CAJ | 학술논문

针对部分高可靠性产品退化规律无法掌握的难题，提出了使用改进粒子群优化-基于神经网络函数（PSO-RBFNN）算法拟合样品退化轨迹、预测伪寿命值的方法。首先，通过改进PSO算法对RBFNN进行训练优化；然后，使用部分测量数据对训练后的RBFNN进行准确度测试；最后，通过RBFNN预测样品退化轨迹，估计出伪寿命值。使用某型电连接器的加速退化试验数据对提出的方法进行了试验验证，成功对该型电连接器进行了寿命预测，得出平均寿命为200412 h。
침대부분고가고성산품퇴화규률무법장악적난제，제출료사용개진입자군우화-기우신경망락함수（PSO-RBFNN）산법의합양품퇴화궤적、예측위수명치적방법。수선，통과개진PSO산법대RBFNN진행훈련우화；연후，사용부분측량수거대훈련후적RBFNN진행준학도측시；최후，통과RBFNN예측양품퇴화궤적，고계출위수명치。사용모형전련접기적가속퇴화시험수거대제출적방법진행료시험험증，성공대해형전련접기진행료수명예측，득출평균수명위200412 h。
According to the problem that the degradation rule of some high-reliability production cannot be acqur-ied, the APSO-RBFNN algorithm, which was ued to fit the degradation path and predict the pseudo lifetime, was proposed. Firstly, RBFNN was trained and optimized through APSO. Then, the accuracy of trained RBFNN was tested with parts of measurements. Lastly, the RBFNN was applied to predict the degradation path of pro-duction and then evaluating the lifetimes. The proposed approach was methodologically explained and experimen-tally was evaluated using accelerated degradation data of some electrical connector. The lifetime of electrical con-nector was successfully predicted and the average lifetime was obtained, 200412 hours.