An aircraft landing gear power switching safety monitoring method and system

Abstract

The application provides an aircraft landing gear power switching safety monitoring method and system, the method comprises the following steps: acquiring the hydraulic oil tank oil quantity data at each time within a preset time period, the end time of the preset time period is the current time; judging whether the hydraulic oil tank is abnormal within the preset time period according to all the hydraulic oil tank oil quantity data, if abnormal, calculating the score of the aircraft landing gear safety switching; analyzing the score of the aircraft landing gear safety switching, if less than the preset score threshold, acquiring the historical maintenance record information, and screening the historical maintenance record information, and sending the screening result to the staff for helping the staff to overhaul. Through the steps in the application, the current aircraft landing gear switching can be monitored according to the hydraulic oil tank oil quantity data, and the related maintenance record can also be screened in advance according to the monitoring result, which is helpful to improve the operation efficiency of the aircraft.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of aviation technology, in particular to an aviation landing gear power switching safety monitoring method and system. BACKGROUND

[0002] Hydraulic oil plays a core role in energy transmission, lubrication guarantee and sealing cooling in aviation landing gear power switching. Among them, as a power transmission medium, it converts the mechanical energy of the standby pump into hydraulic energy to drive the actuator to complete the landing gear extension and retraction, which is the "lifeblood" to ensure the normal operation of the landing gear. Once the hydraulic oil fails, it will cause disastrous consequences, and it is one of the most serious failures in the aviation system. Therefore, it is necessary to monitor the safety of the hydraulic oil to ensure the normal flight of the aircraft. SUMMARY

[0003] The purpose of the present application is to provide an aviation landing gear power switching safety monitoring method and system to improve the above problems.

[0004] In order to achieve the above purpose, the embodiments of the present application provide the following technical solutions:

[0005] On the one hand, the present application provides an aviation landing gear power switching safety monitoring method, which comprises:

[0006] Obtaining hydraulic oil tank oil data at each time within a preset time period, the end time of the preset time period being the current time;

[0007] According to all the hydraulic oil tank oil data, it is judged whether the hydraulic oil tank is abnormal within the preset time period, and if abnormal, the score of the aviation landing gear safety switching is calculated;

[0008] The score of the aviation landing gear safety switching is analyzed, and if it is less than the preset score threshold, the historical maintenance record information is obtained, and the historical maintenance record information is screened, and the screening result is sent to the staff for helping the staff to overhaul.

[0009] Secondly, the present application provides an aviation landing gear power switching safety monitoring system, which comprises:

[0010] The acquisition module is used for acquiring the hydraulic oil tank oil data at each time within a preset time period, the end time of the preset time period being the current time;

[0011] The judgment module is used for judging whether the hydraulic oil tank is abnormal within the preset time period according to all the hydraulic oil tank oil data, and if abnormal, the score of the aviation landing gear safety switching is calculated;

[0012] The screening module is used for analyzing the score of the safety switching of the aircraft landing gear, obtaining historical maintenance record information if the score is less than a preset score threshold, and screening the historical maintenance record information, and sending the screening result to the staff for helping the staff to overhaul.

[0013] In a third aspect, the embodiments of the present application provide an aircraft landing gear power switching safety monitoring device, which comprises a memory and a processor.

[0014] In a fourth aspect, the embodiments of the present application provide a readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the aircraft landing gear power switching safety monitoring method.

[0015] The beneficial effects of the present application are:

[0016] The present application first analyzes the overall trend of the hydraulic oil quantity data in the preset period, and then discriminates the instantaneous abnormal state of the oil quantity data at the current time, forming an efficient double criterion mechanism. Compared with the determination method relying on only a single time point or a single time window, this design has significant advantages, that is, it can effectively avoid false positives caused by sensor instantaneous interference, noise signals or accidental data fluctuations.

[0017] In the present application, after the score of the current aircraft landing gear safety switching is lower than the preset score threshold, the historical maintenance records can be intelligently mined and screened. For the rapid matching of historical maintenance schemes with reference value, the maintenance personnel can quickly locate the fault root cause and develop a maintenance plan, significantly shortening the troubleshooting time, reducing the maintenance cost, and improving the operation efficiency of the aircraft.

