CN117972317A - Toughness portrait method oriented to pilot competence - Google Patents
Toughness portrait method oriented to pilot competence Download PDFInfo
- Publication number
- CN117972317A CN117972317A CN202410371635.6A CN202410371635A CN117972317A CN 117972317 A CN117972317 A CN 117972317A CN 202410371635 A CN202410371635 A CN 202410371635A CN 117972317 A CN117972317 A CN 117972317A
- Authority
- CN
- China
- Prior art keywords
- pilot
- toughness
- data
- portrait
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 39
- 238000012360 testing method Methods 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 description 5
- 230000002411 adverse Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 208000001034 Frostbite Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008255 psychological mechanism Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
- 230000000472 traumatic effect Effects 0.000 description 1
- 210000003454 tympanic membrane Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of pilot toughness portrayal, and particularly relates to a toughness portrayal method for pilot competence, which comprises the steps of firstly acquiring a historical pilot data set, extracting a pilot toughness related data set, and carrying out data preprocessing on the pilot toughness related data set; then creating a pilot toughness portrait model, and inputting a preprocessed pilot toughness related data set to train the pilot toughness portrait model; acquiring a pilot data set to be imaged, and performing toughness image drawing on the pilot data set to be imaged through a trained pilot toughness image model; and finally, comparing the toughness portrait result of the pilot to be portrait with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot. The toughness capability of the pilot is accurately measured and evaluated through the process, so that effective safety risk management for the pilot is realized.
Description
Technical Field
The invention belongs to the technical field of toughness representation of pilots, and particularly relates to a toughness representation method for pilot competence.
Background
For a long time, the international civil aviation industry has continuously trained and studied pilots in terms of "risk management" and "pressure management", etc. In 2016, the European aviation security agency has set forth specific requirements regarding the development of pilot "RESILIENCE" capability in its regulatory clauses and in crew resource management training. "RESILIENCE" may be a skill on the part of pilots that they are most concerned with handling sudden special conditions during the operation of their regular flights.
RESILIENCE is defined as the two-layer meaning, one of which is the ability of a person or thing to quickly return to a good state after suffering from an unpleasant sensation such as impact, injury, or the like. I.e. "stress fit" or "toughness". ② The ability of a substance or object to spring back into shape; namely: "elasticity", "toughness" is a psychological mechanism of recovery and growth under stress, and refers to the effective response and adaptation of a human individual to a loss, difficulty or stress. "toughness" means not only that the individual is able to quickly recover to an original state after a major trauma or stress, but also that it is able to endure and endure under stress threat. "toughness" more emphasizes the ability of individuals to grow and regenerate after frustration.
The current civil aviation aircraft with nearly hundred thousand frames per day safely and smoothly run around the world, compared with the prior art, the great improvement of the civil aviation safety index has very important roles in improving the toughness of flight crewmembers besides benefiting from the improvement of new technical application and aircraft reliability factors. In the past decades, although various adverse conditions, challenges and changes bring a little shadow to the civil aviation industry, the development of the international aviation industry is still easy to see, and the civil aviation pilots of the first generation and the next generation gradually show stronger adaptability after continuous intercity inheritance and grinding.
While for pilot skill, "toughness" is more pronounced as: "ability to successfully cope with high levels of challenges and changes and rebound after a stress or traumatic event. For example, when a flight 2018 flies at a speed of 800 km at a high altitude of nearly ten thousand meters, the windshield of the cockpit suddenly bursts and falls off, the front half of the passenger is instantly sucked out of the window, and the suddenly-changed pressure not only causes great damage to the eardrum of a person in the cabin, but also causes frostbite to the body of the pilot at a low temperature of nearly-40 ℃. Under the severe environment that the instrument panel of the cockpit is lifted, noise and radio failure are caused, and only visual flying operation can be relied on, the adverse effects of difficult factors such as low temperature, low pressure, a large number of instrument failures and the like are overcome by a captain and a crew, the action of the crew human factors is exerted to the greatest extent by the stubborn toughness, and the whole aircraft 128 is led to finally and safely return to the voyage.
