Diaphragm electrical stimulation waveform optimization method and device based on energy control

By using an energy-controlled diaphragmatic electrical stimulation waveform optimization method, and leveraging intelligent algorithms and hardware architecture to achieve dynamic energy constancy, the problem of energy instability in traditional diaphragmatic electrical stimulation systems is solved, thereby improving the reliability and safety of treatment.

CN122440985APending Publication Date: 2026-07-24YAOYI TECHNOLOGY (YUNNAN) CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610348405.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-20
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Traditional diaphragmatic electrical stimulation systems cannot dynamically match tissue impedance changes caused by individual differences, resulting in unstable energy that may cause muscle spasms, local pain, or nerve damage. Furthermore, existing technologies lack sufficient recognition accuracy in multi-task training, affecting efficacy and safety.

Method used

An energy-controlled diaphragmatic electrical stimulation waveform optimization method is adopted. By integrating multi-dimensional intelligent algorithms with a dedicated hardware architecture, multi-source data is collected in real time to build an intelligent evaluation model. The hyperparameters are optimized using the elite-based butterfly optimization algorithm to achieve dynamic constancy of stimulation energy and improve safety.

Benefits of technology

This has improved the reliability and safety of electrical stimulation therapy, significantly enhanced energy control precision and response speed, and provided more efficient and safer individualized adaptive treatment options.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a diaphragm electrical stimulation waveform optimization method and device based on energy control, and relates to the technical field of energy measurement and control and artificial intelligence. The method comprises the following steps: collecting multi-source data reflecting an electrical stimulation process, preprocessing the multi-source data, and constructing a training data set based on the preprocessed multi-source data; constructing an intelligent evaluation model fusing time sequence feature mining and a double-task prediction function, and performing staged training on the intelligent evaluation model according to the training data set, so that the model has a combined prediction capability of neural recruitment efficiency and subjective comfort of different stimulation waveforms and parameter combinations; based on the joint prediction capability of the intelligent evaluation model, performing automatic optimization on key hyper-parameters of the model by adopting an elite-based butterfly optimization algorithm; the dynamic constancy of the preset target stimulation energy is taken as a constraint condition, and the optimal stimulation waveform and parameters are decided according to the intelligent evaluation model after training and hyper-parameter optimization, so that the double improvement of the stimulation curative effect and the safety is realized.
Need to check novelty before this filing date? Find Prior Art