Abnormality detection method, device, equipment, medium and product for aircraft brake system

Abstract

This invention discloses a method, apparatus, device, medium, and product for anomaly detection in an aircraft braking system. The method includes: reconstructing observation data of the aircraft braking system within a target time window using a time-series anomaly detection model to obtain reconstructed data; calculating a comprehensive anomaly score for the target time window based on the observation data and the reconstructed data; and determining the anomaly detection result for the target time window based on the comprehensive anomaly score and a dynamic threshold score for the current period. Embodiments of this invention can improve the efficiency of anomaly detection and the accuracy of alarms.

Description

Technical Field

[0001] This invention relates to the field of anomaly detection technology, and in particular to an anomaly detection method, device, equipment, medium and product for an aircraft braking system. Background Technology

[0002] The aircraft braking system is a critical subsystem for takeoff and landing safety, and its performance directly impacts flight safety and operational efficiency. In aborted takeoff scenarios, the aircraft needs to brake suddenly at high speed. The braking system must absorb enormous kinetic energy and decelerate within a short time; abnormal braking pressure at this point can directly lead to catastrophic consequences such as exceeding braking distance limits or runway overrun. During landing deceleration, the aircraft braking system works in conjunction with the thrust reversers to reduce the aircraft to taxiing speed. Braking pressure control determines the landing distance and the lifespan of the braking system. During taxiing braking, the aircraft frequently turns and stops, requiring precise adjustment of braking pressure at low speeds to maintain smooth taxiing. The automatic braking system automatically adjusts braking pressure according to a preset deceleration rate; its failure or abnormality will drastically increase the pilot's workload.

[0003] In existing technologies, anomaly detection methods based on fixed pressure thresholds typically set upper and lower limits for brake pressure based on empirical values. When the data exceeds the threshold, an alarm is triggered. However, this method cannot adapt to complex changes in operating conditions such as different flight stages, ambient temperatures, and runway conditions. It is also difficult to effectively identify hidden anomalies such as gradual degradation of brake performance. At the same time, manual interpretation of telemetry curves relies on ground engineers to analyze and judge the decoded brake pressure curves in conjunction with the flight stage. This has problems such as high dependence on experience, low analysis efficiency, poor real-time performance, and difficulty in meeting the needs of long-term monitoring. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for detecting anomalies in an aircraft braking system, in order to improve the efficiency of anomaly detection and the accuracy of alarms.

[0005] According to one aspect of the present invention, a method for detecting anomalies in an aircraft braking system is provided, comprising: The observation data of the aircraft braking system within the target time window is reconstructed using a time-series anomaly detection model to obtain the reconstructed data of the observation data. The comprehensive anomaly score for the target time window is calculated based on the observed data and the reconstructed data. The anomaly detection result for the target time window is determined based on the comprehensive anomaly score and the dynamic threshold of the score for the current period.

[0006] According to another aspect of the present invention, an anomaly detection device for an aircraft braking system is provided, comprising: The data reconstruction module is used to reconstruct the observation data of the aircraft braking system within the target time window using a time-series anomaly detection model, and obtain the reconstructed data of the observation data. The scoring calculation module is used to calculate the comprehensive anomaly score of the target time window based on the observed data and the reconstructed data; An anomaly detection module is used to determine the anomaly detection result of the target time window based on the comprehensive anomaly score and the dynamic threshold of the score for the current period.

[0007] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the abnormality detection method for an aircraft braking system according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the abnormal detection method of the aircraft braking system according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the abnormal detection method of the aircraft braking system according to any embodiment of the present invention.

[0010] This invention captures the time-varying correlation of multidimensional parameters through a sliding window mechanism and combines it with dynamic threshold generation based on statistical features, so that the judgment boundary adaptively drifts with the operating conditions, effectively solving the false alarm problem caused by environmental switching and improving the efficiency of anomaly detection and alarm accuracy.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1This is a flowchart of an anomaly detection method for an aircraft braking system according to an embodiment of the present invention; Figure 2 This is a flowchart of an anomaly detection method for an aircraft braking system according to another embodiment of the present invention; Figure 3 This is a structural schematic diagram of an abnormality detection device for an aircraft braking system according to another embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., used in this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Figure 1 This is a flowchart illustrating an anomaly detection method for an aircraft braking system according to an embodiment of the present invention. This embodiment is applicable to situations where anomalies are detected in the braking system during aircraft braking. The method can be executed by an anomaly detection device for the aircraft braking system, which can be implemented in hardware and / or software and can be configured in an electronic device with corresponding data processing capabilities. Figure 1 As shown, the method includes: S110. The observation data of the aircraft braking system within the target time window is reconstructed using a time-series anomaly detection model to obtain the reconstructed data of the observation data.

