A method and system for detecting the health status of an aircraft hydraulic system

Abstract

The present invention discloses a health status detection method and system for an aircraft hydraulic system, which relates to the field of aerospace engineering. The method comprises dividing a multimodal data stream into two parts, an operating parameter subset and an acoustic emission subset, for preprocessing, extracting features from each part to generate feature vectors, concatenating the two feature vectors into a fused feature vector, encoding and mapping the fused feature vector into a quantum initial state, establishing a quantum annealing model, obtaining a state characterization result, processing the state characterization result using a pretrained deep neural network, and calculating a health index to obtain a structured diagnosis result of the aircraft hydraulic system. The present invention utilizes quantum annealing technology to process the nonlinear coupling relationship between multiple variables, generates a state probability distribution of the aircraft hydraulic system through quantum optimization, and captures the potential characteristics of complex states.

Description

Technical Field

[0001] The present invention relates to the field of aerospace engineering, and in particular to a method and system for detecting the health status of an aircraft hydraulic system. Background Art

[0002] Aircraft hydraulic systems are a vital component of modern aircraft, responsible for core functions such as flight control, landing gear extension and retraction, and braking. With the continuous advancement of aviation technology, the demand for hydraulic system health monitoring has also increased, and more efficient and accurate monitoring methods are needed to ensure flight safety.

[0003] In most cases, traditional machine learning or statistical methods are usually used to process multimodal data. However, they are often unable to cope with high-dimensional, nonlinearly coupled multimodal data. They are prone to overfitting when dealing with strongly correlated variables and have difficulty capturing microscopic fault modes. Secondly, traditional time-frequency analysis technology has insufficient resolution and it is difficult to detect nanosecond transient signals, which seriously affects the reliability of the hydraulic system. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for detecting the health status of an aircraft hydraulic system to solve the problem that traditional time-frequency analysis technology has insufficient resolution and is difficult to detect nanosecond-level transient signals.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for detecting the health status of an aircraft hydraulic system, comprising:

[0008] Deploy a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream;

[0009] The multimodal data stream is divided into two parts: the operating parameter subset and the acoustic emission subset for preprocessing, and features are extracted from each part to generate feature vectors. At the same time, the two feature vectors are spliced ​​into a fused feature vector.

[0010] The fused feature vector is encoded and mapped into the quantum initial state, a quantum annealing model is established, and the state representation result is obtained;

[0011] Use a pre-trained deep neural network to process the state characterization results and calculate the health index to obtain structured diagnostic results of the aircraft hydraulic system;

[0012] The diagnostic results are presented in real time through the onboard display module and recorded in the onboard black box and ground maintenance server.

[0013] As a preferred solution of the aircraft hydraulic system health status detection method of the present invention, a multimodal sensor array is deployed to collect real-time data of the aircraft hydraulic system to form a structured multimodal data stream, which specifically includes the following steps:

[0014] The collected real-time data are unified by sequence and timestamp, compressed and transmitted to the onboard processing unit to obtain a structured multimodal data stream.

[0015] As a preferred solution of the aircraft hydraulic system health status detection method of the present invention, the multimodal data stream is divided into two parts: an operating parameter subset and an acoustic emission subset for preprocessing, and features are extracted from each part to generate feature vectors, and the two feature vectors are spliced ​​into a fused feature vector. Specifically, the following steps are included:

[0016] Using a predefined mapping table, the multimodal data stream is divided into an operational parameter subset and an acoustic emission subset;

[0017] Perform compressed sensing analysis on the acoustic emission subset to obtain the reconstructed acoustic wave signal;

[0018] Apply a dual-mode trigger strategy, set a fixed-width sliding window, and preset the rate of change threshold and offset limit;

[0019] Calculating the energy mutation rate of the reconstructed acoustic wave signal, recording a trigger time point when the energy mutation rate exceeds a preset energy threshold, converting the reconstructed acoustic wave signal into the frequency domain using a fast Fourier transform, detecting the shift in the peak frequency, and recording another trigger time point when the shift exceeds a shift limit;

[0020] When two trigger time points coincide, the features of the reconstructed acoustic wave signal centered at the time point are extracted to obtain the acoustic emission feature vector;

[0021] The mean and standard deviation of the subset of operating parameters are calculated through statistical analysis to obtain the operating parameter feature vector;

[0022] The acoustic emission feature vector and the operating parameter feature vector are combined into a fusion feature vector by splicing.

