the threshold, it is identified as an abnormal value and the model needs to be reprocessed, and finally the data with higher accuracy is obtained.

[0091] In this embodiment, the measured data are compared with the simulated calculated values ​​when the standing density is 0 persons / m2, the air supply temperature is 20°C, and the air supply speed is 1m / s. The errors are all less than 2%.

[0092] In this embodiment, three operating modes of temperature 18°C, 20°C, and 22°C and three wind speeds 1m / s, 1.5m / s, and 2m / s were used in the simulation with a standing density of 0, and the air supply parameters were optimized according to the simulation results, wherein the optimization was based on the analysis of the thermal environment parameters, thermal comfort analysis, and air distribution characteristic index analysis in the cabin. The thermal environment simulation parameters include: air supply speed, return air speed, return air temperature, average cabin temperature, average cabin wind speed, cabin temperature at different heights, and cabin wind speed.

[0093] In order to verify the effectiveness of the proposed SKSAM-ResNet network, this patent will use the seat density classification dataset collected by vehicle monitoring data to compare the traditional methods based on basic convolutional neural networks: GoogleNet, DenseNet, and the methods based on attention mechanisms: SKNet, CBAM-ResNet, SENet. The above models are all trained and tested in a unified experimental environment, sharing the same hyperparameters, such as: learning rate (Learning Rate), batch size (BatchSize), number of iterations (epoch), etc., and using the same loss function and weight update method. The experimental parameter settings are: the number of iterations is 10, the batch size (Batch Size) is 32, the initial learning rate is 0.001, and the exponential decay method (Exponential Decay) is used to gradually reduce the learning rate. The optimizer uses Adam, and the pre-trained weights are used to initialize the model. The confusion matrix of each network on the test set is calculated, and the recall rate and precision rate of each network on each category, as well as the average recall rate and average precision rate are calculated according to the confusion matrix, as shown in Table 1 and Table 2. The recall rate evaluates the completeness performance of the classification network, and the precision rate evaluates the precision performance of the classification network.

[0094] Table 3 Recall rate and average recall rate of the algorithm in each category

[0095]

[0096] Table 4 The accuracy and average accuracy of the algorithm in each category

[0097]

[0098] It can be seen from the experimental data table that the classification effect of the method based on the attention mechanism on the four categories is better than that of the basic convolutional network model, which shows that adding the attention mechanism is effective for the classification problem of standing density in the carriage. Among the algorithms based on the attention mechanism, the performance of the CBAM-ResNet algorithm that combines the attention mechanism of the channel domain and the spatial domain is better than SENet, indicating that it is necessary to add a spatial attention module to the network for the problem of standing density classification in the carriage. The performance of SKNet is better than that of CBAM-ResNet, indicating that attention based on the receptive field is more effective than channel attention and spatial attention for this type of problem. The proposed standing density detection algorithm (SKSAM-ResNet) based on the spatial attention module of the adaptive receptive field has the best performance in both recall rate and precision, which shows the effectiveness and accuracy of the proposed algorithm in solving the problem of standing density classification in the carriage.

[0099] Example 3, reference Figure 2 , as an embodiment of the present invention, provides an air-conditioning control system for optimizing thermal comfort in subway cars, including a first processing module, a first acquisition module, a second processing module, a second acquisition module, a third processing module, a third acquisition module, and a fourth processing module.

[0100] Among them, the first processing module is used to use simulation analysis software to establish a car model of a subway car under different standing seat densities, divide the model into grids and perform algorithm convergence processing, and simulate the thermal environment simulation parameters of the subway car under preset boundary conditions. The first acquisition module is used to measure the actual thermal environment parameters of the subway car when the standing seat density is 0. The second processing module is used to perform parameter preprocessing to eliminate measurement errors, calculate the error value between the simulation parameters and the actual parameters of the subway car when the standing seat density is 0, and when the error value exceeds the threshold error, send an instruction to the first processing module. When the error value does not exceed the threshold error, analyze the thermal environment of the car under each standing seat density to obtain the optimized car thermal environment, and classify the standing seat density according to the optimization result. The second acquisition module is used to monitor the passenger distribution in the car in real time through a distributed sensor network and dynamically adjust the monitoring range according to the actual passenger distribution based on the detection algorithm of the standing seat density in the subway car of the spatial attention module of adaptive perception, and calculate the standing seat density in the car at the start time of each station in real time. The third processing module is used to identify the category interval of the standing density and the average temperature in the car after optimization simulated in this interval according to the obtained standing density. The third acquisition module is used to measure the air temperature in the car at the time of train start through the sensor. The fourth processing module is used to link the calculated standing density category interval with the fuzzy PID controller, and use the average temperature in the car after optimization simulated in this interval as the set value. The air temperature in the car measured by the sensor is compared with the set value to obtain the temperature deviation e of the air in the car and the deviation change rate ec. The output obtained by the controller after calculation acts on the train air conditioning system. The air conditioning system adjusts the temperature in the car through the actuator to perform corresponding actions to optimize the thermal comfort of the subway car.

