Pressure sensor intelligent compensation device and method suitable for aviation multi-medium environment

Abstract

The invention provides a pressure sensor intelligent compensation device and method suitable for an aviation multi-medium environment, and belongs to the technical field of aircraft detection. The pressure sensor intelligent compensation device comprises a data acquisition system and a control system, the data acquisition system simulates the liquid medium environment and the temperature and pressure environment of each subsystem of an airplane and acquires data, the control system controls the data acquisition system to reach the required environment condition, and a dynamic compensation model is carried in the control system. And the dynamic compensation model takes the medium type, the actual temperature value and the output value of the to-be-compensated pressure sensor as training set input values, takes the actual pressure value as the output value, trains the dynamic compensation model in the control system, and finally realizes the compensation of the pressure sensor. According to the invention, the pressure sensor can still maintain the high-precision measurement capability in various complex environments, and the reliability and safety of an aircraft system are remarkably improved.

Description

Technical Field

[0001] The invention belongs to the technical field of aircraft detection, and relates to an intelligent compensation device and method for a pressure sensor suitable for an aviation multi-media environment. Background Art

[0002] In the high-performance operation of aircraft, pressure sensors are one of the key components used to monitor pressure parameters of various systems, such as hydraulic systems, fuel systems, and cooling systems. However, due to the drastic temperature changes experienced by aircraft during flight, the readings of pressure sensors will be significantly affected, resulting in inaccurate measurements. This measurement error caused by environmental changes, if not corrected, may have a serious impact on the safety and performance of the aircraft. The application environment of pressure sensors in aircraft is extremely special: these pressure sensors are installed in different subsystems of the aircraft, and the liquid media used in each subsystem are different. For example, the hydraulic system uses hydraulic oil, the fuel system uses fuel, and the cooling system may use coolant. Each liquid medium has different physical and chemical properties, which further increases the complexity of pressure sensor measurement and calibration. Summary of the invention

[0003] The purpose of the present invention is to provide a pressure sensor intelligent compensation device and method suitable for aviation multi-media environment, which can intelligently compensate the pressure sensors of different subsystems to correct the pressure sensor errors caused by changes in the application environment, and ensure that it can still provide accurate pressure measurement in a variable temperature and medium environment. Aircraft will experience drastic temperature changes during flight, which has a significant impact on the pressure sensors installed in the hydraulic system, fuel system and cooling system. In addition, the liquid media used in each subsystem have different physical and chemical properties, such as hydraulic oil, fuel and coolant, which further increases the complexity of measurement errors. By combining experimental data and deep learning algorithms, the present invention establishes a dynamic compensation model that can correct the sensor output in real time, improve measurement accuracy and system reliability, and provide protection for the safe operation of the aircraft.

[0004] The technical solution adopted by the present invention is as follows:

[0005] A pressure sensor intelligent compensation device suitable for aviation multi-media environment, the pressure sensor intelligent compensation device comprises a data acquisition system and a control system.

[0006] The data acquisition system can simulate the liquid medium environment and temperature and pressure environment of each subsystem of the aircraft, and collect the actual temperature value, actual pressure value and pressure value measured by the pressure sensor to be compensated of the simulated environment, including a hydraulic system, a temperature box, a pressure regulator and a temperature sensor. The hydraulic system is not provided with multiple groups of hydraulic pipelines for providing different liquid medium environments, including hydraulic oil, fuel, lubricating oil and coolant; the liquid medium output from the hydraulic system flows into the temperature box through the pressure regulator, and an interface is provided in the temperature box for connecting the pressure sensor to be compensated. The temperature box is used to simulate the environmental conditions of each subsystem of the aircraft, wherein the pressure regulator is used to accurately control the pressure in the temperature box, that is, the actual pressure value, and the temperature box has a built-in temperature sensor for collecting the actual temperature in the temperature box, wherein the temperature range is -40°C to 150°C, and the pressure range is 0 to 30MPa. It is suitable for simulating aircraft subsystems whose medium environment is hydraulic oil, fuel, coolant or lubricating oil, including electromechanical systems, avionics systems, environmental control systems, engine systems, and flight control systems. The data acquisition system can accurately simulate and monitor complex environmental conditions, and provide reliable data support for the dynamic compensation model installed in the control system.

[0007] The control system is used to input the simulated subsystem environmental conditions, control the data acquisition system to achieve the required environmental conditions, and collect data from the temperature sensor, the voltage regulator, and the pressure sensor to be compensated, wherein the control system communicates with the voltage regulator, the temperature sensor, and the pressure sensor to be compensated in the data acquisition system through a bus; the control system is equipped with a dynamic compensation model to realize intelligent compensation for the pressure sensor to be compensated.

