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.

Objective To investigate the longitudinal performance of a surgically implanted neuroprosthesis for lower extremity exercise, standing, and transfers after spinal cord injury. Design Case series. Setting Research or outpatient physical therapy departments of four academic hospitals. Participants 15 subjects with thoracic or low-cervical level spinal cord injuries who had received the 8-channel neuroprosthesis for exercise and standing. Interventions After completing rehabilitation with the device, the subjects were discharged to unrestricted home use of the system. A series of assessments were performed before discharge and at a follow-up appointment approximately one year later. Main Outcome Measure(s) Neuroprosthesis usage, maximum standing time, body weight support, knee strength, knee fatigue index, electrode stability, and component survivability. Results Levels of maximum standing time, body weight support, knee strength, and knee fatigue index were not statistically different from discharge to follow-up (p > 0.05). Additionally, neuroprosthesis usage was consistent with subjects choosing to use the system on approximately half of the days during each monitoring period. Although the number of hours using the neuroprosthesis remained constant, subjects shifted their usage to more functional standing versus more maintenance exercise, suggesting that the subjects incorporated the neuroprosthesis into their lives. Safety and reliability of the system were demonstrated by electrode stability and a high component survivability rate (>90%). Conclusions This group of 15 subjects is the largest cohort of implanted lower extremity neurorprosthetic exercise and standing system users. The safety and efficiency data from this group, and acceptance of the neuroprosthesis as demonstrated by continued usage, indicate that future efforts towards commercialization of a similar device may be warranted.

This paper reports on an investigation of feedback control of coronal plane posture in paraplegic subjects who stand using functional neuromuscular stimulation (FNS). A feedback control system directed at regulating coronal plane hip angle in neutral position was designed, implemented, and evaluated in two paraplegic subjects. The control system included sensor mounting and signal processing techniques, a two-stage feedback controller, stimulation hardware, and a set of percutaneous intramuscular electrodes. The feedback controller consisted of two-stages in cascade: a modified discrete-time proportional-integral-derivative (PID) stage and a nonlinear single-input, multiple-output stage to determine the stimulation to be sent to several muscles. The focus of this work was on evaluating the performance of the feedback controller by comparing the response of the feedback-controlled system to that of an open-loop stimulation system. In an evaluation based on temporal response characteristics the controlled system exhibited a 41% reduction in root-mean-squared (rms) error (where error is defined as the deviation from the desired angle), a 52% reduction in steady-state error, and a 22% reduction in hip compliance. In addition, the feedback-controlled system exhibited significant reductions in variability of these measures on several days. These results demonstrate the ability of the feedback controller to improve the temporal response characteristics of the FNS control system.