Diagnosis of faults in complex, real-time control systems is a complicated task that has resisted solution by traditional methods. We have shown that neural networks can be successfully employed to diagnose faults in digitally controlled powertrain systems. This paper discusses the means we use to develop the appropriate databases for training and testing in order to select the optimum network architectures and to provide reasonable estimates of the classification accuracy of these networks on new samples of data. Recent work applying neural nets to adaptive control of an active suspension system is presented.

It works rather like the BB-8 robot from Star Wars, and could change the way we drive. Goodyear has revealed a radical new spherical tire powered by AI and linked to the car by magnetic force so it can rotate on any axis in any direction. The firm says it will be able to sense road conditions and adapt accordingly, turning itself into either a wet or dry weather configuration instantly. Working like human muscles, the smart tire can re-shape the individual sections of the tire's tread design, adding'dimples' for wet conditions (left) or smoothing the tread for dry conditions (right) Made of super-elastic polymer, the tire's bionic skin has a flexibility similar to that of human skin, allowing it to expand and contract. This outer layer covers a foam-like material that is strong enough to remain flexible despite the weight of a vehicle.