CO2 transcritical railway vehicle air conditioner heat pump system and control method thereof

Abstract

The invention provides a CO2 transcritical rail vehicle air conditioner heat pump system and a control method thereof, and belongs to the technical field of rail vehicle air conditioner control. The control method comprises the steps that heat pump system parameter data and vehicle running state data are obtained, and a vehicle condition mode is determined according to the vehicle running state data; according to the determined vehicle condition mode and the heat pump system parameter data, a high-pressure side pressure set value is generated through a preset self-adaptive heat pump regulation and control model; calculating an opening value of the electronic expansion valve according to the generated pressure set value; and according to the generated pressure set value, the rotating speed of the inverter compressor is adjusted through PID closed-loop control, and the opening degree of the electronic expansion valve is adjusted according to the calculated opening degree value of the expansion valve. According to the CO2 transcritical railway vehicle air conditioner heat pump control method, the energy efficiency of a heat pump system is effectively improved, and the adaptability of the heat pump system is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rail vehicle air-conditioning control, and particularly to a CO2 transcritical rail vehicle air-conditioning heat pump system and its control method. Background Art

[0002] The rail vehicle air-conditioning heat pump system is a core component to ensure passenger comfort and the safe operation of equipment. Especially, the CO2 transcritical cycle system, as a representative, has become the mainstream technical solution due to its environmental protection and high energy efficiency characteristics. The traditional control method realizes the control of refrigerating capacity by presetting the pressure set value and the expansion valve opening rule, and combining the PID to adjust the compressor speed. Such methods rely on engineers' experience to set parameters, and can maintain operation under steady-state conditions. However, in the face of the unique dynamic scenarios of rail vehicles (such as frequent starts and stops, passenger tidal fluctuations, tunnel-station environment switching), redundant design or manual intervention is required to avoid system instability.

[0003] Traditional rail vehicle air-conditioning heat pump systems mostly adopt control strategies based on fixed rules or PID. The operating scenarios of rail vehicles are complex and changeable, and the fixed parameter strategy is difficult to adapt to the dynamic heat load demand in real time, which easily leads to low energy efficiency ratio and cabin temperature fluctuations; the existing control methods do not deeply integrate vehicle operating state data (such as door opening and closing frequency, passenger density), and cannot predict sudden load changes, which easily cause problems such as frequent start and stop of the compressor and overshoot of the high-pressure side pressure during peak hours or extreme conditions. Summary of the Invention

[0004] The present invention provides a CO2 transcritical rail vehicle air-conditioning heat pump system and its control method to solve the problems of poor adaptability to dynamic scenarios and low energy efficiency in the prior art.

[0005] To achieve the above object, on the one hand, an embodiment of the present invention provides a CO2 transcritical rail vehicle air-conditioning heat pump control method, and the CO2 transcritical rail vehicle air-conditioning heat pump control method includes: obtaining heat pump system parameter data and vehicle operating state data, and determining the vehicle condition mode according to the vehicle operating state data; generating a high-pressure side pressure set value through a preset adaptive heat pump regulation model according to the determined vehicle condition mode and the heat pump system parameter data; calculating an electronic expansion valve opening value according to the generated pressure set value; adjusting the speed of the variable-frequency compressor through PID closed-loop control according to the generated pressure set value, and adjusting the opening of the electronic expansion valve according to the calculated expansion valve opening value.

[0006] Optionally, the heat pump system parameters include high-pressure side pressure, evaporation temperature, gas cooler outlet temperature, and compressor speed, and the vehicle operating state data includes door opening and closing frequency, passenger density, geographical location, and power supply mode.

[0007] Optionally, the adaptive heat pump control model is constructed based on the lightweight proximal policy optimization algorithm and configured with an LSTM module. Generating a high-pressure side pressure set value according to the determined vehicle condition mode and the heat pump system parameter data includes: constructing a state vector of the heat pump system according to the heat pump system parameter data; encoding the vehicle condition mode as an independent feature and fusing the state vector. According to the fused state vector, predicting the heat load demand through the LSTM module and generating a pressure adjustment amount; calculating the pressure set value according to the generated pressure adjustment amount in combination with a preset pressure threshold value.

[0008] Optionally, calculating the opening value of the electronic expansion valve according to the generated pressure set value includes: determining a basic adjustment amount of the opening of the electronic expansion valve according to the deviation between the pressure set value and the current high-pressure side pressure; correcting the basic adjustment amount according to the superheat of the evaporator; calculating a vibration compensation amount according to a preset vibration compensation mechanism; calculating the opening value of the electronic expansion valve according to the vibration compensation amount in combination with the corrected basic adjustment amount.

