A multi-module resource optimization method, system and medium for avionics system
Optimizing resource input of avionics system through BP neural network and particle swarm algorithms, solving the resource allocation and energy consumption problems of avionics system, reducing energy consumption and improving working capabilities, and adapting to different tasks and data structures.
Patent Information
- Application Number
- CN202411040412.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-31
AI Technical Summary
The existing avionics system has shortcomings in resource allocation and energy consumption optimization, and cannot effectively utilize the heat dissipation and data storage of multiple modules, resulting in high energy consumption and unreasonable resource input.
Using a multi-module capability prediction model based on BP neural network and a particle swarm algorithm coupled with adaptive learning operators, we optimize the resource input of the avionics system, establish an energy consumption function to reduce energy consumption, and adjust the optimization process through preset thresholds.
It optimizes the energy consumption of each module of the avionics system, reduces energy consumption, and improves the efficiency and working ability of resource input, adapts to different tasks and data structures, and has broad applicability and balances between performance and cost.
Smart Images

Figure CN118569106B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of avionics systems, and in particular to a multi-module resource optimization method, system and medium applied to avionics systems. Background Art
[0002] The development of avionics systems has gone through several stages, including discrete structure, joint structure, and integrated modular (IMA) structure. Nowadays, distributed integrated modular (DIMA) is a new development trend. In the discrete structure, different functional tasks are handled by different avionics subsystems. Each avionics subsystem has independent and complete hardware. The pilot understands the operating status of the aircraft by observing the status of different subsystems. This method is complex to control and has low efficiency. The joint structure uses a large number of field replaceable units (LRUs). LRUs have independent hardware structures. Different LRUs have different internal modules and cannot be replaced with each other. A series of independent LRUs that can only handle specific functions are connected through the 1553B bus to form an avionics subsystem. The 1553B data bus has bidirectional output characteristics, high real-time and reliability, and is widely used in contemporary transport aircraft and a considerable number of civil airliners, military aircraft, and aerospace systems. In the working process of the avionics system, multiple modules need to work together. The heat dissipation and data storage capacity of multiple modules are different. When resources are input, if they cannot be reasonably allocated, each module cannot be fully utilized and the energy consumption is higher.
[0003] In the prior art, a Chinese patent (application number: 202310191273.8, publication number: CN116610437A) discloses a resource allocation method for an integrated modular avionics system, which specifically includes the following steps: Step 1, capturing and confirming potential resident application requirements; Step 2, capturing and confirming platform resource module attributes; Step 3, capturing and confirming platform architecture; Step 4, preliminary resource allocation; Step 5, checking allocation results; Step 6, targeted optimization based on the inspection results; Step 7, confirming and verifying the allocation plan. This solution does not optimize the resources of each module of the avionics system and does not consider the energy consumption of the overall avionics system.
[0004] In the prior art, a Chinese patent (application number: 202210421718.2, publication number: CN114741133A) provides a model-based integrated modular avionics system resource configuration and evaluation method, which includes the following steps: Step 1: According to the resource characteristics of the integrated modular avionics system, a resource capability model and a resource demand capture model are constructed; Step 2: The resource demand of the resident function is captured through the resource demand capture model to form a resource demand model; Step 3: The resource demand model is checked for integrity in combination with the resource capability model. If the data check passes, step 4 is entered. If the data check fails, the resident function supplier is coordinated to locate the problem and optimize the integrated modular avionics system. After the architecture and resource requirements of the integrated modular avionics system are determined, re-enter step 2; step 4: for the resource demand model, based on the resource constraint relationship of the integrated modular avionics system, allocate and optimize the resources of the integrated modular avionics system for the resident function; step 5: according to the resource demand model and the requirements of the integrated modular avionics system, evaluate the results after resource allocation to determine whether it passes the resource verification and evaluation rules. If yes, enter step 6. If not, coordinate with the resident function supplier to optimize the architecture and resource requirements of the integrated modular avionics system and re-enter step 2; step 6: for the resource allocation results that pass the resource verification and evaluation, generate the configuration file and resource evaluation report of the integrated modular avionics system. This solution does not further optimize the resources of each module of the avionics system in view of the energy loss problem of the avionics system. Summary of the invention
[0005] In view of the above deficiencies in the prior art, the present invention provides a multi-module resource optimization method, system and medium applied to an avionics system, which can not only reasonably optimize the resource input according to the differences in heat dissipation and data storage capacity of multiple modules of the avionics system, but also optimize the energy consumption of each module of the avionics system, thereby reducing the energy consumption of the avionics system and further optimizing the resource input to improve the working capacity of the avionics system.
