Large fixed-wing unmanned aerial vehicle control quality airworthiness evaluation method and device and medium

Abstract

The invention discloses a large fixed-wing unmanned aerial vehicle control quality airworthiness evaluation method and device and a medium, and relates to the technical field of civil unmanned aerial vehicle airworthiness certification and flight data intelligent processing. The method comprises the steps that the control quality airworthiness requirement of a large fixed-wing unmanned aerial vehicle system is acquired; constructing an evaluation index system; constructing a flight profile automatic identification model; based on the evaluation index system, a fuzzy comprehensive evaluation method is adopted to construct a manipulation quality seaworthiness evaluation model; and obtaining the airworthiness verification flight data of the large fixed-wing unmanned aerial vehicle to be subjected to control quality airworthiness evaluation, segmenting the flight data according to profiles by using the flight profile recognition model to obtain flight parameters, calculating the Euclidean distance between the flight parameters and a design value, taking the Euclidean distance as the input of a control quality airworthiness evaluation model, and evaluating the control quality airworthiness of the large fixed-wing unmanned aerial vehicle. And obtaining a control quality airworthiness evaluation result of the unmanned aerial vehicle. According to the method provided by the invention, the problem that a reliable systematic solution for evaluating the control quality and the seaworthiness of the large fixed-wing unmanned aerial vehicle system is lacked is solved.

Description

Technical Field

[0001] The present invention relates to the field of civil unmanned aerial vehicle airworthiness certification and flight data intelligent processing technology, and more specifically, to an airworthiness evaluation method, device and medium for the control quality of a large fixed-wing unmanned aerial vehicle. Background Art

[0002] Large fixed-wing UAV systems have the characteristics of high altitude, high speed, long flight time, and large mission load. They are the "pinnacle" of the general aviation industry system and one of the main models for developing the low-altitude economy. The control quality of large fixed-wing UAV systems is the characteristics of the accuracy and difficulty of the UAV to complete the predetermined flight mission. It is an inherent attribute of the UAV that is directly related to mission completion and flight safety through design. It needs to pass airworthiness certification to show that the UAV system conforms to the design and the control quality meets the airworthiness requirements.

[0003] Aircraft handling quality airworthiness evaluation is an important part of type certification. The existing handling quality airworthiness evaluation mainly comes from the handling quality rating method based on the subjective evaluation of pilots and the flight quality evaluation method based on flight parameters and aircraft system status data developed by the Federal Aviation Administration (FAA) for transport aircraft. There are still the following problems when these methods are directly applied to the field of large fixed-wing UAV systems:

[0004] (1) Large fixed-wing UAV systems are controlled remotely by operators through ground control stations, and the operators mainly monitor the status of the aircraft. Manual command and control of the flight is only carried out when necessary or in an emergency. Evaluating the control quality of UAVs based on the subjective feelings of operators after performing flight missions is not only highly subjective, but also fails to reflect the operating characteristics of large fixed-wing UAV systems, which are mainly separated from humans and machines and mainly fly automatically.

[0005] (2) The flight quality assessment method based on flight parameters and aircraft system status information mainly uses QAR data to identify aircraft status and monitor operational risks, identifies abnormal or over-limit events by setting thresholds, and evaluates unsafe pilot operation behaviors. This is a continuous airworthiness evaluation centered on the mission process, which does not carefully reflect the flight quality influencing factors and their measurements in each section of aircraft operation, and cannot accurately evaluate the flight quality during the airworthiness certification stage.

[0006] (3) Large fixed-wing UAV systems lack a systematic airworthiness evaluation solution that starts from airworthiness requirements and establishes a control quality evaluation index system and its measurement method based on the mission flight profile. It is unable to clearly show the flight quality of the UAV under various flight profiles and cannot provide important basis for design improvements and authority review decisions.

[0007] In summary, in view of the unique operating characteristics of large fixed-wing UAV systems, developing an airworthiness evaluation method suitable for the control quality of large fixed-wing UAV systems is an urgent issue to be solved to ensure the safe operation of civil UAV systems and ensure the high-quality development of the low-altitude economy. Summary of the invention

[0008] In order to solve the above technical problems, the present invention provides a method, device and medium for evaluating the airworthiness of the control quality of a large fixed-wing UAV, so as to overcome the deficiency of lack of a reliable systematic solution for evaluating the control quality of a large fixed-wing UAV system.

[0009] In a first aspect, the present invention provides a method for evaluating the airworthiness of a large fixed-wing unmanned aerial vehicle's control quality, the method comprising:

[0010] Obtain the control quality and airworthiness requirements of large fixed-wing UAV systems;

[0011] Based on the airworthiness requirements of the control quality of the large fixed-wing UAV system, an evaluation index system is constructed;

[0012] Construct a flight profile automatic recognition model;

[0013] Based on the evaluation index system, a fuzzy comprehensive evaluation method is used to construct a control quality airworthiness evaluation model;

[0014] The airworthiness verification flight data of a large fixed-wing UAV to be evaluated for controllable quality is obtained, and the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality is segmented by profile using the flight profile recognition model to obtain the corresponding flight parameters in the evaluation index system, and the Euclidean distance between the flight parameters and the design values ​​is calculated as the input of the controllable quality airworthiness evaluation model to obtain the controllable quality airworthiness evaluation result of the UAV.

