Efficiency evaluation method of automatic landing aid decision-making system and medium

Abstract

The invention discloses an efficiency evaluation method of an automatic landing aid decision-making system and a medium, and relates to the field of automatic landing, and the method comprises the steps: obtaining physiological data and flight data of a driver during the execution of an aircraft landing task; a driver executes an aircraft landing task by relying on the automatic landing aid decision-making system; preprocessing the physiological data and the flight data respectively; on the basis of the preprocessed physiological data, a load level value of the driver is calculated by using a sliding window of multiple time scales and a dynamic entropy weight method; extracting features of the preprocessed flight data by using principal component analysis, and calculating an Euclidean distance between the corresponding features and the expert flight data to obtain a landing operation performance level value of the driver; normalizing and adding the load level value and the landing operation performance level value to obtain an effectiveness evaluation score; and when the efficiency evaluation score is greater than or equal to a first threshold value, the efficiency of the automatic landing aid decision-making system is optimal. According to the invention, the efficiency of the automatic landing aid decision-making system is effectively evaluated.

Description

Technical Field

[0001] The present application relates to the field of automatic landing technology, and in particular to a performance evaluation method and medium for an automatic landing auxiliary decision system. Background Art

[0002] With technological advancements, aircraft automatic landing decision-making assistance systems have evolved from simple auxiliary tools to highly sophisticated decision-support systems. By integrating advanced sensors, precise navigation equipment, and intelligent algorithms, these systems provide pilots with real-time flight data and landing recommendations in complex weather conditions and airport environments. They not only reduce pilot workload but also provide critical support in low visibility or emergency situations, thereby improving the success rate and safety of landings.

[0003] To verify the effectiveness of automated landing decision-making systems during landing, their actual performance is often evaluated. Traditional performance evaluation methods typically compare data collected during landing with fixed numerical indicators. This manual verification method is relatively mechanical, and load assessments often rely heavily on subjective methods such as pilot questionnaires, lacking unified, objective standards. Therefore, these traditional methods are ineffective in effectively evaluating the effectiveness of automated landing decision-making systems. Summary of the Invention

[0004] The purpose of this application is to provide a method and medium for evaluating the effectiveness of an automatic landing assistance decision system, which comprehensively considers the pilot's load level and landing operation performance level, and effectively evaluates the effectiveness of the automatic landing assistance decision system.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In a first aspect, the present application provides a method for evaluating the effectiveness of an automatic landing auxiliary decision system, and the method for evaluating the effectiveness of the automatic landing auxiliary decision system is as follows.

[0007] Acquire the pilot's physiological data and flight data when performing the aircraft landing mission; the pilot relies on the automatic landing auxiliary decision system to perform the aircraft landing mission.

[0008] The physiological data and the flight data are preprocessed respectively.

[0009] Based on the preprocessed physiological data, the driver's load level is calculated using sliding windows and dynamic entropy weight methods at multiple time scales.

[0010] Principal component analysis is used to extract the features of the preprocessed flight data, and the Euclidean distance between the corresponding features and the expert flight data is calculated to obtain the pilot's landing operation performance level.

[0011] The load level value and the landing operation performance level value are normalized and then added together to obtain a performance evaluation score.

[0012] When the performance evaluation score is greater than or equal to a first threshold, the performance of the automatic landing assistance decision system is excellent; when the performance evaluation score is greater than or equal to a second threshold and less than the first threshold, the performance of the automatic landing assistance decision system is good; when the performance evaluation score is less than the second threshold, the performance of the automatic landing assistance decision system is poor.

[0013] In a second aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for evaluating the effectiveness of the automatic landing assistance decision system described in the first aspect.

[0014] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0015] This application conducts a comprehensive evaluation of the aircraft's automatic landing assistance decision system from two aspects: the pilot's load level and the landing operation performance level. On the one hand, when the pilot performs the aircraft landing task, his physiological data can truly reflect the pilot's physical condition and load level, and based on physiological data, through data processing, the method of using the dynamic entropy weight method to analyze the load level at multiple time scales has the advantages of objective, real-time, continuous, and multi-dimensional evaluation; on the other hand, based on flight data, after data processing, the method of calculating the Euclidean distance with expert flight data after principal component analysis to obtain the deviation value effectively reflects the pilot's performance and ability when performing the aircraft landing task with the help of the automatic landing assistance decision system. Therefore, this application evaluates the effectiveness of the automatic landing assistance decision system from the above two aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 Flowchart of the performance evaluation method of the automatic landing auxiliary decision system in an embodiment of the present application.

[0018] Figure 2 This is a calculation flow chart of the dynamic entropy weight method in the embodiment of this application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] The purpose of this application is to provide a method and medium for evaluating the effectiveness of an automatic landing assistance decision system, which comprehensively considers the pilot's load level and landing operation performance level, and effectively evaluates the effectiveness of the automatic landing assistance decision system.

