[1]樊立天,江金达,夏景涛,等.基于人工神经网络的系统可靠度预测[J].中国医学物理学杂志,2023,40(2):232-237.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.018]
　FAN Litian,JIANG Jinda,XIA Jingtao,et al.System reliability prediction based on artificial neural network[J].Chinese Journal of Medical Physics,2023,40(2):232-237.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.018]
点击复制

基于人工神经网络的系统可靠度预测()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第2期
页码:
232-237
栏目:
医学人工智能
出版日期:
2023-03-03

文章信息/Info

Title:
System reliability prediction based on artificial neural network
文章编号:
1005-202X（2023）02-0232-06
作者:
樊立天; 江金达; 夏景涛; 崔飞易; 缪吉昌; 王婷婷; 夏红林; 王胜军; 陈宏文
南方医科大学南方医院医学工程科， 广东 广州 510515
Author(s):
FAN Litian;  JIANG Jinda;  XIA Jingtao;  CUI Feiyi;  MIAO Jichang;  WANG Tingting;  XIA Honglin;  WANG Shengjun;  CHEN Hongwen
Department of Medical Engineering, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China
关键词:
人工神经网络; 统计分布; 可靠度预测; 拟合精度
Keywords:
Keywords: artificial neural network statistical distribution reliability prediction fitting accuracy
分类号:
R318；TB114. 3
DOI:
DOI:10.3969/j.issn.1005-202X.2023.02.018
文献标志码:
A
摘要:
提出一种基于人工神经网络的可靠度预测方法，以系统故障时间和对应的中位秩估计值训练网络，在系统故障时间范围内选取大量的故障时间点并求其预测的累积分布函数值，然后结合样条回归法求出系统累积分布函数曲线，概率密度函数曲线及故障率函数曲线。为验证人工神经网络模型的优越性，以婴儿培养箱等5个系统的故障数据为例，用决定系数R2、均方误差和对数似然函数，与Weibull、Fréchet、Logistic等统计分布模型进行对比，结果表明人工神经网络拟合效果最优。
Abstract:
Abstract: A system reliability prediction method based on artificial neural network is proposed. The network is trained with the system failure data and the corresponding estimate of median rank estimate. A large number of failure time points are selected in the system failure duration, and their predicted cumulative distribution function values are found. Subsequently, the cumulative distribution function curve, probability density function curve, and failure rate function curve of the system are derived using spline regression method. To verify the superiority of the artificial neural network model, taking the failure data of 5 systems such as infant incubator as an example, the proposed model is compared with the statistical distribution models such as Weibull, Fréchet and Logistic using the coefficient of determination R2, mean square error and log-likelihood function. The results show that the artificial neural network fits the best.

相似文献/References:

[1]张丽媛,贾楠,郑晓娜,等.基于人工神经网络多叶准直器叶片位置偏差预测[J].中国医学物理学杂志,2021,38(12):1495.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.008]
　ZHANG Liyuan,JIA Nan,ZHENG Xiaona,et al.Prediction of multi-leaf collimator leaf positional deviations based on artificial neural network[J].Chinese Journal of Medical Physics,2021,38(2):1495.[doi:DOI:10.3969/j.issn.1005-202X.2021.12.008]
[2]陈彦宇,柏朋刚,陈榕钦,等.剂量预测引导的鼻咽癌放疗计划质量定量评估方法[J].中国医学物理学杂志,2022,39(9):1076.[doi:DOI:10.3969/j.issn.1005-202X.2022.09.004]
　CHEN Yanyu,BAI Penggang,CHEN Rongqin,et al.Dose prediction-guided quantitative assessment of the quality radiotherapy plan for nasopharyngeal cancer[J].Chinese Journal of Medical Physics,2022,39(2):1076.[doi:DOI:10.3969/j.issn.1005-202X.2022.09.004]

备注/Memo

备注/Memo:
【收稿日期】2022-10-09 【基金项目】国家重点研发计划（2019YFC0121908）；广东省科技计划项目（2017ZC0068）；广东省自然科学基金（2017ZC0069） 【作者简介】樊立天，研究方向：机器学习，E-mail: fanli960@163.com 【通信作者】陈宏文，高级工程师，研究方向：医疗设备质控管理，E-mail: Chw47922@126.com
更新日期/Last Update: 2023-03-03