Airport safety operation and maintenance capability generation method
By constructing an island airport security operation and maintenance capability index system and an improved BP neural network algorithm, the subjectivity and efficiency problems of airport security operation and maintenance capability evaluation in the existing technology are solved, and a scientific and effective task success rate evaluation is achieved.
Patent Information
- Application Number
- CN202510291788.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-12
- Publication Date
- 2025-07-08
AI Technical Summary
The existing airport security operation and maintenance capabilities assessment methods have problems such as strong subjectivity, low computing efficiency, large data processing scale, and complex modeling constraints, making it difficult to achieve scientific and effective evaluation.
An island airport security operation and maintenance capability index system was designed, a task-oriented security operation and maintenance capability index mapping model was built, and an improved BP neural network algorithm was used to determine the index weight based on adaptive learning to generate a solution for security operation and maintenance capabilities.
It improves the scientificity and efficiency of airport security operation and maintenance capabilities assessment, ensures the success rate of tasks, and provides scientific and effective evaluation methods.
Smart Images
Figure CN120278577A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of systems engineering, and particularly to a method for generating airport safety operation and maintenance capabilities. Background Art
[0002] In China, the technology for generating airport safety operation and maintenance capabilities has relatively little research at present, and the main research content is relatively focused on the aspect of capability evaluation.
[0003] The existing methods mainly include multi-attribute evaluation methods, data analysis methods, modeling and simulation methods, and combined evaluation methods. Typical multi-attribute evaluation methods include the analytic hierarchy process, Delphi method, fuzzy evaluation method, etc. This type of method presents the requirements of the evaluation object in the form of an index set or index system, establishes the index system and its configuration according to the attributes of the evaluation object, further clarifies the index weights, and finally determines the system effectiveness through index scoring and construction of a measurement function. However, it is generally used for the comprehensive effectiveness evaluation of the system, and the evaluation process is affected by the prior knowledge or preferences of experts, with a certain degree of subjectivity. The data analysis methods mainly include principal component analysis, entropy weight method, support vector machine method, artificial neural network, etc. This type of method mainly uses statistical or corresponding mathematical methods to analyze and demonstrate the key attributes of the evaluation object, but the sample demand is large, and the calculation efficiency is low when the data processing scale is large. The modeling and simulation methods mainly include system dynamics, discrete event simulation, and agent simulation methods. This type of method models various entities, system operation logic, and constraint relationships of the evaluation object system, obtains a large amount of simulation data through simulating system operation and Monte Carlo experiments, and statistically analyzes its key indicators. Compared with other methods, the modeling and simulation method is more in line with the actual statistical laws, but due to the complex modeling constraints, a large number of state transitions, and a large amount of data statistics, the efficiency design of the evaluation algorithm is the key to affecting its application. Summary of the Invention
[0004] The purpose of the embodiments of the present invention is to provide a method for generating airport safety operation and maintenance capabilities. Taking the safety operation and maintenance tasks of islands as the traction, a mapping model of guarantee tasks, safety operation and maintenance requirements, and safety operation and maintenance capability index sets is designed. Finally, with the task success rate as the goal, based on the improved BP neural network algorithm, a method for determining index weights oriented to tasks is designed to provide a scientific and effective method and technical solution for the generation of airport safety operation and maintenance capabilities.
[0005] To achieve the above purpose, the embodiments of the present invention provide a method for generating airport safety operation and maintenance capabilities, including: Construct an index system for the safety operation and maintenance capabilities of island airports; Based on the safety operation and maintenance task list of island airports and the index system for the safety operation and maintenance capabilities of island airports, construct a mapping model of safety operation and maintenance capability indicators oriented to tasks; With the success rate of the safety operation and maintenance tasks of island airports as the goal, based on the BP neural network of adaptive learning, determine the index weights of the safety operation and maintenance ability indicators; Based on the index weights of the safety operation and maintenance ability indicators, determine the importance degree affecting the safety operation and maintenance, and thus generate a plan for the safety operation and maintenance ability.
[0006] Optionally, construct an index system for the safety operation and maintenance ability of island airports, including: Combined with the environmental characteristics of island airports, construct an index system for the safety operation and maintenance of island airports from multiple dimensions and multiple specialties. Among them, the index system includes multiple first-level indicators, each first-level indicator corresponds to multiple second-level indicators, and each second-level indicator corresponds to multiple third-level indicators.
