System Integration

Abstract

A computer-implemented method for generating a feasibility indication indicative of the feasibility of a weapon carried on an aircraft in flight to successfully engage a target and / or the feasibility of a weapon carried on the target to successfully engage the aircraft, the method comprising: providing a database describing a performance envelope of the weapon; a) generating candidate polynomials, the polynomial variables being some or all of a group of weapon or aircraft firing condition parameters; and b) for each candidate polynomial, comparing the candidate polynomial to the performance envelope of the weapon using a least squares error criterion. calculating coefficients for the candidate polynomial that best fits the characteristics of the line; c) for each candidate polynomial, generating a candidate score according to the quality of the candidate polynomial's fit to the characteristics of the weapon's performance envelope; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomial and its coefficients; and e) repeating the identification process until all required characteristics of the performance envelope have a corresponding polynomial model. d) a method for generating coefficients characteristic of a performance envelope using a generic algorithm, wherein the generic algorithm has the form of a polynomial, uploading coefficients of the identified best candidate polynomial to the aircraft, selecting coefficients for the generic algorithm according to aircraft and target conditions by a reconfigurator on the aircraft containing the same generic algorithm, and generating a feasibility indication by the reconfigurator using the selected coefficients, the method comprising: i) defining a set of orders and / or types of candidate polynomials and dividing the defined set of orders and / or types into a plurality of subsets thereof; ii) iteratively applying the genetic algorithm simultaneously across a plurality of subsets of the defined set of orders and / or types of candidate polynomials, including iteratively applying the genetic algorithm across polynomial variables for each order and / or type of each subset of polynomials and saving the resulting respective coefficients and their scores;iii) using the saved coefficients and scores to select the best scoring polynomial(s) and discard other polynomial(s), thereby identifying the best candidate polynomials and their coefficients.

Description

[Technical Field]

[0001] This invention relates to systems integration, and more particularly to the integration of weapons on complex, highly integrated aircraft. [Background technology]

[0002] Integrating weapons systems with other systems on an aircraft is a complex and lengthy task because it affects all major aircraft systems. Therefore, there is a need to improve weapon integration time and affordability.

[0003] One of the requirements for weapons integration is that weapons must be targeted to a specific target. Successfully engage in combat The objective of the system is to enable the aircraft pilot to display information about whether or not a target is capable of being engaged. For this purpose, weapons are usually grouped into two categories: those designed to engage targets on the ground (air-to-ground weapons) and those designed to engage targets in the air (air-to-air weapons). In the case of air-to-ground weapons, the selected target and Successfully engage in combat A Launch Acceptability Region (LAR) is calculated, which is the area where the probability of a target being hit or hitting the target exceeds some threshold. Successfully engage in combat It is calculated to provide a cockpit display of feasibility in the launching aircraft and is a function of weapon performance characteristics, the relative positions and motions of the aircraft and target, and often ambient conditions such as wind speed and direction.

[0004] For air-to-air weapons, the selected air target and Successfully engage in combat A Launch Success Zone (LSZ) is calculated that indicates the probability that the weapon will be successful in reaching the target. Successfully engage in combat However, calculating the LSZ is more complex than calculating the LAR because the relative speeds and directions of the launching aircraft and target's progress are much greater, the influence of ambient conditions is greater, and the physical characteristics of the weapon in flight are also more important to the calculation.

[0005] The traditional approach has been to create a simple, abstract model of the weapon that is modified according to launch conditions (taking into account aircraft and target conditions (e.g., range, direction, and speed of travel, etc.) and ambient conditions). The model is used onboard the aircraft to generate a LAR or LSZ for display to the pilot. A drawback of the traditional approach is that each model is different for each different weapon type. Storing data for several different implicit models consumes significant storage capacity, and each model must be comprehensively integrated to ensure there are no adverse effects on any of the aircraft systems. Furthermore, if any changes or modifications are made to the weapon (such as performance improvements), or if an entirely new weapon needs to be loaded onto the aircraft, a lengthy and costly integration process must be undertaken because the weapon model is substantially different from anything previously integrated with the aircraft systems. Summary of the Invention

[0006] According to a first aspect of the present invention, a method is provided for detecting a target in an aircraft in flight, the target being a weapon carried on the aircraft. Successfully engage in combat Feasibility and / or the weaponry delivered on the target is compatible with aircraft Successfully engage in combat A computer-implemented method for generating a feasibility display indicative of feasibility is provided, the method comprising: providing a database describing the weapon's performance envelope; a) generating a candidate polynomial, wherein the polynomial variables are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculating coefficients for that candidate polynomial that best fit the candidate polynomial to the characteristics of the weapon's performance envelope using a least squares error criterion; c) generating a candidate score for each candidate polynomial according to the quality of the candidate polynomial's fit to the characteristics of the weapon's performance envelope; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best-scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; e) repeating the identification process until all desired characteristics of the performance envelope have corresponding polynomial models; generating coefficient characteristics of said performance envelope using a general algorithm by steps including: uploading the identified best candidate polynomial coefficients to the aircraft; selecting coefficients for the general algorithm according to aircraft and target conditions by an on-board reconstructor containing the same general algorithm; generating, by a reconstructor, a feasibility representation using the selected coefficients; wherein step d) of applying a genetic algorithm to the candidate polynomials and scores comprises: i) defining a set of orders and / or types of candidate polynomials and dividing the defined set of orders and / or types into a plurality of subsets thereof; ii) iteratively applying a genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials, and calculating the resulting coefficients and their scores. keep iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types, including: iii) keep using the determined coefficients and scores to select the best-scoring polynomial(s) and discard the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; The present invention is characterized by comprising:

[0007] In this way, the method significantly improves weapon integration time and cost. More specifically, genetic algorithms typically proceed iteratively by generating a population of new strings from a population of old strings. Every string is a coded version of a tentative solution. An evaluation function associates a fitness measure with every string, indicating its suitability for the problem. The algorithm applies probabilistic operators, such as selection, crossover, and mutation, to an initially random population to calculate the entire generation of new strings. The inventors have determined that these algorithms can be adapted for use on multiple processor workstations or distributed systems with transparent process migration. All fitness evaluations and adaptation operations can be performed in separate processes, i.e., simultaneously. For trivial fitness functions, due to the level of overhead, improvements in the speed of evolution are unlikely to be observed. However, for weapon targeting and many tasks on a given system, this is clearly time-consuming and reflects the ad-hoc nature of the solution process. The accuracy of the adaptation depends on the complexity of the performance envelope. To accurately represent the performance envelope and achieve the required accuracy for the entire envelope or a subset thereof, a large data set may be required. As the data size increases, the amount of computation and processing time increases. The advantage of performing goodness-of-fit evaluation in parallel is significant.

[0008] To apply a genetic algorithm to a specific application, an internal representation of the space to be explored is chosen and an external function is defined that assigns fitness values ​​to candidate solutions. The inventors have adapted the genetic algorithm to parallelize across many polynomial orders (also known as degrees) and input parameters that the genetic algorithm must run. Each run tests several parameter combinations of polynomial order and input, and reports the run time, memory, and flop operations for the final model requirements to solve the problem for each parameter combination, as described in more detail below.

