Unmanned aerial vehicle airborne equipment arrangement optimization method based on genetic algorithm

Abstract

The invention belongs to the technical field of overall design of aircrafts, and particularly relates to an unmanned aerial vehicle airborne equipment arrangement optimization method based on a genetic algorithm. Comprising the following steps: step 1, establishing a multi-objective optimization mathematical model by taking the minimum weight of a power supply cable of equipment, the minimum weight of a cross signal cable between the equipment and the minimum gravity center positioning deviation as optimization objectives; 2, determining airborne equipment arrangement constraint conditions; and 3, solving the multi-objective optimization mathematical model by adopting a genetic algorithm in combination with airborne equipment arrangement constraint conditions to obtain an optimal arrangement scheme of the airborne equipment of the unmanned aerial vehicle. Equipment cable laying can be simplified, the gravity center of equipment can be accurately positioned, the arrangement coordination and iteration times are reduced, the development period is shortened, and the reliability and optimization efficiency of an arrangement scheme are effectively improved.

Description

Technical Field

[0001] The invention belongs to the technical field of overall aircraft design, and in particular relates to a method for optimizing the layout of unmanned aerial vehicle airborne equipment based on a genetic algorithm. Background Art

[0002] The layout of UAV airborne equipment needs to consider many aspects of design goals and engineering constraints, including space limitations inside the fuselage, structural load-bearing layout, simple cable laying, center of gravity positioning of airborne equipment, convenient disassembly and maintenance, and effective performance of equipment functions and performance. These constraints are not isolated, but influence each other and have an inherent connection, which is bound to bring difficulties to the layout of airborne equipment. At present, the layout of UAV airborne equipment mainly relies on personal layout experience, and is achieved through repeated coordination, comprehensive balance and multiple iterations of various disciplines. The design cycle is long and the efficiency is low. In addition, the layout schemes formed generally have problems such as heavy cable laying and deviation of the center of gravity of the equipment. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a method for optimizing the layout of UAV-mounted equipment based on a genetic algorithm, which can simplify the laying of equipment cables, accurately locate the center of gravity of the equipment, reduce the number of layout coordination and iterations, shorten the development cycle, and effectively improve the reliability and optimization efficiency of the layout plan.

[0004] The present invention is implemented by adopting the following technical scheme.

[0005] A method for optimizing the layout of UAV airborne equipment based on a genetic algorithm comprises the following steps:

[0006] Step 1: Establish a multi-objective optimization mathematical model with the minimum weight of the equipment power supply cable, the minimum weight of the cross signal cable between the equipment, and the minimum center of gravity positioning deviation as the optimization goals;

[0007] Step 2: Determine the constraints for the layout of airborne equipment;

[0008] Step 3: Combined with the constraints of airborne equipment layout, the genetic algorithm is used to solve the multi-objective optimization mathematical model to obtain the optimal layout plan of the UAV airborne equipment.

[0009] Furthermore, the objective function for minimizing the weight of the equipment power supply cable is specifically:

[0010]

[0011] In formula (1), The weight of the power cable for the equipment; i represents the equipment number, P i represents the ith device identifier, i = 1, 2, ... m, m is the total number of devices; ρ i Indicates device P iWeight per unit length of power supply cable; (x 0 ,h 0 ) represents the coordinates of the cable power supply point; (x i ,h i +h 0 +l i t) indicates device P i The center coordinates, h i For device P i The wiring height itself, For device P i Total height of layout layers:

[0012]

[0013] Wherein, L represents the height of the equipment compartment, and t represents the number of floors in the equipment compartment.

[0014] Furthermore, the objective function for minimizing the weight of cross-signal cables between devices is specifically:

[0015]

[0016] In formula (3), The weight of the signal cables between devices; α ij Indicates P i , P j Weight per unit length of signal cable between devices; X ij P i , P j The routing length of the signal cable between devices can be expressed as:

[0017]

[0018] Where D is the width of the equipment compartment, s ij Indicates device P i and P j The difference in the number of columns arranged, t1 and t2 are respectively i and P j The number of layers of equipment compartments arranged.

[0019] Furthermore, the objective function for minimizing the center of gravity positioning deviation is specifically:

[0020]

[0021] In formula (5), is the equipment center of gravity positioning deviation value, W i Indicates device P i The weight, x wc The ideal coordinate value of the device's center of gravity.

[0022] Furthermore, with the minimum weight of the equipment power supply cable, the minimum weight of the cross signal cable between the equipment, and the minimum center of gravity positioning deviation as the optimization goals, a multi-objective optimization mathematical model is established as follows:

[0023] Construct the objective function of equipment layout optimization:

[0024]

[0025] In formula (6), C R represents the overall optimization objective; δ 1 ,δ 2 ,δ 3 is the multi-objective weight.

