Recorded recurrent deep reinforcement learning guidance laws for intercepting endoatmospheric maneuvering missiles

This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.

Online task planning method of anti-ship missile based on rolling optimization

Based on the wave attack task planning method in static complex environment and the rolling optimization framework, an online task planning method in dynamic complex environment based on rolling optimization is proposed. In the process of online task planning in dynamic complex environment,online task planning is based on event triggering including target information update event, new target addition event, target failure event, weapon failure event, etc., and the methods include defense area reanalysis, parameter space update, and mission re-planning. Simulation is conducted for different events and the result shows that the index value of the attack scenario after re-planning is better than that before re-planning and according to the probability distribution of statistical simulation method, the index value distribution after re-planning is obviously in the region of high index value, and the index value gap before and after re-planning is related to the degree of posture change.

Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory(LSTM) neural network is nested into the extended Kalman filter(EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states,an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF(AEKF) when there exist large uncertainties in the system model.

Impact point prediction guidance of ballistic missile in high maneuver penetration condition

An impact point prediction(IPP) guidance based on supervised learning is proposed to address the problem of precise guidance for the ballistic missile in high maneuver penetration condition.An accurate ballistic trajectory model is applied to generate training samples,and ablation experiments are conducted to determine the mapping relationship between the flight state and the impact point.At the same time,the impact point coordinates are decoupled to improve the prediction accuracy,and the sigmoid activation function is improved to ameliorate the prediction efficiency.Therefore,an IPP neural network model,which solves the contradiction between the accuracy and the speed of the IPP,is established.In view of the performance deviation of the divert control system,the mapping relationship between the guidance parameters and the impact deviation is analysed based on the variational principle.In addition,a fast iterative model of guidance parameters is designed for reference to the Newton iteration method,which solves the nonlinear strong coupling problem of the guidance parameter solution.Monte Carlo simulation results show that the prediction accuracy of the impact point is high,with a 3 σ prediction error of 4.5 m,and the guidance method is robust,with a 3 σ error of 7.5 m.On the STM32F407 singlechip microcomputer,a single IPP takes about 2.374 ms,and a single guidance solution takes about9.936 ms,which has a good real-time performance and a certain engineering application value.

Uncertainty entropy-based exploratory evaluation method and its applications on missile effectiveness evaluation

Some attributes are uncertain for evaluation work because of incomplete or limited information and knowledge.It leads to uncertainty in evaluation results.To that end,an evaluation method,uncertainty entropy-based exploratory evaluation(UEEE),is proposed to guide the evaluation activities,which can iteratively and gradually reduce uncertainty in evaluation results.Uncertainty entropy(UE)is proposed to measure the extent of uncertainty.First,the belief degree distributions are assumed to characterize the uncertainty in attributes.Then the belief degree distribution of the evaluation result can be calculated by using uncertainty theory.The obtained result is then checked based on UE to see if it could meet the requirements of decision-making.If its uncertainty level is high,more information needs to be introduced to reduce uncertainty.An algorithm based on the UE is proposed to find which attribute can mostly affect the uncertainty in results.Thus,efforts can be invested in key attribute(s),and the evaluation results can be updated accordingly.This update should be repeated until the evaluation result meets the requirements.Finally,as a case study,the effectiveness of ballistic missiles with uncertain attributes is evaluated by UEEE.The evaluation results show that the target is believed to be destroyed.

Novel Early-Warning Model for Customer Churn of Credit Card Based on GSAIBAS-Cat Boost

As the banking industry gradually steps into the digital era of Bank 4.0,business competition is becoming increasingly fierce,and banks are also facing the problem of massive customer churn.To better maintain their customer resources,it is crucial for banks to accurately predict customers with a tendency to churn.Aiming at the typical binary classification problem like customer churn,this paper establishes an early-warning model for credit card customer churn.That is a dual search algorithm named GSAIBAS by incorporating Golden Sine Algorithm(GSA)and an Improved Beetle Antennae Search(IBAS)is proposed to optimize the parameters of the CatBoost algorithm,which forms the GSAIBAS-CatBoost model.Especially,considering that the BAS algorithm has simple parameters and is easy to fall into local optimum,the Sigmoid nonlinear convergence factor and the lane flight equation are introduced to adjust the fixed step size of beetle.Then this improved BAS algorithm with variable step size is fused with the GSA to form a GSAIBAS algorithm which can achieve dual optimization.Moreover,an empirical analysis is made according to the data set of credit card customers from Analyttica official platform.The empirical results show that the values of Area Under Curve(AUC)and recall of the proposedmodel in this paper reach 96.15%and 95.56%,respectively,which are significantly better than the other 9 common machine learning models.Compared with several existing optimization algorithms,GSAIBAS algorithm has higher precision in the parameter optimization for CatBoost.Combined with two other customer churn data sets on Kaggle data platform,it is further verified that the model proposed in this paper is also valid and feasible.