[0009] The method can be used for different weapon types, and a respective set of coefficients can be readily determined for each weapon type, for example, for each of a plurality of different firing conditions (i.e., aircraft and target conditions). Aircraft and target conditions can include, but are not limited to, one or more of their relative positions, distances, direction of movement, speeds, and ambient atmospheric conditions. Weapon or aircraft firing condition parameters can include, but are not limited to, parameters such as aircraft speed, aircraft height, aircraft attitude, slant range to the target, target speed, target height, line of sight azimuth, target pitch and aspect angle, and wind speed. Weapon or aircraft firing condition parameters can include, but are not limited to, the relative speed and direction of travel of the launching aircraft and target, and the relative speed and direction of travel of the weapon relative to the target.

[0010] Advantageously, the general polynomial / algorithm described above can be used by multiple different types of aircraft (e.g., simultaneously). In other words, different types of aircraft can use the same general algorithm to calculate the LAR / LSZ. Also, the same general algorithm can be used to calculate the LAR / LSZ of different weapon types. Thus, aircraft software comprising the general polynomial and means for enabling coefficients to be loaded for each weapon carried on the aircraft is created only once. The software algorithm and coefficients for any given weapon are the same for every aircraft type. This tends to differ from traditional methods in which, although common tools may be used for polynomial and coefficient generation, both the software (including the algorithm / polynomial) and the coefficients are generated for each weapon type and each time weapon performance is changed. This need to rewrite the software and its certification tends to be particularly costly. The methods and systems described above tend to advantageously provide that aircraft software does not need to be rewritten, and therefore new certification is not required.

[0011] In some embodiments, each aircraft in a fleet of different aircraft is loaded with the same common general polynomial. When a weapon is loaded onto an aircraft in the fleet, the specific coefficients corresponding to that weapon may also be loaded onto that aircraft. This tends to contrast with traditional systems where the tools for generating the LAR / LSZ may be common across different aircraft, but when a weapon is loaded onto an aircraft, both the polynomial / algorithm for generating the LAR / LSZ and the corresponding coefficients are generated for that aircraft and weapon loading / unloading.

[0012] The coefficients can be implemented as loadable data to allow accurate and precise weapon behavior to be realized within the weapon system. Also, using only one or a few generic algorithms will allow different weapon systems to be licensed or certified / qualified for use with aircraft with reduced effort and more quickly than the extensive testing required with traditional approaches. That is, a minimum number of generic weapon targeting algorithms can be used to account for all weapon types.

[0013] The use of a common algorithm for weapon targeting also allows increases or significant changes in weapon system capabilities to be integrated with aircraft systems with significantly less effort than previously possible.

[0014] The weapons delivered on the target are aircraft and Successfully engage in combat By determining the feasibility of the aircraft being carried by a hostile target, Successfully engage in combat It indicates whether or how much of a threat there is. This calculation of opposing LSZ / MEZ allows for a better assessment of the engagement. This, in turn, can lead to a confident prediction of the benefits and likely outcomes of the engagement.

[0015] Advantageously, the above aspects provide a common polynomial / algorithm that can be used by multiple different types of aircraft (e.g., simultaneously). Different types of aircraft may use the same common algorithm to calculate the LAR / LSZ. Also, the same common algorithm may be used to calculate the LAR / LSZ for different weapon types. Thus, aircraft software with the common polynomial and means to allow coefficients for each weapon carried on the aircraft is created only once. The software algorithm and coefficients for any given weapon are the same for every aircraft type. This tends to differ from traditional methods in which, although common tools may be used for polynomial and coefficient generation, both the software (including the algorithm / polynomial) and the coefficients are generated for each weapon type and each time weapon capabilities are changed. This need to rewrite the software and its certification tends to be particularly costly. The above-described methods and systems tend to advantageously provide that aircraft software does not need to be rewritten, and therefore new certification is not required.

[0016] In one example, iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types comprises iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types on respective processors and / or different threads.

[0017] In this way, the iterative application of the genetic algorithm is enhanced at the same time as the genetic algorithm is iteratively applied on each thread and / or processor.

[0018] In one example, iteratively applying a genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials includes: selecting a combination of polynomial variables for each order and / or type of each subset of polynomials; iteratively applying a genetic algorithm over selected combinations of polynomial variables for each order and / or type of each subset of polynomials; Equipped with.

[0019] In this way, the genetic algorithm is applied iteratively over selected combinations of polynomial variables (also known as inputs), e.g., only to selected combinations of polynomial variables, thereby accelerating the method.

[0020] In one example, iteratively applying the genetic algorithm over selected combinations of polynomial variables for each order and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously over selected combinations of polynomial variables for each order and / or type of each subset of polynomials.

[0021] In this manner, the genetic algorithm is applied iteratively over selected combinations of polynomial variables for each order and / or type of each subset of polynomials simultaneously, thereby accelerating the method.

[0022] In one example, iteratively applying the genetic algorithm simultaneously over selected combinations of polynomial variables for each order and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously over selected combinations of polynomial variables for each order and / or type of each subset of polynomials on respective threads and / or processors.

[0023] In this way, the iterative application of the genetic algorithm is enhanced at the same time as the genetic algorithm is iteratively applied on each thread and / or processor.

[0024] In one example, a genetic algorithm is applied iteratively over the polynomial variables for each order and / or type of each subset of polynomials, and each resulting coefficient and its score are calculated. keep Iteratively applying a genetic algorithm simultaneously across multiple subsets of the defined set of orders and / or types of candidate polynomials, including iteratively applying a genetic algorithm across polynomial variables for each order and / or type of each subset of polynomials, and calculating the respective resulting coefficients and their scores. keep conditionally iteratively applying a genetic algorithm simultaneously across multiple subsets of a defined set of candidate polynomial orders and / or types, including:

[0025] In this manner, iterative application of the genetic algorithm simultaneously across multiple subsets of a defined set of candidate polynomial orders and / or types may be contingent upon, for example, not meeting a predetermined threshold, thereby, for example, accelerating the termination of the iterations.

[0026] In one example, conditionally iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types comprises terminating application of the genetic algorithm across polynomial variables for each order and / or type of each subset of polynomials if the respective scores are below a threshold.

[0027] In one example, the threshold is predetermined.

[0028] In one example, the method comprises determining a threshold value based on a previous score.

[0029] In this manner, application of the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials is terminated if each score does not satisfy the previous score, i.e., does not improve the fit.

[0030] In one example, the types of candidate polynomials in the set of candidate polynomials include univariate polynomials, multivariate polynomials, and modifications thereof. Other polynomial types are known.

[0031] In one example, the order of the candidate polynomials in the set of candidate polynomials is in the range of 1 to 100, preferably in the range of 2 to 25, more preferably in the range of 3 to 10, and most preferably in the range of 5 to 9, for example 5, 6, 7, 8, 9.