[0007] Based on the safety operation and maintenance task list of island airports and the index system for the safety operation and maintenance ability of island airports, construct a task-oriented mapping model for the safety operation and maintenance ability indicators, including: Based on the safety operation and maintenance task list of the airport, and denote the set of safety operation and maintenance tasks of the island airport as , where is the th task; Assume that the th task is decomposed into activities, and denote the set of activities as , , where is the th activity in the th task; Assume that the safety operation and maintenance requirement set corresponding to the th task and the th activity is denoted as , is decomposed into activities, denoted as , where is the th activity in the th requirement; Determine the set of ability indicators corresponding to the corresponding task , denote as the mapping model from the th task to the ability indicators, where the set of ability indicators is a subset of the index system for the safety operation and maintenance ability of island airports.
[0008] Optionally, the construction process of the BP neural network of adaptive learning includes: Set the numbers of the input layer, hidden layer, and output layer respectively, as well as the number of nodes corresponding to the input layer, hidden layer, and output layer. Among them, the number of nodes corresponding to the input layer is the same as the number of island airport safety capability indicators; Configure the index weights, denoted as the index weight of the th index, the weight of the th index for the th neuron in the hidden layer, and the weight of the th neuron in the hidden layer for the output result; Adopt the sigmoid function as the activation function and the logsig(n) function as the transfer function, and configure the neuron threshold and the threshold of the output node. Among them, the threshold of the output node is determined by the mission success degree; Among them, the adaptive learning BP neural network includes an input layer, a hidden layer, and an output layer.
[0009] Optionally, the number of hidden layer nodes satisfies the following formula: ; In the formula, is a constant, m represents the number of hidden layer nodes, is the number of input layer nodes, is the number of output layer nodes.
[0010] Optionally, calculate the mission success degree according to the following formula: ; In the formula, D represents the mission success degree, is the mission reliability, is the recovery degree when the system is in an unreliable state.
[0011] Optionally, with the success rate of the island airport safety operation and maintenance task as the goal, based on the adaptive learning BP neural network, determine the index weights of the safety operation and maintenance capability indicators, including: Based on the adaptive learning BP neural network, use the mission success degree as the output threshold constraint condition to train the weights of each layer of neurons; If the output meets the mission success degree, determine the weights of each layer of neurons as the index weights of the safety operation and maintenance capability indicators; if the output does not meet the mission success degree, update the weights of each layer of neurons through the adaptive learning rate.
[0012] Optionally, calculate the adaptive learning rate according to the following formula: ; In the formula, E(k) is the kSum of squared step errors E(k +1 ) is the sum of squared errors for the k +1 step, η(k) and is the k step learning factor.
[0013] Through the above technical solution, taking the island security operation and maintenance task as the traction, a mapping model of the guarantee task, security operation and maintenance requirements, and security operation and maintenance capability index set is designed. Finally, with the task success rate as the goal, based on the improved BP neural network algorithm, a method for determining the index weight for tasks is designed, providing a scientific and effective method and technical solution for generating the security operation and maintenance capability of the airport, and improving work efficiency.
[0014] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification. Together with the following specific implementation, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings: Figure 1 is the implementation flowchart of a method for generating the security operation and maintenance capability of an airport provided by an embodiment of the present invention; Figure 2 is a schematic diagram of an index system provided by an embodiment of the present invention; Figure 3 is a schematic diagram of the process for tailoring the airport security operation and maintenance capability index for tasks provided by an embodiment of the present invention; Figure 4 is a schematic diagram of the BP neural network structure based on the adaptive learning rate provided by an embodiment of the present invention; Figure 5 is a schematic diagram of the process for determining the weight of the security operation and maintenance capability index based on the neural network provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0016] The following will detail the specific implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the specific implementation described here is only for explaining and understanding the embodiments of the present invention, and is not used to limit the embodiments of the present invention.
[0017] Refer to Figure 1 shown, which is the implementation flowchart of a method for generating the security operation and maintenance capability of an airport provided by an embodiment of the present invention, including the following execution steps: Step 100: Construct an index system for the security operation and maintenance capability of the island airport.
[0018] Specifically, when performing step 100, the following steps can be specifically executed: Combining the environmental characteristics of island airports, construct an index system for the safety operation and maintenance of island airports from multiple dimensions and multiple specialties. Among them, the index system includes multiple first-level indicators, each first-level indicator corresponds to multiple second-level indicators, and each second-level indicator corresponds to multiple third-level indicators.
[0019] Exemplarily, based on the system engineering concept, combining the characteristics of harsh natural environment and prominent strategic location of far-sea island airports, an index system for the safety operation and maintenance of far-sea island airports is constructed from four dimensions of "person, machine, environment, and management" and "six specialties". The index system includes 6 first-level indicators (including: personnel and safety management guarantee ability, airport pavement guarantee ability, aircraft power supply and navigation lighting guarantee ability, aircraft fire fighting and rescue guarantee ability, aircraft arresting guarantee ability, bird strike prevention guarantee ability), 16 second-level indicators (physical and mental state, knowledge, skills, safety management ability, airport artificial pavement maintenance ability, airport soil area maintenance ability, airport ancillary facilities maintenance ability, wartime airport pavement bomb disposal and emergency repair ability, aircraft power supply facilities maintenance ability, airport navigation lighting system maintenance ability, aircraft fire fighting guarantee ability, aircraft rescue guarantee ability, aircraft arresting facilities management and maintenance ability, aircraft net collision emergency handling ability, bird strike prevention ability, and bird repelling guarantee ability), and 37 third-level indicators (physical fitness, mental outlook, general knowledge, professional knowledge, professional skills, education and training, working environment, facilities and equipment, safety system, artificial pavement monitoring ability, artificial pavement cleaning ability, artificial pavement repair ability, soil area monitoring ability, soil area maintenance ability, drainage facilities maintenance ability, boundary facilities maintenance ability, wartime airport pavement bomb disposal ability, wartime airport pavement emergency repair ability, aircraft power supply facilities inspection ability, aircraft power supply facilities repair ability, airport navigation lighting system monitoring ability, airport navigation lighting system repair ability, airport emergency navigation lighting fixture layout ability, aircraft fire fighting equipment management and maintenance ability, airport fire fighting facilities management and maintenance ability, airport fire fighting equipment management and maintenance ability, aircraft fire fighting emergency handling ability, aircraft rescue equipment management and maintenance ability, aircraft rescue emergency handling ability, aircraft arresting net maintenance ability, aircraft arresting apron maintenance ability, aircraft net collision on-site handling ability, aircraft net collision recovery ability, bird strike prevention material and equipment management ability, aircraft field area environmental governance ability, airport bird situation investigation and research ability, and airport bird repelling guarantee operation ability). The index system is shown in Figure 2 shown.
[0020] Step 101: Based on the safety operation and maintenance task list of the island airport and the safety operation and maintenance ability index system of the island airport, construct a task-oriented safety operation and maintenance ability index mapping model.
[0021] Specifically, when performing step 101, the following steps can be specifically executed: S1: Based on the airport security operation and maintenance task list, denote the set of island airport security operation and maintenance tasks as , where is the th task.
[0022] S2: Assume that the th task is decomposed into activities, and denote the set of activities as , , where is the rd activity in the th task .
[0023] S3: Assume that the set of security operation and maintenance requirements corresponding to the th task and the th activity is denoted as , which is decomposed into activities, denoted as , where is the th activity in the th requirement.
[0024] S4: Determine the set of ability indicators corresponding to the task according to the guarantee requirements, and denote as the mapping model from the th task to the ability indicators. Among them, the set of ability indicators is a subset of the island airport security operation and maintenance ability indicator system.
[0025] In some embodiments, the task-oriented airport security operation and maintenance ability indicator tailoring process is as shown in Figure 3 , including airport security operation and maintenance task R - operation and maintenance guarantee activity A - security operation and maintenance guarantee requirement S - security operation and maintenance ability indicator set X.
[0026] Exemplarily, denote the island airport security operation and maintenance ability indicator system as , is the th type of indicator set, is the th type of indicator in the th type of indicator set, is the th type of indicator in the th type of indicator set and is the th indicator.
[0027]
[0028] Step 102: Taking the success rate of the safety operation and maintenance tasks of the island airport as the goal, based on the BP neural network with adaptive learning, determine the index weights of the safety operation and maintenance ability indicators.
[0029] In some embodiments, referring to Figure 4 shown, it is a schematic diagram of the BP neural network structure based on the adaptive learning rate, and the construction process of its BP neural network with adaptive learning includes the following steps: S1: Respectively set the number of the input layer, the hidden layer, and the output layer, as well as the number of nodes corresponding to the input layer, the hidden layer, and the output layer. Among them, the number of nodes corresponding to the input layer is the same as the number of island airport safety ability indicators; It should be noted that the number of hidden layer nodes satisfies the following formula: ; In the formula, is a constant, m represents the number of hidden layer nodes, is the number of input layer nodes, is the number of output layer nodes.