[0009] Optionally, calculating the vibration compensation amount according to the preset vibration compensation mechanism includes: embedding the historical electronic expansion valve opening adjustment sequence into the state vector to generate a new state vector; according to the generated new state vector, learning the law of the response lag of the electronic expansion valve in the vibration environment through the adaptive heat pump control model and generating the vibration compensation amount.

[0010] Optionally, determining the vehicle condition mode according to the vehicle operation state data includes: when the power supply mode is the regenerative braking mode and the geographical location is the platform area, switching the vehicle condition mode to the energy-saving mode; when it is detected that the door opening and closing frequency is greater than a preset frequency or the passenger density is greater than a preset density value, switching the vehicle condition mode to the sudden load mode; when the vehicle operation state data simultaneously meets the energy-saving mode and the sudden load mode, switching the vehicle condition mode to the energy-saving mode; otherwise, switching the vehicle condition mode to the normal mode.

[0011] Optionally, the CO2 transcritical rail vehicle air-conditioning heat pump control method further includes: when it is detected that the door opening and closing frequency is greater than a preset frequency, expanding the adjustment range of the pressure set value; when the passenger density is greater than a preset density value, expanding the adjustment range of the opening value of the electronic expansion valve; when the geographical location is a tunnel, switching the vehicle condition mode to the normal mode and restricting the adjustment range of the pressure set value.

[0012] Optionally, the training process of the adaptive heat pump control model adopts a multi-objective reward function, and adjusts the weights in the multi-objective reward function according to the vehicle operation state data and the vehicle condition mode. The adjustment of the weights in the multi-objective reward function includes: when it is detected that the door opening and closing frequency exceeds the preset frequency, increasing the weight of the compressor power overlimit penalty term to strengthen the priority of temperature stability; when the vehicle is in the regenerative braking mode, increasing the weight of the real-time energy efficiency ratio to give priority to improving the energy efficiency ratio.

[0013] Optionally, the CO2 transcritical rail vehicle air-conditioning heat pump control method further includes: when the outlet temperature of the gas cooler is lower than the dew point temperature and the duration exceeds the preset time, triggering a defrosting instruction; according to the defrosting instruction, outputting a bypass valve opening instruction through the adaptive heat pump control model; according to the output opening instruction, adjusting the bypass valve opening to direct the exhaust heat of the variable-frequency compressor into the gas cooler.

[0014] On the other hand, the present invention also provides a CO2 transcritical rail vehicle air-conditioning heat pump system for implementing the above-mentioned CO2 transcritical rail vehicle air-conditioning heat pump control method. The CO2 transcritical rail vehicle air-conditioning heat pump system includes: a variable-frequency compressor, an electronic expansion valve, a gas cooler, a bypass valve, a sensor network, and an on-vehicle edge controller. Among them, the on-vehicle edge controller is configured with a multi-source data fusion module and an adaptive heat pump control model. The on-vehicle edge controller is used to generate a high-pressure side pressure set value and an electronic expansion valve opening value through the adaptive heat pump control model, and adjust the variable-frequency compressor and the electronic expansion valve according to the generated high-pressure side pressure set value and electronic expansion valve opening value.

[0015] The CO2 transcritical rail vehicle air-conditioning heat pump system and its control method provided by the present invention significantly improve the comprehensive performance of the CO2 transcritical rail vehicle air-conditioning heat pump system by integrating the adaptive heat pump control model and multi-source data fusion technology. It can dynamically adjust the pressure set value and the expansion valve opening based on the vehicle condition mode to achieve high-stability control of the cabin temperature fluctuation; optimize the cooperation efficiency of the compressor and the expansion valve through a lightweight reinforcement learning model (PPO+LSTM) to effectively improve the energy efficiency ratio (COP); the innovative vibration compensation mechanism combined with the anti-vibration hardware design effectively reduces the control precision error of the expansion valve and effectively responds to the random vibration interference of the track; at the same time, the system integrates multi-objective optimization, geographical environment perception, and intelligent defrosting functions, taking into account energy efficiency, safety, and adaptability to extreme working conditions. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0017] Figure 1 is a flowchart of the CO2 transcritical rail vehicle air-conditioning heat pump control method provided by an embodiment of the present invention;

[0018] Figure 2 is an architecture diagram of the adaptive heat pump regulation model provided by an embodiment of the present invention;

[0019] Figure 3 is a vibration compensation mechanism diagram provided by an embodiment of the present invention;

[0020] Figure 4 is a defrost control flowchart provided by an embodiment of the present invention;

[0021] Figure 5 is a structural schematic diagram of the CO2 transcritical rail vehicle air-conditioning heat pump system provided by an embodiment of the present invention. Detailed Embodiments

[0022] The following will detail the specific embodiments of the embodiments of the present invention in conjunction with the drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the present invention, and are not used to limit the embodiments of the present invention.

