جستجوی مقالات مرتبط با کلیدواژه "remaining useful life (rul)" در نشریات گروه "فنی و مهندسی"

This paper proposes a remaining useful life (RUL) prediction method that uses the peak of the vibration acceleration signal as an appropriate feature to indicate the degradation process in the rolling element bearings (REBs). In the first step, this feature is transformed into a stationary time series using logarithmic transformation. That is because the long short-term memory neural network (LSTM-NN) works better with the stationary time series. Training the LSTM-NN is performed by this stationary time series as the input and the response is the training time series with values shifted by one time step. Therefore, the LSTM-NN learns to predict the value of the next time step at each point. In other words, to forecast the values of multiple time steps in the future, previous forecasted steps are used as inputs. Next, the values of the future time steps are returned to the main non-stationary form to predict the trend of the peak in the future. Importantly, new measured data can be used to perform new predictions. For this purpose, for every new measured data, the LSTM-NN repeats the mentioned steps and generates a new trend. This algorithm is a trend-dependent method. Therefore, an REB that has a slow degradation stage in its life, which is corresponding to the growth and expansion of defects in REBs, is appropriate to be studied by this algorithm. This method is implemented on two REBs from PRONOSTIA accelerated-life test which have been used by many researchers in the literature. According to the prediction results, the remaining time that peak amplitude trend touches a given threshold is provided. If this threshold is a criterion for the end of life (EoL), this method can be used to determine the RUL. The performance of the proposed method has been evaluated and the presented results are in a good agreement with the experimental data.

Maintenance is one of the most important elements in any industry. Next to manufacturing, it probably has utmost importance in the production of industrialgoods.It has even higher priority when rotary machines are used. Having an appropriate algorithm for maintenance can prevent human and financial problems in such industries. In recent times, various methods of remaining useful life (RUL) prognosis have been proposed for rotary machines, but there is not a comprehensive review article that can well differentiate different methods. Herein, after describing the meaning of remaining useful life, the three most commonly used prognosis methods, including data-driven approach, model-based approach and hybrid prognostics approach, are elaborated upon. Subsequent to that, concept and mathematics of RUL in rotary machines for each method, have been discussed. Toward the end, there are constructive suggestions for researchers in this field in terms of dealing with RUL and PHM.

The Residual Useful Life (RUL) provides an estimate of the amount of remaining useful life before a system failure depends on present conditions and past operating profiles. In this paper, RUL is estimated based on reliability and for convergence to more realistic results, the effect of operating environment conditions in the form of risk factors (covariates) is also involved in the analysis. These environmental conditions are sometimes tangible and "Observable" and sometimes it is not possible to determine and include them in the analysis and are analyzed under the heading of “Un-observed risk factors” using the frailty model. RUL analysis of a case study of the loading system (Shovel Komatsu 1250) of the Sungun copper mine, based on 8-months information, has shown that Weibull mix proportional hazard (W-MPHM) has the best fit on the data. In this model, four factors including shift risk, rock kind, load system type and rainfall with risk rates of 2.66, 3.79, 0.204 and 1.18 have been obtained as the most effective factors. System RUL became zero in the next two scenarios in about 40 hours. Comparing W-MPHM and Ex-PHM over 80 hours showed that the concurrence of the reliability curve in the second model is greater than the first model and in fact, the reliability decline rate is higher at the beginning of the range. This result reflects the impact of intangible risk factors on system performance analysis, regardless of which will result in significant inconsistency of the results.

Determination of degradation status and estimating remaining useful life are two main activities in prognostics and health management. These two main activities can be perceived as the problem of multi-sensor data fusion. These sensors contain information including speed, pressure, and temperature. In terms of evidence theory, the information obtained from each of these sensors can be regarded as a part of the evidence and determination of degradation status and estimating remaining useful life based upon this information can be considered as the problem of multi-sensor data fusion. In this article, the Dempster-Shafer theory has been employed as a tool for modeling and multi-sensor data fusion as an indicator of the health status of the turbofan. In this regard, initially, the theory of evidence has been reviewed and then how to model the remaining useful life estimation problem by multi-sensor data fusion within the framework of the concepts of this theory including mass function, focal elements and rules of evidence composition is explained. This paper has introduced a new approach for combining the results of different estimates of remaining useful life through determining the weighs. Furthermore, it has offered two different scenarios to specify the similarity between the system under study and the available evidence. Finally, to appraise the proposed method, the turbofan engines data set (C-MAPSS) has been used as it has been extensively addressed in literature by researchers. According to the results, the proposed method revealed better score and performance compared with other available methods in the literature.

In this research، the evaluation of cavitation threshold detection and the automation of the detection process with regard to the Remaining Useful Life (RUL) of the Sefidrood power plant turbine، has been studied. The input of generated model by MATLAB program includes data driven from kaplan hydro turbine located on Tarik hydro power plant. The proposed model is based on 61 features resulting from 6 cavitation sensitivity parameters and 17 operational conditions. For training in MATLAB program, 12 individual data sets and 4095 unique combinations were created and 408 data were selected for examination. The training data combined with sensor rating and cavitation sensitivity feature were employed to predict the cavitation and the best training data set with 98% accuracy. The results showed that the use of a fully automated process for sensitivity determination and cavitation classification was more suitable than the use of a process based on manually selected thresholds. Furthermore, considering the operational conditions and RUL, the automation of determination of cavitation threshold without human intervention was much more accurate.

Development of monitoring systems to Fault detection, in Offensive and defensive systems, UAV, aircraft and other complex systems technically make it possible and favorable, Predictive diagnosis of faults.
Health management model and predict equipment failures (PHM) were created in recent years by formation a strong bond of Science in Engineering, Computer and reliability. For this reason, more intelligent approaches in maintenance, have been using in intelligent fault diagnosis and prediction. Discovering useful knowledge about the diagnosis faults and life prediction of military equipment and determine the readiness of equipment can be effective to determining the ability continuity preparedness of equipment in military missions in battle situations. The problem is how we can present the method for determining the ability continuity preparedness equipment in military missions in battle situations?
In this study, by using PHM system, equipment, component or system health can be known at any point and time and prevent the occurrence of failure, also, it is possible to achieve a zero defects.
On the other hand, in defense equipment’s and systems, it will be prevented of sudden failure of the entire system of creation and of human and financial costs resulting from the irreparable avoid this problem, so, the aim of this research is a continuation of equipment in the military mission .

In this research, an intelligent method is introduced for remaining useful life prediction of an internal combustion engine timing belt based on its vibrational signals. For this goal, an accelerated durability test for timing belt was designed and performed based on high temperature and high pre tension. Then, the durability test was began and vibration signals of timing belt were captures using a vibrational displacement meter laser device. Three feature functions, namely, Energy, Standard deviation and kurtosis were extracted from vibration signals of timing belt in healthy and faulty conditions and timing belt failure threshold was determined. The Artificial Neural Network (ANN) was used for prediction and monitoring vibrational behavior of timing belt. Finally, the ANN method based on Energy, Standard deviation and kurtosis features of vibration signals was predicted timing belt remaining useful life with accuracy of 98%, 98% and 97%, respectively. The correlation factor (R2) of vibration time series prediction by ANN and based on Energy, Standard deviation and kurtosis features of vibration signals were determined as 0.87, 0.91 and 87, respectively. Also, Root Mean Square Error (RMSE) of ANN based on Energy, Standard deviation and kurtosis features of vibration signals were calculated as 3.6%, 5.4% and 5.6%, respectively.