Aero-engine self-adaptive intelligent control system and method based on multi-mode perception

Abstract

The invention discloses an aero-engine adaptive intelligent control system and method based on multi-mode perception, and the system comprises an instruction generator, an adaptive controller, a time disturbance observer, a multi-model sensor, a parameter estimator, and a data cloud platform. The controller is used for generating a dynamic instruction signal meeting index requirements according to a control target set by a system, and the dynamic instruction signal has a preset rotating speed tracking trajectory characteristic so as to guide rotating speed adjustment of an engine; the input module is used for inputting an output control quantity of the self-adaptive specified interference elimination composite controller, a state feedback value representing the rotating speed of an aero-engine shaft and a system output quantity; according to the method, internal and external interference factors of the aero-engine system can be rapidly and accurately described and compensated, compared with a traditional observer, the method has determined convergence time and better dynamic performance, and therefore it is ensured that the system can still operate stably when facing complex interference.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive intelligent control systems, and in particular to an adaptive intelligent control system and method for an aero-engine based on multimodal perception. Background Art

[0002] Existing domestic and international aircraft engine correction technologies mainly focus on component characteristic correction based on steady-state operating points. That is, for a given steady-state operating point, a variety of solution methods are used to adjust the correction parameters. To a certain extent, this type of correction process is the optimization process of the steady-state model parameters. For the transition state of the aircraft engine, the current common method is still based on the steady-state operating point model and uses an interpolation algorithm to approximate the transition state process. Due to the small number of characteristic steady-state operating points and the large interpolation error, the dynamic response error of the model is large. The above-mentioned model correction method is difficult to solve the accuracy problem of the key output parameters of the transition state process within the full envelope. In addition, the number of health parameters involved in the aircraft engine model is far greater than the key measurable parameters of the aircraft engine. In actual engineering applications, only health parameters equivalent to the number of key measurable parameters are often selected for adaptive adjustment.

[0003] In Chinese patent 201910522225.6, only aircraft engine faults are monitored. This approach ignores the positive effects that certain interferences may have under specific conditions. When an aircraft engine operates under different operating conditions, certain external disturbances may have a certain positive effect on the closed-loop performance of the system, especially in improving the system response speed and reducing fuel consumption. Therefore, the present invention proposes an aircraft engine adaptive intelligent control system and method based on multimodal perception to solve the problems existing in the prior art. Summary of the Invention

[0004] In response to the above problems, the purpose of the present invention is to propose an adaptive intelligent control system and method for aircraft engines based on multimodal perception. The adaptive intelligent control system and method for aircraft engines based on multimodal perception can quickly and accurately describe and compensate for internal and external interference factors of the aircraft engine system. Compared with traditional observers, it has a certain convergence time and better dynamic performance, thereby ensuring that the system can still maintain stable operation in the face of complex interference. It uses multiple sensors to collect multi-dimensional data of the engine and provide comprehensive engine status perception.

[0005] To achieve the purpose of the present invention, the present invention is implemented through the following technical solutions: an adaptive intelligent control system and method for an aircraft engine based on multimodal perception, including a command generator, an adaptive controller, a time disturbance observer, a multi-model sensor, a parameter estimator and a data cloud platform;

[0006] An instruction generator is used to generate a dynamic instruction signal that meets the index requirements according to the control target set by the system, and the dynamic instruction signal has a preset speed tracking trajectory characteristic to guide the speed regulation of the engine;

[0007] An adaptive controller is configured to input an output control variable of an adaptive specified interference cancellation composite controller, a state feedback value representing the shaft speed of the aircraft engine, and a system output, and estimate the lumped interference in real time within a fixed time based on the state feedback information of the aircraft engine and the output control command of the controller;

[0008] The time disturbance observer realizes the observation and real-time estimation of the aggregate disturbance within a fixed time by extending the state observation method;

[0009] Multi-model sensors, including temperature sensors, pressure sensors, vibration sensors, and sound sensors, are used to monitor various physical and chemical parameters of the engine in real time;

[0010] a parameter estimator for observing model parameters, wherein the parameter estimator has three input terminals respectively connected to a system input port, a system output port, and a time disturbance observer of the aircraft engine, and an output terminal connected to the adaptive controller for outputting estimated values ​​of the model parameters;

[0011] The data cloud platform uploads the collected data to the cloud platform for storage and backup, performs remote analysis, and uses cloud computing resources to perform big data analysis and processing to collect and use engine information.