[0015] Furthermore, based on the control quality and airworthiness requirements of the large fixed-wing UAV system, an evaluation index system is constructed, including:

[0016] Construct a large fixed-wing UAV flight profile and divide the UAV operation into six flight phases: take-off, climb, level flight, hover, descent, and landing;

[0017] An evaluation index system is established based on the performance parameters corresponding to the six flight phases and the operator's workload of controlling the UAV as the top-level indicators.

[0018] Furthermore, the evaluation index system includes primary indicators, secondary indicators and tertiary indicators; wherein the primary indicators include take-off performance, climb performance, level flight performance, hovering performance, descent performance, landing performance and workload; the secondary indicators include speed, route, acceleration, attitude angle, attitude angular rate, signal delay time and environmental adaptability; the tertiary indicators include longitudinal axis speed, lateral axis speed, vertical axis speed, climb rate, descent rate, longitudinal axis direction, altitude, vertical axis direction, longitudinal axis acceleration, lateral axis acceleration, vertical axis acceleration, pitch angle, sideslip angle, roll angle, longitudinal axis attitude angular rate, lateral axis attitude angular rate, vertical axis attitude angular rate, C2 link delay time, system delay time, total delay time, range and environment.

[0019] Furthermore, a flight profile automatic recognition model is constructed, including:

[0020] Construct a flight parameter characteristic pattern X that can characterize six profiles: takeoff, climb, level flight, hover, descent, and landing, and establish the label y of the flight profile corresponding to the flight parameter pattern;

[0021] Create a data set {(X i ,y k )|i=1,2,…,n,k=1,2…6}; where X i represents the characteristic mode of the i-th flight parameter, y k Represents X i The label of , k is used to indicate the type of flight profile, and n is the number of samples in the data set;

[0022] Initialize the decision tree root node, which contains the entire data set;

[0023] The data set is divided into sections at each node and the Gini impurity G is calculated according to formula (1):

[0024]

[0025] In the formula, p k is the proportion of the k-th profile samples in the data set;

[0026] Select the feature and threshold that minimizes the weighted average Gini impurity to divide the current node. The calculation is shown in formula (2):

[0027]

[0028] Where n 1、 n 2、 G 0 , G 左 , G 右Respectively represent the number of samples in the left branch of the decision tree, the number of samples in the right branch, the Gini impurity of the parent node of the current node, the Gini impurity of the left branch, and the Gini impurity of the right branch;

[0029] Recursively process each child node until the stopping condition is met, adjust the minimum sample threshold of the node and implement pruning strategy to optimize the constructed decision tree model;

[0030] All samples of the data set are used as training sets to train the decision tree model, and the trained decision tree model is used as the flight profile automatic recognition model.

[0031] Furthermore, based on the evaluation index system, a fuzzy comprehensive evaluation method is used to construct a control quality airworthiness evaluation model, including:

[0032] The subjective weights of the secondary indicators are determined by using the analytic hierarchy process (AHP). The combined weights of the tertiary indicators are determined by using the AHP and entropy weight methods, with the weights calculated by the AHP accounting for 40% of the combined weights.

[0033] According to the secondary fuzzy comprehensive evaluation, the factor set and sub-factor set of the secondary and tertiary indicators in the control quality airworthiness evaluation index system are constructed; according to the Euclidean distance between the tertiary indicator data of the expected secondary indicators and the actual operation data, the comment set is set to {excellent, good, medium, poor, extremely poor} and the corresponding numerical evaluation standards;

[0034] The trapezoidal membership function is used to calculate the membership of each indicator to each comment set and generate a judgment matrix;

[0035] The first-level fuzzy comprehensive evaluation set is determined according to the single factor evaluation and combined weight of each factor of the three-level indicators; wherein the first-level fuzzy comprehensive evaluation set is shown in formula (3):

[0036] B i =A i ·R i =[b i1 ,b i2 ,...,b im ],i=1,2,...,s (3)

[0037] In the formula, B i represents the first-level index evaluation vector, R i represents the single factor evaluation matrix, A i represents the secondary weight, b im represents the eigenvalue of the first-level index evaluation vector, i represents the number of any sub-factor set of the comment set, and s represents the number of sub-factor sets of the comment set;

[0038] The secondary fuzzy comprehensive evaluation set is obtained through the following formula:

[0039] B=A·R=[b 1 ,b 2 ,...,b m ] (4)

[0040] In the formula, B represents the secondary indicator weight matrix, A represents the secondary indicator weight matrix, R represents the secondary indicator evaluation matrix, and b m Represents the eigenvalue of the secondary index evaluation vector.

[0041] Furthermore, the control quality airworthiness evaluation model responds to the Euclidean distance between the flight parameter of the input index and the design value, substitutes the Euclidean distance between the flight parameter of the index and the design value into each trapezoidal membership function, obtains the evaluation value of the index, normalizes the evaluation value and constructs a secondary evaluation matrix based on formula (4), and obtains the control quality airworthiness evaluation result of the UAV according to the secondary evaluation matrix and the numerical evaluation standard.

[0042] Furthermore, the trapezoidal membership function includes trapezoidal membership functions with evaluation levels of excellent, good, medium, poor and extremely poor.

[0043] Furthermore, the trapezoidal membership functions of the evaluation levels of excellent, good, medium, poor and extremely poor are respectively expressed as:

[0044]

[0045]

[0046]

[0047]

[0048]

[0049] Where x represents the Euclidean distance between the flight parameter of the indicator and the design value; A 优 (x), A 良 (x), A 中 (x), A 差 (x) and A 极差 (x) represents the trapezoidal membership of the evaluation levels of excellent, good, medium, poor and extremely poor.

