A Framework of LSTM Neural Network Model in Multi-Time Scale Real-Time Prediction of Ship Motions in Head Waves

Ship motions induced by waves have a significant impact on the efficiency and safety of offshore operations.Real-time prediction of ship motions in the next few seconds plays a crucial role in performing sensitive activities.However,the obvious memory effect of ship motion time series brings certain difficulty to rapid and accurate prediction.Therefore,a real-time framework based on the Long-Short Term Memory(LSTM)neural network model is proposed to predict ship motions in regular and irregular head waves.A 15000 TEU container ship model is employed to illustrate the proposed framework.The numerical implementation and the real-time ship motion prediction in irregular head waves corresponding to the different time scales are carried out based on the container ship model.The related experimental data were employed to verify the numerical simulation results.The results show that the proposed method is more robust than the classical extreme short-term prediction method based on potential flow theory in the prediction of nonlinear ship motions.

One Method for Fast Gate Oxide TDDB Lifetime Prediction

A method for fast gate oxide TDDB lifetime prediction for process control monitors （PCM） is proposed. For normal TDDB lifetime prediction at operation voltage and temperature, we must ge（three lifetimes at relative low stress voltages and operation temperature. Then we use these three lifetimes to project the TDDB lifetime at operation voltage and temperature via the E-model. This requires a very long time for measurement. With our new method,it can be calculated quickly by projecting the TDDB lifetime at operation voltage and temperature with measurement data at relatively high stress voltages. Our test case indicates that this method is very effective. And the result with our new method is very close to that with the normal TDDB lifetime prediction method. But the measurement time is less than 50s for one sample,less than 1/100000 of that with the normal prediction method. With this new method,we can monitor gate oxide TDDB lifetime on-line.

Residual lifetime prediction model of nonlinear accelerated degradation data with measurement error

For the product degradation process with random effect (RE), measurement error (ME) and nonlinearity in step-stress accelerated degradation test (SSADT), the nonlinear Wiener based degradation model with RE and ME is built. An analytical approximation to the probability density function (PDF) of the product's lifetime is derived in a closed form. The process and data of SSADT are analyzed to obtain the relation model of the observed data under each accelerated stress. The likelihood function for the population-based observed data is constructed. The population-based model parameters and its random coefficient prior values are estimated. According to the newly observed data of the target product in SSADT, an analytical approximation to the PDF of its residual lifetime (RL) is derived in accordance with its individual degradation characteristics. The parameter updating method based on Bayesian inference is applied to obtain the posterior value of random coefficient of the RL model. A numerical example by simulation is analyzed to verify the accuracy and advantage of the proposed model.

The Application of Neural Network in Lifetime Prediction of Concrete

There are many difficulties in concrete endurance prediction, especially in accurate predicting service life of concrete engineering. It is determined by the concentration of S042-/ Mg2+ / Cl- /Ca2+ , reactionareas , the cycles of freezing and dissolving, alternatives of dry and wet state, the kind of cement, etc. . In general , because of complexity itself and cognitive limitation, endurance prediction under sulphate erosion is still illegible and uncertain, so this paper adopts neural network technology to research this problem. Through analyzing , the paper sets up a 3 - levels neural network and a 4 - levels neural network to predict the endurance undersulphate erosion. The 3 - levels neural network includes 13 inputting nodes, 7 outputting nodes and 34 hidden nodes. The 4 - levels neural network also has 13 inputting nodes and 7 outputting nodes with two hidden levels which has 1 nodes and 8 nodes separately. In the end the paper give a example with laboratorial data and discussion the result and deviation. The paper shows that deviation results from some faults of training specimens; such as few training specimens and few distinctions among training specimens. So the more specimens should be collected to reduce data redundancy and improve the reliability of network analysis conclusion.

