A composite loading test system and method applied to a solid engine shell

Abstract

The application discloses a composite loading test system and method applied to a solid engine shell, and belongs to the field of aerospace test devices.The system comprises an axial loading system, an internal pressure loading system, an external pressure loading system, a temperature rise strain test system and a control system.The system is used for simultaneously applying axial load, internal pressure, external pressure and high-temperature load to the solid engine shell.Further, an accurate control method for applying axial load, internal pressure and external pressure is provided.The system can realize the function of monitoring the stress and strain conditions of the shell in real time, can more comprehensively reflect the mechanical behavior of the shell under complex working conditions, and can provide more reliable basis for shell structure design and material selection.

Description

Technical Field

[0001] This invention belongs to the field of aerospace test equipment, specifically relating to a composite loading test system and method for solid rocket motor casings. Background Technology

[0002] Solid-propellant engines are one of the core components of missile systems, responsible for providing propulsion and enabling the missile to fly along a predetermined trajectory. As the power core of the missile system, their performance and reliability are crucial to the stability and effectiveness of the entire missile system. Solid-propellant engines have advantages such as simple structure, stable storage, and rapid start-up, which make them widely used in the military and aerospace fields. At the same time, solid-propellant engines bear the heavy responsibility of ensuring mission success and safety; therefore, verifying their reliability and resilience is particularly important.

[0003] In solid rocket motor testing, relying solely on high-temperature or high-pressure loading methods has significant limitations. High-temperature loading primarily assesses the thermal stability and heat resistance of materials under high-temperature environments, but it neglects the combined effects of high pressure on the material structure, resulting in an incomplete reflection of the mechanical properties under actual operation. While high-pressure loading can demonstrate the shell's pressure-bearing capacity, it fails to consider the changes in material properties under high-temperature conditions and their impact on the overall structural strength. Therefore, testing under a single loading condition cannot accurately simulate the complex stress states of a solid rocket motor during operation, potentially leading to an incomplete assessment of material and structural reliability. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a composite loading test system and method for solid rocket motor casings. This system has the function of real-time monitoring of the stress and strain of the casing, and can more comprehensively reflect the mechanical behavior of the casing under complex working conditions, providing a more reliable basis for casing structure design and material selection.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a composite loading test system for solid engine casings, comprising an axial loading system, an internal pressure loading system, an external pressure loading system, a temperature rise strain testing system, and a control system;

[0007] The axial loading system includes a servo hydraulic station and a loading cylinder; the servo hydraulic station adjusts the flow and pressure of the hydraulic oil in the loading cylinder through a servo valve and feeds the data back to the control system, thereby controlling the output force of the loading rod to apply the axial load to the housing.

[0008] The internal pressure loading system and the external pressure loading system include a high-temperature heat transfer oil tank, a high-temperature oil pump, a pressure sensor, and a control valve. The two sets of high-temperature oil pumps inject heat transfer oil into the inner cavity of the shell and the annulus formed between the shell and the pressure vessel, respectively. The internal pressure and external pressure of the shell under test are adjusted by the control valve, and the data is fed back to the control system to control the internal pressure and external pressure.

[0009] The temperature rise strain testing system collects temperature and strain data, generates a temperature curve, and analyzes it synchronously with the strain data.

[0010] As a further improvement of the present invention, the internal pressure loading system injects high-pressure heat transfer oil into the inner cavity of the test housing through a high-temperature oil pump to simulate the pressurized environment inside the housing when the engine is working.

[0011] The heat transfer oil used in the internal pressure loading system enters the inner cavity after impurities are removed; the inner cavity of the tested housing is equipped with a pressure sensor to monitor the pressure changes in the inner cavity in real time, and dynamically adjusts the output flow and pressure of the oil pump through a feedback control loop to control the internal pressure.

[0012] As a further improvement of the present invention, the internal pressure loading system and the external pressure loading system adopt independent dual-loop control, and the internal and external pressures are independently regulated and coupled through pressure regulating valves.

[0013] As a further improvement of the present invention, the temperature rise strain testing system includes a temperature control cabinet, a heating jacket, a temperature sensor, and strain gauges. The heating jacket is arranged outside the pressure vessel and heats the shell uniformly through heat conduction by the heat transfer oil filled inside the pressure vessel. The temperature sensor is arranged on the surface of the pressure vessel to monitor the temperature change of the shell surface in real time. The strain gauges are attached to the key stress concentration points of the shell to measure the strain of the shell under different load conditions. All sensor data are transmitted to the control system through a data acquisition system for real-time monitoring and recording of load and strain.

[0014] As a further improvement of the present invention, the control system integrates multi-point pressure sensors and multi-point temperature sensors, which are respectively arranged on the inner and outer surfaces of the housing and in the environment, for real-time monitoring of internal pressure, external pressure and temperature.

[0015] Multiple pressure sensors are arranged on the inner and outer surfaces of the test housing to monitor the internal and external pressures in real time; multiple temperature sensors are arranged on the inner and outer surfaces of the test housing to monitor the temperature in real time.

[0016] It also includes fiber Bragg grating sensors: used to monitor the deformation and stress distribution of the tested housing in real time.

[0017] As a further improvement of the present invention, the control system includes a multi-layer neural network optimization controller, which includes a convolutional neural network and a long short-term memory network to perform multi-scale feature extraction and time series prediction on real-time data to generate optimized control parameters; at the same time, an adaptive fuzzy logic controller is also adopted, which dynamically adjusts the control strategy based on a multi-layer fuzzy logic algorithm, combining real-time data and historical data; the control system adopts PLC programming logic and has adaptive control capability, dynamically adjusting the loading force and temperature according to sensor feedback.

[0018] As a further improvement of the present invention, the control system also integrates a multi-channel data acquisition and processing system, supporting data transmission and storage, multi-threading and parallel computing, and various communication protocols and data encryption; specifically including:

[0019] Central processing unit, supporting multi-threading and parallel computing;

[0020] The communication module supports multiple communication protocols and data encryption functions.

[0021] Secondly, the present invention provides a control method based on the aforementioned composite loading test system applied to a solid rocket motor casing, comprising:

[0022] S1. Precisely place the solid rocket motor casing into the pressure vessel, ensuring the sealing and alignment between the casing and the vessel, and confirming that each subsystem is in optimal working condition; based on the casing's design parameters and operating environment, set the internal pressure, external pressure, axial load, and temperature through the control system; the control system generates and optimizes the synchronization control strategy based on a multi-stress synchronous control algorithm to ensure the coordination and synchronization of the loading process of each physical parameter; calibrate each sensor and actuator;

[0023] S2 employs multi-stress synchronous control technology to precisely coordinate the loading process of temperature rise strain, internal pressure, external pressure, and axial load. The high-temperature heating system uses multi-point high-precision temperature sensors distributed on the shell surface to provide real-time feedback and dynamically adjust the heating power, ensuring that the shell surface temperature strictly follows the preset temperature gradient distribution. The internal and external pressure loading system uses high-precision servo control valves to precisely adjust the flow and pressure of hydraulic oil, achieving high-precision loading of internal and external pressure, thereby simulating the stress state of a solid rocket motor shell in a real working environment. The axial load system adjusts the axial load in real time based on changes in internal and external pressure and feedback from strain sensors, ensuring the precise application of the composite load. The control system adopts a closed-loop feedback control mechanism to synchronously adjust temperature, internal pressure, external pressure, and axial load in real time, ensuring that all parameters remain coordinated and consistent during dynamic changes.

