A knowledge-guided evolutionary optimization method for resource scheduling of aircraft measurement and control equipment

Abstract

The present invention discloses a knowledge-guided evolutionary optimization method for resource scheduling of aircraft measurement and control equipment, comprising the following steps: based on measurement and control equipment task scheduling and path planning that maximizes task completion, constructing a joint optimization model that satisfies various constraints and maximizes comprehensive evaluation indicators; starting from the perspective of finding a combination scheme of measurement and control points and equipment, introducing decision variables that can represent combination schemes and maneuver schemes; optimizing the objectives: considering measurement and control operation constraints, measurement and control equipment requirement constraints, measurement and control equipment performance constraints, and measurement and control performance parameter calculations; solving the model using a knowledge-guided evolutionary optimization method. This application combines the global optimization characteristics of the evolutionary algorithm and the local search characteristics of the heuristic algorithm to find a high-quality solution to the problem; the knowledge-guided evolutionary algorithm can find high-quality solutions globally, and the rule-based heuristic algorithm ensures the quality of the solution locally.

Description

Technical Field

[0001] The present invention belongs to the technical field of measurement, control and scheduling, and in particular relates to a knowledge-guided evolutionary optimization method for resource scheduling of aircraft measurement and control equipment. Background Art

[0002] To ensure that the aircraft's technical indicators meet the expected standards, multiple flight tests are required. These flight tests are not only a test of the aircraft's performance, but also a rigorous assessment of the relevant measurement and control technologies and strategies.

[0003] The measurement and control system plays a crucial role in aircraft flight testing. It collects, transmits, and analyzes a wide range of flight data, providing critical support for aircraft development, testing, optimization, and evaluation. However, with the increasing number and complexity of flight test missions, effectively scheduling and deploying measurement and control resources to ensure efficient, accurate, and safe test completion has become a pressing issue.

[0004] Currently, the scheduling and deployment of measurement and control resources mostly rely on experience and intuition, which can lead to resource waste and low efficiency to a certain extent. Therefore, how to use modern optimization techniques and algorithms to achieve scientific and efficient scheduling and deployment of measurement and control resources is one of the research goals in this field. Summary of the Invention

[0005] To achieve the above objectives, the present application discloses a knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling, comprising the following steps:

[0006] Step 1, model construction: Based on the task scheduling and path planning of measurement and control equipment to maximize task completion, a joint optimization model is constructed that meets various constraints and maximizes comprehensive evaluation indicators;

[0007] Step 2: Introduce decision variables: From the perspective of finding a combination of measurement and control points and equipment, introduce decision variables that can represent the combination and maneuver options.

[0008] Step 3, optimization goal: Consider the two aspects of effective coverage and balance, and then maximize the comprehensive evaluation test effect. The optimization goal is to maximize the comprehensive evaluation index ;

[0009] Step 4: Analyze constraints: Consider measurement and control operation constraints, measurement and control equipment requirement constraints, measurement and control equipment performance constraints, and calculate measurement and control performance parameters;

[0010] Step 5: Establish a model solving algorithm: Use the knowledge-guided evolutionary optimization method to solve the model.

[0011] Furthermore, various constraints are precisely classified and simplified, including task matching constraints and equipment working and maneuvering time constraints. According to the specific constraints of each measurement and control equipment, all possible matching combinations of "aircraft-arc-measurement and control point-measurement and control equipment" are calculated in advance. Based on the task scheduling and path planning of measurement and control equipment that maximizes task completion, a joint optimization model that meets various constraints and maximizes comprehensive evaluation indicators is constructed.

[0012] Furthermore, the decision variables include:

[0013] : 0-1 variable, if the Task No. Arc segment by device 1 if measurement and control is enabled, otherwise 0;

[0014] : 0-1 variable, if the device Should be deployed to the point Measurement and control tasks is 1, otherwise 0;

[0015] : 0-1 variable, if the device Need to Move to the corresponding measurement and control point to complete the task is 1, otherwise 0;

[0016] : 0-1 variable, if the device From the measurement and control point Maneuver to the measurement and control point is 1, otherwise 0;

[0017] :The equipment is located at the measurement and control point To the measurement and control point maneuvering time;

[0018] :equipment From the measurement and control point Maneuver to the measurement and control point Time of departure;

[0019] :equipment No. The time it takes to reach the supply point.

[0020] Furthermore, the optimization goal is to maximize the comprehensive evaluation index :

[0021] ;

[0022] Comprehensive evaluation indicators The calculation formula is:

[0023] ;

[0024] Comprehensive evaluation indicators Effective coverage for tasks and balance The weighted average of

[0025] Effective coverage of tasks The calculation process is as follows:

[0026] A single task consists of several arcs, which are divided into key arcs and regular arcs;

[0027] The effective coverage of the key arc is defined as:

[0028] ;

[0029] Among them, the key arc For the Task No. arc segments, for The effective coverage of For arc segments duration, for The actual tracking time;

[0030] The effective coverage of a conventional arc segment is defined as:

[0031] ;

[0032] Among them, the conventional arc For the Task No. arc segments, for The effective coverage of For arc segments duration, for The actual tracking time;

[0033] Set up the first The tasks are arcs, the effective coverage of the task is:

[0034] ;

[0035] in, for Task No. The weight of each arc segment; arc segments of different types of equipment should be calculated separately; tasks, the total effective coverage of tasks is:

[0036] ;

[0037] Balance The calculation formula is:

[0038] ;

[0039] Where, is the total duration of the planning cycle, is the total number of mobile equipment, t j For the The total working time of a mobile equipment in the entire planning cycle refers to the total duration of the planning cycle minus the supply time; mobile equipment that has not been mobilized in the entire planning cycle is not included in the calculation of balance.

[0040] Furthermore, the various constraints include:

[0041] Device task constraints:

[0042] ;

[0043] Where, Is a 0-1 variable, indicating that if Task No. The arc segment is controlled by the measurement and control equipment 1 if measurement and control is enabled, otherwise 0; this constraint ensures that each device can only be assigned to one time arc of a task at a time;

[0044] Equipment point constraints:

[0045] ;

[0046] Where, Is a 0-1 variable, indicating if the measurement and control equipment Assign to point To complete the task is 1, otherwise it is 0; this constraint ensures that each device can only be assigned to one point at the same time;

[0047] Device time constraints:

[0048] ;

[0049] Where, Is a 0-1 variable, indicating if the measurement and control equipment Need to Move to the corresponding measurement and control point to complete the task 1, otherwise 0; this constraint ensures that each device can only measure and control one task at most per day;

[0050] Time point constraints:

[0051] ;

[0052] This constraint ensures the time and location relationship between the equipment's execution of the measurement and control task. If the equipment is to execute the measurement and control task, both the time and location are determined at the same time.

[0053] Equipment mobility constraints:

[0054] ;

[0055] Where, Is a 0-1 variable, indicating that if the device From the measurement and control point Maneuver to the measurement and control point 1 if it is set to 0, otherwise it is 0; these two constraints ensure that each device can only maneuver from one position to another, and this position cannot be the current position of the device;

[0056] Time constraints for measurement and control equipment to reach measurement and control points:

[0057] ;

[0058] Where, Indicates a task The launch date of the spacecraft, Indicates a task This constraint ensures that the equipment participating in the task must be Arrive at the corresponding measurement and control point before 24:00 on the day;

[0059] Time constraints for the measurement and control equipment to leave the measurement and control point after completing the task:

[0060] ;

[0061] Where, Representation device From the measurement and control point Maneuver to the measurement and control point Departure time; this constraint ensures that the equipment participating in the task must be You can leave after 24:00 on the day;

[0062] Maximum continuous working time constraints:

[0063] ;

[0064] Where, Representation device No. Time to reach the supply point, Representation device The maximum continuous working time of the motorized equipment is guaranteed by this constraint. The time from the last time a person leaves the supply point to the next time they arrive at the supply point for replenishment shall not exceed the maximum continuous working time;

[0065] Maneuver time constraints:

[0066] Use Floyd's algorithm to solve the problem of using the position of the measurement and control points arrive The shortest path from Point to Maneuvering time of point The sum of the travel time of each road segment in its shortest path;

[0067] Type and frequency band constraints:

[0068] ;

[0069] Where, Indicates the Task No. The type of measurement and control equipment required for each arc segment, Representation device This constraint ensures that each arc in each task The required measurement and control equipment must be of the required type, and if the required equipment type is telemetry, it must further meet the frequency band requirements:

[0070] ;

[0071] Where, Indicates the Task No. The frequency band required by each arc segment, Representation device This constraint ensures that the telemetry equipment can only complete the mission if it has the receiving function of the same frequency band as the measurement and control aircraft.

