Research On Prediction Of Equipemnt’s Heath Based On Modified Hidden Semi-markov Model

With the rapid development of science and technology,the industrial age is advancing towards the information age.The emergence of high-tech such as digital twinning,intelligent manufacturing and flexible production brings the industrial production to a more intelligent,humanized and digital stage.This also puts forward higher requirements for the reliability of industrial production equipment.How to guarantee the availability and reliability of equipment is an urgent industrial production problem to be solved in today’s era.To ensure the efficiency and reliability of equipment,more efficient and perfect equipment health management methods are needed.The traditional health management mode is no longer suitable for the complex equipment and multi-component equipment in today’s era.How to seek innovation and improvement is the focus of research in the field of health management.Therefore,this topic takes the ubiquitous large-scale mechanical production equipment as the research object,and the prior information is insufficient as the premise,considering the equipment aging,signal integration and other complex scenarios,and carries out the health mode diagnosis and residual life prediction of the equipment respectively.The main research content is divided into the following three parts:(1)In order to solve the problem of large deviation between Hidden Markov Model and actual equipment health diagnosis,this paper developed an improved Degenerated Hidden Markov Model(DGHMM)with a core of the quasi power relation.First,the model adopted the degradation factors,modeling the process of recession for the equipment’s continuous decrease in performance.Compared with the conventional exponential accelerated degradation,the quasi power relation accelerated degradation can better describe the process that the performance of the equipment decreases gradually with the increase of service age.Then,the improved genetic algorithm can replace the conventional EM algorithm for parameters’ estimation,which overcomes the limitation that the EM algorithm is easy to fall into local optimization.At the same time,in terms of the limitation of life prediction problem as a result of the Hidden Markov Model must obey exponential distribution,an algorithm named greed &approximation based on approximation algorithm and Viterbi algorithm came out,and to seek maximum probability remaining observation,for the purpose of seeking maximum probability dynamically surplus state path,to predict the residual life of equipment.Finally,the proposed method is validated and evaluated with the data set of caterpillar hydraulic pumps.The results show that the method of equipment health diagnosis and life prediction based on the improved degraded hidden Markov model is more effective in describing equipment’s degeneration and the accuracy of equipment state diagnosis,and is also feasible in the prediction of residual life.(2)Health diagnosis and prognosis of equipment is considered crucial for condition-based maintenance.This paper presents a prognostics health and monitoring scheme framework based on the modified hidden semi-Markov model(HSMM).A novel scalarization method for raw signals is developed based on the Weibull distribution with a short-time function window.Then,the conglutination coefficient and deterioration kernel are introduced into the HSMM to simulate the inherent deterioration process of the equipment.A co-evolutional algorithm based on a genetic algorithm and salp swarm algorithm is proposed to estimate the parameters of the modified HSMM.A model base is established based on several sub-models with different fault modes for the health prognosis and diagnosis of equipment.Based on this,the residual useful life of the equipment can be predicted using the historical whole useful life data and the current working conditions.Finally,the proposed method is verified using turbofan engine datasets,and the results show that it is effective and feasible.And the proposed scheme can provide novel solutions for the health prognostics of non-vibration signal.(3)To solve the problem of large residual life prediction error,a residual life prediction model based on the Higher-order Hidden Semi Markov Model(HOHSMM)is proposed,which is established according to the Hidden Semi Markov Model.And an order reduction method is proposed based on permutation and composite nodes mechanism,accordingly improve the state transition matrix and the observation matrix,making the higher order model can be converted into the corresponding first-order model.Thus there will be more nodes dependency information storing in the parameters to be estimated.Secondly,Estimation Maximal algorithm is replaced by intelligent optimization algorithm group to estimate the parameters and optimize the structure of the model,which simplifies the topology of the high-order model.Thirdly,the state lingering variable in the higher-order model are defined and derived,and the prediction method based on polynomial fitting is used to realize the prediction of equipment residual life in the case of unknown prior distribution.Finally,the framework is validated by the hydraulic pump data set of Caterpillar Inc.The results show that the residual life prediction method based on the High-order Hidden Semi Markov Model is more effective.The above three research works are progressive,which provides a new idea for the equipment maintenance strategy based on conditions under the mass production mode,and can effectively improve the overall benefits of enterprises and reduce costs.