[0012] A further improvement is that the instruction generator converts the decisions in the system into actual control actions, which are used to adjust the fuel flow, change the angle of the turbine blades and adjust the speed of the compressor. According to the real-time status of the engine and changes in the external environment, the instruction generator dynamically adjusts the control parameters.

[0013] Further improvements are as follows: the adaptive controller combines the total interference estimate of the dynamic instruction set of the instruction generator and the state feedback information of the aircraft engine, adjusts the control quantity in real time based on the backstepping method and the dynamic inverse method, and combines the adaptive specified interference elimination method to generate adaptive control instructions through real-time estimation and feedback compensation of the total interference and output them to the aircraft engine.

[0014] A further improvement is that the time disturbance observer estimates and compensates for the disturbances and uncertainties in the system that change over time. The disturbances include changes in the external environment, fluctuations in internal system parameters, and sensor noise. The time disturbance observer estimates the disturbance signal in the system that changes over time in real time. The time disturbance observer feeds back the estimated disturbance signal to the control system, enabling the controller to dynamically adjust the control instructions to compensate for the impact of the disturbance.

[0015] Further improvements are: the multi-model sensor provides comprehensive data input, enabling the system to more accurately monitor and analyze the engine status. The data from different sensors can be verified with each other, thereby improving the system's confidence in the engine status judgment and reducing false alarms and missed alarms. Different sensors have different sensitivities to environmental changes, and the multi-model sensor combination can be effectively monitored in different environments.

[0016] A further improvement is that the parameter estimator analyzes the sensor data to calibrate the system model to ensure that the model accurately reflects the working state of the engine. During the operation of the system, the parameter estimator updates the parameter values ​​in real time.

[0017] Further improvements include: the data cloud platform provides a central repository for storing various sensor data from aircraft engines, including temperature, pressure, vibration and sound. Multimodal data allows data to be securely stored, managed and retrieved. The data cloud platform processes and analyzes large amounts of sensor data in real time, providing immediate insights and feedback.

[0018] A further improvement is that the output end of the instruction generator is connected to the input end of the adaptive controller.

[0019] A further improvement is that the fixed-time disturbance observer has its input end connected to the output end of the adaptive controller and the state feedback end and system output end of the downstream aircraft engine respectively.

[0020] Further improvement is: comprising the following steps:

[0021] Step 1: Model the aircraft engine through the system, input and output data, and build an affine nonlinear data model with disturbance through system identification method;

[0022] Step 2: Generate command tracking through the model. By adjusting and arranging the process links, the system generates a command that meets the preset control indicators and calculates the time derivative of the command to ensure that the system's dynamic response under different working conditions can maintain good tracking performance.

[0023] Step 3: After the time differentiation is completed, fixed-time interference observation is performed to observe and estimate the aggregate interference in real time within a fixed time to obtain the estimated value of the aggregate interference;

[0024] Step 4: Perform adaptive specified disturbance elimination composite control calculations using estimated values, design virtual control variables using nonlinear backstepping, and control the system based on system error feedback and dynamic command signals using nonlinear backstepping.

[0025] Step 5: Judge the system control and use closed-loop control to determine whether the command to end control is received. If so, end the control. If not, jump to the command tracking link for loop execution and continue tracking control and interference estimation.

