遗传算法优化BP神经网络在中医按摩机器人中的应用

Application of BP neural network based on genetic algorithm optimization in Chinese medicine massage robot

针对中医按摩设备的临床需求,研制了一种基于多种按摩手法的中医按摩机器人系统。同时,为了提高中医按摩机器人穴位寻找行为规划的精度,提出了一种基于遗传算法优化BP神经网络的中医按摩机器人穴位坐标预测方法,利用遗传算法弥补BP神经网络的缺陷,提高神经网络的预测精度,求解出最优解,保证了中医按摩机器人对患者做出精确的按摩治疗行为决策。并对上述方法进行了实现与仿真,结果表明,该方法对中医按摩机器人寻找患者穴位坐标具有较好的精度和较高的预测准确性。

Aiming at the clinical demand for the Chinese medicine massage devices, a Chinese medicine massage robot system was developed based on the various massage techniques. Besides, in order to improve the precision of the behavior planning for searching acupuncture point coordinates, this paper presented a prediction method for see-king acupuncture point coordinates of Chinese massage robot based on BP neural network （BPNN） optimized by genetic algorithm （GA） . The deficiencies of BPNN can be made up by GA, which can improve the prediction ac-curacy of neural network. And the optimal solution should be solved, so that massage robot can make the precision of the behavior planning for patients^ massage therapy that will be ensured. Then, the presented method was simula-ted. And the results show that massage robot can research acupuncture point coordinates of patients with high pre-diction accuracy.