Life Prediction Technology Research Articles

Research on the remaining life prediction technology of environmentally friendly gas switchgear based on approximate dynamic programming

Research on the remaining life prediction technology of environmentally friendly gas switchgear based on approximate dynamic programming

Review on Aging Risk Assessment and Life Prediction Technology of Lithium Energy Storage Batteries

Review on Aging Risk Assessment and Life Prediction Technology of Lithium Energy Storage Batteries

Remaining useful life prediction of lithium-ion batteries via an EIS based deep learning approach

Reliable life prediction technology is of great significance in ensuring a safe and efficient lifetime of lithium batteries. However, the traditional health factors such as battery capacity are the effects of battery aging rather than the direct causes, which cannot directly reflect the internal degradation mechanism information of the battery, and the prediction accuracy is easily affected by the working environment of the battery. Electrochemical impedance spectroscopy (EIS) data can more directly reflect the internal mechanism information of the battery, which includes a wealth of battery aging information. In order to deeply investigate the mapping relationship between impedance spectrum and remaining useful life (RUL) of lithium batteries, EIS method is employed to obtain the impedance and phase of lithium batteries under different health states and temperatures, as well as explore the visualization and quantification of impedance frequency response of lithium battery. Furthermore, the mapping relationship between RUL and the lithium battery impedance is investigated in a full impedance spectrum at different temperatures. It is found that, as lithium battery aging, its negative imaginary parts impedance increases significantly, especially in the middle of the frequency band, and has no significant dependence on temperature. While the real part impedance shows an obvious dependence on temperature. Therefore, it is found that the negative imaginary parts impedance of impedance spectrum has a well-fit characterization ability for RUL of a lithium battery. In this paper, a fusion neural network model of Conv1d-SAM (one-dimensional convolutional neural network-self-attention mechanism) was established with negative imaginary part impedance as input factor to predict battery RUL. The predicted results show that Conv1d-SAM has improved accuracy and stability in RUL prediction, and the mean absolute error function of the proposed model is increased by 72% compared with the latest published method.

Study on self-diagnosis/prediction technology for LIDAR sensor of autonomous vehicles

Along with the development of autonomous driving technology, the need for self-failure diagnosis and Remaining Useful Life (RUL) prediction technology for core parts for autonomous driving is increasing. In particular, the characteristics of the light detection and ranging (LIDAR) sensor exposed to the outside further increase the need to apply fault diagnosis and RUL prediction technology considering various environmental variables. In this study, based on the accelerated degradation test of LIDAR, the failure mode was analyzed. Through this, LIDAR failure due to thermal runaway, which is the first failure type in high temperature conditions, was identified, and whether there were major environmental data that could identify thermal runaway was identified. In the case of LIDAR's thermal runaway phenomenon, a study on an algorithm to identify the precursor symptoms of failure in an accidental failure situation is conducted. Afterwards, through the actual vehicle test process, various environmental variable information is analyzed for correlation with LIDAR internal sensor data, and the abnormal data for the temperature of the internal parts of the LIDAR is predicted through the external environmental sensor.

Research on wear state identification and life prediction technology of ultrasonic straight-edge knife

Research on wear state identification and life prediction technology of ultrasonic straight-edge knife

A Review of Remaining Useful Life Prediction for Energy Storage Components Based on Stochastic Filtering Methods

Lithium-ion batteries are a green and environmental energy storage component, which have become the first choice for energy storage due to their high energy density and good cycling performance. Lithium-ion batteries will experience an irreversible process during the charge and discharge cycles, which can cause continuous decay of battery capacity and eventually lead to battery failure. Accurate remaining useful life (RUL) prediction technology is important for the safe use and maintenance of energy storage components. This paper reviews the progress of domestic and international research on RUL prediction methods for energy storage components. Firstly, the failure mechanism of energy storage components is clarified, and then, RUL prediction method of the energy storage components represented by lithium-ion batteries are summarized. Next, the application of the data–model fusion-based method based on kalman filter and particle filter to RUL prediction of lithium-ion batteries are analyzed. The problems faced by RUL prediction of the energy storage components and the future research outlook are discussed.

