Modelling nonlinear vehicle dynamics with neural networks

The nonlinear modelling ability of neural networks has been widely recognised as an effective tool to identify and control dynamic systems, with applications including nonlinear vehicle dynamics which this paper focuses on using multi-layer perceptron networks. Existing neural network literature does not detail some of the factors which effect neural network nonlinear modelling ability. This paper investigates into and concludes on required network size, structure and initial weights, considering results for networks of converged weights. The paper also presents an online training method and an error measure representing the network's parallel modelling ability over a range of operating conditions. Copyright © 2010 Inderscience Enterprises Ltd.

Assessing the road-damaging potential of heavy vehicles

The relative influence of various heavy vehicle design features on road-damaging potential is discussed. Testing procedures that could be used to measure the road-damaging potential of heavy vehicles are examined. A validated vehicle simulation is used to examine some of the characteristics of dynamic tyre forces generated by typical leaf sprung and air sprung articulated heavy vehicles for typical highway conditions. The proposed EC suspension test is simulated and the results compared with dynamic tyre forces generated under highway conditions. It is concluded that the road-damaging potential of a vehicle cannot be assessed by the simplistic parametric measurement of the proposed EC test. It is questionable whether a vehicle that passes the test will be any more 'road friendly' than one that fails.