A new analytical model for thermal stresses in multi-phase materials and lifetime prediction methods

Based on the fundamental equations of the mechanics of solid continuum, the paper employs an analytical model for determination of elastic thermal stresses in isotropic continuum represented by periodically distributed spherical particles with different distributions in an infinite matrix, imaginarily divided into identical cells with dimensions equal to inter-particle distances, containing a central spherical particle with or without a spherical envelope on the particle surface. Consequently, the multi-particle-（envelope）- matrix system, as a model system regarding the analytical modelling, is applicable to four types of multi-phase materials. As functions of the particle volume fraction v, the inter-particle distances dl, d2, d3 along three mutually per- pendicular axes, and the particle and envelope radii, R1 and R2, respectively, the thermal stresses within the cell, are originated during a cooling process as a consequence of the difference in thermal expansion coefficients of phases rep- resented by the matrix, envelope and particle. Analytical-（experimental）-computational lifetime prediction methods for multi-phase materials are proposed, which can be used in engineering with appropriate values of parameters of real multi-phase materials.

Remaining lifetime prediction for nonlinear degradation device with random effect

For the large number of nonlinear degradation devices existing in a project, the existing methods have not systematically studied the effects of random effect on the remaining lifetime(RL),the accuracy and efficiency of the parameters estimation are not high, and the current degradation state of the target device is not accurately estimated. In this paper, a nonlinear Wiener degradation model with random effect is proposed and the corresponding probability density function(PDF) of the first hitting time(FHT)is deduced. A parameter estimation method based on modified expectation maximum(EM) algorithm is proposed to obtain the estimated value of fixed coefficient and the priori value of random coefficient in the model. The posterior value of the random coefficient and the current degradation state of target device are updated synchronously by the state space model(SSM) and the Kalman filter algorithm. The PDF of RL with random effect is deduced. A simulation example is analyzed to verify that the proposed method has the obvious advantage over the existing methods in parameter estimation error and RL prediction accuracy.

A real-time prediction method for tunnel boring machine cutter-head torque using bidirectional long short-term memory networks optimized by multi-algorithm

Based on data from the Jilin Water Diversion Tunnels from the Songhua River(China),an improved and real-time prediction method optimized by multi-algorithm for tunnel boring machine(TBM)cutter-head torque is presented.Firstly,a function excluding invalid and abnormal data is established to distinguish TBM operating state,and a feature selection method based on the SelectKBest algorithm is proposed.Accordingly,ten features that are most closely related to the cutter-head torque are selected as input variables,which,in descending order of influence,include the sum of motor torque,cutter-head power,sum of motor power,sum of motor current,advance rate,cutter-head pressure,total thrust force,penetration rate,cutter-head rotational velocity,and field penetration index.Secondly,a real-time cutterhead torque prediction model’s structure is developed,based on the bidirectional long short-term memory(BLSTM)network integrating the dropout algorithm to prevent overfitting.Then,an algorithm to optimize hyperparameters of model based on Bayesian and cross-validation is proposed.Early stopping and checkpoint algorithms are integrated to optimize the training process.Finally,a BLSTMbased real-time cutter-head torque prediction model is developed,which fully utilizes the previous time-series tunneling information.The mean absolute percentage error(MAPE)of the model in the verification section is 7.3%,implying that the presented model is suitable for real-time cutter-head torque prediction.Furthermore,an incremental learning method based on the above base model is introduced to improve the adaptability of the model during the TBM tunneling.Comparison of the prediction performance between the base and incremental learning models in the same tunneling section shows that:(1)the MAPE of the predicted results of the BLSTM-based real-time cutter-head torque prediction model remains below 10%,and both the coefficient of determination(R^(2))and correlation coefficient(r)between measured and predicted values exceed 0.95;and(2)the incremental learning method is suitable for realtime cutter-head torque prediction and can effectively improve the prediction accuracy and generalization capacity of the model during the excavation process.

Real-time prediction of mechanical behaviors of underwater shield tunnel structure using machine learning method based on structural health monitoring data

Predicting the mechanical behaviors of structure and perceiving the anomalies in advance are essential to ensuring the safe operation of infrastructures in the long run.In addition to the incomplete consideration of influencing factors,the prediction time scale of existing studies is rough.Therefore,this study focuses on the development of a real-time prediction model by coupling the spatio-temporal correlation with external load through autoencoder network(ATENet)based on structural health monitoring(SHM)data.An autoencoder mechanism is performed to acquire the high-level representation of raw monitoring data at different spatial positions,and the recurrent neural network is applied to understanding the temporal correlation from the time series.Then,the obtained temporal-spatial information is coupled with dynamic loads through a fully connected layer to predict structural performance in next 12 h.As a case study,the proposed model is formulated on the SHM data collected from a representative underwater shield tunnel.The robustness study is carried out to verify the reliability and the prediction capability of the proposed model.Finally,the ATENet model is compared with some typical models,and the results indicate that it has the best performance.ATENet model is of great value to predict the realtime evolution trend of tunnel structure.