[0006] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:
[0007] A multi-module resource optimization method applied to an avionics system, the method comprising:
[0008] U1. Based on the historical working data information of the avionics system during the flight of the aircraft, obtain the historical data information of the heat dissipation of multiple modules of the avionics system and the historical data information of the data storage capacity, and obtain the data information of the resource input of multiple modules of the avionics system in real time;
[0009] U2. Based on the historical data information of the heat dissipation and data storage capacity of the multiple modules of the avionics system, a multi-module capacity prediction model of the avionics system based on the BP neural network is constructed to predict the heat dissipation and data storage capacity of the multiple modules of the avionics system, and obtain the heat dissipation data information and data storage capacity data information of the multiple modules of the avionics system;
[0010] U3. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, a particle swarm algorithm coupled with an adaptive learning operator is used to optimize the resource input of each module of the avionics system to obtain the optimized resource input data information of each module of the avionics system;
[0011] U4. Based on the resource input data information of each module of the optimized avionics system, an energy consumption function P of the avionics system is established, the energy consumption of the avionics system is estimated, and the energy consumption data information of the avionics system is obtained.
[0012] Furthermore, the method further comprises:
[0013] U5. Based on the energy consumption data information of the avionics system, a preset threshold is set. If the energy consumption of the avionics system exceeds the preset threshold, the process returns to repeat steps U2-U3. If the energy consumption of the avionics system does not exceed the preset threshold, the resources of each module of the optimized avionics system are output.
[0014] Furthermore, the energy consumption function P of the avionics system is:
[0015] ,
[0016] Among them, x i is the resource input data information of the i-th module of the optimized avionics system, α1 and α2 are the multi-module energy consumption determining factors of the avionics system, x0 is the multi-module resource mean input of the avionics system, and n is the number of multi-modules of the avionics system.
[0017] Furthermore, the multi-module resource mean input x0 of the avionics system is
[0018] ,
[0019] Among them, x i is the resource input data information of the i-th module of the optimized avionics system, x i+1 is the resource input data information of the i+1th module of the optimized avionics system, and n is the number of multiple modules of the avionics system;
[0020] The constraints of the multi-module energy consumption determining factors α1 and α2 of the avionics system are:
[0021] .
[0022] Furthermore, in step U2, the construction of the avionics system multi-module capacity prediction model based on the BP neural network to predict the heat dissipation and data storage capacity of the avionics system multi-module includes:
[0023] U21. Based on the historical data information of the heat dissipation of the multiple modules of the avionics system and the historical data information of the data storage capacity, a weight function G of the multiple modules of the avionics system based on the BP neural network is constructed.
[0024] ,
[0025] Among them, y1 is the historical data information of the heat dissipation of the multiple modules of the avionics system, y2 is the historical data information of the data storage capacity of the multiple modules of the avionics system, β1 and β2 are the weight coefficients of the multiple modules of the avionics system, and the weights of the multiple modules of the avionics system are calculated to obtain the multi-module weight matrix data information of the avionics system;
[0026] U22. Based on the multi-module weight matrix data information of the avionics system, a multi-module activation function H of the avionics system based on the BP neural network is established.
[0027] ,
[0028] Among them, g is the multi-module weight matrix data information of the avionics system, λ1, λ2 and λ3 are the activation factors of the multi-modules of the avionics system, and the activation parameters of the multi-modules of the avionics system are characterized to obtain the activation matrix data information of the multi-modules of the avionics system;
[0029] U23. Based on the activation matrix data information of the multiple modules of the avionics system, a heat dissipation prediction function W1 and a data storage capacity prediction function W2 of the multiple modules of the avionics system are established.
[0030] ,
[0031] ,
[0032] Among them, h is the activation matrix data information of the multiple modules of the avionics system, µ1, µ2 and µ3 are the heat dissipation aggregation factors of the multiple modules of the avionics system, ω1, ω2 and ω3 are the data storage capacity determining factors of the multiple modules of the avionics system. The heat dissipation and data storage capacity of the multiple modules of the avionics system are predicted to obtain the heat dissipation data information and data storage capacity data information of the multiple modules of the avionics system.