Two-stage aging trajectory prediction of LFP lithium-ion battery based on transfer learning with the cycle life prediction

With the wide application of the LFP lithium-ion batteries, more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging monitoring. In recent years, long-term aging trajectory prediction of the lithium-ion battery is always a challenge due to its complex nonlinear aging behaviors especially the aging behaviors in the two aging stages are quite different when the battery experiences the two-stage aging process under fast-charging conditions. Thus, it is harder to achieve accurate long-term aging trajectory prediction of the LFP lithium-ion batteries on the condition of the two-stage aging process. To address it, a novel transfer learning strategy combined with the cycle life prediction technology is presented in this paper. Specifically, a new cycle life prediction method is proposed based on feature extraction and deep learning technology and achieves accurate cycle life prediction. The transfer learning is started by developing a base aging model offline to learn the information of the two-stage aging process. Then, taking the predicted cycle life as its prior information, the Bayesian model migration technology is employed to predict the aging trajectory accurately, and the uncertainty of the aging trajectory is quantified. Two batches of the battery datasets are used for performance evaluation and comparison with two benchmarks. It is novel to combine the cycle life prediction and transfer learning technique to achieve accurate two-stage aging trajectory prediction with only a few data available (first 30%).

Development of data-driven residual life prediction technology based on particle filtering including focus on research conducted in Prof. Liang's wider group

Professor Jin-Wei Liang, Center for Reliability Engineering, Ming Chi University of Technology, Taiwan, is a researcher who collaborates closely with industry and his work is focused on nonlinear dynamics, vibration and control. In his investigations, Liang is seeking to predict the remaining useful life (RUL) of important components in rotary machinery. Previously, he applied a neural-network (NN) method to the development of a data-driven residual life prediction technology and he is now investigating the same problem using a particle filter (PF) approach. The expectation is that using this approach will enable Liang and the team to improve insight and confidence. Alongside this, the researchers have developed a NN-based health index prediction model that can be used to determine how long particular equipment used in industrial applications will function in normal operations. Having received very limited run-to-failure datasets from a local chemical factory, Liang and the team have been able to test and validate their hypotheses using the NN-based health index prediction algorithm. Initially, the local plastic manufacturing company with which the researchers are collaborating that will benefit most from the research results and, subsequently, it is expected that other businesses and industries will benefit. Liang believes the method he and the team have developed will help companies to save on costs such as the replacement charge for a new critical component of rotary machinery and the greater costs that can occur due to unforeseeable shut-down events caused by component damage.

Research on Thermal Fatigue Life Prediction Technology of PoP Laminated BGA Products

In this paper, a fast prediction method for thermal fatigue life of PoP laminated BGA Product was proposed. Firstly, the stress and strain of the solder joints of each layer of the laminated device in thermal fatigue test was determined by finite element simulation method. According to the research idea of relative stress and strain, the solder joints were divided into sensitive solder joints and reliable solder joints. Secondly, sensitive solder joint were connected with PCB traces through the internal pads, bonding wires, TSVs and reliable solder joints to form a daisy chain. Through real-time dynamic monitoring of the resistance change of the daisy chain in thermal fatigue test to judge whether the solder joints fail, and record the occurrence time of the first failure solder joint. Finally, the thermal fatigue life of the product was estimated by the Norris-Landzberg formula.

Remaining useful life prediction for complex systems considering varying future operational conditions

AbstractRemaining useful life (RUL) prediction technology is important for optimizing maintenance schedules. With the advancement of sensing technology, several deep learning approaches have been proposed to predict RUL without relying on prior knowledge about systems. However, previous deep learning‐based approaches rarely consider the future operational conditions, which can be known according to the future work plan and is an important influential factor for RUL prediction. This paper proposes a multi‐input neural network based on long short‐term memory for RUL prediction considering the temporal dependencies among the measurements when the future operational conditions are known. The sliding window approach is employed for determining the input time sequences of previous monitoring data (including operational condition and sensor measurements), and the length of input time sequences of the future operational conditions are determined based on the prior estimated RUL. Fine‐tuning strategy is proposed to make the training of the multi‐input network more effective. To illustrate the effectiveness of the proposed methods, a case study referring to the C‐MAPSS dataset is used and a sensitivity analysis is also conducted on the future operational conditions.

Research on life prediction technology of wind turbine gearbox based on virtual simulation

As the core component of wind turbine energy conversion, the gearbox has been operating under variable frequency and variable load condition for a long time. The repair time is long after its fault, which leads to a large loss of power generation. This paper proposes a gearbox life prediction method. By collecting the design and manufacturing process parameters of gearbox, the gearbox virtual simulation model is established, the gearbox observable damage can be predicted accurately by inputting the actual operation load. According to the results, the maintenance and repair time of the gearbox can be arranged scientifically, which can effectively avoid the occurrence of serious faults, greatly reduce the gearbox replacement rate and unscheduled downtime, the economic benefits are obvious. After field application, the accuracy of this method can be 93.5%, which has a good prospect of application.

