Control method and system for aircraft air conditioner

Abstract

The invention provides a control method for an aircraft air conditioner, and the method can comprise the steps: obtaining information which can comprise external sensor information of an aircraft, load information of the aircraft and operation parameters of an air conditioning system of the aircraft; determining an optimal control strategy from a plurality of candidate control strategies based on the acquired information and the expected operation target, wherein each of the candidate control strategies corresponds to a group of regulation and control state parameters of the aircraft air conditioning system; and the aircraft air conditioning system is controlled based on the regulation and control state parameters corresponding to the optimal control strategy. The invention further provides a control system for the aircraft air conditioner. The air conditioner control parameters can be accurately regulated and controlled in real time, and it is guaranteed that the comfort of an air conditioner system is not interrupted.

Description

Technical Field

[0001] This invention relates to the field of aviation environmental engineering and thermal protection technology, and more specifically, to a control method and system for aircraft air conditioning. Background Technology

[0002] Currently, civil aircraft air conditioning systems employ a three-stage cooling system to meet the cabin's requirements for temperature, humidity, and fresh air volume, ensuring the safety and comfort of passengers, pilots, and flight attendants. Aircraft air conditioning systems require airflow at specific temperatures, pressures, and flow rates to operate. Stable pressure and temperature ensure efficient and stable system operation, improving aircraft comfort. Aircraft operating environments change drastically, rapidly transitioning from high-temperature, high-pressure ground to low-temperature, low-pressure high-altitude environments. These external environmental changes cause significant fluctuations in the air conditioning system's intake parameters, leading to variations in the outlet parameters. When the controller detects these changes, it adjusts corresponding valves, actuators, and other equipment, resulting in fluctuating air conditioning system operation. Furthermore, the air conditioning system contains numerous monitoring and control devices. When feedback mechanisms malfunction, accurate monitoring of the system and equipment's operational status becomes impossible, leading to incorrect control signal output. Current aircraft control logic typically uses the last correctly fed-back signal as the system's input signal when monitoring equipment malfunctions, controlling the system and maintaining its functionality. In this case, the air conditioning system operates with a fault, making it highly susceptible to failure and unable to maintain the required comfort levels. In addition, large fluctuations in the air intake pressure of the air conditioning system can lead to instability in the operating parameters of the air conditioning system, such as temperature, pressure, and speed, and may also cause the air duct components to become stuck. Summary of the Invention

[0003] This summary is provided to introduce, in a simplified form, some concepts that will be further described in the following detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to help determine the scope of the claimed subject matter.

[0004] The present invention aims to provide a control method and system for aircraft air conditioning.

[0005] According to one aspect of the present invention, a control method for an aircraft air conditioning system is provided, the method comprising: acquiring information including external sensor information of the aircraft, load information of the aircraft, and operating parameters of the aircraft's air conditioning system; determining an optimal control strategy from a plurality of candidate control strategies based on the acquired information and expected operating objectives, each of the candidate control strategies corresponding to a set of control state parameters of the aircraft air conditioning system; and controlling the aircraft air conditioning system based on the control state parameters corresponding to the optimal control strategy.

[0006] According to an embodiment of the present invention, the method may further include: using an intelligent control model to determine an optimal control strategy, wherein the intelligent control model establishes a correspondence between the acquired information and the control state parameters of the aircraft air conditioning system, wherein, when the acquired information changes, the intelligent control model scores different candidate control strategies under different flight states based on the same operational objective, and the optimal control strategy corresponds to the candidate control strategy with the highest score.

[0007] According to one embodiment of the present invention, when a sensor fails, the corresponding control state parameters of the aircraft air conditioning system are selected based on the acquired information and the intelligent control model to control the aircraft air conditioning system.

[0008] According to one embodiment of the present invention, when there is a deviation exceeding a threshold between the real-time measurement value of the sensor and the derived value calculated by the intelligent control model, and the duration of the deviation exceeds a set duration, a sensor malfunction is indicated.