[0023] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of this application all comply with the relevant regulations of national laws and regulations. In the embodiments of this application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solutions of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0024] The rail vehicle air-conditioning heat pump system is a core component to ensure passenger comfort and the safe operation of equipment. When facing the unique dynamic scenarios of rail vehicles, it is necessary to rely on redundant design or manual intervention to avoid system instability. In the prior art, some improvement solutions attempt to introduce fuzzy control or simple feedback mechanisms, but the core logic is still limited to local parameter adjustment and fails to achieve multi-source data fusion and global optimization. Therefore, it is particularly important to develop a more effective air-conditioning heat pump control method.

[0025] In view of this problem, the present invention provides a CO2 transcritical rail vehicle air-conditioning heat pump system and its control method, which realizes precise control through multi-source data fusion and dynamic decision-making mechanism. By introducing vehicle operation state data, it provides a scenario-based decision-making basis for generating pressure set values and expansion valve opening degrees. At the same time, a vibration compensation mechanism and a multi-objective reward function are innovatively embedded to ensure the stable execution of control commands in a complex vibration environment and balance multiple objectives such as energy efficiency, temperature stability, and power limitation. Compared with traditional methods, the present invention significantly improves the response speed, anti-interference ability, and comprehensive energy efficiency of the rail vehicle air-conditioning system in dynamic scenarios.

[0026] The CO2 transcritical cycle is an efficient thermodynamic cycle using carbon dioxide (R744) as the refrigerant. Its core feature is that the refrigerant crosses the critical point (critical temperature 31.1 °C, critical pressure 7.38 MPa) during the cycle. In this cycle, CO2 exchanges heat with ambient air in the gas cooler in a supercritical fluid state (pressure > 7.38 MPa, temperature > 31.1 °C) without undergoing the condensation phase change of traditional refrigerants, but achieving heat transfer through continuous changes in pressure and temperature; subsequently, the high-pressure CO2 is throttled and depressurized to the subcritical state by the expansion valve and enters the evaporator to absorb heat and complete the refrigeration cycle. This technology, with the natural environmental friendliness of CO2 (ODP = 0, GWP = 1), high volumetric refrigeration capacity (3 - 5 times higher than that of Freon), and excellent high-temperature environment adaptability, has become an ideal solution in the fields of rail transit, heat pump heating, etc. However, its high-pressure operation characteristics (8 - 12 MPa) and dynamic control requirements also pose technical challenges in system design and energy efficiency optimization.

[0027] The following will Figures 1 to 5 describe the present invention specifically.

[0028] An embodiment of the present invention provides a CO2 transcritical rail vehicle air-conditioning heat pump system, and the CO2 transcritical rail vehicle air-conditioning heat pump system includes: a variable-frequency compressor, an electronic expansion valve, a gas cooler, a bypass valve, a sensor network, and an on-vehicle edge controller. Among them, the on-vehicle edge controller is configured with a multi-source data fusion module and an adaptive heat pump regulation model. The on-vehicle edge controller is used to generate a high-pressure side pressure set value and an electronic expansion valve opening value through the adaptive heat pump regulation model, and adjust the variable-frequency compressor and the electronic expansion valve according to the generated high-pressure side pressure set value and electronic expansion valve opening value.

[0029] As Figure 5As shown in the figure, specifically, the sensor network includes: a pressure sensor installed at the compressor outlet and the evaporator inlet, a temperature sensor installed at the gas cooler outlet, a Hall sensor installed on the vehicle door, and a camera. The vehicle-mounted edge controller obtains vehicle data through the sensor network, synchronizes with the heat pump parameters, and constructs a state vector, and then outputs a pressure set value and an electronic expansion valve opening value through the adaptive heat pump control model. The variable-frequency compressor tracks the pressure set value through the PID controller, and the electronic expansion valve adjusts itself according to the electronic expansion valve opening value, drives the stepping motor with a PWM signal, and adjusts the opening. In the defrosting mode, the bypass valve is adjusted according to the opening command.

[0030] An embodiment of the present invention further provides a CO2 transcritical rail vehicle air-conditioning heat pump control method, which is applied to the above heat pump system, as Figure 1 shown, the CO2 transcritical rail vehicle air-conditioning heat pump system control method includes:

[0031] S101: Obtain the heat pump system parameter data and the vehicle operation state data, and determine the vehicle condition mode according to the vehicle operation state data;

[0032] S102: Generate a high-pressure side pressure set value through a preset adaptive heat pump control model according to the determined vehicle condition mode and the heat pump system parameter data;

[0033] S103: Calculate the electronic expansion valve opening value according to the generated pressure set value;

[0034] S104: Adjust the speed of the variable-frequency compressor through PID closed-loop control according to the generated pressure set value, and adjust the opening of the electronic expansion valve according to the calculated expansion valve opening value.