[0032] In one example, the general polynomial (i.e., the general algorithm has the form of a polynomial) is of the form:

[0033]

number

[0034] where: α mn represents the m coefficients required to compute output n, {x1...x Ni} represents the normalized input, {y1...y Ni} represents the output, p 1mn represents the power (exponent) of the x1 variable of the m-th term of the n-th polynomial.

[0035] In one example, the best candidate polynomial is of the form:

[0036]

number

[0037] where:

[0038]

number

[0039]

number

[0040]

number

[0041] In one example, the order of the general polynomial is 3 or greater. In one example, the order of the general polynomial is in the range of 10 to 25, e.g., 20. Surprisingly, the inventors have found that using a general algorithm having an order of approximately 20 accurately and sufficiently describes most air-to-air engagements at a reasonable runtime for implementation on an aircraft. Nevertheless, the general algorithm may have an order greater than 2.

[0042] In one example, step b) of calculating, for each candidate polynomial, coefficients for the candidate polynomial that best fit the candidate polynomial to the characteristics of the weapon's performance envelope using a least-squares error criterion comprises: 1) generating an initial population of candidate polynomials; 2) calculating, for each candidate polynomial, a set of coefficients that fit the polynomial to the performance envelope according to one or more criteria; 3) calculating, for each candidate polynomial and each set of coefficients, a score function that indicates the quality of fit of the candidate polynomial and its set of coefficients to the performance envelope; and 4) recursively applying a genetic algorithm to the set of candidate polynomials until one or more criteria are met, including retaining at least the best-scoring polynomial and discarding the other polynomial(s). In one example, the output of the retained polynomial(s) is used to provide input for creating higher-order candidate polynomials, which are layers of a self-organizing polynomial neural network. In one example, these steps are repeated for the higher-order candidate polynomials. In one example, the final result is obtained from the path that ends with the best candidate score.

[0043] In one example, the target comprises and / or is an aircraft, hi one example, the feasibility indication indicates a successful launch zone for the aircraft and / or the target.

[0044] In one example, the target comprises and / or is a ground-based target. In one example, the feasibility indication indicates an aircraft launch clearance area and / or a missile engagement zone of the target.

[0045] In one example, step b) for each candidate polynomial calculates coefficients for that candidate polynomial that best fit the candidate polynomial to the characteristics of the weapon's performance envelope using a least squares error criterion, generating an initial population of candidate polynomials; For each candidate polynomial, calculating a set of coefficients that fit that polynomial to the performance envelope according to one or more criteria (e.g., a least-squares criterion); For each candidate polynomial and each set of coefficients, calculating a score function indicative of the quality of fit of that candidate polynomial and its set of coefficients to the performance envelope; recursively applying a genetic algorithm to the set of candidate polynomials until one or more criteria are met, including retaining at least the best-scoring polynomial and discarding the other polynomial(s); Equipped with.

[0046] In one example, the output of the retained polynomial(s) is used to provide input for creating higher-order candidate polynomials, which are layers of a self-organizing polynomial neural network, which in one example are iterated until a final result with the best candidate score is obtained.

[0047] In one example, the weapon performance envelope is the performance of the weapon when implemented on an aircraft, e.g., a minimum envelope that defines the performance of the weapon. In one example, the weapon performance envelope is the respective performance of the weapon when implemented on aircraft of different aircraft types. In one example, the method comprises obtaining respective performance envelopes for one or more different aircraft types, e.g., a plurality of different aircraft types.

[0048] In one example, the method comprises determining a performance envelope using a plurality of aircraft performance envelopes, including determining a performance envelope defining the performance of all of the different aircraft types (i.e., a "maximum aircraft performance envelope"), and using the performance envelopes representing the performance of all of the different aircraft types and the weapon performance envelope to determine a performance envelope defining the performance of the weapon when implemented on each of the different aircraft types. In one example, the performance envelope is a minimum size envelope defining the performance of the weapon when implemented on each of the different aircraft types.

[0049] In some aspects, the database is generated by defining a range of conditions under which the weapon may be required to be fired, a range of aircraft conditions under which the aircraft is feasible to fire the weapon, and a range of weapon conditions under which the weapon is feasible to fire; generating data indicative of weapon performance for each weapon firing possibility within the defined ranges; and creating a database defining the overall performance envelope of the weapon. Coefficients can then be determined from this database and the general polynomial. In this manner, the database can be generated on a ground-based system, so the aircraft system only needs the capacity to store the general polynomial and process the coefficients with the aircraft and target conditions to generate the feasibility display. This tends to reduce the amount of data storage / processing capacity required on the aircraft.

[0050] The coefficients can be implemented as loadable data to allow accurate and precise weapon behavior to be realized within the weapon system, and using only one or a few generic algorithms will allow different weapon systems to be licensed or certified / qualified for use with aircraft with reduced effort and more quickly than the extensive testing required with traditional approaches.

[0051] The step of uploading the generated coefficients to the aircraft may be performed when the weapon is loaded as an aircraft store. When loading a new weapon store, the coefficients associated with the weapon may be uploaded to the aircraft simultaneously with the weapon to integrate the weapon with the aircraft targeting system. Preferably, the coefficients are stored with the weapon on a hardware device, and the device is connected to the aircraft for uploading the coefficient data when the weapon is loaded.

[0052] According to a second aspect of the present invention, a weapon carried on an aircraft is targeted. Successfully engage in combat Feasibility and / or the weaponry delivered on the target is compatible with aircraft Successfully engage in combat There is provided a system for generating a feasibility indication indicative of feasibility on board an aircraft in flight, the system comprising computers, namely a first computer comprising a memory and a processor and remote from the aircraft, and a second computer comprising a memory and a processor and on board the aircraft; The first computer is providing a database describing the weapon's performance envelope; a) generating a candidate polynomial, wherein the polynomial variables are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculating coefficients for that candidate polynomial that best fit the candidate polynomial to the characteristics of the weapon's performance envelope using a least squares error criterion; c) generating a candidate score for each candidate polynomial according to the quality of the candidate polynomial's fit to the characteristics of the weapon's performance envelope; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best-scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; e) repeating the identification process until all desired characteristics of the performance envelope have corresponding polynomial models; generating coefficient characteristics of said performance envelope using a general algorithm by steps including: uploading the identified best candidate polynomial coefficients to a second computer; and the second computer is configured to: selecting coefficients for the general algorithm according to aircraft and target conditions by a reconstructor including the same general algorithm; generating, by a reconstructor, a feasibility representation using the selected coefficients; In a system configured to perform the following, the step d) of applying a genetic algorithm to the candidate polynomials and scores comprises: i) defining a set of orders and / or types of candidate polynomials and dividing the defined set of orders and / or types into a plurality of subsets thereof; ii) iteratively applying a genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials, and calculating the resulting coefficients and their scores. keep iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types, including: iii) keep using the determined coefficients and scores to select the best-scoring polynomial(s) and discard the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; The present invention is characterized by comprising:

[0053] In one example, the system includes a display for displaying the feasibility representation.

