Lincheng Shen

A Bionic Neural Network for Fish-Robot Locomotion

A bionic neural network for fish-robot locomotion is presented. The bionic neural network inspired from fish neural network consists of one high level controller and one chain of central pattern generators (CPGs). Each CPG contains a nonlinear neural Zhang oscillator which shows properties similar to sine-cosine model. Simulation results show that the bionic neural network presents a good performance in controlling the fish-robot to execute various motions such as startup, stop, forward swimming, backward swimming, turn right and turn left.

Design of a Central Pattern Generator for Bionic-robot Joint with Angular Frequency Modulation

The paper proposes an artificial central pattern generator (CPG) for bionic-robot joint control. The neural oscillator adopted to produce rhythmic pattern is specially designed from original sin-cosine oscillator model. An amplitude neural estimator consisted of two neurons is presented to provide sensor feedback to CPG control. The artificial CPG can adapt itself to the physical system parameters variety by rhythmic movement angular frequency modulation.

Morphological Measurement and Analysis of Gymnarchus Niloticus

Gymnarchus niloticus swims by undulations of a long-based dorsal fin, while its body axis is in many cases held straight during swimming. This paper provides a brief relevant introduction to Gymnarchus niloticus, which belongs to the African freshwater electric eels but can inspire our bionic interests in propulsion besides its abilities in electric sensing. A special larva of Gymnarchus niloticus was morphologically measured by photographing it with a piece of scale-calibrated paper as the background. Then we analyzed the data by a CFD-aided approach. Detailed flow patterns around the larva and a NACA0012 hydrofoil were respectively calculated and visualized at the Reynolds number of 7350 or so. The results show that the profile of Gymnarchus niloticus is well streamlined.

Locomotion of Gymnarchus niloticus : Experiment and kinematics

In addition to forward undulatory swimming, Gymnarchus niloticus can swim via undulations of the dorsal fin while the body axis remains straight; furthermore, it swims forward and backward in a similar way, which indicates that the undulation of the dorsal fin can simultaneously provide bidirectional propulsive and maneuvering forces with the help of the tail fin. A high-resolution Charge-Coupled Device (CCD) imaging camera system is used to record kinematics of steady swimming as well as maneuvering in G. niloticus. Based on experimental data, this paper discusses the kinematics (cruising speed, wave speed, cycle frequency, amplitude, lateral displacement) of forward as well as backward swimming and maneuvering.During forward swimming, the propulsive force is generated mainly by undulations of the dorsal fin while the body axis remains straight. The kinematic parameters (wave speed, wavelength, cycle frequency, amplitude) have statistically significant correlations with cruising speed. In addition, the yaw at the head is minimal during steady swimming. From experimental data, the maximal lateral displacement of head is not more than 1% of the body length, while the maximal lateral displacement of the whole body is not more than 5% of the body length. Another important feature is that G. niloticus swims backwards using an undulatory mechanism that resembles the forward undulatory swimming mechanism. In backward swimming, the increase of lateral displacement of the head is comparatively significant; the amplitude profiles of the propulsive wave along the dorsal fin are significantly different from those in forward swimming. When G. niloticus does fast maneuvering, its body is first bent into either a C shape or an S shape, then it is rapidly unwound in a travelling wave fashion. It rarely maneuvers without the help of the tail fin and body bending.

A Hybrid Neural Network Method for UAV Attack Route Integrated Planning

This paper proposes a hybrid neural network method to solve the UAV attack route planning problem considering multiple factors. In this method, the planning procedure is decomposed by two planners: penetration planner and attack planner. The attack planner determines a candidate solution set, which adopts Guassian Radial Basis Function Neural Networks (RBFNN) to give a quick performance evaluation to find the optimal candidate solutions. The penetration planner adopts an alterative Hopfield Neural Network (NN) to refine the candidates in a fast speed. The combined effort of the two neural networks efficiently relaxes the coupling in the planning procedure and is able to generate a near-optimal solution within low computation time. The algorithms are simple and can easily be accelerated by parallelization techniques. Detailed experiments and results are reported and analyzed.

