Prediction Of Remaining Service Life Research Articles

Remaining useful life prediction and state of health diagnosis of lithium-ion batteries with multiscale health features based on optimized CatBoost algorithm

Due to the large-scale application of electric vehicles, the remaining service life prediction and health status diagnosis of lithium-ion batteries as their power core is particularly important, and the essence of RUL prediction and SOH diagnosis is the prediction of remaining capacity. Through the aging experiment of cycle charging and discharging of lithium-ion batteries, the health features of experimental data are extracted for the prediction of remaining capacity. In this paper, a deep feature extraction method based on Bilinear CNN combined with CatBoost algorithm based on fractional order method optimization particle swarm optimization, and ant colony optimization algorithm is proposed for battery remaining capacity prediction. Seven groups of health features extracted from ten groups of battery data were used to input them into the optimized CatBoost algorithm for regression prediction. The results show that the proposed model achieves accurate SOH and RUL prediction, the three evaluation indicators MAE, RMSE, and MAPE of SOH are all within 1.7 % and the error rate of RUL is not higher than 1.5 %, and the test of multiple batteries also proves its strong robustness.

Research on performance degradation patterns of metal rubber components under the coupling of static compression and full immersion corrosive environment

Metal rubber component (MRC) is commonly used in special work conditions such as high temperature/corrosive environments primarily due to its excellent vibration damping/insulation properties. But in special work conditions for a long time, the performance of MRC will deteriorate to a failure to meet the work requirements. Therefore, it is imperative to enhance the performance of MRC and study its performance degradation in special work conditions. In this paper, pickling, silanization and pickle-silanization surface treatments for metal rubber components (MRCs) were carried out. The properties of MRCs after surface treatment under static compression and full immersion corrosive test were studied, and a remaining service life prediction model of MRCs under corrosion condition was established. Compared with MRC without surface treatment (U-MRC), the performance degradation degree of several MRCs was evaluated based on four physical and mechanical parameters - the amplitude of variation in height, average stiffness, energy dissipation, and loss factor. The results indicated that MRCs exhibited different degrees of performance degradation. Among them, pickling-silanized MRC (PS-MRC) has the best corrosion resistance. The stiffness variation amplitude must be nearly 8% smaller than that of U-MRC, and the energy consumption variation amplitude is about 12% smaller than that of U-MRC.

Summarization of Remaining Life Prediction Methods for Special Power Plants

With continuous improvements in integration, totalization and automation, remaining useful life predictions of mechanical equipment have become a key feature of technology and core element of equipment prediction and health management. The traditional method based on degradation mechanisms is not fully capable of predicting remaining useful life, especially for special power plants that use industrial transmissions, barrel launchers, etc. The expected service requirements are higher for condition monitoring and remaining service life prediction. The effective prediction of the remaining useful life of such special power plants is a major challenge and technical bottleneck in the industrial field and national defense equipment construction. This paper analyzes and expands on the research on the remaining life prediction methods for special power plants and analyzes the remaining life prediction methods of existing dynamic models, as well as data-driven and data–model fusion drives, and specific ideas for future research and development in four aspects, including remaining useful life prediction tests supplemented with soft measurements. Additionally, future research directions for the remaining life prediction of special power plants are provided.

Prediction of remaining service life of cement concrete pavement in airfield runway

An improved Remaining Service Life (RSL) prediction model of slab based on strain gauge data was presented in this paper. Numerical simulation models were developed to analyse the responses on airfield pavement slabs for more than 10,935 loading scenarios. Then, the bottom transverse strains of the slab, as well as the slab thickness, elastic modulus of the slab, base thickness and elastic modulus of the base, were used to calculate the Cumulative Damage Factor (CDF) of the slab. The slab was divided into different strips to accurately locate the failure zone. The RSL of the slab calculated by the model developed were compared with result of the FAARFIELD software. The results showed that the RSL prediction method proposed in this paper is within 5% of the results of FAARFIELD. Furthermore, the constructed model for predicting the RSL of slabs can capture the failure regions of airfield runways.