[0050] In a second aspect, the present invention provides an airworthiness evaluation device for the control quality of a large fixed-wing UAV, the device comprising:

[0051] A data acquisition unit configured to acquire the airworthiness requirements of the control quality of a large fixed-wing UAV system;

[0052] A system construction unit is configured to construct an evaluation index system based on the control quality airworthiness requirements of the large fixed-wing UAV system;

[0053] A first model building unit is configured to build a flight profile automatic recognition model;

[0054] A second model building unit is configured to build a handling quality airworthiness evaluation model based on the evaluation index system using a fuzzy comprehensive evaluation method;

[0055] The airworthiness evaluation unit is configured to obtain the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality, segment the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality by profile using the flight profile recognition model, obtain the corresponding flight parameters in the evaluation index system, calculate the Euclidean distance between the flight parameters and the design value as the input of the controllable quality airworthiness evaluation model, and obtain the controllable quality airworthiness evaluation result of the UAV.

[0056] In a third aspect, the present invention provides a readable storage medium, wherein the readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method as described above.

[0057] The present invention has at least the following beneficial effects:

[0058] The present invention realizes a systematic airworthiness evaluation solution starting from airworthiness requirements and establishing a control quality evaluation index system and its measurement method based on mission flight profiles, providing a feasible idea for airworthiness compliance verification of the control quality of large fixed-wing UAVs; the control quality airworthiness evaluation method that integrates subjective and objective factors more accurately evaluates the control quality of UAVs in the airworthiness certification stage; and clearly shows the control quality of UAVs under various flight profiles, providing an important basis for design improvements and authority certification decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A flow chart of a method for evaluating the airworthiness of control quality of a large fixed-wing UAV according to an embodiment of the present invention is shown.

[0060] Figure 2 A schematic diagram of a large fixed-wing UAV system control quality airworthiness evaluation framework according to an embodiment of the present invention is shown.

[0061] Figure 3 A flight profile recognition flow chart of a flight profile automatic recognition model according to an embodiment of the present invention is shown.

[0062] Figure 4A structural diagram of an airworthiness evaluation device for the control quality of a large fixed-wing UAV according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and specific embodiments, but are not intended to limit the present invention. For the various steps described herein, if there is no necessity for a causal relationship between each other, the order in which they are described as examples herein should not be regarded as a limitation, and those skilled in the art should know that they can be adjusted in order, as long as the logic between them is not destroyed, resulting in the inability to implement the entire process.

[0064] The embodiment of the present invention provides an airworthiness evaluation method for the control quality of a large fixed-wing unmanned aerial vehicle. By semi-supervised optimization of the image enhancement module based on the pre-trained target detection module, the target detection features are directly optimized to improve the utilization efficiency of unlabeled data. At the same time, a residual image enhancement foggy target detection model is designed based on the semi-supervised optimization framework to further improve the foggy detection performance. In addition, in order to solve the problem of feature differences between synthetic and real foggy images, the present invention provides an unsupervised domain adaptive data enhancement method, which enhances the training data by transferring the statistical information of unlabeled real foggy images during the training process. Finally, the foggy target detection technology of the present invention uses the proposed new foggy target detection data set for optimization training. The data set is a semi-supervised data set, which contains more than 120,000 high-quality labeled images and about 30,000 unlabeled images, providing a large-scale, semi-supervised and reliable data resource for the field of foggy target detection. The present invention significantly improves the generalization ability and detection accuracy of the model in real foggy scenes.

[0065] Specifically, if Figure 1 FIG. 1 is a flow chart of a method for evaluating the airworthiness of a large fixed-wing UAV control quality. The method for evaluating the airworthiness of a large fixed-wing UAV control quality includes steps S10 to S50, which are described in detail as follows.

[0066] S10: Obtain the airworthiness requirements for the control quality of large fixed-wing UAV systems.

[0067] For example, the top-level airworthiness requirements for the control quality of large UAVs are mainly the CCAR92.703 clauses, and the specific requirements exist in Chapter B of the special conditions for airworthiness of large UAVs with various operating characteristics or in the flight and performance-related contents of the general requirements. GB / T 43504-2023, GB / T38996-2020, GB / T38911-2020, and GB / T 42862-2023 provide flight test requirements for the flight performance of large and medium-sized fixed-wing UAVs and general requirements for UAV flight control systems. The comprehensive application of these standards provides a conformity verification method for the evaluation of control quality airworthiness. Establish a control quality airworthiness standard system, that is, CCAR92.703 is the top-level standard, the special conditions for airworthiness certification of various large UAV models that have been published are the second-level standards, and GB is the third-level standard, and the control quality airworthiness requirements are extracted from top to bottom.

[0068] S20: Construct an evaluation index system based on the control quality and airworthiness requirements of large fixed-wing UAV systems.

[0069] In some embodiments, the evaluation index system is constructed by the following method:

[0070] The flight profile of a large fixed-wing UAV is constructed, and the operation of the UAV is divided into six flight stages: take-off, climb, level flight, hover, descent, and landing. The control quality is defined as take-off, climb, level flight, hover, descent, landing, and endurance performance. These seven performances are used as top-level indicators to establish a control quality airworthiness evaluation index system. The control quality of each stage is evaluated and the control quality of the UAV system is comprehensively obtained. Combined with the operating characteristics of the UAV system, which is mainly automatic flight and manual command and control in necessary or emergency situations, the workload of the operator controlling the UAV is also used as an airworthiness evaluation index of the control quality. After the operator performs the manual command and control mission flight, the workload level can be obtained by filling in the NASA-TLX scale. Based on this airworthiness evaluation framework, the airworthiness evaluation of the control quality of each profile and the overall control quality in manual control and automatic flight modes is realized.

