Orthopedic Actuator Control Using State Machine-Guided Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for controlling orthopedic device actuators face high computational effort and low control accuracy, particularly in pattern recognition tasks involving EMG signals, leading to inefficiencies in decision-making and actuator activation.
Innovation Solution
A control method combining a state machine with a classification process to reduce data classification efforts by focusing on relevant options, using sensor data and classified data to determine actuator activation or deactivation, with feedback mechanisms to optimize classifier parameters and states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pattern recognition methods with EMG signals are used for control, then control accuracy is improved, but computational effort increases significantly
Solution Approach 1:
The control method is segmented into two distinct parts: a state machine that handles high-level decision-making and state transitions, and a classification process that handles specific sensor data interpretation. This segmentation allows each component to specialize, reducing the overall computational burden while maintaining control accuracy.
Solution Approach 2:
The state machine performs preliminary action by pre-determining the current state and possible state transitions based on sensor data. This preliminary classification narrows down the decision space before the more computationally intensive classification process is applied, significantly reducing the computational effort required for pattern recognition.
2Measurement precision
If comprehensive pattern recognition is applied to all sensor data, then control accuracy improves, but processing time increases
Solution Approach 1:
Different processing approaches are applied to different aspects of sensor data based on their local quality requirements. The state machine handles temporal patterns and state transitions with simpler logic, while the classification process focuses on specific sensor data features. This localized specialization reduces overall processing time while maintaining classification accuracy where needed.
3Adaptability or versatility
If state machine with multiple states is used, then control versatility improves, but device complexity increases
Solution Approach 1:
The classification process acts as an intermediary between the sensor data and the state machine. It translates complex sensor data into simplified classification results that the state machine can process efficiently. This intermediary layer reduces the complexity of the state machine while maintaining control versatility by handling the computational complexity in a dedicated classification module.
Data Source
AI summary
The invention relates to a method for controlling at least one actuator (4) of an orthopedic device (2) with an electronic control device (E), which is coupled to the actuator (4) and at least one sensor (8) and which has an electronic processor (μC) for processing sensor data (s), wherein at least one state machine (SM) in which states (z) of the orthopedic device (2) and state transitions of the actuator (4) are determined is stored in the control device (E), wherein a classifier (K) in which sensor data (s) and/or states (z) are automatically classified within the scope of a classification method is stored in the control device (E), wherein the state machine (SM) and the classification method are used in combination and, on the basis of the classification and the states (z), a decision is made about the manner of activating or deactivating the actuator (4) as a control signal.