| With the continuous development of modern electronic technology and information technology,military equipment has become increasingly diversified and complicated.New features,new situations and new problems have emerged in equipment maintenance.However,because the traditional task forecasting technology is relatively mechanized and simplistic,and cannot fully consider the influence of various factors,it has been difficult to meet the needs of information security.Therefore,in order to ensure that the equipment can operate stably,reliably,and efficiently in actual tasks,it is very necessary to conduct in-depth research on the application of equipment mission prediction technology.This paper takes this as the research goal,summarizes the research status of task prediction and related theories,and constructs two task prediction models of planned maintenance and fault maintenance.The main research work of this paper is as follows:(1)To solve the problem of equipment centralized repair,this paper constructed a task prediction model based on planned maintenance.Firstly,this paper deeply studies the theoretical basis of planned maintenance.Secondly,this paper analyzes the equipment maintenance system and maintenance interval,and determines the optimization goal of the model built.Then,based on the maintenance standards of different types of equipment,this paper comprehensively analyzes the data of equipment utilization,and formulates the annual utilization plan.Finally,this paper designs BSO algorithm(i.e.beetle antennae search algorithm and particle swarm optimization)to solve the model,and makes full use of the advantages of the two intelligent algorithms to improve the global and local search ability of the hybrid algorithm.The simulation result shows that the model established in this paper is in line with the actual requirements,and the annual utilization plan is reasonable,which can make the motorcycle hours meet the echelon reserve and solve the problem of centralized repair.(2)To solve the problem of fault prediction based on equipment historical data,this paper takes vehicle bearing as the research object,and constructs a task prediction model based on fault maintenance,which is mainly divided into three parts: feature extraction,fault diagnosis and fault prediction.Firstly,this paper uses variational mode decomposition(VMD)and multi-scale permutation entropy(MPE)to solve the problem that the fault features in bearing vibration signals were difficult to extract.Secondly,in view of the slow convergence speed and low accuracy of the whale optimization algorithm,the introduction of von neumann topology and adaptive weights for improvement can appropriately adjust the balance between the global search ability and the local search ability.Then,the improved whale algorithm(WOA)is used to optimize the parameters and penalty factors of the kernel function of the least squares support vector machine(LSSVM),and the rolling bearing fault diagnosis model is established.Then,this paper uses the improved whale algorithm to optimize the parameters and penalty factors of the least squares support vector machine kernel function,and establishes a fault diagnosis model for rolling bearings.Finally,this article uses genetic algorithm and levenberg-marquarat algorithm to optimize BP network,and makes full use of the advantages of the two algorithms.The simulation result shows that the accuracy of the fault diagnosis proposed in this paper can reach 96.49%,and the prediction accuracy can reach 93.96%. |