[0026] The beneficial effects of the present invention are as follows: through the mutual coordination between the instruction generator, adaptive controller, time disturbance observer, multi-model sensor, parameter estimator and data cloud platform, the present invention can quickly and accurately describe and compensate for internal and external interference factors of the aircraft engine system. Compared with traditional observers, it has a certain convergence time and better dynamic performance, thereby ensuring that the system can still maintain stable operation in the face of complex interference. It uses multiple sensors to collect multi-dimensional data of the engine, providing comprehensive engine state perception, which helps to more accurately monitor and diagnose the health status of the engine, monitor the key parameters of the engine in real time, analyze the data through intelligent algorithms, promptly discover anomalies and potential faults, perform fault diagnosis and early warning, improve the robustness and reliability of the control system, take into account both dynamic and static performance and robustness, and thus have good control performance. During dynamic changes, the system can quickly adjust and adapt to interference, thereby reducing steady-state errors and improving control stability and accuracy. It exhibits good dynamic and static performance under different working conditions, especially outstanding performance when facing complex and nonlinear disturbances, ensuring efficient and accurate control performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 A schematic diagram of the system of the present invention;

[0029] Figure 2 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0031] In the description of the present invention, it should be noted that, unless otherwise specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0032] In document 201910522225.6, the status of the aircraft engine is comprehensively evaluated. Compared with the previous single vibration signal analysis, the specific performance is analyzed by adding the step of collecting acoustic emission data, and monitoring the early fault signals of the aircraft engine based on the acoustic emission data; the intelligent monitoring method has enhanced perception ability, the fault signal frequency that can be monitored is wider, and the system has stronger noise resistance. However, in this application, the traditional control method's indiscriminate treatment of interference is broken. Through dynamic observation of interference, the beneficial effect of the lumped interference in the aircraft engine system on tracking control is fully utilized, and the convergence speed of the closed-loop system is improved. It not only improves the system's tracking accuracy of the target instruction, but also takes into account the static characteristics, which can indirectly improve the engine control system design and parameter debugging effect.

[0033] according to Figure 1 、 Figure 2 As shown, this embodiment provides an adaptive intelligent control system and method for an aircraft engine based on multimodal perception, including a command generator, an adaptive controller, a time disturbance observer, a multi-model sensor, a parameter estimator, and a data cloud platform;

[0034] The command generator is used to generate a dynamic command signal that meets the index requirements according to the control target set by the system. The dynamic command signal has a preset speed tracking trajectory characteristic to guide the speed regulation of the engine;

[0035] An adaptive controller is configured to input an output control variable of an adaptive specified interference cancellation composite controller, a state feedback value representing the shaft speed of the aircraft engine, and a system output, and estimate the lumped interference in real time within a fixed time based on the state feedback information of the aircraft engine and the output control command of the controller;

[0036] The time disturbance observer realizes the observation and real-time estimation of the aggregate disturbance within a fixed time by extending the state observation method;

[0037] Multi-model sensors, including temperature sensors, pressure sensors, vibration sensors, and sound sensors, are used to monitor various physical and chemical parameters of the engine in real time;

[0038] a parameter estimator for observing model parameters, wherein the parameter estimator has three input terminals respectively connected to a system input port, a system output port, and a time disturbance observer of the aircraft engine, and an output terminal connected to the adaptive controller for outputting estimated values ​​of the model parameters;

[0039] The data cloud platform uploads the collected data to the cloud platform for storage and backup, performs remote analysis, and uses cloud computing resources to perform big data analysis and processing to collect and use engine information.

[0040] The command generator converts decisions in the system into actual control actions, which are used to adjust fuel flow, change the angle of turbine blades and adjust the speed of the compressor. According to the real-time status of the engine and changes in the external environment, the command generator dynamically adjusts the control parameters to ensure that the engine operates in the best condition. When the system detects an abnormal fault, the command generator generates emergency control commands, including reducing power and switching to the backup system.

[0041] The adaptive controller combines the total disturbance estimation value of the dynamic instruction set of the instruction generator and the state feedback information of the aircraft engine, adjusts the control quantity in real time based on the backstepping method and the dynamic inverse method, and combines the adaptive specified disturbance elimination method to generate adaptive control instructions through real-time estimation and feedback compensation of the total disturbance and output them to the aircraft engine, realizing real-time tracking control of the aircraft engine speed and adaptive elimination of specified disturbance.

[0042] The time disturbance observer estimates and compensates for the time-varying disturbances and uncertainties in the system. These disturbances include changes in the external environment, fluctuations in the system's internal parameters, and sensor noise. The time disturbance observer estimates the time-varying disturbance signal in the system in real time and feeds the estimated disturbance signal back to the control system, enabling the controller to dynamically adjust the control instructions to compensate for the impact of the disturbance. Through disturbance estimation and compensation, the time disturbance observer improves the robustness of the system, enabling the system to maintain stable performance in the face of uncertainty and disturbances.