[0024] The S3 multi-channel data acquisition card synchronously acquires axial load, internal shell pressure, external shell pressure, strain, and temperature data; the acquired data is processed by an advanced filtering algorithm, displayed and recorded in real time; a comprehensive test report is generated based on the acquired data; and abnormal data is identified and alerted.

[0025] As a further improvement to the present invention, axial load application specifically includes:

[0026] S1, selecting the loading rod stroke, velocity, and output force as state variables, and establishing a reference model based on the component parameters of the axial loading system:

[0027]

[0028] in These are the loading rod stroke, speed, and output force, respectively. The damping coefficient, stiffness, and mass of the tested shell are obtained after a second-order approximate equivalent. and It is a nonlinear function. The input signal is used to control the axial loading servo valve;

[0029] S2, based on the reference model, designs the servo valve input signal for the axial loading system, employing a terminal sliding mode control method. A nonlinear attractor is introduced based on the sliding mode control, and the sliding surface is designed as follows:

[0030]

[0031] in The error between the output force and the expected value of the reference model. These are all hyperparameters, from which the servo valve reference input signal is derived. for:

[0032]

[0033] in This is the gain coefficient. For symbolic functions, The desired output force;

[0034] S3, Design an adaptive neural network to provide compensation signals for the servo valve. The compensation signal is expressed as...

[0035]

[0036] in This represents the force output error between the actual loading system and the reference model. This is the gain coefficient. This is the upper bound of the disturbance. For neural network pairs Uncertainty estimation, with neural network weights adaptively updated during the loading process;

[0037] The final input signal for the servo valve is the reference input signal. With compensation signal sum.

[0038] As a further improvement to the present invention, the method for precise control of axial load loading, internal pressure, and external pressure loading specifically includes:

[0039] S1, precisely place the solid rocket motor casing in the pressure vessel, and collect comprehensive data on key parts of the inner and outer surfaces of the casing through a distributed sensor network;

[0040]

[0041] in, and These are multi-point measurements of the internal and external pressures of the test housing after preloading.

[0042] S2, data preprocessing

[0043]

[0044]

[0045] The effect of oil temperature on pressure was introduced, among which, and These are multiple measurements of the initial temperature; , , , This is the preprocessing matrix;

[0046] S3 uses a combination of convolutional neural networks and long short-term memory networks in a deep learning framework to perform multi-scale feature extraction and time series prediction on real-time acquired stress data, generating optimized control parameters:

[0047]

[0048]

[0049] Among them, CNN and LSTM are convolutional neural networks and long short-term memory networks, respectively. Indicates feature fusion operation;

[0050] S4, based on fuzzy logic algorithm, dynamically adjusts the control strategy by combining real-time data; the fuzzy logic controller adopts a hybrid optimization method based on particle swarm optimization algorithm and genetic algorithm to ensure the global optimality of control parameters;

[0051]

[0052]

[0053] in, and The control signal output by the adaptive fuzzy logic controller. and For fuzzy rule membership degree, and For fuzzy logic parameters;

[0054] The fuzzy logic parameters are determined using a hybrid optimization algorithm:

[0055]

[0056]

[0057] PSO and GA are the particle swarm optimization algorithm and the genetic algorithm, respectively. This indicates a hybrid optimization operation. The range of values ​​for each optimized parameter;

[0058] S5 employs a high-response, multi-redundant actuator to precisely adjust based on optimized control parameters;

[0059]

[0060]

[0061] in and To optimize the adjusted pressure, and The final control signal generated by the combined action of the multilayer neural network optimization controller and the fuzzy logic controller. and This is the actuator gain matrix.

[0062] The beneficial effects of this invention are reflected in:

[0063] The most significant advantage of the composite loading system proposed in this invention lies in its ability to simultaneously apply axial load, internal pressure, external pressure, and temperature stress to the solid rocket motor casing. This ability to simultaneously load multiple stresses allows the system to highly simulate the multidimensional stress state of the casing in actual working environments, significantly improving the realism and reliability of the experiments. Compared to traditional single-stress loading systems, this system possesses the ability to accurately simulate complex working conditions. It is not limited to static stress loading but can also simulate the dynamic stress state of the engine casing under high temperature and high pressure environments. It can accurately reproduce the stress changes of the casing at different stages such as launch, flight, and recovery, comprehensively reflecting the mechanical behavior of the casing under complex working conditions, and providing a more reliable basis for structural design and material selection.

[0064] Furthermore, this system enables precise control of load application, ensuring not only the synchronization and coordination of multi-stress loading but also dynamic adjustment of loading force and temperature based on real-time sensor feedback. The combined use of a multi-layer neural network optimized controller and an adaptive fuzzy logic controller improves the system's prediction accuracy and real-time response capability, ensuring the stability and safety of the experimental process. Especially under high temperature and high pressure environments, this precise control capability effectively copes with sudden changes in operating conditions, guaranteeing the smooth progress of the experiment. Attached Figure Description

[0065] Figure 1 This is a schematic diagram of the complete structure of the composite loading test system;

[0066] Figure 2 This is a schematic diagram illustrating the steps involved in achieving precise control of axial loading.

[0067] Figure 3 This is a schematic diagram illustrating the steps involved in precisely controlling internal and external pressure loading.

[0068] Figure 4 This is a flowchart of the test procedure for the composite loading system;

[0069] Figure 5 This is a schematic diagram of the control system;

[0070] Figure 6 This is a diagram of the neural network structure used for precise control of axial loading;

[0071] Figure 7 This is a schematic diagram of a single LSTM computing unit.

[0072] Among them, 1 is the servo hydraulic station; 2 is the loading cylinder; 3 is the PLC; 4 is the PC; 5 is the temperature control cabinet; 6 is the heating jacket; 7 is the main supporting frame; 8 is the pressure vessel; 9 is the loading rod; 10 is the test housing; 11 is the controller; 12 is the high-temperature heat transfer oil tank; and 13 is the high-temperature oil pump. Detailed Implementation

[0073] The significance of combined high-temperature and high-pressure loading lies in its ability to more realistically simulate the operating environment of solid rocket motors, thereby providing a more comprehensive assessment of material properties and structural strength. This combined testing method can reveal the behavior of the casing when simultaneously subjected to high temperature and high pressure. By reproducing the actual operating conditions of the engine under laboratory conditions, it allows designers to more accurately predict and improve its performance and lifespan under real-world conditions. Furthermore, this test can effectively identify potential failure modes, ensuring appropriate optimization during the design phase and further enhancing the safety and reliability of the missile system. The data obtained through combined loading can provide a basis for material selection, structural optimization, and process improvement, driving innovation and ensuring that the design of next-generation engines is more robust and reliable.

