Autonomous Maneuver Decisions via Transfer Learning Pigeon-Inspired Optimization for UCAVs in Dogfight Engagements

This paper proposes an autonomous maneuver decision method using transfer learning pigeon-inspired optimization(TLPIO)for unmanned combat aerial vehicles(UCAVs)in dogfight engagements.Firstly,a nonlinear F-16 aircraft model and automatic control system are constructed by a MATLAB/Simulink platform.Secondly,a 3-degrees-of-freedom(3-DOF)aircraft model is used as a maneuvering command generator,and the expanded elemental maneuver library is designed,so that the aircraft state reachable set can be obtained.Then,the game matrix is composed with the air combat situation evaluation function calculated according to the angle and range threats.Finally,a key point is that the objective function to be optimized is designed using the game mixed strategy,and the optimal mixed strategy is obtained by TLPIO.Significantly,the proposed TLPIO does not initialize the population randomly,but adopts the transfer learning method based on Kullback-Leibler(KL)divergence to initialize the population,which improves the search accuracy of the optimization algorithm.Besides,the convergence and time complexity of TLPIO are discussed.Comparison analysis with other classical optimization algorithms highlights the advantage of TLPIO.In the simulation of air combat,three initial scenarios are set,namely,opposite,offensive and defensive conditions.The effectiveness performance of the proposed autonomous maneuver decision method is verified by simulation results.

Optimization of multi-revolution low-thrust transfer based on modified direct method

A modified direct optimization method is proposed to solve the optimal multi-revolution transfer with low-thrust between Earth-orbits. First, through parameterizing the control steering angles by costate variables, the search space of free parameters has been decreased. Then, in order to obtain the global optimal solution effectively and robustly, the simulated annealing and penalty function strategies were used to handle the constraints, and a GA/SQP hybrid optimization algorithm was utilized to solve the parameter optimization problem, in which, a feasible suboptimal solution obtained by GA was submitted as an initial parameter set to SQP for refinement. Comparing to the classical direct method, this novel method has fewer free parameters, needs not initial guesses, and has higher computation precision. An optimal-fuel transfer problem from LEO to GEO was taken as an example to validate the proposed approach. The results of simulation indicate that our approach is available to solve the problem of optimal muhi-revolution transfer between Earth-orbits.

Optimization of natural convection heat transfer of Newtonian nanofluids in a cylindrical enclosure

This study characterizes and optimizes natural convection heat transfer of two Newtonian Al2O3 and Ti O2/water nano fluids in a cylindrical enclosure. Nusselt number(Nu) of nano fluids in relation to Rayleigh number(Ra) for different concentrations of nano fluids is investigated at different con figurations and orientations of the enclosure.Results show that adding nanoparticles to water has a negligible or even adverse in fluence upon natural convection heat transfer of water: only a slight increase in natural convection heat transfer of Al2O3/water is observed,while natural convection heat transfer for TiO2/water nano fluid is inferior to that for the base fluid. Results also reveal that at low Ra, the likelihood of enhancement in natural convection heat transfer is more than at high Ra: at low Ra, inclination angle, aspect ratio of the enclosure and nanoparticle concentration in fluence natural convection heat transfer more pronouncedly than that in high Ra.

Decision Model of Knowledge Transfer in Big Data Environment

A decision model of knowledge transfer is presented on the basis of the characteristics of knowledge transfer in a big data environment.This model can determine the weight of knowledge transferred from another enterprise or from a big data provider.Numerous simulation experiments are implemented to test the efficiency of the optimization model.Simulation experiment results show that when increasing the weight of knowledge from big data knowledge provider,the total discount expectation of profits will increase,and the transfer cost will be reduced.The calculated results are in accordance with the actual economic situation.The optimization model can provide useful decision support for enterprises in a big data environment.