[0026] Furthermore, the constraints for the layout of airborne equipment are determined to include:

[0027] Devices located in the same layer and column do not collide or overlap:

[0028]

[0029] In formula (7), b i , b j Respectively represent equipment P i , P j The length dimension, d (i,j) Indicates P i , P j Minimum safe distance between devices.

[0030] Furthermore, determining the constraints for the placement of airborne equipment also includes:

[0031] Equipment on any layer cannot collide with the cabin structure wall:

[0032]

[0033] In formula (8), ω represents the minimum distance between the equipment and the cabin structure wall, S t Indicates the starting coordinate value of the equipment cabin on the tth floor, B t Indicates the length of the equipment compartment on the tth floor.

[0034] Furthermore, in the process of solving the multi-objective optimization mathematical model using genetic algorithm,

[0035] The fitness function of the genetic algorithm is expressed as:

[0036]

[0037] F is the penalty term.

[0038] The present invention proposes a method for optimizing the layout of UAV airborne equipment based on genetic algorithms, which fully considers the integrated optimization of the weight and center of gravity control of the airborne equipment layout, effectively avoiding the problems of heavy cable laying and equipment center of gravity deviation in conventional layouts. At the same time, the genetic algorithm is used to solve the problem of airborne equipment layout optimization, which can quickly and efficiently obtain the optimization plan for the layout of UAV airborne equipment. This method has been successfully applied to a certain type of unmanned helicopter and can be applied to other manned aircraft in the future, with certain engineering application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of iterative fitness provided by an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of an optimized arrangement of equipment on board a UAV provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0042] A method for optimizing the layout of UAV airborne equipment based on genetic algorithm is proposed. A mathematical model for integrated optimization of equipment layout weight and center of gravity control is established. Based on the optimization objectives of minimizing the weight of equipment power cables, minimizing the weight of cross signal cables between equipment, and minimizing the center of gravity positioning deviation, weighted values ​​are introduced to transform it into a single optimization model. At the same time, constraints such as body loading space, equipment layout, disassembly and maintenance are considered. The optimization model is solved by genetic algorithm to quickly obtain the optimization plan for the layout of UAV airborne equipment.

[0043] A method for optimizing the layout of UAV airborne equipment based on a genetic algorithm comprises the following steps:

[0044] Step 1: Establish a multi-objective optimization mathematical model with the minimum weight of the equipment power supply cable, the minimum weight of the cross signal cable between devices, and the minimum center of gravity positioning deviation as the optimization goals.

[0045] (1) Objective function for minimizing the weight of equipment power cables

[0046] The location of airborne equipment directly affects the laying path of its power supply cables. Considering the weight control issue of equipment layout, the primary goal is to minimize the weight of the equipment power supply cables.

[0047]

[0048] In formula (1), The weight of the power cable for the equipment; i represents the equipment number, P i represents the ith device identifier, i = 1, 2, ... m, m is the total number of devices; ρ i Indicates device P iWeight per unit length of power supply cable; (x 0 ,h 0 ) represents the coordinates of the cable power supply source point; Indicates device P i The center coordinates, h i For device P i The wiring height itself, For device P i Total height of layout layers:

[0049]

[0050] Wherein, L represents the height of the equipment compartment, and t represents the number of floors in the equipment compartment.

[0051] (2) Objective function for minimizing the weight of cross-signal cables between devices

[0052] The ability of drones to be remotely controlled / autonomous in flight mainly relies on the auxiliary control and perception of the onboard equipment. This requires planning for all instructions to flow automatically between devices to form an information cross-linking network. Therefore, uplink, downlink, storage and other signal cables need to be laid between devices. Considering the weight control issue of equipment layout, the weight of cross-signal cables between devices should be minimized.

[0053]

[0054] In formula (3), The weight of the signal cables between devices; α ij Indicates P i , P j Weight per unit length of signal cable between devices; X ij P i , P j The routing length of the signal cable between devices can be expressed as:

[0055]

[0056] Where D is the width of the equipment compartment, s ij Indicates device P i and P j The difference in the number of columns arranged, t1 and t2 are respectively i and P j The number of layers of equipment compartments arranged.

[0057] (3) Objective function for minimizing the center of gravity positioning deviation

[0058] The center of gravity of the entire aircraft is an important factor affecting the flight quality and payload of the UAV. The quality of the center of gravity control will directly affect the flight safety of the UAV. Therefore, when planning the layout of the airborne equipment, try to position the center of gravity to the ideal position, so the minimum center of gravity positioning deviation is taken as an optimization goal.

[0059]

[0060] In formula (5), is the equipment center of gravity positioning deviation value, W i Indicates device P i The weight, x wc The ideal coordinate value of the device's center of gravity.

