No abstract

In the high-resolution radar imaging system, step-frequency radar signal is very important in getting the high-resolution range-profile, which can be used for target's detection and recognition. However, target radial velocity will produce many problems, therefore, movingtargets imaging is a bottleneck for step-frequency radar signal. In this paper, an effective motion compensation methods is presented, which is based on the function of Range-profile Contrast. The numeric simulation indicates that this method is effective, which can estimate the target's velocity in real-time, and it is easy to be used in engineering project. After target's motion compensation, the high-resolution range-profile will be much better than that is used to be, which can be used for the detection, recognition and ranging of moving targets..

This paper presents a tolerance analog circuit hard fault and soft fault diagnosis method based on the BP neural network and particle swarm optimization algorithm. First, select the mean square error function of BP neural network as the fitness function of the PSO algorithm. Second, change the guidance of neural network algorithms rely on gradient information to adjust the network weights and threshold methods, through the use of the characteristics of the particle swarm algorithm groups parallel search to find more appropriate network weights and threshold. Then using the adaptive learning rate and momentum BP algorithm to train the BP neural network. Finally, the network is applied to fault diagnosis of analog circuit, can quickly and effectively to the circuit fault diagnosis.

In order to diagnose single soft fault in analog circuit, the particle swarm neural network was applied to fault diagnosis of analog circuit. The particle swarm neural network training process was divided into two steps. Firstly, BP network weights and threshold values as the position vector of the particle, used PSO algorithm searches for a near-optimal position vector as BP neural network initial weight values and thresholds. Secondly, used the BP algorithm to further optimization based on the initial weights and thresholds, got the optimal network weights and threshold value. The training method can improve the convergence accuracy and learning speed of the network training. The simulation results show that this diagnostic method can effectively achieve the accurate diagnosis of analog circuit soft fault.

Base on improved particle swarm algorithm, this paper proposes a linear decreasing inertia weight particle swarm algorithm and error back propagation algorithm based on hybrid algorithm combining. The linear decreasing inertia weight particle swarm algorithm and momentum-adaptive learning rate BP algorithm interchangeably adjust the network weights, so that the two algorithms are complementary. It gives full play to the PSO's global optimization ability and the BP algorithm local search advantage, to overcome the slow convergence speed and easily falling into local weight problems. Simulation results show that this diagnostic method can be used for tolerance analog circuit fault diagnosis, with a high convergence rate and diagnostic accuracy.