[0023] As a preferred solution of the aircraft hydraulic system health status detection method of the present invention, wherein: the fusion feature vector encoding is mapped into a quantum initial state, and a quantum annealing model is established, specifically comprising the following steps:

[0024] Normalize the fused eigenvector and map it to the initial quantum state;

[0025] Set the energy function as the core of the quantum annealing model and select the linear scheduling method to complete the configuration of the quantum annealing model;

[0026] As a preferred solution of the method for detecting the health status of an aircraft hydraulic system according to the present invention, the method of obtaining the health status characterization result specifically includes the following steps:

[0027] The target state is obtained by minimizing the target problem term, the initial quantum state is adjusted according to the selected linear scheduling method, and the transition to the target state is achieved. The probability distribution of the hydraulic system state is generated by iteration.

[0028] Use post-processing tools to analyze the evolution trajectory of the quantum state, calculate the weight value of each feature in the fusion feature vector, and form a weight vector;

[0029] The weight vector is combined with the probability distribution of the hydraulic system state to obtain the state representation result.

[0030] As a preferred embodiment of the health status detection method of the aircraft hydraulic system of the present invention, a pre-trained deep neural network is used to process the state characterization results and calculate the health index to obtain a structured diagnosis result of the aircraft hydraulic system, which specifically includes the following steps:

[0031] Establish a historical spectrum database and set fault thresholds based on historical fault data;

[0032] Input the state representation result into the pre-trained deep neural network;

[0033] Extract the probability value of each probability distribution in the state characterization result and calculate it to obtain the preliminary state judgment of the aircraft hydraulic system;

[0034] The sum of the probability values ​​of the micro-fault state and the severe fault state is compared with the fault threshold, and a state label and a trigger signal are obtained when the fault threshold is exceeded;

[0035] The weight vector is extracted from the state characterization results to determine the features that contribute most to the abnormal state. The features are then matched with the patterns in the historical spectrum database to identify the faulty components and obtain the structured diagnosis results of the aircraft hydraulic system.

[0036] As a preferred embodiment of the method for detecting the health status of an aircraft hydraulic system according to the present invention, the structured diagnostic result of the aircraft hydraulic system specifically includes the following steps:

[0037] The health index is calculated based on the probability value of the normal state, and the status labels and faulty components are integrated to generate a diagnostic report of the aircraft hydraulic system.

[0038] In a second aspect, the present invention provides a method and system for detecting the health status of an aircraft hydraulic system, comprising:

[0039] The acquisition module deploys a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream;

[0040] The fusion module divides the multimodal data stream into two parts: the operating parameter subset and the acoustic emission subset for preprocessing, extracts features from each part to generate feature vectors, and concatenates the two feature vectors into a fused feature vector.

[0041] The quantum processing module encodes and maps the fused feature vector into the quantum initial state, establishes a quantum annealing model, and obtains the state representation result;

[0042] The diagnostic module uses a pre-trained deep neural network to process the state representation results and calculate the health index to obtain structured diagnostic results of the aircraft hydraulic system;

[0043] The recording module presents the diagnostic results in real time through the onboard display module and records them in the onboard black box and ground maintenance server.

[0044] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the aircraft hydraulic system health status detection method as described in the first aspect of the present invention is implemented.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the aircraft hydraulic system health status detection method as described in the first aspect of the present invention is implemented.