[0017] S120. Calculate the comprehensive anomaly score of the target time window based on the observed data and the reconstructed data.

[0018] S130. Determine the anomaly detection result of the target time window based on the comprehensive anomaly score and the dynamic threshold of the score for the current period.

[0019] The observation data consists of observations of at least two dimensions of the aircraft braking system, including brake pressure, automatic braking level, brake temperature, and aircraft speed.

[0020] Braking pressure includes the aircraft's left inner brake pressure, left outer brake pressure, right inner brake pressure, and right outer brake pressure.

[0021] Specifically, relevant observational data on the aircraft's braking system during flight are collected. Data sources include the aircraft's rapid access recorder, aircraft condition monitoring system, integrated aircraft data system, and flight parameter recording system. The observational data is then normalized, and one of the following methods is selected based on the data distribution characteristics: Min-Max normalization: Applicable to observational data with known upper and lower bounds (such as brake pressure, automatic braking level), it linearly maps the data to the [0,1] interval. Z-score standardization: Applicable to observational data with relatively symmetrical distributions (such as brake temperature and aircraft speed), it transforms them into a standard normal distribution.

[0022] A sliding window method is used to extract observation data from at least two time windows from the normalized observation data (which is essentially multi-dimensional time series data). The observation data within the target time window is then input into a pre-trained time series anomaly detection model, which infers theoretically normal reconstructed data based on the observation data.

[0023] By comparing the reconstructed data and the observed data using mathematical methods, the degree of anomaly in the observed data is determined, and a numerical comprehensive anomaly score is used to quantify the specific degree of anomaly.

[0024] The dynamic threshold for scoring changes dynamically with the anomaly score. The dynamic threshold for the current period is compared with the overall anomaly score, and the degree of anomaly in the observed data is determined based on the comparison result, which is then output as the anomaly detection result. The advantage of a dynamic threshold over a fixed threshold is that when changes in flight conditions (such as different runway lengths, different landing weights, wet runways, etc.) cause changes in the normal fluctuation range of brake pressure, the dynamic threshold adaptively adjusts, effectively reducing the false alarm rate.

[0025] This invention captures the time-varying correlation of multidimensional parameters through a sliding window mechanism and combines it with dynamic threshold generation based on statistical features, so that the judgment boundary adaptively drifts with the operating conditions, effectively solving the false alarm problem caused by environmental switching and improving the efficiency of anomaly detection and alarm accuracy.

[0026] Based on the above embodiments, optionally, determining the anomaly detection result of the target time window according to the comprehensive anomaly score and the dynamic threshold of the score in the current period includes: If the overall anomaly score is greater than the dynamic threshold of the score in the current period and the duration does not reach the first time threshold, then the transient interference caused by the minor anomaly is determined as the anomaly detection result of the target time window. If the overall anomaly score is greater than the dynamic threshold of the current period and the duration reaches the first time threshold but not the second time threshold, then the moderate anomaly caused by performance degradation is determined as the anomaly detection result of the target time window. If the comprehensive anomaly score is greater than the dynamic threshold of the current period and the duration reaches the second time threshold, or if the anomaly score is greater than the product of the dynamic threshold of the current period and the severity amplification coefficient, then the serious anomaly caused by the fault risk is determined as the anomaly detection result of the target time window.

[0027] Specifically, based on the comprehensive anomaly score Dynamic threshold of score for the current period Based on the comparison relationship and combined with the cumulative effect of the time window, the abnormal state of the braking system is divided into three levels for graded early warning output: Level 3 anomaly (minor anomaly / transient disturbance): Triggering conditions: Furthermore, the duration Δt did not reach the first time threshold. .

[0028] Status Definition and Response: This type of anomaly is usually caused by random noise from sensors, transient environmental interference, or non-faulty transient fluctuations. The handling measure is as follows: the system automatically records the anomaly event but does not trigger a real-time audible and visual alarm. Instead, it outputs a low-priority prompt message to the ground station monitoring system to remind maintenance personnel to pay attention to it during subsequent routine maintenance.