[0009] According to one embodiment of the present invention, when the aircraft is flying along a predetermined route, the control state parameters of the aircraft air conditioning system are pre-set based on the predetermined route and a trained intelligent control model.

[0010] According to one embodiment of the present invention, controlling the aircraft air conditioning system may include: adjusting the opening degree of the flow control valve; adjusting the valve core position of the temperature control valve; and executing an active drive ram air inlet actuator.

[0011] According to one embodiment of the present invention, the information from external sensors of the aircraft may include one or more of the following: atmospheric temperature, atmospheric humidity, weather conditions, flight altitude and radiation intensity, and the load information may include one or more of the following: number of aircraft occupants, set temperature, area temperature, circulating air volume, route information, aircraft operating status and cabin pressure.

[0012] According to one embodiment of the present invention, the operating parameters of the air conditioning system may include one or more of the following: inlet flow rate, inlet pressure, inlet temperature, component outlet temperature, component outlet pressure, and component temperature; and the control status parameters of the air conditioning system may include one or more of the following: flow control valve opening, pressure regulating valve opening, and temperature control valve opening.

[0013] According to another aspect of the present invention, a control system for an aircraft air conditioning system can be provided, the system comprising: an external parameter monitoring module configured to acquire information from external sensors of the aircraft; a system load information module configured to acquire load information of the aircraft; and a controller configured to: determine an optimal control strategy from a plurality of candidate control strategies based on the acquired information and expected operating objectives, each of the candidate control strategies corresponding to a set of control state parameters of the aircraft air conditioning system; and control the aircraft air conditioning system based on the control state parameters corresponding to the optimal control strategy.

[0014] According to another embodiment of the present invention, the controller can be further configured to: use an intelligent control model to determine the optimal control strategy, the intelligent control model establishing a correspondence between the acquired information and the control state parameters of the aircraft air conditioning system, wherein, when the acquired information changes, the intelligent control model scores different candidate control strategies under different flight states based on the same operational objective, and the optimal control strategy corresponds to the candidate control strategy with the highest score.

[0015] Compared with existing solutions, the intelligent control method and system for aircraft air conditioning provided by this invention have at least the following advantages: (1) Identify equipment malfunctions, repair or replace them in a timely manner, and improve system security; (2) Ensure the safety of system operation and avoid the risk of equipment damage; (3) Maintain real-time and accurate control of air conditioning parameters to ensure uninterrupted comfort; (4) Reduce the complexity of emergency response to faults and improve operation and maintenance efficiency.

[0016] These and other features and advantages will become apparent from the following detailed description and with reference to the accompanying drawings. It should be understood that the foregoing general description and the following detailed description are illustrative only and do not limit the scope of the claims. Attached Figure Description

[0017] To gain a more detailed understanding of the manner in which the features of the present invention are described above, reference can be made to various embodiments to provide a more specific description of the above-briefly summarized aspects, some of which are illustrated in the accompanying drawings. However, it should be noted that the drawings illustrate only certain typical aspects of the invention and should not be considered as limiting its scope, as this description may allow for other equivalent and effective aspects.

[0018] Figure 1 This is a schematic diagram of a control method for an aircraft air conditioner according to one aspect of the present invention.

[0019] Figure 2 This is a flowchart of an autonomous learning process for a control method of an aircraft air conditioner according to an embodiment of the present invention.

[0020] Figure 3 This is a schematic diagram of a control system for an aircraft air conditioner according to another aspect of the present invention. Detailed Implementation

[0021] The present invention will now be described in detail with reference to the accompanying drawings, and its features will become further apparent in the following specific description.

