摘要
传统的神经网络故障诊断方法对于新发生故障的误诊率较高,提出了将反面选择算法与神经网络相结合的故障诊断方法.该故障诊断方法对已知故障类型和未知故障类型都具有较准确的诊断能力.往复压缩机气阀的故障诊断实例表明该方法的有效性.
Traditional approach to neural network fault diagnosis can not efficiently diagnose new fault types.In order to solve the problem,the fault diagnosis approach based on negative selection algorithm and neural network is proposed.The fault diagnosis method has better diagnosis capability for both known faults and unknown faults.The diagnosis result of gas valves for piston compressors shows the approach proposed is efficient.
出处
《大庆石油学院学报》
CAS
北大核心
2005年第6期104-106,共3页
Journal of Daqing Petroleum Institute
基金
国家自然科学基金资助项目(50475183)
黑龙江省教育厅科学技术研究项目(10541010)
关键词
反面选择算法
神经网络
故障诊断
活塞压缩机
negative selection algorithm
neural network
fault diagnosis
piston compressor
