基于GRNN神经网络的电子装备状态预测方法研究
|
摘要
状态预测是装备维修保障领域的重要研究方向,电子装备状态的自动监测与故障预测对于保证装备的正常使用、提高装备的战备完好性、减轻维护使用人员的工作量具有重要意义。首先,基于GRNN神经网络建立了电子装备的状态预测模型;其次,通过采集电子装备电路中的状态参数预测可能产生的故障并自动生成解决方案;最后,对状态预测模型进行了仿真分析,比较了不同神经网络模型下的预测效果,验证了模型的可行性与预测的准确性。
State prediction has become a major direction in the field of equipment maintenance. For electronic equipment,state monitoring and fault prediction it is of great significance for improvement of operation readiness and decrease of workload. Firstly,state prediction model is established based on GRNN neural network,and then,state parameters of electronic equipment are collected. Based on that,possible failure is predicted and further resolution is generated automatically. Finally,the state prediction model is simulated and analyzed, and the prediction effects under different neural network models are compared, and the feasibility and prediction accuracy are verified.
State prediction has become a major direction in the field of equipment maintenance. For electronic equipment,state monitoring and fault prediction it is of great significance for improvement of operation readiness and decrease of workload. Firstly,state prediction model is established based on GRNN neural network,and then,state parameters of electronic equipment are collected. Based on that,possible failure is predicted and further resolution is generated automatically. Finally,the state prediction model is simulated and analyzed, and the prediction effects under different neural network models are compared, and the feasibility and prediction accuracy are verified.
引文
[1]殷海俊,黄惠宁.舰船电子装备的状态监测与故障诊断[J].舰船电子工程,2015,35(1):144-146.
[2]许庆芬,黄高明,黄傲林.基于证据理论的舰船电子信息装备技术状态评估方法[J].舰船电子工程,2017,37(8):110-114
[3]杨森,孟晨,王成.基于模糊SVDD的电子装备状态评估模型研究[J].计算机工程与设计,2013,34(2):676-680.
[4]闻新,李新,张兴旺,等.应用Matlab实现神经网络[M].北京:国防工业出版社,2015.
[5]Salim Heddam. Generalized Regression Neural Network Based Approach as a New Tool for Predicting Total Dissolved Gas(TDG)Downstream of Spillways of Dams:a Case Study of Columbia River Basin Dams,USA[J]. Environmental Processes,2017,4(1):235-253.
[6]OVUNC P,TULAY Y. Genetic Optimization of GRNN for Pattern Recognition without Feature Extraction[J]. Expert Systems with Applications,2008,34(4):2444-2448.
[7]孔国利,张璐璐.遗传算法的广义回归神经网络建模方法[J].计算机工程与设计,2017,38(2):488-493.
[8]郁磊,史峰,王辉,等. Matlab智能算法30个案例分析[M].北京:北京航空航天大学出版社,2015:248-256.
[9]侯晓东,王永攀,杨江平,等.基于状态的武器电子装备故障预测研究综述[J].系统工程与电子技术,2018,40(2):360-367.
[10]李永军,胡昌林,赵广宁.基于BIT的电子装备状态与故障预测系统[J].武器装备自动化,2005,24(2):22-23.
[11]董磊,任章,李清东.基于多因子高阶模糊变动的飞机操纵面故障趋势预测[J].中南大学学报(自然科学版),2013,44(S/1):232-237.
[12]秦旭东.火控系统故障诊断专家系统的研究[D].沈阳:沈阳工业大学,2017.
[2]许庆芬,黄高明,黄傲林.基于证据理论的舰船电子信息装备技术状态评估方法[J].舰船电子工程,2017,37(8):110-114
[3]杨森,孟晨,王成.基于模糊SVDD的电子装备状态评估模型研究[J].计算机工程与设计,2013,34(2):676-680.
[4]闻新,李新,张兴旺,等.应用Matlab实现神经网络[M].北京:国防工业出版社,2015.
[5]Salim Heddam. Generalized Regression Neural Network Based Approach as a New Tool for Predicting Total Dissolved Gas(TDG)Downstream of Spillways of Dams:a Case Study of Columbia River Basin Dams,USA[J]. Environmental Processes,2017,4(1):235-253.
[6]OVUNC P,TULAY Y. Genetic Optimization of GRNN for Pattern Recognition without Feature Extraction[J]. Expert Systems with Applications,2008,34(4):2444-2448.
[7]孔国利,张璐璐.遗传算法的广义回归神经网络建模方法[J].计算机工程与设计,2017,38(2):488-493.
[8]郁磊,史峰,王辉,等. Matlab智能算法30个案例分析[M].北京:北京航空航天大学出版社,2015:248-256.
[9]侯晓东,王永攀,杨江平,等.基于状态的武器电子装备故障预测研究综述[J].系统工程与电子技术,2018,40(2):360-367.
[10]李永军,胡昌林,赵广宁.基于BIT的电子装备状态与故障预测系统[J].武器装备自动化,2005,24(2):22-23.
[11]董磊,任章,李清东.基于多因子高阶模糊变动的飞机操纵面故障趋势预测[J].中南大学学报(自然科学版),2013,44(S/1):232-237.
[12]秦旭东.火控系统故障诊断专家系统的研究[D].沈阳:沈阳工业大学,2017.