Development of Pavement Performance and Remaining Service Life Prediction Tools for Iowa Jointed Plain Concrete Pavement Systems

Moving Ahead for Progress in the Twenty-First Century (MAP-21) requires US state highway agencies (SHA) to utilize performance-based approaches in their pavement management decision-making processes, and use of a remaining service life (RSL) model would be one of such performance-based approaches for facilitating the pavement management decision-making process for SHAs. In this study, statistical and artificial neural network (ANN)-based pavement performance and RSL models were developed for Iowa jointed plain concrete pavement systems (JPCP) using actual pavement structural, traffic, construction history, and pavement performance records obtained from the Iowa Department of Transportation pavement-management information system database. While both models were found to be potentially useful for project and network level performance and RSL predictions, statistical and ANN-based models were respectively found to be more suitable for project and network level analysis. Using these models, efficient Microsoft Excel-based automation tools were created to predict future performance of a JPCP section and estimate RSL values based on predicted future performance and threshold limits for the performance indicators. Consequence analysis was also conducted to investigate the impact of traffic and preservation treatment (diamond grinding) on the RSL of a JPCP. The tool, also capable of estimating realistic pavement pretreatment and posttreatment performance and RSL, could be successfully used as part of performance-based pavement management strategies and helping decision-makers make better-informed pavement management decisions to properly allocate agency resource expenditures. Moreover, this study provides a better understanding of RSL and the factors that influence both the project and network level RSL.

Remaining service life prediction using road structure performance data with pavement condition index (PCI) and Benkelman beam (BB) methods

The design life of a road is the amount of time a road can take from the time the road is used until the road requires major repairs. The inability of a pavement to reach its design life can be caused by several factors. These factors cause the uncertainty of the service life of the road, so that the remaining service life of the pavement becomes difficult to predict. This study will discuss the condition of the road pavement and predict the remaining service life on the Losari - Pejagan road, Demak ring road, and Rembang - Bulu road sections using the PCI (Pavement Condition Index) and Benkelman Beam (BB) methods. Based on the analysis of road condition assessment, the average PCI value for the Losari - Pejagan road section is 45.76 (poor), for the Demak Ring road section is 74.63 (satisfactory), and for the Rembang - Bulu road section is 50.41 (poor). The results of the analysis of the remaining service life using the PCI method found that 67.2% of all segments on the three road had a remaining service life of less than a year and 32.8% of all segments had a remaining service life of more than 1 year. Using the BB method, it was found that the remaining service life of 93.7% segments on the three road are less than a year and 6.7% segments are more than 1 year.

Implementation of Extreme Learning Machine to Predict Distribution Power Transformer Lifetime

The estimated remaining life of transformers is the most critical factor in maintaining service continuity and quality assurance in distributing electrical energy to customers. Therefore, an accurate approach is needed to predict the remaining life of a distribution power transformer. In this paper, an approach to predict transformer lifetime is carried out by utilizing transformer current, voltage, and temperature. The resulting model estimates the transformer age through Extreme Learning Machine in order to extract the maximum information from the transformer. Tests were performed using the proposed and other classification methods on a 20 kV/380-220V transformer whose remaining life spans between 14 and 26 years. Results show that the proposed method yields the lowest minimum error outperforming the other methods with the selection feature MAE at 0.1076 and MSE at 0.0179. The results further validate that the proposed method can achieve accuracy better than the ones obtained from other transformer remaining service life prediction methods.

Gear Fault Diagnosis and Life Prediction of Petroleum Drilling Equipment Based on SOM Neural Network.

In order to solve the problem that variable working conditions and fault types cannot be diagnosed in gear fault diagnosis of petroleum drilling equipment, four kinds of faults, namely, gear broken tooth, gear crack, gear pitting, and gear wear, are studied in this paper. Based on the SOM neural network algorithm, an intelligent diagnosis model of gear fault is proposed, and the PCA method is used to reduce data dimension and fuse features. The state index of life prediction is determined, and the remaining service life prediction of gear transmission system is predicted based on exponential degradation model. The results show that the accuracy of the SOM model for fault diagnosis is high, and the bearing in gearbox can be replaced or repaired in advance according to the residual life curve, so as to achieve the purpose of predictive maintenance.

Prediction of Remaining Useful Life of the Lithium-Ion Battery Based on Improved Particle Filtering

Remaining useful life (RUL) prediction of lithium-ion batteries plays an important role in battery failure prediction and health management (PHM). By accurately predicting the RUL of the battery, the battery can be replaced accordingly, thereby effectively avoiding the occurrence of an accident and ensuring the normal operation of the entire system. In the prediction of the remaining service life of lithium-ion batteries, it is difficult to ensure accuracy due to the problem of particle degradation and the influence of singular values in the particle filter algorithm. In view of these problems, this article introduces the unscented Kalman algorithm to improve the particle filter algorithm from the perspective of re-weighting the particles, so as to improve the accuracy of the prediction results of the remaining service life of lithium-ion batteries. The improved particle filter is simulated and verified using the battery sample data in the Arbin experimental test platform. Comparing the simulation results with the traditional particle filter method, when the number of reference samples is the same, the PDF width of the prediction results of the improved particle filter algorithm is slightly smaller than that of the particle filter algorithm, indicating that the fluctuation of the prediction result is more accurate. It is proved that the improved particle filter method proposed in this article can provide more accurate battery RUL prediction results and can effectively improve the accuracy and robustness of the remaining service life prediction of lithium-ion batteries.