[0022] Figure 1 A schematic diagram of a control method 100 for an aircraft air conditioner according to one aspect of the present invention is illustrated. (See attached diagram.) Figure 1 As shown, the intelligent control method 100 for aircraft air conditioning may include acquiring information at point 102, including external sensor information of the aircraft, aircraft load information (e.g., aircraft air conditioning load information), and operating parameters of the aircraft's air conditioning system. External sensor information may include: atmospheric temperature, atmospheric humidity, weather conditions, flight altitude, and radiation intensity, etc. Aircraft load information may include: number of aircraft occupants, set temperature, area temperature, recirculated air volume, flight path information, aircraft operating status, and cabin pressure, etc. Operating parameters of the aircraft's air conditioning system may include: inlet flow rate, inlet pressure, inlet temperature, component outlet temperature, component outlet pressure, and component temperature, etc.

[0023] A smart control method 100 for aircraft air conditioning may include, at point 104, determining an optimal control strategy from a plurality of candidate control strategies based on acquired information and expected operational objectives, each of the candidate control strategies corresponding to a set of control state parameters of the aircraft air conditioning system. According to embodiments of the invention, an intelligent control model can be used to determine the optimal control strategy. This intelligent control model can establish a correspondence between the acquired information and the control state parameters of the aircraft air conditioning system. When the acquired information changes, the intelligent control model can score different candidate control strategies under different flight states based on the same operational objective, with the optimal control strategy corresponding to the candidate control strategy with the highest score. The establishment of the intelligent control model and the correspondence between the acquired information and the control state parameters of the aircraft air conditioning system will be combined... Figure 2 Detailed description.

[0024] Under the condition that the acquired system operation information (including external environmental parameters, load demand, internal status and equipment control status) changes dynamically, the intelligent control model can always use a unified operation objective (such as maintaining the accuracy of the cabin set temperature, ensuring the thermodynamic stability of the system, optimizing the consistency between component outlet temperature and air outlet temperature, etc.) as the evaluation benchmark to score multiple candidate control strategies (e.g., control logic a, control logic b, control logic c) in real time under the current flight state.

[0025] Specifically, the model first constructs a high-dimensional state space based on the current flight conditions (e.g., cruise, climb, descent), external parameters (e.g., temperature, humidity, air pressure, weather), load information (e.g., number of passengers, regional temperature control requirements, flight duration, cabin pressure settings), and real-time feedback from within the system (e.g., inlet / outlet flow, pressure, temperature). In this space, each candidate control strategy corresponds to a set of system regulation state parameters and their dynamic response characteristics.

[0026] Subsequently, the model quantitatively evaluates the expected performance of each strategy under this specific state using a pre-defined objective function (e.g., minimizing the deviation between the set temperature and the actual temperature, minimizing the outlet temperature fluctuation rate, maximizing the system energy efficiency ratio, and ensuring the pressure gradient safety margin). The evaluation process can be implemented using methods such as simulation prediction, historical data backtesting, or reinforcement learning value networks.

[0027] After each multi-strategy comparison, if strategy a outperforms strategy b in terms of target achievement, strategy a's cumulative "control logic evaluation score" increases by 1 point; if strategy a also outperforms strategy c, strategy a gains another point. Through repeated verification and scoring accumulation using a large number of flight state samples (covering different altitudes, speeds, weather conditions, and load combinations), a stable score ranking will be formed for each control strategy. Ultimately, under any new operating condition, the model can directly select the strategy with the highest current score as the optimal control scheme for execution.

[0028] Therefore, this mechanism not only achieves the adaptive capability of "maintaining consistency of objectives under information changes", but also continuously optimizes control decisions through data-driven methods, enabling the system to maintain high stability, high comfort and high energy efficiency in complex and ever-changing aviation environments.