[0030] Preferably, the number of hidden layers and the number of output layer nodes adopted in this embodiment are 1.
[0031] S2: Configure the index weights. Denote as the index weight of the th index, as the weight of the th index to the th neuron in the hidden layer, as the weight of the th neuron in the hidden layer to the output result; S3: Adopt the sigmoid function as the activation function , the logsig(n) function as the transfer function , and configure the neuron threshold and the threshold of the output node , where the threshold of the output node is determined by the task success degree ; Among them, the BP neural network with adaptive learning includes an input layer, a hidden layer, and an output layer.
[0032] Specifically, calculate the task success degree according to the following formula: ; In the formula, D represents the task success degree, is the task reliability, is the recovery degree when the system is in an unreliable state.
[0033] Specifically, when performing step 102, the following steps can be specifically executed: S1020: Based on the BP neural network of adaptive learning, with the task success rate as the output threshold constraint condition, train the weights of neurons in each layer.
[0034] In some embodiments, the process for determining the weights of security operation and maintenance ability indicators based on a neural network is referred to Figure 5 As shown, with the task success rate as the goal, set the number of neurons, the number of network layers, the activation function, and the transfer function based on the neural network model, perform model initialization, and determine the indicator weights through the output results after model training.
[0035] S1021: If the output meets the task success rate, determine the weights of neurons in each layer as the indicator weights of the security operation and maintenance ability; if the output does not meet the task success rate, update the weights of neurons in each layer through the adaptive learning rate.
[0036] Specifically, the adaptive learning rate is calculated according to the following formula: ; In the formula, E(k) is the sum of squared errors at the k th step, E(k +1 ) is the sum of squared errors at the k +1th step, η(k) is the learning factor at the k th step.
[0037] Step 103: Based on the indicator weights of the security operation and maintenance ability, determine the importance degree affecting security operation and maintenance, so as to generate a security operation and maintenance ability plan.
[0038] The generation system of the task-oriented island airport security operation and maintenance ability includes a processor and a memory. The processor contains a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set. By adjusting the kernel parameters, with the island security operation and maintenance task as the traction, a mapping model of guarantee tasks, security operation and maintenance requirements, and security operation and maintenance ability indicator sets is designed. Finally, with the task success rate as the goal, based on the improved BP neural network algorithm, a method for determining indicator weights oriented to tasks is designed to provide a scientific and effective method and technical solution for the generation of the airport's security operation and maintenance ability.
[0039] The memory may include non-permanent memory in a computer-readable medium, forms such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one storage chip.
[0040] An embodiment of the present invention provides a storage medium, on which a program is stored, and when the program is executed by a processor, the airport security operation and maintenance capability generation method is implemented.
[0041] An embodiment of the present invention provides a processor, which is used to run a program, and when the program runs, the airport security operation and maintenance capability generation method is executed.
[0042] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: constructing an index system for the security operation and maintenance capability of island airports; constructing a task-oriented security operation and maintenance capability index mapping model based on the security operation and maintenance task list of island airports and the index system for the security operation and maintenance capability of island airports; taking the success rate of security operation and maintenance tasks of island airports as the goal, and determining the index weights of security operation and maintenance capability indexes based on the BP neural network with adaptive learning; determining the importance degree affecting security operation and maintenance based on the index weights of the security operation and maintenance capability indexes, so as to generate a security operation and maintenance capability solution. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.
[0043] The present application also provides a computer program product, which is suitable for executing a program initialized with the following method steps when executed on a data processing device: constructing an index system for the security operation and maintenance capability of island airports; constructing a task-oriented security operation and maintenance capability index mapping model based on the security operation and maintenance task list of island airports and the index system for the security operation and maintenance capability of island airports; taking the success rate of security operation and maintenance tasks of island airports as the goal, and determining the index weights of security operation and maintenance capability indexes based on the BP neural network with adaptive learning; determining the importance degree affecting security operation and maintenance based on the index weights of the security operation and maintenance capability indexes, so as to generate a security operation and maintenance capability solution.
[0044] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0045] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general purpose computers, special purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in the process Figure 1 in one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.
[0046] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in the process Figure 1 in one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.