[0029] Level 2 anomaly (moderate anomaly / performance degradation): Triggering conditions: And the duration Δt reaches the first time threshold. However, the second time threshold was not reached. (Right now ).

[0030] Status Definition and Response: This type of anomaly indicates a progressive degradation characteristic of the braking system (such as accelerated brake disc wear, minor seal leakage, or sluggish hydraulic system response). The handling measures are as follows: The system generates a performance degradation alarm and automatically recommends scheduled maintenance within a limited preset operating cycle in the maintenance management system. Simultaneously, the system records the score evolution trend and multi-dimensional correlation parameter matrix during the anomaly period, providing data support for subsequent troubleshooting.

[0031] Level 1 anomaly (critical anomaly / failure risk): Triggering conditions: The event will be triggered if one of the following conditions is met: Abnormal scores showed a step surge, satisfying (in (The severity amplification factor is set); the duration Δt reaches or exceeds the second time threshold. (Right now ).

[0032] Status Definition and Response: This type of anomaly indicates a major malfunction in the braking system or a risk of immediate functional failure (such as severe hydraulic line leakage, pressure regulator failure, or severe asymmetry between the left and right brakes). The handling measures are as follows: the system immediately triggers the highest-level emergency alarm, generating immediate maintenance instructions or abnormal inspection procedure linkage suggestions.

[0033] In addition, duration threshold and The data sampling frequency is set to ensure that high-frequency noise can be effectively filtered and persistent physical degradation trends can be accurately captured.

[0034] Based on the above embodiments, optionally, the temporal anomaly detection model is obtained by training a Transformer model based on a self-attention mechanism; the training samples of the temporal anomaly detection model are obtained by extracting historical observation data of the aircraft braking system through a sliding window.

[0035] Specifically, a sliding window method is used to construct training samples for the temporal anomaly detection model from historical observation data of the aircraft braking system. Let the historical observation data be... ,in for Moment dimensional observation vector ( (parameter dimension), sliding window length is Each time step corresponds to a physical time range determined by converting the sampling frequency into a corresponding dynamic observation window. The sliding window movement step size is... Each time step generates multiple training samples X. t It is expressed as follows: The sliding window mechanism can retain complete dynamic information on pressure buildup, maintenance, and release during braking, while capturing the time-varying correlations between various parameters. Window length The selection is based on the typical time constant of the braking system pressure response, and it is necessary to ensure that the window can effectively cover the core dynamic characteristics of pressure build-up and the complete braking event in a single braking operation.

[0036] The temporal anomaly detection model is based on the self-attention mechanism. It captures the long-distance dependencies of the input temporal data through a multi-head attention layer. The core computation module is multi-head self-attention.

[0037] The loss function used during model training is the mean squared reconstruction error (MSE): in, The training samples are used as input to the model. The reconstructed samples output by the model. This represents the total number of training samples. After model training converges, the reconstruction error is relatively small for normal samples in the test samples; however, for abnormal samples in the test samples, the reconstruction error will significantly increase because the model did not learn their potential abnormal patterns during the training phase. Therefore, the magnitude of the reconstruction error can be directly used as a score indicator to measure the degree of sample abnormality. A deep learning-based temporal anomaly detection model automatically extracts temporal dependencies, replacing the traditional, tedious manual curve interpretation work. The algorithm has high real-time performance and can seamlessly integrate with ground monitoring, SMS push notifications, and automatic triggering systems, significantly improving the efficiency of intelligent aviation operations and maintenance and the safety assurance capabilities for takeoff and landing of large-scale fleets.

[0038] Figure 2 This is a flowchart illustrating an anomaly detection method for an aircraft braking system, provided in another embodiment of the present invention. This embodiment is an optimization and improvement upon the above embodiment. Figure 2 As shown, the method includes: S210. The observation data of the aircraft braking system within the target time window is reconstructed using a time-series anomaly detection model to obtain the reconstructed data of the observation data.

[0039] S220. Calculate the first anomaly score based on the absolute error between the observed data and the reconstructed data.

[0040] S230. Calculate the second anomaly score based on the squared error of the observed data and the reconstructed data.

[0041] S240. The first abnormal score and the second abnormal score are weighted and summed to obtain the comprehensive abnormal score for the target time window.