[0072] "Characteristic measurement" requirement constraints:

[0073] ;

[0074] Where, Indicates the Task No. Arc segments Other measurement and control requirements: 0 means “none”, 1 means “characteristic measurement”, 2 means “double coverage”, and 3 means “telemetry and security control”; A 0-1 variable representing the device Whether it has the characteristic measurement function, 1 if it does, 0 otherwise. This constraint ensures that if there is a "characteristic measurement" requirement, then the radar equipment measuring and controlling this arc segment must have the characteristic measurement function;

[0075] "Double coverage" requirement constraints:

[0076] ;

[0077] Where, The actual tracking time of the device. The duration of joint tracking by multiple similar devices. This constraint ensures that if "double coverage" is required, the tracking duration of this arc segment is the period of joint tracking by two or more similar devices.

[0078] "Telemetry and security control" requirements and constraints:

[0079] ;

[0080] Where, A 0-1 variable representing the device Whether it has security control function, 1 if it has, 0 otherwise. This constraint ensures that if there is a "telemetry + security control" requirement, then this arc segment is a key arc segment, and the telemetry equipment used to measure and control this arc segment must have security control function.

[0081] Measurement and control point level constraints:

[0082] ;

[0083] Where, For measurement and control points level, For equipment The minimum point level required;

[0084] The distance R of the target relative to the device is constrained:

[0085] ;

[0086] Where, For the Task No. The first arc The position relative to the device at that moment distance, For equipment The device will track and measure the target only when the distance between the target and the device is within the device's range.

[0087] Azimuth angle A of the target relative to the device:

[0088] ;

[0089] Where, For the Task No. The first arc Position relative to the device at that moment The azimuth of 、 For equipment The azimuth angle of the target is within the working range of the device. The device will track and measure the target at that moment.

[0090] The target's pitch angle E and shielding angle SA constraints relative to the device are:

[0091] ;

[0092] Where, For the Task No. The first arc Position relative to the device at that moment The pitch angle, 、 For equipment The lower and upper limits of the pitch angle working, For measurement and control points When the device is observing a target, the pitch angle is required to be within the working range of the device's pitch angle indicator and greater than the shielding angle of the point;

[0093] VA constraint of the target's relative azimuth velocity:

[0094] ;

[0095] Where, For the Task No. The first arc The position change relative to the device at a moment and its previous moment The azimuthal velocity, For equipment The device will track and measure the target only when the target's azimuth velocity relative to the device is within the device's operating range.

[0096] The target's pitch angular velocity VE constraint relative to the device:

[0097] ;

[0098] Where, For the Task No. The first arc The position change relative to the device at a moment and its previous moment The pitch angular velocity, For equipment The device will track and measure the target only when the target's pitch angular velocity relative to the device is within the device's operating range.

[0099] Furthermore, the measurement and control performance parameters are calculated as follows:

[0100] The coordinates of the measurement and control equipment in the geocentric rectangular coordinate system are ( , , ), the coordinates in the geodetic coordinate system are ( , , ), coordinate point in geocentric rectangular coordinate system ( , , ), coordinates in the rectangular coordinate system of the measuring station ( , , )have:

[0101] ;

[0102] From the station rectangular coordinate system coordinates ( , , ) The formula for the coordinates of the RAE coordinate system of the transfer station is:

[0103] ;

[0104] ;

[0105] The velocity in the geocentric rectangular coordinate system ( , , ) is converted into the velocity in the RAE coordinate system of the measuring station. First, the position vector of the target point relative to the measuring station is determined. , then, calculate The RAE coordinate system is obtained by using the three orthogonal unit vectors R, A, and E; specifically:

[0106] Calculate the position vector :

[0107] ;

[0108] Calculate the orthogonal unit vectors of R, A, and E:

[0109] ;

[0110] in, The three components are the velocities in the R, A and E directions, and the last two components are the azimuthal velocities and pitch angular velocity .

[0111] Furthermore, the knowledge-guided evolutionary optimization method comprises the following steps:

[0112] The S1 knowledge guidance mechanism guides the generation and selection of solutions by extracting conflicting information between current individual tasks: extracting valuable knowledge from the solutions, which provides insights into the evaluation and improvement of the solution quality; secondly, using a feasible rule-based approach and combining this knowledge to formulate an environment selection strategy;

[0113] Specifically, the number and location of the current individual's measurement and control task conflicts are first recorded. The number of conflicts can be regarded as the distance between the current individual and the feasible domain, while the location of the conflicts indicates the search direction. When selecting solutions, individuals with fewer conflicts are preferred. In crossover and mutation operations, the crossover and mutation probability of the conflicting locations is increased, but to avoid falling into local optimality, operations are avoided directly at the conflicting locations. This strategy guides the search for solutions closer to the feasible domain.

[0114] To minimize the number of devices that do not meet the constraints, a pair of data is used to mark conflicts. That is, <(i, j, k)> indicates that in the i-th coverage measurement, the measurement and control equipment of the j-th arc segment k of the aircraft cannot meet the constraints. This conflict information is passed to the crossover and mutation operators to guide the evolution of these conflicts.

[0115] S2 coding mechanism: A two-layer coding method is used, namely main coding and double-cover coding. Specifically, the matching combination of "aircraft-arc-T&C point-T&C equipment" is first calculated. The main coding records an integer value for each variable in the two-dimensional matrix. This integer value represents the index value of the "T&C point-T&C equipment" combination that can provide observations for the aircraft and arc. For double-cover coding, the selected "aircraft-arc-T&C point-T&C equipment" combination performs the observation task.

[0116] S3 is based on a knowledge-guided crossover and mutation operator: the crossover and mutation operator guides the crossover and mutation operations by increasing the probability of selecting points containing conflicting information, thereby making the offspring more likely to improve;

[0117] S4 Environment selection strategy based on knowledge guidance and feasibility criteria: Adopt feasibility criteria to deal with constraints and use environment selection strategy based on knowledge guidance and feasibility criteria; the feasibility criteria are:

[0118] First compare the feasibility of the solutions: a feasible solution is always better than an infeasible solution;

[0119] If both solutions are feasible, they are compared based on the value of the objective function;

[0120] If both solutions are infeasible, they are compared based on the degree of constraint violation;

[0121] Specifically, the constraint violation degree and fitness value of the individual are considered first. When there are differences in fitness values between individuals, the solution with a larger fitness value is preferred. The number of conflicts within the individual is used as the second criterion. When there is no difference in fitness values, the individual with fewer conflicts is preferred.

[0122] S5: Solve the measurement and control equipment path planning problem using a rule-based heuristic algorithm, which includes the following steps:

[0123] S51: Calculate the distance between each aircraft and each measurement and control point during flight based on the input information , azimuth , pitch angle , azimuth velocity , pitch angular velocity ;

[0124] S52: Based on the above information and other constraints, filter out each arc segment in each task A set of solutions that can be measured and controlled ,Right now ;

[0125] S53: Iterate each solution of each arc segment in each task:

[0126] S54: Calculate and detect arc segments In the corresponding combination plan set, whether the equipment can arrive before the mission start time; if not, the coverage rate of the arc segment is 0; the number of conflicts is increased by 1; if it exists, determine whether it needs to be moved. If the equipment does not need to be moved, calculate the coverage rate of the arc segment. If it needs to be moved, the equipment needs to maneuver to another location to perform the measurement and control mission. According to the preset equipment supply and maneuvering rules, the maneuvering and supply operations are carried out, and the coverage rate of the arc segment is calculated;

[0127] S55: If double coverage is required, repeat step S4;

[0128] S56 calculates comprehensive evaluation indicators: effective coverage and balance.

[0129] The equipment supply and maneuvering rules include:

[0130] When both the starting point and the target point are replenishment points: the device directly travels from the starting point to the target point, because the longest maneuvering time between the two points is less than the maximum continuous working time of the device. After arriving, the device is replenished at the target point.