[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 in one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.
[0048] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.
[0049] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.
[0050] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0051] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0052] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A method for generating airport safety operation and maintenance capabilities, characterized in that Including: Constructing an indicator system for the safe operation and maintenance capabilities of island airports; Based on the task list of the safe operation and maintenance of island airports and the indicator system for the safe operation and maintenance capabilities of island airports, constructing a task-oriented mapping model for the safe operation and maintenance capabilities indicators; Taking the success rate of the safe operation and maintenance tasks of island airports as the goal, and based on the BP neural network with adaptive learning, determining the indicator weights of the safe operation and maintenance capabilities indicators; Based on the indicator weights of the safe operation and maintenance capabilities indicators, determining the importance degree affecting the safe operation and maintenance, so as to generate a solution for the safe operation and maintenance capabilities.
2. The method for generating airport security operation and maintenance capabilities according to claim 1, wherein Constructing an indicator system for the safe operation and maintenance capabilities of island airports, including: Combining the environmental characteristics of island airports, constructing an indicator system for the safe operation and maintenance of island airports from multiple dimensions and multiple specialties, wherein the indicator system includes multiple first-level indicators, each first-level indicator corresponds to multiple second-level indicators, and each second-level indicator corresponds to multiple third-level indicators.
3. The method for generating airport security operation and maintenance capabilities according to claim 1, characterized in that Based on the task list of the safe operation and maintenance of island airports and the indicator system for the safe operation and maintenance capabilities of island airports, constructing a task-oriented mapping model for the safe operation and maintenance capabilities indicators, including: Based on the airport safety operation and maintenance task list, and denote the set of island airport safety operation and maintenance tasks as , where is the th task; Assume that the th task is decomposed into activities, and the set of activities is denoted as , , where is the th activity in the th task ; Assume that the safety operation and maintenance requirement set corresponding to the th task and the th activity is denoted as , which is decomposed into activities, denoted as . Among them, is the th requirement in the th activity . Determine the corresponding tasks according to the guarantee requirements of the set of capability indicators , denoted as the th mapping model from tasks to capability indicators, where the set of capability indicators is a subset of the island airport safety operation and maintenance capability indicator system.
4. The method for generating airport security operation and maintenance capabilities according to claim 1, wherein The construction process of the BP neural network with adaptive learning includes: Respectively setting the number of the input layer, the hidden layer and the output layer, as well as the number of nodes corresponding to the input layer, the hidden layer and the output layer, wherein the number of nodes corresponding to the input layer is the same as the number of the safe operation and maintenance capabilities indicators of island airports; Configure the index weight, denoted as the index weight of the th index, the weight of the th index for the th neuron in the hidden layer, the weight of the th neuron in the hidden layer for the output result; Using the sigmoid function as the activation function and the logsig(n) function as the transfer function, and configuring the neuron threshold and the threshold of the output node, wherein the threshold of the output node is determined by the task success degree; Wherein, the BP neural network with adaptive learning includes an input layer, a hidden layer and an output layer.
5. The method for generating airport security operation and maintenance capabilities according to claim 4, wherein The number of nodes in the hidden layer satisfies the following formula: ； wherein, is a constant, m represents the number of hidden layer nodes, is the number of input layer nodes, is the number of output layer nodes.
6. The method for generating airport security operation and maintenance capabilities according to claim 4, wherein Calculating the task success degree according to the following formula: ； Where D represents the task success degree, is the task reliability, is the recovery degree when the system is in an unreliable state.
7. The method for generating airport security operation and maintenance capabilities according to claim 4, characterized in that Taking the success rate of the safe operation and maintenance tasks of island airports as the goal, and based on the BP neural network with adaptive learning, determining the indicator weights of the safe operation and maintenance capabilities indicators, including: Based on the BP neural network with adaptive learning, using the task success degree as the output threshold constraint condition to train the weights of each layer of neurons; If the output meets the task success degree, determining the weights of each layer of neurons as the indicator weights of the safe operation and maintenance capabilities indicators; if the output does not meet the task success degree, updating the weights of each layer of neurons through the adaptive learning rate.
8. The method for generating airport security operation and maintenance capabilities according to claim 7, characterized in that, The adaptive learning rate is calculated according to the following formula: ； Wherein, E(k) is the sum of squared errors of the k th step, E(k +1 ) is the sum of squared errors of the k ( k +1)th step, η(k) is the learning factor of the k th step.