Dynamic analysis on the bionic propulsor imitating undulating fin of aquatic animals

The undulating fin propulsion mode belonged to one of MPF (median and/or paired fin) has a great potential and a bright prospect because of the remarkable advantages including capable of producing vector thrust, smaller disturbance to ambient flow field, as well as tending to transplant to underwater robots. In this paper, we will introduce a novel bionic propulsor that imitates the structure and function of the undulating fin of aquatic animals, and propose a simplified computational model to analyze the dynamics of the propulsor. The hydrodynamic model of the bionic propulsor including six components of forces and moments is derived theoretically. In addition, the basic relationships between the hydrodynamics of the bionic propulsor with the undulating motion parameters and geometric parameters of the fin surface as well as the velocity induced by its carrier are studied by means of simulation method. At last, the validity of the analytic method presented by the paper and the rationality of its relevant conclusions are preliminarily verified through conducting the thrust and moment test to the bionic propulsor.

CFD Validation of the Optimal Arrangement of the Propulsive Dorsal Fin of Gymnarchus niloticus

Gymnarchus niloticus, a typical freshwater fish, swims by undulations of a long-based dorsal fin aided by the two pectoral fins, while commonly it holds its body rigid and straight. The long flexible dorsal fin is the main propulsor of G. niloticus; it has also considerable influence on the streamline profile. This paper proposes a CFD approach to validate that the natural arrangement of the propulsive dorsal fin is optimal. Using morphological data and a smoothness-keeping algorithm, the dorsal fin is ‘virtually’ moved forward and backward with several displacements from the natural location. For each case, we reconstruct geometry, generate CFD grids, and calculate the pressure, viscous and total drag coefficients respectively. The results show that the pressure and total drag coefficients increase whether the dorsal fin is displaced forward or backward, and that greater displacement from its original position leads to greater pressure and total drag coefficients. This suggests that the natural position of the dorsal fin is significant for maintaining the fish’s streamline profile and reducing drag.

Dynamic Analysis of a Novel Artificial Neural Oscillator

This paper proposes a novel artificial neural oscillator consisted of two neurons with excellent control properties. The mutual connections between the neurons are just linear functions and determine the oscillation angular frequency. And each neuron has a nonlinear self-feedback connection to hold up oscillation amplitude. The dynamics of the neural oscillator was modelled with nonlinear coupling functions. And the stability, amplitude, angular frequency of the oscillator are determined independently by three parameters of the functions. Since it has simple structure and favorable control advantages, it can be used in bionic robots locomotion control system. The first application is an artificial central pattern generator (CPG) controller for bionic robots joint. The second is a bionic neural network for fish-robots locomotion control.

Advances and Trends of Bionic Underwater Propulsors

In recent twenty years, tens of the bionic underwater prototype propulsors which imitate aquatic animals have been invented. The bionic principles hand classification of bionic propulsors were presented firstly. The main advance of the bionic propulsors in the world has been listed in table form. Then the bottlenecks which include low efficiency and massive mechanism, hard-shelled reverse control method and exterior hydro-dynamic analysis are discussed. The future trends of the bionic underwater propulsors are forecasted. The main potential breakthroughs include innovative smart actuators and bionic neural control methods.

Optimization of tactical aircraft weapon delivery using Tactics Templates

This paper proposes a new method with a three-level architecture named tactics template (TT) for tactical aircraft attack path planning and optimization. Distinguished from the traditional path planning algorithms, the TT method extends the ability to deal with tactics and actions rather than trajectories, which maintains the benefits of traditional path planning algorithms while well-satisfying pilots need. As a preliminary study, the TT method is analyzed and tested under the conditions of single aircraft releasing conventional bombs. However, this method is applicable to more complex cases and other potential application areas.