[0131] When the starting point is a replenishment point, but the target point is not: the device goes directly from the starting point to the target point; however, since the target point is not a replenishment point, the device does not recharge after arriving.

[0132] When the starting point is not a refueling point, but the target point is: first determine whether the device will exceed its maximum continuous working time before reaching the target point; if not, the device will go directly there and refuel there. If it exceeds the time limit, the device will refuel at the nearest refueling point along the way; in addition, determine whether the device can still reach the target point in time to complete the task after refueling midway; if so, the device will refuel at both the nearest refueling point and the target point; if not, the solution violates the constraints and becomes infeasible;

[0133] When neither the starting point nor the target point is a resupply point: Since neither point is a resupply point, the device must be resupplyed en route to ensure that the maximum working time is not exceeded; it is also necessary to determine whether the device can still reach the target point in time to complete the task after the mid-way resupply. If so, the device will be resupplyed en route at the nearest resupply point. If not, then this plan will violate the constraints and become infeasible.

[0134] The beneficial effects of this application are as follows:

[0135] This application addresses the task scheduling and path planning issues for measurement and control equipment and constructs a joint optimization model for task scheduling and path planning based on maximizing task completion. This model fully considers the practical context and various constraints of the problem, ensuring its integrity and practicality.

[0136] By decoupling the model, the model is divided into a main problem and sub-problems, making the problem-solving process clearer and more operational. The algorithm design combines the global optimization properties of evolutionary algorithms with the local search properties of heuristic algorithms, aiming to find high-quality solutions to the problem.

[0137] The proposed knowledge-guided evolutionary algorithm is able to find high-quality solutions globally, while the rule-based heuristic algorithm ensures the quality of the solutions locally. The combination of the two provides an efficient and practical solution to the task scheduling and path planning problems of measurement and control equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0138] Figure 1 Based on the knowledge-guided evolutionary algorithm process;

[0139] Figure 2 Description of the knowledge guidance mechanism;

[0140] Figure 3 Solution coding method (the darker ones are arcs that need secondary coverage);

[0141] Figure 4 Knowledge-guided crossover mutation operator (dark color indicates selected crossover point) DETAILED DESCRIPTION

[0142] The present invention will be further described below with reference to the accompanying drawings, but the present invention is not limited in any way. Any changes or substitutions made based on the teachings of the present invention fall within the scope of protection of the present invention.

[0143] Table 1 Symbols:

[0144] ;

[0145] ;

[0146] ;

[0147] This involves the deployment and scheduling of measurement and control (T&C) resources during aircraft flight tests. Appropriate T&C equipment deployment and maneuvering strategies must be developed based on the performance of the equipment and the specific requirements of the test. Furthermore, the test department's flight test plan includes multiple missions, each of which is further divided into several arcs. Each arc has specific T&C requirements, including the required equipment type and other specific requirements such as "characteristic measurement" or "double coverage." The core of the problem lies in finding the optimal deployment and maneuvering strategy to maximize the weighted average of effective mission coverage and balance.

[0148] Solution:

[0149] 1. Model Construction: First, a joint optimization model for measurement and control equipment task scheduling and path planning should be constructed. This model should aim to maximize overall task completion, with measurement and control task allocation and path planning as the primary decision variables. Furthermore, the model needs to account for various practical constraints.

[0150] 2. Constraint classification: To simplify the solution process, the constraints can be classified and simplified, mainly including:

[0151] (1) Measurement and control operation constraints: This involves the matching of “aircraft-arc-time-measurement and control point-measurement and control equipment”. Considering that the working time and maneuvering time of the measurement and control equipment may be difficult to directly mathematically express, heuristic methods are considered to ensure the feasibility and high quality of the solution;

[0152] (2) Measurement and control equipment performance constraints: Before optimization, first calculate the relevant parameters of each measurement and control point and the theoretical trajectory of each task, such as distance, azimuth, pitch angle, etc. Then, according to the working environment requirements of the measurement and control equipment, screen out feasible matching combinations and calculate their coverage. This can greatly reduce the decision space and improve the solution efficiency;

[0153] (3) Constraints on measurement and control equipment requirements: Different arcs of different tasks require different types of measurement and control equipment, and some arcs have other requirements that need to be met, namely "characteristic measurement", "double coverage" and "telemetry and security control".

[0154] To simplify the problem, in one embodiment, this application assumes the following about the model:

[0155] 1. Equipment restrictions at supply points: Assume that there is no limit on the number of measurement and control equipment that can be supplied at each supply point, that is, multiple devices can be supplied at the same supply point at the same time;

[0156] 2. Recharge time: Assuming that each recharge takes at least 1 day, the device is considered to have completed recharge when it stays at the recharge point for 1 day or more. The device cannot perform other operations during the recharge process.

[0157] 3. Radar Technical Characteristics: To simplify the model, it is assumed that the radar's angular velocity when observing a target is not restricted. Furthermore, all radar equipment utilizes advanced phased array technology, enabling faster response times and greater flexibility.

[0158] 4. Equipment post-task action: Once the equipment completes all assigned tasks, it is no longer considered whether it needs to be resupplied or its subsequent location changes;

[0159] 5. Parallelism of equipment replenishment and measurement and control: In the model, the equipment is allowed to perform measurement and control tasks simultaneously during the replenishment process, but this may affect its measurement and control performance;

[0160] 6. Environmental stability: It is assumed that during the flight test, environmental factors such as weather and electromagnetic interference remain stable and will not affect the operation of the measurement and control equipment;

[0161] 7. Equipment reliability: To simplify the model, it is assumed that all measurement and control equipment works normally during the test and there are no equipment failures or emergencies.

[0162] The knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling disclosed in this application includes the following steps:

[0163] Step 101, model construction: Based on the task scheduling and path planning of measurement and control equipment to maximize task completion, a joint optimization model is constructed that satisfies various constraints and maximizes comprehensive evaluation indicators;

[0164] Step 102, introducing decision variables: From the perspective of finding a combination solution of measurement and control points and equipment, it is necessary to introduce decision variables that can represent the combination solution and the maneuver solution;

[0165] Step 103, optimization goal: Considering the two aspects of effective coverage and balance, and then maximizing the comprehensive evaluation test effect, the optimization goal is to maximize the comprehensive evaluation index ;;

[0166] Step 104: Analyze the constraints: consider the measurement and control operation constraints, measurement and control equipment requirement constraints, measurement and control equipment performance constraints, and calculate the measurement and control performance parameters;

[0167] Step 105, establishing a model solving algorithm: considering the nonlinear constraints and simulation calculation process of the above model, the problem is solved using an evolutionary computing method, the problem is decoupled into a main problem and sub-problems, and a heuristic algorithm is used.

[0168] Step 1, model construction: Based on the task scheduling and path planning of measurement and control equipment to maximize task completion, a joint optimization model is constructed that meets various constraints and maximizes comprehensive evaluation indicators.

[0169] Step 2: Introduce decision variables: From the perspective of finding a combination of measurement and control points and equipment, it is necessary to introduce decision variables that can represent the combination scheme and maneuver scheme.

[0170] 2.1 From the perspective of finding a combination of measurement and control points and equipment, it is necessary to introduce decision variables that can represent the combination and maneuvering schemes, as shown below:

[0171] : 0-1 variable, if the Task No. Arc segment by device 1 if measurement and control is enabled, otherwise 0;

[0172] : 0-1 variable, if the device Should be deployed to the point Measurement and control tasks is 1, otherwise 0;

[0173] : 0-1 variable, if the device Need to Move to the corresponding measurement and control point to complete the task is 1, otherwise 0;

[0174] : 0-1 variable, if the device From the measurement and control point Maneuver to the measurement and control point is 1, otherwise 0;

[0175] :The equipment is located at the measurement and control point To the measurement and control point maneuvering time;

[0176] :equipment From the measurement and control point Maneuver to the measurement and control point Time of departure;

[0177] :equipment No. The time it takes to reach the supply point.

[0178] Step 3, optimization goal: Consider the two aspects of effective coverage and balance, and then maximize the comprehensive evaluation test effect. The optimization goal is to maximize the comprehensive evaluation index .