[0074] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0075] This invention proposes a composite loading test system for solid rocket motor casings, specifically comprising an axial loading system, an internal pressure loading system, an external pressure loading system, a temperature rise strain testing system, and a control system. A complete structural schematic diagram of the test system is shown below. Figure 1 As shown. It is used to simultaneously apply axial loads, internal pressures, external pressures, and high-temperature loads to the solid rocket motor casing, achieve precise load control, and monitor the stress and strain of the casing in real time.

[0076] Specifically, the test housing 10 is placed in a specially designed pressure vessel 8. The design of the pressure vessel 8 fully considers the ease of entry, exit, and connection of the test housing 10. Both ends of the vessel are designed to be openable, with flange connections and high-temperature resistant sealing gaskets to ensure good sealing performance even after multiple disassemblies and reassemblies. The inner wall of the vessel is polished to reduce frictional damage that may occur when the housing is moved in and out.

[0077] The axial loading system includes a servo hydraulic station 1, a loading cylinder 2, a loading rod 9, and a main bearing frame 7, which is used to apply axial pressure to the solid engine housing to evaluate its deformation and strength characteristics under axial load.

[0078] Furthermore, the servo hydraulic station 1, serving as the power source, employs a high-response servo valve. Its closed-loop control system enables precise adjustment of the loading force, ensuring force control accuracy and stability during the loading process. The frequency response characteristics of the servo valve have been optimized to adapt to different loading rates, thus meeting various test conditions. The servo hydraulic station 1 regulates the flow and pressure of the hydraulic oil in the loading cylinder 2 through the high-precision servo valve and feeds the data back to the control system, thereby precisely controlling the output force of the loading rod 9 and accurately applying the axial load to the housing.

[0079] Both the internal and external pressure loading systems consist of a high-temperature heat-conducting oil tank 12, a high-temperature oil pump 13, a pressure sensor, and a control valve. The two sets of high-temperature oil pumps 13 inject heat-conducting oil into the inner cavity of the shell and the annulus formed between the shell and the pressure vessel 8, respectively. The control valves regulate the internal and external pressures of the tested shell 10 and feed the data back to the control system to achieve precise control of the internal and external pressures. The loading cylinder 2 in the axial loading system is connected to the servo hydraulic station 1 via a dedicated high-pressure pipeline. The cylinder has a built-in displacement sensor to monitor the piston stroke in real time, ensuring positional accuracy during loading. The loading rod 9 is made of high-strength alloy material with a chrome-plated surface and undergoes precision grinding to improve its wear resistance and corrosion resistance. The connection between the loading rod 9 and the pressure vessel 8 employs high-temperature and high-pressure resistant dynamic sealing technology, specifically using a bidirectional wear-resistant sealing ring to ensure no leakage occurs during long-term high-pressure testing.

[0080] Specifically, the main load-bearing frame 7 in the axial loading system is welded from high-strength steel and undergoes stress relief treatment. Its structural design is optimized through finite element analysis, effectively bearing and dispersing high axial loads, and avoiding additional stress concentration on other components of the system. The fixed supports of the frame are designed with adjustment mechanisms, which can be flexibly adjusted according to different specifications of the test shell 10.

[0081] The internal pressure loading system injects high-pressure heat transfer oil into the inner cavity of the test housing 10 via a high-temperature oil pump 13 to simulate the pressurized environment inside the housing during engine operation. The high-temperature oil pump 13 is a plunger pump made of high-temperature resistant and corrosion-resistant materials. The plunger and valves inside the pump body are hardened to ensure service life under high-temperature and high-pressure conditions.

[0082] Furthermore, the heat transfer oil used in the internal pressure loading system undergoes a precision filtration system to remove impurities before entering the inner cavity, preventing impurities from damaging the inner wall of the housing. A pressure sensor is installed inside the tested housing 10 to monitor pressure changes in real time. Through a feedback control loop, the output flow and pressure of the oil pump are dynamically adjusted to achieve precise control of the internal pressure.

[0083] Furthermore, the working principle of the external pressure loading system is similar to that of the internal pressure loading system. The heat transfer oil is injected into the annular outer cavity formed by the test housing 10 and the pressure vessel 8 through the high-temperature oil pump 13 to simulate the external pressure environment of the engine housing in actual operation.

[0084] As an example, the internal pressure loading system and the external pressure loading system employ independent dual-loop control, achieving independent adjustment and coupled control of internal and external pressures through a high-precision pressure regulating valve. The internal and external pressure loading systems can operate simultaneously to perform coupled pressure tests on the shell under complex stress states, evaluating its deformation and strength performance under the combined action of internal and external pressures.

[0085] Specifically, the temperature rise strain testing system includes a temperature control cabinet 5, a heating jacket 6, temperature sensors, and strain gauges. The heating jacket 6 is arranged outside the pressure vessel 8 and heats the shell uniformly through heat conduction by the heat-conducting oil filled inside the pressure vessel 8. The temperature sensors are arranged on the surface of the pressure vessel 8 to monitor the temperature change of the shell surface in real time. The strain gauges are attached to the key stress concentration points of the shell to measure the strain of the shell under different load conditions. All sensor data are transmitted to the control system through a data acquisition system to realize real-time monitoring and recording of high-temperature loads and strains.

[0086] As an example, the temperature rise strain testing system uses a heating jacket 6 located outside the pressure vessel 8 to control the temperature rise of the tested shell 10 through the thermal conduction effect of the heat-conducting oil filled in the pressure vessel 8. The heating jacket 6 uses a specially customized ceramic heater, and its power adjustment is achieved through a solid-state relay, which can precisely adjust the heating power according to the test requirements to gradually increase the surface temperature of the shell.

[0087] As an example, the temperature rise strain testing system is equipped with a temperature sensor arranged on the surface of the heating jacket 6. The temperature control cabinet 5 has a built-in PID controller 11, which dynamically adjusts the output power of the heater based on real-time data feedback from the temperature sensor, ensuring that the shell surface temperature remains stable within the set range. Strain gauges are attached to key stress concentration areas of the shell to measure the strain of the shell under different load conditions. By collecting temperature and strain data, a temperature curve is generated and analyzed synchronously with the strain data, providing data support for evaluating the thermodynamic properties of the shell.

[0088] Furthermore, the control system integrates high-precision multi-point pressure sensors and high-precision multi-point temperature sensors, respectively positioned on the inner and outer surfaces of the housing and in the environment, for real-time monitoring of internal pressure, external pressure, and temperature; a fiber Bragg grating (FBG) sensor is used to monitor the deformation and stress distribution of the housing in real time. These sensors, combined with a high-precision data acquisition card, can capture transient data in real time under high temperature and high pressure conditions. This acquisition card features high-speed sampling and high resolution, ensuring the accuracy and completeness of data under complex operating conditions. The acquired data is transmitted to a computer via a dedicated interface for real-time monitoring and subsequent analysis, ensuring the reliability of the test results.

