FES has achieved significant efficacy in the rehabilitation of patients with motor dysfunction. However, existing closed-loop electrical stimulators suffer from the drawbacks of large size and difficulty in accurately assessing fatigue level. In this study, a wearable electrical stimulator system with adaptive adjustment of parameters was proposed to address this drawback. Additionally, muscle fatigue was induced via 60% MVC, and sEMG signals were acquired during this process. MF, MPF, and SampEn were extracted to validate their relationships with muscle fatigue. A fatigue detection algorithm based on I-value was introduced to dynamically adjust the stimulation parameters in real time to avoid fatigue and injury caused by overstimulation. In addition, the system’s effectiveness in real-world scenarios was validated based on different \({I}_{at}\) . The WBAN heterogeneous architecture technology adopted in this paper, together with the lightweight wearable design, greatly reduces the weight of the device. The weight of the signal acquisition device is only 3g, and the electrical stimulation device is only 3.2g. All the functions of the fabricated device are basically in accordance with the expectations.