When faced with emergency or faced with adverse circumstances, it is an absolute benefit of personal ability and human resources to have high "toughness" in accurately judging, solving problems, and decision making. For a pilot to stay in the cockpit all the year round and responsible for the shoulder, "toughness" is one of the most interesting and improving capabilities.
At present, in the process of selecting and pulling a pilot and the process of daily training, the toughness capability is used as an important index of the pilot, plays a role in safety risk management in the subsequent pilot flying process, so how to accurately measure and evaluate the toughness capability of the pilot is a technical problem to be solved at present.
Disclosure of Invention
The invention aims to provide a toughness portrait method oriented to the competence of a pilot, which is used for solving the technical problem that the toughness of the pilot cannot be measured and evaluated accurately in the prior art.
In order to solve the technical problems, the invention adopts the following technical scheme:
A toughness representation method facing pilot competence comprises the following steps:
S1: acquiring a historical pilot data set, extracting a pilot toughness related data set from the historical pilot data set, and carrying out data preprocessing on the pilot toughness related data set;
S2: creating a pilot toughness portrait model, and inputting a preprocessed pilot toughness related data set to train the pilot toughness portrait model;
S3: acquiring a pilot data set to be sketched, and performing toughness image drawing on the pilot data set to be sketched through a trained pilot toughness image model;
s4: comparing the toughness portrait result of the pilot to be portrait with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot;
The toughness portraits refer to the evaluation of the toughness capability of the pilot according to the control data, situation awareness and risk decision data, the control data of an automatic system and the set management and man-machine interaction data of the pilot in various conditions during the flight execution and training process;
The toughness portrait result is the evaluation result of the toughness capability of the pilot according to the control data, situation awareness and risk decision data, the control data of an automation system and the set management and man-machine interaction data of the pilot in various conditions during the flight execution and training process, and is set as a score of 100 minutes.
Preferably, step S1 comprises the steps of:
S11: acquiring a historical pilot data set and extracting a pilot toughness related data set;
S12: dividing the pilot toughness related data set into a training set, a verification set and a test set;
s13: and respectively preprocessing the data of the training set, the verification set and the test set.
Preferably, the data preprocessing in step S13 includes the following specific procedures:
s131: carrying out data denoising treatment on the pilot toughness related data set;
S132: and carrying out data normalization processing on the denoised pilot toughness related data set.
Preferably, in step S131, denoising the data in the pilot toughness related data set by using a weighted average filtering algorithm, where the mathematical expression of the weighted average filtering algorithm is:
；
Wherein, For the first item of data in the pilot toughness related dataset,/>For the second item of data in the pilot toughness related dataset,/>For the ith data point in the pilot toughness related dataset,/>Weight of the first data point,/>Weights for the second data point,/>Weights for the ith data point,/>The values of the filtered data points are weighted average.
Preferably, the weighted average filtering algorithm is in a mathematical expression ofThe mathematical expression of (2) is:
；
Wherein, The weight of the ith data point, c is the current time point and σ is the standard deviation of the gaussian function.
Preferably, training the pilot toughness representation model in step S2 includes the following specific processes:
s21: training the created pilot toughness portrait model through a training set in the pilot toughness related data set;
s22: verifying the validity of the pilot toughness portrait model through a verification set in the pilot toughness related data set;
S23: testing the pilot toughness portrait model through a test set in the pilot toughness related data set, judging whether the robustness of the pilot toughness portrait model meets the standard, if so, testing the model to meet the standard, and if not, executing step S24;
S24: and (3) adjusting parameters of the pilot toughness portrait model, and re-executing the steps S21-S23 until the robustness of the model reaches the standard.
Preferably, the pilot toughness representation model in step S3 employs a convolutional neural network model, and the convolutional neural network model employs a two-channel network model, each channel including a convolutional layer, a pooling layer, and a full-join layer, wherein the convolutional layer of channel one of the two channels uses two 3×3 convolutional layers, and the convolutional layer of channel two of the two channels uses three 5×5 convolutional layers.