Thermomechanical Analysis of a Reactor Pressure Vessel under Pressurized Thermal Shock Caused by Inadvertent Actuation of the Safety Injection System

The damage induced pressurized thermal shock (PTS) may pose to a reactor pressure vessel (RPV) is a critical safety requirement assessed as part of the ageing management programme of pressurized water reactors (PWRs). A number of researches have studied PTS initiated mainly by postulated accidents such as loss of coolant accidents (LOCAs). However, investigations on PTS-induced threat on RPV caused by inadvertent actuation of the safety injection, a frequent anticipated transient, have not been thoroughly studied. In this paper, a simplified multistep analysis method is applied to study the thermomechanical status of a two-loop PWR under PTS loads caused by inadvertent actuation of the safety injection system. A direct-coupling thermomechanical analysis is performed using a three-dimensional (3D) RPV finite element model. A 3D finite element submodel (consisting of the highiest stress concentration area in the RPV) and an assumed crack are then used to perform fracture mechanics analysis. Subsequently, the critical integrity parameter-stress intensity factor (SIF) is estimated based on FRANC3D-M-integral method coupled in the multistep simulation. The material fracture toughness of the vessel is computed based on the master curve method with experimental fracture toughness data. The results obtained from the direct coupling stress analysis in comparison with sequential coupling approach demonstrate the effectiveness of the proposed multistep method. Also, comparing SIF results obtained with that calculated based on the conventional virtual crack-closure technique (VCCT) and extended finite element method (XFEM) show good agreement. This study provides a useful basis for future studies on anticipated transient-induced crack propagation and remaining service life prediction of ageing reactor pressure vessels.

Pitting and CO2 corrosion behavior of oil and gas pipeline welds

Abstract A finite element (FE) model is presented in this work that is used to analyze the effect of pitting corrosion on the CO2 corrosion behavior of oil and gas pipeline welds. The FE model contains two parts, i. e., stress calculation of the welded joint using Abaqus software, and of the chemical reaction at the welded joint using COMSOL Multiphysics® software. The effect of transportation pressure, pit depth and welding material on the CO2 corrosion behavior of weld metal was investigated using the FE model. It turned out that the FE model is helpful to instruct the management and to assess the remaining service life prediction of pipelines in the oil and gas industry.

Assessment of remaining service life of deteriorated concrete bridges under imprecise probabilistic information

This paper proposes a framework for the reliability-based remaining service life prediction of existing deteriorated structures considering both aleatory and epistemic uncertainties separately. A Bayesian probability box (p-box) is developed for modelling the epistemic uncertainty by considering the bounds of the distribution parameter, whereas the aleatory uncertainty is modelled as a precise distribution function. The framework allows to automatically update results and the bounds of estimation of remaining service life (RSL) by deploying data from regular and recurrent inspections of bridges, which are typically available in practice. The framework is applied to a real reinforced concrete bridge that has deteriorated due to corrosion of steel reinforcements to assess the capabilities of the proposed method. Results show a notable dispersion of the prediction of the RSL considering the imprecision of data which strongly highlights that the epistemic uncertainty should be considered when making decisions related to existing bridges. In fact, for the example presented, considering the epistemic uncertainty on corrosion of reinforcements could impact the probability of failure by a factor of nearly two. In addition, the updated Bayesian p-box can efficiently quantify significant reductions of epistemic uncertainty if additional information becomes available.

Remaining Service Life Prediction of Aging Concrete Bridges Based on Multiple Relevant Explanatory Variables

AbstractConcrete highway bridge remaining service life has been at the forefront of bridge owners’ concerns for several years in terms of growing bridge maintenance needs. Distresses in concrete br...