[0101] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0102] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0103] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0104] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0105] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An air conditioning control method for optimizing thermal comfort in a subway car, characterized in that: include: Use simulation analysis software to build subway car models with different standing density; Carry out meshing and convergence processing on the established carriage model; Under the preset boundary conditions, the thermal environment simulation parameters of the subway car with different seat densities are simulated; Measure the actual parameters of the thermal environment of the subway car when the standing density is 0, and perform parameter preprocessing; Calculate the error value between the simulation parameter and the actual parameter when the standing density is 0; comparing the error value to a threshold error range; Analyze the thermal environment of the carriage at different seat densities to obtain the optimized carriage thermal environment; According to the optimization results, a detection algorithm based on the spatial attention module of adaptive receptive field is used to dynamically classify the density of standing seats in subway cars, and the interval of standing seat density in the car at the start time of each station is calculated in real time; The standing seat density category interval obtained by linkage calculation is used to control the car air-conditioning system using fuzzy PID. The air-conditioning system adjusts the temperature in the car through the actuator to perform corresponding actions and optimize the thermal comfort of the subway car.

2. The air conditioning control method for optimizing thermal comfort in a subway car according to claim 1, characterized in that: The use of simulation analysis software to establish subway car models with different standing density includes modeling according to the actual length, width and height of the car, the size and distribution of doors and windows, and the shape of the vehicle, taking a 1 / 2 symmetrical structure for grid division and numerical simulation, and establishing the standing density according to the standing-to-sitting ratio. People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 , People / m 2 There are seven carriage models in total; Among them, the standing density refers to the average number of standing passengers in the subway car, which is the area of ​​the ground minus the area occupied by the infrastructure. It is used to characterize the degree of crowding of people and cars under the standing density, and is expressed as: Where C is the density of standing seats for passengers in the subway car, which is a positive integer. N is the number of standing passengers in the subway car. X is the floor area of ​​the subway car minus the area occupied by infrastructure.

3. The air conditioning control method for optimizing thermal comfort in a subway car according to claim 2, characterized in that: The thermal environment simulation parameters of the subway car under different seat densities are simulated under the preset boundary conditions, including adopting the RNG k-ε model and component transport in the turbulence model, and using the standard wall function for calculation. The turbulent kinetic energy and dissipation rate of the RNG k-ε turbulence model are expressed as: Among them, μ eff is the effective viscosity coefficient, G k is the turbulent kinetic energy generation term caused by the average velocity gradient, ρ is the air density, α k , α ε is the reciprocal of k and the effective Prandtl number, is an empirical constant, The RNG k-ε turbulence model is selected together with the law of conservation of mass, law of conservation of momentum and law of conservation of energy to form the control model. The tensor form is: Continuity equation: Momentum is expressed as: Energy is expressed as: The component transport is expressed as: Among them, u i Represents the velocity component, where i = 1, 2, 3, representing the x, y, and z directions respectively. i 、x j represents the spatial position coordinates, P represents the pressure, T represents the fluid temperature, g represents the gravitational acceleration, C p represents the specific heat at constant pressure, ρ represents the fluid density, C represents the local concentration of the fluid, Re represents the Reynolds number, Sc represents the Schmidt number, Q represents the occurrence rate of the defined pollutant source term, L0 represents the characteristic length, and C0 represents the special positive concentration.

