Traditionally, rotor smoothing has been performed by acquiring vibration phase and amplitude at a few locations in the fixed-frame during dedicated maintenance test flights, in which the flight crew acquires the data at specified ground, hover and forward flight conditions. Although this process is effective, it is time consuming and expensive. A method to reduce or eliminate special maintenance test flights is highly desirable. In this paper, the use of vibration data acquired continuously throughout the flight for rotor smoothing is studied. Vibration data for one AH-64A Apache was acquired both continuously and manually. The vibration characteristics and recommended adjustments for each method are compared. The solution from the continuously collected vibration data was applied to the aircraft. The results demonstrate that this method may be effective at smoothing both main and tail rotors via small adjustments between maintenance flights on aircraft that do not have a regime-based rotor smoothing data acquisition capability.

A general, neural network based algorithm has been developed and applied to the problem of helicopter rotor smoothing. This approach provides non-parametric mappings between the spaces of rotor adjustment and vibration measurements, which are derived directly from empirical data, and permits to relax the usually used linearity assumption. Additionally, the rotor smoothing solutions are optimized to minimize not only the predicted vibration levels and track split but also the number of required adjustment moves. The neural network rotor smoothing system is a part of the VMEP (Vibration Management Enhancement Program) PC Ground Base Station program and has been successfully applied to the AH-64 Apache and UH-60 Blackhawk helicopters. Applications to other types of helicopters are under development.

Helicopter Rotor Smoothing (Track and Balance) is a periodic maintenance task required to minimize rotor induced aircraft vibrations at the fundamental (once per revolution) rotor frequency. We have designed and implemented a general, neural network based software system for rotor smoothing. Neural networks provide non-parametric mappings between the spaces of adjustments and vibration measurements. In the network training process, these mappings are extracted from experimental data without any assumptions about their functional form. On the other hand, when the experimental data available for training is not complete, simulated data based on model dependencies (linear or other) may be also incorporated into the neural network model. The neural networks are easily updated (retrained) if new data becomes available thus allowing the system to evolve and mature in the course of its use.The customization of the system for helicopters of different types is facilitated by general-purpose software for application development, which includes preparation of flight data and neural network training. It is worth noting that the prototype applications developed up to date required relatively modest amount of flight data (20-30 flights).The neural network system has been applied to Apache (AH-64), Blackhawk (UH-60), and Kiowa Warrior (OH-58D) helicopters as part of the Vibration Management Enhancement Program (VMEP). Preliminary results are very encouraging. In the verification tests, we were able to shorten the smoothing time for AH-64, with all of the rotor smoothing procedures completed in 2 to 4 flights. In all cases, the neural network approach produced solutions with experimentally verified low vibration levels and small track split. The system has also demonstrated the ability to detect errors in implementation of the smoothing adjustments. Application to other types of helicopters is considered.