模糊减法聚类算法下大型医疗设备故障可视化诊断系统  

Visual diagnosis system for large medical equipment faults under fuzzy subtraction clustering algorithm

作　　者：金鑫 叶真 朱婷婷 JIN Xin;YE Zhen;ZHU Tingting(Seventh People’s Hospital of Shanghai University of TCM(Shanghai Seventh People’s Hospital),Shanghai 200137,China)

机构地区：[1]上海中医药大学附属第七人民医院(上海市第七人民医院),上海200137

出　　处：《电子设计工程》2025年第6期85-90,共6页Electronic Design Engineering

摘　　要：针对医疗设备故障诊断不足问题,研究基于模糊神经网络与减法聚类算法开发一种故障可视化诊断系统,通过对大型医疗设备故障建模分析,完成系统可视化开发。该项技术创新点在于引入模糊神经网络构建诊断模型,提升对复杂特征数据识别效果;同时引入减法聚类算法优化模型参数,提升模型诊断效率。在诊断误差分析中,研究技术迭代收敛时均方根误差与平均绝对误差分别为0.012与0.015,同类技术中误差最低。而在故障诊断准确度方面研究技术综合表现也最佳。经实验该技术满足大型医疗设备的高效故障诊断要求,研究内容将为医疗设备智能化故障检测提供技术支持。Aiming at the problem of insufficient diagnosis of medical equipment faults,a fault visualization diagnosis system based on fuzzy neural network and subtraction clustering algorithm is developed.Through modeling and analyzing the faults of large medical equipment,the system visualization development is completed.The innovation of this technology lies in the introduction of fuzzy neural networks to construct diagnostic models and improve the recognition performance of complex feature data;Simultaneously introducing subtraction clustering algorithm to optimize model parameters and improve model diagnostic efficiency.In the analysis of diagnostic errors,the root mean square error and mean absolute error of the iterative convergence of the research technique are 0.012 and 0.015,respectively,with the lowest error among similar techniques.And in terms of the accuracy of fault diagnosis,the comprehensive performance of research technology is also the best.Through experiments,this technology meets the efficient fault diagnosis requirements of large medical equipment,and the research content will provide technical support for intelligent fault detection of medical equipment.

关 键 词：模糊神经网络 减法聚类算法 医疗设备 故障诊断 可视化 

分 类 号：TP99[自动化与计算机技术]