[0179] 3.1 From the perspective of finding a combination of measurement and control points and equipment, it is necessary to introduce decision variables that can represent the combination plan and maneuver plan, as shown below:

[0180] : 0-1 variable, if the Task No. Arc segment by device 1 if measurement and control is enabled, otherwise 0;

[0181] : 0-1 variable, if the device Should be deployed to the point Measurement and control tasks is 1, otherwise 0;

[0182] : 0-1 variable, if the device Need to Move to the corresponding measurement and control point to complete the task is 1, otherwise 0;

[0183] : 0-1 variable, if the device From the measurement and control point Maneuver to the measurement and control point is 1, otherwise 0;

[0184] :The equipment is located at the measurement and control point To the measurement and control point maneuvering time;

[0185] :equipment From the measurement and control point Maneuver to the measurement and control point Time of departure;

[0186] :equipment No. The time it takes to reach the supply point.

[0187] Step 4: Analyze the constraints: consider the measurement and control operation constraints, measurement and control equipment requirement constraints, measurement and control equipment performance constraints, and calculate the measurement and control performance parameters.

[0188] The effectiveness of the measurement and control equipment in the test task is mainly considered in terms of effective coverage and balance. In order to maximize the comprehensive evaluation test effect, the optimization goal is to maximize the comprehensive evaluation index :

[0189] ;

[0190] Comprehensive evaluation indicators The calculation formula is:

[0191] ;

[0192] Comprehensive evaluation indicators Effective coverage for tasks and balance The weighted average of .

[0193] Effective coverage of tasks The calculation process is as follows:

[0194] A single task contains several arcs, which can be divided into key arcs and regular arcs.

[0195] The effective coverage of the key arc is defined as:

[0196] ;

[0197] Among them, the key arc For the Task No. arc segments, for The effective coverage of For arc segments duration, for The actual tracking time.

[0198] The effective coverage of a conventional arc segment is defined as:

[0199] ;

[0200] Among them, the conventional arc For the Task No. arc segments, for The effective coverage of For arc segments duration, for The actual tracking time.

[0201] Set up the first The tasks are arcs, the effective coverage of the task is:

[0202] ;

[0203] in, for Task No. The weight of each arc segment. The arc segments of different types of equipment must be calculated separately and cannot be replaced by each other. tasks, the total effective coverage of tasks is:

[0204] ;

[0205] Balance The calculation formula is:

[0206] ;

[0207] Where, is the total duration of the planning cycle (questions 1 and 2 are calculated as 30 days, and question 3 is calculated as 28 days), is the total number of mobile equipment, t j For the The total operating time of a mobile unit during the entire planning cycle is the total duration of the planning cycle minus the resupply time (if a measurement and control mission is performed at a resupply point, the mission cycle time is included in the operating time). Mobile units that are not mobilized during the entire planning cycle are not included in the balance calculation.

[0208] Device task constraints:

[0209] (8);

[0210] Where, Is a 0-1 variable, indicating that if Task No. The arc segment is controlled by the measurement and control equipment 1 if measurement and control is enabled, otherwise 0. This constraint ensures that each device can only be assigned to one time arc of a task at a time.

[0211] Equipment point constraints:

[0212] (9);

[0213] Where, Is a 0-1 variable, indicating if the measurement and control equipment Assign to point To complete the task is 1, otherwise it is 0. This constraint ensures that each device can only be assigned to one point at the same time

[0214] Device time constraints:

[0215] (10);

[0216] Where, Is a 0-1 variable, indicating if the measurement and control equipment Need to Move to the corresponding measurement and control point to complete the task is 1, otherwise it is 0. This constraint ensures that each device can only measure and control one task at most in a day.

[0217] Time point constraints:

[0218] (11);

[0219] This constraint ensures the time and location relationship when the equipment performs the measurement and control task. If the measurement and control task is to be performed, the time and location are determined at the same time.

[0220] Equipment mobility constraints:

[0221] (12);

[0222] (13);

[0223] Where, Is a 0-1 variable, indicating that if the device From the measurement and control point Maneuver to the measurement and control point 1 if the device is in the same position as the current one, otherwise it is 0. These two constraints ensure that each device can only maneuver from one position to another, and this position cannot be the current position of the device.

[0224] Time constraints for measurement and control equipment to reach measurement and control points:

[0225] (14);

[0226] Where, Indicates a task The launch date of the spacecraft, Indicates a task This constraint ensures that the devices participating in the task must Arrive at the corresponding measurement and control point before 24:00 on the same day.

[0227] Time constraints for the measurement and control equipment to leave the measurement and control point after completing the task:

[0228] (15);

[0229] Where, Representation device From the measurement and control point Maneuver to the measurement and control point This constraint ensures that the equipment participating in the task must be You can leave after 24:00.

[0230] Maximum continuous working time constraints:

[0231] (16);

[0232] (17);

[0233] Where, Representation device No. Time to reach the supply point, Representation device The maximum continuous working time of the motorized equipment is guaranteed by this constraint. The time from the last time the company leaves the supply point to the next time it arrives at the supply point for replenishment shall not exceed its maximum continuous working time.

[0234] Maneuver time constraints:

[0235] Use Floyd's algorithm to solve the problem of using the position of the measurement and control points arrive The shortest path from Point to Maneuvering time of point The sum of the travel time of each road segment in its shortest path.

[0236] Type and frequency band constraints:

[0237] (18);

[0238] Where, Indicates the Task No. The type of measurement and control equipment required for each arc segment, Representation device This constraint ensures that each arc in each task The required measurement and control equipment must be of the required type. If the required equipment type is telemetry, it must also meet the frequency band requirements:

[0239] (19);

[0240] Where, Indicates the Task No. The frequency band required by each arc segment, Representation device This constraint ensures that the telemetry equipment can only complete the mission if it has the receiving function of the same frequency band as the measurement and control aircraft.

[0241] "Characteristic measurement" requirement constraints:

[0242] (20);

[0243] Where, Indicates the Task No. Arc segments Other measurement and control requirements: 0 means “none”, 1 means “characteristic measurement”, 2 means “double coverage”, and 3 means “telemetry + security control”. A 0-1 variable representing the device Whether it has the characteristic measurement function, 1 if it has it, otherwise 0. This constraint ensures that if there is a "characteristic measurement" requirement, then the radar equipment measuring and controlling this arc segment must have the characteristic measurement function.

[0244] "Double coverage" requirement constraints:

[0245] (twenty one);

[0246] Where, The actual tracking time of the device. The duration of tracking by multiple devices of the same type. This constraint ensures that if "double coverage" is required, the tracking duration of the arc segment is the period of tracking by two or more devices of the same type.

[0247] "Telemetry + Security Control" requirements and constraints:

[0248] (twenty two);

[0249] Where, A 0-1 variable representing the device Whether it has security control function, 1 if it has, otherwise 0. This constraint ensures that if there is a "telemetry + security control" requirement, then the arc segment is a key arc segment, and the telemetry equipment used to measure and control this arc segment must have security control function.

[0250] (3) Performance constraints of measurement and control equipment

[0251] Measurement and control point level constraints:

[0252] (twenty three);

[0253] Where, For measurement and control points level, For equipment The minimum required level of point. Different measurement and control equipment has different infrastructure requirements and requires that they be located at the corresponding level or higher to operate.

[0254] Distance (R) constraint of the target relative to the device:

[0255] (twenty four);

[0256] Where, For the Task No. The first arc The position relative to the device at that moment distance, For equipment When the distance between the target and the device is within the device's operating range, the device can track and measure the target at that moment.

[0257] Azimuth (A) constraint of the target relative to the device:

[0258] (25);

[0259] Where, For the Task No. The first arc Position relative to the device at that moment The azimuth of 、 For equipment The device can only track and measure the target when the azimuth angle of the target relative to the device is within the device's operating range.

[0260] The target's elevation angle (E) and shielding angle (SA) constraints relative to the device are:

[0261] (26);

[0262] Where, For the Task No. The first arc Position relative to the device at that moment The pitch angle, 、 For equipment The lower and upper limits of the pitch angle working, For measurement and control points When the device observes a target, the pitch angle must be within the working range of the device's pitch angle indicator and greater than the shielding angle at that point.