[0029] In one embodiment of the invention, multiple candidate control strategies can be generated based on the current aircraft status (e.g., the aircraft is in the cruise phase, the outside temperature is -50 degrees Celsius, the pressure is 20 kPa, the number of passengers is 150, and the set cabin temperature is 23 degrees Celsius). For example, strategy a: open the large flow valve to increase the component outlet temperature; strategy b: reduce the ram air inlet to reduce the compressor load; strategy c: dynamically adjust the mixing valve ratio. For each strategy, its operating effect is simulated and the results are recorded, such as whether the set temperature is reached quickly; whether cabin temperature fluctuations are small (related to stability); whether the component outlet temperature is within a safe range; and whether the system frequently starts and stops (related to air conditioning lifespan). Subsequently, each strategy is compared and scored based on operating objectives (e.g., set temperature accuracy and system stability). For example, comparing strategy a and strategy b: if strategy a achieves a more stable and faster cabin temperature, strategy a gains 1 point; comparing strategy a and strategy c, if strategy a achieves a better component outlet temperature, strategy a gains 1 point; comparing strategy b and strategy c, if strategy c is more energy-efficient and stable, strategy c gains 1 point. Ultimately, strategy a scores 2 points, strategy b scores 0 points, and strategy c scores 1 point. Strategy a is identified as the optimal control strategy under the current operating conditions.

[0030] In another embodiment of the invention, when external parameters change continuously (e.g., aircraft climb: outside temperature changes from 15 degrees Celsius to -56 degrees Celsius, pressure decreases, etc.), the intelligent control model can record the entire performance of each control strategy (e.g., strategy a, strategy b, strategy c) throughout the entire change process, and compare the comprehensive performance of different strategies across the entire flight profile. For example, which strategy has the smoothest valve action (associated with reduced mechanical wear); which strategy recovers fastest under sudden weather changes; which strategy has the smallest cabin temperature overshoot, etc., and then score the entire control process. For example, if strategy a's comprehensive performance during the entire climb phase is better than strategy b, then strategy a's process control logic gains 1 point. Through multiple flight profile learning sessions, the process control logic with the highest accumulated score is selected as the optimal control logic. This makes the entire control process based on the control trajectory rather than a single-point control command.

[0031] The intelligent control method 100 for aircraft air conditioning may include controlling the aircraft air conditioning system at point 106 based on control state parameters corresponding to the optimal control strategy. Specifically, after determining the optimal control strategy under the current flight conditions (e.g., strategy a mentioned above), the intelligent controller of the aircraft air conditioning system directly maps the set of control state parameters corresponding to the strategy into command outputs to key actuators, thereby achieving active and coordinated control of the following three types of core actuators: 1. Flow control valve (FCV): Based on the bleed air demand and component load specified by the strategy, the opening degree is automatically adjusted to precisely control the engine bleed air flow entering the air conditioning components; 2. Temperature control valve (TAV) dynamically adjusts the hot and cold bypass ratio to bring the module outlet temperature close to the target value; 3. Ram air inlet actuator: Adjusts the opening of the ram air inlet according to the outside temperature, flight speed and heat dissipation requirements to optimize the efficiency of the primary / secondary heat exchangers.

[0032] Figure 2 A flowchart illustrating the autonomous learning process of a control method 200 for aircraft air conditioning according to an embodiment of the present invention is provided. Figure 2 As shown, the control method 200 for aircraft air conditioning begins at 202, acquires atmospheric environmental parameters through external aircraft sensors at 204, acquires thermal load information through the system load information module at 206, acquires internal sensor values ​​through internal sensors of the aircraft air conditioning system at 208, and acquires system regulation status parameters through the air conditioning components at 210. Internal sensor values ​​include, but are not limited to, PIPS inlet pressure sensor, PDPS component outlet pressure sensor, PDTS component outlet temperature sensor, CDTS compressor outlet temperature sensor, PTS component temperature sensor, and PIFS inlet flow sensor. The system's operating parameters correspond to the values ​​acquired by the internal sensors of the aircraft air conditioning system. Regulation status parameters include, but are not limited to, flow control valve (FCV), temperature control valve (TAV), and ram air actuator.

[0033] Control method 200 transmits the parameters collected by the system to the controller via a dedicated data transmission link at point 212. The controller stores these parameters in a local database, forming a historical data ledger, providing basic data support for subsequent intelligent model learning.