[0089] As an example, the control system includes a multi-layer neural network optimized controller 11, which incorporates a convolutional neural network (CNN) and a long short-term memory network (LSTM). This controller is capable of multi-scale feature extraction and time series prediction of real-time data to generate optimized control parameters. Simultaneously, the system also employs an adaptive fuzzy logic controller 11, based on a multi-layer fuzzy logic algorithm, which dynamically adjusts the control strategy by combining real-time and historical data. The synergistic effect of the multi-layer neural network and adaptive fuzzy logic not only improves the system's prediction accuracy and real-time response capability but also enhances its robustness against noise and uncertainty. Furthermore, the control system uses optimized PLC 3 programming logic, possessing adaptive control capabilities that can dynamically adjust the loading force and temperature based on sensor feedback. This real-time adjustment mechanism ensures the stability and safety of the experimental process, especially under high temperature and high pressure environments, effectively responding to sudden changes in operating conditions and guaranteeing the smooth progress of the experiment.

[0090] In addition, the control system integrates a multi-channel data acquisition and processing system, supporting high-bandwidth, high-precision data transmission and storage; a high-performance central processing unit (CPU) supports multi-threading and parallel computing; and a high-bandwidth, low-latency communication module supports multiple communication protocols and data encryption functions. The combined use of these components enables the system to operate efficiently and stably in complex and ever-changing experimental environments.

[0091] Among them, the high-precision multi-point pressure sensor is arranged on the inner and outer surfaces of the test housing 10 to monitor the internal and external pressure in real time;

[0092] High-precision multi-point temperature sensor: arranged on the inner and outer surfaces of the test housing 10 for real-time temperature monitoring;

[0093] Fiber Bragg grating (FBG) sensor: used for real-time monitoring of deformation and stress distribution of the tested housing 10;

[0094] Multi-layer neural network optimization controller 11: includes convolutional neural network (CNN) and long short-term memory network (LSTM), which can perform multi-scale feature extraction and time series prediction on real-time data and generate optimized control parameters;

[0095] Adaptive fuzzy logic controller 11: Based on a multi-layer fuzzy logic algorithm, it can dynamically adjust the control strategy and generate fuzzy logic control signals by combining real-time data;

[0096] Multi-channel data acquisition and processing system: supports high-bandwidth, high-precision data transmission and storage;

[0097] Central Processing Unit (CPU): A high-performance processor that supports multi-threading and parallel computing;

[0098] Communication module: A high-bandwidth, low-latency communication module that supports multiple communication protocols and data encryption functions.

[0099] As a further improvement of the present invention, the control method for accurately applying axial load during the combined loading process is designed as follows.

[0100] Since the governing equations of the axial loading system process are relatively clear, a model reference adaptive algorithm is used to control the precise application of the axial load. A schematic diagram of the overall algorithm is shown below. Figure 2 As shown. The specific steps include:

[0101] S1, select the stroke, speed and output force of loading rod 9 as state variables, and establish a reference model based on the component parameters of the axial loading system. The reference model is shown in equation (1).

[0102] Using nonlinear dynamic equations, fundamental laws of fluid mechanics, and dynamic equations considering the characteristics of compressible fluids, detailed mathematical models are established for key components (hydraulic cylinders, servo valves, etc.) in an axial loading system. After obtaining the dynamic equations of these key components, a state-space model of the force closed-loop control system is constructed. The state-space expression of the axial loading system is as follows:

[0103]

[0104] in These are the stroke, speed, and output force of the loading lever 9, respectively. The damping coefficient, stiffness, and mass of the tested shell 10 are obtained after a second-order approximate equivalent. and It is a nonlinear function. The input signal is used to control the axial loading servo valve.

[0105] S2, based on the reference model, the servo valve input signal of the axial loading system is designed, and the terminal sliding mode control method is adopted. That is, a nonlinear attractor is introduced on the basis of traditional sliding mode control to ensure the stability of the system within a finite time. The sliding surface is designed as Equation (2).

[0106] Based on the mathematical model established in S1, and according to the given desired output force trajectory, a terminal sliding mode control method is used to limit the error convergence time, thus completing the design of the reference model. The sliding surface expression is designed as follows:

[0107]

[0108] in The error between the output force and the expected value of the reference model. All are hyperparameters, servo valve reference input signal As shown in equation (3).

[0109]

[0110] in This is the gain coefficient. For symbolic functions, The desired output force.

[0111] S3. An adaptive neural network is designed to provide compensation signals for the servo valve to eliminate the error between the reference model and the actual loading system. The expression of the compensation signal is shown in equation (4).

[0112] The neural network controller 11 generates a compensation signal, which is superimposed on the reference input signal in S1 and applied to the real loading system. The uncertainty of the output force error derivative between the reference model and the real system is obtained by using a neural network approximation method. The neural network output is substituted into the sliding mode control exponential approach law to obtain the compensation signal calculation formula, thereby eliminating the tracking error between the real loading system and the reference model and achieving the purpose of accurately loading the real system according to the predetermined trajectory. The expression of the compensation signal is shown in equation (4).

[0113]

[0114] in This represents the force output error between the actual loading system and the reference model. This is the gain coefficient. This is the upper bound of the disturbance. For neural network pairs Uncertainty estimation. The neural network weights can be adaptively updated during the loading process.

[0115] The final input signal for the servo valve is the reference input signal. With compensation signal sum.

[0116] As a further improvement of the present invention, the method for achieving precise control of the internal and external pressure of the tested housing 10 during the combined loading process is designed as follows.

[0117] Since there is a lack of accurate control equations for the internal and external pressure loading process of the shell, a control system including a high-precision distributed sensor network, a multi-layer neural network optimization controller 11, and an adaptive fuzzy logic algorithm module was designed to accurately and collaboratively load the internal and external pressures of the shell 10 under test.

[0118] Due to the large loading area inside and outside the shell, and the large volume of heat transfer oil filling the inner cavity and outer annulus, the loading process exhibits significant time delay and nonlinearity, making it difficult to obtain an accurate mathematical expression using traditional methods. Therefore, this invention employs a control system including a multi-layer neural network optimization controller 11, an adaptive fuzzy logic controller 11, a high-precision distributed sensor network, a central processing unit, and a communication module to achieve real-time monitoring and precise adjustment of the internal and external pressures of the shell, ensuring the stability and reliability of the system under complex operating conditions. A schematic diagram of the overall algorithm is shown below. Figure 3 As shown. Specifically, it includes the following steps:

[0119] S1, the solid rocket motor casing is precisely placed in the pressure vessel 8, and a distributed sensor network is used to collect comprehensive data on key parts of the inner and outer surfaces of the casing.

[0120] Shell Installation and Data Acquisition: The solid rocket motor shell is precisely placed in the pressure vessel 8, and comprehensive data acquisition is performed on the inner and outer surfaces of the shell through a distributed sensor network, including multi-point pressure and temperature measurements, to ensure the accuracy of the initial data.