Research on remaining service life prediction of platform screen doors system based on genetic algorithm to optimise BP neural network

ABSTRACT The platform screen door system related to the safety of passengers, vehicle and station operation in rail transit is the research object. Relay, the key component of the PSD system, is selected as the breakthrough point, and the number of pull-in is used as the evaluation index of the service life of the relay. The precise and complex mapping between the influencing factors of the relay (coil resistance, pull-in voltage, release voltage, pull-in time, release time and contact resistance) and the remaining service life of the PSD system are established based on genetic algorithm to optimise BP neural network, and a new model for predicting the remaining life of the PSD is constructed. The PSD system of Guangzhou Metro Line 8 – KeCun Station is taken as the experimental test object. By comparing the BP algorithm, the PSO-BP algorithm and the GA-BP algorithm, it is demonstrated in detail how the prediction model can effectively predict the remaining service life of the PSD system with high precision, so that the equipment early warning before failure occurs to ensure the normal operation of subway lines. Experimental examples effectively prove the stability and accuracy of the GA-BP algorithm proposed.

Quantitative determination of corrosion status of rebar by electrochemical parameters

In this paper, the relationship between electrochemical parameters and corrosion status of rebar was analyzed by measuring macro-current and potential difference of self-made anode ladder monitoring system under different environmental conditions.Laboratory tests show that the anode ladder monitoring system can better judge the corrosion status of steel bars and provide a basis for structural durability evaluation and remaining life prediction. Reinforced concrete is the most widely used building material in engineering. The durability of reinforced concrete structure gradually declines under the long-term action of unfavorable factors in using environment. At present, there are many "models" for predicting the durability life of concrete published in the world, and more researches are being carried out. The most studied "model" is the "model" related to corrosion, especially the relationship between reinforcement corrosion and concrete durability, is the most common and in-depth research. The problem of durability of reinforced concrete structures caused by corrosion of reinforcing bar has been paid more and more attention in engineering field. Early detection and diagnosis of reinforcement corrosion is an important prerequisite for durability evaluation, remaining service life prediction and maintenance scheme selection of reinforced concrete structures.The development of accurate and reliable on-site monitoring technology of reinforcement corrosion has become the focus of scholars at home and abroad. In order to monitor the corrosion of reinforcement in concrete, some electrochemical parameters need to be measured by sensors. These electrochemical parameters include: potential distribution, macrocurrent, concrete resistance, and so on. Among them, the measurement of macrocurrent is a relatively simple and easy method, which has been widely used in the measurement of reinforcement corrosion. Using this method, in recent years, many countries have developed anodic sensor systems for monitoring reinforcement corrosion, a typical non-destructive monitoring system for the embedded durability of TRAPEZOIDAL anode ladder concrete structure is developed by the Institute of Civil Engineering, Aachen University of Technology, Germany, the corrosion degree and depth of steel bar in concrete can be measured for a long time by embedding steel bar sensors with different depths in concrete, which has been put into engineering application in many countries. In this paper, a self-made multi-group anode ladder monitoring system is designed in the laboratory. The corrosion status of each anode steel bar and the change of electrochemical parameters are obtained by using the method of half-cell potential test in the environmental solution of different concentrations, the criterion of electrochemical parameters to determine the corrosion status of rebar was obtained.

Research on Life Prediction of Fan Spindle Bearing Based on Gated Recurrent Unit Neural Network

In order to solve the problems of redundancy calculation and inefficiency of traditional machine learning algorithm in dealing with large amount of historical data of fan, a new predictive algorithm based on gated recurrent unit (GRU) is proposed to predict the remaining service life of fan spindle bearing. Firstly, the vibration history data of the main shaft bearing of the fan is analyzed to find out the relationship between the characteristic value and the remaining life, and the characteristic parameters which can reflect the remaining life are selected; Then, GRU is used to build the remaining service life prediction model of spindle bearing, and the main parameters of the model are adjusted to improve the prediction accuracy of the model. Compared with long short term (LSTM) algorithm, GRU is an effective tool to deal with a large number of data sets.

Remaining service life prediction based on gray model and empirical Bayesian with applications to compressors and pumps

AbstractIn this study, a three‐step remaining service life (RSL) prediction method, which involves feature extraction, feature selection, and fusion and prognostics, is proposed for large‐scale rotating machinery in the presence of scarce failure data. In the feature extraction step, eight time‐domain degradation features are extracted from the faulty variables. A fitness function as a weighted linear combination of the monotonicity, robustness, correlation, and trendability metrics is defined and used to evaluate the suitability of the features for RSL prediction. The selected features are merged using a canonical variate residuals‐based method. In the prognostic step, gray model is used in combination with empirical Bayesian algorithm for RSL prediction in the presence of scarce failure data. The proposed approach is validated on failure data collected from an operational industrial centrifugal pump and a compressor.