[0034] Subsequently, control method 200 proceeds to 214, where, based on the control objective (e.g., the stability of PDPS and PDTS), it autonomously learns external parameters and internal control state parameters to establish an intelligent control model. Specifically, the controller, based on the historical big data stored in step 212, uses "system stability meeting standards, accurate component output parameters, and optimal operating efficiency" as the criteria for judging operational stability. It then uses machine learning algorithms (e.g., random forest algorithm, decision tree algorithm, etc.) to mine data correlation patterns. Specifically, it mines the mapping relationship between external environmental parameters, system load parameters, system operating parameters, and corresponding system control state parameters, ultimately generating an intelligent control model for the air conditioning system that can adapt to different operating conditions.

[0035] Then, the control method proceeds to step 216, primarily using an intelligent control model to monitor sensor status in real time and continuously refine and optimize the intelligent model. Specifically, during the establishment of the intelligent control model, control method 200 adopts a transitional strategy of "parallel traditional control and intelligent control": First, relying on the device's existing traditional control logic, the actions of actuators such as FCV, TAV, and ram air actuators are controlled by real-time monitoring of parameters fed back from sensors to ensure the basic operational requirements of the system; simultaneously, external parameters, system load information, and system operating parameters are input variables into the intelligent control model. The model generates corresponding control commands through its built-in control law and synchronously compares these commands with the control signals output by the traditional control logic and the actual state parameters monitored by the sensors. If the control commands output by the intelligent model cause system parameter deviations to exceed the allowable range, the model parameters are immediately adjusted until the matching degree between the model output and the actual requirements is met.

[0036] Then, control method 200 proceeds to 218, where the status parameters are compared over a long period of time to ensure consistency, and the device is operated using the intelligent model control. Specifically, control method 200 enters the "intelligent model verification and switching" stage: through long-term monitoring (e.g., continuous operation ≥72 hours), if the control commands output by the intelligent control model and the corresponding actuator status parameters remain consistent with the control signals output by the traditional control logic and the system status parameters monitored in real time by sensors (e.g., cabin temperature, pressure, air conditioning component outlet pressure), then the control mode dominated by the intelligent control model can be switched. In this mode, the air conditioning system will still monitor the internal and external state parameters of the cabin in real time through sensors (e.g., changes in heat load caused by passenger increases or decreases, sudden changes in outside air temperature, etc.), and continuously correct and optimize the intelligent control model based on these parameters. For example, when the external parameters (e.g., air temperature) are the same, if the system detects different control information (e.g., the cabin temperature adjustment effect corresponding to two different TAV openings), it will select the better control strategy by comparing the three indicators of "adjustment speed, energy consumption level, and system stability" and update it in the intelligent control model. At the same time, the traditional control logic will not stop running, but will run synchronously as "backup monitoring logic" and compare it with the output of the intelligent control model in real time. If an anomaly is found in the intelligent control model (e.g., the output command causes the system parameters to exceed the tolerance), the correction mechanism will be triggered immediately to adjust the model, or in extreme cases, it will switch back to the traditional control logic. When the system runs continuously (e.g., system uptime ≥ 168 hours, 7 days) and the output information of the intelligent control model is identical to that of the traditional control logic, it can be determined that the intelligent control model has independent operating capability. At this point, the active control function of the traditional control logic can be stopped, retaining only its monitoring and backup function, and the intelligent control model can independently control the air conditioning system under all operating conditions. The method ends at step 220.

[0037] As mentioned above, the aircraft air conditioning system can be controlled directly based on the intelligent control model without the need for gradual feedback from the outside to the inside of the system. This allows for early prediction of the stable state of the aircraft air conditioning system, enabling it to reach a stable state more quickly. At the same time, the intelligent control model can reduce the signal acquisition frequency of the aircraft's own sensors, lower the sensor development assurance level and reliability requirements, and when a sensor fails, the intelligent control model can also automatically control the stable operation of the aircraft air conditioning system.