The beneficial effects of the invention include:
According to the toughness portrait method for pilot competence, firstly, a historical pilot data set is obtained, a pilot toughness related data set is extracted, and data preprocessing is carried out on the pilot toughness related data set; then creating a pilot toughness portrait model, and inputting a preprocessed pilot toughness related data set to train the pilot toughness portrait model; acquiring a pilot data set to be imaged, and performing toughness image drawing on the pilot data set to be imaged through a trained pilot toughness image model; and finally, comparing the toughness portrait result of the pilot to be portrait with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot. The toughness capability of the pilot is accurately measured and evaluated through the process, so that effective safety risk management for the pilot is realized.
Drawings
FIG. 1 is a flow chart of the pilot competence oriented toughness representation method of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
The present application will present various aspects, embodiments, or features about a system that may include a plurality of devices, components, modules, etc. It is to be understood and appreciated that the various systems may include additional devices, components, modules, etc. and/or may not include all of the devices, components, modules etc. discussed in connection with the figures. Furthermore, combinations of these schemes may also be used.
In addition, in the embodiments of the present application, words such as "exemplary," "for example," and the like are used to indicate an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of the term "exemplary" is intended to present concepts in a concrete fashion.
In the embodiment of the present application, "information", "signal", "message", "channel", and "signaling (singaling)" may be used in a mixed manner, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized. "of", "corresponding (corresponding, relevant)" and "corresponding (corresponding)" are sometimes used in combination, and it should be noted that the meaning of the expression is consistent when the distinction is not emphasized.
The invention is described in further detail below with reference to fig. 1:
referring to FIG. 1, a method for toughness representation for pilot competence includes the steps of:
s1: acquiring a historical pilot data set, extracting pilot toughness related data from the historical pilot data set to form a pilot toughness related data set, and carrying out data preprocessing on the pilot toughness related data set;
S2: creating a pilot toughness portrait model, and inputting a preprocessed pilot toughness related data set to train the pilot toughness portrait model;
S3: acquiring a pilot data set to be sketched, and performing toughness image drawing on the pilot data set to be sketched through a trained pilot toughness image model;
s4: comparing the toughness portrait result of the pilot to be portrait with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot;
The toughness portraits refer to the evaluation of the toughness capability of the pilot according to the control data, situation awareness and risk decision data, the control data of an automatic system and the set management and man-machine interaction data of the pilot in various conditions during the flight execution and training process;
The toughness portrait result is the evaluation result of the toughness capability of the pilot according to the control data, situation awareness and risk decision data, the control data of an automation system and the set management and man-machine interaction data of the pilot in various conditions during the flight execution and training process, and is set as a score of 100 minutes.
In the scheme, the historical pilot data set is obtained, wherein the historical pilot data comprises various data of a retired pilot and an active pilot, the data comprise flight execution data, flight training data and flight performance data, the extracted pilot toughness related data comprise control data, situation awareness and risk decision data, automation system control data and unit management and man-machine interaction data which meet various conditions in the flight execution and training process, the pilot toughness related data set is further formed, and the pilot toughness related data set is used as a data basis to provide data support for training of a subsequent pilot toughness portrait model. After the relevant data set of the toughness of the pedestrian is obtained, data preprocessing is needed to be carried out on the data of the data set so as to improve the effectiveness of the data in the data set, avoid negative influence of invalid data or abnormal data in the data set on subsequent model training and reduce the accuracy of the model.
The pilot toughness portrait model is created and is a convolutional neural network model, and the pilot toughness portrait model is trained through the preprocessed pilot toughness related data set, so that the neural network model has learning ability meeting requirements, and analysis of data is realized.
The training of the pilot toughness portrait model aims at analyzing new data, such as analyzing pilot data sets to be portrait, obtaining toughness capability of pilots to be portrait, and realizing toughness portrait of pilots.
