Nonlinearity and implicitness are common degradation features of the stochastic degradation equipment for prognostics.These features have an uncertain effect on the remaining useful life(RUL)prediction of the equipmen...Nonlinearity and implicitness are common degradation features of the stochastic degradation equipment for prognostics.These features have an uncertain effect on the remaining useful life(RUL)prediction of the equipment.The current data-driven RUL prediction method has not systematically studied the nonlinear hidden degradation modeling and the RUL distribution function.This paper uses the nonlinear Wiener process to build a dual nonlinear implicit degradation model.Based on the historical measured data of similar equipment,the maximum likelihood estimation algorithm is used to estimate the fixed coefficients and the prior distribution of a random coefficient.Using the on-site measured data of the target equipment,the posterior distribution of a random coefficient and actual degradation state are step-by-step updated based on Bayesian inference and the extended Kalman filtering algorithm.The analytical form of the RUL distribution function is derived based on the first hitting time distribution.Combined with the two case studies,the proposed method is verified to have certain advantages over the existing methods in the accuracy of prediction.展开更多
In this paper the Hamming distance is used to contr ol individual difference in the process of creating an original population, and a peak-depot is established to preserve information of different peak-points. So me n...In this paper the Hamming distance is used to contr ol individual difference in the process of creating an original population, and a peak-depot is established to preserve information of different peak-points. So me new methods are also put forward to improve optimization performance of genet ic algorithm, such as point-cast method and neighborhood search strategy around peak-points. The methods are used to deal with genetic operation besides of cr ossover and mutation, in order to obtain a global optimum solution and avoid GA ’s premature convergence. By means of many control rules and a peak-depot, the new algorithm carries out optimum search surrounding several peak-points. Alon g with evolution of individuals of population, the fitness of peak-points of pe ak-depot increases continually, and a global optimum solution can be obtained. The new algorithm searches around several peak-points, which increases the prob ability to obtain the global optimum solution to the best. By using some example s to test the modified genetic algorithm, the results indicate what we have done makes the modified genetic algorithm effectively to solve both of linear optimi zation problems and nonlinear optimization problems with restrictive functions.展开更多
基金supported by the National Defense Foundation of China(7160118371901216)the China Postdoctoral Science Foundation(2017M623415)
文摘Nonlinearity and implicitness are common degradation features of the stochastic degradation equipment for prognostics.These features have an uncertain effect on the remaining useful life(RUL)prediction of the equipment.The current data-driven RUL prediction method has not systematically studied the nonlinear hidden degradation modeling and the RUL distribution function.This paper uses the nonlinear Wiener process to build a dual nonlinear implicit degradation model.Based on the historical measured data of similar equipment,the maximum likelihood estimation algorithm is used to estimate the fixed coefficients and the prior distribution of a random coefficient.Using the on-site measured data of the target equipment,the posterior distribution of a random coefficient and actual degradation state are step-by-step updated based on Bayesian inference and the extended Kalman filtering algorithm.The analytical form of the RUL distribution function is derived based on the first hitting time distribution.Combined with the two case studies,the proposed method is verified to have certain advantages over the existing methods in the accuracy of prediction.
文摘In this paper the Hamming distance is used to contr ol individual difference in the process of creating an original population, and a peak-depot is established to preserve information of different peak-points. So me new methods are also put forward to improve optimization performance of genet ic algorithm, such as point-cast method and neighborhood search strategy around peak-points. The methods are used to deal with genetic operation besides of cr ossover and mutation, in order to obtain a global optimum solution and avoid GA ’s premature convergence. By means of many control rules and a peak-depot, the new algorithm carries out optimum search surrounding several peak-points. Alon g with evolution of individuals of population, the fitness of peak-points of pe ak-depot increases continually, and a global optimum solution can be obtained. The new algorithm searches around several peak-points, which increases the prob ability to obtain the global optimum solution to the best. By using some example s to test the modified genetic algorithm, the results indicate what we have done makes the modified genetic algorithm effectively to solve both of linear optimi zation problems and nonlinear optimization problems with restrictive functions.