[0054] According to a third aspect of the inventive concept, there is provided an aircraft comprising a second computer according to the second aspect.

[0055] According to a fourth aspect of the present invention there is provided a computer comprising a processor and a memory configured to carry out the method according to the first aspect.

[0056] According to a fifth aspect of the present invention there is provided a computer program comprising instructions which, when executed by a computer comprising a processor and a memory, cause the computer to carry out a method according to the first aspect.

[0057] According to a sixth aspect of the present invention there is provided a non-transitory computer readable storage medium comprising instructions which, when executed by a computer comprising a processor and a memory, cause the computer to perform a method according to the first aspect.

[0058] Embodiments of the present invention will now be described, by way of example only, with reference to the drawings in which: [Brief explanation of the drawings]

[0059] [Figure 1A] 1 illustrates a schematic of a launch area rating (LAR) for an air-to-ground weapon. [Figure 1B] 1 illustrates a schematic of a launch area rating (LAR) for an air-to-ground weapon. [Figure 2] 1 illustrates a schematic of a launch success zone (LSZ) for an air-to-air weapon. [Figure 3] 1 illustrates a schematic diagram of a system according to an illustrative embodiment; [Figure 4] 4 illustrates schematically the system of FIG. 3 in more detail. [Figure 5] 3 is a schematic diagram of the system in more detail, showing the configuration of the SOPNN. [Figure 6] In more detail, we schematically illustrate the system of FIG. 3, showing the GA-SOPNN parallelization across many polynomial orders and input parameters. [Figure 7] 4 illustrates schematically the system of FIG. 3 in more detail. DETAILED DESCRIPTION OF THE INVENTION

[0060] FIG. 1A schematically illustrates the LAR in the flight plane of a launching aircraft 1 flying along a flight path 3 relative to a target 5 for an air-to-ground weapon (not shown) carried on board the aircraft. The LAR is calculated to provide a cockpit display of situational feasibility and firing opportunities in the launching aircraft 1. FIG. 1B schematically illustrates the display generated for the LAR of FIG. 1A in the form of a down-range and cross-range display (shaded area), where the weapon flight path 7 coincides with the aircraft flight path 3 and is aligned with the target 5 as shown in the display. Successfully engage in combat To achieve this, the target must be within the shaded LAR. As Aircraft 1 moves downrange, the displayed LAR is within the minimum range R. min and maximum range R max It is bounded by

[0061] In addition to the LAR for launching aircraft 1, a missile engagement zone (MEZ) for target 5 may be determined and displayed to the pilot of aircraft 1. This MEZ defines the area within which a surface-to-air weapon (e.g., a missile) carried by target 5 may be launched by aircraft 1. Successfully intercept the Areas where the probability is above a threshold may be indicated.

[0062] The LSZ, shown in Figure 2, is the area where the probability of an air-to-air weapon hitting an airborne target T exceeds a threshold level. Calculating the LSZ is more complex than the LAR because it involves a greater number of factors, including the relative speed and direction of travel of the launching aircraft and the target, and the relative speed and direction of travel of the weapon relative to the target. The shape of the LSZ is also more complex than the shape of the LAR, and like the LAR, the LSZ is the area between which the target T lies. Successfully engage in combat The maximum range R min and minimum range R max However, given the speed and direction of travel of the launching aircraft and target T, it is beyond the ability of the launching aircraft to operate the weapon and hit the target when it is very close to the target. Successfully engage in combat Can't, R min In this example, the LSZ is the so-called "range of no escape" RNE Further includes: R NE and R min The zone bounded by is the area where objective T is located. Successfully avoid The LSZ is a zone where the probability falls below a threshold probability. This range may be determined using performance parameters of the weapon, the launching aircraft 1, and the target T. As is known in the art, there are two LSZs: one for the launching aircraft to engage the target T and one for the target to engage the launching aircraft.

[0063] It is often necessary to calculate the LAR or LSZ for an engagement to display information to the launching aircraft crew regarding the feasibility or likelihood of success of the engagement, as well as to support fire control and guidance decisions. The conventional approach is to create a simple abstract model of the weapon with parameters defined by the launch conditions, which is then used on board the launching aircraft to generate the LAR, LSZ, or MEZ and appropriate display.

[0064] Traditional weapon targeting processes typically involve custom design, implementation, and qualification for every weapon / platform combination. Custom approaches are very costly and time-intensive. Even small changes in weapon performance create complex loops around the customization process. Such processes also tend to be limited in on-board computing capacity. However, today's platforms are exceeding critical capacity limits. To improve weapon integration time and affordability, the inventors developed a Data Driven Weapon Integration (DDWI) approach that uses generic algorithms that can be "customized" for specific weapons by using a unique set of data coefficients. In doing so, DDWI breaks the reliance on custom models for weapon targeting creation. It reduces avionics lifecycle costs and improves timescales, resulting in significant improvements. keepThis provides flexibility in service to "tune" and / or "sanitize" weapon targeting performance. Mission data coefficients uploaded onto the platform are derived from advanced multi-dimensional weapon models. By performing parallel computations on multi-core computers, GPUs, and computer clusters, we solve such computationally and data-intensive problems, freeing up more performance and reducing processing time.

[0065] Figure 3 illustrates a schematic diagram of a system according to an exemplary embodiment. DDWI has three elements: · Calibration Toolset, an office-based design tool for mission systems engineers to turn weapon truth data into a set of weapon coefficients; Data load coefficients, a common format that can be software build / theater / mission data loaded into different platforms for the same weapon, and · A common on-board algorithm that can represent any weapon on any platform and is weaponized only when the coefficients are loaded.

[0066] Figure 4 illustrates the system of Figure 3 in more detail, divided into a process 11 performed on the ground and a process 13 performed on board the launch aircraft 1. The system is Successfully engage in combat Feasibility and / or the weaponry delivered on the target is compatible with aircraft Successfully engage in combat The system is for generating a feasibility display indicating feasibility on board an aircraft in flight, and includes computers, namely a first computer having a memory and a processor and located away from the aircraft, and a second computer having a memory and a processor and located on board the aircraft.

[0067] The first computer 11 provides a database describing the weapon's performance envelope; a) generates candidate polynomials, where the polynomial variables are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculates coefficients for the candidate polynomial that best fit the candidate polynomial to the characteristics of the weapon's performance envelope using a least squares error criterion; c) for each candidate polynomial, generates a candidate score according to the quality of the candidate polynomial's fit to the characteristics of the weapon's performance envelope; and d) selects the best-scoring polynomial(s). and (d) applying a genetic algorithm to the candidate polynomials and scores, including selecting a best candidate polynomial and discarding other polynomial(s), thereby identifying a best candidate polynomial and its coefficients; and (e) creating coefficient characteristics of the performance envelope using a generic algorithm by steps including: repeating the identification process until all required characteristics of the performance envelope have a corresponding polynomial model, wherein the generic algorithm has the form of a polynomial; and uploading the coefficients of the identified best candidate polynomial to a second computer. The step d) of applying a genetic algorithm to the candidate polynomials and scores includes: i) defining a set of orders and / or types of candidate polynomials and dividing the defined set of orders and / or types into a plurality of subsets thereof; ii) iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials, and computing the resulting coefficients and their scores. keep iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types, including: keep and using the determined coefficients and scores to select the best-scoring polynomial(s) and discard the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients.

[0068] The second computer 13 is configured to select coefficients for the general algorithm according to aircraft and target conditions by a reconstructor containing the same general algorithm, and to generate a feasibility indication by the reconstructor using the selected coefficients.

[0069] More specifically, the core of DDWI is an offline coefficient generator 21. The coefficient generator 21 identifies coefficients for a generic algorithm that allow the generic algorithm to "fit" the performance envelope shape. The form of the generic algorithm is typically predetermined, such as an arbitrary polynomial of degree (i.e., order) up to n. The coefficient generator 21 receives the true performance envelope and calculates coefficients for the generic algorithm. The coefficients allow the generic algorithm to "fit" the performance envelope shape.

[0070] The estimation and adaptation process uses a genetic algorithm for a self-organizing polynomial neural network approach. It calculates a set of coefficients that will allow the geometry of the LAR / LSZ region to be modeled (and subsequently reconstructed) by a standard polynomial "algorithm" (see Figure 5). It uses an evolutionary technique called a genetic algorithm as the central mechanism for a self-organizing polynomial neural network (GA-SOPNN) to automate the derivation of the coefficients of several polynomial models in each layer. The process involves the following steps: 1. Creating an initial population of candidate polynomials of different orders with inputs comprising some or all of the firing parameters, where each polynomial function is a unique solution to the problem; 2. Using the least squares error criterion, calculate the coefficients for fitting these candidates to the weapon performance envelope for selected characteristics of the LAR / LSZ; 3. Calculate a score function for each candidate; 4. Recursively improve this population using a genetic algorithm, a) Retain the candidates with the best scores; b) reject the worst candidates; c) "Growing" a new population with randomly selected combinations of features drawn from the best groups; 5. Repeat until improvement stops or accuracy criteria are met. 6. The result is the first layer of a self-organizing polynomial neural network (SOPNN), 7. Each subsequent layer of the SOPNN takes as its input the best output of the previous layer and then proceeds as described above, 8. The effect is to create higher-order candidate polynomials for consideration, 9. The optimization within the new layer uses the same genetic algorithm as before, 10. Layers are added until improvement stops or the maximum layer set by the user is reached. 11. Only the single best polynomial and coefficient set of interest, i.e., the output of the final layer with the best score. 12. All other outputs of the final layer are rejected, 13. All nodes in the lower layer that do not contribute to the best polynomial are rejected.

[0071] To apply a genetic algorithm to a specific application, an internal representation of the space to be explored is chosen and an external function is defined that assigns fitness values ​​to candidate solutions. We adapted the genetic algorithm to parallelize across the many polynomial orders and input parameters that the genetic algorithm must run, as shown in Figure 6. Each run tests several parameter combinations of polynomial order and input, and reports the run time, memory, and flop operations for the final model requirements to solve the problem for each parameter combination, as described in more detail below.

[0072] In this example, the polynomial is parameterized to a string of binary strings with three parameters (also known as subchromosomes): The first parameter is the order, The second parameter is the number of inputs, The third parameter identifies which inputs are used by the polynomial.

[0073] In this example, iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials may be: selecting a combination of polynomial variables for each order and / or type of each subset of polynomials; iteratively applying a genetic algorithm over selected combinations of polynomial variables for each order and / or type of each subset of polynomials; Equipped with.

[0074] In this example, the genetic algorithm starts with an initial population of randomly generated strings, and hence a corresponding initial population of randomly generated polynomials (order, input). Each polynomial is scored using a least-squares fit, and the best polynomial is selected. These best polynomials are mutated by switching binaries in the corresponding strings to modify (order, input). The modified strings are used to generate new polynomials in new layers of the SOPNN. The order of the polynomials increases from layer to layer.

[0075] In this example, iteratively applying the genetic algorithm over selected combinations of polynomial variables for each order and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously over selected combinations of polynomial variables for each order and / or type of each subset of polynomials.

[0076] In this example, iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types comprises iteratively applying the genetic algorithm simultaneously across multiple subsets of the defined set of candidate polynomial orders and / or types on respective processors and / or different threads.

[0077] In this example, iteratively applying the genetic algorithm simultaneously over selected combinations of polynomial variables for each order and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously over selected combinations of polynomial variables for each order and / or type of each subset of polynomials on each thread and / or processor.

[0078] In this example, the maximum polynomial order is upper bounded and the maximum number of inputs is upper bounded. Upper bounding the maximum order and the maximum number of inputs means that polynomials randomly generated during GA training can have any order and input, respectively, up to their maximum values. In this example, each coefficient for each polynomial order is calculated by an individual processor. In this example, each coefficient for each input for each polynomial order is calculated by an individual processor.

[0079] Parallelizing the operation of GA-SOPNN itself allows / will free up more performance, as shown in Figure 7. By allocating NUM_THREADS for each process, the individual solutions in the population can be divided among the threads. For example, in the case of a GA population with 100 individuals and 4 CPU cores, the 100 iterations are divided into 4, so that thread 0 does iterations 1-25, thread 1 does iterations 26-50, etc., which results in the GA-SOPNN algorithm working approximately 4 times faster.

[0080] More specifically, processes 11, 13 begin with the generation of a data space, which is the range of conditions for which the weapon performance envelope is to be defined, this is done by a data space generator 15 and depends on the range of conditions under which it is required to fire the weapon (defined by the weapon user / operator), it is feasible to fire according to the launch aircraft capabilities, and it is feasible to fire according to the weapon capabilities / performance.

[0081] In this example, the data space generator 15 comprises data describing performance parameters for each of a plurality of different aircraft types. The different types of aircraft may have different capabilities; thus, for example, aircraft with the same or similar capabilities may be considered to be the same "aircraft type." The different types of aircraft may be different models or makes of aircraft and / or have different manufacturers. The different types of aircraft may have different operating parameters (maximum speed, maximum altitude, g-limit, etc.). The different types of aircraft may be configured for different purposes or functions (e.g., bomb, fighter, refueling, etc.). These aircraft performance envelopes may be provided by the aircraft manufacturer or through testing. The plurality of different aircraft types includes a type of launch aircraft 1 and preferably a type of target aircraft T. The performance parameters for each of the aircraft types may include, but are not limited to, a maximum achievable altitude, a maximum achievable g-force, and a maximum achievable angle of climb. The values ​​of the performance parameters for the different types of aircraft may differ from one another. For example, a first type of aircraft may have a maximum altitude of 45,000 feet, while a second type of aircraft may have a maximum altitude of 55,000 feet, and so on.

[0082] In this example, data space generator 15 further includes data describing performance parameters for each of a plurality of different weapon types, e.g., different weapons that may be carried on the launch aircraft or that may be expected to be delivered by a hostile target. These weapon performance envelopes may be provided by the weapon manufacturer or through testing. The plurality of different weapon types includes the type of weapon delivered by launch aircraft 1 and preferably the target. The performance parameters for each weapon type may include, but are not limited to, a maximum altitude at which the weapon may be released, a maximum g-force at which the weapon may be released, and a weapon release mechanism. The values ​​of the performance parameters for different types of weapon may differ from one another. For example, a first type of weapon may be capable of being released up to an altitude of 35,000 feet, while a second type of weapon may be capable of being released up to an altitude of 45,000 feet, etc.

[0083] The data space generator 15 may define the release, weather, and commanded impact conditions for the training and validation sets to be run by the truth data generator 17 .

[0084] The truth data generator 17 determines the weapon performance for each firing case in the data space, which relies on weapon performance models typically provided by the weapon manufacturer.

[0085] The product of the truth data generator 17 is a truth database 19, which is a set of data that specifies, for each weapon type, additional weapon performance envelopes for each of a number of example weapon fires. The truth data generator 17 may produce training and validation sets that are used by the coefficient generator 21.

[0086] Conventionally, the truth database is used as a model that can be used on board a launch aircraft to generate a feasibility of engagement display (LAR or LSZ, as appropriate).

[0087] In this example, the coefficient generator 21 receives the additional weapon performance envelopes stored by the truth database 19 and calculates coefficients for each weapon type and each illustrative weapon fire according to a generic LAR / LSZ algorithm 23 that "fits" the generic algorithm to the additional weapon performance envelope shape.

[0088] Described herein is a method for determining coefficient values ​​that adapt the general algorithm to the performance envelope of a particular weapon type and a particular illustrative weapon fire. In practice, it will be recognized that a set of coefficients will be determined for each weapon type for each illustrative weapon fire.

[0089] In this method, the coefficient generator 21 begins by creating an initial set of candidate polynomials whose variables are some or all of the weapon or aircraft firing condition parameters. Each of the candidate polynomials is a unique solution to the matching problem. Some or all of the candidate polynomials may have a different order or dimension than some or all of the other candidate polynomials. For each candidate polynomial, a set of coefficients is then calculated that best "fits" that candidate polynomial to the weapon performance envelope. This may be done using a least squares error criterion or any other fitting method. For each candidate polynomial, a score indicating the quality of this fit is then calculated.

[0090] The number of inputs 27 and the form of each polynomial descriptor, PD layer node, are determined by an optimization method known as a genetic algorithm. The genetic algorithm is applied to the candidate polynomials and scores. In this example, the best-scoring polynomial is retained, and the other (i.e., worst-scoring) polynomials are rejected. A new candidate polynomial with similar characteristics to the retained candidate polynomial is then created to replace the rejected candidate polynomial (e.g., by "propagating" or "mutating" the retained candidate polynomial). A set of coefficients and score values ​​is then calculated for the generation of this new candidate, and so on.

[0091] The genetic algorithm is repeated until there is an improvement in the score of the best candidate or some other criterion is met. The result is the first layer, Layer 1, of a Self-Organizing Polynomial Neural Network (SOPNN).

[0092] The entire process is then repeated, with the output of the first layer providing the input to create the second layer of the SOPNN, Layer 2. The new layer has the effect of creating higher-order candidate polynomials and coefficients for consideration. The selection of polynomials in the new layer is again governed and optimized by the genetic algorithm.

[0093] Layers are added to the SOPNN in this manner until the score of the best candidate is improved or some other criterion is met. A completed network with two layers is depicted in Figure 5. The final network is recursively obtained from the path that ends in the output node with the best score in the final generation of candidates (the "optimal solution"). Any nodes that do not have a connection to this path are discarded, as shown in Figure 5, where nodes that contribute to the optimal solution are lightly shaded and discarded nodes are black.

[0094] As explained above, the inventors have adapted the genetic algorithm to parallelize over the many polynomial orders and input parameters that the genetic algorithm must run over.

[0095] The best single candidate polynomial and coefficient set is identified and stored. This process is repeated until all required characteristics of the LAR / LSZ have a corresponding polynomial model. In other words, this process is repeated for each firing condition and each weapon type until a polynomial model is generated that is fitted to the additional weapon performance envelope for that weapon type and firing condition.

[0096] The general LAR / LSZ algorithm is predetermined, and in this example the general polynomial is of the following form, as previously explained:

[0097]

number

[0098] In this example, the best candidate polynomial is of the form:

[0099]

number

[0100] In this example, a typical polynomial order is in the range of 10 to 25, say 20.

[0101] 4, the output of the coefficient generator 21 is a set of coefficients that are loaded into the launch aircraft by the data uploader. Following this step, the onboard process 13 includes a reconstructor 25 that integrates the uploaded coefficients with a general LAR / LSZ algorithm 23 (held in the aircraft system) to reconstruct the LAR, LSZ, or MEZ for the particular engagement by selecting the appropriate algorithm and coefficients for the current firing conditions (i.e., weapon or aircraft launch conditions).

[0102] Once the LAR, LSZ, or MEZ has been reconstructed for a particular engagement by systems onboard the aircraft, the LAR, LSZ, or MEZ is displayed by conventional means onboard the aircraft. In this example, during operation, when launch aircraft 1 engages hostile target aircraft T, reconstructor 25 onboard launch aircraft 1 may select coefficients from the uploaded coefficients that correspond to the weapon carried by launch aircraft 1 and to the associated firing conditions (altitude, angle of attack, environmental conditions, g-forces, etc.). The selected coefficients may then be used to reconstruct and display the LSZ of launch aircraft 1 to the pilot of launch aircraft 1. The reconstructed LSZ of launch aircraft 1 may also be used by other systems onboard launch aircraft 1 to recommend actions to the pilot of launch aircraft 1 (e.g., a recommendation that a weapon be fired, etc.).

[0103] When the launch aircraft 1 engages a hostile target aircraft T, the aircraft type of the hostile target T may be determined by the pilot of the launch aircraft 1 (or by other means) and input to the reconstructor 25. The reconstructor 25 onboard the launch aircraft 1 may then select, from the uploaded coefficients, a coefficient that corresponds to the weapon most likely to be carried by the hostile target T and to the associated firing conditions. The selected coefficient may then be used to reconstruct and display to the pilot of the launch aircraft 1 the LSZ of the hostile target T. The reconstructed LSZ of the hostile target T may also be used by other systems onboard the launch aircraft 1 to recommend actions to the pilot of the launch aircraft 1 (e.g., a recommendation that a particular evasive maneuver be performed, etc.).

[0104] In this example, during operation, when the launch aircraft 1 engages a hostile ground target 5, the reconstructor 25 on board the launch aircraft 1 may select from the uploaded coefficients those coefficients that correspond to the weapon carried by the launch aircraft 1 and to the associated firing conditions (altitude, angle of attack, environmental conditions, g-forces, etc.) experienced. The selected coefficients may then be used to reconstruct the LAR of the launch aircraft 1 and display it to the pilot of the launch aircraft 1. The reconstructed LAR of the launch aircraft 1 may also be used by other systems on board the launch aircraft 1 to recommend actions to the pilot of the launch aircraft 1 (e.g., a recommendation that a weapon be fired, etc.).

[0105] When the launch aircraft 1 engages a hostile ground target 5, the type of ground target 5 may be determined by the pilot of the launch aircraft 1 (or by other means) and input to the reconstructor 25. The reconstructor 25 onboard the launch aircraft 1 may then select from the uploaded coefficients those coefficients that correspond to the weapon most likely to be carried by the ground target 5 and to the associated firing conditions. The selected coefficients may then be used to reconstruct the MEZ of the ground target 5 and display it to the pilot of the launch aircraft 1. The reconstructed MEZ of the ground target 5 may also be used by other systems onboard the launch aircraft 1 to recommend actions to the pilot of the launch aircraft 1 (e.g., a recommendation that a certain evasive maneuver be performed, etc.).

[0106] Apparatus, including any of the processors mentioned above, for implementing the above-described configurations may be provided by configuring or adapting any suitable apparatus, for example, one or more computers or other processing devices or processors, and / or by providing additional modules. The apparatus may comprise a computer, a network of computers, or one or more processors for implementing instructions and using data, including instructions and data in the form of a computer program or multiple computer programs stored in or on a machine-readable storage medium such as computer memory, computer disk, ROM, PROM, etc., or any combination of these or other storage media. The following is a summary of the claims as originally filed: [1] A computer-implemented method for generating a feasibility indication, in a flying aircraft, indicating the feasibility of a weapon carried on the aircraft successfully engaging a target and / or the feasibility of a weapon carried on the target successfully engaging the aircraft, the method comprising: providing a database describing a performance envelope of the weapon; a) generating a candidate polynomial, wherein the variables of said polynomial are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculating coefficients for that candidate polynomial that best fit the candidate polynomial to the performance envelope characteristics of the weapon using a least squares error criterion; c) generating a candidate score for each candidate polynomial according to the quality of the candidate polynomial's fit to the characteristics of the performance envelope of the weapon; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best-scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; e) repeating the identification process until all required characteristics of the performance envelope have corresponding polynomial models; creating coefficients characteristic of the performance envelope using a generic algorithm, wherein the generic algorithm has the form of a polynomial; uploading coefficients of the identified best candidate polynomial to the aircraft; and selecting coefficients for the generic algorithm according to conditions of the aircraft and the target by a reconfigurator on the aircraft containing the same generic algorithm. generating, by the reconstructor, the feasibility representation using the selected coefficients; and wherein step d) of applying the genetic algorithm to the candidate polynomials and scores comprises: i) defining a set of orders and / or types of the candidate polynomials and dividing the set of defined orders and / or types into a plurality of subsets thereof; ii) iteratively applying the genetic algorithm simultaneously across the plurality of subsets of the defined set of candidate polynomial orders and / or types, including iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials and saving each resulting coefficient and its score; iii) using the saved coefficients and scores to select the best-scoring polynomial(s) and discard other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; A method comprising: [2] The method described in [1], wherein iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of orders and / or types of the candidate polynomials comprises iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of orders and / or types of the candidate polynomials on each processor. [3] Iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials includes: selecting a combination of variables of the polynomials for each order and / or type of each subset of polynomials; iteratively applying the genetic algorithm over selected combinations of variables of the polynomials for each order and / or type of each subset of polynomials; The method according to [1] or [2], comprising: [4] The method described in [3], wherein iteratively applying the genetic algorithm over the selected combinations of polynomial variables for each order and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously over the selected combinations of polynomial variables for each order and / or type of each subset of polynomials. [5] The method described in [4], wherein iteratively applying the genetic algorithm simultaneously across selected combinations of polynomial variables for each order and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously across selected combinations of polynomial variables for each order and / or type of each subset of polynomials on each thread. [6] The method of any one of [1] to [5], wherein iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of orders and / or types of the candidate polynomials, including iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials and saving each resulting coefficient and its score, comprises conditionally iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of orders and / or types of the candidate polynomials, including iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials and saving each resulting coefficient and its score. [7] The method of [6], wherein conditionally iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of orders and / or types of the candidate polynomials comprises terminating application of the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials if the respective scores are below a threshold. [8] The method according to [7], wherein the threshold value is predetermined. [9] The method according to [7] or [8], comprising determining the threshold based on a previous score.

[10] The method according to any one of [1] to [9], wherein the types of candidate polynomials in the set of candidate polynomials include univariate polynomials, multivariate polynomials, and modifications thereof.

[11] The general polynomial is of the following form:

number

[10] .

[12] A system for generating a feasibility indication on board an aircraft in flight indicating the feasibility of a weapon carried on the aircraft successfully engaging a target and / or the feasibility of a weapon carried on the target successfully engaging the aircraft, the system comprising: computers, i.e., a first computer having a memory and a processor and remote from the aircraft; and a second computer having a memory and a processor and on board the aircraft; The first computer providing a database describing the performance envelope of said weapon; a) generating a candidate polynomial, wherein the variables of said polynomial are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculating coefficients for that candidate polynomial that best fit the candidate polynomial to the performance envelope characteristics of the weapon using a least squares error criterion; c) generating a candidate score for each candidate polynomial according to the quality of the candidate polynomial's fit to the characteristics of the performance envelope of the weapon; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best-scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; e) repeating the identification process until all required characteristics of the performance envelope have corresponding polynomial models; creating coefficients characteristic of the performance envelope using a general algorithm, wherein the general algorithm has the form of a polynomial; and uploading the identified best candidate polynomial coefficients to the second computer. wherein the second computer is configured to: selecting coefficients for the general algorithm according to the aircraft and target conditions by a reconstructor including the same general algorithm; generating, by the reconstructor, the feasibility representation using the selected coefficients; and wherein step d) of applying the genetic algorithm to the candidate polynomials and scores comprises: i) defining a set of orders and / or types of the candidate polynomials and dividing the set of defined orders and / or types into a plurality of subsets thereof; ii) iteratively applying the genetic algorithm simultaneously across the plurality of subsets of the defined set of candidate polynomial orders and / or types, including iteratively applying the genetic algorithm across the polynomial variables for each order and / or type of each subset of polynomials and saving each resulting coefficient and its score; iii) using the saved coefficients and scores to select the best-scoring polynomial(s) and discard other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; A system comprising:

[13] The system of

[12] , comprising a display for displaying the feasibility display.

[14] An aircraft equipped with the second computer described in

[12] or

[13] .