[0018] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be understood from the practice of the present application. The purpose and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0020] Figure 1This is a schematic diagram of the safety monitoring method for aircraft landing gear power switching described in this embodiment of the invention;

[0021] Figure 2 This is a schematic diagram of the structure of the aircraft landing gear power switching safety monitoring system described in this embodiment of the invention;

[0022] Figure 3 This is a schematic diagram of the structure of the aircraft landing gear power switching safety monitoring device described in this embodiment of the invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0024] It should be noted that similar reference numerals or letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0025] Example 1

[0026] like Figure 1 As shown in the figure, this embodiment provides a method for monitoring the safety of aircraft landing gear power switching, which includes steps S1, S2 and S3.

[0027] Step S1: Obtain hydraulic oil tank oil volume data at each moment within a preset time period, with the current moment being the end time of the preset time period;

[0028] In this step, the length of the preset time period can be customized; acquiring hydraulic tank oil level data is a mature technology in the aviation field, and the acquisition method will not be described in detail in this embodiment; the hydraulic tank oil level data at each moment within the preset time period can also be understood as time-series data; this embodiment is applicable to aircraft containing hydraulic tanks;

[0029] Step S2, judging whether the hydraulic oil tank is abnormal in the preset time period according to all the hydraulic oil tank oil quantity data, and if abnormal, calculating the score of the safety switching of the aircraft landing gear;

[0030] The traditional monitoring only triggers an alarm after the oil quantity is lower than a fixed threshold, and the behavior is lagging, while the present step can identify abnormal signs in advance through continuous trend analysis of the oil quantity data before the fault has caused substantial impact. The specific implementation steps of the present step include step S21 and step S22.

[0031] Step S21, fitting the hydraulic oil tank oil quantity data at each time in the preset time period by using a moving average to obtain the fitting data corresponding to each time in the preset time period; calculating the difference between the fitting data at each time and the hydraulic oil tank oil quantity data, and recording the absolute value of the difference as the first data corresponding to each time;

[0032] The present step can be understood as follows: the hydraulic oil tank oil quantity data at each time in the preset time period is time series data, which can also be referred to as hydraulic oil tank oil quantity time series data; the fitting time series is obtained after fitting, and the first data is obtained by calculating the difference between the fitting data corresponding to each time and the true value; a weighted moving average model can also be used for fitting, and the method is not limited;

[0033] Step S22, judging whether the hydraulic oil tank is abnormal in the preset time period according to all the first data, and if abnormal, calculating the score of the safety switching of the aircraft landing gear.

[0034] The specific implementation steps of the present step include step S221 and step S222.

[0035] Step S221, summing all the first data to obtain second data, summing the fitting data corresponding to each time in the preset time period to obtain third data; comparing the ratio of the square root of the second data to the third data with a preset abnormal threshold range, if the ratio is within the preset abnormal threshold range, it is judged that the hydraulic oil tank oil quantity data in the preset time period is abnormal; calculating the mean and variance of all the first data, and summing the mean and variance to obtain fourth data; summing the fitting data at the current time and the fourth data to obtain fifth data, subtracting the fourth data from the fitting data at the current time to obtain sixth data; judging whether the hydraulic oil tank oil quantity data at the current time is less than the sixth data or greater than the fifth data, if yes, it is judged that the hydraulic oil tank oil quantity data at the current time is abnormal;

[0036] In this step, it is divided into two parts, the first part judges whether the hydraulic oil tank oil quantity data in the preset period is abnormal, and the other part judges whether the hydraulic oil tank oil quantity data at the current time is abnormal, when both are abnormal, it is determined that the hydraulic oil tank is abnormal; That is, in the design of this step, the abnormality judgment mechanism adopts a double verification logic architecture: first, the overall trend of the hydraulic oil quantity data in the preset period is analyzed, and then the instantaneous abnormal state of the oil quantity data at the current time is judged. Only when both conditions are met, the system finally determines that the hydraulic oil tank is abnormal. This phased composite criterion strategy has a significant advantage over the single time point or single time window determination method: it can effectively avoid false positives caused by sensor transient interference, noise signals or accidental data fluctuations;

[0037] Step S222, when the hydraulic oil tank oil quantity data in the preset period is abnormal and the hydraulic oil tank oil quantity data at the current time is abnormal, it is determined that the current hydraulic oil tank is abnormal; When it is determined that the current hydraulic oil tank is abnormal, the failure rate of the current hydraulic oil tank is calculated, and the influence degree of the oil tank oil quantity data on the power switching of the aircraft landing gear is obtained. The influence degree of the oil tank oil quantity data on the power switching of the aircraft landing gear is multiplied by the failure rate to obtain the seventh data, and the preset first value is subtracted from the seventh data to obtain the score of the current aircraft landing gear safety switching.