Robust missile autopilot design based on dynamic surface control

Since the dynamical system and control system of the missile are typically nonlinear, an effective acceleration tracking autopilot is designed using the dynamic surface control(DSC)technique in order to make the missile control system more robust despite the uncertainty of the dynamical parameters and the presence of disturbances. Firstly, the nonlinear mathematical model of the tail-controlled missile is decomposed into slow acceleration dynamics and fast pitch rate dynamics based on the naturally existing time scale separation. Secondly, the controller based on DSC is designed after obtaining the linear dynamics characteristics of the slow and fast subsystems. An extended state observer is used to detect the uncertainty of the system state variables and aerodynamic parameters to achieve the compensation of the control law. The closed-loop stability of the controller is derived and rigorously analyzed. Finally, the effectiveness and robustness of the design is verified by Monte Carlo simulation considering different initial conditions and parameter uptake. Simulation results illustrate that the missile autopilot based DSC controller achieves better performance and robustness than the other two well-known autopilots.The method proposed in this paper is applied to the design of a missile autopilot, and the results show that the acceleration tracking autopilot based on the DSC controller can ensure accurate tracking of the required commands and has better performance.

Design and Simulation of Controller for Hyper Velocity Kinetic Energy Missile

The controller design and digital simulation for the hyper velocity kinetic energy missile is investigated. A mathematical model of the trajectory deviation from the line of sight was established, the guidance closed loop was compensated with a phase advance lag corrective network, a selecting algorithm of the attitude control motors used to steer the missile's attitude was presented. In the presence of a wide variety of disturbances the results of digital simulation are satisfactory to circular error probability(CEP) being less than 0 5?m. The steering scheme utilizing attitude control motors as actuators to control the attitude of the missile is feasible.

Active Control of Initial Disturbances for Rockets and Missiles

The active control theory and methods of initial disturbances for rockets and missiles are investigated. The rocket or missile/launcher is simplified as a flexible beam excited by a moving varying velocity rigid body which has two points in contact with the beam. The control force is applied at the supporting point on the beam. Active control strategies based on optimal control theory are proposed and computer simulation is carried out. Simulation results are consistent with the theoretical results, and show that the active control strategies proposed can accomplish the purpose to control the initial disturbances actively. The results show that active control of initial disturbances for rockets and missiles is feasible for application.

Construction of Early-warning Model for Plant Diseases and Pests Based on Improved Neural Network

By studying principles and methods related to early-warning model of plant diseases and using PSO method, parameter optimization was conducted to backward propagation neural network, and a pre-warning model for plant diseases based on particle swarm and neural network algorithm was established. The test results showed that the construction of early-warning model is effective and feasible, which will provide a via- ble model structure to establish the effective early-warning platform.

VIRTUAL TARGET DIFFERENTIAL GAME MIDCOURSE GUIDANCE LAW FOR HYPERSONIC CRUISE MISSILE BASED ON NEURAL NETWORK

For the high altitude cruising flight phase of a hypersonic cruise missile （HCM）, a relative motion mod- el between the missile and the target is established by defining virtual target and combining the theory of the dif- ferential geometry with missile motion equations. Based on the model, the motion between the missile and the tar- get is considered as a single target differential game problem, and a new open-loop differential game midcourse guidance law （DGMGL） is deduced by solving the corresponding Hamiltonian Function. Meanwhile, a new struc- ture of a closed-loop DGMGL is presented and the training data for back propagation neural network （BPNN） are designed. By combining the theory of BPNN with the open-loop DGMGL obtained above, the law intelligence is realized. Finally, simulation is carried out and the validity of the law is testified.

Cross Spectral Estimation and Its Application in Missile Systems

A new method based on cross-spectrum estimation for the verification and validation of computer simulation models is expounded in accordance with the characteristics of missile systems. The new method can expose the differences between two time processes in several aspects and can also give quantitative analysis results about the statistical consistence between them. An application to an actual anti-tank missile system simulation is presented and the calculated results confirm the effectiveness of the method. The approach can also be employed to verify the simulation models of other dynamic systems.

Variable Structure Proportional Navigation for Homing Missile

The purpose of this paper is to design control loop and guidance loop for the homing missile, to prove that the modified variable structure proportional navigation (VSPN) can be used in passive homing guidance system, and to compare the VSPN with the proportional navigation (PN). Angular rate and linear acceleration are fed back to improve the stability and robust of autopilot, VSPN and PN are compared in mathematics simulation of homing missile in attacking tanks and helicopters. The damp and the stability of the missile body are increased. The VSPN cuts down the overload of guidance phase dramatically, makes the ballistic trajectory straighter than PN and leads to smaller missdistance. The VSPN can be used for passive homing guidance system, and is especially suitable for attacking helicopter.