[0061] (4) Constructing the overall objective function

[0062] Assign corresponding weights to the above objective function values ​​and construct the objective function for equipment layout optimization:

[0063]

[0064] In formula (6), C R represents the overall optimization objective; δ 1 ,δ 2 ,δ 3 is the multi-objective weight.

[0065] Step 2: Determine the constraints on the layout of the onboard equipment by comprehensively considering the internal loading space of the fuselage, equipment layout elements, disassembly and maintenance requirements, etc.

[0066] (1) Devices on the same layer and row do not collide or overlap

[0067]

[0068] In formula (7), b i , b j Respectively represent equipment P i , P j The length dimension, d (i,j) Indicates P i , P j Minimum safe distance between devices.

[0069] (2) Equipment on any layer cannot collide with the cabin structure wall

[0070]

[0071] In formula (8), ω represents the minimum distance between the equipment and the cabin structure wall, S t Indicates the starting coordinate value of the equipment cabin on the tth floor, B t Indicates the length of the equipment compartment on the tth floor.

[0072] Step 3: Use genetic algorithm to solve the integrated optimization model of equipment layout weight configuration and center of gravity control.

[0073] (1) Equipment layout optimization identification, identifying the fitness function and constraints of the problem model as the layout optimization;

[0074] (2) Population initialization. Randomly generate n arrangements of all equipment layouts, and for each arrangement, solve the center coordinates corresponding to the equipment layout according to the constraints to form n chromosomes as the initial population.

[0075] (3) Fitness calculation. The equipment layout optimization function is converted into a fitness function. For equipment that exceeds all equipment compartment layout constraints or special equipment installation and maintenance constraints, a penalty term F is introduced. The fitness function can be expressed as:

[0076]

[0077] (5) Genetic selection operation. Calculate the fitness values ​​of all chromosomes in the population and arrange them in order from large to small. Keep the top 10% of chromosomes to enter the next generation population without crossover and mutation operations. Use the roulette wheel method to perform crossover and mutation operations on the remaining 90% of chromosomes (called inferior population).

[0078] (6) Genetic crossover operation. An adaptive crossover operation is performed on the arrangement of chromosomes of the disadvantaged population according to the crossover probability. That is, for each chromosome in the disadvantaged population, a chromosome to be crossed and a crossover node are randomly generated, the genes of the two chromosomes to be crossed at the crossover node are exchanged, and then the duplicate genes at other nodes of the chromosome are corrected to replacement genes; according to the arrangement scheme after the crossover, the center coordinates corresponding to the device arrangement are solved in combination with the constraint conditions to form a new chromosome; the fitness value of the new chromosome is calculated. If the value is greater than the fitness value of the original chromosome, crossover repair is performed; otherwise, the original chromosome is retained.

[0079] (7) Genetic mutation operation. The arrangement of chromosomes in the disadvantaged population is adaptively mutated according to the mutation probability, that is, two different mutation nodes are randomly generated, and the genes of the chromosomes to be mutated in the disadvantaged population on the two mutation nodes are swapped; according to the arrangement scheme after mutation, the center coordinates corresponding to the device arrangement are solved in combination with the constraint conditions to form a new chromosome to complete the mutation operation.

[0080] (8) Replacement of unqualified chromosomes. For chromosomes in the population, if any device exceeds the layout constraints of all equipment compartments, the chromosome with the largest fitness value in the population is used for replacement to facilitate genetic optimization.

[0081] (9) Termination condition judgment: determine whether the maximum number of iteration termination times has been reached. If so, output the optimal equipment layout plan. Otherwise, proceed to step (5) for iterative optimization.

[0082] Example description:

[0083] The specific information of the planning and design of a drone-mounted equipment in the example is as follows:

[0084] The equipment cabin of the drone has two floors with a floor height of 0.4m. The bottom floor has two rows with a width of 0.3m and a length range of 3.3m to 4.8m. The top floor has a single row with a length range of 4.1m to 5.5m. According to the overall layout planning requirements, 9 different airborne equipment are prepared for cabin layout, and the distance between the equipment and the cabin boundary is required to be 0.14m; the equipment related information (weight, length, wiring height, weight per unit length of power supply cable, minimum safety distance) is shown in Table 1; the weight per unit length of signal cable between equipment is shown in Table 2; the coordinates of the power supply point of the whole machine cable in the whole machine coordinate system are (4.6m, 0m); the ideal coordinates of the center of gravity of the airborne equipment in the x direction are 4.2m.