[0046] The present invention achieves the following beneficial effects: it uses quantum annealing technology to process the nonlinear coupling relationships between multiple variables, then generates the state probability distribution of the aircraft hydraulic system through quantum optimization, capturing the potential characteristics of complex states. This step achieves efficient solution capabilities for high-dimensional nonlinear problems, significantly reducing computational complexity and dimensionality limitations compared to classical computational methods, improving the accuracy and real-time performance of state representation, and providing accurate technical support for ultra-early detection of microscopic faults. Furthermore, by performing energy mutation rate and frequency domain offset detection on acoustic emission subsets, transient fault characteristics can be captured, enabling rapid response to faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 Schematic diagram of the overall flow of the aircraft hydraulic system health status detection method in Example 1.

[0049] Figure 2 This is a schematic diagram of the collaborative work of multiple modules of the health status detection system in Example 1.

[0050] Figure 3 This is a flowchart of multimodal feature extraction and fusion processing in Example 1.

[0051] Figure 4 This is a diagram of the joint processing architecture of quantum annealing and deep neural network in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0055] Example 1, with reference to Figure 1 、 Figure 2 、 Figure 3 and Figure 4 , which is a first embodiment of the present invention, provides a method for detecting the health status of an aircraft hydraulic system, comprising the following steps:

[0056] S1. Deploy a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream.

[0057] The specific steps include:

[0058] A four-dimensional heterogeneous sensor matrix consisting of pressure, flow, temperature, and acoustic emission sensors is deployed in key areas of the aircraft's hydraulic system (such as pumps, valves, pipe joints, and actuators). These sensors are securely mounted to the component surfaces using aviation-grade fixtures or high-temperature adhesives to ensure vibration resistance (acceleration <20g) and high-temperature resistance (<150°C). These sensors collect pressure, flow, temperature, and broadband acoustic emission signal data from the aircraft's hydraulic system.

[0059] Preferably, compared to the traditional detection method using a single type of sensor (such as pressure / temperature), this solution integrates a four-dimensional sensing matrix (pressure / flow / temperature / acoustic emission) to achieve complementary detection of physical quantities. Acoustic emission sensors fill the blind spot of traditional vibration sensors in detecting early faults such as microcracks / cavitation.

[0060] The real-time data collected from the aircraft hydraulic system is uniformly numbered and timestamped in chronological order. Each sensor's data is precisely timestamped to facilitate subsequent data synchronization and analysis. For example, pressure data, flow data, temperature data, and acoustic emission signal data are all tagged to the same point in time, ensuring data consistency and traceability.

[0061] To improve data transmission efficiency and reduce bandwidth usage, the collected raw data is compressed. Using efficient compression algorithms (such as LZ77), data volume is significantly reduced while ensuring data integrity. The compressed data is transmitted via wired or wireless communication to an onboard processing unit, where it is decompressed and further processed to form a structured multimodal data stream.

[0062] Preferably, a multimodal data stream is formed through unified time series numbering, timestamp marking and decompression and reorganization by the onboard processing unit, which can well support subsequent deep learning analysis. The traditional processing method uses discrete storage, which has poor data correlation and is difficult to support subsequent joint fault diagnosis.

[0063] S2. Divide the multimodal data stream into two parts: the operating parameter subset and the acoustic emission subset for preprocessing, extract features from each part to generate feature vectors, and concatenate the two feature vectors into a fused feature vector.

[0064] The specific steps include:

[0065] Based on predefined logical rules (by signal type discrimination), the multimodal data stream is divided into two subsets. The operating parameter subset contains three types of data: pressure, flow, and temperature, reflecting the working status trend of the hydraulic system; the acoustic emission subset independently processes high-frequency acoustic emission signals to capture transient fault characteristics of equipment.

[0066] S2.1. Perform compressed sensing analysis on the acoustic emission subset to reconstruct the acoustic signal. Compressed sensing technology can reduce the sampling rate while preserving the key information of the signal, which is particularly important for processing high-frequency acoustic emission signals. This technology can recover high-quality acoustic signals from limited data, thereby improving the accuracy of subsequent analysis.

[0067] Set a sliding window with a fixed width (e.g., 5 milliseconds) to analyze the acoustic signal segment by segment;

[0068] The energy mutation rate change threshold and peak frequency deviation limit are set based on historical data (the values ​​of the change rate threshold and deviation limit can be customized according to specific usage scenarios and actual conditions).

