CMAC Neural Network Control for High Precision Motion Control in the Presence of Large Friction

Abstract

Precision requirements in ultra-precision machining are often given in the order of micrometers or sub-micrometers. Machining at these levels requires precise control of the position and speed of the machine tool axes. Furthermore, in machining of brittle materials, extremely low feed rates of the machine tool axes are required. At these low feed rates there is a large and erratic friction characteristic in the drive system which standard PID controllers are unable to deal with. In order to achieve the desired accuracies, friction must be accurately compensated in the real-time servo control algorithm. A learning controller based on the CMAC algorithm is studied for this task.

Optimal design of motion control for scan tracking measurement: A CMAC approach

“…In comparison to other neural networks, CMAC has the advantage of very fast learning, and it has the unique property of quickly training certain areas of memory without affecting the whole memory structure, which is called local generalization. The advantage in training speed is very important in real-time applications [18][19][20][21][22], and the local generalization is particularly suitable for local area features prediction in scan measuring processes. Fig.…”

Local sparse coding control of CVPSTs

“…The CMAC was first proposed by Albus (1971Albus ( , 1975aAlbus ( , 1975b and since then, it has been modified and improved. These studies focused on the development of algorithms (Abdelhameed Magdy et al, 2002;Hsu Yuan et al, 2002;Commuri and Lewis, 1997), improvements of CMAC structure, and applications (Cembrano et al, 1997;Larsen et al,1995;Kim et al, 2002;Pan et al, 1996). Lin and Chiang (1997) described the CMAC technique using a mathematical formulation and used this formulation to study the CMAC's convergence properties.…”

How to prevent undesired oscillation in NC rotary table

“…The nonlinear term of friction and its effect on the positioning systems have been studied by Armstrong et al (1994); Adams and Payandeh (1996). To achieve accurate positioning, the friction is modeled and it is compensated by incorporating adaptive (Yang and Tomizuka, 1988), fuzzy logic (Popovic et al, 1995), neural network control (Larsen et al, 1995), and hybrid fuzzy-neural control (Kazuo and Toshio, 1996). Although the problem of pure friction nonlinearities on the control system has been well studied, a small number of researchers have discussed combined nonlinearity of plants such as machine tools.…”