And finally, according to the toughness portrait result of the pilot to be portrait, namely according to the toughness capability data of the pilot to be portrait, comparing with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot. Therefore, an aviation manager can grasp the toughness state of the pilot through the method, different flight tasks are distributed according to the toughness data of each pilot according to local conditions, a certain training direction is provided for daily training of the pilot, the flight toughness capability of the pilot is improved, and a certain selection index can be provided for selection of the pilot so as to reduce the safety risk of flight.
Step S1 in the above scheme includes the following procedure:
S11: acquiring a historical pilot data set and extracting a pilot toughness related data set;
S12: dividing a pilot toughness related data set into a training set, a verification set and a test set, wherein the training set is used for training a pilot toughness portrait model, the verification set is used for verifying the accuracy of the pilot toughness portrait model, and the test set is used for carrying out validity test on the pilot toughness portrait model, so that the accuracy and the validity of the pilot toughness portrait model are ensured;
S13: and respectively carrying out data preprocessing on the data of the training set, the verification set and the test set, wherein the data preprocessing comprises denoising processing and normalization processing, and the denoising processing enables invalid data and abnormal data in the data of the training set, the verification set and the test set to be removed, so that the influence of the invalid data and abnormal data on the training of the model is avoided. The normalization processing enables the data of the data set to have the same measurement scale, the dimensional influence among the data is eliminated, the data distribution is consistent, moreover, the influence of abnormal data samples can be eliminated, because the abnormal samples can increase the difficulty of learning a network model, the training is not converged, the characteristic with small numerical value of the output characteristic can be fully learned, and the training, the verification and the test of the toughness portrait model of the pilot can be conveniently carried out subsequently.
The data preprocessing in step S13 includes the following specific procedures:
s131: carrying out data denoising treatment on the pilot toughness related data set;
S132: and carrying out data normalization processing on the denoised pilot toughness related data set.
In the step S131, denoising is performed on the data in the pilot toughness related data set by using a weighted average filtering algorithm, where the mathematical expression of the weighted average filtering algorithm is as follows:
；
Wherein, For the first item of data in the pilot toughness related dataset,/>For the second item of data in the pilot toughness related dataset,/>For the ith data point in the pilot toughness related dataset,/>Weight of the first data point,/>Weights for the second data point,/>Weights for the ith data point,/>The values of the filtered data points are weighted average.
In the mathematical expression of the weighted average filtering algorithmThe mathematical expression of (2) is:
；
Wherein, The weight of the ith data point, c is the current time point and σ is the standard deviation of the gaussian function.
In step S132, the denoised pilot toughness related data set is subjected to data normalization, and the data is normalized to a standard normal distribution with a mean value of 0 and a standard deviation of 1, where the mathematical expression is as follows:
；
Wherein, Normalized value for data,/>For the value before data normalization,/>Is the mean value of data,/>Is the standard deviation of the data.
Training the pilot toughness portrait model in the step S2 comprises the following specific processes:
s21: training the created pilot toughness portrait model through a training set in the pilot toughness related data set;
s22: verifying the validity of the pilot toughness portrait model through a verification set in the pilot toughness related data set;
S23: testing the pilot toughness portrait model through a test set in the pilot toughness related data set, judging whether the robustness of the pilot toughness portrait model meets the standard, if so, testing the model to reach the standard, ending training, and if not, executing step S24;
S24: and (3) adjusting parameters of the pilot toughness portrait model, and re-executing the steps S21-S23 until the robustness of the model reaches the standard.
The pilot toughness portrait model in the step S3 adopts a convolution neural network model, and the convolution neural network model adopts a two-channel network model, wherein each channel comprises a convolution layer, a pooling layer and a full-connection layer, two 3×3 convolution layers are used for the convolution layer of the two-channel I, and three 5×5 convolution layers are used for the convolution layer of the two-channel II.