[0121]

[0122] in, and These are multi-point measurements of the initial internal pressure and external pressure, respectively.

[0123] S2, Data preprocessing: The collected pressure and temperature data are preprocessed, the influence of oil temperature on pressure is introduced, and the initial data is converted into a multi-dimensional vector that can be used for multi-layer neural network processing to ensure data consistency and availability.

[0124]

[0125]

[0126] The effect of oil temperature on pressure was introduced, among which, and These are multiple measurements of the initial temperature; , , , This is the preprocessing matrix.

[0127] S3 uses a combination of convolutional neural networks (CNN) and long short-term memory networks (LSTM) in a deep learning framework to perform multi-scale feature extraction and time series prediction on real-time collected stress data, generating optimized control parameters.

[0128] Multilayer Neural Network Optimized Control: A Convolutional Neural Network (CNN) is used to extract spatial features from preprocessed multidimensional vectors, and a Long Short-Term Memory (LSTM) network is used to process and predict time-series data of internal and external pressures to generate optimized control parameters. This process combines the spatial feature extraction capabilities of CNNs with the time-series prediction capabilities of LSTMs, improving control accuracy and response speed.

[0129]

[0130]

[0131] Among them, CNN and LSTM are convolutional neural networks and long short-term memory networks, respectively. This indicates a feature fusion operation.

[0132] S4, based on fuzzy logic algorithms, dynamically adjusts the control strategy using real-time data to cope with nonlinear pressure changes in complex environments. The fuzzy logic controller 11 employs a hybrid optimization method based on particle swarm optimization (PSO) and genetic algorithm (GA) to ensure the global optimality of control parameters.

[0133] Because neural networks are highly sensitive to noise in the input data, especially in experimental environments where sensor data may exhibit significant fluctuations and errors, this can affect the model's prediction and control performance. Therefore, an adaptive fuzzy logic controller 11 is used as a compensation controller 11, working in conjunction with the multilayer neural network optimization controller 11 in S3, to enable the system to maintain high robustness in the face of uncertainty and noisy data.

[0134] The adaptive fuzzy logic controller 11 receives preprocessed sensor data and dynamically adjusts the control strategy through a multi-layer fuzzy logic algorithm to cope with nonlinear pressure changes in complex environments. The fuzzy logic controller 11 employs a hybrid optimization method based on particle swarm optimization (PSO) and genetic algorithm (GA) to ensure the global optimality of control parameters, thereby further improving the stability and reliability of the system.

[0135]

[0136]

[0137] in, and The control signal output by the adaptive fuzzy logic controller 11 and For fuzzy rule membership degree, and For fuzzy logic parameters.

[0138] The fuzzy logic parameters are determined using a hybrid optimization algorithm:

[0139]

[0140]

[0141] PSO and GA are the particle swarm optimization algorithm and the genetic algorithm, respectively. This indicates a hybrid optimization operation. The range of values ​​for each optimized parameter.

[0142] S5, Multiple Redundant Actuator Adjustment: The high-response-speed multiple redundant hydraulic actuator is precisely adjusted according to optimized control parameters to ensure instantaneous response and long-term stability of internal and external pressure.

[0143]

[0144]

[0145] in and To optimize the adjusted pressure, and The final control signal generated by the combined action of the multilayer neural network optimization controller 11 and the fuzzy logic controller 11. and This is the actuator gain matrix.

[0146] In addition, the present invention also provides a high-temperature and high-pressure composite loading test method for solid rocket motor casings, the method comprising the following main steps:

[0147] S1. Test Preparation and Parameter Setting. First, the solid rocket motor casing is precisely placed in a specially designed pressure vessel 8, ensuring the casing and vessel are sealed and aligned. Each subsystem (including the high-temperature heating system, internal and external pressure loading system, and axial loading system) is confirmed to be in optimal working condition. Based on the casing's design parameters and the operating environment, key test parameters such as internal pressure, external pressure, axial load, and temperature are precisely set through the control system. The control system, based on a multi-stress synchronous control algorithm, automatically generates and optimizes the synchronous control strategy to ensure the coordination and synchronization of the loading process for each physical parameter (temperature, pressure, load). Simultaneously, the system automatically calibrates each sensor and actuator to ensure they are within their normal operating range, guaranteeing the accuracy and safety of the test.

[0148] S2, Synchronous Composite Loading Control. During loading, the control system precisely coordinates the loading process of temperature rise strain, internal pressure, external pressure, and axial load through multi-stress synchronous control technology. The high-temperature heating system uses multi-point high-precision temperature sensors distributed on the shell surface to provide real-time feedback and dynamically adjust the heating power to ensure that the shell surface temperature strictly follows the preset temperature gradient distribution. The internal and external pressure loading system uses high-precision servo control valves to precisely adjust the flow and pressure of hydraulic oil, achieving high-precision loading of internal and external pressure, thereby simulating the stress state of the solid rocket motor shell in the actual working environment. The axial load system adjusts the axial load in real time based on changes in internal and external pressure and feedback from strain sensors to ensure the precise application of the composite load. The control system adopts a closed-loop feedback control mechanism to synchronously adjust temperature, internal pressure, external pressure, and axial load in real time, ensuring that all parameters remain coordinated and consistent during dynamic changes, avoiding experimental errors caused by changes in a single parameter.

[0149] S3 features multi-channel data acquisition and real-time monitoring. During the test, a multi-channel high-precision data acquisition card simultaneously collects key data such as axial load, internal shell pressure, external shell pressure, strain, and temperature. The acquired data is processed by an advanced filtering algorithm, then displayed and recorded in real time to ensure accuracy and completeness. The control system generates comprehensive test reports based on the acquired data. Test personnel can view the changes in each parameter in real time through a human-machine interface and dynamically adjust test conditions as needed. The system's built-in intelligent algorithm automatically identifies and alerts to abnormal data, ensuring the safety of the test process and the reliability of the data. Furthermore, the system supports real-time data storage and backup, ensuring long-term preservation and traceability of test data.

[0150] The present invention will be described in detail below with reference to specific embodiments.

[0151] Example 1

[0152] This embodiment describes the working process of the composite loading test system. Through the coordinated operation of the axial loading system, internal pressure loading system, external pressure loading system, temperature rise strain testing system, and control system, precise control and real-time monitoring of axial load, internal pressure, external pressure, and temperature are achieved, completing the comprehensive performance test of the solid rocket motor casing under complex stress conditions. The test procedure is as follows: Figure 4 As shown, the specific steps are as follows:

[0153] 1. Experimental Preparation

[0154] Before the test begins, the solid engine housing to be tested is first installed. The flanges at both ends of pressure vessel 8 are opened, and the condition of the sealing gaskets is checked to ensure they are intact. The housing is placed stably on the support frame inside the vessel, ensuring the housing is aligned with the loading rod 9 to avoid eccentric loading. After tightening the flanges of pressure vessel 8, the status of each system is checked. The oil level of the servo hydraulic station 1 is confirmed, ensuring there are no leaks in the hydraulic lines. The amount of heat transfer oil in the high-temperature oil pump 13 is checked, and it is confirmed that the heat transfer oil has been treated by the precision filtration system. All sensors (including pressure, temperature, and strain gauges) are properly connected. The heating device and temperature control cabinet 5 are checked, ensuring they are in standby mode and the temperature sensors are correctly positioned. After completing these preparations, the system enters the standby state.