[0043] Multi-model sensors provide comprehensive data input, enabling the system to more accurately monitor and analyze the status of the engine. Data from different sensors can be verified with each other, improving the system's confidence in judging the engine status and reducing false alarms and missed alarms. Different sensors have different sensitivities to environmental changes. Multi-model sensor combinations are used for effective monitoring in different environments. Temperature sensors are used to measure the temperature inside and outside the engine, including the combustion chamber, turbine and compressor. Pressure sensors are used to measure the pressure in the engine intake and exhaust ducts, fuel system and hydraulic system. By monitoring the pressure, it is ensured that the pressure of each part of the engine is within the normal range to avoid performance degradation due to abnormal pressure. Vibration sensors are used to detect the vibration level of the engine, which helps to monitor the structural integrity and mechanical health of the engine. Abnormal vibration modes indicate wear and imbalance of engine components. At the same time, vibration sensors provide early warning functions. Sound sensors are used to measure the noise level generated by the engine, which helps to evaluate the engine's operating status and potential mechanical problems.

[0044] The parameter estimator analyzes sensor data and calibrates the system model to ensure that the model accurately reflects the operating status of the engine. During system operation, the parameter estimator updates the parameter values ​​in real time to adapt to changes in the engine status and external environment. Accurate parameter estimation helps improve the accuracy of the control system and enables the controller to more effectively adjust the engine's operating parameters.

[0045] The data cloud platform provides a central repository for storing various sensor data from aircraft engines, including temperature, pressure, vibration, and sound. Multimodal data allows data to be securely stored, managed, and retrieved. The data cloud platform processes and analyzes large amounts of sensor data in real time, providing immediate insights and feedback, which is critical for monitoring engine performance and responding to potential problems in a timely manner. Leveraging cloud computing resources, the data cloud platform can perform complex computing tasks, including training and inference of machine learning models, without the need to install additional hardware on the aircraft. The platform promotes data sharing and collaboration, allowing maintenance personnel to access and analyze data across regions and work together to optimize engine performance and maintenance plans.

[0046] The output terminal of the command generator is connected to the input terminal of the adaptive controller.

[0047] The fixed-time disturbance observer has its input terminal connected to the output terminal of the adaptive controller and the state feedback terminal of the downstream aircraft engine and the system output terminal respectively.

[0048] The following steps are involved:

[0049] Step 1: Model the aircraft engine through the system, input and output data, and build an affine nonlinear data model with disturbance through system identification method;

[0050] Step 2: Generate command tracking through the model. By adjusting and arranging the process links, the system generates a command that meets the preset control indicators and then differentiates the command with respect to time to ensure that the system's dynamic response under different working conditions can maintain good tracking performance.

[0051] Step 3: After the time differentiation is completed, fixed-time interference observation is performed to observe and estimate the aggregate interference in real time within a fixed time to obtain the estimated value of the aggregate interference;

[0052] Step 4: Perform adaptive specified disturbance elimination composite control calculations using estimated values, design virtual control variables using nonlinear backstepping, and control the system based on system error feedback and dynamic command signals using nonlinear backstepping.

[0053] Step 5: Judge the system control and use closed-loop control to determine whether the command to end control has been received. If so, end the control. If not, jump to the command tracking link for loop execution and continue tracking control and interference estimation to ensure that the engine maintains stable performance control under complex working conditions.

[0054] This multimodal sensing-based adaptive intelligent control system and method for aircraft engines utilizes the beneficial effect of lumped disturbances in aircraft engine systems on tracking control, improves the convergence speed of closed-loop systems, and takes into account static characteristics, including static error and control ripple. By benefiting from beneficial disturbances and compensating for adverse disturbances, superior speed tracking control performance of aircraft engines is achieved, realizing adaptive intelligent control.