[0038] In this step, after the failure rate is calculated, the influence degree of the oil tank oil quantity data on the power switching of the aircraft landing gear is obtained, and the influence degree of the oil tank oil quantity data on the power switching of the aircraft landing gear is artificially set. The preset first value can be 1. At the same time, the specific implementation steps of calculating the failure rate of the current hydraulic oil tank when it is determined that the current hydraulic oil tank is abnormal in this step include step S2221.

[0039] Step S2221, identify the change point in the hydraulic oil tank oil quantity data at each time in the preset period using the CUSUM algorithm, divide all the oil tank oil quantity data in the preset period into multiple data sets according to the change point, and calculate the Shannon entropy corresponding to each data set. Input the Shannon entropy corresponding to each data set into the preset abnormal score detection model to obtain the abnormal score corresponding to each data set, and take the maximum abnormal score as the abnormal score of the current hydraulic oil tank. Wherein, the training method of the abnormal score detection model is to obtain historical oil tank oil quantity time series data, identify the change point in the historical oil tank oil quantity time series data, divide the historical oil tank oil quantity time series data into multiple subsets according to the change point, calculate the Shannon entropy of each subset, and obtain the abnormal score of the hydraulic oil tank corresponding to each subset. Take the Shannon entropy as the input of the convolutional neural network model, and take the abnormal score of the hydraulic oil tank as the output to train the convolutional neural network model to obtain the abnormal score detection model. The ratio between the abnormal score of the current hydraulic oil tank and the preset maximum abnormal score is taken as the failure rate of the current hydraulic oil tank.

[0040] In this step, the method of obtaining the maximum abnormal score can be that, when marking the abnormal score of the hydraulic oil tank corresponding to each subset, the maximum abnormal score appearing in the marking process is taken as the preset maximum abnormal score appearing in step S2221.

[0041] Step S3, analyze the score of the safety switching of the aircraft landing gear, if less than the preset score threshold, obtain the historical maintenance record information, and screen the historical maintenance record information, and send the screening result to the staff for helping the staff to repair.

[0042] In this step, if less than the preset score threshold, the aircraft landing gear switching may have problems, and finally maintenance will be carried out, so the relevant historical maintenance records are screened out in advance and sent to the relevant maintenance personnel, which can improve the efficiency of subsequent maintenance; The specific implementation steps of this step include step S31.

[0043] Step S31, analyze the score of the safety switching of the aircraft landing gear, if less than the preset score threshold, obtain a plurality of first maintenance record information in a first historical period, the first maintenance record information includes the reason for maintenance, and the reason for maintenance includes that the hydraulic oil tank failure causes the aircraft landing gear power switching to have problems; At the same time, a plurality of second maintenance record information in a second historical period is obtained, the second historical period is located after the first historical period, the second maintenance record information is clustered to obtain a plurality of first clustering clusters, each first clustering cluster is labeled, a preset number of second maintenance record information is randomly selected from each first clustering cluster, which is taken as a training sample and each second maintenance record information corresponding to the label is taken as a label information to train the model, and a classification model is obtained; According to the classification model, the final target maintenance record information is screened out, and the final target maintenance record information is sent to the staff.

[0044] In this step, the format of the maintenance record information can be an image format, that is, the maintenance record information is saved in the form of an image, and the image contains information such as the reason for maintenance; When the score of the safety switching of the aircraft landing gear is less than the preset score threshold, the alarm system can also be triggered to prompt that there may be problems in the aircraft landing gear switching process, so as to remind the staff to take corresponding measures.