[0155] 2. Axial loading operation

[0156] Start the servo hydraulic station 1 and set the initial axial loading force in the control software, typically 1.5 times the weight of the housing, and select an appropriate loading rate. The servo hydraulic station 1 controls the output force of the loading cylinder 2 via a high-response servo valve, beginning to apply axial pressure to the housing. Real-time monitoring of the data from the displacement sensor built into the loading cylinder 2 ensures the piston stroke matches the predetermined position, preventing overload. Gradually increase the axial load according to test requirements; the control system adjusts the loading force in real-time through closed-loop feedback to ensure force control accuracy.

[0157] 3. Internal pressure loading operation

[0158] In the internal pressure loading system, the target pressure is set, and the pressurization rate is selected. The high-temperature oil pump 13 is started to inject precision-filtered high-temperature heat transfer oil into the housing cavity. Data from the internal cavity pressure sensor is monitored in real time, and the output flow and pressure of the oil pump are dynamically adjusted through a feedback control loop to ensure stable internal pressure.

[0159] 4. External pressure loading operation

[0160] In the external pressure loading system, the target pressure is set, and the pressurization rate is selected. A separate set of high-temperature oil pumps 13, distinct from the internal pressure loading system, is started to inject heat transfer oil into the annular outer cavity between the shell and the pressure vessel 8. Data from the pressure sensor is monitored in real time, and the external pressure is controlled by a high-precision pressure regulating valve to ensure pressure stability. The internal and external pressure systems are coupled and controlled through an independent dual-loop control system to ensure synchronous regulation and coordination of the internal and external pressures. If the test requires a complex stress state, the control system can, according to preset parameters, achieve alternating or synchronous loading of the internal and external pressures to simulate coupled loads under actual working conditions.

[0161] 5. High-temperature heating operation

[0162] The temperature rise strain test system is started, and the target temperature of the shell surface is set according to the test requirements, and the heating rate is selected. The ceramic heater is started, and the heating power is adjusted through a solid-state relay to gradually increase the shell surface temperature. The PID controller 11 in the temperature control cabinet 5 dynamically adjusts the heater output power based on feedback data from the thermocouple temperature sensor to ensure precise temperature control. The temperature changes of the shell surface and heat transfer oil are monitored in real time, and the control software generates a temperature curve, which is recorded synchronously with the strain data. If the temperature exceeds the set range, the system will immediately alarm and automatically reduce the heating power or stop heating to prevent overheating from damaging the shell or equipment.

[0163] 6. Data Acquisition and Experiment Completion Procedures

[0164] During loading and heating, strain gauges monitor the minute deformations of the shell under axial load, internal pressure, external pressure, and high temperature in real time. Data is transmitted to a computer via a data acquisition card, and the control software generates stress-strain curves and displays them in real time. Pressure sensors in the inner and outer cavities monitor pressure changes within the system in real time. Data is also transmitted to a computer via a data acquisition card, and the control software generates pressure-time curves and analyzes them synchronously with temperature data. The control software integrates all collected data (including strain, pressure, and temperature) and generates comprehensive test reports. Through the control software, test personnel can view the trends of various physical quantities in real time and adjust test parameters as needed, such as increasing or decreasing axial load, internal pressure, external pressure, or temperature. The system automatically records all data to ensure that any changes during the test are accurately captured for subsequent analysis. The control software also alerts test personnel to abnormal data, such as strain values ​​exceeding expectations or large pressure fluctuations, ensuring timely response.

[0165] After the test reaches the predetermined time or loading conditions, the internal and external pressures are gradually reduced, and the system slowly unloads the load. Simultaneously, the heater's output power is gradually reduced, causing the shell temperature to drop slowly and avoiding thermal stress concentration caused by rapid cooling. The temperature control system automatically adjusts according to the preset cooling rate via PID controller 11 to ensure a uniform temperature decrease. Once the internal pressure and temperature of the system have dropped to a safe range, the axial pressure is gradually unloaded via servo hydraulic station 1. The control system adjusts the output force of loading cylinder 2 in real time to ensure a smooth unloading process. When the axial load drops to its initial state, the servo system shuts down, and the piston of loading cylinder 2 returns to its original position.

[0166] After unloading is complete, stop the data acquisition system and save all test data (including strain, pressure, temperature, etc.) to the computer hard drive to generate the final test report. Check the status of each system to ensure there are no leaks or abnormalities, then shut down the entire test system. After the system has completely cooled down, open the flange of pressure vessel 8 and remove the tested shell 10. Inspect the shell for deformation, cracks, or other damage, and compare the results with the test data to evaluate its performance under complex stress conditions.

[0167] 7. Follow-up Analysis

[0168] After the experiment, the stress-strain curves and temperature-time curves were analyzed in detail using the analysis module of the control software to evaluate the deformation and strength characteristics of the shell under different loads and temperatures. By comparing data from different test conditions, the comprehensive performance of the shell under the combined effects of axial compression, internal pressure, external pressure, and high temperature was analyzed. Based on the test data, a detailed test report was generated, including test conditions, loading curves, temperature changes, strain data, etc., providing data support for subsequent shell design and improvement. If any abnormalities or problems were found during the experiment, corresponding improvement suggestions were proposed and provided as a reference for subsequent experiments. The control system structure is as follows: Figure 5 As shown.

[0169] Example 2

[0170] This embodiment describes a specific implementation method for controlling precise axial load application using a model reference adaptive approach, including the following steps:

[0171] S1, using nonlinear dynamic equations, fundamental laws of fluid mechanics, and dynamic equations considering the characteristics of compressible fluids, selects the stroke, velocity, and output force of loading rod 9 as state variables. A reference model is established based on the component parameters of the axial loading system, as shown in equation (14).

[0172]

[0173] in The damping coefficient, stiffness, and mass are the equivalent values ​​after load. The calculation formula is:

[0174] When u>0

[0175]

[0176] When u<0

[0177]

[0178] The calculation formula is:

[0179]

[0180] in For the flow area of ​​the servo valve, For valve core displacement, This is the gain coefficient between the input signal and the valve core displacement. The average density of the hydraulic oil before and after the valve. Let V be the cross-sectional area of ​​the high-pressure chamber and the low-pressure chamber. The elastic modulus of hydraulic oil. The orifice flow coefficient of the servo valve. For pump pressure, This refers to the pressure in the cavity directly connected to the pump source. For the corresponding volume, This is another cavity volume.

[0181] S2, the reference input signal of the servo valve is designed based on the reference model. The design method is to introduce a nonlinear attractor on the basis of traditional sliding mode control to ensure that the system is stable within a finite time. The expression of the sliding surface is shown in equation (18).

