Neural network control of functional neuromuscular stimulation systems: computer simulation studies

Abstract

A neural network control system has been designed for the control of cyclic movements in Functional Neuromuscular Stimulation (FNS) systems. The design directly addresses three major problems in FNS control systems: customization of control system parameters for a particular individual, adaptation during operation to account for changes in the musculoskeletal system, and attaining resistance to mechanical disturbances. The control system was implemented by a two-stage neural network that utilizes a combination of adaptive feedforward and feedback control techniques. A new learning algorithm was developed to provide rapid customization and adaptation. The control system was evaluated in a series of studies on a computer simulated musculoskeletal model. The model of electrically stimulated muscle used in the study included nonlinear recruitment, linear dynamics, and multiplicative nonlinear torque-angle and torque-velocity scaling factors. The skeletal model consisted of a one-segment planar system with passive constraints on joint movement. Results of the evaluation have demonstrated that the control system can provide automated customization of the feedforward controller parameters for a given musculoskeletal system. It can account for changes in the musculoskeletal system by adapting the feedforward controller parameters on-line and it can resist the effects of mechanical disturbances. These results suggest that this design may be suitable for the control of FNS systems and other dynamic systems.

Closed-Loop Neural Network-Based NMES Control for Human Limb Tracking

“…The estimate mismatch for the ideal weight matrices, denoted by and , are defined as (15) and the mismatch for the hidden-layer output error, denoted by , is defined as…”

Computer-based test-bed for clinical assessment of hand/wrist feed-forward neuroprosthetic controllers using artificial neural networks

“…Several studies have investigated the use of ANNs for the control of neuroprostheses (ABBAS and CHIZECK, 1995;ABBAS, 1997;POPOVIC et al, 1999), but only a few studies have been performed to incorporate the use of ANNs in upper extremity control (HoSHIMIYA et al, 1989, MACHINO et al, 1995. The feasibility of using artificial neural networks to co-ordinate hand grasp and wrist angle has been shown in simulations (ADAMCZYK and CRAGO, 1997;2000), but must now be tested experimentally.…”

Modeling biological motor control for human locomotion with functional electrical stimulation

“…Some control engineers have made forays into this marginal field with various control methods, such as model reference control (MRC Hatwell et al 1991), model predictive control ( MPC Towhidkhah 1996), adaptive control (Chizeck 1992;Davidson et al 2002), fuzzy logic control (FLC Davoodi and Andrews 1998;He et al 2001), iterative learning control (ILC Dou et al 1999), H ∞ robust control (Hunt et al 2001), sliding mode control (Jezernik et al 2004), data-driven control (Previdi et al 2004), artificial neural network (ANN) control (Ababas and Chizeck 1995;Chang et al 1997;Jonic et al 1999;Tong and Granat 1999), and so on. Most of the previous work on human walking control was based on optimal methods (Anderson and Pandy 2001;Pandy 2000;Srinivasan and Ruina 2006), which are good at dealing with the problem of redundancy in a complex dynamic system.…”