[0045] Meanwhile, in this step, the first maintenance record information is obtained by screening all historical maintenance record information by manual; specifically, the historical maintenance record in which the maintenance reason includes that the hydraulic oil tank failure causes the problem of the aircraft landing gear power switching is screened; in consideration of saving labor and improving efficiency, the second maintenance record information is not manually screened, but is screened according to the mode of this step; in this step, the label of each second maintenance record information is the label corresponding to the first clustering cluster to which the second maintenance record information belongs, and the second maintenance record information in the same first clustering cluster has the same label; training the model by taking the second maintenance record information as the training sample and taking the label corresponding to each second maintenance record information as the annotation information can be understood as training the xgboost model by using the training sample to obtain the classification model.

[0046] Meanwhile, in this step, the specific implementation steps of screening the final target maintenance record information according to the classification model include steps S311 and S312.

[0047] Step S311, classifying the first maintenance record information by using the classification model, counting the number of the first maintenance record information corresponding to each label, and marking the label corresponding to the maximum number as a target label; screening the second maintenance record information with the target label from the first maintenance record information set, and recording each first maintenance record information and second maintenance record information in the set as eighth data; extracting the feature data of each eighth data, clustering all eighth data by using the K-means clustering algorithm, obtaining a plurality of second clustering clusters; for each second clustering cluster, combining the eighth data in each second clustering cluster in pairs to form an eighth data pair, counting the first number of eighth data pairs, and calculating the similarity between the two eighth data in each eighth data pair, counting the second number of eighth data pairs whose similarity does not exceed the preset similarity threshold.

[0048] In this step, screening the second maintenance record information with the target label from the first maintenance record information set completes the screening of the second maintenance record information, and the screened second maintenance record information is identified as including the maintenance reason, and the maintenance reason includes that the hydraulic oil tank failure causes the problem of the aircraft landing gear power switching; in this step, assuming that the number of eighth data in each clustering cluster is N, then the number of eighth data pairs is , that is, the first number is .

[0049] In this step, the feature data of each eighth data can be extracted in the following way:

[0050] For each piece of eighth data, the first feature extraction model and the second feature extraction model are used to obtain feature data; wherein the first feature extraction model includes two convolution layers, and the second feature extraction model includes two Transformer modules; first, the eighth data is input into the first convolution layer to obtain first feature information at each position, and then the eighth data is input into the first Transformer module to obtain second feature information at each position; after adding the first feature information and the second feature information at each position, third feature information corresponding to each position is obtained; all third feature information is input into the second convolution layer to obtain fourth feature information; the first feature information, the second feature information and the fourth feature information are arranged in sequence to form first target feature information; all third feature information is input into the second Transformer module to obtain fifth feature information; the first feature information, the second feature information and the fifth feature information are arranged in sequence to form second target feature information; the first target feature information and the second target feature information are arranged in sequence to form feature data corresponding to each piece of eighth data.

[0051] In this step, each piece of eighth data can be regarded as an image data, and when feature extraction is performed, feature information at each position in the image can be obtained; when arranging and combining, each feature information is arranged in sequence, for example, the first feature information A, the second feature information B and the fourth feature information C are arranged in sequence to form (A, B, C); the arrangement and combination logic in the formation of the second target feature information and the feature data is the same as above.

[0052] In step S312, a first logarithm is added to the number of eighth data in each second clustering cluster to obtain ninth data, and a ratio between a second logarithm and the ninth data is recorded as a first ratio; the number of eighth data in each second clustering cluster is subtracted by a preset second value to obtain tenth data, and a ratio between the tenth data and the ninth data is recorded as a second ratio; it is judged whether the first ratio is greater than the second ratio, if greater, the eighth data contained in this second clustering cluster is deleted, and the remaining eighth data is taken as the final target maintenance record information.

[0053] In this step, the ninth data can be understood as equal to N ; the second value can be 1; when the first ratio is greater than the second ratio, it is determined that this clustering cluster is abnormal, and therefore it is deleted; the logic of step S311 and step S312 is that the second maintenance record information is first preliminarily screened, and then the screened second maintenance record information and the first maintenance record information are further abnormally screened, and the abnormal data is deleted, and thus the final target maintenance record information is obtained.

[0054] Example 2

[0055] As Figure 2 shown, the embodiment provides an aircraft landing gear power switching safety monitoring system, which comprises an acquisition module 1, a judgment module 2 and a screening module 3.