[0035] Preferably, the heat pump system parameters include the high-pressure side pressure, the evaporation temperature, the gas cooler outlet temperature, and the compressor speed, and the vehicle operation state data includes the door switch frequency, the passenger density, the geographical location, and the power supply mode.

[0036] A CO2 transcritical rail vehicle air-conditioning heat pump control method provided by an embodiment of the present invention constructs a scientific and efficient system operation regulation mechanism. First, by comprehensively collecting heat pump system parameter data, such as key data reflecting the internal operation state of the system, like high-pressure side pressure, evaporation temperature, etc., and vehicle operation state data, such as data closely related to the actual use scenario of the vehicle, such as door switch frequency, passenger density, etc., it provides a rich and accurate information basis for subsequent control decisions. Then, based on the obtained vehicle operation state data, the vehicle condition mode is accurately determined. For example, it can be identified as an energy-saving mode when in the regenerative braking mode and in the platform area, and switched to the sudden load mode when the door switches frequently or the passenger density is large. Subsequently, using the preset adaptive heat pump regulation model, the determined vehicle condition mode is combined with the heat pump system parameter data, and through complex calculations and analyses, a high-pressure side pressure set value that meets the current working condition requirements is generated. Finally, based on this pressure set value, on the one hand, the PID closed-loop control algorithm is used to dynamically adjust the speed of the variable-frequency compressor to ensure that the system pressure is stable near the set value; on the other hand, the opening value of the electronic expansion valve is calculated through a series of calculations and the opening of the electronic expansion valve is adjusted accordingly, so as to achieve precise control of the refrigerant flow rate. Through such a complete control process, the air-conditioning heat pump system can intelligently and accurately adapt to different working conditions, effectively optimize the system performance, improve the energy utilization efficiency and the comfort of the vehicle interior environment.

[0037] Preferably, as Figure 2 shown, the adaptive heat pump regulation model is constructed based on the lightweight proximal policy optimization algorithm and is configured with an LSTM module. The generating of the high-pressure side pressure set value according to the determined vehicle condition mode and the heat pump system parameter data through the preset adaptive heat pump regulation model includes: constructing a state vector of the heat pump system according to the heat pump system parameter data; encoding the vehicle condition mode as an independent feature and fusing the state vector. According to the fused state vector, predicting the heat load demand through the LSTM module and generating a pressure adjustment amount; calculating the pressure set value according to the generated pressure adjustment amount in combination with a preset pressure threshold.

[0038] In a preferred embodiment of the present invention, the lightweight proximal policy optimization algorithm is used to construct the adaptive heat pump control model. This algorithm can optimize the model in an efficient manner, ensuring the convergence speed and performance of the model while reducing the consumption of computing resources, and is particularly suitable for the railway vehicle air conditioning system with strict requirements for real-time performance and resource occupancy. LSTM (Long Short-Term Memory) has a powerful ability to process sequential data and can capture long-term dependencies in the data, which is crucial for accurately predicting the heat load demand because the heat load is affected by various factors on different time scales. In the step of generating the high-pressure side pressure set value, first, according to the obtained heat pump system parameter data, a state vector of the heat pump system is constructed. The state vector S t can be expressed as:

[0039] S t =[P high , T gc , N comp (1)

[0040] where P high represents the high-pressure side pressure, T gc represents the outlet temperature of the gas cooler, and N comp represents the compressor speed. This state vector is a comprehensive quantitative representation of the current operating state of the system and provides a basis for subsequent calculations and predictions. Subsequently, the vehicle condition modes (such as energy-saving mode, sudden load mode, etc.) are encoded as independent features and fused with the state vector. The advantage of this is to incorporate the external operating condition information of the system into the state representation, enabling the model to more comprehensively consider the effects of various factors on the heat load and pressure. Finally, the fused state vector is input into the LSTM module, and using its powerful sequential analysis ability, the future heat load demand is predicted. The heat load demand is a key factor in the control of the air conditioning system, and accurate prediction can enable the system to make adjustments in advance, improving the response speed and control accuracy. Based on the heat load demand prediction result, the model generates a pressure adjustment amount. This adjustment amount reflects the change that the high-pressure side pressure of the system needs to make to meet the predicted heat load demand. After obtaining the pressure adjustment amount, the final pressure set value is calculated in combination with a preset pressure threshold. This adaptive heat pump control model processes and analyzes multi-source data through advanced algorithms and modules, achieving accurate calculation of the high-pressure side pressure set value and providing strong support for the efficient and stable operation of the CO2 transcritical railway vehicle air conditioning heat pump system.