A Health Indicator for the Online Lifetime Estimation of an Electric Vehicle Power Li-Ion Battery

With the further development of the electric vehicle (EV) industry, the reliability of prediction and health management (PHM) systems has received great attention. The original Li-ion battery life prediction technology developed by offline training data can no longer meet the needs of use under complex working conditions. The existing methods pay insufficient attention to the dispersive information of health indicators (HIs) under EV driving conditions, and can only calculate through standard configuration files. To solve the problem that it is difficult to directly measure the capacity loss in real time, this paper proposes a battery HI called excitation response level (ERL) to describe the voltage variation at different lifetimes, which could be easily calculated according to the current and voltage under the actual load curve. In addition, in order to further optimize the proposed HI, Box–Cox transformation was used to enhance the linear correlation between the initially extracted HI and the capacity. Several Li-ion batteries were discharged to the 50% state of health (SOH) through profiles with different depths of discharge (DODs) and mean states of charge (SOCs) to verify the accuracy and robustness of the proposed method. The average estimation error of the tested batteries was less than 3%, which shows a good performance for accuracy and robustness.

A new approach for safety life prediction of industrial rolling bearing based on state recognition and similarity analysis

Rolling bearing is an important part of rotating machinery which operation safety and reliability are directly related to the normal operation of equipment. Remaining useful life is an important index for describing the safe operation of industrial rolling bearing and life prediction technology of machinery equipment is an important method to realize intelligent maintenance and industrial safety operation. According to the idea of data-driven, a new method for predicting the life of rolling bearing was proposed. By using life-cycle data of bearing from normal to failure, based on the new clustering algorithm of K-means and threshold correction, the recognition and partition of different operation states of rolling bearings were realized and the life model was established by defining the state matrix. For the monitoring bearing, comprehensive similarity analysis with the historical data was carried out to construct the life proportional adjustment function and dynamically modify the parameters of the state matrix model, so as to realize the adaptive prediction of the life of the monitoring bearing. The bearing test data of the University of Cincinnati Laboratory Center were used to carry out the applied research. The normal operation state and remaining life of two bearings were predicted by a set of bearing life data. The results showed that the method had better prediction accuracy and generalization compared with hidden Markov model and grey model. This study provides some theoretical guidance and basis for the industrial safe operation and maintenance of rolling bearings during service.

Fatigue Life Prediction of Steam Generator Tubes by Tube Specimens with Circular Holes

Heat exchangers manufactured from Inconel 690 tubes are widely used for steam generators in nuclear power plants. Inconel 690 tubes have suffered failures of fatigue fracture due to flow induced vibration. It is difficult to obtain the fatigue life of the tube directly since the conventional fatigue test would potentially cause end fatigue failure due to the stress concentration at the clamp end. In this study, a thin-walled Inconel 690 tube with circular hole is designed to deduce the fatigue life of smooth tube based on the notch fatigue life prediction technology. Firstly, the local stress and strain distributions around the hole based on the finite element analysis are discussed. Local stress-strain is calculated and compared with Neuber’s ruler. Meanwhile, fatigue life tests using tube specimens with circular holes are carried out. Finally, based on the best-fitted fatigue life curve of Inconel 690 alloy, the fatigue life of tube specimen is estimated from the local strain according to Neuber’s ruler. The results show that the local stress and strain estimated by Neuber’s ruler are basically consistent with those obtained by finite element analysis. Compared with the average fatigue life of nickel-based alloy, the new predicted equivalent fatigue life of heat Inconel 690 transfer tube with a hole is higher. The Inconel 690 heat transfer tube has better fatigue performance.

Bearing Capacity Model of Corroded RC Eccentric Compression Columns Based on Hermite Interpolation and Fourier Fitting

