基于BP神经网络的医疗设备精准预防性维护
|
摘要
目的:针对当前医疗设备预防性维护(preventive maintenance,PM)中存在的问题,基于误差反向传播(back propagation,BP)神经网络实现医疗设备精准PM。方法:以医疗设备的运行数据、仪器使用率、工作时长、历史维护情况等作为输入数据,建立3层的BP神经网络,以BP神经网络经过训练得出的连接权值系数作为决策模型,预测医疗设备的维护期限、维护部件及维护项目。结果:可以预测出医疗设备的维护期限、维护部件及维护项目等,实现了医疗设备精准PM。结论:BP神经网络可以根据医疗设备运行参数及信息化平台上的数据学习决策,提高医疗设备PM的精准度,从而预防在诊断或治疗过程中因医疗设备故障带来的不良事件。
Objective To execute medical equipment precise preventive maintenance(PM) based on error back propagation(BP) neural network to solve the existing problems. Methods A 3-layer BP neural network was established by using the operation parameter data of medical equipment, instrument utilization rate, working time and historical maintenance were as input data, and the weight coefficient obtained by BP neural network after training was regarded as decision model to predict the maintenance date, maintenance components and maintenance items, etc. Results Medical equipment maintenance could be predicted involving in the maintenance time limit, maintenance components and maintenance items so as to realize precise preventive maintenance. Conclusion BP neural network can learn and make decisions through the operation parameters of medical equipment and the data on the information platform, improving the accuracy of preventive maintenance of medical equipment, preventing adverse events caused by medical equipment in the process of diagnosis or treatment. [Chinese Medical Equipment Journal,2019,40(7):78-80,85]
Objective To execute medical equipment precise preventive maintenance(PM) based on error back propagation(BP) neural network to solve the existing problems. Methods A 3-layer BP neural network was established by using the operation parameter data of medical equipment, instrument utilization rate, working time and historical maintenance were as input data, and the weight coefficient obtained by BP neural network after training was regarded as decision model to predict the maintenance date, maintenance components and maintenance items, etc. Results Medical equipment maintenance could be predicted involving in the maintenance time limit, maintenance components and maintenance items so as to realize precise preventive maintenance. Conclusion BP neural network can learn and make decisions through the operation parameters of medical equipment and the data on the information platform, improving the accuracy of preventive maintenance of medical equipment, preventing adverse events caused by medical equipment in the process of diagnosis or treatment. [Chinese Medical Equipment Journal,2019,40(7):78-80,85]
引文
[1]吴翠峰.关于医院医疗设备维护保养的若干思考[J].中国科技博览,2010(35):475.
[2]戴顺平.医院大型医疗设备管理浅析[J].医疗卫生装备,2013,34(8):118-120.
[3]吕颖莹,王吉鸣,冯靖祎.医疗设备预防性维护现状分析及探讨[J].中国医疗设备,2016,31(2):92-94.
[4]尹军,陈维平.基于JCI标准的医疗设备预防性维护体系探讨[J].医疗卫生装备,2014,35(12):135-137.
[5] SIMMON H.神经网络原理[M].叶世伟,史忠植,译. 2版.北京:机械工业出版社,2004.
[6] STUART E D. Artificial neural networks,back propagation,and the Kelley-Bryson gradient procedure[J]. J Guidance,1990,13(5):926-928.
[7] HENRY J K. Gradient theory of optimal flight paths[J]. Ars J,1960,30(10):947-954.
[8] DREYFUS S E. The numerical solution of variational problems[J]. J Math Anal Appl,1962,5(1):30-45.
[9]袁亚湘,孙文瑜.最优化理论与方法[M].北京:科学出版社,1997.
[10]李董辉,童小娇,万中.数值最优化[M].北京:科学出版社,2005.
[11]严嘉伟,张飞鸿,赵丽萍,等.血透临床工程师对血透机的日常管理及维护保养[J].中国医疗设备,2013,28(12):88-90.
[2]戴顺平.医院大型医疗设备管理浅析[J].医疗卫生装备,2013,34(8):118-120.
[3]吕颖莹,王吉鸣,冯靖祎.医疗设备预防性维护现状分析及探讨[J].中国医疗设备,2016,31(2):92-94.
[4]尹军,陈维平.基于JCI标准的医疗设备预防性维护体系探讨[J].医疗卫生装备,2014,35(12):135-137.
[5] SIMMON H.神经网络原理[M].叶世伟,史忠植,译. 2版.北京:机械工业出版社,2004.
[6] STUART E D. Artificial neural networks,back propagation,and the Kelley-Bryson gradient procedure[J]. J Guidance,1990,13(5):926-928.
[7] HENRY J K. Gradient theory of optimal flight paths[J]. Ars J,1960,30(10):947-954.
[8] DREYFUS S E. The numerical solution of variational problems[J]. J Math Anal Appl,1962,5(1):30-45.
[9]袁亚湘,孙文瑜.最优化理论与方法[M].北京:科学出版社,1997.
[10]李董辉,童小娇,万中.数值最优化[M].北京:科学出版社,2005.
[11]严嘉伟,张飞鸿,赵丽萍,等.血透临床工程师对血透机的日常管理及维护保养[J].中国医疗设备,2013,28(12):88-90.