[0263] Target's azimuth velocity (VA) constraint relative to the device:

[0264] (27);

[0265] Where, For the Task No. The first arc The position change relative to the device at a moment and its previous moment The azimuthal velocity, For equipment The device can track and measure the target only when the target's azimuth velocity relative to the device is within the device's operating range.

[0266] The target's relative pitch velocity (VE) constraint:

[0267] (28);

[0268] Where, For the Task No. The first arc The position change relative to the device at a moment and its previous moment The pitch angular velocity, For equipment The device can track and measure the target only when the target's pitch angular velocity relative to the device is within the device's operating range.

[0269] If and only if the device Only when all measurement and control performance constraints are met can the device be considered to be able to track and measure the target at that moment.

[0270] (4) Measurement and control performance parameters ( 、 、 、 、 )calculate

[0271] Assume that the coordinates of the measurement and control equipment in the geocentric rectangular coordinate system are ( , , ), the coordinates in the geodetic coordinate system are ( , , ). The coordinate point in the geocentric rectangular coordinate system ( , , ), coordinates in the rectangular coordinate system of the measuring station ( , , )have:

[0272] (29);

[0273] From the station rectangular coordinate system coordinates ( , , ) The formula for the coordinates of the RAE coordinate system of the transfer station is:

[0274] ;

[0275] To calculate the velocity in the geocentric rectangular coordinate system ( , , ) is converted into the velocity in the RAE coordinate system of the measuring station. First, the position vector of the target point relative to the measuring station must be determined. Then, we can calculate The RAE coordinate system is obtained by using the three orthogonal unit vectors R, A, and E. Specifically:

[0276] Calculate the position vector :

[0277] (34);

[0278] Calculate the orthogonal unit vectors of R, A, and E:

[0279] (35);

[0280] (36);

[0281] (37);

[0282] in, The three components are the velocities in the R, A and E directions, and the last two components are the azimuthal velocities and pitch angular velocity .

[0283] Step 5, establish a model solving algorithm: Considering the nonlinear constraints and simulation calculation process of the above model, use the evolutionary computing method to solve the problem, decouple the problem, and adopt a heuristic algorithm.

[0284] The evolutionary algorithm is combined with the heuristic algorithm to solve the joint optimization model of measurement and control equipment task scheduling and path planning. The parameters of the evolutionary algorithm are set as follows:

[0285] Population size: 100

[0286] Iterations: 400

[0287] Crossover mutation probability: 0.6, 0.05.

[0288] Considering the nonlinear constraints and simulation calculation process in the above model, this application considers using evolutionary computation methods to solve the problem. At the same time, considering the separable nature of the problem, this application decouples the problem into a main problem and sub-problems. When evaluating the index value of the main problem solution, it is necessary to obtain the optimal solution of the sub-problem. In order to quickly obtain the optimal solution of the sub-problem, this application proposes a rule-based heuristic algorithm.

[0289] S1 problem decoupling:

[0290] Complex combinatorial optimization problems, such as task scheduling and path planning for measurement and control equipment, often involve multiple, interrelated decision-making levels. Directly solving these problems as a whole not only incurs significant computational overhead but can also make it difficult to find a globally optimal solution. To address this challenge, this application employs a problem decoupling strategy.

[0291] (1) Evolutionary computation and decoupling strategy

[0292] Considering the nonlinear constraints and simulation computations involved in the model, evolutionary computation methods are the preferred choice due to their powerful global search capabilities and ability to handle nonlinear problems. Evolutionary algorithms are particularly advantageous in scenarios with numerous constraints and multi-objective optimization. Based on the characteristics of the problem, this application divides the problem into a main problem and sub-problems.

[0293] (2) Definition and relationship between master and sub-problems

[0294] Main problem: Focuses on task scheduling of measurement and control equipment, with the goal of maximizing comprehensive evaluation indicators, such as effective coverage and balance of tasks;

[0295] Subproblem: Focuses on device path planning to determine how the device should maneuver to meet mission requirements. Although the decision space is relatively small, multiple constraints must be met, such as interactions between devices and energy constraints.

[0296] In order to solve the subproblems efficiently, refer to Figure 1 This application proposes a rule-based heuristic algorithm that can quickly find optimal paths that satisfy constraints. Once the solution to a subproblem is determined, it can provide feedback on the main problem, helping the evolutionary algorithm to better optimize task scheduling.

[0297] (3) Advantages of decoupling

[0298] Simplify computation: By breaking down complex problems into smaller, more manageable parts, each sub-problem can be solved more focused and efficiently;

[0299] Enhanced flexibility: We can independently adjust and optimize the solution strategies for the main problem and sub-problems for different scenarios and needs;

[0300] Improved solution quality: Decoupling allows us to select the most appropriate algorithm for each subproblem, leading to better solutions overall.

[0301] Through the decoupling strategy, this application not only improves the efficiency of problem solving, but also ensures the quality of understanding, laying a solid foundation for subsequent practical applications.

[0302] S2: Solving the measurement and control equipment task scheduling problem based on knowledge-guided constrained evolutionary algorithm

[0303] Evolutionary computation is a simulation of natural selection mechanisms that can effectively handle large-scale, multi-objective, and highly nonlinear optimization problems. Its main advantages can be summarized as follows: 1. Global search capability. Evolutionary computation possesses powerful global search capabilities, allowing it to search extensively across the solution space, thereby increasing the chances of finding the global optimal solution. 2. Parallelism. Multiple solutions can evolve simultaneously, leveraging the power of the swarm to explore multiple possible solution paths. 3. Adaptability. Through natural selection and genetic manipulation, evolutionary computation can adaptively adjust its search strategy to better suit the characteristics of the problem. 4. Problem-specific independence. It does not require much prior knowledge of the specific form of the problem, making it widely applicable.

[0304] This application proposes a knowledge-guided constrained evolutionary algorithm to solve the measurement and control equipment task scheduling problem. The following will introduce the various components in detail.

[0305] (1) Knowledge guidance mechanism

[0306] Traditional evolutionary algorithms typically use random crossover and mutation operators to explore the decision space. This randomness often leads to solutions without a clear direction when solving complex problems. This means that the quality of the solution may be negatively affected due to the lack of guiding information to guide the search process.

[0307] To address this issue, this application introduces a knowledge-guided approach, which differs from traditional evolutionary algorithms in two key ways: First, this application extracts valuable knowledge from the solution, which can provide insights for evaluating and improving the quality of the solution. The introduction of this knowledge helps improve the quality of the solution and makes the algorithm more targeted. Second, this application proposes a feasible rule-based approach and incorporates this knowledge to formulate an environment selection strategy. This means that we not only focus on the quality of the solution, but also consider the feasibility of the solution, so as to better meet the constraints of the problem.

[0308] Figure 2 This is a schematic diagram of the knowledge guidance method proposed in this application, where the dots represent individuals in the iterative search process using an evolutionary algorithm. Generally, when an evolutionary algorithm generates new individuals through crossover and mutation, its direction is random, such as Figure 2 As shown in point E in . Although point E may exchange genes with high-quality individuals in the current population, such exchanges are often inefficient. Especially when the decision space is complex and the feasible domain is narrow, individuals in the population may conduct aimless searches in the infeasible domain, resulting in a huge waste of computing resources. For the joint optimization problem of task scheduling and path planning of measurement and control equipment studied in this application, since the equipment needs to consider the maximum continuous working time, movement time limit, etc., the feasible domain of the problem becomes narrower, which makes it difficult for evolutionary algorithms to obtain feasible solutions when solving such problems.

[0309] The knowledge guidance method proposed in this application aims to guide the generation and selection of solutions by extracting the conflict information between the current individual tasks. Specifically, the number and location of the measurement and control task conflicts of the current individual are first recorded. The number of conflicts can be regarded as the distance between the current individual and the feasible domain, while the conflict location indicates the search direction. When selecting a solution, individuals with fewer conflicts are preferred, such as Figure 2 Points D and C in the figure. During crossover and mutation operations, the probability of crossover and mutation at conflicting locations is increased, but to avoid falling into local optima, operations are avoided directly at conflicting locations. This strategy guides the search for solutions closer to the feasible region, significantly improving algorithm efficiency.