[0071] For example, Figure 2The figure shows a schematic diagram of the airworthiness evaluation framework for the control quality of large fixed-wing UAV systems. The evaluation index system includes first-level, second-level and third-level indicators; among them, the first-level indicators include take-off performance, climb performance, level flight performance, hovering performance, gliding performance, landing performance and workload; the second-level indicators include speed, route, acceleration, attitude angle, attitude angular rate, signal delay time and environmental adaptability; the third-level indicators include longitudinal speed, transverse speed, vertical speed, climb rate, gliding rate, longitudinal direction, altitude, vertical direction, longitudinal acceleration, transverse acceleration, vertical acceleration, pitch angle, sideslip angle, roll angle, longitudinal attitude angular rate, transverse attitude angular rate, vertical attitude angular rate, C2 link delay time, system delay time, total delay time, range and environment.

[0072] Specifically, each first-level indicator corresponds to all second-level indicators. Taking takeoff performance as an example, its corresponding second-level indicators represent the speed, route, acceleration, attitude angle, attitude angular rate, signal delay time and environmental adaptability during the takeoff phase. The second-level indicators corresponding to the other first-level indicators are similar and will not be described in detail here. A second-level indicator corresponds to a specific third-level indicator. Specifically, the speed in the second-level indicator corresponds to the longitudinal speed, transverse speed, vertical speed, climb rate, and glide rate; the route corresponds to the longitudinal direction, altitude, and vertical direction; the acceleration corresponds to the longitudinal acceleration, transverse acceleration, and vertical acceleration; the attitude angle corresponds to the pitch angle, sideslip angle, and roll angle; the attitude angular rate corresponds to the longitudinal attitude angular rate, transverse attitude angular rate, and vertical attitude angular rate; the signal delay time corresponds to the C2 link delay time, system delay time, and total delay time; and the environmental adaptability corresponds to the range and environment.

[0073] S30: Construct a flight profile automatic recognition model.

[0074] In some embodiments, step S30 is implemented by the following steps:

[0075] S31, construct a flight parameter feature pattern X that can characterize the six profiles of takeoff, climb, level flight, hover, descent, and landing, and establish a label y for the flight profile corresponding to the flight parameter pattern. Given a data set {(X i ,y k )|i=1,2,…,n,k=1,2…6}, initialize the root node of the decision tree, which contains the entire data set. The data set is profiled at each node and the Gini impurity G is calculated according to formula (1). The p in formula (1) k is the proportion of the k-th profile samples in the data set.

[0076]

[0077] S32, select the feature and threshold that minimize the weighted average Gini impurity to divide the current node, and the weighted average Gini impurity The calculation is shown in formula (2), n 1、 n 2、 G 0 , G 左 , G 右 They represent the number of samples in the left branch of the decision tree, the number of samples in the right branch, the Gini impurity of the parent node of the current node, the Gini impurity of the left branch, and the Gini impurity of the right branch.

[0078]

[0079] S33, recursively process each child node until the stop condition is met. Finally, the minimum sample threshold of the node is adjusted and the pruning strategy is implemented to optimize the constructed decision tree model. All samples of the data set are used as training sets to train the decision tree model, and the trained model is used to predict the input feature vector X, that is, the flight profile corresponding to the feature vector is obtained.

[0080] For example, Figure 3 As shown in the figure, it is a flow chart of flight profile recognition of the automatic flight profile recognition model. First, it is determined whether the UAV is in the climbing stage. If the height change rate is ≥1.00017, it is determined to be in the climbing stage. If the height change rate is <1.00017, it is further determined whether it is in the descent stage. If the height change rate is <-0.099977, it is determined to be in the descent stage. If the height change rate is ≥-0.099977, it is further determined whether it is in the take-off stage or the level flight stage. If the normalized height is <0.0672824, it is determined to be in the take-off stage. If the normalized height is ≥0.0672824, it is determined to be in the level flight stage.

[0081] S40: Based on the evaluation index system, a fuzzy comprehensive evaluation method is used to construct a control quality airworthiness evaluation model.

[0082] In some embodiments, step S40 is implemented by the following steps:

[0083] S41. Select UAV certification test flight crew and scientific research test flight crew as expert members, evaluate and score the control quality airworthiness of the third-level indicators under each second-level indicator, and use the Analytic Hierarchy Process (AHP) to determine the subjective weight of the second-level airworthiness evaluation indicator; then use AHP and Entropy Weight Method (EWM) to comprehensively determine the combined weight of the three-level indicators, among which the weight calculated by AHP accounts for 40% of the final weight.

[0084] S42. Construct a control quality airworthiness evaluation model based on fuzzy comprehensive evaluation: Construct the factor set and sub-factor set of the second-level and third-level indicators in the control quality airworthiness evaluation index system according to the second-level fuzzy comprehensive evaluation; according to the Euclidean distance between the third-level indicator data of the expected second-level indicator and the actual operation data, set the comment set as {excellent, good, medium, poor, extremely poor} and the corresponding numerical evaluation criteria in combination with expert opinions; use the trapezoidal membership function to calculate the membership of each indicator to each comment set, and generate a judgment matrix. The first-level fuzzy comprehensive evaluation is determined by the single factor evaluation of each factor of the third-level indicator and the multi-factor comprehensive evaluation results of the indicator at this level. The single factor evaluation matrix is ​​R i The weight of each indicator is the combined weight determined by AHP+EWM. The first-level weight is set as A 1×s , the secondary weight is The first-level fuzzy comprehensive evaluation set is obtained, as shown in formula (3).