In summary, according to the toughness portrait method for pilot competence, firstly, a history pilot data set is obtained, a pilot toughness related data set is extracted, and data preprocessing is performed on the pilot toughness related data set; a pilot toughness representation model is then created to obtain a data base for the subsequent pilot toughness representation model. The preprocessed pilot toughness related data set is input to train a pilot toughness portrait model, so that the model has accurate and effective toughness portrait capability; acquiring a pilot data set to be imaged, and performing toughness image drawing on the pilot data set to be imaged through a trained pilot toughness image model; and finally, comparing the toughness portrait result of the pilot to be portrait with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot. The toughness capability of the pilot is accurately measured and evaluated through the process, so that effective safety risk management for the pilot is realized, and a data base and a training direction are provided for daily training of the pilot.
The above examples merely illustrate specific embodiments of the application, which are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that it is possible for a person skilled in the art to make several variants and modifications without departing from the technical idea of the application, which fall within the scope of protection of the application.
Claims (7)
1. A toughness portrait method facing pilot competence is characterized by comprising the following steps:
S1: acquiring a historical pilot data set, extracting a pilot toughness related data set from the historical pilot data set, and carrying out data preprocessing on the pilot toughness related data set;
S2: creating a pilot toughness portrait model, and inputting a preprocessed pilot toughness related data set to train the pilot toughness portrait model;
S3: acquiring a pilot data set to be sketched, and performing toughness image drawing on the pilot data set to be sketched through a trained pilot toughness image model;
s4: comparing the toughness portrait result of the pilot to be portrait with a preset standard value, judging whether the toughness portrait result is larger than the preset standard value, if so, meeting the toughness requirement of the pilot, and if not, not meeting the toughness requirement of the pilot;
The toughness portraits refer to the evaluation of the toughness capability of the pilot according to the control data, situation awareness and risk decision data, the control data of an automatic system and the set management and man-machine interaction data of the pilot in various conditions during the flight execution and training process;
The toughness portrait result is the evaluation result of the toughness capability of the pilot according to the control data, situation awareness and risk decision data, the control data of an automation system and the set management and man-machine interaction data of the pilot in various conditions during the flight execution and training process, and is set as a score of 100 minutes.
2. The method of toughness representation for pilot competence according to claim 1, wherein step S1 comprises the steps of:
S11: acquiring a historical pilot data set and extracting a pilot toughness related data set;
S12: dividing the pilot toughness related data set into a training set, a verification set and a test set;
s13: and respectively preprocessing the data of the training set, the verification set and the test set.
3. The pilot competence oriented toughness representation method according to claim 2, wherein the data preprocessing in step S13 comprises the following specific processes:
s131: carrying out data denoising treatment on the pilot toughness related data set;
S132: and carrying out data normalization processing on the denoised pilot toughness related data set.
4. A method for toughness representation for pilot competency according to claim 3, wherein in step S131, the data in the pilot toughness related data set is denoised by a weighted average filtering algorithm, wherein the mathematical expression of the weighted average filtering algorithm is:
；
Wherein, For the first item of data in the pilot toughness related dataset,/>For the second item of data in the pilot toughness related dataset,/>For the ith data point in the pilot toughness related dataset,/>Weight of the first data point,/>Weights for the second data point,/>Weights for the ith data point,/>The values of the filtered data points are weighted average.
5. The pilot competence-oriented toughness representation method according to claim 4, wherein said weighted average filtering algorithm is a mathematical expression ofThe mathematical expression of i is:
；
Wherein, The weight of the ith data point, c is the current time point and σ is the standard deviation of the gaussian function.
6. The pilot competence oriented toughness representation method according to claim 2, wherein training the pilot toughness representation model in step S2 comprises the following specific processes:
s21: training the created pilot toughness portrait model through a training set in the pilot toughness related data set;
s22: verifying the validity of the pilot toughness portrait model through a verification set in the pilot toughness related data set;
S23: testing the pilot toughness portrait model through a test set in the pilot toughness related data set, judging whether the robustness of the pilot toughness portrait model meets the standard, if so, testing the model to meet the standard, and if not, executing step S24;
S24: and (3) adjusting parameters of the pilot toughness portrait model, and re-executing the steps S21-S23 until the robustness of the model reaches the standard.