[15] A computer having a processor and a memory configured to carry out the method according to any one of [1] to

[11] , a computer program having instructions that, when executed by a computer having a processor and a memory, cause the computer to carry out the method according to any one of [1] to

[11] , or a non-transitory computer-readable storage medium having instructions that, when executed by a computer having a processor and a memory, cause the computer to carry out the method according to any one of [1] to

[11] .

Claims

1. 1. A computer-implemented method for generating a feasibility indication on an aircraft in flight indicating the feasibility of weapons delivered on the aircraft successfully engaging a target and / or the feasibility of weapons delivered on the target successfully engaging the aircraft, the method comprising: providing a database describing the performance envelope of said weapon; generating coefficients characteristic of the performance envelope using a general algorithm, wherein the general algorithm has a polynomial form, and said generating includes: a) generating a candidate polynomial, wherein the variables of said polynomial are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculating coefficients for that candidate polynomial that best fit the candidate polynomial to the performance envelope characteristics of the weapon using a least squares error criterion; c) generating a candidate score for each candidate polynomial according to the quality of the candidate polynomial's fit to the characteristics of the performance envelope of the weapon; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best-scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; e) repeating the identification process until all required characteristics of the performance envelope have corresponding polynomial models; by steps including uploading the identified best candidate polynomial coefficients to the aircraft; selecting coefficients for the generic algorithm according to the conditions of the aircraft and the target by a reconfigurator on the aircraft that includes the same generic algorithm; generating, by the reconstructor, the feasibility representation using the selected coefficients; and and step d) of applying the genetic algorithm to the candidate polynomials and scores comprises: i) defining a set of degrees and / or types of the candidate polynomials and dividing the defined set of degrees and / or types into a plurality of subsets thereof, wherein the degrees are in the range of 5 to 9; ii) iteratively applying the genetic algorithm simultaneously across the plurality of subsets of the defined set of candidate polynomial degrees and / or types, including iteratively applying the genetic algorithm across the polynomial variables for each degree and / or type of each subset of polynomials and saving each resulting coefficient and its score; iii) using the stored coefficients and scores to select the best-scoring polynomial(s) and discard other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; A method comprising:

2. 2. The method of claim 1 , wherein iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of degrees and / or types of the candidate polynomials comprises iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of degrees and / or types of the candidate polynomials on respective processors.

3. Iteratively applying the genetic algorithm across the polynomial variables for each degree and / or type of each subset of polynomials includes: selecting a combination of variables of the polynomials for each degree and / or type of each subset of polynomials; iteratively applying the genetic algorithm over selected combinations of variables of the polynomials for each degree and / or type of each subset of polynomials; The method of claim 1 , comprising:

4. 4. The method of claim 3, wherein iteratively applying the genetic algorithm over the selected combinations of polynomial variables for each degree and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously over the selected combinations of polynomial variables for each degree and / or type of each subset of polynomials.

5. 5. The method of claim 4, wherein iteratively applying the genetic algorithm simultaneously across the selected combinations of polynomial variables for each degree and / or type of each subset of polynomials comprises iteratively applying the genetic algorithm simultaneously across the selected combinations of polynomial variables for each degree and / or type of each subset of polynomials on respective threads.

6. 2. The method of claim 1 , wherein iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of candidate polynomial degrees and / or types, including iteratively applying the genetic algorithm across the polynomial variables for each degree and / or type of each subset of polynomials and saving each resulting coefficient and its score, comprises conditionally iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of candidate polynomial degrees and / or types, including iteratively applying the genetic algorithm across the polynomial variables for each degree and / or type of each subset of polynomials and saving each resulting coefficient and its score.

7. 7. The method of claim 6, wherein conditionally iteratively applying the genetic algorithm simultaneously across the multiple subsets of the defined set of degrees and / or types of the candidate polynomials comprises terminating application of the genetic algorithm across the polynomial variables for each degree and / or type of each subset of polynomials if the respective scores are below a threshold.

8. The method of claim 7 , wherein the threshold is predetermined.

9. The method of claim 7 , comprising determining the threshold based on a previous score.

10. The method of claim 1 , wherein the types of candidate polynomials in the set of candidate polynomials include univariate polynomials, multivariate polynomials, and modifications thereof.

11. The polynomial is of the form: [Equation 1] Where: α mn represents the m coefficients required to compute output n, {x 1 …x Ni } represents the normalized input, {y 1 …y Ni } represents the output, p 1mn is the x of the m-th term of the n-th polynomial 1 The method of claim 1 , wherein the exponent of the variable is expressed.

12. 1. A system for generating a feasibility indication on board an aircraft in flight indicating the feasibility of weapons carried on the aircraft successfully engaging a target and / or the feasibility of weapons carried on the target successfully engaging the aircraft, the system comprising: computers, i.e., a first computer having a memory and a processor and remote from the aircraft; and a second computer having a memory and a processor and on board the aircraft; The first computer providing a database describing the performance envelope of said weapon; generating coefficients characteristic of the performance envelope using a general algorithm, wherein the general algorithm has a polynomial form, and said generating includes: a) generating a candidate polynomial, wherein the variables of said polynomial are some or all of a group of weapon or aircraft firing condition parameters; b) for each candidate polynomial, calculating coefficients for that candidate polynomial that best fit the candidate polynomial to the performance envelope characteristics of the weapon using a least squares error criterion; c) generating a candidate score for each candidate polynomial according to the quality of the candidate polynomial's fit to the characteristics of the performance envelope of the weapon; d) applying a genetic algorithm to the candidate polynomials and scores, including selecting the best-scoring polynomial(s) and discarding the other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; e) repeating the identification process until all required characteristics of the performance envelope have corresponding polynomial models; by steps including uploading the identified best candidate polynomial coefficients to the second computer; configured to: The second computer selecting coefficients for the general algorithm according to the aircraft and target conditions by a reconstructor including the same general algorithm; generating, by the reconstructor, the feasibility representation using the selected coefficients; and and step d) of applying the genetic algorithm to the candidate polynomials and scores comprises: i) defining a set of degrees and / or types of the candidate polynomials and dividing the defined set of degrees and / or types into a plurality of subsets thereof, wherein the degrees are in the range of 5 to 9; ii) iteratively applying the genetic algorithm simultaneously across the plurality of subsets of the defined set of candidate polynomial degrees and / or types, including iteratively applying the genetic algorithm across the polynomial variables for each degree and / or type of each subset of polynomials and saving each resulting coefficient and its score; iii) using the stored coefficients and scores to select the best-scoring polynomial(s) and discard other polynomial(s), thereby identifying the best candidate polynomials and their coefficients; A system comprising:

13. The system of claim 12 , comprising a display for displaying the feasibility representation.

14. A computer comprising a processor and memory configured to perform the method of claim 1.

15. A computer program comprising instructions that, when executed by a computer having a processor and memory, cause the computer to perform the method of claim 1.

16. A non-transitory computer-readable storage medium comprising instructions that, when executed by a computer having a processor and memory, cause the computer to perform the method of claim 1.

Images