[0021] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0022] In an exemplary embodiment, Figure 1 As shown, a method for evaluating the effectiveness of an automatic landing auxiliary decision system is provided, and the method for evaluating the effectiveness of the automatic landing auxiliary decision system is as follows.

[0023] Step S1: Acquire the pilot's physiological data and flight data when performing an aircraft landing mission.

[0024] In this embodiment, the pilot primarily relies on the automatic landing decision support system to execute the aircraft landing mission. By measuring changes in their physiological indicators, the pilot's workload can be assessed. While performing a flight mission, the pilot's heartbeat, muscles, and breathing can all reflect the intensity of the pilot's workload. By monitoring changes in the pilot's physiological data, such as electromyography, electrocardiogram, pulse data, and respiratory data, the pilot's workload can be assessed. Furthermore, physiological data assessment offers the advantages of being objective, real-time, continuous, and multi-dimensional. Furthermore, with technological advancements, physiological data collection equipment is becoming non-invasive, integrated, and intelligent.

[0025] The landing operation performance level is used to evaluate the performance and ability of the pilot when performing the aircraft landing mission with the help of the automatic landing assistance decision system. The flight data recording program is used to record the pilot's flight data such as aircraft attitude angle, aircraft altitude, aircraft airspeed, aircraft descent speed, number of aircraft go-arounds, aircraft touchdown speed, aircraft horizontal deviation, etc.

[0026] Step S2: Preprocess the physiological data and flight data respectively.

[0027] In this embodiment, the acquired physiological data is preprocessed by channel and characteristics. For example, EMG data is filtered for power frequency and baseline corrected, ECG and pulse data are identified and located, and respiratory data is extracted for respiratory phase. For the acquired flight data, duplicate and outlier values ​​are removed, and data normalization is performed.

[0028] Step S3: Based on the preprocessed physiological data, the driver's load level value is calculated using sliding windows of multiple time scales and dynamic entropy weight methods.

[0029] In this embodiment, step S3 is specifically as follows.

[0030] Step S31: Based on the pre-processed physiological data, the physiological features of different frequencies are extracted using sliding windows of three time scales of 1s, 2s and 5s to obtain the physiological feature data set X{x kij |k=1,2,3;i=1,…,l;j=1,…,n},x kij is the feature data extracted from the i-th sliding window of the k-th sliding window of the j-th physiological feature channel, l is the total number of sliding windows, and n is the total number of physiological feature channels.

[0031] Step S32: Based on the physiological characteristic data set, the dynamic entropy weight method is used to calculate the weight of each physiological characteristic in the load level calculation, and the driver's load level value is obtained through weighted calculation.

[0032] like Figure 2 As shown in Figure 2, when using the dynamic entropy weight method to process data, the physiological characteristic data set is first dynamically normalized to eliminate the dimensional influence between different indicators and ensure the comparability of each indicator in the evaluation process. The dynamic normalization calculation is as follows.

[0033]

[0034] Where, X norm is the data after dynamic normalization, X is the exact value of the original data at this moment, X min 、X max are the minimum and maximum values ​​in the previous data. After normalization, the original data will be converted to the range of [0,1].

[0035] Then, the time factor is taken into consideration and the information entropy is calculated by time scale. As an objective weighting method, the entropy weight method calculates the information entropy of each indicator based on the principle of information theory to determine the weight. Information entropy is used to measure the degree of disorder of data. The smaller the value, the greater the variability of the indicator, the more information it contains, and the greater the weight in the evaluation. Due to dynamic normalization, the range used in early data may be too small, and a time correction coefficient is added. Reduce the information entropy adoption rate of early data. The information entropy calculation formula is as follows.

[0036]

[0037] Where, e kj is the information entropy of the jth physiological feature channel under the kth sliding window.

[0038] Then, the difference coefficient matrix is ​​calculated based on the degree of dispersion of the difference coefficient measurement index. Among them, the difference coefficient d of the j-th physiological feature channel in the k-th sliding window is kj The calculation of is as follows.

[0039] d kj =(1-e kj ).

[0040] The indicator weight is determined based on the difference coefficient, and the difference coefficient is normalized to obtain the indicator weight matrix. Among them, the weight w of the jth physiological feature channel in the kth sliding window is kj The calculation of is as follows.

[0041]

[0042] Finally, a weighted calculation is performed based on the weight to obtain the driver's load level value Score.

[0043]

[0044] Where x k(end)j It is the last sliding window feature measurement value of the kth sliding window of the jth physiological feature channel.

[0045] Step S4: Use principal component analysis to extract the features of the preprocessed flight data, and calculate the Euclidean distance between the corresponding features and the expert flight data to obtain the pilot's landing operation performance level value.

[0046] In this embodiment, in order to facilitate an effective evaluation of the pilot's landing operation performance, it is necessary to compare it with expert flight data. Generally, expert flight data refers to the data generated by professional pilots with decades of flying experience during the aircraft landing process. By recording and summarizing this data, the corresponding expert flight data can be obtained.