[0056] The acquisition module 1 is used for acquiring the hydraulic oil tank oil quantity data at each time within a preset time period, and the cutoff time of the preset time period is the current time;

[0057] The judgment module 2 is used for judging whether the hydraulic oil tank is abnormal within the preset time period according to all the hydraulic oil tank oil quantity data, and if abnormal, calculating the score of the aircraft landing gear safety switching;

[0058] The screening module 3 is used for analyzing the score of the aircraft landing gear safety switching, and if less than a preset score threshold, acquiring the historical maintenance record information and screening the historical maintenance record information, and sending the screening result to the staff for helping the staff to overhaul.

[0059] In one specific embodiment of the present disclosure, the judgment module 2 further comprises a first calculation unit 21 and a judgment unit 22.

[0060] The first calculation unit 21 is used for fitting the hydraulic oil tank oil quantity data at each time within the preset time period by using the moving average to obtain the fitting data corresponding to each time within the preset time period; calculating the difference between the fitting data at each time and the hydraulic oil tank oil quantity data, and recording the absolute value of the difference as the first data corresponding to each time;

[0061] The judgment unit 22 is used for judging whether the hydraulic oil tank is abnormal within the preset time period according to all the first data, and if abnormal, calculating the score of the aircraft landing gear safety switching.

[0062] In one specific embodiment of the present disclosure, the judgment unit 22 further comprises a second calculation unit 221 and a third calculation unit 222.

[0063] The second calculation unit 221 is used for summing all the first data to obtain second data, summing the fitting data corresponding to each time within the preset time period to obtain third data, comparing the ratio of the square root of the second data to the third data with a preset abnormal threshold range, if the ratio is within the preset abnormal threshold range, judging that the hydraulic oil tank oil quantity data within the preset time period is abnormal; calculating the mean and variance of all the first data, summing the mean and variance to obtain fourth data; summing the fitting data at the current time and the fourth data to obtain fifth data, subtracting the fourth data from the fitting data at the current time to obtain sixth data; judging whether the hydraulic oil tank oil quantity data at the current time is less than the sixth data or greater than the fifth data, if yes, judging that the hydraulic oil tank oil quantity data at the current time is abnormal;

[0064] The third calculation unit 222 is configured to determine that the current hydraulic oil tank is abnormal when the hydraulic oil tank oil quantity data is abnormal in the preset period and the hydraulic oil tank oil quantity data at the current time is abnormal, calculate a failure rate of the current hydraulic oil tank when it is determined that the current hydraulic oil tank is abnormal, and obtain an influence degree of the oil tank oil quantity data on the power switching of the aircraft landing gear, multiply the influence degree of the oil tank oil quantity data on the power switching of the aircraft landing gear by the failure rate to obtain a seventh data, and subtract the seventh data from the preset first value to obtain a score of the current aircraft landing gear safety switching.

[0065] In one specific embodiment of the present disclosure, the third calculation unit 222 further comprises a fourth calculation unit 2221.

[0066] The fourth calculation unit 2221 is configured to identify a change point in the hydraulic oil tank oil quantity data at each time in the preset period by using a CUSUM algorithm, divide all the oil tank oil quantity data in the preset period into a plurality of data sets according to the change points, calculate the Shannon entropy corresponding to each data set, input the Shannon entropy corresponding to each data set into a preset abnormal score detection model to obtain an abnormal score corresponding to each data set, and take the maximum abnormal score as the abnormal score of the current hydraulic oil tank. The training method of the abnormal score detection model is to obtain historical oil tank oil quantity time series data, identify change points in the historical oil tank oil quantity time series data, divide the historical oil tank oil quantity time series data into a plurality of subsets according to the change points, calculate the Shannon entropy of each subset, obtain the abnormal score of the hydraulic oil tank corresponding to each subset, take the Shannon entropy as the input of a convolutional neural network model, take the abnormal score of the hydraulic oil tank as the output, train the convolutional neural network model to obtain the abnormal score detection model, and take the ratio between the abnormal score of the current hydraulic oil tank and a preset maximum abnormal score as the failure rate of the current hydraulic oil tank.

[0067] In one specific embodiment of the present disclosure, the screening module 3 further comprises an analysis unit 31.

