CAJ | 학술논문

基于灰色理论适合进行小样本、贫信息不确定型系统建模以及最小二乘支持向量机不需要求解二次规划就能求得模型参数的优点，建立了灰色最小二乘支持向量机模型。针对温度、振动等环境载荷影响石英挠性加速度计内部参数变化，使石英挠性加速度计参数随着时间发生漂移从而难以准确描述的问题，提出了基于灰色最小二乘支持向量机进行石英挠性加速度计参数预测的方法。为了验证方法的有效性，针对两年自然贮存条件的石英挠性加速度计的参数标定值进行了建模，计算结果表明灰色最小二乘支持向量机具有很好的预测效果。
기우회색이론괄합진행소양본、빈신식불학정형계통건모이급최소이승지지향량궤불수요구해이차규화취능구득모형삼수적우점，건립료회색최소이승지지향량궤모형。침대온도、진동등배경재하영향석영뇨성가속도계내부삼수변화，사석영뇨성가속도계삼수수착시간발생표이종이난이준학묘술적문제，제출료기우회색최소이승지지향량궤진행석영뇨성가속도계삼수예측적방법。위료험증방법적유효성，침대량년자연저존조건적석영뇨성가속도계적삼수표정치진행료건모，계산결과표명회색최소이승지지향량궤구유흔호적예측효과。
In view that small sample copy and poor information uncertainty problem can be easily solved by grey theory, and least squares support vector machine model parameters can obtain good results without quadratic programming, the grey least squares support vector machine is modeled. Since temperature and vibration and other environment factors have significant effects on the inner parameters of quartz flexure accelerometer, the accelerometer parameters are difficult to be described exactly. This paper put forward an accelerometer parameters’ prediction method based on the grey least squares support vector machine. A 2-year natural environmental scale value of accelerometer parameters is molded. The experimental results show that the grey least squares support vector machine has got the best prediction performance.