[0038] Figure 3 A schematic diagram of an aircraft air conditioning system 300 according to another aspect of the present invention is provided. Figure 3 As shown, the entire aircraft air conditioning system 300 may include external aircraft sensors 302, load information module 304, controller, PIPS, PIFS, PITS, PDPS, PDTS, CDTS, PTS, FCV, and air conditioning components (e.g., including primary heat exchanger, main heat exchanger, ram air actuator, air circulator, temperature control valve, regenerator, condenser, air-water separator, water jet, etc.).

[0039] The aircraft external sensor 302 is mainly used to monitor atmospheric temperature, humidity, weather conditions, flight altitude (external pressure), radiation intensity, etc. The load information module 304 is mainly used to set the number of aircraft occupants, temperature settings, area temperature monitoring, airflow, flight path information, aircraft operating status, cabin pressure, etc. The aircraft external sensor 302 and load information module 304 are essential components of the air conditioning intelligent control system, providing the various parameters required by the intelligent control system.

[0040] While the aircraft is performing its designated route mission, the system continuously acquires the following three types of parameters: external environmental parameters (e.g., ambient temperature, static pressure, total pressure, humidity, solar radiation intensity, weather type, flight altitude, airspeed, etc.); mission and crew setting parameters (e.g., cabin target temperature, estimated crew number, flight phase, remaining range, route geographic information, etc.); and the system's current internal status (e.g., component outlet temperature, component outlet pressure, ram air inlet flow rate, reheater temperature, mixing chamber pressure, actual temperature in each area, current valve position, compressor speed, etc.).

[0041] The system will combine the current real-time parameters P current The input is fed into a pre-trained intelligent control model. This model internally stores a massive amount of learned operating condition samples. Each sample can contain: an input feature vector X = [external environment + settings + internal parameters]; a set of candidate control strategies {a, b, c, ...}; and the cumulative win scores of each strategy (e.g., strategy a: 87 points, strategy b: 62 points, strategy c: 45 points). The system finds the nearest neighbor (k-NN) match between P and the target system using nearest neighbor search (k-NN) or clustering matching.current The most recent historical operating conditions are selected. From these matched historical conditions, the comprehensive score of each control strategy is extracted, and strategy a is selected as the current optimal control logic. Strategy a is not a fixed instruction, but rather a set of parameterized control rules. For example, when the component outlet temperature is <85 degrees Celsius and the cabin temperature deviation is >+1 degree Celsius, the flow valve is opened by 5%, while the ram air actuator is fine-tuned to 70% opening. Furthermore, new operating data can be recorded for subsequent offline learning and updating of the intelligent control model.

[0042] As described above, the controller in the aircraft air conditioning system takes "system stability compliance, accurate component output parameters, and optimal operating efficiency" as its core autonomous learning objectives. By establishing an intelligent control model, it correlates and maps the input parameters of the external parameter monitoring module, the input parameters of the system load information module, the system operating parameters, and the system control state parameters. It selects the control strategy with the highest cumulative score using the optimal control strategy selection method described above, and then uses the control state parameters corresponding to the optimal control strategy to control the aircraft air conditioning system.

[0043] After the aircraft air conditioning system completes a full flight cycle, it has compared the effectiveness of various candidate control strategies against thousands of combinations of state parameters covering different flight phases (e.g., takeoff, cruise, descent), different external environments (e.g., high temperature and humidity, low temperature and low pressure, high-altitude jet streams), and different cabin loads (e.g., full / half-capacity, full / partial operation of electronic equipment, changes in cargo hold refrigeration requirements). The controller will automatically calculate the cumulative evaluation score of each candidate control strategy throughout the entire cycle, forming a quantitative scoring matrix. Through hierarchical analysis of the scoring results, it can accurately identify control state parameter combinations that meet core objectives such as "system stability compliance, accurate component output parameters, and optimal operating efficiency" in various sub-scenarios.