[0068] The analysis unit 31 is configured to analyze the score of the safety switching of the aircraft landing gear, and if the score is less than a preset score threshold, obtain a plurality of first maintenance record information in a first historical period, the first maintenance record information including a maintenance reason, and the maintenance reason including that a hydraulic oil tank failure causes problems in the power switching of the aircraft landing gear; meanwhile, obtain a plurality of second maintenance record information in a second historical period, the second historical period being after the first historical period, cluster the second maintenance record information to obtain a plurality of first clustering clusters, label each first clustering cluster, randomly select a preset number of second maintenance record information from each first clustering cluster, take the second maintenance record information as a training sample, and take the label corresponding to each second maintenance record information as annotation information to train a model to obtain a classification model; filter out final target maintenance record information according to the classification model, and send the final target maintenance record information to a staff.

[0069] It should be noted that, as for the system in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

[0070] Embodiment 3

[0071] Corresponding to the above method embodiments, the present embodiment also provides an aircraft landing gear power switching safety monitoring device. The aircraft landing gear power switching safety monitoring device described below can be referred to in conjunction with the aircraft landing gear power switching safety monitoring method described above.

[0072] Figure 3 FIG. 3 is a block diagram of an aircraft landing gear power switching safety monitoring device 300 according to an example embodiment. As shown in FIG. 3, the aircraft landing gear power switching safety monitoring device 300 can include a processor 301 and a memory 302. The aircraft landing gear power switching safety monitoring device 300 can also include one or more of a multimedia component 303, an I / O interface 304, and a communication component 305. Figure 3

[0073] ​The processor 301 is configured to control overall operation of the aircraft landing gear power switching safety monitoring device 300 to complete all or part of the steps of the aircraft landing gear power switching safety monitoring method described above. The memory 302 is configured to store various types of data to support the operation of the aircraft landing gear power switching safety monitoring device 300. For example, the data can include instructions for any application or method operating on the aircraft landing gear power switching safety monitoring device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 302 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 storage, flash memory, magnetic disk or optical disk. The multimedia component 303 can include a screen and an audio component. The screen can be a touch screen, for example, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 302 or transmitted through the communication component 305. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 305 is configured to enable wired or wireless communication between the aircraft landing gear power switching safety monitoring device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 305 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0074] In an exemplary embodiment, the aircraft landing gear power switching safety monitoring device 300 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic components for executing the above-mentioned aircraft landing gear power switching safety monitoring method.

[0075] In another exemplary embodiment, a computer readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-mentioned aircraft landing gear power switching safety monitoring method is also provided. For example, the computer readable storage medium can be the above-mentioned memory 302 including program instructions that can be executed by the processor 301 of the aircraft landing gear power switching safety monitoring device 300 to complete the above-mentioned aircraft landing gear power switching safety monitoring method.

[0076] Embodiment 4

[0077] Corresponding to the above method embodiments, the embodiments of the present disclosure also provide a readable storage medium. The readable storage medium described below can be referred to in conjunction with the above-mentioned aircraft landing gear power switching safety monitoring method.

[0078] A readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implements the steps of the above-mentioned aircraft landing gear power switching safety monitoring method of the method embodiments.

