Life Prediction Method Of MKRVM For Capacitive RF-MEMS Switches

Capacitive radio frequency micro-electromechanical system(RF-MEMS)switches have been widely used in today’s society with rapid development of information because of their small size and superior performance to other devices of the same type.However,the reliability of such switches has become one of the factors restricting their rapid development.Therefore,more and more researchers pay attention to improving the reliability of switch applications.Among them,the life prediction of such switches has gradually become one of the research hotspots.In this research,the elastic coefficient k_b,one of the factors affecting the life of capacitive RF-MEMS switches,is chosen as the research object to study the life length of switches under different coefficients.Firstly,the empirical mode decomposition with bandwidth constraints is used to denoise the life data obtained in the experimentSecondly,an improved sine and cosine optimization algorithm based on differential evolution is used to obtain the sparse function of multi-kernel correlation vector machine.The lifetime of these switches with different elastic coefficients is predicted by multi-core correlation vector machine algorithm.Finally,the actual data obtained from the experiment are used to test the methods involved in this paper,and the comparison experiments with other methods are carried out.The life prediction method proposed in this paper can obtain the prediction result within 0.2143 s,and the resulting health index is 3.1843e+06 s,which is closest to the original data of 3.1732e+06 s.At the same time,it can be concluded that this type of switch has the longest life when its elastic coefficient is in the range of 4-16 N/m.