[0044] These optimal control parameters, validated across the entire route, will be stored as baseline templates. In subsequent missions on the same or similar routes, the controller can directly call the matching parameter template as the initial control scheme. Combined with real-time status, the controller will select the control state parameters corresponding to the highest-scoring control strategy according to preset scoring rules to control the air conditioning system. This will significantly improve the response speed and control accuracy of the air conditioning system, providing reliable data support and decision-making basis for cabin comfort, equipment operation safety, and operational economy.

[0045] According to an embodiment of the present invention, during normal system operation, when the external environmental parameters, system load information, core operating parameters of the air conditioning system, and system control status parameters are all in a mutually matched and coordinated state, and conform to the association logic preset by the intelligent control model, if there is a significant deviation between the real-time measurement value of a certain sensor (e.g., an inlet temperature sensor, pressure sensor, or flow sensor) and the theoretical derivation value calculated by the intelligent control model based on the current overall parameter coupling relationship (e.g., the deviation exceeds a preset threshold), and the deviation continues for more than a set time (e.g., 3 minutes), while excluding factors such as signal transmission interference, it can be determined that the sensor has a measurement deviation and the sensor is faulty.

[0046] Specifically, during normal system operation, the controller can continuously run two sets of state estimation paths in parallel: 1. Actual measurement path: Directly read the raw signals from each sensor (e.g., T). sensor =Component outlet temperature probe reading); 2. Intelligent Control Model Prediction Path: Input identical current input conditions (e.g., external atmospheric parameters (from ADIRU), aircraft operating status (from FMS), crew numbers and cabin temperature settings (from cabin management system), and all current valve control commands (FCV / TAV feedback values)) into the intelligent control model, and output the predicted value T. comp_out Then, the controller calculates the residual: R=|T comp_out -T sensor | If R>δ threshold (For example, δ) threshold If the temperature deviation exceeds 5 degrees Celsius and persists for more than N sampling periods (e.g., N=3 to prevent misjudgment due to transient interference), and other relevant sensors do not issue conflicting alarms (e.g., pressure and flow data are reasonable), then the system can determine that the sensor has a "measurement deviation" or "slow drift" fault. At this time, the system can trigger maintenance code and display "Air conditioning sensor data abnormal" on the human-machine interface.

[0047] According to another embodiment of the present invention, when the system detects a failure of a critical sensor (e.g., a temperature, pressure, or flow sensor) (e.g., signal interruption, continuous data exceeding limits, or deviation exceeding acceptable range and unable to be corrected through self-calibration), the system will immediately activate the sensor failure emergency control mechanism. At this time, the controller will retrieve the core parameters of the current operating state in real time and, in conjunction with the intelligent control model that has been trained and optimized through full-line data, automatically generate an alternative control scheme.

[0048] Specifically, when the system detects T sensorWhen the signal remains at 0, exceeds the physical range, or a communication timeout occurs, and residual detection simultaneously detects a discrepancy between the measured value and the predicted value T... comp_out If the deviation exceeds the threshold and the duration exceeds the preset value, the system determines T. sensor If a sensor fails, it is logically isolated from the control loop. The controller can immediately initiate sensorless state estimation, such as real-time calculation of T based on other reliable inputs. comp_out For example, based on the current operating conditions (e.g., temperature -56 degrees Celsius, flight altitude FL370, passenger capacity 185, set temperature 22 degrees Celsius), the T output by the intelligent control model... comp_out The temperature is 203 degrees Celsius, which matches the component outlet temperature in high-altitude, low-temperature environments. Therefore, the controller can adjust the temperature (T)... comp_out Treating the system as an analog sensor, the system is fed into the optimal control strategy selection engine to compare candidate strategies and obtain the candidate strategy with the highest score through scoring. Subsequently, the controller sends the air conditioning control state parameters corresponding to the highest-scoring candidate control strategy (the optimal control strategy) to the actuator to enable the air conditioner to operate autonomously in the event of sensor failure.