7. The pilot competence-oriented toughness representation method according to claim 1, wherein the pilot toughness representation model in step S3 employs a convolutional neural network model and the convolutional neural network model employs a two-channel network model, each channel comprising a convolutional layer, a pooling layer, and a fully-connected layer, wherein the two-channel one convolutional layer uses two 3 x 3 convolutional layers and the two-channel two convolutional layer uses three 5 x 5 convolutional layers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410371635.6A CN117972317B (en) | 2024-03-29 | 2024-03-29 | Toughness portrait method oriented to pilot competence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410371635.6A CN117972317B (en) | 2024-03-29 | 2024-03-29 | Toughness portrait method oriented to pilot competence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117972317A true CN117972317A (en) | 2024-05-03 |
| CN117972317B CN117972317B (en) | 2024-06-14 |
Family
ID=90858133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410371635.6A Active CN117972317B (en) | 2024-03-29 | 2024-03-29 | Toughness portrait method oriented to pilot competence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117972317B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB840336A (en) * | 1956-05-07 | 1960-07-06 | Phillips Petroleum Co | Process and apparatus for producing carbon black and carbon black so produced |
| AU2008278607A1 (en) * | 2007-07-26 | 2009-01-29 | Qualcomm Incorporated | Systems and methods for generalized slot-to-interlace mapping |
| CN110619691A (en) * | 2019-09-25 | 2019-12-27 | 南京天芯云数据服务有限公司 | Prediction method and device for slab surface cracks |
| CN111047078A (en) * | 2019-11-25 | 2020-04-21 | 中山大学 | Traffic characteristic prediction method, system and storage medium |
| CN111240350A (en) * | 2020-02-13 | 2020-06-05 | 西安爱生无人机技术有限公司 | Unmanned aerial vehicle pilot dynamic behavior evaluation system |
| CN113312424A (en) * | 2021-06-28 | 2021-08-27 | 北京航空航天大学 | QAR data-based pilot flight skill portrait method and system |
| CN114219302A (en) * | 2021-12-13 | 2022-03-22 | 中国民用航空飞行学院 | Method for portraying wind competence of pilot facing to flight skill full life cycle |
| CN115187138A (en) * | 2022-08-16 | 2022-10-14 | 八方智能科技(南京)有限公司 | Pilot three-dimensional portrait method based on big data |
| CN115959138A (en) * | 2023-01-09 | 2023-04-14 | 中国第一汽车股份有限公司 | Driver rescue method, device and system based on physiological data |
| CN117547270A (en) * | 2023-11-14 | 2024-02-13 | 宝鸡文理学院 | Pilot cognitive load feedback system with multi-source data fusion |
| CN117708659A (en) * | 2023-11-02 | 2024-03-15 | 三峡大学 | Device and method for predicting and preventing power wing-mounted flight danger |
-
2024
- 2024-03-29 CN CN202410371635.6A patent/CN117972317B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB840336A (en) * | 1956-05-07 | 1960-07-06 | Phillips Petroleum Co | Process and apparatus for producing carbon black and carbon black so produced |
| AU2008278607A1 (en) * | 2007-07-26 | 2009-01-29 | Qualcomm Incorporated | Systems and methods for generalized slot-to-interlace mapping |
| CN110619691A (en) * | 2019-09-25 | 2019-12-27 | 南京天芯云数据服务有限公司 | Prediction method and device for slab surface cracks |
| CN111047078A (en) * | 2019-11-25 | 2020-04-21 | 中山大学 | Traffic characteristic prediction method, system and storage medium |
| CN111240350A (en) * | 2020-02-13 | 2020-06-05 | 西安爱生无人机技术有限公司 | Unmanned aerial vehicle pilot dynamic behavior evaluation system |
| CN113312424A (en) * | 2021-06-28 | 2021-08-27 | 北京航空航天大学 | QAR data-based pilot flight skill portrait method and system |
| CN114219302A (en) * | 2021-12-13 | 2022-03-22 | 中国民用航空飞行学院 | Method for portraying wind competence of pilot facing to flight skill full life cycle |
| CN115187138A (en) * | 2022-08-16 | 2022-10-14 | 八方智能科技(南京)有限公司 | Pilot three-dimensional portrait method based on big data |