[0033] Furthermore, the relationship function f1 between the heat dissipation aggregation factors µ1, µ2 and µ3 of the multiple modules of the avionics system is:
[0034] ,
[0035] The relationship function f2 between the data storage capacity determining factors ω1, ω2 and ω3 of the multi-module of the avionics system is:
[0036] ,
[0037] Among them, the value range of the relationship function f1 is (0,1), and the value range of the relationship function f2 is (0,1).
[0038] Furthermore, in step U3, the optimization of the resource input amount of each module of the avionics system by using a particle swarm algorithm coupled with an adaptive learning operator includes:
[0039] U31. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, construct a particle population of the multiple modules of the avionics system, initialize it, determine the population parameters, and obtain the particle population data information of the multiple modules of the avionics system after the initialization;
[0040] U32. Based on the particle population data information of the multiple modules of the avionics system after the initialization, establish the fitness function Q of the population individuals,
[0041] ,
[0042] Among them, z is the data information of the particle population of the multi-module avionics system after initialization, θ1, θ2 and θ3 are the fitness factors of the particle population of the multi-module avionics system, δ is the adaptive learning operator of the particle population of the multi-module avionics system, and the fitness value of the individual particle population is calculated to obtain the fitness value data information of the individual particle population of the multi-module avionics system;
[0043] U33. Based on the fitness value data information of the individual particle population of the multi-module avionics system, establish the resource input optimization function V of the multi-module avionics system,
[0044] ,
[0045] Among them, q j is the fitness value data information of the individual multi-module particle population of the avionics system, J is the sample capacity of the multi-module particle population of the avionics system, ρ j The optimization factor of the resource input amount of multiple modules of the avionics system is used to optimize the resource input amount of each module of the avionics system to obtain the resource input amount data information of each module of the optimized avionics system.
[0046] Furthermore, the adaptive learning operator δ of the particle population of the multi-module avionics system is:
[0047] ,
[0048] Among them, z is the particle population data information of the multi-module of the avionics system after initialization, and γ1 and γ2 are the gradient change determining factors of the multi-module of the avionics system.
[0049] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a multi-module resource optimization system applied to an avionics system, including a computer device, which is programmed or configured to execute any one of the steps of the multi-module resource optimization method applied to an avionics system.
[0050] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the multi-module resource optimization methods applied to an avionics system.
[0051] The present invention has the following positive effects:
[0052] 1. The present invention predicts the heat dissipation and data storage capacity of multiple modules of the avionics system by constructing a multi-module capacity prediction model of the avionics system based on the BP neural network, and optimizes the resource input of each module of the avionics system by combining the particle swarm algorithm coupled with an adaptive learning operator. It can not only reasonably optimize the resource input according to the different heat dissipation and data storage capacity of multiple modules of the avionics system, but also has flexibility and can easily adapt to different types of tasks and data structures without large-scale modifications. For new tasks, the model can achieve significant performance improvement through fine-tuning or a small amount of adjustment, showing its wide applicability in different fields, and can easily integrate new features, levels or technologies, so as to better adapt to future technology and application development.
[0053] 2. The present invention optimizes the energy consumption of the avionics system by establishing an energy consumption function P of the avionics system. It can not only optimize the energy consumption of each module of the avionics system and reduce the energy consumption of the avionics system, but also further optimize the resource input, improve the working capacity of the avionics system, and achieve a balance between performance and cost. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 It is a schematic diagram of the method flow of the present invention;
[0055] Figure 2 A schematic diagram of the process of constructing a multi-module capability prediction model of an avionics system based on a BP neural network according to the present invention;
[0056] Figure 3 The figure is a flow chart of the particle swarm algorithm coupled with an adaptive learning operator according to the present invention. DETAILED DESCRIPTION
[0057] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0058] Example 1: Figure 1 As shown, a multi-module resource optimization method applied to an avionics system, the method comprising:
[0059] U1. Based on the historical working data information of the avionics system during the flight of the aircraft, obtain the historical data information of the heat dissipation of multiple modules of the avionics system and the historical data information of the data storage capacity, and obtain the data information of the resource input of multiple modules of the avionics system in real time;
[0060] U2. Based on the historical data information of the heat dissipation and data storage capacity of the multiple modules of the avionics system, a multi-module capacity prediction model of the avionics system based on the BP neural network is constructed to predict the heat dissipation and data storage capacity of the multiple modules of the avionics system, and obtain the heat dissipation data information and data storage capacity data information of the multiple modules of the avionics system;
[0061] U3. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, a particle swarm algorithm coupled with an adaptive learning operator is used to optimize the resource input of each module of the avionics system to obtain the optimized resource input data information of each module of the avionics system;
[0062] U4. Based on the resource input data information of each module of the optimized avionics system, an energy consumption function P of the avionics system is established, the energy consumption of the avionics system is estimated, and the energy consumption data information of the avionics system is obtained.
[0063] In this embodiment, the method further includes:
[0064] U5. Based on the energy consumption data information of the avionics system, a preset threshold is set. If the energy consumption of the avionics system exceeds the preset threshold, the process returns to repeat steps U2-U3. If the energy consumption of the avionics system does not exceed the preset threshold, the resources of each module of the optimized avionics system are output.
[0065] In this embodiment, the energy consumption function P of the avionics system is:
[0066] ,
[0067] Among them, x i is the resource input data information of the i-th module of the optimized avionics system, α1 and α2 are the multi-module energy consumption determining factors of the avionics system, x0 is the multi-module resource mean input of the avionics system, and n is the number of multi-modules of the avionics system.
[0068] In this embodiment, the multi-module resource mean input x0 of the avionics system is
[0069] ,
[0070] Among them, x i is the resource input data information of the i-th module of the optimized avionics system, x i+1 is the resource input data information of the i+1th module of the optimized avionics system, and n is the number of multiple modules of the avionics system;
[0071] The constraints of the multi-module energy consumption determining factors α1 and α2 of the avionics system are:
[0072] .
[0073] In this embodiment, if Figure 2 As shown, in step U2, the construction of the avionics system multi-module capacity prediction model based on the BP neural network to predict the heat dissipation and data storage capacity of the avionics system multi-module includes:
[0074] U21. Based on the historical data information of the heat dissipation of the multiple modules of the avionics system and the historical data information of the data storage capacity, a weight function G of the multiple modules of the avionics system based on the BP neural network is constructed.
[0075] ,
[0076] Among them, y1 is the historical data information of the heat dissipation of the multiple modules of the avionics system, y2 is the historical data information of the data storage capacity of the multiple modules of the avionics system, β1 and β2 are the weight coefficients of the multiple modules of the avionics system, and the weights of the multiple modules of the avionics system are calculated to obtain the multi-module weight matrix data information of the avionics system;
[0077] U22. Based on the multi-module weight matrix data information of the avionics system, a multi-module activation function H of the avionics system based on the BP neural network is established.
[0078] ,
[0079] Among them, g is the multi-module weight matrix data information of the avionics system, λ1, λ2 and λ3 are the activation factors of the multi-modules of the avionics system, and the activation parameters of the multi-modules of the avionics system are characterized to obtain the activation matrix data information of the multi-modules of the avionics system;
[0080] U23. Based on the activation matrix data information of the multiple modules of the avionics system, a heat dissipation prediction function W1 and a data storage capacity prediction function W2 of the multiple modules of the avionics system are established.
[0081] ,
[0082] ,
[0083] Among them, h is the activation matrix data information of the multiple modules of the avionics system, µ1, µ2 and µ3 are the heat dissipation aggregation factors of the multiple modules of the avionics system, ω1, ω2 and ω3 are the data storage capacity determining factors of the multiple modules of the avionics system. The heat dissipation and data storage capacity of the multiple modules of the avionics system are predicted to obtain the heat dissipation data information and data storage capacity data information of the multiple modules of the avionics system.
[0084] In this embodiment, the relationship function f1 between the heat dissipation aggregation factors µ1, µ2 and µ3 of the multiple modules of the avionics system is:
[0085] ,
[0086] The relationship function f2 between the data storage capacity determining factors ω1, ω2 and ω3 of the multi-module of the avionics system is:
[0087] ,
[0088] Among them, the value range of the relationship function f1 is (0,1), and the value range of the relationship function f2 is (0,1).
[0089] Embodiment 2: Based on the multi-module resource optimization method applied to an avionics system in Embodiment 1, the present invention is further illustrated and described below.
[0090] like Figure 1 As shown, a multi-module resource optimization method applied to an avionics system, the method comprising:
[0091] U1. Based on the historical working data information of the avionics system during the flight of the aircraft, obtain the historical data information of the heat dissipation of multiple modules of the avionics system and the historical data information of the data storage capacity, and obtain the data information of the resource input of multiple modules of the avionics system in real time;
[0092] U2. Based on the historical data information of the heat dissipation and data storage capacity of the multiple modules of the avionics system, a multi-module capacity prediction model of the avionics system based on the BP neural network is constructed to predict the heat dissipation and data storage capacity of the multiple modules of the avionics system, and obtain the heat dissipation data information and data storage capacity data information of the multiple modules of the avionics system;
[0093] U3. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, a particle swarm algorithm coupled with an adaptive learning operator is used to optimize the resource input of each module of the avionics system to obtain the optimized resource input data information of each module of the avionics system;
[0094] U4. Based on the resource input data information of each module of the optimized avionics system, an energy consumption function P of the avionics system is established, the energy consumption of the avionics system is estimated, and the energy consumption data information of the avionics system is obtained.
[0095] In this embodiment, if Figure 3 As shown, in step U3, the use of a particle swarm algorithm coupled with an adaptive learning operator to optimize the resource input amount of each module of the avionics system includes:
[0096] U31. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, construct a particle population of the multiple modules of the avionics system, initialize it, determine the population parameters, and obtain the particle population data information of the multiple modules of the avionics system after the initialization;
[0097] U32. Based on the particle population data information of the multiple modules of the avionics system after the initialization, establish the fitness function Q of the population individuals,
[0098] ,
[0099] Among them, z is the data information of the particle population of the multi-module avionics system after initialization, θ1, θ2 and θ3 are the fitness factors of the particle population of the multi-module avionics system, δ is the adaptive learning operator of the particle population of the multi-module avionics system, and the fitness value of the individual particle population is calculated to obtain the fitness value data information of the individual particle population of the multi-module avionics system;
[0100] U33. Based on the fitness value data information of the individual particle population of the multi-module avionics system, establish the resource input optimization function V of the multi-module avionics system,
[0101] ,
[0102] Among them, qj is the fitness value data information of the individual multi-module particle population of the avionics system, J is the sample capacity of the multi-module particle population of the avionics system, ρ j The optimization factor of the resource input amount of multiple modules of the avionics system is used to optimize the resource input amount of each module of the avionics system to obtain the resource input amount data information of each module of the optimized avionics system.
[0103] In this embodiment, the adaptive learning operator δ of the particle population of the multi-module avionics system is,
[0104] ,
[0105] Among them, z is the particle population data information of the multi-module of the avionics system after initialization, and γ1 and γ2 are the gradient change determining factors of the multi-module of the avionics system.
[0106] In this embodiment, the present invention provides a multi-module resource optimization system applied to an avionics system, including a computer device, which is programmed or configured to execute any one of the steps of the multi-module resource optimization method applied to an avionics system.
[0107] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the multi-module resource optimization methods for an avionics system.
[0108] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0109] In summary, the present invention can not only reasonably optimize resource input according to the differences in heat dissipation and data storage capacity of multiple modules of the avionics system, but also optimize the energy consumption of each module of the avionics system, thereby reducing the energy consumption of the avionics system and further optimizing the resource input to improve the working capacity of the avionics system.
[0110] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A multi-module resource optimization method applied to an avionics system, characterized in that: The method comprises: U1. Based on the historical working data information of the avionics system during the flight of the aircraft, obtain the historical data information of the heat dissipation of multiple modules of the avionics system and the historical data information of the data storage capacity, and obtain the data information of the resource input of multiple modules of the avionics system in real time; U2. Based on the historical data information of the heat dissipation and data storage capacity of the multiple modules of the avionics system, a multi-module capacity prediction model of the avionics system based on the BP neural network is constructed to predict the heat dissipation and data storage capacity of the multiple modules of the avionics system, and obtain the heat dissipation data information and data storage capacity data information of the multiple modules of the avionics system; U3. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, a particle swarm algorithm coupled with an adaptive learning operator is used to optimize the resource input of each module of the avionics system to obtain the optimized resource input data information of each module of the avionics system; U4. Based on the resource input data information of each module of the optimized avionics system, an energy consumption function P of the avionics system is established, the energy consumption of the avionics system is estimated, and the energy consumption data information of the avionics system is obtained; The energy consumption function P of the avionics system is: , Among them, x i is the resource input data information of the i-th module of the optimized avionics system, α1 and α2 are the multi-module energy consumption determining factors of the avionics system, x0 is the multi-module resource mean input of the avionics system, and n is the number of multi-modules of the avionics system; In step U2, the construction of the avionics system multi-module capacity prediction model based on the BP neural network to predict the heat dissipation and data storage capacity of the avionics system multi-module includes: U21. Based on the historical data information of the heat dissipation of the multiple modules of the avionics system and the historical data information of the data storage capacity, a weight function G of the multiple modules of the avionics system based on the BP neural network is constructed. , Among them, y1 is the historical data information of the heat dissipation of the multiple modules of the avionics system, y2 is the historical data information of the data storage capacity of the multiple modules of the avionics system, β1 and β2 are the weight coefficients of the multiple modules of the avionics system, and the weights of the multiple modules of the avionics system are calculated to obtain the multi-module weight matrix data information of the avionics system; U22. Based on the multi-module weight matrix data information of the avionics system, a multi-module activation function H of the avionics system based on the BP neural network is established. , Among them, g is the multi-module weight matrix data information of the avionics system, λ1, λ2 and λ3 are the activation factors of the multi-modules of the avionics system, and the activation parameters of the multi-modules of the avionics system are characterized to obtain the activation matrix data information of the multi-modules of the avionics system; U23. Based on the activation matrix data information of the multiple modules of the avionics system, a heat dissipation prediction function W1 and a data storage capacity prediction function W2 of the multiple modules of the avionics system are established. , , Among them, h is the activation matrix data information of the multiple modules of the avionics system, µ1, µ2 and µ3 are the heat dissipation aggregation factors of the multiple modules of the avionics system, ω1, ω2 and ω3 are the data storage capacity determining factors of the multiple modules of the avionics system, and the heat dissipation and data storage capacity of the multiple modules of the avionics system are predicted to obtain the heat dissipation data information and data storage data information of the multiple modules of the avionics system; In step U3, the optimization of the resource input amount of each module of the avionics system by using the particle swarm algorithm coupled with an adaptive learning operator includes: U31. Based on the heat dissipation data information and data storage data information of the multiple modules of the avionics system and the data information of the resource input of the multiple modules of the avionics system, construct a particle population of the multiple modules of the avionics system, initialize it, determine the population parameters, and obtain the particle population data information of the multiple modules of the avionics system after the initialization; U32. Based on the particle population data information of the multiple modules of the avionics system after the initialization, establish the fitness function Q of the population individuals, , Among them, z is the data information of the particle population of the multi-module avionics system after initialization, θ1, θ2 and θ3 are the fitness factors of the particle population of the multi-module avionics system, δ is the adaptive learning operator of the particle population of the multi-module avionics system, and the fitness value of the individual particle population is calculated to obtain the fitness value data information of the individual particle population of the multi-module avionics system; U33. Based on the fitness value data information of the individual particle population of the multi-module avionics system, establish the resource input optimization function V of the multi-module avionics system, , Among them, q j is the fitness value data information of the individual multi-module particle population of the avionics system, J is the sample capacity of the multi-module particle population of the avionics system, ρ j The optimization factor of the resource input amount of multiple modules of the avionics system is used to optimize the resource input amount of each module of the avionics system to obtain the resource input amount data information of each module of the optimized avionics system; The multi-module resource mean input x0 of the avionics system, , Among them, x i is the resource input data information of the i-th module of the optimized avionics system, x i+1 is the resource input data information of the i+1th module of the optimized avionics system, and n is the number of multiple modules of the avionics system; The constraints of the multi-module energy consumption determining factors α1 and α2 of the avionics system are: ; The adaptive learning operator δ of the particle population of the multi-module avionics system is: , Among them, z is the particle population data information of the multi-module of the avionics system after initialization, and γ1 and γ2 are the gradient change determining factors of the multi-module of the avionics system.
2. The multi-module resource optimization method applied to an avionics system according to claim 1, characterized in that: The method further comprises: U5. Based on the energy consumption data information of the avionics system, a preset threshold is set. If the energy consumption of the avionics system exceeds the preset threshold, the process returns to repeat steps U2-U3. If the energy consumption of the avionics system does not exceed the preset threshold, the resource input data information of each module of the optimized avionics system is output.
3. The multi-module resource optimization method applied to an avionics system according to claim 1, characterized in that: The relationship function f1 between the heat dissipation aggregation factors µ1, µ2 and µ3 of the multi-modules of the avionics system is: , The relationship function f2 between the data storage capacity determining factors ω1, ω2 and ω3 of the multi-module of the avionics system is: , Among them, the value range of the relationship function f1 is (0,1), and the value range of the relationship function f2 is (0,1).
4. A multi-module resource optimization system for an avionics system, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the multi-module resource optimization method applied to an avionics system as claimed in any one of claims 1 to 3.
5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program programmed or configured to execute the multi-module resource optimization method applied to an avionics system as claimed in any one of claims 1 to 3.