[0310] The primary challenge for this application is conflicts among measurement and control equipment. Because these equipment is subject to constraints on maximum operating duration and arrival time, the goal is to minimize the number of devices that fail these constraints. In this application, conflicts are marked using a pair of data: <(i, j, k)> indicates that, in the i-th coverage measurement, the measurement and control equipment for arc segment k of aircraft j fails to meet the constraints. This conflict information is passed to the crossover and mutation operators to guide the evolution of these conflicts, thereby improving the solution quality and enhancing algorithm performance.

[0311] (2) Coding mechanism

[0312] In view of the characteristics of the task scheduling problem of measurement and control equipment, in order to fully represent the information of individuals, this application adopts a two-layer coding method, namely main coding and double covering coding, such as Figure 3 shown.

[0313] Specifically, we first need to calculate the matching combination of "aircraft-arc-measurement and control point-measurement and control equipment", Figure 3 As can be seen in the figure, each variable in the two-dimensional matrix records an integer value, which represents the index value of the combination of "measurement and control point position-measurement and control equipment" that can provide observations under the aircraft and arc segment. For example, the combination that can be selected for the first arc segment of aircraft M1 is:<C57,L2><C50,L10><C50,L11><C50,L12><C50,L13> , then the first arc of spacecraft M1 will be observed by the fifth combination, namely C50 and L13. Similarly, for double coverage coding, the observation task will also be carried out by the combination selected.

[0314] (3) Knowledge-guided crossover mutation operator

[0315] In evolutionary algorithms, crossover and mutation are two core genetic operators. Their importance lies in their combined ability to ensure both exploration and exploitation. Exploration enables the algorithm to search the entire solution space, while exploitation allows the algorithm to conduct a detailed search once it has found promising areas. Properly balancing these two capabilities is key to achieving an efficient evolutionary algorithm.

[0316] Based on the encoding method and extracted knowledge proposed in this application, a crossover mutation operator is designed, as follows: Figure 4 As shown in Figure 2, knowledge guidance guides crossover and mutation operations by increasing the probability of selecting points containing conflicting information, making future generations more likely to improve. This approach helps improve algorithm performance and enables the solution to converge faster to a higher-quality state.

[0317] (4) Environmental selection strategy based on knowledge guidance and feasibility criteria

[0318] The selection of offspring plays a vital role in evolutionary algorithms, which directly affects the convergence speed and search efficiency of the algorithm. In this algorithm, a knowledge-guided selection method is proposed to more comprehensively evaluate the quality of offspring. In the evolutionary process, evaluating the quality of the solution only from the dimension of individual fitness may lead to the elimination of some offspring with the potential to achieve the optimal solution. In addition, the existence of constraints makes it more difficult for the algorithm to obtain the optimal solution. Therefore, this application adopts the feasibility criterion to deal with the constraints and proposes an environmental selection strategy based on knowledge guidance and feasibility criteria. Among them, the feasibility criterion can be described as follows:

[0319] First compare the feasibility of the solutions: a feasible solution is always considered better than an infeasible solution;

[0320] If both solutions are feasible, they are compared based on the value of the objective function;

[0321] If two solutions are both infeasible, they can be compared based on the degree to which they violate the constraints.

[0322] First, consider the degree of constraint violation and fitness of the individuals. When there are differences in fitness between individuals, we give priority to solutions with larger fitness values, because these solutions are usually closer to the optimal solution. However, in some cases, the fitness values between individuals may be very close or equal, and then a more refined evaluation criterion needs to be introduced. Therefore, we also consider the number of conflicts within the individual as a second criterion. Generally speaking, individuals with fewer conflicts have more potential to approach the optimal solution because they may have more feasible task combinations. Therefore, when there is no difference in fitness, individuals with fewer conflicts are given priority. This selection strategy helps to accelerate the convergence of the algorithm and guide the search process in a more promising direction.

[0323] S3: Rule-based heuristic algorithm for solving measurement and control equipment path planning problems

[0324] When the aforementioned evolutionary algorithm solves the main problem, evaluating the fitness of the solution requires solving the maneuvering path of each device to meet the constraints of the device's maximum continuous working time and the time constraint of reaching the working point. Maneuvering path planning can be regarded as an optimization problem. Therefore, after decoupling the problem, this application designs a heuristic algorithm to calculate the optimal device maneuvering route under a given measurement and control equipment scheduling scheme, thereby providing services for the optimization of the main problem, as shown in Table 2. In layman's terms, this method can also be regarded as a decoding algorithm for the encoding scheme.

[0325] Table 2 Rule-based heuristic algorithms

[0326] ;

[0327] S1: Calculate the distance of each aircraft to each measurement and control point during flight based on the input information ( ), azimuth ( )、Pitch angle( ), azimuth velocity ( ), pitch angular velocity ( );

[0328] S2: Based on the above information and other constraints (such as equipment type constraints, point level constraints, etc.), filter out each arc segment in each task A set of solutions that can be measured and controlled ,Right now , each solution set There may be multiple alternative location and equipment combinations.

[0329] S3: Iterate each solution of each arc segment in each task:

[0330] S4: Calculate and detect arc segments In the corresponding combination solution set, whether the device can arrive before the mission start time; if not, the coverage rate of the arc segment is 0; the number of conflicts is +1; if it exists, determine whether it needs to be moved. If the device does not need to move, calculate the coverage rate of the arc segment. If it needs to move, the device needs to maneuver to another location to perform the measurement and control mission, and implement maneuvering and replenishment operations according to the preset rules to calculate the coverage rate of the arc segment;

[0331] S5: If double coverage is required, repeat step S4;

[0332] S6 calculates comprehensive evaluation indicators: effective coverage and balance.

[0333] Table 3 Equipment Supply and Maneuvering Rules

[0334]

[0335] (1) Algorithm Overview

[0336] As shown in Table 2, the algorithm first traverses all missions and all arcs in the order of mission launch times. For the current arc, it first checks whether the device can reach the scheduled measurement and control point within the mission period (if it cannot arrive on time, this information is recorded as "knowledge"). Secondly, it checks whether resupply is required according to the rules and provides a resupply maneuver plan. If resupply is unsuccessful, the device's maximum operating time has been exceeded, the plan does not meet the constraints, and this information is recorded as "knowledge."

[0337] (2) Equipment Supply and Maneuvering Rules

[0338] The device's maneuvers during a mission can be categorized based on the nature of its departure and arrival points. This categorization can be seen in Table 3. To prevent the device from exceeding its maximum operating time, this application adopts two strategies. Strategy 1: When the device reaches a resupply point, it performs a resupply operation. Strategy 2: If the device requires resupply en route, it selects the nearest resupply point for this operation.

[0339] The following is a description of the specific maneuvers:

[0340] 1. When both the starting point and the target point are resupply points: The device can directly reach the target point from the starting point, as the maximum maneuvering time between the two points is less than the device's maximum continuous operating time. Upon arrival, the device will resupply at the target point.

[0341] 2. When the starting point is a refueling point, but the target point is not: the device can directly reach the target point from the starting point. However, since the target point is not a refueling point, the device does not need to be refueled after arriving;

[0342] 3. When the starting point is not a refueling point, but the target point is: In this case, it is necessary to first determine whether the device will exceed its maximum continuous operating time before reaching the target point (refueling point). If not, the device can go directly there and refuel there. However, if it will time out, the device needs to choose the nearest refueling point along the way for refueling. In addition, it is necessary to determine whether the device can still reach the target point in time to complete the task after refueling midway. If so, the device will refuel at both the nearest refueling point and the target point. If not, then the solution will violate the constraints and become infeasible;

[0343] 4. When neither the starting point nor the destination is a refueling point: Since neither point is a refueling point, the device must refuel en route to ensure that the maximum operating time is not exceeded. Similarly, we must determine whether the device can still reach the destination in time to complete the mission after refueling en route. If so, the device will refuel at the nearest refueling point. If not, the solution violates the constraints and becomes infeasible.

[0344] For all possible combinations, ignoring equipment maneuvering options, there are a total of 5.1005e+76 measurement and control scenarios. If 10,000 scenarios can be calculated per second, it would take 1.6174e+65 years to complete all evaluations. Therefore, designing a well-designed and powerful optimization algorithm is crucial.