[0041] For example, assume that a train is at a platform and in the regenerative braking mode. After its CO2 transcritical air-conditioning heat pump system obtains the heat pump system parameter data (high-pressure side pressure of 10 MPa, evaporation temperature of 5 °C, gas cooler outlet temperature of 35 °C, compressor speed of 3000 revolutions per minute) and the vehicle operating state data (the doors are opened and closed 10 times in the past 5 minutes, 5 passengers per square meter), it determines that the vehicle condition mode is the energy-saving mode. Then, the heat pump system parameters are constructed into a state vector [10, 5, 35, 3000], the energy-saving mode is encoded as [1, 0, 0] and fused with the state vector to obtain [1, 0, 0, 10, 5, 35, 3000], which is input into an adaptive heat pump control model constructed based on the lightweight proximal policy optimization algorithm and configured with an LSTM module. After the LSTM module predicts the heat load demand, it generates a pressure adjustment amount of -1 MPa. Combining the initial basic pressure set value of 11 MPa with the preset pressure threshold of 8 - 12 MPa, the final high-pressure side pressure set value is calculated to be 10 MPa. Subsequently, the system adjusts the compressor speed and the opening degree of the electronic expansion valve accordingly to achieve energy-saving operation.

[0042] Preferably, as Figure 3 shown, calculating the opening degree value of the electronic expansion valve according to the generated pressure set value includes: determining the basic adjustment amount of the opening degree of the electronic expansion valve according to the deviation between the pressure set value and the current high-pressure side pressure; correcting the basic adjustment amount according to the superheat of the evaporator; calculating the vibration compensation amount according to a preset vibration compensation mechanism; and calculating the opening degree value of the electronic expansion valve according to the vibration compensation amount in combination with the corrected basic adjustment amount.

[0043] More preferably, calculating the vibration compensation amount according to the preset vibration compensation mechanism includes: embedding the historical electronic expansion valve opening adjustment sequence into the state vector to generate a new state vector; and according to the generated new state vector, through the adaptive heat pump control model, learning the law of the response lag of the electronic expansion valve in the vibration environment and generating the vibration compensation amount.

[0044] In a preferred embodiment of the present invention, the vibration during the operation of the rail vehicle will interfere with the normal response of the electronic expansion valve, resulting in a lag or inaccuracy in the opening adjustment. To solve this problem, the present invention is provided with a vibration compensation mechanism. First, the historical electronic expansion valve opening adjustment sequence is embedded into the state vector to generate a new state vector. This operation integrates the historical adjustment information, enabling the new state vector to more comprehensively reflect the operation history and dynamic changes of the system. Then, the adaptive heat pump control model is used to analyze the new state vector. The model is constructed based on the lightweight proximal policy optimization algorithm and configured with an LSTM module, and has strong learning and prediction capabilities. By learning the new state vector, the model can capture the law of the response lag of the electronic expansion valve in the vibration environment and generate the vibration compensation amount accordingly. The calculation formula of the vibration compensation amount can be expressed as:

[0045]

[0046] wherein, Δθ vib represents the vibration compensation amount, a represents the compensation coefficient, N is the length of the historical window, represents the adjustment amount of the expansion valve opening at the i-th time in history.

[0047] For example, assume that the length of the historical window N = 10, the compensation coefficient a = 0.2, and the adjustment amounts of the expansion valve opening for the 10 historical times are 0.1, 0.2, 0.15, 0.25, 0.12, 0.22, 0.18, 0.28, 0.16, 0.26 respectively. Then the vibration compensation amount Δθ vib After calculation by formula (2), it is obtained that: Δθ vib

[0048] = 0.0384. Adding 0.0384 to the basic adjustment amount can obtain the final opening value of the electronic expansion valve.

[0049] Preferably, determining the vehicle condition mode according to the vehicle operation state data includes: when the power supply mode is the regenerative braking mode and the geographical location is the platform area, switching the vehicle condition mode to the energy-saving mode; when it is detected that the door opening and closing frequency is greater than the preset frequency, or the passenger density is greater than the preset density value, switching the vehicle condition mode to the sudden load mode; when the vehicle operation state data simultaneously meets the energy-saving mode and the sudden load mode, switching the vehicle condition mode to the energy-saving mode; otherwise, switching the vehicle condition mode to the normal mode.

[0050] In a preferred embodiment of the present invention, the vehicle condition mode is closely related to the vehicle operation state data. When the vehicle operation state data simultaneously meets the conditions of the energy-saving mode and the sudden load mode, it is preferentially switched to the energy-saving mode, fully considering the vehicle operation characteristics and energy-saving requirements. Although the sudden load mode is designed to cope with the sharp change of the heat load, in the platform area and in the regenerative braking mode, the priority of energy saving is higher. At this time, even if there is a certain heat load fluctuation, through reasonable system regulation in the energy-saving mode, it is still possible to save energy to the greatest extent while ensuring the basic comfort.

