针对坐立转换平衡能力评估存在测量仪器缺失和数据指标单一的不足，研制了一种采集肢体多点压力的坐立转换工效学特征测量装置，可实现同步记录肢体手部、足部及臀部的垂直压力时序数据。为覆盖平衡能力从正常状态到不同程度衰退的典型梯度，实验共纳入年轻人、社区活力老人与康复医院老人85名，采集起坐行为中原始多通道压力信号，采用滤波加和、片段截取、归一化以及阶段划分等预处理操作；按时间、力量、平衡中心三个类别提取55个候选特征，经过单因素检验、共线性剔除与前向逐步回归筛选，构建足部力发展率、手部压力时间积分与足部最小压力三项关键特征变量。基于该特征组合建立多元有序 Logistic 回归模型划分平衡等级，并采用十次重复五折交叉验证评估性能。结果显示：模型AIC为39.20，Pseudo R² 为 0.843，三项变量均达统计显著性（P＜0.05）；重复交叉验证平均分类准确率为91.06%，表现出良好的拟合度和稳健预测能力。回归分析表明，足部力发展率与足部最小压力的数值越高表征更佳平衡能力，而手部压力时间积分数值越高表征平衡能力较差。本文通过所设计的坐立转换工效学测量设备采集时序数据，进行有序Logistic回归建模，可实现较为准确的平衡能力分类，有望为老年人平衡能力评估提供新的方法。

To address the lack of measurement devices and limited data indicators in current sit-to-stand (STS) balance assessments, a novel ergonomic measurement device was developed to capture multi-point vertical pressure signals from the hands, feet, and hips during the STS process. The system enables synchronized acquisition of time-series pressure data across key body regions. To represent a typical gradient of balance abilities from normal to various levels of decline, a total of 85 participants were recruited, including young adults, community-dwelling older adults, and elderly patients from rehabilitation hospitals. Raw multi-channel pressure signals were collected during the STS movement and preprocessed using filtering, summation, segmentation, normalization, and phase division. Fifty-five candidate features were extracted based on time, force, and center-of-pressure dimensions. After univariate testing, collinearity elimination, and forward stepwise regression, three key features were selected: rate of force development in the feet, pressure-time integral of the hands, and minimum foot pressure. An ordinal logistic regression model was constructed using these features to classify balance ability levels, and its performance was evaluated via 10-times repeated 5-fold cross-validation. The model achieved an AIC of 39.20, a Pseudo R² of 0.84, and an average classification accuracy of 91.06%, with all three variables showing statistical significance (P < 0.05). Regression analysis revealed that higher foot force development rate and higher minimum foot pressure were associated with better balance, while a higher hand pressure-time integral indicated poorer balance, reflecting compensatory reliance on upper limbs. This study demonstrates that STS time-series pressure data collected by the proposed measurement device, combined with ordinal logistic modeling, can enable accurate balance classification and offers a promising new method for evaluating balance ability in older adults.