In this paper, a methodology to obtain a reliability model for time dependent strength is discussed. A conditional probability density function was evaluated considering the strength follows normal distribution with changing mean and variance over time. The methodology was developed taking into account the nonlinear degradation of strength. Maximum likelihood estimation method was used along with Jaya algorithm to estimate the model parameters. The life prediction is based on the probability that the minimum strength is less than the predetermined failure threshold.  The proposed methodology was applied to a data of solder strengths in automotive circuits. It was found that the proposed model gives promising results with faster compilation time.