[0079] The readable storage medium can be specifically a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0080] The above only describes preferred embodiments of the present disclosure and is not used to limit the present disclosure. For those skilled in the art, the present disclosure can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An aircraft landing gear power switching safety monitoring method, characterized in that, The method comprises the following steps: acquiring hydraulic oil tank oil quantity data at each time point within a preset time period, the end time point of the preset time period being the current time point; judging whether the hydraulic oil tank is abnormal within the preset time period according to all the hydraulic oil tank oil quantity data, and calculating the score of the aircraft landing gear safety switching if the hydraulic oil tank is abnormal; analyzing the score of the aircraft landing gear safety switching, acquiring historical maintenance record information if the score is less than a preset score threshold, and screening the historical maintenance record information, and sending the screening result to the staff for helping the staff to overhaul; wherein, judging whether the hydraulic oil tank is abnormal within the preset time period according to all the hydraulic oil tank oil quantity data, and calculating the score of the aircraft landing gear safety switching if the hydraulic oil tank is abnormal, comprises: fitting the hydraulic oil tank oil quantity data at each time point within the preset time period by using a moving average to obtain fitting data corresponding to each time point within the preset time period; calculating the difference between the fitting data at each time point and the hydraulic oil tank oil quantity data, and recording the absolute value of the difference as the first data corresponding to each time point; judging whether the hydraulic oil tank is abnormal within the preset time period according to all the first data, and calculating the score of the aircraft landing gear safety switching if the hydraulic oil tank is abnormal, comprises: summing all the first data to obtain second data, summing the fitting data corresponding to each time point within the preset time period to obtain third data, comparing the ratio of the square root of the second data to the third data with a preset abnormal threshold range, and judging that the hydraulic oil tank oil quantity data within the preset time period is abnormal if the ratio is within the preset abnormal threshold range; calculating the mean and variance of all the first data, summing the mean and variance to obtain fourth data; summing the fitting data at the current time point and the fourth data to obtain fifth data, subtracting the fourth data from the fitting data at the current time point to obtain sixth data; judging whether the hydraulic oil tank oil quantity data at the current time point is less than the sixth data or greater than the fifth data, and judging that the hydraulic oil tank oil quantity data at the current time point is abnormal if yes; judging that the current hydraulic oil tank is abnormal when the hydraulic oil tank oil quantity data within the preset time period is abnormal and the hydraulic oil tank oil quantity data at the current time point is abnormal; calculating the failure rate of the current hydraulic oil tank when it is judged that the current hydraulic oil tank is abnormal, and acquiring the influence degree of the oil tank oil quantity data on the aircraft landing gear power switching, multiplying the influence degree of the oil tank oil quantity data on the aircraft landing gear power switching by the failure rate to obtain seventh data, and subtracting the seventh data from a preset first value to obtain the score of the current aircraft landing gear safety switching.

2. The method of claim 1, wherein, calculating the failure rate of the current hydraulic oil tank when it is judged that the current hydraulic oil tank is abnormal, comprises: The CUSUM algorithm is used to identify the change point in the hydraulic oil tank oil quantity data at each time in a preset period, the total oil tank oil quantity data in the preset period is divided into multiple data sets according to the change point, and the Shannon entropy corresponding to each data set is calculated; the Shannon entropy corresponding to each data set is input into a preset abnormal score detection model to obtain the abnormal score corresponding to each data set, and the maximum abnormal score is taken as the abnormal score of the current hydraulic oil tank; wherein, the training method of the abnormal score detection model is to obtain historical oil tank oil quantity time series data, identify the change point in the historical oil tank oil quantity time series data, divide the historical oil tank oil quantity time series data into multiple subsets according to the change point, calculate the Shannon entropy of each subset, and obtain the abnormal score of the hydraulic oil tank corresponding to each subset, take the Shannon entropy as the input of the convolutional neural network model, and take the abnormal score of the hydraulic oil tank as the output to train the convolutional neural network model to obtain the abnormal score detection model; the ratio between the abnormal score of the current hydraulic oil tank and the preset maximum abnormal score is taken as the failure rate of the current hydraulic oil tank.

3. The method of claim 1, wherein, The score of the safety switching of the aircraft landing gear is analyzed, and if it is less than a preset score threshold, historical maintenance record information is obtained, and the historical maintenance record information is screened, including: The score of the safety switching of the aircraft landing gear is analyzed, and if it is less than a preset score threshold, a plurality of first maintenance record information in a first historical period is obtained, the first maintenance record information includes the reason for maintenance, and the reason for maintenance includes that the hydraulic oil tank failure causes the aircraft landing gear power switching to have a problem; a plurality of second maintenance record information in a second historical period is also obtained, the second historical period is located after the first historical period, the second maintenance record information is clustered to obtain a plurality of first clustering clusters, each first clustering cluster is labeled, a preset number of second maintenance record information is randomly selected from each first clustering cluster, which is taken as a training sample, and the label corresponding to each second maintenance record information is taken as annotation information to train the model to obtain a classification model; the final target maintenance record information is screened out according to the classification model, and the final target maintenance record information is sent to the staff.

4. An aircraft landing gear power switching safety monitoring system, characterized in that, Including: The acquisition module is configured to acquire hydraulic oil tank oil quantity data at each time in a preset period, and the end time of the preset period is the current time; The judgment module is configured to determine whether the hydraulic oil tank is abnormal in the preset period according to the total hydraulic oil tank oil quantity data, and if it is abnormal, to calculate the score of the safety switching of the aircraft landing gear; The screening module is configured to analyze the score of the safety switching of the aircraft landing gear, and if it is less than a preset score threshold, to obtain historical maintenance record information, and to screen the historical maintenance record information, and to send the screening result to the staff for assisting the staff in maintenance; The judgment module includes: The first calculation unit is configured to fit the hydraulic oil tank oil quantity data at each time in a preset period using a moving average to obtain fitting data corresponding to each time in the preset period; the fitting data at each time is difference calculated with the hydraulic oil tank oil quantity data, and the absolute value of the difference is taken as the first data corresponding to each time; The judging unit is configured to determine whether the hydraulic oil tank is abnormal in the preset time period according to all the first data, and calculate a score of the safety switching of the aircraft landing gear if the hydraulic oil tank is abnormal. The judging unit comprises: The second calculating unit is configured to sum all the first data to obtain second data, sum the fitting data corresponding to each time point in the preset time period to obtain third data, compare a ratio of the square root of the second data to the third data with a preset abnormal threshold range, and determine that the oil quantity data of the hydraulic oil tank in the preset time period is abnormal if the ratio is in the preset abnormal threshold range; calculate the mean and variance of all the first data, sum the mean and the variance to obtain fourth data; sum the fitting data at the current time point with the fourth data to obtain fifth data, and subtract the fourth data from the fitting data at the current time point to obtain sixth data; determine whether the oil quantity data of the hydraulic oil tank at the current time point is less than the sixth data or greater than the fifth data, and determine that the oil quantity data of the hydraulic oil tank at the current time point is abnormal if yes. The third calculating unit is configured to determine that the current hydraulic oil tank is abnormal when the oil quantity data of the hydraulic oil tank in the preset time period is abnormal and the oil quantity data of the hydraulic oil tank at the current time point is abnormal; calculate a failure rate of the current hydraulic oil tank when it is determined that the current hydraulic oil tank is abnormal, obtain an influence degree of the oil quantity data of the hydraulic oil tank on the power switching of the aircraft landing gear, multiply the influence degree of the oil quantity data of the hydraulic oil tank on the power switching of the aircraft landing gear by the failure rate to obtain seventh data, and subtract the seventh data from a preset first value to obtain a score of the safety switching of the current aircraft landing gear.

5. The aircraft landing gear power switching safety monitoring system of claim 4, wherein, The third calculating unit comprises: The fourth calculating unit is configured to identify a variable point in the oil quantity data of the hydraulic oil tank at each time point in the preset time period by using a CUSUM algorithm, divide all the oil quantity data of the hydraulic oil tank in the preset time period into a plurality of data sets according to the variable point, calculate Shannon entropy corresponding to each data set, input the Shannon entropy corresponding to each data set into a preset abnormal score detection model to obtain an abnormal score corresponding to each data set, and take the maximum abnormal score as an abnormal score of the current hydraulic oil tank; wherein, a training method of the abnormal score detection model is to obtain historical oil quantity time series data, identify a variable point in the historical oil quantity time series data, divide the historical oil quantity time series data into a plurality of subsets according to the variable point, calculate Shannon entropy of each subset, obtain an abnormal score of the hydraulic oil tank corresponding to each subset, take the Shannon entropy as an input of a convolutional neural network model, take the abnormal score of the hydraulic oil tank as an output, train the convolutional neural network model to obtain the abnormal score detection model, and take a ratio between the abnormal score of the current hydraulic oil tank and a preset maximum abnormal score as a failure rate of the current hydraulic oil tank.

6. The aircraft landing gear power switching safety monitoring system of claim 4, wherein, The screening module comprises: The analysis unit is used for analyzing the score of the safety switching of the aircraft landing gear. If the score is less than a preset score threshold, a plurality of first maintenance record information in a first historical period is obtained. The first maintenance record information includes a maintenance reason. The maintenance reason includes that a hydraulic oil tank failure causes problems in the power switching of the aircraft landing gear. Meanwhile, a plurality of second maintenance record information in a second historical period is obtained. The second historical period is located after the first historical period. The second maintenance record information is clustered to obtain a plurality of first clustering clusters. Each first clustering cluster is labeled. A preset number of second maintenance record information is randomly selected from each first clustering cluster. The second maintenance record information is used as a training sample. Each second maintenance record information corresponding to the label information is used as label information to train the model to obtain a classification model. The final target maintenance record information is filtered out according to the classification model, and the final target maintenance record information is sent to the staff.

Images