[0085] Table 1 Airborne equipment information

[0086]

[0087] Table 2 Weight per unit length of signal cables between devices

[0088]

[0089] The integrated optimization model of the airborne equipment layout weight and center of gravity control proposed in this invention is solved by using a genetic algorithm. The algorithm parameters are set as follows: the population size is 100, the crossover probability is 0.5, the mutation probability is 0.2, and the maximum number of iteration terminations is 200; the weight of the optimization objective function is set to δ 1 =1,δ 2 =1,δ 3 =1; the penalty value is F=100. The optimal layout plan of the UAV airborne equipment is obtained as follows:

[0090] Table 3 Optimal solution for UAV airborne equipment layout

[0091]

[0092] from Figure 1 It can be seen that the UAV airborne equipment layout optimization method based on genetic algorithm proposed in the present invention fully considers the integrated optimization of the airborne equipment layout weight and center of gravity control, and can quickly and efficiently obtain the optimization plan of the UAV airborne equipment layout, such as Figure 2 shown.

[0093] The method for optimizing the layout of UAV airborne equipment based on genetic algorithm is applicable to the layout of multiple equipment with multiple constraints and complicated cable cross-linking, and can quickly and efficiently obtain the optimization plan for the layout of UAV airborne equipment. The UAV can be an unmanned helicopter, a fixed-wing UAV or other multi-rotor UAV; the genetic operation can be a crossover followed by a mutation operation, or a mutation followed by a crossover operation.

[0094] The present invention proposes a method for optimizing the layout of UAV airborne equipment based on genetic algorithms, which fully considers the integrated optimization of the weight and center of gravity control of the airborne equipment layout, effectively avoiding the problems of heavy cable laying and equipment center of gravity deviation in conventional layouts. At the same time, the genetic algorithm is used to solve the problem of airborne equipment layout optimization, which can quickly and efficiently obtain the optimization plan for the layout of UAV airborne equipment. This method has been successfully applied to a certain type of unmanned helicopter and can be applied to other manned aircraft in the future, with certain engineering application value.

Claims

1. A method for optimizing the layout of UAV airborne equipment based on genetic algorithm, characterized in that: The following steps are involved: Step 1: Establish a multi-objective optimization mathematical model with the minimum weight of the equipment power supply cable, the minimum weight of the cross signal cable between the equipment, and the minimum center of gravity positioning deviation as the optimization goals; Step 2: Determine the constraints for the layout of airborne equipment; Step 3: Combined with the constraints of airborne equipment layout, the genetic algorithm is used to solve the multi-objective optimization mathematical model to obtain the optimal layout plan of the UAV airborne equipment.

2. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 1, characterized in that: The objective function for minimizing the weight of the equipment power supply cable is as follows: In formula (1), The weight of the power cable for the equipment; i represents the equipment number, P i represents the ith device identifier, i = 1, 2, ... m, m is the total number of devices; ρ i Indicates device P i The weight of the power supply cable per unit length; (x0,h0) represents the coordinates of the cable power supply source point; Indicates device P i The center coordinates, h i For device P i The wiring height itself, For device P i Total height of layout layers: Wherein, L represents the height of the equipment compartment, and t represents the number of floors in the equipment compartment.

3. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 2, characterized in that: The objective function for minimizing the weight of cross-signal cables between devices is as follows: In formula (3), The weight of the signal cables between devices; α ij Indicates P i , P j Weight per unit length of signal cable between devices; X ij P i , P j The routing length of the signal cable between devices can be expressed as: Where D is the width of the equipment compartment, s ij Indicates device P i and P j The difference in the number of columns arranged, t1 and t2 are respectively i and P j The number of layers of equipment compartments arranged.

4. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 3, characterized in that: The objective function for minimizing the center of gravity positioning deviation is as follows: In formula (5), is the equipment center of gravity positioning deviation value, W i Indicates device P i The weight, x wc The ideal coordinate value of the device's center of gravity.

5. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 4, characterized in that: Taking the minimum weight of equipment power supply cables, the minimum weight of cross signal cables between equipment, and the minimum center of gravity positioning deviation as the optimization goals, a multi-objective optimization mathematical model is established as follows: Construct the objective function of equipment layout optimization: In formula (6), C R represents the overall optimization goal; δ1, δ2, δ3 are multi-objective weights.

6. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 5, characterized in that: Determine the constraints for the layout of airborne equipment including: Devices located in the same layer and column do not collide or overlap: In formula (7), b i , b j Respectively represent equipment P i , P j The length dimension, d (i,j) Indicates P i , P j Minimum safe distance between devices.

7. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 6, characterized in that: Determining the constraints for the layout of airborne equipment also includes: Equipment on any layer cannot collide with the cabin structure wall: In formula (8), ω represents the minimum distance between the equipment and the cabin structure wall, S t Indicates the starting coordinate value of the equipment cabin on the tth floor, B t Indicates the length of the equipment compartment on the tth floor.

8. The method for optimizing the layout of UAV airborne equipment based on genetic algorithm according to claim 7, characterized in that: In the process of solving the multi-objective optimization mathematical model using genetic algorithm, The fitness function of the genetic algorithm is expressed as: F is the penalty term.

Images