Reliability Analysis of Minnesota’s Unbonded Concrete Overlay Performance

Minnesota Department of Transportation (MnDOT) has studied pavement performance associated with various interventions in the road network. In this study, unbonded overlay, a major concrete pavement intervention known for its long service life, was examined. Curve fitting was performed, including a comparison of the current decay curves with previous patterns toward a default performance curve, stepwise regression to identify performance variables associated with and predictive of remaining service life (RSL), and reliability (Weibull) analysis to examine the reliability and other performance characteristics of unbonded overlay in the Minnesota network. Reliability analysis resulted in a RSL (scale parameter) of 36 years, which was reasonably consistent with the 35.5 year RSL derived from the MnDOT Highway Pavement Management Analysis (HPMA). It also provided evidence that the unbonded overlay displays an end-of-life failure pattern as well as a 7-year threshold time to failure (location parameter). MnDOT’s sigmoidal decay model predicted the same expected service life (35.5 years) as did the Weibull analysis process (35.8 years). Stepwise linear regression showed a positive correlation between the time from the most recent rehabilitation (TTR_MR) and RSL. The other explanatory variables including RQI_Spike and time from original construction to intervention (TTR) were found to be non-significant in the prediction of RSL.

Statistics and Artificial Intelligence-Based Pavement Performance and Remaining Service Life Prediction Models for Flexible and Composite Pavement Systems

In their pavement management decision-making processes, U.S. state highway agencies are required to develop performance-based approaches by the Moving Ahead for Progress in the 21st Century (MAP-21) federal transportation legislation. One of the performance-based approaches to facilitate pavement management decision-making processes is the use of remaining service life (RSL) models. In this study, a detailed step-by-step methodology for the development of pavement performance and RSL prediction models for flexible and composite (asphalt concrete [AC] over jointed plain concrete pavement [JPCP]) pavement systems in Iowa is described. To develop such RSL models, pavement performance models based on statistics and artificial intelligence (AI) techniques were initially developed. While statistically defined pavement performance models were found to be accurate in predicting pavement performance at project level, AI-based pavement performance models were found to be successful in predicting pavement performance in network level analysis. Network level pavement performance models using both statistics and AI-based approaches were also developed to evaluate the relative success of these two models for network level pavement performance modeling. As part of this study, in the development of pavement RSL prediction models, automation tools for future pavement performance predictions were developed and used along with the threshold limits for various pavement performance indicators specified by the Federal Highway Administration. These RSL models will help engineers in decision-making processes at both network and project levels and for different types of pavement management business decisions.

An intelligent diagnostic and prognostic framework for large-scale rotating machinery in the presence of scarce failure data

In this work, a novel diagnostic and prognostic framework is proposed to detect faults and predict remaining service life of large-scale rotating machinery in the presence of scarce failure data. In the proposed framework, a canonical variate residuals–based diagnostic method is developed to facilitate remaining service life prediction by continuously implementing detection of the prediction start time. A novel two-step prognostic feature exploring approach that involves fault identification, feature extraction, feature selection and multi-feature fusion is put forward. Most existing prognostic methods lack a fault-identification module to automatically identify the fault root-cause variables required in the subsequent prognostic analysis and decision-making process. The proposed prognostic feature exploring method overcomes this challenge by introducing a canonical variate residuals–based fault-identification method. With this method, the most representative degradation features are extracted from only the fault root-cause variables, thereby facilitating machinery prognostics by ensuring accurate estimates. Its effectiveness is demonstrated for slow involving faults in two case studies of an operational industrial centrifugal pump. Moreover, an enhanced grey model approach is developed for remaining useful life prediction. In particular, the empirical Bayesian algorithm is employed to improve the traditional grey forecasting model in terms of quantifying the uncertainty of remaining service life in a probabilistic form and improving its prediction accuracy. To demonstrate the superiority of empirical Bayesian–grey model, existing prognostic methods such as grey model, particle filter–grey model and empirical Bayesian–exponential regression are also utilized to realize machinery remaining service life prediction, and the results are compared with that of the proposed method. The achieved predictive accuracy shows that the proposed approach outperforms its counterparts and is highly applicable in fault prognostics of industrial rotating machinery. The use of in-service data in a practical scenario shows that the proposed prognostic approach is a promising tool for online health monitoring.