[0069] Within each sliding window, the energy mutation rate of the reconstructed acoustic signal is calculated. If the energy mutation rate exceeds a preset energy threshold, the current time point is recorded as the first trigger time point. This step helps identify significant fluctuations in the signal that may indicate a potential fault.

[0070] At each trigger time point, the reconstructed acoustic signal is converted to the frequency domain using a fast Fourier transform (FFT). In the frequency domain, the peak frequency shift is detected. If the shift exceeds a preset limit, the time point is recorded as the second trigger time point. This combined time-frequency analysis method can more comprehensively capture subtle changes in the acoustic emission signal.

[0071] When two triggering time points coincide, the features of the reconstructed acoustic wave signal centered at that time point are extracted, including peak frequency, energy amplitude, duration, and bandwidth, to form an acoustic emission feature vector. The features of the reconstructed acoustic wave signal can effectively describe abnormal patterns in the acoustic emission signal and provide a basis for subsequent fault diagnosis.

[0072] Statistical analysis is performed on a subset of operating parameters (pressure, flow, and temperature data), and their mean and standard deviation are calculated to generate an operating parameter feature vector. These statistical features can reflect the overall operating status of the hydraulic system and help identify potential abnormal trends.

[0073] The acoustic emission feature vector and the operating parameter feature vector are combined into a fused feature vector by splicing. This fusion not only integrates different types of feature information but also enhances the integrity of the feature vector.

[0074] It is further explained that the traditional dual-mode trigger strategy has only a single energy threshold, the trigger is easily interfered by environmental noise, and it is difficult to capture frequency domain anomalies based solely on time domain characteristics. However, the energy-frequency joint trigger mechanism of this scheme can simultaneously capture transient impact signals and identify harmonic offsets caused by component wear.

[0075] S3. Map the fused feature vector encoding to the quantum initial state, establish a quantum annealing model, and obtain the state representation result.

[0076] The specific steps include:

[0077] The fused feature vectors extracted and concatenated from the multimodal data streams are normalized. Normalization ensures consistent scales across features, preventing some features from dominating the optimization process due to excessively large values. The normalized fused feature vectors are then mapped to the initial quantum state using a quantum state representation (such as a qubit or quantum register).

[0078] Furthermore, by mapping the fused feature vectors into quantum initial states, the limitations of traditional methods in high-dimensional spaces are overcome. Quantum state representation can handle complex nonlinear relationships in higher-dimensional spaces, thereby more accurately capturing subtle changes in the aircraft hydraulic system.

[0079] S3.1. In the quantum annealing model, an energy function is set as the core. The energy function consists of an initial energy term and a target problem term. The initial energy term is usually used to describe the ground state energy of the aircraft hydraulic system, while the target problem term reflects the objective function to be optimized for the aircraft hydraulic system.

[0080] The quantum annealing model was configured by selecting a linear scheduling method (a process that gradually adjusts parameters to guide the aircraft hydraulic system from its initial state to its target state). This linear scheduling method effectively controls the evolution path of the quantum state, ensuring that the aircraft hydraulic system can smoothly reach the optimal solution.

[0081] Using a quantum annealing algorithm, the target state of the aircraft hydraulic system is found by minimizing the target problem term through an iterative process. During this process, the initial quantum state is dynamically adjusted using a linear scheduling method to gradually transition toward the target state. Each iteration generates a probability distribution of the aircraft hydraulic system's states, including normal states, microscopic fault states (such as nanoscale wear of seals), and severe fault states (such as pipeline leaks). This probability distribution reflects the likelihood of the aircraft hydraulic system in different health states.

[0082] Ideally, classical sensor signal analysis (such as threshold alarms and spectrum analysis) is insensitive to early micron- and nanometer-scale faults (such as nano-wear of seals and micro-bubbles in oil), resulting in a high false alarm rate. This invention uses quantum annealing to detect microscopic energy changes that are indiscernible to traditional methods, directly outputting the probability of microscopic faults rather than binary judgments, thus supporting preventive maintenance decisions.