Application of Generalized Predictive Adaptive Control Algorithm in the Design of Missile Control System

To study the application of the generalized predictive adaptive control algorithm in missile control system, the algorithm is presented based on the recursive least square estimation, and a controller of the pitch channel of a missile is designed by using this algorithm. The simulations verify that the designed controller can meet the demands of the task well.

Simulation Study on the Feasibility of Gun-Launched Missile Against Attack Helicopters

The feasibility of providing the tank a limited anti helicopter ability with gun launched missile is studied. A type of simulation model of gun launched missile against attack helicopters is established. The simulation and the parameter optimization of missile control system under various circumstances are done. The gun launched missile can directly hit the helicopters in the typical tracks, all the missdistances are less than 1?m and the maximum overload is less than available overload. Gun launched missile is a feasible choice for tanks against attack helicopters.

Missile flight simulation and attitude display

Simulation has become an important method for missile flight research to reduce cost and improve accuracy. This paper concerns missile flight trajectory and attitude calculation. As a result, mechanical analysis and modeling are done, the characteristics of missile flight decoding algorithm and attitude parameters are analyzed, the missile trajectory is dynamically simulated in a vertical plane and the missile attitude is real-time displayed. The description of missile flight process in a labo- ratory has provided a basis for actual missile flight.

Control Effect of Bio-guide Wasp Virus Missile on Ostrinia furnacalis and Its Benefits for Maize Production in Nanchong City

In order to promote ＂green plant protection＂, reduce the administration dosage and residue of pesticides and control cost of environment pollution, and improve maize production, quality and agricultural ecological environment safety. In this study, the control effect and benefit of bio-guide wasp virus missile（BGWVM） on Ostrinia furnacalis in Nanchong City was investigated by using insect light traps and combined method of field investigation and experimental demonstration. According to the results, applying 30-37 pairs of BGWVM per hectare exhibited an average control efficiency of 78.0%, and the control cost was 139.50-172.50 CNY/hm2, which was reduced by 142.50-168.00 CNY/hm^2 compared with conventional chemical control. Average maize yield in BGWVM demonstration plot was 817.8 kg/hm2 higher and improved by 11.0% compared with blank control plot. The output value was improved by 1 799.16 CNY/hm^2 and the revenue increased by 1 941.66-1 967.16CNY/hm2. During 2003-2014, the cumulative demonstration and popularization area of BGWVM technique in Nanchong City had reached 24 507.33 hm^2, and the cumulative yield increment reached 20.042 1 million kg. BGWVM application improved total output value by 44.092 6 million CNY and saved control cost by 3.492 3-4.117 2 million CNY, thus increasing the revenue by 47.584 9-48.209 8 million CNY. BGWVM application reduced 551.41 t of 5% dimehypo GG or 12.87 t of 90%monosultap WP. In addition, BGWVM technique is simple to use, labor-saving and safe for human, animals, environment and crops, with significant economic, ecological and social benefits and without any side effect, which has become an ideal substitute for controlling O. furnacalis and reducing chemical pesticides in organic agriculture industry, modern agriculture industry, production of green and pollution-free agricultural products and IBM prevention and control demonstration gardens.

Bayes Estimation of Parameter for the Safety Component Failure Model of the Safe Arming System of Missile

A Bayesian method is used to evaluate the component safety failure model parameter of the safe arming system of an air faced missile in flight. It was proved that Bayes estimation of the model parameter is coincident with the physical explanation of the prior probability density distribution of the random parameter.

Mid-Course Guidance Law for Long Range Multi-Purpose Missiles

A useful mid course guidance law for long range multi purpose missiles is proposed. The law consists of two parts. One is used in the horizontal guidance plane, and the other in the vertical guidance plane. The mid course is combined with variable structure proportional navigation in the homing phase. Simulation results show that the proposed guidance law can meet the demands for starting up the homing phase and so the handing over between mid course guidance and terminal guidance can be carried out successfully.

Optimum Design of the Control System for a Laser Beam Riding Guidance Anti-Tank Missile

The optimum theory and methods were adopted to design the laser beam riding guidance anti tank missile's control system in the short run. Through building the mathematical model of system, selecting a proper method and taking advantage of computer's high speed calculation and logic traits, an optimal controller was designed. Simulation results showed that the designed control system has fair performance and it satisfies the tactical and technical requirements. The results also demonstrate that by the combination of the optimizing methods and the computer the control system could be designed as soon as possible.