Search

This paper addresses task assignment (TA) for multivehicle systems. Multivehicle TA problems are formulated as a combinatorial optimization problem and further as a global optimization problem. To fulfill heterogeneous tasks, cooperation among heterogeneous vehicles is incorporated in the problem formulations. A collaborative neurodynamic optimization approach is developed for solving the TA problems. Experimental results on four types of TA problems are discussed to substantiate the efficacy of the approach.

The effect of impingement jet on heat transfer in a rotating wedge-shaped ribbed trailing edge was experimentally investigated in this study. The inlet Reynolds number varied from 10000 to 61000, a...

In this paper, a method is presented for antidisturbance constrained control of autonomous underwater vehicles subject to uncertainties and constraints. The uncertainties stem from uncertain hydrodynamic parameters, modeling errors, and unknown forces due to the ocean currents in an underwater environment. An antidisturbance constrained controller is developed by designing a command governor and a disturbance observer. Specifically, the disturbance observer is developed to estimate the lumped disturbance composed of parametric model uncertainties, modeling errors, and unknown environmental forces. The command governor is designed for optimizing command signals in the receding horizon within the state and input constraints. The command governor is formulated as a quadratically constrained quadratic programming problem. To facilitate online implementations, a neurodynamic optimization method based on a one-layer recurrent neural network is employed for solving the quadratic optimization problem subject to inequality constraints with finite-time convergence. The efficacy of the proposed antidisturbance constrained control method for autonomous underwater vehicles is substantiated via simulations and comparisons.

This article presents a collaborative neurodynamic optimization (CNO) approach to multivehicle task assignments (TAs). The original combinatorial quadratic optimization problem for TA is reformulated as a quadratic unconstrained binary optimization (QUBO) problem with a quadratic utility function and a penalty function for handling load capacity and cooperation constraints. In the framework of CNO with a population of discrete Hopfield networks (DHNs), a TA algorithm is proposed for solving the formulated QUBO problem. Superior experimental results in four typical multivehicle operation scenarios are reported to substantiate the efficacy of the proposed neurodynamics-based TA approach.

This paper addresses the travelling salesman problem (TSP) based on collaborative neurodynamic optimization (CNO). In the CNO approach to TSP, a population of discrete Hopfield networks are employed for searching local optimal solutions and repeatedly reinitialized by using the particle swarm optimization rule towards a global optimal solution. Experimental results for solving four TSP benchmarks are reported to substantiate the efficacy of the CNO approach.

This article presents a neurodynamic approach to nonlinear programming. Motivated by the idea of sequential quadratic programming, a class of two-timescale multilayer recurrent neural networks is presented with neuronal dynamics in their output layer operating at a bigger timescale than in their hidden layers. In the two-timescale multilayer recurrent neural networks, the transient states in the hidden layer(s) undergo faster dynamics than those in the output layer. Sufficient conditions are derived on the convergence of the two-timescale multilayer recurrent neural networks to local optima of nonlinear programming problems. Simulation results of collaborative neurodynamic optimization based on the two-timescale neurodynamic approach on global optimization problems with nonconvex objective functions or constraints are discussed to substantiate the efficacy of the two-timescale neurodynamic approach.

Dynamic modularity is one of the fundamental characteristics of the human brain. Cooperative divide and conquer strategy is a basic problem solving approach. This chapter proposes a new subnet training method for modular neural networks with the inspiration of the principle of “an expert with other capabilities.” The key point of this method is that a subnet learns the neighbor data sets while fulfilling its main task: learning the objective data set. Additionally, a relative distance measure is proposed to replace the absolute distance measure used in the classical method and its advantage is theoretically discussed. Both methodology and empirical study are presented. Two types of experiments respectively related with the approximation problem and the prediction problem in nonlinear dynamic systems are designed to verify the effectiveness of the proposed method. Compared with the classical learning method, the average testing error is dramatically decreased and more stable. The superiority of the relative distance measure is also corroborated. Finally, a mind-gut frame is proposed.

This paper discusses dynamically weighted model predictive control based on two-timescale neurodynamic optimization. Minimax optimization problems with dynamic weights in objective functions are used in the model predictive control. The minimax optimization problems are solved by using a two-timescale neurodynamic optimization approach. Examples on controlling HVAC (heating, ventilation, and air-conditioning) and CSTR (cooling continuous stirred tank reactor) systems are elaborated to substantiate the efficacy of the control approach.

This article contains a new subnet training method for modular neural networks, proposed with the inspiration of the principle of “an expert with other capabilities”. The key point of this method is that a subnet learns the neighbor data sets while fulfilling its main task: learning the objective data set. Additionally, a relative distance measure is proposed to replace the absolute distance measure used in the classical subnet learning method and its advantage in the general case is theoretically discussed. Both methodology and empirical study of this new method are presented. Two types of experiments respectively related with the approximation problem and the prediction problem in nonlinear dynamic systems are designed to verify the effectiveness of the proposed method. Compared with the classical subnet learning method, the average testing error of the proposed method is dramatically decreased and more stable. The superiority of the relative distance measure is also corroborated.

This paper addresses receding horizon control of a heating, ventilation, and air-conditioning (HVAC) system based on neurodynamic optimization. The receding horizon control problem for the HVAC system is formulated as sequential quadratic programs, which are solved by using a neurodynamic optimization model. Simulation results on temperature setpoint regulation of the HVAC system are discussed to substantiate the efficacy of the approach.

The heat transfer characteristics in a rectangular channel under rotating conditions with impingement jet and film holes was studied. The key features of the geometry are multiple impingement jets and film holes in the leading edge model. The jet Reynolds number (Rej), jet rotation number (Roj) and buoyancy number (Buo) varied from 5000 to 10,000, from 0 to 0.24, and from 0 to 0.57, respectively. Four temperature ratio (TR) cases (0.07, 0.10, 0.13, and 0.16) and three channel orientations (β = 90, 135, and 180) are selected. For all experiment cases, the spacing of jet-to-jet (s/d = 3) and jet-to-target surface (l/d = 3) were held constant. In the non-rotating cases, the heat transfer level of the T2 region (stagnation point), impinged by the jet directly, is the strongest and about twice to the other regions. The overall heat transfer distribution almost does not change significantly as the Rej varied from 5000 to 10,000. The jet rotation number plays an important role under the rotation state. For the orientation of 135°, the Coriolis force deflects the jet and weakens the heat transfer of the medium radius in the T2 region. No obvious variation in the heat transfer distribution for different temperature ratio under non-rotating and rotating cases was observed. The Coriolis force generated by different rotation directions causes two influences on the flow structure, leading to the different heat transfer distribution. The overall heat transfer level for the orientation of 90° and 135° varies little (5%) with the rotation number, while that of 180° decreases much (25%).

This article addresses neurodynamics-based model predictive control of continuous-time under-actuated mechatronic systems. The control problem is formulated as a global optimization problem based on sampled data, which is solved by using a collaborative neurodynamic approach. The closed-loop system is proven to be asymptotically stable. Specific applications on control of autonomous surface vehicles and unmanned wheeled vehicles are elaborated to substantiate the efficacy of the approach.