[0083] To further refine the state characterization results, post-processing tools are used to analyze the quantum state evolution trajectory. Specifically, the weight of each feature in the fused feature vector is calculated using the gradient of the energy function to form a weight vector. This process involves quantifying the contribution of each feature during the quantum state evolution process, helping to identify which features have the greatest impact on the state changes of the aircraft hydraulic system. The weight vector not only provides information on feature importance but also provides a basis for subsequent state classification and fault diagnosis.

[0084] S4. Use the pre-trained deep neural network to process the state characterization results and calculate the health index to obtain the structured diagnosis results of the aircraft hydraulic system.

[0085] The specific steps include:

[0086] Based on historical hydraulic system failure data, a historical spectrum database is constructed. This database analyzes past failure cases to extract characteristic patterns of component failures (such as hydraulic pumps and main control valves). For example, this database identifies the relationship between specific frequency peaks in acoustic emission signals and component damage. Next, based on statistical analysis of historical failure data, a failure threshold is set. This threshold reflects the critical point at which the sum of the probabilities of micro-fault states and severe fault states is considered abnormal.

[0087] Furthermore, by establishing a historical spectrum database and setting fault thresholds, we can summarize fault characteristics and quantify abnormality judgment criteria, providing a reliable basis for fault location and status classification.

[0088] S4.1. First, a deep neural network is constructed. The first layer is the input layer, the second and third layers are hidden layers, each layer contains a fixed number of neurons, and the fourth layer is the output layer, which is designed with three output nodes, corresponding to the three state categories of the hydraulic system: normal state, micro-fault state, and severe fault state. The training process adopts a supervised learning method, and the goal is to make the output of the deep neural network match the labeled state categories (normal, micro-fault, severe fault) as much as possible. The specific method uses the backpropagation algorithm combined with the stochastic gradient descent optimizer to adjust the weights and bias of the network through multiple rounds of iterations. The loss function uses cross-entropy loss to measure the difference between the predicted probability and the true label to drive model convergence.

[0089] S4.2. The deep neural network extracts probability values ​​from the state probability distribution, corresponding to normal, micro-fault, and severe fault states. Using internal weights and activation functions, it calculates the confidence level for each state and generates a preliminary state judgment for the aircraft hydraulic system. The result is stored as a state vector, representing the current state's propensity.

[0090] Check the sum of the probability values ​​of the micro-fault state and the serious fault state to determine whether it exceeds the fault threshold. If it exceeds the threshold, it is determined that there is an abnormality in the aircraft hydraulic system and a trigger signal is generated to indicate whether to locate the fault. If it does not exceed the threshold, it is determined to be a normal state and the trigger signal value is no need for location.

[0091] Preferably, the present invention utilizes the dynamic classification capability of neural networks, surpassing the singleness of traditional threshold judgment, achieving the effect of improving the sensitivity and accuracy of state recognition, and providing better support for ultra-early fault detection.

[0092] S4.3. Check the trigger signal. If positioning is required, extract the weight vector from the state characterization results. Analyze the magnitude of each weight value to determine which features contribute most to the abnormal state. For example, the acoustic emission peak frequency may have a higher weight, indicating a significant impact on the fault. Load the established historical spectrum database and retrieve the characteristic pattern data, such as the correspondence between specific frequency peaks and component faults. Then, match the features with larger weights with the patterns in the database. Using a pattern recognition algorithm, compare the similarity between the feature values ​​and the fault pattern to identify the possible faulty component. For example, if the acoustic emission peak frequency matches the fault characteristics of a hydraulic pump, the fault is located as a hydraulic pump. The positioning result is stored as a component identifier, and the faulty component identifier is output.

[0093] It is further explained that compared with the existing technology, the combination of weight vectors and historical spectrum databases surpasses the traditional method of coarse positioning relying on a single feature, and improves the accuracy of fault location and the depth of feature analysis.