[0049] This control scheme will accurately calculate the system control parameters that match the current state based on the learning results of the intelligent control model from similar historical operating conditions, achieving sensorless control of the air conditioning components. This mechanism not only effectively reduces system parameter fluctuations caused by sensor failure, preventing a sudden drop in cabin comfort, but also ensures stable operation of the air conditioning system even in the event of critical sensor failure, preventing safety hazards such as component overheating and overpressure caused by parameter malfunctions. Thus, while ensuring flight safety, it also maintains cabin comfort and system reliability.

[0050] The foregoing description includes examples of various aspects of the claimed subject matter. It is certainly impossible to describe every conceivable combination of components or methods for the purpose of depicting the claimed subject matter, but those skilled in the art will recognize that many further combinations and arrangements of the claimed subject matter are possible. Thus, the disclosed subject matter is intended to cover all such changes, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A control method for an aircraft air conditioner, the method comprising: Acquire information, including external sensor information of the aircraft, load information of the aircraft, and operating parameters of the aircraft's air conditioning system; The optimal control strategy is determined from multiple candidate control strategies based on the acquired information and expected operational objectives. Each of the candidate control strategies corresponds to a set of control state parameters of the aircraft air conditioning system. as well as The aircraft air conditioning system is controlled based on the regulation state parameters corresponding to the optimal control strategy.

2. The method of claim 1, further comprising: An intelligent control model is used to determine the optimal control strategy. The intelligent control model establishes a correspondence between the acquired information and the control state parameters of the aircraft air conditioning system. When the acquired information changes, the intelligent control model scores different candidate control strategies under different flight states based on the same operational objective. The optimal control strategy corresponds to the candidate control strategy with the highest score.

3. The method as described in claim 2, characterized in that, When the sensor fails, the corresponding control state parameters of the aircraft air conditioning system are selected based on the acquired information and the intelligent control model to control the aircraft air conditioning system.

4. The method as described in claim 2, characterized in that, When there is a deviation exceeding a threshold between the real-time measurement value of the sensor and the derived value calculated by the intelligent control model, and the duration of the deviation exceeds a set time, a sensor malfunction is indicated.

5. The method as described in claim 2, characterized in that, When the aircraft flies along a predetermined route, the control parameters of the aircraft's air conditioning system are pre-set based on the predetermined route and the trained intelligent control model.

6. The method as described in claim 1, characterized in that, Controlling the aircraft air conditioning system includes: adjusting the opening degree of the flow control valve; adjusting the valve core position of the temperature control valve; and actuating the active drive of the ram air inlet actuator.

7. The method as described in claim 1, characterized in that, The information from external aircraft sensors includes one or more of the following: atmospheric temperature, atmospheric humidity, weather conditions, flight altitude, and radiation intensity; the load information includes one or more of the following: number of aircraft occupants, set temperature, area temperature, circulating air volume, route information, aircraft operating status, and cabin pressure.

8. The method as described in claim 1, characterized in that, The operating parameters of the air conditioning system include one or more of the following: inlet flow rate, inlet pressure, inlet temperature, component outlet temperature, component outlet pressure, and component temperature. The control status parameters of the air conditioning system include one or more of the following: flow control valve opening, pressure regulating valve opening, and temperature control valve opening.

9. A control system for an aircraft air conditioning system, the system comprising: An external parameter monitoring module is configured to acquire information from external sensors of the aircraft. A system load information module, configured to acquire aircraft load information; as well as The controller is configured to: The optimal control strategy is determined from multiple candidate control strategies based on the acquired information and expected operational objectives. Each of the candidate control strategies corresponds to a set of control state parameters of the aircraft air conditioning system. as well as The aircraft air conditioning system is controlled based on the regulation state parameters corresponding to the optimal control strategy.

10. The control system of claim 9, wherein the controller is further configured to: An intelligent control model is used to determine the optimal control strategy. The intelligent control model establishes a correspondence between the acquired information and the control state parameters of the aircraft air conditioning system. When the acquired information changes, the intelligent control model scores different candidate control strategies under different flight states based on the same operational objective. The optimal control strategy corresponds to the candidate control strategy with the highest score.

Images