[0055] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive intelligent control system for aircraft engines based on multimodal perception, characterized by: Including command generator, adaptive controller, time disturbance observer, multi-model sensor, parameter estimator and data cloud platform; An instruction generator is used to generate a dynamic instruction signal that meets the index requirements according to the control target set by the system, and the dynamic instruction signal has a preset speed tracking trajectory characteristic to guide the speed regulation of the engine; An adaptive controller is configured to input an output control variable of an adaptive specified interference cancellation composite controller, a state feedback value representing the shaft speed of the aircraft engine, and a system output, and estimate the lumped interference in real time within a fixed time based on the state feedback information of the aircraft engine and the output control command of the controller; The time disturbance observer realizes the observation and real-time estimation of the aggregate disturbance within a fixed time by extending the state observation method; Multi-model sensors, including temperature sensors, pressure sensors, vibration sensors, and sound sensors, are used to monitor various physical and chemical parameters of the engine in real time; a parameter estimator for observing model parameters, wherein the parameter estimator has three input terminals respectively connected to a system input port, a system output port, and a time disturbance observer of the aircraft engine, and an output terminal connected to the adaptive controller for outputting estimated values ​​of the model parameters; The data cloud platform uploads the collected data to the cloud platform for storage and backup, conducts remote analysis, and uses cloud computing resources to perform big data analysis and processing to collect and summarize engine information.

2. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1 is characterized by: The command generator converts the decisions in the system into actual control actions, which are used to adjust the fuel flow, change the angle of the turbine blades, and regulate the speed of the compressor.

3. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1 is characterized by: The adaptive controller combines the total disturbance estimation value of the dynamic instruction set of the instruction generator and the state feedback information of the aircraft engine to adjust the control quantity in real time based on the backstepping method and the dynamic inverse method.

4. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1, characterized in that: The temporal disturbance observer estimates and compensates for disturbances and uncertainties that vary with time in the system. Disturbances include changes in the external environment, fluctuations in system internal parameters, and sensor noise. The temporal disturbance observer estimates the disturbance signal that varies with time in the system in real time.

5. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1 is characterized in that: The multi-model sensor provides comprehensive data input, enabling the system to more accurately monitor and analyze the engine status. The data from different sensors can verify each other, thereby improving the system's confidence in the engine status judgment and reducing false alarms and missed alarms. Different sensors have different sensitivities to environmental changes.

6. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1, characterized in that: The parameter estimator analyzes the sensor data and calibrates the system model to ensure that the model accurately reflects the working state of the engine. During the operation of the system, the parameter estimator updates the parameter values ​​in real time.

7. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1, characterized in that: The data cloud platform provides a central repository for storing various sensor data from aircraft engines, including temperature, pressure, vibration and sound. Multimodal data enables data to be securely stored, managed and retrieved. The data cloud platform processes and analyzes large amounts of sensor data in real time, providing immediate insights and feedback.

8. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1, characterized in that: The output end of the instruction generator is connected to the input end of the adaptive controller.

9. The aircraft engine adaptive intelligent control system based on multimodal perception according to claim 1, characterized in that: The input end of the fixed-time disturbance observer is respectively connected to the output end of the adaptive controller and the state feedback end and system output end of the downstream aircraft engine.

10. The method for an aircraft engine adaptive intelligent control system applied to multimodal perception according to claims 1-9, characterized in that: The following steps are involved: Step 1: Model the aircraft engine through the system, input and output data, and build an affine nonlinear data model with disturbance through system identification method; Step 2: Generate command tracking through the model. By adjusting and arranging the process links, the system generates a command that meets the preset control indicators and calculates the time derivative of the command to ensure that the system's dynamic response under different working conditions can maintain good tracking performance. Step 3: After the time differentiation is completed, fixed-time interference observation is performed to observe and estimate the aggregate interference in real time within a fixed time to obtain the estimated value of the aggregate interference; Step 4: Perform adaptive specified disturbance elimination composite control calculations using estimated values, design virtual control variables using nonlinear backstepping, and control the system based on system error feedback and dynamic command signals using nonlinear backstepping. Step 5: Judge the system control and use closed-loop control to determine whether the command to end control is received. If so, end the control. If not, jump to the command tracking link for loop execution and continue tracking control and interference estimation.

Images