[0094] S4.4. Extract the probability value of the normal state from the state probability distribution, multiply it by 100, and convert it into a percentage value. This percentage is stored as a health index, representing the health of the aircraft hydraulic system. The health index is then compared with a preset health threshold based on historical fault data analysis. If it is below the health threshold, it is determined to be a very early fault. If it is above or equal to the threshold, the state category is determined based on the state label, such as normal or micro-fault. The state label, health index, and fault component identifier are then integrated to form a structured diagnostic report containing three fields: the state category describes the current state, the health index quantifies the health level, and the fault component identifier indicates the location of the anomaly. This field is blank if location tracking is not triggered.

[0095] Preferably, through health index calculation and structured diagnostic report generation, the quantitative assessment and multi-dimensionality of the aircraft hydraulic system status are integrated together to provide comprehensive health information. Compared with existing technologies, this step transcends the limitations of traditional single indicators through neural network classification and health index quantification, providing a reliable basis for real-time monitoring and fault warning.

[0096] S5. The diagnosis results are presented in real time through the onboard display module and recorded in the onboard black box and the ground maintenance server.

[0097] The specific steps include:

[0098] The diagnostic report is transmitted to the onboard display module (ODM). The ODM is a display device installed in the cockpit, such as a high-resolution LCD screen. The diagnostic results are loaded onto the display interface, with status categories displayed in text, such as micro-faults, and health indicators presented as percentage bar graphs. Faulty components are labeled with specific names, such as hydraulic pumps. The ODM refreshes data at a fixed frequency, ensuring that pilots can view the latest status of the aircraft's hydraulic system in real time. The same diagnostic report is then sent to the onboard black box, a high-temperature and shock-resistant storage device. Data is written via an internal interface and recorded as time-stamped log entries. Simultaneously, the diagnostic report is transmitted to the ground maintenance server via an aviation communication link, such as satellite or 5G network. The server receives the data and stores it in a database for maintenance personnel to review. The transmission process ensures low latency, and the data is stored in encrypted form to prevent loss and tampering.

[0099] This embodiment further provides a method and system for detecting the health status of an aircraft hydraulic system, comprising:

[0100] The acquisition module deploys a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream;

[0101] The fusion module divides the multimodal data stream into two parts: the operating parameter subset and the acoustic emission subset for preprocessing, extracts features from each part to generate feature vectors, and concatenates the two feature vectors into a fused feature vector.

[0102] The quantum processing module encodes and maps the fused feature vector into the quantum initial state, establishes a quantum annealing model, and obtains the state representation result;

[0103] The diagnostic module uses a pre-trained deep neural network to process the state representation results and calculate the health index to obtain structured diagnostic results of the aircraft hydraulic system;

[0104] The recording module presents the diagnostic results in real time through the onboard display module and records them in the onboard black box and ground maintenance server.

[0105] This embodiment also provides a computer device suitable for the case of a method for detecting the health status of an aircraft hydraulic system, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for detecting the health status of an aircraft hydraulic system as proposed in the above embodiment.