| CN115959138A (en) * | 2023-01-09 | 2023-04-14 | 中国第一汽车股份有限公司 | Driver rescue method, device and system based on physiological data |
| CN117708659A (en) * | 2023-11-02 | 2024-03-15 | 三峡大学 | Device and method for predicting and preventing power wing-mounted flight danger |
| CN117547270A (en) * | 2023-11-14 | 2024-02-13 | 宝鸡文理学院 | Pilot cognitive load feedback system with multi-source data fusion |
Non-Patent Citations (4)
| Title |
|---|
| CHEN, NONGTIAN等: "An entropy weight variable fuzzy recognition and 1D-CNN deep learning method for general aviation fleet reliability evaluation", 《JOURNAL OF INTELLIGENT & FUZZY SYSTEMS》, vol. 46, no. 2, 14 February 2024 (2024-02-14), pages 4609 - 4619 * |
| NONGTIAN CHEN等: "Identification of flight accidents causative factors base on SHELLO and improved entropy gray correlation method", 《HELIYON》, vol. 9, no. 2, 5 February 2023 (2023-02-05), pages 13534 * |
| 陈农田等: "面向飞行员飞行全生命周期的作风胜任能力画像", 《人类工效学》, vol. 29, no. 03, 30 June 2023 (2023-06-30), pages 30 - 36 * |
| 顾振中: "飞行中惊奇和惊吓反应对初始训练飞行员胜任力的影响", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 11, 15 November 2022 (2022-11-15), pages 031 - 43 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117972317B (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107085744A (en) | Utilize the enhanced aircraft maintenance of data analysis and inspection | |
| CN109284896B (en) | Human error mode influence analysis method | |
| CN106548294A (en) | A kind of landing maneuver Performance Evaluation Methods and device based on flying quality | |
| CN110781572B (en) | Unmanned aerial vehicle intelligent monitoring threshold value determining method based on probability density distribution | |
| CN113297994B (en) | Pilot behavior analysis method and system | |
| Suhir | ‘Miracle-on-the-Hudson’: quantitative aftermath | |
| CN105550473A (en) | Heavy landing prediction method based on support vector machine classification | |
| CN114692786B (en) | Civil aircraft fault diagnosis method based on multi-source data fusion | |
| CN111783355A (en) | Man-machine interaction risk assessment method under multi-agent architecture | |
| CN116129510A (en) | Method and device for evaluating pilot perception of different coded information based on eye movement data | |
| CN108446673A (en) | A kind of controller's giving fatigue pre-warning method based on face recognition | |
| CN112817296A (en) | Flight fault prediction method and system based on flight data and deep learning | |
| CN116842475A (en) | Fatigue driving detection method based on multi-mode information fusion | |
| CN113869749A (en) | Flight training quality evaluation system and method for simulated aircraft | |
| CN117972317B (en) | Toughness portrait method oriented to pilot competence | |
| Liu et al. | Effect of HFACS and non-HFACS-related factors on fatalities in general aviation accidents using neural networks | |
| Naeeri et al. | Exploring the relationship between pilot's performance and fatigue when interacting with cockpit interfaces | |
| Wu et al. | Flight situation recognition under different weather conditions | |
| Muraviov et al. | Method for improving the reliability of an ergatic control system for an automated aircraft | |
| CN117542027A (en) | Unit disabling state monitoring method based on non-contact sensor | |
| Ison | Comparative analysis of accident and non-accident pilots | |
| CN110844092A (en) | Aircraft fault warning method and system | |
| CN114118802A (en) | Helicopter flight risk assessment method based on analytic hierarchy process | |
| Li et al. | The application of aeronautical decision-making support systems for improving pilots' performance in flight operations | |
| Dong et al. | Evaluation for Trainee Pilot Workload Management Competency During Approach Phase Based on Flight Training Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |