Research on fault prediction method of typical equipment in open-pit mine based on MCMC Algorithm

Large equipment is an important part of the open-pit mining process system, and the effective use of equipment directly determines the production efficiency of open-pit mines. In order to solve the problem of fault prediction of typical equipment in open-pit mine and reduce the failure rate and maintenance cost of equipment, a fault prediction algorithm for typical equipment of open pit mine based on Markov Monte Carlo method is proposed. The algorithm uses the Markov Monte Carlo method to estimate the equipment fault data, and obtains the parameter λ of the homogeneous Poisson process corresponding to the number of equipment failures; Then according to the nature of the bathtub curve, the λ is continuously corrected and fitted to determine the value of the Poisson distribution parameter λc of the number of failures in the current state of the device; Reusing the inter-point spacing of random points in the homogeneous Poisson process is a property of a series of exponentially distributed random variables that are independent of each other, The reciprocal of λc is used as the estimated value of the exponential distribution parameter to determine the exponential distribution obeyed by the equipment fault occurrence time interval, and last use the exponential distribution to predict the equipment failure occurrence time. The results show that: The Poisson distribution parameters obeyed by the number of equipment failures change dynamically with time; The maintenance time of equipment failure increases with the increase of service life of equipment (medium-sized faults in equipment and increased number of medium-sized faults); The algorithm proposed in this paper is verified by CSRF and is reasonable and effective and can be used to predict the failure of typical equipment in open-pit mines. Numerical simulation results show: when the external environment does not change significantly, the algorithm can accurately and effectively predict the fault occurrence time and fault category of typical equipment in open pit mines. The research results can not only provide a basis for the enterprise scientific development of equipment preventive maintenance plans, but also provide effective basic decision data for the construction of intelligent open-pit mines.