[0042] Specifically, this refers to the actual observation data within the target time window. Reconstructing data with model inference The deviation between the two is calculated to evaluate the anomaly score of the current state. This invention supports the following two complementary anomaly scoring mechanisms: Mechanism 1: First outlier score based on absolute value error in, The first anomaly score is more sensitive to moderate deviations and is better suited for detecting gradual performance degradation or early, subtle anomalies.

[0043] Mechanism 2: Outlier Scores Based on Squared Error in, The second anomaly score applies a high non-linear penalty weight to large deviations, making it suitable for the rapid capture of sudden, large-amplitude anomalies.

[0044] In multi-dimensional time-series scenarios, the comprehensive anomaly score is determined using a weighted average: in, To calculate the overall abnormal score, , These are weighting coefficients, which can be determined based on prior knowledge.

[0045] S250. Determine the anomaly detection result of the target time window based on the comprehensive anomaly score and the dynamic threshold of the score for the current period.

[0046] Based on the above embodiments, optionally, after calculating the comprehensive anomaly score of the target time window based on the observation data and the reconstructed data, the method further includes: Calculate the mean and standard deviation of the combined anomaly scores for at least two time windows within the current period; The standard deviation is multiplied by the confidence coefficient, and the result is added to the mean to obtain the dynamic threshold of the score for the next period.

[0047] Specifically, to adapt to the changing distribution of brake pressure data under different operating conditions, this invention employs a dynamic threshold mechanism based on statistical characteristics to achieve periodic updates of the dynamic score threshold: T pot =μ score +k*σ score Among them, T pot μ is the dynamic score threshold for the next period. scoreσ is the average of the combined anomaly scores for at least two time windows within the current period. score Let k be the standard deviation of the combined anomaly scores for at least two time windows within the current period, and k be the confidence coefficient. The configuration of the confidence coefficient k determines the sensitivity of the system: the larger the value of k, the higher the tolerance margin.

[0048] The number of time windows included in each period is pre-defined. After calculating the comprehensive anomaly score for each of these number (≥2) time windows, the dynamic score threshold for the next period is calculated based on the statistical characteristics (mean and standard deviation) of the comprehensive anomaly scores for each time window within that update period. The next period will no longer use the dynamic score threshold of the current period used in the previous period, but will instead use the newly calculated dynamic score threshold.

[0049] The embodiments of the present invention provide a complementary scoring mechanism based on absolute error and squared error, which can capture progressive degradation such as brake disc wear and minor leakage through cumulative effect, and can quickly capture pressure changes through high penalty weight, and realize condition-based maintenance through a multi-level early warning mechanism.

[0050] Figure 3 This is a schematic diagram of the structure of an anomaly detection device for an aircraft braking system, provided in another embodiment of the present invention. Figure 3 As shown, the device includes: Data reconstruction module 310 is used to reconstruct the observation data of the aircraft braking system within the target time window through a time series anomaly detection model, and obtain the reconstructed data of the observation data. The scoring calculation module 320 is used to calculate the comprehensive anomaly score of the target time window based on the observed data and the reconstructed data. The anomaly detection module 330 is used to determine the anomaly detection result of the target time window based on the comprehensive anomaly score and the dynamic threshold of the score in the current period.

[0051] The abnormal detection device for the aircraft braking system provided in this embodiment of the invention can execute the abnormal detection method for the aircraft braking system provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0052] Optionally, the score calculation module 320 is specifically used for: The first anomaly score is calculated based on the absolute error between the observed data and the reconstructed data. The second anomaly score is calculated based on the squared error of the observed and reconstructed data; The first and second anomaly scores are weighted and summed to obtain the comprehensive anomaly score for the target time window.

[0053] Optionally, the device further includes a threshold update module for: Calculate the mean and standard deviation of the combined anomaly scores for at least two time windows within the current period; The standard deviation is multiplied by the confidence coefficient, and the result is added to the mean to obtain the dynamic threshold of the score for the next period.

[0054] Optionally, the anomaly detection module 330 is specifically used for: If the overall anomaly score is greater than the dynamic threshold of the score in the current period and the duration does not reach the first time threshold, then the transient interference caused by the minor anomaly is determined as the anomaly detection result of the target time window. If the overall anomaly score is greater than the dynamic threshold of the current period and the duration reaches the first time threshold but not the second time threshold, then the moderate anomaly caused by performance degradation is determined as the anomaly detection result of the target time window. If the comprehensive anomaly score is greater than the dynamic threshold of the current period and the duration reaches the second time threshold, or if the anomaly score is greater than the product of the dynamic threshold of the current period and the severity amplification coefficient, then the serious anomaly caused by the fault risk is determined as the anomaly detection result of the target time window.