[0085] B i =A i ·R i =[b i1 ,b i2 ,...,b im ],i=1,2,...,s (3)

[0086] In the formula, B i represents the first-level index evaluation vector, R i represents the single factor evaluation matrix, A i represents the secondary weight, b im It represents the eigenvalue of the first-level index evaluation vector, i represents the number of any sub-factor set of the comment set, and s represents the number of sub-factor sets of the comment set.

[0087] The secondary fuzzy comprehensive evaluation set is shown in formula (4).

[0088] B=A·R=[b 1 ,b 2 ,...,b m ] (4)

[0089] In the formula, B represents the secondary indicator weight matrix, A represents the secondary indicator weight matrix, R represents the secondary indicator evaluation matrix, and b m Represents the eigenvalue of the secondary index evaluation vector.

[0090] The secondary fuzzy comprehensive evaluation set determines the membership of the secondary indicators to each evaluation set. The seven vectors obtained are combined into a fuzzy judgment matrix to solve the weight of each indicator for the evaluation of control quality and airworthiness. The overall evaluation result of the control quality and airworthiness of the UAV is obtained by matrix synthesis.

[0091] S50: Acquire the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for its controllable quality, segment the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for its controllable quality by profile using the flight profile recognition model, obtain the corresponding flight parameters in the evaluation index system, calculate the Euclidean distance between the flight parameters and the design values, and use the calculated Euclidean distance as the input of the controllable quality airworthiness evaluation model to obtain the controllable quality airworthiness evaluation result of the UAV.

[0092] In this embodiment, the purpose of step S50 is to implement the airworthiness evaluation of each flight profile or the overall control quality of a large fixed-wing UAV. Obtain the airworthiness verification flight data of the large fixed-wing UAV whose control quality is to be evaluated, and use the flight profile identification model constructed in step S30 to segment the flight data by profile, and obtain the flight parameters corresponding to all the third-level indicators under the second-level indicator of environmental adaptability in the airworthiness evaluation index system in step S20. Calculate the Euclidean distance between the flight parameters and the design value as the input of step S40. The control quality airworthiness of each profile of the UAV can be evaluated according to the second-level comprehensive evaluation method of step S40; the control quality airworthiness evaluation result of the UAV can be obtained by performing fuzzy comprehensive evaluation on the 7 first-level indicators.

[0093] The feasibility and advancement of the present invention will be further illustrated below in conjunction with specific examples.

[0094] In a specific example, the airworthiness evaluation method for the control quality of a large fixed-wing UAV is implemented by the following steps to evaluate the airworthiness of the control quality of a large fixed-wing UAV:

[0095] Step 1: Extract the control quality airworthiness requirements of large fixed-wing UAV system according to step S10 mentioned above.

[0096] Step 2: Construct a large fixed-wing UAV control quality airworthiness evaluation framework according to step S20 mentioned above.

[0097] Step 3: Construct a large fixed-wing UAV flight profile automatic recognition model based on a decision tree, which is implemented by the following steps:

[0098] Step 31, flight parameter acquisition: After the large fixed-wing UAV airworthiness verification flight, the flight data set is constructed using the UAV speed, altitude, attitude and other data recorded by the ground station at each moment and transmitted back through the communication link downlink. The data sets of each dimension are normalized, and the altitude change rate and altitude are selected as the feature mode X of the decision tree, and the flight profile label y corresponding to the feature mode is manually marked. k ,{(X i ,y k )|i=1,2,…,n,k=1,2…6} is used as the training set for decision tree model training.

[0099] Step 32, model training and prediction: The decision tree model is constructed and trained through the ClassificationTree.fit() function of MATLAB, and the predict() function implements the input feature pattern to obtain the predicted profile.

[0100] Step 33: Continuous optimization of the model: Generate an optimized decision tree model by setting the minimum number of sample data in the ClassificationTree.fit() function and performing pruning with the cvloss() and prune() functions, and add the correctly predicted samples to the training set.

[0101] Step 4: Taking the airworthiness evaluation of the control quality of a certain type of UAV during the manual landing phase as an example, the airworthiness evaluation is carried out through the following steps:

[0102] Step 41, collect flight parameters, and use the constructed profile recognition decision tree model to extract flight parameters for the landing phase. Select the UAV certification test flight crew and the scientific research test flight crew as expert members, evaluate and score the control quality and airworthiness of the third-level indicators under each second-level indicator of the first-level indicator "landing performance", fill in the NASA-TLX scale, and calculate the workload level. Use AHP to determine the subjective weight of the second-level indicator; then use AHP+EWM to comprehensively determine the combined weight of the third-level indicators, of which the weight calculated by AHP accounts for 40% of the total weight.

[0103] Step 42: Construct a landing control quality airworthiness evaluation model based on fuzzy comprehensive evaluation: Construct a fuzzy evaluation factor set U and a sub-factor set U according to step S4 mentioned above. i , the judgment set V = {excellent, good, medium, poor, extremely poor}. The Euclidean distance between the flight parameters of the landing profile and the design value is calculated, and the evaluation criteria of the comment set are constructed in combination with the expert opinions. The results are shown in Table 1. According to Table 1, the trapezoidal membership function formula is established as shown in formulas (5) to (9). In formulas (5) to (9), x represents the Euclidean distance between the flight parameters of the indicator and the design value; A 优 (x), A 良 (x), A 中 (x), A 差 (x) and A 极差 (x) represents the trapezoidal membership of the evaluation levels of excellent, good, medium, poor and extremely poor.