[0008] The dynamic compensation model uses a deep learning model to correct the pressure value measured by the pressure sensor in real time and correct the impact of the environment on the measurement accuracy of the pressure sensor. The dynamic compensation model uses a multi-layer perceptron (MLP), whose input layer includes three features: temperature value, measured pressure value and medium type; the hidden layer consists of three layers, each layer contains 64 neurons, the activation function is the rectified linear unit function (Rectified Linear Unit, ReLU), and a Dropout layer is added to prevent overfitting; the output layer is a node for predicting the compensated pressure value; the loss function of the dynamic compensation model uses the mean square error (MSE), and the optimizer selects the Adam optimizer because it has a good convergence speed and effect. Based on the actual temperature value, actual pressure value, medium type and pressure value of the pressure sensor collected by the acquisition system, the dynamic compensation model can provide accurate and reliable pressure sensor compensation results, which not only improves the measurement accuracy of the sensor in a complex environment, but also enhances the overall reliability and safety of the aircraft system.

[0009] Furthermore, the accuracy of the voltage regulator is 0.05%.

[0010] Furthermore, the dynamic compensation model in the control system, in addition to the deep learning model, i.e., the multi-layer perceptron, can also adopt long short-term memory (LSTM), convolutional neural network (CNN), swarm intelligence optimization algorithm, such as gray wolf algorithm, particle swarm algorithm, whale algorithm, etc.

[0011] A pressure sensor intelligent compensation method applicable to an aviation multi-media environment, the pressure sensor intelligent compensation method comprising the following steps:

[0012] Step 1: Connect the pressure sensor to be compensated in a temperature box, and input the liquid medium, ambient temperature and ambient pressure of the aircraft subsystem where the pressure sensor to be compensated is located into the control system.

[0013] Step 2: The control system regulates the hydraulic system in the data acquisition system to provide the target liquid medium.

[0014] Step 3: The control system adjusts the temperature box and the voltage regulator to simulate different ambient temperatures and ambient pressures, and collects the output value, actual temperature value, and actual pressure value of the pressure sensor to be compensated under different ambient temperatures and ambient pressures.

[0015] Step 4, using the medium type, the actual temperature value collected and the output value of the pressure sensor to be compensated as the training set input value, and the actual pressure value collected as the output value, the dynamic compensation model in the control system is trained to finally realize the compensation of the pressure sensor.

[0016] Beneficial effects of the present invention: The present invention can construct the liquid medium environment, temperature environment and pressure environment of the aircraft subsystem where the pressure sensor is located, and can collect temperature values, pressure values ​​measured by the pressure sensor and pressure values ​​in the actual environment in real time. Based on the collected data, a compensation model is established, which can correct the pressure value measured by the sensor in real time and correct the influence of the environment on the measurement accuracy of the pressure sensor. The present invention can enable the pressure sensor to maintain high-precision measurement capabilities in various complex environments, which can not only significantly improve the reliability and safety of the aircraft system, but also provide a new solution for pressure sensor calibration in similar environments in the future. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is the architecture diagram of the intelligent compensation device for the pressure sensor;

[0018] Figure 2 This is the architecture diagram of the control system;

[0019] Figure 3 This is a diagram of the dynamic compensation model architecture;

[0020] Figure 4 This is a diagram of the pressure sensor measurement results after adopting the pressure sensor intelligent compensation method.

[0021] In the figure: 1 data acquisition system; 2 control system; 3 hydraulic system; 4 pressure regulator; 5 temperature box; 6 temperature sensor; 7 pressure sensor; 8 bus; 9 dynamic compensation model. DETAILED DESCRIPTION

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative labor.

[0023] This embodiment provides a pressure sensor intelligent compensation device suitable for aviation multimedia environment, the pressure sensor intelligent compensation device includes a data acquisition system 1 and a control system 2, such as Figure 1 and Figure 2 shown.