[0051] For example, at 10 am on Saturday, the train stops at Platform C. This platform is close to a large amusement park. Passengers get on and off the train frequently, the door opening and closing frequency is high, and the passenger density in the car is large, meeting the conditions of the sudden load mode. But at the same time, the train is in the regenerative braking mode and is located in the platform area, also meeting the conditions of the energy-saving mode. According to the rules, the system preferentially switches to the energy-saving mode. In the energy-saving mode, the system optimizes the control strategy and appropriately adjusts the refrigeration capacity, ensuring the basic comfort and making the best use of the regenerative braking energy to reduce energy consumption.

[0052] Preferably, the control method for the CO2 transcritical rail vehicle air conditioning heat pump system further includes: when it is detected that the door opening and closing frequency is greater than a preset frequency, expanding the adjustment range of the pressure set value; when the passenger density is greater than a preset density value, expanding the adjustment range of the opening value of the electronic expansion valve; when the geographical location is a tunnel, switching the vehicle condition mode to the normal mode and restricting the adjustment range of the pressure set value.

[0053] In a preferred embodiment of the present invention, larger heat load fluctuations require the system to have stronger adjustment capabilities. By expanding the adjustment range of the pressure set value, the system can more flexibly adjust the high-side pressure. For example, in hot weather, frequent opening and closing of the doors allows a large amount of hot air to enter the carriage. At this time, a larger range of pressure adjustment can make the compressor output more matching cooling capacity, quickly reduce the temperature inside the vehicle, and meet the passengers' comfort requirements. As a key component for controlling the refrigerant flow, expanding the opening adjustment range of the electronic expansion valve can more precisely control the amount of refrigerant entering the evaporator. For example, during peak hours, the carriage is overcrowded, and a large amount of heat dissipation from the human body causes a sharp increase in the heat load. A larger range of opening adjustment can ensure that the evaporator fully exerts its refrigeration effect and maintain a suitable temperature inside the vehicle. The environment inside the tunnel is relatively enclosed, the operating conditions of the vehicle are relatively stable, and the change in the heat load is relatively small. Switching to the normal mode allows the system to operate according to the parameters under stable operating conditions, ensuring the stability of the operation. Restricting the adjustment range of the pressure set value can prevent the system from generating additional energy consumption due to unnecessary frequent pressure adjustments, and at the same time avoid damage to the system components caused by excessive pressure fluctuations, ensuring stable and efficient operation inside the tunnel.

[0054] Preferably, the training process of the adaptive heat pump control model adopts a multi-objective reward function, and adjusts the weights in the multi-objective reward function according to the vehicle operation state data and the vehicle condition mode. The adjustment of the weights in the multi-objective reward function includes: when it is detected that the door opening and closing frequency exceeds the preset frequency, increasing the weight of the compressor power overlimit penalty term to strengthen the priority of temperature stability; when the vehicle is in the regenerative braking mode, increasing the weight of the real-time coefficient of performance to give priority to improving the coefficient of performance.

[0055] Specifically, the multi-objective reward function can be expressed as:

[0056]

[0057] where α, β, and γ all represent weight coefficients, COP t represents the real-time coefficient of performance, P high represents the current high-side pressure, represents the high-side pressure set value, T cab represents the carriage temperature, T setIt represents the target temperature of the passenger compartment, and Power_p represents the penalty term for compressor power overlimit.

[0058] In a preferred embodiment of the present invention, frequent opening and closing of the door will cause a large fluctuation in the heat load inside the vehicle. At this time, strengthening the priority of temperature stability is of great significance. Increasing the weight of the penalty term for compressor power overlimit can prompt the model to pay more attention to avoiding excessive increase in compressor power when adjusting the system parameters, preventing large temperature fluctuations caused by pursuing rapid cooling and heating. For example, if the compressor power increases without limit to cope with sudden changes in heat load, although the temperature can be quickly changed, it may cause temperature overshoot or large oscillations, affecting the comfort of passengers. Through this weight adjustment, the model will give priority to maintaining temperature stability while ensuring a certain cooling and heating capacity, so that the temperature inside the vehicle can also be kept within a comfortable range under frequent changes in heat load. During the regenerative braking mode, the vehicle can recover energy. At this time, giving priority to improving the coefficient of performance (COP) conforms to the overall goal of energy conservation. After increasing the weight of the real-time COP, the model will be more inclined to optimize the system operation parameters during the training process, enabling the air-conditioning system to operate with higher efficiency on the basis of utilizing the regenerative braking energy. For example, the model will adjust parameters such as the compressor speed and the opening degree of the electronic expansion valve, so that the system can meet the heat load demand inside the vehicle while minimizing additional power consumption, achieving the maximum utilization of energy, improving the overall energy efficiency level of the system, and reducing the dependence on the external power grid.