Transfer Path Contribution to Floor Vibration of Metro Vehicles Based on Operational Transfer Path Analysis Method

Operational transfer path analysis(OTPA)is an advanced vibration and noise transfer path identification and contribution evaluation method.However,the application of OTPA to rail transit vehicles considers only the excitation amplitude and ignores the influence of the excitation phase.This study considers the influence of the excitation amplitude and phase,and analyzes the contribution of the secondary suspension path to the floor vibration when the metro vehicle runs at 60 km/h,using an analysis based on the OTPA method.The results show that the vertical direction of the anti-rolling torsion bar area provides the maximum contribution to the floor vibration,with a contribution of 22.1%,followed by the longitudinal vibration of the air spring area,with a contribution of 17.1%.Based on the contribution analysis,a transfer path optimization scheme is proposed,which may provide a reference for the optimization of the transfer path of metro vehicles in the future.

Air interaction around outdoor air-cooled condensers

In order to increase cooling or heating efficiency,a porous computational fluid dynamics（CFD）model is employed to predict the thermo-fluid status and optimize the placement of outdoor units.A full scale model is established to validate the accuracy of CFD simulation in terms of velocity and temperature distributions.The comparison between the measurement and the simulation shows a good agreement.By evaluating the condensers＇ sucked air temperature with CFD for three units installed in a row,it is found that the minimum separation distance among neighboring units is 0.2 m;a vertical wall should be apart from the unit line by at least 0.8 m;and large different operating pressures among units do not impact the flow rate and the heat transfer of the other units meaningfully.

Optimization of heat transfer and heat-work conversion based on generalized heat transfer law

Examples of heat transfer and heat-work conversion are optimized with entropy generation and entransy loss,respectively based on the generalized heat transfer law in this paper.The applicability of entropy generation and entransy loss evaluation in these optimization problems is analyzed and discussed.The results show that the entransy loss rate reduces to the entransy dissipation rate in heat transfer processes,and that the entransy loss evaluation is effective for heat transfer optimization.However,the maximum heat transfer rate does not correspond to the minimum entropy generation rate with prescribed heat transfer temperature difference,which indicates that the entropy generation minimization is not always appropriate to heat transfer optimization.For heat-work conversion processes,the maximum entransy loss rate and the minimum entropy generation rate both correspond to the maximum output power,and they are both appropriate to the optimization of the heat-work conversion processes discussed in this paper.

A multi-objective decision-making method for the treatment scheme of landslide hazard

The treatment engineering of landslide hazard is a complicated systemengineering. The selecting treatment scheme is influenced by many factors such as technology,economics, environment, and risk. The decision-making of treatment schemes of landslide hazard is aproblem of comprehensive judgment with multi-hierarchy and multi-objective. The traditional analysishierarchy process needs identity test. The traditional analysis hierarchy process is improved bymeans of optimal transfer matrix here. An improved hierarchy decision-making model for the treatmentof landslide hazard is set up. The judgment matrix obtained by the method can naturally meet therequirement of identity, so the identity test is not necessary. At last, the method is applied tothe treatment decision-making of the dangerous rock mass at the Slate Mountain, and its applicationis discussed in detail.

Detailed string stability analysis for bi-directional optimal velocity model

The class of bi-directional optimal velocity models can describe the bi-directional looking effect that usually exists in the reality and is even enhanced with the development of the connected vehicle technologies. Its combined string stability condition can be obtained through the method of the ring-road based string stability analysis. However, the partial string stability about traffic fluctuation propagated backward or forward was neglected, which will be analyzed in detail in this work by the method of transfer function and its H∞ norm from the viewpoint of control theory. Then, through comparing the conditions of combined and partial string stabilities, their relationships can make traffic flow be divided into three distinguishable regions, displaying various combined and partial string stability performance. Finally, the numerical experiments verify the theoretical results and find that the final displaying string stability or instability performance results from the accumulated and offset effects of traffic fluctuations propagated from different directions.

Entransy dissipation,entransy-dissipation-based thermal resistance and optimization of one-stream hybrid thermal network

The one-stream hybrid thermal network is analyzed and discussed based on the entransy theory,and the results are compared with those from the entropy generation optimization.The theoretical analysis indicates that the minimum heat-flow-weighted temperature of the thermal networks corresponds to the minimum entransy dissipation rate and the minimum thermal resistance.For a simple hybrid thermal network consisting of three thermal components,the expression of entransy dissipation is conducted,and the heat transfer area and the mass flow rate are calculated and optimized.The optimal results are obtained in order to minimize the entransy dissipation and the thermal resistance.The optimal results are calculated for various combinations,such as series connection,parallel connection and other hybrid connections.The numerical results are in accordance with the theoretical analysis.Both the theoretical analysis and the numerical results show that the minimum entransy dissipation and the minimum thermal resistance correspond to the minimum heat-flow-weighted temperature of the thermal networks while the minimum entropy generation does not.

Optimal circle-to-rectilinear orbit transfer with circumferential thrust

This paper investigates the optimal transfer trajectories from a circular parking orbit towards the apocenter of a rectilinear ellipse,where the spacecraft reaches a quasi-stationary condition relative to an inertial reference frame.The spacecraft is equipped with a propulsion system that provides a circumferential continuous propulsive acceleration,that is,an acceleration whose direction is perpendicular to the primary body-spacecraft line.The performance index to minimize is the total flight time,and an indirect method is used to analyze the transfer trajectories.In this context,the optimal transfer performance is obtained as a function of the spacecraft propulsive acceleration magnitude through an interpolation procedure of numerical simulations.The results obtained with a continuous thrust propulsion system are also compared with those derived from a multi-impulse transfer.Finally,the paper investigates a heliocentric mission scenario in which the spacecraft minimizes the flight time required to reach a rectilinear ellipse with a given value of the aphelion radius.

An Iterative Thresholding Method for the Heat Transfer Problem

In this paper,we propose a simple energy decaying iterative thresholding algorithm to solve the heat transfer problem.The material domain is implicitly represented by its characteristic function,and the problem is formulated into a minimum-minimum problem.We prove that the energy is decreasing in each iteration.Numerical experiments for two types the heat transfer problems(volume to point and volume to sides)are performed to demonstrate the effectiveness of the proposed methods.

Constructal entransy dissipation rate minimization for leaf-like fins

Based on constructal theory,the constructs of the leaf-like fins are optimized by taking minimum entransy dissipation rate(for the fixed total thermal current,i.e.,the equivalent thermal resistance) as optimization objective.The optimal constructs of the leaf-like fins with minimum dimensionless equivalent thermal resistance are obtained.The results show that there exists an optimal elemental leaf-like fin number,which leads to an optimal global heat conduction performance of the first order leaf-like fin.The Biot number has little effects on the optimal elemental fin number,optimal ratios of length and width of the elemental and first order leaf-like fins;with the increase of the thermal conductivity ratio of the vein and blade,the optimal elemental fin number and optimal ratio of the length and width of the elemental leaf-like fin increase,and the optimal shape of the first order leaf-like fin becomes tubbier.The optimal construct based on entransy dissipation rate minimization is obviously different from that based on maximum temperature difference minimization.The dimensionless equivalent thermal resistance based on entransy dissipation rate minimization is reduced by 11.54% compared to that based on maximum temperature difference minimization,and the global heat conduction performance of the leaf-like fin is effectively improved.For the same volumes of the elemental and first order leaf-like fins,the minimum dimensionless equivalent thermal resistance of the first order of the leaf-like fin is reduced by 30.10% compared to that of the elemental leaf-like fin,and the global heat conduction performance of the first order leaf-like fin is obviously better than that of the elemental leaf-like fin.Essentially,this is because the temperature gradient field of the first order leaf-like fin based on entransy dissipation rate minimization is more homogenous than that of the elemental leaf-like fin.The dimensionless equivalent thermal resistance defined based on entransy dissipation rate reflects the average heat transfer performance of the leaf-like fin,and can provide some guidelines for the thermal design of the fins from the viewpoint of heat transfer optimization.

An efficient GPU-based parallel tabu search algorithm for hardware/software co-design

Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel tabu search algorithm(GPTS)for HW/SW partitioning.A single GPU kernel of compacting neighborhood is proposed to reduce the amount of GPU global memory accesses theoretically.A kernel fusion strategy is further proposed to reduce the amount of GPU global memory accesses of GPTS.To further minimize the transfer overhead of GPTS between CPU and GPU,an optimized transfer strategy for GPU-based tabu evaluation is proposed,which considers that all the candidates do not satisfy the given constraint.Experiments show that GPTS outperforms state-of-the-art work of tabu search and is competitive with other methods for HW/SW partitioning.The proposed parallelization is significant when considering the ordinary GPU platform.