[0047] Step S5: Normalize the load level value and the landing operation performance level value and add them together to obtain a performance evaluation score.

[0048] In this embodiment, the load level value is calculated using a physiological evaluation method, and the landing operation performance level value is calculated using a performance evaluation method. The effectiveness of the automatic landing assistance decision system is effectively evaluated by combining the physiological evaluation method and the performance evaluation method.

[0049] Step S6: When the performance evaluation score is greater than or equal to the first threshold, the performance of the automatic landing assistance decision system is excellent; when the performance evaluation score is greater than or equal to the second threshold and less than the first threshold, the performance of the automatic landing assistance decision system is good; when the performance evaluation score is less than the second threshold, the performance of the automatic landing assistance decision system is poor.

[0050] As a preferred implementation, the first threshold is 1.5 and the second threshold is 1.

[0051] Based on the above analysis, the ADL system can be adjusted and improved based on the final performance evaluation results. If the ADL system's performance is excellent, no adjustments are required and the system can continue to operate during flight. If the ADL system's performance is good or poor, further improvements and optimizations are needed to the system's sensors, navigation equipment, and intelligent algorithms.

[0052] In another exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above embodiment are implemented.

[0053] In summary, this application mainly has the following advantages.

[0054] 1) This application accurately and dynamically analyzes the pilot's physiological and flight data, capturing key information through feature extraction technology, reducing misjudgment rates and improving assessment reliability. This efficient assessment capability is crucial for improving the safety and efficiency of automated landing decision support systems, as it monitors the pilot's workload in real time and provides timely decision support to ensure a smooth and safe landing.

[0055] 2) This application was designed with full consideration given to the scalability of the system, allowing for customized adjustments based on different flight missions and environments to adapt to changing automatic landing requirements and technological advances. This scalability ensures that the system can maintain its advanced nature over the long term.

[0056] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0057] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0058] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0059] All actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0060] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0061] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for evaluating the effectiveness of an automatic landing support decision system, characterized in that: The effectiveness evaluation method of the automatic landing auxiliary decision system includes: Acquire the pilot's physiological data and flight data when performing the aircraft landing mission; the pilot relies on the automatic landing auxiliary decision system to perform the aircraft landing mission; Preprocessing the physiological data and the flight data respectively; Based on the pre-processed physiological data, the driver's load level is calculated using sliding windows and dynamic entropy weight methods at multiple time scales. Principal component analysis is used to extract the features of the preprocessed flight data, and the Euclidean distance between the corresponding features and the expert flight data is calculated to obtain the pilot's landing operation performance level. Normalizing the load level value and the landing operation performance level value and adding them together to obtain a performance evaluation score; When the performance evaluation score is greater than or equal to a first threshold, the performance of the automatic landing assistance decision system is excellent; when the performance evaluation score is greater than or equal to a second threshold and less than the first threshold, the performance of the automatic landing assistance decision system is good; when the performance evaluation score is less than the second threshold, the performance of the automatic landing assistance decision system is poor.

2. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 1, characterized in that: The physiological data at least includes electromyographic data, electrocardiographic data, pulse data and respiratory data.

3. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 1, characterized in that: The flight data at least includes aircraft attitude angle, aircraft altitude, aircraft airspeed, aircraft descent speed and aircraft horizontal deviation.

4. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 2, characterized in that: Preprocessing the physiological data specifically includes: Performing power frequency filtering and baseline correction on the electromyographic data; performing heartbeat identification and positioning on the electrocardiogram data and the pulse data; A respiratory phase is extracted from the respiratory data.

5. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 1, characterized in that: Preprocessing the flight data specifically includes: Duplicate values ​​and outliers in the flight data were removed, and data normalization was completed.

6. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 1, characterized in that: There are three time scales of the sliding window, namely 1s, 2s and 5s.

7. The effectiveness evaluation method of the automatic landing assistance decision system according to claim 6, characterized in that: Based on the preprocessed physiological data, the driver's load level is calculated using sliding windows and dynamic entropy weight methods at multiple time scales, including: Based on the preprocessed physiological data, the sliding windows of three time scales, 1s, 2s, and 5s, were used to extract physiological features of different frequencies and obtain the physiological feature dataset. Based on the physiological characteristic data set, the dynamic entropy weight method is used to calculate the weight of each physiological characteristic in the load level calculation, and the driver's load level value is obtained through weighted calculation.

8. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 7, characterized in that: The calculation formula of the load level value is: Where Score is the load level value, n is the total number of physiological characteristic channels, and w kj is the weight of the jth physiological feature channel in the kth sliding window, x k(end)j It is the last sliding window feature measurement value of the kth sliding window of the jth physiological feature channel.

9. The effectiveness evaluation method of the automatic landing auxiliary decision system according to claim 1, characterized in that: The first threshold is 1.5, and the second threshold is 1.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the effectiveness evaluation method of the automatic landing assistance decision system according to any one of claims 1 to 9 are implemented.

Images