4. The air conditioning control method for optimizing thermal comfort in a subway car according to claim 3, characterized in that: The thermal environment simulation parameters include supply air speed, return air speed, return air temperature, average cabin temperature, average cabin wind speed, and cabin temperature and cabin wind speed at different heights.

5. The air conditioning control method for optimizing thermal comfort in a subway car according to claim 4, characterized in that: The comparing the error value with the threshold error range includes re-gridding and re-converging the established car model when the error value exceeds the threshold error range; When the error value does not exceed the threshold error range, the thermal environment of the carriage under various seat densities is analyzed to obtain the optimized thermal environment of the carriage.

6. The air conditioning control method for optimizing thermal comfort in a subway car according to claim 5, characterized in that: The detection algorithm based on the spatial attention module of the adaptive receptive field is used to dynamically classify the standing seat density in the subway car, including using the SKSAM-ResNet algorithm to detect the standing seat density in the subway car in real time, embedding the series combination of the adaptive receptive field attention module in front and the spatial attention module in the back into the backbone network ResNet-50 model, and replacing the 3×3 convolution kernel in ResNet-50 with the adaptive receptive field module and the spatial attention module. At the start time of the train at each station, the standing seat density in the car is calculated in real time, and the air supply parameters are dynamically adjusted to ensure that the thermal environment in the car is always in the best state.

7. The air conditioning control method for optimizing thermal comfort in a subway car according to claim 6, characterized in that: The fuzzy PID control car air conditioning system is adopted. The air conditioning system performs corresponding actions to adjust the temperature in the car through the actuator, including monitoring the interval of the standing density at the time of vehicle startup, taking the optimized average temperature in the car after simulation under the interval as the set value, comparing the air temperature in the car measured by the sensor with the set value, and obtaining the temperature deviation e and the deviation change rate ec of the air in the car as the input variables of the controller, and then obtaining the output through the fuzzification, reasoning and defuzzification process. The controller gives different PID parameters in real time according to different situations and expert experience, so as to meet the control requirements of the train car under different car thermal environments, optimize the system temperature control, and make the car thermal environment comfortable.

8. A system using the air conditioning control method for optimizing thermal comfort in a subway car as claimed in any one of claims 1 to 7, characterized in that: It includes a first processing module, a first acquisition module, a second processing module, a second acquisition module, a third processing module, a third acquisition module, and a fourth processing module; The first processing module is used to use simulation analysis software to establish a subway car model with different standing density, divide the model into grids and perform algorithm convergence processing, and simulate the thermal environment simulation parameters of the subway car under preset boundary conditions using the obtained car model; The first acquisition module is used to measure the actual parameters of the thermal environment of the subway car when the standing density is 0; The second processing module is used to perform parameter preprocessing to eliminate measurement errors, calculate the error value between the simulated parameters and the actual parameters of the subway car when the standing seat density is 0, and when the error value exceeds the threshold error, send an instruction to the first processing module; when the error value does not exceed the threshold error, analyze the thermal environment of the car under each standing seat density to obtain an optimized car thermal environment, and classify the standing seat density according to the optimization result; The second acquisition module is used to monitor the passenger distribution in the carriage in real time through a distributed sensor network and dynamically adjust the monitoring range according to the actual passenger distribution based on the detection algorithm of the spatial attention module of the adaptive perception, and calculate the standing seat density in the carriage at the start time of each station in real time; The third processing module is used to identify the category interval of the standing seat density and the optimized average temperature in the vehicle compartment obtained by simulation under the interval according to the obtained standing seat density; The third acquisition module is used to measure the air temperature in the carriage at the time of train start through a sensor; The fourth processing module is used to link the calculated standing density category interval with the fuzzy PID controller, and use the optimized average temperature in the car after simulation under this interval as the set value. The air temperature in the car measured by the sensor is compared with the set value to obtain the temperature deviation e and the deviation change rate ec of the air in the car. The output obtained by the input controller after calculation acts on the train air-conditioning system. The air-conditioning system performs corresponding actions through the actuator to adjust the temperature in the car and optimize the thermal comfort of the subway car.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the air conditioning control method for optimizing thermal comfort of a subway car according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the air conditioning control method for optimizing thermal comfort in a subway car according to any one of claims 1 to 7 are implemented.

Images