[0024] The data acquisition system 1 can simulate the liquid medium environment and temperature and pressure environment of each subsystem of the aircraft, and collect the actual temperature value, actual pressure value of the simulated environment and the pressure value measured by the pressure sensor to be compensated, including a hydraulic system 3, a temperature box 5, a pressure regulator 4 and a temperature sensor 6. The hydraulic system 3 is not provided with multiple groups of hydraulic pipelines for providing different liquid medium environments, including hydraulic oil, fuel, lubricating oil, and coolant; the liquid medium output from the hydraulic system 3 flows into the temperature box 5 through the pressure regulator 4, and the temperature box 5 is provided with an interface for connecting the pressure sensor 7 to be compensated. The temperature box 5 is used to simulate the environmental conditions of each subsystem of the aircraft. Among them, the voltage regulator 4 is used to accurately control the pressure in the temperature box 5, that is, the actual pressure value, with an accuracy of 0.05%. The temperature box 5 has a built-in temperature sensor 6 for collecting the actual temperature in the temperature box 5, wherein the temperature range is -40°C to 150°C, and the pressure range is 0 to 30MPa. The data acquisition system 1 is suitable for simulating aircraft subsystems whose medium environment is hydraulic oil, fuel, coolant or lubricating oil, including electromechanical systems, avionics systems, environmental control systems, engine systems, and flight control systems. The data acquisition system 1 can accurately simulate and monitor complex environmental conditions and provide reliable data support for the dynamic compensation model carried in the control system.

[0025] The control system 2 is used to input the simulated subsystem environmental conditions, control the data acquisition system 1 to achieve the required environmental conditions, and collect data from the temperature sensor 6, the voltage regulator 4, and the pressure sensor 7 to be compensated, wherein the control system 2 communicates with the voltage regulator 4, the temperature sensor 6, and the pressure sensor 7 to be compensated in the data acquisition system 1 through a bus 8; the control system 2 is equipped with a dynamic compensation model 9 to realize intelligent compensation for the pressure sensor 7 to be compensated.

[0026] The dynamic compensation model 9 uses a deep learning model to correct the pressure value measured by the pressure sensor 7 in real time and correct the influence of the environment on the measurement accuracy of the pressure sensor 7. Figure 3 As shown, the dynamic compensation model adopts a multilayer perceptron, whose input layer includes three features: temperature value, measured pressure value and medium type; the hidden layer consists of three layers, each layer contains 64 neurons, the activation function is a rectified linear unit function, and a Dropout layer is added to prevent overfitting; the output layer is a node, which is used to predict the compensated pressure value; the loss function of the dynamic compensation model adopts mean square error, and the optimizer selects Adam optimizer because of its good convergence speed and effect. Based on the actual temperature value, actual pressure value, medium type and pressure value of the pressure sensor collected by the acquisition system, the dynamic compensation model can provide accurate and reliable pressure sensor compensation results, which not only improves the measurement accuracy of the sensor in complex environments, but also enhances the overall reliability and safety of the aircraft system.

[0027] In other embodiments, the dynamic compensation model in the control system 2 may also adopt long short-term memory, convolutional neural network, swarm intelligence optimization algorithm, such as grey wolf algorithm, particle swarm algorithm, whale algorithm, etc.

[0028] This embodiment also provides a pressure sensor intelligent compensation method applicable to an aviation multimedia environment, and the pressure sensor intelligent compensation method comprises the following steps:

[0029] Step 1, connect the pressure sensor 7 to be compensated in the temperature box 5, input the liquid medium, ambient temperature and ambient pressure of the aircraft subsystem where the pressure sensor 7 to be compensated is located in the control system 2. In this embodiment, lubricating oil is selected as the liquid medium to simulate the engine system.

[0030] Step 2: The control system regulates the hydraulic system in the data acquisition system to provide the target liquid medium.

[0031] Step 3, the control system adjusts the temperature box and the voltage regulator to simulate different ambient temperatures and ambient pressures. In this embodiment, the temperature box 5 is set with 10 different temperature points, including -20℃, -10℃, 0℃, 10℃, 20℃, 30℃, 40℃, 50℃, 60℃ and 70℃, and the voltage regulator 4 adjusts 11 different pressure values, including 1MPa, 3MPa, 6MPa, 9MPa, 12MPa, 15MPa, 18MPa, 21MPa, 24MPa, 27MPa and 28MPa; the output value, actual temperature value and actual pressure value of the pressure sensor 7 to be compensated under different ambient temperatures and ambient pressures are collected, wherein the measurement values ​​of the pressure sensor 7 are all collected under the set standard pressure generated by the high-precision voltage regulator 4.

[0032] Step 4, using the medium type, the actual temperature value collected and the output value of the pressure sensor to be compensated as the training set input value, and the actual pressure value collected as the output value, the dynamic compensation model 9 in the control system 2 is trained to finally realize the compensation of the pressure sensor.

[0033] After adopting the above-mentioned intelligent compensation method for pressure sensor, the pressure value result of pressure sensor 7 is Figure 4 As shown, the results show that after calibration, the measured value of the pressure sensor 7 is almost the same as the pressure value set by the pressure regulator 4 with an accuracy of 0.05%. This result proves that the present invention can effectively correct the sensor measurement error caused by the medium environment and temperature changes.