[0106] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0107] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for detecting the health status of an aircraft hydraulic system as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0108] In summary, the present invention utilizes quantum annealing technology to process the nonlinear coupling relationships between multiple variables, then generates the state probability distribution of the aircraft hydraulic system through quantum optimization to capture the underlying characteristics of complex states. This step achieves efficient solution capabilities for high-dimensional nonlinear problems, significantly reducing computational complexity and dimensionality limitations compared to classical computational methods, improving the accuracy and real-time performance of state representation, and providing accurate technical support for ultra-early detection of microscopic faults. Furthermore, by detecting the energy mutation rate and frequency domain offset of acoustic emission subsets, transient fault characteristics can be captured, enabling rapid response to faults.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting the health status of an aircraft hydraulic system, characterized by: include, Deploy a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream; The multimodal data stream is divided into two parts: the operating parameter subset and the acoustic emission subset for preprocessing, and features are extracted to generate feature vectors respectively. At the same time, the two feature vectors are spliced ​​into a fusion feature vector. The specific steps include the following: Using a predefined mapping table, the multimodal data stream is divided into an operational parameter subset and an acoustic emission subset; Perform compressed sensing analysis on the acoustic emission subset to obtain the reconstructed acoustic wave signal; Apply a dual-mode trigger strategy, set a fixed-width sliding window, and preset the rate of change threshold and offset limit; Calculating the energy mutation rate of the reconstructed acoustic wave signal, recording a trigger time point when the energy mutation rate exceeds a preset energy threshold, converting the reconstructed acoustic wave signal into the frequency domain using a fast Fourier transform, detecting the shift in the peak frequency, and recording another trigger time point when the shift exceeds a shift limit; When two trigger time points coincide, the features of the reconstructed acoustic wave signal centered at the time point are extracted to obtain the acoustic emission feature vector; The mean and standard deviation of the subset of operating parameters are calculated through statistical analysis to obtain the operating parameter feature vector; The acoustic emission feature vector and the operating parameter feature vector are combined into a fusion feature vector by splicing; The fusion feature vector is encoded and mapped into the quantum initial state, and a quantum annealing model is established to obtain the state representation result. Specifically, the following steps are included: Normalize the fused eigenvector and map it to the initial quantum state; Set the energy function as the core of the quantum annealing model and select the linear scheduling method to complete the configuration of the quantum annealing model; The target state is obtained by minimizing the target problem term, the initial quantum state is adjusted according to the selected linear scheduling method, and the transition to the target state is achieved. The probability distribution of the hydraulic system state is generated by iteration. Use post-processing tools to analyze the evolution trajectory of the quantum state, calculate the weight value of each feature in the fusion feature vector, and form a weight vector; The weight vector is combined with the probability distribution of the hydraulic system state to obtain the state representation result; The state characterization results are processed using a pre-trained deep neural network and the health index is calculated to obtain the structured diagnosis results of the aircraft hydraulic system. The specific steps include the following: Establish a historical spectrum database and set fault thresholds based on historical fault data; Input the state representation result into the pre-trained deep neural network; Extract the probability value of each probability distribution in the state characterization result and calculate it to obtain the preliminary state judgment of the aircraft hydraulic system; The sum of the probability values ​​of the micro-fault state and the severe fault state is compared with the fault threshold, and a state label and a trigger signal are obtained when the fault threshold is exceeded; Extract weight vectors from the state characterization results to determine the features that contribute most to the abnormal state. These features are then matched with patterns in the historical spectrum database to identify the faulty components and obtain structured diagnostic results for the aircraft hydraulic system. The diagnostic results are presented in real time through the onboard display module and recorded in the onboard black box and ground maintenance server.

2. The method for detecting the health status of an aircraft hydraulic system according to claim 1, wherein: Deploy a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream. The specific steps include the following: The collected real-time data are unified by sequence and timestamp, compressed and transmitted to the onboard processing unit to obtain a structured multimodal data stream.

3. The method for detecting the health status of an aircraft hydraulic system according to claim 2, wherein: The structured diagnostic results of the aircraft hydraulic system are obtained, specifically comprising the following steps: The health index is calculated based on the probability value of the normal state, and the status labels and faulty components are integrated to generate a diagnostic report of the aircraft hydraulic system.

4. A method and system for detecting the health status of an aircraft hydraulic system, based on the method for detecting the health status of an aircraft hydraulic system according to any one of claims 1 to 3, characterized in that: include, The acquisition module deploys a multimodal sensor array to collect real-time data from the aircraft hydraulic system and form a structured multimodal data stream; The fusion module divides the multimodal data stream into two parts: the operating parameter subset and the acoustic emission subset for preprocessing, extracts features from each part to generate feature vectors, and concatenates the two feature vectors into a fused feature vector. The quantum processing module encodes and maps the fused feature vector into the quantum initial state, establishes a quantum annealing model, and obtains the state representation result; The diagnostic module uses a pre-trained deep neural network to process the state representation results and calculate the health index to obtain structured diagnostic results of the aircraft hydraulic system; The recording module presents the diagnostic results in real time through the onboard display module and records them in the onboard black box and ground maintenance server.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the aircraft hydraulic system health status detection method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the health status of an aircraft hydraulic system according to any one of claims 1 to 3 are implemented.

Images