[0182]

[0183] in The error between the output force and the expected value of the reference model. All parameters are hyperparameters. The exponential reaching law is used to ensure that s converges to 0 in a finite time, and the system enters the sliding mode.

[0184]

[0185] Under this design, after the system reaches s=0, it converges from the state e(0)≠0 at this moment to e(t). s The time when ) = 0 is:

[0186]

[0187] This ensures that the error converges to zero within a finite time, thus enabling the servo valve reference input signal to... Designed as follows:

[0188]

[0189] in This is the gain coefficient. For symbolic functions, The desired output force.

[0190] S3. Design an adaptive neural network to provide compensation signals for the servo method, in order to eliminate the error between the reference model and the actual loading system. The expression for the compensation signal is:

[0191]

[0192] in This represents the force output error between the actual loading system and the reference model. This is the gain coefficient. This is the upper bound of the disturbance. For neural network pairs For uncertainty estimation, the neural network weights can be adaptively updated according to the error during the loading process. The specific calculation formula is as follows:

[0193]

[0194]

[0195]

[0196] in As input to the neural network, To account for the pressure error in the high-pressure chamber of the hydraulic cylinder between the reference model and the actual system, For neural network activation functions, and For adaptive weights, the neural network structure is as follows: Figure 6 As shown.

[0197] The final input signal for the servo valve in the axial loading system is the reference input signal. With compensation signal sum.

[0198] Example 3

[0199] Since the goals of internal and external pressure loading are to apply uniform pressure to the entire outer and inner walls of the shell, the loading area is large, and the volume of heat transfer oil filling the inner cavity and external annulus is also large. This results in significant time delay and nonlinearity in the process, making it impossible to obtain a mathematically accurate expression like that of coaxial loading. Therefore, a control system integrating a multi-layer neural network optimization controller 11, an adaptive fuzzy logic controller 11, a high-precision distributed sensor network, a central processing unit (CPU), and a communication module is adopted to achieve real-time monitoring and precise adjustment of the internal and external pressures of the shell, ensuring the stability and reliability of the system under complex operating conditions. Specifically, the following steps are included:

[0200] S1, the solid rocket motor casing is precisely placed in the pressure vessel 8, and a multi-sensor network is used to collect comprehensive and multi-dimensional data on the pressure inside and outside the casing.

[0201]

[0202] in, and These are multi-point measurements of the initial internal pressure and external pressure, respectively.

[0203] S2, preprocesses the data.

[0204]

[0205]

[0206] The effect of oil temperature on pressure was introduced, among which, and These are multiple measurements of the initial temperature; , , , This is the preprocessing matrix.

[0207] S3 uses a convolutional neural network primarily to extract spatial features from raw sensor data. The input to the convolutional neural network is a preprocessed multidimensional vector.

[0208]

[0209] A convolutional neural network consists of multiple convolutional layers and pooling layers, and its output can be represented as...

[0210]

[0211] in This represents the convolution operation. and These are the weights and biases of the convolutional layer, respectively.

[0212] S4 uses a Long Short-Term Memory network to process and predict time-varying sequence data of internal and external pressure. By combining spatial features extracted by CNN, LSTM can more accurately predict future system states.

[0213] set up The output of the LSTM layer can be calculated as follows:

[0214]

[0215] The output of the convolutional neural network is used as the input to the LSTM computation unit, with the specific structure as follows: Figure 7 As shown, the output calculation formulas for each part of the LSTM computing unit are as follows:

[0216]

[0217]

[0218]

[0219]

[0220]

[0221]

[0222] Optimize objective function It can be represented as:

[0223]

[0224] in and The target pressure is set.

[0225] The optimization algorithm updates the weights using gradient descent.

[0226]

[0227] in, It's the learning rate. It is the gradient of the objective function.

[0228] The output layer generates optimized control parameters. and :

[0229]

[0230] In step S5, a fuzzy logic controller 11 is used to provide a compensation signal. Since the multilayer neural network controller 11 in step S4 is highly sensitive to noise in the input data, especially in experimental environments where sensor data may exhibit significant fluctuations and errors, affecting the model's prediction and control performance, an adaptive fuzzy logic controller 11 is used as the compensation controller 11 to work in conjunction with the multilayer neural network optimization controller 11 in step S3. This allows the system to maintain high robustness in the face of uncertainty and noisy data.

[0231] The adaptive fuzzy logic controller 11 receives preprocessed sensor data. For each sensor, the input provided to the fuzzy logic controller 11 is:

[0232]

[0233] Transform the input data into a fuzzy set. and These represent the effects of internal pressure and external pressure on the first... The function value of the membership function of the fuzzy rule:

[0234]

[0235]

[0236] in , , and For the first The parameters to be optimized are the membership functions of the fuzzy rules. The above parameter combination is then optimized using a hybrid optimization module combining Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).

[0237]

[0238]

[0239] in This represents the range of values ​​for each parameter to be optimized.

[0240] The optimization objective function can be expressed as:

[0241]

[0242] Based on the fuzzified input data, fuzzy rules are applied to generate a fuzzy output. Let... and Corresponding to the first Control parameters for internal and external pressure derived from sensor data:

[0243]

[0244]

[0245] By averaging the control parameters obtained from all sensors, the final parameters of the fuzzy logic controller 11 for the internal and external pressures can be written as follows:

[0246]

[0247]

[0248] By combining CNN and LSTM multilayer neural network optimization control with adaptive fuzzy logic control, the system's prediction accuracy and real-time response capability are improved, its robustness in the face of noise and uncertainty is enhanced, and it performs well in handling complex working conditions and multi-objective optimization, achieving more comprehensive, accurate and reliable control results.

Claims

1. A composite loading test system applied to a solid engine case, characterized in that, The axial loading system, the internal pressure loading system, the external pressure loading system, the temperature rise strain test system and the control system are comprised; The axial loading system comprises a servo hydraulic station and a loading oil cylinder; the servo hydraulic station adjusts the flow and pressure of the hydraulic oil of the loading oil cylinder through a servo valve and feeds back data to the control system, so that the output force of the loading rod is controlled and the axial load of the shell is applied; The internal pressure loading system and the external pressure loading system comprise high-temperature heat conducting oil tanks, high-temperature oil pumps, pressure sensors and control valves; two groups of high-temperature oil pumps respectively inject heat conducting oil into the inner cavity of the shell and the annular space formed between the shell and the pressure container, the internal pressure and the external pressure of the tested shell are adjusted through the control valve, and the data are fed back to the control system to control the internal pressure and the external pressure; The temperature rise strain test system generates a temperature curve by collecting temperature and strain data and synchronously analyzes the strain data; The control system comprises a multi-layer neural network optimization controller; the controller comprises a convolutional neural network and a long short-term memory network, performs multi-scale feature extraction and time series prediction on real-time data, generates optimized control parameters, adopts a self-adaptive fuzzy logic controller based on a multi-layer fuzzy logic algorithm, dynamically adjusts the control strategy, combines real-time data and historical data, and adopts PLC programming logic to have self-adaptive control capability and dynamically adjust the internal pressure, the external pressure and the temperature according to sensor feedback. The axial load of the shell is applied, and specifically comprises: S1, selecting the stroke, the speed and the output force of the loading rod as state variables, establishing a reference model according to the element parameters of the axial loading system: wherein are the load rod stroke, velocity and output force, respectively, are the damping coefficient, stiffness and mass of the second order approximation of the shell under test, and are non-linear functions, is the input signal to control the axial loading servo valve; S2, designing the input signal of the servo valve of the axial loading system based on the reference model, adopting terminal sliding mode control, introducing a nonlinear attractor on the basis of the sliding mode control, and designing the sliding mode surface as: wherein is the error of the reference model output force and the desired value, are hyperparameters, and the servo valve reference input signal is wherein is a gain coefficient, is a sign function, is a desired output force; S3, designing an adaptive neural network to provide a compensation signal for the servo valve, and the compensation signal is expressed as in This represents the force output error between the actual loading system and the reference model. This is the gain coefficient. This is the upper bound of the disturbance. For neural network pairs Uncertainty estimation, with neural network weights adaptively updated during the loading process; The final input signal to the servo valve is the sum of the reference input signal and the compensation signal .