[0055] Optionally, the temporal anomaly detection model is obtained by training a Transformer model based on a self-attention mechanism; the training samples of the temporal anomaly detection model are obtained by extracting aircraft braking system data through a sliding window.

[0056] Optionally, the observation data includes the aircraft's left inner brake pressure, left outer brake pressure, right inner brake pressure, and right outer brake pressure.

[0057] The aircraft braking system anomaly detection device described in further detail can also execute the aircraft braking system anomaly detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0058] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0059] like Figure 4As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 and a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded from storage unit 48 into the RAM 43. The RAM 43 can also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0060] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0061] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as anomaly detection methods for aircraft braking systems.

[0062] In some embodiments, the anomaly detection method for the aircraft braking system can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the anomaly detection method for the aircraft braking system described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the anomaly detection method for the aircraft braking system by any other suitable means (e.g., by means of firmware).

[0063] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0064] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0065] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0066] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0067] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0068] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0069] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0070] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An abnormality detection method for an aircraft brake system, characterized by, The method includes: The observation data of the aircraft braking system within the target time window is reconstructed using a time-series anomaly detection model to obtain the reconstructed data of the observation data. The comprehensive anomaly score for the target time window is calculated based on the observed data and the reconstructed data. The anomaly detection result for the target time window is determined based on the comprehensive anomaly score and the dynamic threshold of the score for the current period.

2. The method according to claim 1, characterized in that, The calculation of the comprehensive anomaly score for the target time window based on the observed data and reconstructed data includes: The first anomaly score is calculated based on the absolute error between the observed data and the reconstructed data. The second anomaly score is calculated based on the squared error of the observed and reconstructed data; The first and second abnormal scores are weighted and summed to obtain the comprehensive abnormal score for the target time window.

3. The method according to claim 2, characterized in that, After calculating the comprehensive anomaly score of the target time window based on the observed data and reconstructed data, the method further includes: Calculate the mean and standard deviation of the combined anomaly scores for at least two time windows within the current period; The standard deviation is multiplied by the confidence coefficient, and the result is added to the mean to obtain the dynamic threshold of the score for the next period.

4. The method according to claim 1, characterized in that, The step of determining the anomaly detection result of the target time window based on the comprehensive anomaly score and the dynamic threshold of the score for the current period includes: If the overall anomaly score is greater than the dynamic threshold of the score in the current period and the duration does not reach the first time threshold, then the transient interference caused by the minor anomaly is determined as the anomaly detection result of the target time window. If the overall anomaly score is greater than the dynamic threshold of the current period and the duration reaches the first time threshold but not the second time threshold, then the moderate anomaly caused by performance degradation is determined as the anomaly detection result of the target time window. If the comprehensive anomaly score is greater than the dynamic threshold of the current period and the duration reaches the second time threshold, or if the anomaly score is greater than the product of the dynamic threshold of the current period and the severity amplification coefficient, then the serious anomaly caused by the fault risk is determined as the anomaly detection result of the target time window.

5. The method according to claim 1, characterized in that, The temporal anomaly detection model is obtained by training a Transformer model based on a self-attention mechanism; the training samples of the temporal anomaly detection model are obtained by extracting aircraft braking system data through a sliding window.

6. The method according to claim 1, characterized in that, The observation data includes the aircraft's left inner brake pressure, left outer brake pressure, right inner brake pressure, and right outer brake pressure.

7. An anomaly detection device for an aircraft braking system, characterized in that, The device includes: The data reconstruction module is used to reconstruct the observation data of the aircraft braking system within the target time window using a time-series anomaly detection model, and obtain the reconstructed data of the observation data. The scoring calculation module is used to calculate the comprehensive anomaly score of the target time window based on the observed data and the reconstructed data; An anomaly detection module is used to determine the anomaly detection result of the target time window based on the comprehensive anomaly score and the dynamic threshold of the score for the current period.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the abnormal detection method for the aircraft braking system according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the abnormal detection method for the aircraft braking system according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the abnormal detection method for the aircraft braking system as described in any one of claims 1-6.

Images