[0104] Table 1 Evaluation criteria for the review set

[0105] Rating Evaluation Criteria excellent [0，0.2] good (0.2，0.4] middle (0.4，0.6] Difference (0.6，0.8] Very bad (0.8，+∞)

[0106] Trapezoidal membership function for an evaluation grade of "excellent":

[0107]

[0108] Trapezoidal membership function for evaluation grade "good":

[0109]

[0110] Trapezoidal membership function for evaluation level "medium":

[0111]

[0112] Trapezoidal membership function for a rating of "poor":

[0113]

[0114] Trapezoidal membership function for the evaluation level "very bad":

[0115]

[0116] Step 43, landing control quality evaluation results: Substitute the Euclidean distance between the flight parameters of the corresponding indicators and the design values ​​into each trapezoidal membership function to obtain the evaluation value of each indicator. Normalize the evaluation value and construct a secondary evaluation matrix

[0117] B=[0.22251,0.635023,0.039867,0,0.1026]

[0118] According to the principle of maximum membership, 0.635023 is the maximum value, corresponding to the second position among "excellent, good, medium, poor, and very poor". The landing quality airworthiness assessment level of this type of UAV is "good".

[0119] The embodiment of the present invention also provides an airworthiness evaluation device for the control quality of a large fixed-wing UAV, such as Figure 4 As shown, the device comprises:

[0120] The data acquisition unit 401 is configured to acquire the airworthiness requirements of the control quality of the large fixed-wing UAV system;

[0121] A system construction unit 402 is configured to construct an evaluation index system based on the control quality airworthiness requirements of the large fixed-wing UAV system;

[0122] A first model building unit 403 is configured to build a flight profile automatic recognition model;

[0123] The second model building unit 404 is configured to build a handling quality airworthiness evaluation model based on the evaluation index system using a fuzzy comprehensive evaluation method;

[0124] The airworthiness evaluation unit 405 is configured to obtain the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality, segment the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality by profile using the flight profile identification model, obtain the corresponding flight parameters in the evaluation index system, calculate the Euclidean distance between the flight parameters and the design value as the input of the controllable quality airworthiness evaluation model, and obtain the controllable quality airworthiness evaluation result of the UAV.

[0125] In some embodiments, the system building unit is further configured to:

[0126] Construct a large fixed-wing UAV flight profile and divide the UAV operation into six flight phases: take-off, climb, level flight, hover, descent, and landing;

[0127] An evaluation index system is established based on the performance parameters corresponding to the six flight phases and the operator's workload of controlling the UAV as the top-level indicators.

[0128] In some embodiments, the evaluation index system includes primary indicators, secondary indicators and tertiary indicators; wherein the primary indicators include take-off performance, climb performance, level flight performance, hovering performance, descent performance, landing performance and workload; the secondary indicators include speed, route, acceleration, attitude angle, attitude angular rate, signal delay time and environmental adaptability; the tertiary indicators include longitudinal axis speed, lateral axis speed, vertical axis speed, climb rate, descent rate, longitudinal axis direction, altitude, vertical axis direction, longitudinal axis acceleration, lateral axis acceleration, vertical axis acceleration, pitch angle, sideslip angle, roll angle, longitudinal axis attitude angular rate, lateral axis attitude angular rate, vertical axis attitude angular rate, C2 link delay time, system delay time, total delay time, range and environment.

[0129] In some embodiments, the first model building unit is further configured to:

[0130] Construct a flight parameter characteristic pattern X that can characterize six profiles: takeoff, climb, level flight, hover, descent, and landing, and establish the label y of the flight profile corresponding to the flight parameter pattern;

[0131] Create a data set {(X i ,y k )|i=1,2,…,n,k=1,2…6}; where X i represents the characteristic mode of the i-th flight parameter, y k Represents X i The label of , k is used to indicate the type of flight profile, and n is the number of samples in the data set;

[0132] Initialize the decision tree root node, which contains the entire data set;

[0133] The data set is divided into sections at each node and the Gini impurity G is calculated according to formula (1):

[0134]

[0135] In the formula, p k is the proportion of the k-th profile samples in the data set;

[0136] Select the feature and threshold that minimizes the weighted average Gini impurity to divide the current node. The calculation is shown in formula (2):

[0137]

[0138] Where n 1、 n 2、 G 0 , G 左 , G 右 Respectively represent the number of samples in the left branch of the decision tree, the number of samples in the right branch, the Gini impurity of the parent node of the current node, the Gini impurity of the left branch, and the Gini impurity of the right branch;

[0139] Recursively process each child node until the stopping condition is met, adjust the minimum sample threshold of the node and implement pruning strategy to optimize the constructed decision tree model;

[0140] All samples of the data set are used as training sets to train the decision tree model, and the trained decision tree model is used as the flight profile automatic recognition model.

[0141] In some embodiments, the second model building unit is further configured to:

[0142] The subjective weights of the secondary indicators are determined by using the analytic hierarchy process (AHP). The combined weights of the tertiary indicators are determined by using the AHP and entropy weight methods, with the weights calculated by the AHP accounting for 40% of the combined weights.