2. The composite loading test system for a solid rocket engine case according to claim 1, wherein The internal pressure loading system injects high-pressure heat conducting oil into the inner cavity of the tested shell through the high-temperature oil pump to simulate the pressurized environment inside the shell during engine operation; The heat conducting oil used by the internal pressure loading system enters the inner cavity after impurities are removed; the inner cavity of the tested shell is provided with a pressure sensor for monitoring the pressure change of the inner cavity in real time, and the output flow and pressure of the oil pump are dynamically adjusted through a feedback control loop to control the internal pressure.

3. The composite loading test system for a solid rocket motor case according to claim 1, wherein The internal pressure loading system and the external pressure loading system adopt independent double-loop control to independently adjust and coupled control the internal and external pressures through pressure regulating valves.

4. The composite loading test system for a solid rocket motor case according to claim 1, wherein The temperature rise strain test system comprises a temperature control cabinet, a heating jacket, temperature sensors and strain gauges; the heating jacket is arranged outside the pressure container and uniformly heats the shell through heat conduction of the heat conducting oil filled in the pressure container; the temperature sensors are arranged on the surface of the pressure container and used for monitoring the temperature change of the surface of the shell in real time; the strain gauges are pasted on the key stress concentration parts of the shell and used for measuring the strain of the shell under different load conditions; the data of all the sensors are transmitted to the control system through a data acquisition system for real-time monitoring and recording of the load and the strain.

5. The composite loading test system for a solid rocket motor case according to claim 1, wherein The control system integrates multi-point pressure sensors and multi-point temperature sensors arranged on the inner and outer surfaces of the shell and in the environment, respectively, for real-time monitoring of the internal pressure, external pressure and temperature; The multi-point pressure sensors are arranged on the inner and outer surfaces of the shell to be tested for real-time monitoring of the internal pressure and external pressure; The multi-point temperature sensors are arranged on the inner and outer surfaces of the shell to be tested for real-time monitoring of the temperature; It also includes a fiber Bragg grating sensor for real-time monitoring of the deformation and stress distribution of the shell to be tested.

6. The composite loading test system for a solid rocket motor case according to claim 1, wherein The control system also integrates a multi-channel data acquisition and processing system, which supports data transmission and storage, multi-threading and parallel computing, and multiple communication protocols and data encryption; specifically including: A central processing unit supporting multi-threading and parallel computing; A communication module supporting multiple communication protocols and data encryption functions.

7. A control method based on the composite loading test system applied to the solid engine shell according to any one of claims 1-6, characterized in that, It includes: S1, accurately place the solid rocket engine shell in the pressure vessel, ensure the sealing and centring between the shell and the vessel, and confirm that each subsystem is in the best working state; based on the design parameters and working environment of the shell, set the internal pressure, external pressure, axial load and temperature through the control system; the control system generates and optimizes the synchronous control strategy based on the multi-stress synchronous control algorithm, ensuring the coordination and synchronization of the loading process of each physical parameter; calibrate each sensor and actuator; S2, accurately coordinate the loading process of temperature rise strain, internal pressure, external pressure and axial load through multi-stress synchronous control technology; The high-temperature heating system dynamically adjusts the heating power in real time through the real-time feedback of the multi-point high-precision temperature sensors distributed on the surface of the shell, ensuring that the shell surface temperature strictly follows the preset temperature gradient distribution; the internal and external pressure loading system accurately adjusts the flow and pressure of hydraulic oil through high-precision servo control valves, realizing high-precision loading of internal and external pressure, thereby simulating the stress state of the solid rocket engine shell in the actual working environment; the axial load system adjusts the axial load in real time according to the changes of internal and external pressure and the feedback of strain sensors, ensuring the accurate application of composite load; the control system adopts a closed-loop feedback control mechanism to adjust the temperature, internal pressure, external pressure and axial load in real time; S3, the multi-channel data acquisition card synchronously collects axial load, shell internal cavity pressure, shell external pressure, strain and temperature data; the collected data is processed by high-level filtering algorithm, and is displayed and recorded in real time; based on the collected data, comprehensive test report is generated; abnormal data is identified and prompted.

8. The control method of claim 7, wherein, The internal and external pressure loading precise control method specifically includes: S1, accurately place the solid rocket engine shell in the pressure vessel, and collect data from key parts on the inner and outer surfaces of the shell through a distributed sensor network; wherein, and are the multi-point measurements of the internal and external pressure of the shell to be tested after preloading, respectively; S2, preprocess the data The influence of the oil temperature on the pressure is introduced, wherein and are the measured values of the initial temperature at multiple points; , , , is a pre-processing matrix; S3, use the method of combining convolutional neural network and long short-term memory network in deep learning framework to extract multi-scale features and time series prediction of real-time collected pressure data, and generate optimized control parameters: wherein CNN and LSTM are convolutional neural network and long short-term memory network, respectively, denotes a feature fusion operation; S4, dynamically adjust the control strategy based on real-time data based on fuzzy logic algorithm; the fuzzy logic controller adopts a hybrid optimization method based on particle swarm optimization algorithm and genetic algorithm to ensure the global optimality of the control parameters; wherein, and is a control signal output from an adaptive fuzzy logic controller, and is a fuzzy rule membership, and is a fuzzy logic parameter; Adopt hybrid optimization algorithm to determine fuzzy logic parameters: wherein PSO and GA are particle swarm optimization algorithm and genetic algorithm, respectively, denotes a hybrid optimization operation, is the value range of each optimized parameter; S5, adopt high response speed of multiple redundant actuators, according to the optimized control parameters for accurate adjustment; wherein and is the optimized adjusted pressure, and is the final control signal generated by the combined action of the multilayer neural network optimization controller and the fuzzy logic controller, and is the actuator gain matrix.

Images