With an extension in service years, bridges inevitably suffer from performance deterioration. Columns are the main components of bridge structures, which support the superstructure. The damage of pier columns is often more harmful to bridges than that of other components. To accurately evaluate the time-varying characteristics of corroded columns, this paper proposes a new model for the bearing capacity evaluation of deteriorated reinforced concrete (RC) eccentric compression columns based on the Hermite interpolation and Fourier function. Firstly, the axial compression point, the pure bending point and the balanced failure point were selected as the basic points, and the deteriorated strength of these basic points was calculated by considering factors such as concrete cracking, reduction of reinforcement area, buckling of the steel bar, bond slip and strength reduction of confined concrete. After that, the interpolation points were generated by a piecewise cubic Hermite interpolating polynomial, and the explicit expression of the interpolation points fitting function was realized by the trigonometric Fourier series model. Finally, comparison studies based on measured data from forty-five corroded RC eccentric compression columns were conducted to investigate the accuracy and efficiency of the proposed method. The results show that: (1) the prediction results for bearing capacity of corroded RC columns are in good agreement with the measured data, with the average ratio of predicted results to test results at 1.06 and the standard deviation at 0.14; (2) the proposed model unifies the three stress states of axial compression, eccentric compression and pure bending, and is consistent with the continuum mechanics characteristics; (3) the decrements of axial load carrying capacity for 10% and 50% of the corrosion rate are 31.4% and 45.2%, while in flexure they are 25.4% and 77.4%, respectively; and (4) the test data of small-scale specimens may overestimate the negative effect of corrosion on the bearing capacity of actual structures. The findings in this paper could lay a solid starting point for structural life prediction technologies based on nondestructive testing.

Application of Random Average Method in Remain Useful Life Prediction of Rolling Bearing

Remain useful life (RUL) prediction technology which is significant in the condition based maintenance (CBM) is a hot research topic nowadays. Rolling bearing is a basic component widely used in the mechanical industry, and its reliability affects the operation of rotating machinery. On the basis of traditional RUL technology for rolling bearing, a method named random average method (RAM) is introduced into RUL prediction and the implementation of it is instructed in detail via the processing of vibration data in full life of rolling bearing. Compared to traditional method, the proposed method based on RAM is better in both accuracy and timeliness.

Advanced technology in creep life prediction and damage evaluation for creep strength enhanced ferritic steels

Creep damage mechanisms of recently developed boiler and steam-turbine steels are not well clarified, however, creep life prediction technology for such creep strength enhanced ferritic steels, grades 91, 92 122, etc. with tempered martensitic structure including welds has been strongly demanded by power plant operators and equipment manufacturers. In this paper, the technologies related to the creep life prediction and damage evaluation for creep strength enhanced ferritic steels being studied from the various aspects in Japan will be surveyed and presented. The creep life prediction of this type of steel must be grounded on the findings on microstructural degradation and creep softening in martensitic structure composed of very fine martensite lath, block, packet and prior austenite grains, and precipitation and dislocation structures. Physical properties response to the creep degradation and measurement and detection of localized creep damage/strength would be useful tools to develop diagnostic techniques for life prediction of creep strength enhanced ferritic steels. Other important techniques to support the creep life prediction based on creep-strain/rupture data are creep modelling and data analysis which have been successfully investigated to date.

Analysis of Aircraft Composite Structural Health Monitoring and Life Prediction Technology

Along with the constantly updated aircraft structure design, higher performance and reliability design indexes as well as usage of a large portion of new materials especially lightweight composite materials put forward higher requirements for aircraft structure safety. The damage detection, diagnosis, forecast and management become an important part of aircraft Prognostics and Health Management(PHM).In order to better build the Structural Prognostics and Health Management system of a new generation aircraft for the improvement of security, task reliability and economy, this paper introduced the development situation of aircraft composite structural health monitoring and life prediction technologies, classified the existing technologies, and then discussed the principle, quality point, applicability and application situation, finally, pointed out several critical issues which still need further study.

Validation and Verification of Life Prediction Technology for Electromechanical Products

Supporters of life prediction claim that this technology can provide enormous benefits to users. Among so many performance indicators of life prediction technology, the accuracy and stability of life prediction is of greatest concern. This article compares advantages and disadvantages of various performance indicators in the prediction of product’s life between life prediction algorithm based on statistical and that based on degradation path model.

Advanced technology in creep life prediction and damage evaluation for creep strength enhanced ferritic steels

Creep damage mechanisms of recently developed boiler and steam-turbine steels are not well clarified, however, creep life prediction technology for such creep strength enhanced ferritic steels, grades 91, 92 122, etc. with tempered martensitic structure including welds has been strongly demanded by power plant operators and equipment manufacturers. In this paper, the technologies related to the creep life prediction and damage evaluation for creep strength enhanced ferritic steels being studied from the various aspects in Japan will be surveyed and presented. The creep life prediction of this type of steel must be grounded on the findings on microstructural degradation and creep softening in martensitic structure composed of very fine martensite lath, block, packet and prior austenite grains, and precipitation and dislocation structures. Physical properties response to the creep degradation and measurement and detection of localized creep damage/strength would be useful tools to develop diagnostic techniques for life prediction of creep strength enhanced ferritic steels. Other important techniques to support the creep life prediction based on creep-strain/rupture data are creep modelling and data analysis which have been successfully investigated to date.