[0059] Preferably, as Figure 4 shown, the control method for the CO2 transcritical rail vehicle air-conditioning heat pump system further includes: when the outlet temperature of the gas cooler is lower than the dew point temperature and the duration exceeds a preset time, triggering a defrosting instruction; according to the defrosting instruction, through the adaptive heat pump control model, outputting a bypass valve opening instruction; according to the output opening instruction, adjusting the opening degree of the bypass valve to direct the exhaust heat of the variable-frequency compressor into the gas cooler.

[0060] For example, the train is on the way. As the outside temperature is as low as -10℃, the heat load in the carriage is relatively stable, but the gas cooler is continuously affected by the low temperature environment. At this time, the gas cooler outlet temperature sensor detects that the temperature has dropped to 5℃, while the air humidity in the area is high, and the dew point temperature is calculated to be 8℃, and the gas cooler outlet temperature is lower than the dew point temperature. Moreover, this low temperature state lasts for 15 minutes, exceeding the system preset 10 minutes. Therefore, the system quickly triggers the defrost command. The adaptive heat pump control model starts working immediately, which comprehensively considers the current system's high-pressure side pressure, compressor speed, evaporator temperature and other operating parameters, as well as information such as the vehicle's operating mode. Through complex algorithms and pre-learned experience, the model quickly calculates the bypass valve opening command, assuming that the output opening value is 40%. According to the command, the system accurately adjusts the bypass valve opening to 40%. At this time, part of the high-temperature and high-pressure gas discharged by the variable frequency compressor flows directly to the gas cooler through the bypass valve. These high-temperature gases carry a lot of heat and quickly act on the frost layer on the surface of the gas cooler. Within a few minutes of continuous heating, the frost layer gradually melts into water droplets and is discharged along a specific drainage channel, and the heat exchange performance of the gas cooler is gradually restored. As the frost layer is removed, the gas cooler outlet temperature gradually rises. When the temperature stabilizes above the dew point temperature and remains above it for a period of time, the defrosting process ends and the system returns to normal operation, continuing to provide a comfortable temperature environment for passengers in the car.

[0061] In summary, the present invention provides a CO2 transcritical rail vehicle air conditioning heat pump system and a control method thereof, which determines the vehicle condition mode by comprehensively collecting heat pump system parameters and vehicle operation status data, generates a high-pressure side pressure setting value through an adaptive heat pump control model, adjusts the speed of the variable frequency compressor by combining PID closed-loop control, accurately calculates and adjusts the opening of the electronic expansion valve, and realizes refined intelligent control of the system. In terms of adaptability, it can flexibly switch between energy-saving, sudden load, conventional and other vehicle condition modes according to different working conditions such as door switch frequency, passenger density, geographical location, power supply mode, etc., to meet the heat load requirements in different scenarios and effectively ensure the comfort of the interior environment. In terms of energy-saving design, the regenerative braking mode is switched to the energy-saving mode when in the platform area. At the same time, when training the adaptive heat pump control model, the real-time energy efficiency ratio weight is increased for the regenerative braking mode, the system energy efficiency is optimized, and the energy consumption is reduced. In terms of defrosting mechanism, scientific defrosting trigger conditions are set, and the bypass valve opening instruction is accurately output by using the adaptive heat pump control model. The exhaust heat of the variable frequency compressor is introduced in a directional manner for defrosting, which is efficient and ensures the stability and safety of the system, and improves the system performance in all aspects.

[0062] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0063] In addition, the terms "system" and "network" in this document are often used interchangeably herein. The term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after.

[0064] It should be understood that in the embodiments of the present invention, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0065] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0066] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0067] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection to each other can be an indirect coupling or communication connection through some interfaces, devices, or units, or can also be an electrical, mechanical, or other form of connection.

[0068] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present invention.

[0069] In addition, in each embodiment of the present invention, each functional unit may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0070] From the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by firmware, or by a combination thereof. When implemented in software, the above functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. The computer-readable medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transfer of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. By way of example but not limitation: the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, magnetic disk storage media or other magnetic storage devices or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer. In addition, any connection may suitably be a computer-readable medium. For example, if the software is transmitted from a website, server or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, wireless and microwave are included in the definition of the medium. As used in the present invention, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disk generally magnetically replicates data, while disc optically replicates data with a laser. The above combinations should also be included within the scope of protection of the computer-readable medium.

[0071] In summary, the above are only the preferred embodiments of the technical solution of the present invention, and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A control method for a CO2 transcritical rail vehicle air-conditioning heat pump, characterized in that The CO2 transcritical rail vehicle air-conditioning heat pump control method includes: Obtain the heat pump system parameter data and vehicle operation state data, and determine the vehicle condition mode according to the vehicle operation state data; According to the determined vehicle condition mode and the heat pump system parameter data, generate a high-pressure side pressure set value through a preset adaptive heat pump regulation model; Calculate the opening value of the electronic expansion valve according to the generated pressure set value; According to the generated pressure set value, adjust the speed of the variable-frequency compressor through PID closed-loop control, and adjust the opening of the electronic expansion valve according to the calculated opening value of the expansion valve.

2. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 1, wherein, The heat pump system parameters include high-pressure side pressure, evaporation temperature, gas cooler outlet temperature, and compressor speed. The vehicle operation state data includes door opening and closing frequency, passenger density, geographical location, and power supply mode.

3. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 2, characterized in that, The adaptive heat pump regulation model is constructed based on the lightweight proximal policy optimization algorithm and is configured with an LSTM module. The step of generating a high-pressure side pressure set value according to the determined vehicle condition mode and the heat pump system parameter data includes: Construct a state vector of the heat pump system according to the heat pump system parameter data; Encode the vehicle condition mode as an independent feature and fuse the state vector; According to the fused state vector, predict the heat load demand through the LSTM module and generate a pressure adjustment amount; Calculate the pressure set value according to the generated pressure adjustment amount in combination with a preset pressure threshold.

4. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 1, wherein The step of calculating the opening value of the electronic expansion valve according to the generated pressure set value includes: Determine the basic adjustment amount of the electronic expansion valve opening according to the deviation between the pressure set value and the current high-pressure side pressure; Correct the basic adjustment amount according to the superheat of the evaporator; Calculate the vibration compensation amount according to a preset vibration compensation mechanism; Calculate the opening value of the electronic expansion valve according to the vibration compensation amount in combination with the corrected basic adjustment amount.

5. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 4, characterized in that, The step of calculating the vibration compensation amount according to a preset vibration compensation mechanism includes: Embed the historical electronic expansion valve opening adjustment sequence into the constructed state vector to generate a new state vector; According to the generated new state vector, learn the law of the response lag of the electronic expansion valve in the vibration environment through the adaptive heat pump regulation model and generate the vibration compensation amount.

6. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 2, characterized in that, The step of determining the vehicle condition mode according to the vehicle operation state data includes: When the power supply mode is the regenerative braking mode and the geographical location is the platform area, switch the vehicle condition mode to the energy-saving mode; When it is detected that the door opening and closing frequency is greater than a preset frequency, or the passenger density is greater than a preset density value, switch the vehicle condition mode to the sudden load mode; When the vehicle operation state data simultaneously satisfies the energy-saving mode and the sudden load mode, switch the vehicle condition mode to the energy-saving mode; Otherwise, switch the vehicle condition mode to the normal mode.

7. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 2, characterized in that The CO2 transcritical rail vehicle air-conditioning heat pump control method further includes: When it is detected that the door opening and closing frequency is greater than a preset frequency, expand the adjustment range of the pressure set value; When the passenger density is greater than a preset density value, expand the adjustment range of the electronic expansion valve opening value; When the geographical location is a tunnel, switch the vehicle condition mode to the normal mode and limit the adjustment range of the pressure set value.

8. The CO2 transcritical air-conditioning heat pump control method for rail vehicles according to claim 1, characterized in that The training process of the adaptive heat pump control model uses a multi-objective reward function, and adjusts the weights in the multi-objective reward function according to the vehicle operation state data and the vehicle condition mode. The adjustment of the weights in the multi-objective reward function includes: When it is detected that the door opening and closing frequency exceeds the preset frequency, increase the weight of the compressor power overlimit penalty term to strengthen the priority of temperature stability; When the vehicle is in the regenerative braking mode, increase the weight of the real-time coefficient of performance to preferentially improve the coefficient of performance.

9. The CO2 transcritical rail vehicle air-conditioning heat pump control method according to claim 1, characterized in that, The CO2 transcritical rail vehicle air-conditioning heat pump control method further includes: When the outlet temperature of the gas cooler is lower than the dew point temperature and the duration exceeds the preset time, trigger a defrosting instruction; According to the defrosting instruction, output a bypass valve opening instruction through the adaptive heat pump control model; According to the output opening instruction, adjust the bypass valve opening to direct the exhaust heat of the variable frequency compressor into the gas cooler.

10. A CO2 transcritical rail vehicle air-conditioning heat pump system, characterized in that, A CO2 transcritical rail vehicle air-conditioning heat pump system for implementing the CO2 transcritical rail vehicle air-conditioning heat pump control method according to any one of claims 1-9, the CO2 transcritical rail vehicle air-conditioning heat pump system includes: a variable frequency compressor, an electronic expansion valve, a gas cooler, a bypass valve, a sensor network, and a vehicle-mounted edge controller; Wherein, the vehicle-mounted edge controller is configured with a multi-source data fusion module and an adaptive heat pump control model, and the vehicle-mounted edge controller is used to generate a high-pressure side pressure set value and an electronic expansion valve opening value through the adaptive heat pump control model, and adjust the variable frequency compressor and the electronic expansion valve according to the generated high-pressure side pressure set value and electronic expansion valve opening value.

Images