The paper presents an investigation into parallel processing techniques for real-time adaptive control of a flexible beam structure. Three different algorithms, namely simulation, control and identification are involved in the adaptive control algorithm. These are implemented on a number of uniprocessor and multiprocessor, homogeneous and heterogeneous, computing platforms involving transputers, digital signal processing devices and several general purpose sequential processors. The partitioning and mapping of the algorithms on the homogeneous and heterogeneous architectures is also explored. The interprocessor communication speed is investigated to establish the real-time performance aspects of the processors on the basis of the nature of the algorithms involved. A close investigation into the performance of several compilers is made and discussed within the context of real-time implementations. Finally, a comparison of the results of the implementations is made, on the basis of real-time communications performance, computation performance and compiler performance, to lead to merits of design of parallel systems incorporating fast processing techniques for real-time control applications.