[0034] The above-described embodiments merely express the implementation methods of the present invention, but they should not be understood as limiting the scope of the present invention. It should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. An intelligent compensation device for pressure sensors suitable for aviation multi-media environments, characterized in that: The pressure sensor intelligent compensation device comprises a data acquisition system (1) and a control system (2); the data acquisition system (1) is used to simulate the liquid medium environment and the temperature and pressure environment of each aircraft subsystem, and collect the actual temperature value and the actual pressure value of the simulated environment and the pressure value measured by the pressure sensor (7) to be compensated; the control system (2) is used to input the simulated subsystem environmental conditions, control the data acquisition system (1) to achieve the required environmental conditions, and realize intelligent compensation for the pressure sensor (7) to be compensated.

2. According to claim 1, a pressure sensor intelligent compensation device suitable for aviation multimedia environment is characterized in that: The pressure sensor intelligent compensation device is specifically: The data acquisition system (1) comprises a hydraulic system (3), a temperature box (5), a pressure regulator (4) and a temperature sensor (6); the hydraulic system (3) is not provided with a plurality of hydraulic pipelines for providing different liquid medium environments; the liquid medium output from the hydraulic system (3) flows into the temperature box (5) through the pressure regulator (4); an interface is provided in the temperature box (5) for connecting a pressure sensor to be compensated (7); the temperature box (5) is used to simulate environmental conditions of various subsystems of the aircraft; the pressure regulator (4) is used to accurately control the pressure in the temperature box (5); the temperature box (5) has a built-in temperature sensor (6) for collecting the actual temperature in the temperature box (5); The control system (2) communicates with the voltage regulator (4), the temperature sensor (6) and the pressure sensor to be compensated (7) in the data acquisition system (1) via a bus 8; the control system (2) is equipped with a dynamic compensation model (9) for realizing intelligent compensation of the pressure sensor to be compensated (7).

3. The intelligent compensation device for pressure sensors suitable for aviation multimedia environments according to claim 2 is characterized in that: The liquid medium provided by the hydraulic system (3) includes hydraulic oil, fuel oil, lubricating oil and coolant.

4. The intelligent compensation device for pressure sensors suitable for aviation multimedia environments according to claim 2, characterized in that: The temperature range simulated by the temperature box (5) is -40°C to 150°C, and the pressure range is 0 to 30 MPa.

5. The intelligent compensation device for pressure sensors suitable for aviation multimedia environments according to claim 2, characterized in that: The accuracy of the voltage regulator (4) is 0.05%.

6. The intelligent compensation device for pressure sensors suitable for aviation multimedia environments according to claim 2, characterized in that: The dynamic compensation model (9) adopts a multi-layer perceptron, whose input layer includes three features: temperature value, measured pressure value and medium type; the hidden layer consists of three layers, each layer contains 64 neurons, the activation function is a rectified linear unit function, and a Dropout layer is added to prevent overfitting; the output layer is a node for predicting the compensated pressure value; the loss function of the dynamic compensation model (9) adopts mean square error, and the optimizer selects Adam optimizer.

7. The intelligent compensation device for pressure sensors suitable for aviation multimedia environments according to claim 2, characterized in that: The dynamic compensation model (9) in the control system (2) may also adopt long short-term memory, convolutional neural network, or swarm intelligence optimization algorithm.

8. A pressure sensor intelligent compensation method suitable for aviation multimedia environment, implemented based on the pressure sensor intelligent compensation device according to any one of claims 1 to 7, characterized in that: The pressure sensor intelligent compensation method comprises the following steps: Step 1, connecting the pressure sensor to be compensated (7) in a temperature box (5), and inputting the liquid medium, ambient temperature and ambient pressure of the aircraft subsystem where the pressure sensor to be compensated (7) is located in the control system (2); Step 2, the control system (2) regulates the hydraulic system (3) in the data acquisition system (1) to provide a target liquid medium; Step 3, the control system (2) adjusts the temperature box (5) and the voltage regulator (4) to simulate different ambient temperatures and ambient pressures, and collects the output value, actual temperature value and actual pressure value of the pressure sensor to be compensated (7) under different ambient temperatures and ambient pressures; Step 4, using the medium type, the actual temperature value collected and the output value of the pressure sensor (7) to be compensated as the training set input value, and the actual pressure value collected as the output value, to train the dynamic compensation model (9) in the control system (2), and finally realize compensation for the pressure sensor (7).

Images