[0345] Table 4 Maximum measurement and control coverage under different aircraft-arc segments

[0346]

[0347] The beneficial effects of this application are as follows:

[0348] This application addresses the task scheduling and path planning issues for measurement and control equipment and constructs a joint optimization model for task scheduling and path planning based on maximizing task completion. This model fully considers the practical context and various constraints of the problem, ensuring its integrity and practicality.

[0349] By decoupling the model, the model is divided into a main problem and sub-problems, making the problem-solving process clearer and more operational. The algorithm design combines the global optimization properties of evolutionary algorithms with the local search properties of heuristic algorithms, aiming to find high-quality solutions to the problem.

[0350] The proposed knowledge-guided evolutionary algorithm is able to find high-quality solutions globally, while the rule-based heuristic algorithm ensures the quality of the solutions locally. The combination of the two provides an efficient and practical solution to the task scheduling and path planning problems of measurement and control equipment.

[0351] As used herein, the word "preferred" is intended to serve as an example, instance, or illustration. Any aspect or design described herein as "preferred" is not necessarily to be construed as advantageous over other aspects or designs. Rather, the use of the word "preferred" is intended to present concepts in a concrete manner. As used in this application, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean any of the naturally inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then "X employs A or B" is satisfied in any of the foregoing examples.

[0352] Moreover, although the present disclosure has been shown and described with respect to one or implementation, those skilled in the art will think of equivalent variations and modifications based on reading and understanding of this specification and the accompanying drawings. The present disclosure includes all such modifications and variations and is limited only by the scope of the appended claims. In particular, with respect to the various functions performed by the above-mentioned components (such as elements, etc.), the terms used to describe such components are intended to correspond to any component (unless otherwise indicated) that performs the specified function of the component (such as it is functionally equivalent), even if structurally different from the disclosed structure that performs the function in the exemplary implementation of the present disclosure shown herein. In addition, although the specific features of the present disclosure have been disclosed with respect to only one of several implementations, such features can be combined with one or other features of other implementations that can be desired and advantageous for a given or specific application. Moreover, insofar as the terms "including", "having", "containing" or their variations are used in specific embodiments or claims, such terms are intended to be included in a manner similar to the term "comprising".

[0353] The functional units in the embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or multiple or more units may be integrated into a single module. The aforementioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc. The aforementioned devices or systems may execute the storage method in the corresponding method embodiment.

[0354] In summary, the above embodiment is one implementation method of the present invention, but the implementation method of the present invention is not limited to the described embodiment. Any other changes, modifications, substitutions, combinations, and simplifications that deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the scope of protection of the present invention.

Claims

1. A knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling, characterized in that: The following steps are involved: Step 1, model construction: Based on the task scheduling and path planning of measurement and control equipment to maximize task completion, a joint optimization model is constructed that meets various constraints and maximizes comprehensive evaluation indicators; Step 2: Introduce decision variables: From the perspective of finding a combination of measurement and control points and equipment, introduce decision variables that can represent the combination and maneuver options. Step 3, optimization goal: Consider the two aspects of effective coverage and balance, and then maximize the comprehensive evaluation test effect. The optimization goal is to maximize the comprehensive evaluation index ; Step 4: Analyze constraints: Consider measurement and control operation constraints, measurement and control equipment requirement constraints, measurement and control equipment performance constraints, and calculate measurement and control performance parameters; Step 5: Establish a model-solving algorithm: Use a knowledge-guided evolutionary optimization method to solve the model. The knowledge-guided evolutionary optimization method includes: extracting conflict information between current individual tasks to guide solution generation and selection; using a two-layer encoding mechanism for encoding; using a crossover mutation operator to increase the probability of selecting points containing conflict information; using a feasibility criterion to handle constraints, using an environment selection strategy based on knowledge guidance and feasibility criteria; and solving the measurement and control equipment path planning problem using a rule-based heuristic algorithm. Among them, the optimization goal is to maximize the comprehensive evaluation index : ； Comprehensive evaluation indicators The calculation formula is: ； Comprehensive evaluation indicators Effective coverage for tasks and balance The weighted average of Effective coverage of tasks The calculation process is as follows: A single task consists of several arcs, which are divided into key arcs and regular arcs; The effective coverage of the key arc is defined as: ； Among them, the key arc For the Task No. arc segments, for The effective coverage of For arc segments duration, for The actual tracking time; The effective coverage of a conventional arc segment is defined as: ； Among them, the conventional arc For the Task No. arc segments, for The effective coverage of For arc segments duration, for The actual tracking time; Set up the first The tasks are arcs, the effective coverage of the task is: ； in, for Task No. The weight of each arc segment; arc segments of different types of equipment should be calculated separately; tasks, the total effective coverage of tasks is: ； Balance The calculation formula is: ； Where, is the total duration of the planning cycle, is the total number of mobile equipment, t j For the The total working time of a mobile equipment in the entire planning cycle refers to the total duration of the planning cycle minus the supply time; mobile equipment that has not been mobilized in the entire planning cycle is not included in the calculation of balance.

2. The knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling according to claim 1, characterized in that: Accurately classify and simplify various constraints, including task matching constraints and equipment working and maneuvering time constraints. Based on the specific constraints of each measurement and control equipment, pre-calculate all possible matching combinations of "aircraft-arc-measurement and control point-measurement and control equipment". Based on the measurement and control equipment task scheduling and path planning that maximizes mission completion, construct a joint optimization model that meets various constraints and maximizes comprehensive evaluation indicators.

3. The knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling according to claim 1, characterized in that: The decision variables include: : 0-1 variable, if the Task No. Arc segment by device 1 if measurement and control is enabled, otherwise 0; : 0-1 variable, if the device Should be deployed to the point Measurement and control tasks is 1, otherwise 0; : 0-1 variable, if the device Need to Move to the corresponding measurement and control point to complete the task is 1, otherwise 0; : 0-1 variable, if the device From the measurement and control point Maneuver to the measurement and control point is 1, otherwise 0; :The equipment is located at the measurement and control point To the measurement and control point maneuvering time; :equipment From the measurement and control point Maneuver to the measurement and control point Time of departure; :equipment No. The time it takes to reach the supply point.