[0143] According to the secondary fuzzy comprehensive evaluation, the factor set and sub-factor set of the secondary and tertiary indicators in the control quality airworthiness evaluation index system are constructed; according to the Euclidean distance between the tertiary indicator data of the expected secondary indicators and the actual operation data, the comment set is set to {excellent, good, medium, poor, extremely poor} and the corresponding numerical evaluation standards;

[0144] The trapezoidal membership function is used to calculate the membership of each indicator to each comment set and generate a judgment matrix;

[0145] The first-level fuzzy comprehensive evaluation set is determined according to the single factor evaluation and combined weight of each factor of the three-level indicators; wherein the first-level fuzzy comprehensive evaluation set is shown in formula (3):

[0146] B i =A i ·R i =[b i1 ,b i2 ,...,b im ],i=1,2,...,s (3)

[0147] In the formula, B i represents the first-level index evaluation vector, R i represents the single factor evaluation matrix, A i represents the secondary weight, b im represents the eigenvalue of the first-level index evaluation vector, i represents the number of any sub-factor set of the comment set, and s represents the number of sub-factor sets of the comment set;

[0148] The secondary fuzzy comprehensive evaluation set is obtained through the following formula:

[0149] B=A·R=[b 1 ,b 2 ,...,b m ] (4)

[0150] In the formula, B represents the secondary indicator weight matrix, A represents the secondary indicator weight matrix, R represents the secondary indicator evaluation matrix, and b m Represents the eigenvalue of the secondary index evaluation vector.

[0151] In some embodiments, the control quality airworthiness evaluation model responds to the Euclidean distance between the flight parameter of the input index and the design value, substitutes the Euclidean distance between the flight parameter of the index and the design value into each trapezoidal membership function, obtains the evaluation value of the index, normalizes the evaluation value and constructs a secondary evaluation matrix based on formula (4), and obtains the control quality airworthiness evaluation result of the UAV according to the secondary evaluation matrix and the numerical evaluation standard.

[0152] In some embodiments, the trapezoidal membership function includes a trapezoidal membership function with evaluation levels of excellent, good, medium, poor and extremely poor.

[0153] In some embodiments, the trapezoidal membership functions of the evaluation levels of excellent, good, medium, poor and extremely poor are respectively expressed as:

[0154]

[0155]

[0156]

[0157]

[0158]

[0159] Where x represents the Euclidean distance between the flight parameter of the indicator and the design value; A 优 (x), A 良 (x), A 中 (x), A 差 (x) and A 极差 (x) represents the trapezoidal membership of the evaluation levels of excellent, good, medium, poor and extremely poor.

[0160] It should be noted that the structure of the airworthiness evaluation device for the control quality of each large fixed-wing UAV described in this embodiment belongs to the same technical concept as the airworthiness evaluation method for the control quality of a large fixed-wing UAV described previously, and achieves the same beneficial effect through the same principle, which will not be repeated here.

[0161] An embodiment of the present invention further provides a readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the method described in any of the above embodiments.

[0162] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present invention with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. The elements in the claims will be interpreted broadly based on the language adopted in the claims, and are not limited to the examples described in this specification or during the implementation of this application, and the examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, and the true scope and spirit are indicated by the following claims and the full scope of their equivalents.

[0163] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art can use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features can be grouped together to simplify the present invention. This should not be interpreted as a feature of an invention that is not claimed for protection being necessary for any claim. On the contrary, the subject matter of the present invention may be less than all the features of the embodiments of a specific invention. Thus, the following claims are incorporated into the specific embodiments as examples or embodiments, wherein each claim is independently used as a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or arrangements. The scope of the present invention should be determined with reference to the full scope of the equivalent forms of the attached claims and these claims.

Claims

1. A method for evaluating the airworthiness of the control quality of a large fixed-wing UAV, characterized in that: The method comprises: Obtain the control quality and airworthiness requirements of large fixed-wing UAV systems; Based on the airworthiness requirements of the control quality of the large fixed-wing UAV system, an evaluation index system is constructed; Construct a flight profile automatic recognition model; Based on the evaluation index system, a fuzzy comprehensive evaluation method is used to construct a control quality airworthiness evaluation model; The airworthiness verification flight data of a large fixed-wing UAV to be evaluated for controllable quality is obtained, and the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality is segmented by profile using the flight profile recognition model to obtain the corresponding flight parameters in the evaluation index system, and the Euclidean distance between the flight parameters and the design values ​​is calculated as the input of the controllable quality airworthiness evaluation model to obtain the controllable quality airworthiness evaluation result of the UAV.

2. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 1 is characterized in that: Based on the control quality and airworthiness requirements of the large fixed-wing UAV system, an evaluation index system is constructed, including: Construct a large fixed-wing UAV flight profile and divide the UAV operation into six flight phases: take-off, climb, level flight, hover, descent, and landing; An evaluation index system is established based on the performance parameters corresponding to the six flight phases and the operator's workload of controlling the UAV as the top-level indicators.

3. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 2 is characterized in that: The evaluation index system includes primary indicators, secondary indicators and tertiary indicators; wherein the primary indicators include take-off performance, climb performance, level flight performance, hovering performance, descent performance, landing performance and workload; the secondary indicators include speed, route, acceleration, attitude angle, attitude angular rate, signal delay time and environmental adaptability; the tertiary indicators include longitudinal axis speed, lateral axis speed, vertical axis speed, climb rate, descent rate, longitudinal axis direction, altitude, vertical axis direction, longitudinal axis acceleration, lateral axis acceleration, vertical axis acceleration, pitch angle, sideslip angle, roll angle, longitudinal axis attitude angular rate, lateral axis attitude angular rate, vertical axis attitude angular rate, C2 link delay time, system delay time, total delay time, range and environment.

4. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 1 is characterized in that: Build a flight profile automatic recognition model, including: Construct a flight parameter characteristic pattern X that can characterize six profiles: takeoff, climb, level flight, hover, descent, and landing, and establish the label y of the flight profile corresponding to the flight parameter pattern; Create a data set {(X i ,y k )|i=1,2,…,n,k=1,2…6}; where X i represents the characteristic mode of the i-th flight parameter, y k Represents X i The label of , k is used to indicate the type of flight profile, and n is the number of samples in the data set; Initialize the decision tree root node, including the entire data set; The data set is divided into sections at each node and the Gini impurity G is calculated according to formula (1): In the formula, p k is the proportion of the k-th profile samples in the data set; Select the feature and threshold that minimizes the weighted average Gini impurity to divide the current node. The calculation is shown in formula (2): Where n 1、 n 2、 G0, G 左 , G 右 Respectively represent the number of samples in the left branch of the decision tree, the number of samples in the right branch, the Gini impurity of the parent node of the current node, the Gini impurity of the left branch, and the Gini impurity of the right branch; Recursively process each child node until the stopping condition is met, adjust the minimum sample threshold of the node and implement pruning strategy to optimize the constructed decision tree model; All samples of the data set are used as training sets to train the decision tree model, and the trained decision tree model is used as the flight profile automatic recognition model.

5. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 3 is characterized in that: Based on the evaluation index system, a fuzzy comprehensive evaluation method is used to construct a control quality airworthiness evaluation model, including: The subjective weights of the secondary indicators are determined by using the analytic hierarchy process (AHP). The combined weights of the tertiary indicators are determined by using the AHP and entropy weight methods, with the weights calculated by the AHP accounting for 40% of the combined weights. According to the secondary fuzzy comprehensive evaluation, the factor set and sub-factor set of the secondary and tertiary indicators in the control quality airworthiness evaluation index system are constructed; according to the Euclidean distance between the tertiary indicator data of the expected secondary indicators and the actual operation data, the comment set is set to {excellent, good, medium, poor, extremely poor} and the corresponding numerical evaluation standards; The trapezoidal membership function is used to calculate the membership of each indicator to each comment set and generate a judgment matrix; The first-level fuzzy comprehensive evaluation set is determined according to the single factor evaluation and combined weight of each factor of the three-level indicators; wherein the first-level fuzzy comprehensive evaluation set is shown in formula (3): B i =A i ·R i =[b i1 ,b i2 ,...,b im ],i=1,2,...,s (3) In the formula, B i represents the first-level index evaluation vector, R i represents the single factor evaluation matrix, A i represents the secondary weight, b im represents the eigenvalue of the first-level index evaluation vector, i represents the number of any sub-factor set of the comment set, and s represents the number of sub-factor sets of the comment set; The secondary fuzzy comprehensive evaluation set is obtained through the following formula: B=A·R=[b1,b2,...,b m ] (4) In the formula, B represents the secondary indicator weight matrix, A represents the secondary indicator weight matrix, R represents the secondary indicator evaluation matrix, and b m Represents the eigenvalue of the secondary index evaluation vector.

6. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 5 is characterized in that: The control quality airworthiness evaluation model responds to the Euclidean distance between the flight parameter of the input index and the design value, substitutes the Euclidean distance between the flight parameter of the index and the design value into each trapezoidal membership function, obtains the evaluation value of the index, normalizes the evaluation value and constructs a secondary evaluation matrix based on formula (4), and obtains the control quality airworthiness evaluation result of the UAV according to the secondary evaluation matrix and the numerical evaluation standard.

7. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 5 is characterized in that: The trapezoidal membership function includes trapezoidal membership functions with evaluation levels of excellent, good, medium, poor and extremely poor.

8. The airworthiness evaluation method for the control quality of a large fixed-wing UAV according to claim 7 is characterized in that: The trapezoidal membership functions of the evaluation grades of excellent, good, medium, poor and extremely poor are respectively expressed as: Where x represents the Euclidean distance between the flight parameter of the indicator and the design value; A 优 (x), A 良 (x), A 中 (x), A 差 (x) and A 极差 (x) represents the trapezoidal membership of the evaluation levels of excellent, good, medium, poor and extremely poor.

9. An airworthiness evaluation device for the control quality of a large fixed-wing UAV, characterized in that: The device comprises: A data acquisition unit configured to acquire the airworthiness requirements of the control quality of a large fixed-wing UAV system; A system construction unit is configured to construct an evaluation index system based on the control quality airworthiness requirements of the large fixed-wing UAV system; A first model building unit is configured to build a flight profile automatic recognition model; A second model building unit is configured to build a handling quality airworthiness evaluation model based on the evaluation index system using a fuzzy comprehensive evaluation method; The airworthiness evaluation unit is configured to obtain the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality, segment the airworthiness verification flight data of the large fixed-wing UAV to be evaluated for controllable quality by profile using the flight profile recognition model, obtain the corresponding flight parameters in the evaluation index system, calculate the Euclidean distance between the flight parameters and the design value as the input of the controllable quality airworthiness evaluation model, and obtain the controllable quality airworthiness evaluation result of the UAV. 10 . A non-transitory computer-readable storage medium storing instructions, which, when executed by a processor, perform the method according to claim 1 .

Images