4. The knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling according to claim 3, characterized in that: The various constraints include: Device task constraints: ； Where, Is a 0-1 variable, indicating that if Task No. The arc segment is controlled by the measurement and control equipment 1 if measurement and control is enabled, otherwise 0; this constraint ensures that each device can only be assigned to one time arc of a task at a time; Equipment point constraints: ； Where, Is a 0-1 variable, indicating if the measurement and control equipment Assign to point To complete the task is 1, otherwise it is 0; this constraint ensures that each device can only be assigned to one point at the same time; Device time constraints: ； Where, Is a 0-1 variable, indicating if the measurement and control equipment Need to Move to the corresponding measurement and control point to complete the task 1, otherwise 0; this constraint ensures that each device can only measure and control one task at most per day; Time point constraints: ； This constraint ensures the time and location relationship between the equipment's execution of the measurement and control task. If the equipment is to execute the measurement and control task, both the time and location are determined at the same time. Equipment mobility constraints: ； Where, Is a 0-1 variable, indicating that if the device From the measurement and control point Maneuver to the measurement and control point 1 if it is set to 0, otherwise it is 0; these two constraints ensure that each device can only maneuver from one position to another, and this position cannot be the current position of the device; Time constraints for measurement and control equipment to reach measurement and control points: ； Where, Indicates a task The launch date of the spacecraft, Indicates a task This constraint ensures that the equipment participating in the task must be Arrive at the corresponding measurement and control point before 24:00 on the day; Time constraints for the measurement and control equipment to leave the measurement and control point after completing the task: ； Where, Representation device From the measurement and control point Maneuver to the measurement and control point Departure time; this constraint ensures that the equipment participating in the task must be You can leave after 24:00 on the day; Maximum continuous working time constraints: ； Where, Representation device No. Time to reach the supply point, Representation device The maximum continuous working time of the motorized equipment is guaranteed by this constraint. The time from the last time a person leaves the supply point to the next time they arrive at the supply point for replenishment shall not exceed the maximum continuous working time; Maneuver time constraints: Use Floyd's algorithm to solve the problem of using the position of the measurement and control points arrive The shortest path from Point to Maneuvering time of point The sum of the travel time of each road segment in its shortest path; Type and frequency band constraints: ； Where, Indicates the Task No. The type of measurement and control equipment required for each arc segment, Representation device This constraint ensures that each arc in each task The required measurement and control equipment must be of the required type, and if the required equipment type is telemetry, it must further meet the frequency band requirements: ； Where, Indicates the Task No. The frequency band required by each arc segment, Representation device This constraint ensures that the telemetry equipment can only complete the mission if it has the receiving function of the same frequency band as the measurement and control aircraft. "Characteristic measurement" requirements constraints: ； Where, Indicates the Task No. Arc segments Other measurement and control requirements: 0 means "none", 1 means "characteristic measurement", 2 means "double coverage", and 3 means "telemetry and security control"; A 0-1 variable representing the device Whether it has the characteristic measurement function, 1 if it does, 0 otherwise. This constraint ensures that if there is a "characteristic measurement" requirement, then the radar equipment measuring and controlling this arc segment must have the characteristic measurement function; "Double coverage" requirement constraints: ； Where, The actual tracking time of the device. The duration of joint tracking by multiple similar devices. This constraint ensures that if "double coverage" is required, the tracking duration of this arc segment is the period of joint tracking by two or more similar devices. "Telemetry and security control" requirements and constraints: ； Where, A 0-1 variable representing the device Whether it has security control function, 1 if it has, 0 otherwise. This constraint ensures that if there is a "telemetry and security control" requirement, then this arc segment is a key arc segment, and the telemetry equipment used to measure and control this arc segment must have security control function. Measurement and control point level constraints: ； Where, For measurement and control points level, For equipment The minimum point level required; The distance R of the target relative to the device is constrained: ； Where, For the Task No. The first arc The position relative to the device at that moment distance, For equipment The device will track and measure the target only when the distance between the target and the device is within the device's range. Azimuth angle A of the target relative to the device: ； Where, For the Task No. The first arc Position relative to the device at that moment The azimuth of 、 For equipment The azimuth angle of the target is within the working range of the device. The device will track and measure the target at that moment. The target's pitch angle E and shielding angle SA constraints relative to the device are: ； Where, For the Task No. The first arc Position relative to the device at that moment The pitch angle, 、 For equipment The lower and upper limits of the pitch angle working, For measurement and control points When the device is observing a target, the pitch angle is required to be within the working range of the device's pitch angle indicator and greater than the shielding angle of the point; VA constraint of the target's relative azimuth velocity: ； Where, For the Task No. The first arc The position change relative to the device at a moment and its previous moment The azimuthal velocity, For equipment The device will track and measure the target only when the target's azimuth velocity relative to the device is within the device's operating range. The target's pitch angular velocity VE constraint relative to the device: ； Where, For the Task No. The first arc The position change relative to the device at a moment and its previous moment The pitch angular velocity, For equipment The device will track and measure the target only when the target's pitch angular velocity relative to the device is within the device's operating range.

5. The knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling according to claim 4, characterized in that: The measurement and control performance parameters are calculated as follows: The coordinates of the measurement and control equipment in the geocentric rectangular coordinate system are ( , , ), the coordinates in the geodetic coordinate system are ( , , ), coordinate point in geocentric rectangular coordinate system ( , , ), coordinates in the rectangular coordinate system of the measuring station ( , , )have: ； From the station rectangular coordinate system coordinates ( , , ) The formula for the coordinates of the RAE coordinate system of the transfer station is: ； ； The velocity in the geocentric rectangular coordinate system ( , , ) is converted into the velocity in the RAE coordinate system of the measuring station. First, the position vector of the target point relative to the measuring station is determined. , then, calculate The RAE coordinate system is obtained by using the three orthogonal unit vectors R, A, and E; specifically: Calculate the position vector : ； Calculate the orthogonal unit vectors of R, A, and E: ； in, The three components are the velocities in the R, A and E directions, and the last two components are the azimuthal velocities and pitch angular velocity .

6. The knowledge-guided evolutionary optimization method for aircraft measurement and control equipment resource scheduling according to claim 5, characterized in that: In the knowledge-guided evolutionary optimization method, the generation and selection of solutions are guided by extracting conflict information between current individual tasks, including: extracting valuable knowledge from the solutions, which provides insights into the evaluation and improvement of the solution quality; secondly, using a feasible rule-based method and combining this knowledge to formulate an environment selection strategy; Specifically, the number and location of the current individual's measurement and control task conflicts are first recorded. The number of conflicts can be regarded as the distance between the current individual and the feasible domain, while the location of the conflicts indicates the search direction. When selecting solutions, individuals with fewer conflicts are preferred. In crossover and mutation operations, the crossover and mutation probability of the conflicting locations is increased, but to avoid falling into local optimality, operations are avoided directly at the conflicting locations. This strategy guides the search for solutions closer to the feasible domain. To minimize the number of devices that do not meet the constraints, a pair of data is used to mark conflicts. That is, <(i, j, k)> indicates that in the i-th coverage measurement, the measurement and control equipment of the j-th arc segment k of the aircraft cannot meet the constraints. This conflict information is passed to the crossover and mutation operators to guide the evolution of these conflicts. The two-layer coding consists of a primary code and a double-cover code. Specifically, a matching combination of "aircraft-arc-T&C point-T&C equipment" is first calculated. The primary code records an integer value for each variable in the two-dimensional matrix, representing the index value of the "T&C point-T&C equipment" combination that can provide observations for that aircraft and arc. For the double-cover code, the selected "aircraft-arc-T&C point-T&C equipment" combination performs the observation task. The feasibility criteria are: First compare the feasibility of the solutions: a feasible solution is always better than an infeasible solution; If both solutions are feasible, they are compared based on the value of the objective function; If both solutions are infeasible, they are compared based on the degree of constraint violation; Specifically, the constraint violation degree and fitness value of the individual are considered first. When there are differences in fitness values between individuals, the solution with a larger fitness value is preferred. The number of conflicts within the individual is used as the second criterion. When there is no difference in fitness values, the individual with fewer conflicts is preferred. The rule-based heuristic algorithm for solving the measurement and control equipment path planning problem includes the following steps: S51: Calculate the distance between each aircraft and each measurement and control point during flight based on the input information , azimuth , pitch angle , azimuth velocity , pitch angular velocity ; S52: Based on the above information and other constraints, filter out each arc segment in each task A set of solutions that can be measured and controlled ,Right now ; S53: Iterate each solution of each arc segment in each task: S54: Calculate and detect arc segments In the corresponding combination plan set, whether the equipment can arrive before the mission start time; if not, the coverage rate of the arc segment is 0; the number of conflicts is increased by 1; if it exists, determine whether it needs to be moved. If the equipment does not need to be moved, calculate the coverage rate of the arc segment. If it needs to be moved, the equipment needs to maneuver to another location to perform the measurement and control mission. According to the preset equipment supply and maneuvering rules, the maneuvering and supply operations are carried out, and the coverage rate of the arc segment is calculated; S55: If double coverage is required, repeat step S4; S56 calculates comprehensive evaluation indicators: effective coverage and balance; The equipment supply and maneuvering rules include: When both the starting point and the target point are replenishment points: the device directly travels from the starting point to the target point, because the longest maneuvering time between the two points is less than the maximum continuous working time of the device. After arriving, the device is replenished at the target point. When the starting point is a replenishment point, but the target point is not: the device goes directly from the starting point to the target point; however, since the target point is not a replenishment point, the device does not recharge after arriving. When the starting point is not a refueling point, but the target point is a refueling point: First, determine whether the device will exceed its maximum continuous operating time before reaching the target point. If not, the device will go directly there and refuel there. If it exceeds the time limit, the device will refuel at the nearest refueling point along the way. In addition, determine whether the device can still reach the target point in time to complete the task after refueling. If so, the device will refuel at both the nearest refueling point and the target point. If not, the solution violates the constraints and becomes infeasible. When neither the starting point nor the target point is a resupply point: Since neither point is a resupply point, the device must be resupplyed en route to ensure that the maximum working time is not exceeded; it is also necessary to determine whether the device can still reach the target point in time to complete the task after the mid-way resupply. If so, the device will be resupplyed en route at the nearest resupply point. If not, then this plan will violate the constraints and become infeasible.

Images