Real-time 3-D space numerical shake prediction for earthquake early warning

In earthquake early warning systems, real-time shake prediction through wave propagation simulation is a promising approach. Compared with traditional methods, it does not suffer from the inaccurate estimation of source parameters. For computation efficiency, wave direction is assumed to propagate on the 2-D surface of the earth in these methods. In fact, since the seismic wave propagates in the 3-D sphere of the earth, the 2-D space modeling of wave direction results in inaccurate wave estimation. In this paper, we propose a 3-D space numerical shake pre- diction method, which simulates the wave propagation in 3-D space using radiative transfer theory, and incorporate data assimilation technique to estimate the distribution of wave energy. 2011 Tohoku earthquake is studied as an example to show the validity of the proposed model. 2-D space model and 3-D space model are compared in this article, and the prediction results show that numerical shake prediction based on 3-D space model can estimate the real-time ground motion precisely, and overprediction is alleviated when using 3-D space model.

CRACK PROPAGATION BEHAVIOR AND LIFETIME PREDICTION IN ALUMINA AND ZIRCONIA

The lifetime prediction of ceramics is discussed on the basis of therelationship between stress intensity factor K_1 and crack velocity nu. The effects of waterenvironment, the cyclic loading and microstructure of material on K_1-nu characteristics are studiedby carrying out the crack growth tests by the double torsion (DT) method under the static andcyclic loading in both environments of air and water for alumina and zirconia. K_1-nucharacteristics determined by the double torsion method are used to predict time-to-failure underthe cyclic loading of alumina and zirconia ceramics. The predictions agree qualitatively with theexperimental results.

FATIGUE DAMAGE AND LIFETIME PREDICTION OF AERONAUTIC WELDED STRUCTURES UNDER HIGH TEMPERATURE

The fatigue damage evolution equations and the relation of fatigue damage parameter with maximum cyclic stress of superalloy GH150 and its welded structures are established. The fatigue damage evolution equations in a multiaxial stress state are also given. By use of cyclic thermal elastoplastic damage constitutive relations, the fatigue damage and lifetime predictions are carried out for the welded combustion chamber of aeroengine.

Prediction of long-term creep behaviour and lifetime of polystyrene by linear extrapolation

The universal creep function derived from the kinetic equations is successful in relating the creep (ε) to the aging time (t a), coefficient of retardation time (β), and intrinsic time (t 0). The relation was used to treat the creep experimental data for polystyrene (PS) specimens which were aged at a given temperature and different times (short term) and tested at a certain temperature and different stress levels. Then unified master lines were constructed with the treated data and curves according to the universal equation. The master lines can be used to predict the long term creep behaviour and lifetime by extrapolating to a required ultimate strain. The verifications of results obtained with this method were shown as well.

Prediction of long-term creep behavior and lifetime of PPC pipe materials by linear extrapolation

The universal creep equation relates creep behavior (ε/ε 0) to aging time (t a), coefficient of retardation time (β), and intrinsic time (t 0). The relation was used to treat the creep experimental data for pipe specimens of polypropylene block copolymer (PPC), which were aged for different days (short term) and tested under different stress levels at a certain temperature. Then unified master lines were constructed with the treated data and curves according to the universal equation. The master straight lines can be used for extrapolation to predict the long term creep behavior and lifetime of the pipe materials of PPC in the same way as plate materials.

Lifetime prediction and failure analysis of organic coatings by EIS

Organic coatings are widely used to control the corrosion of steel structure. The anticorrosive property of these coatings depends on their barrier properties, making a separation between the corrosive medium and the substrate. But unavoidable completely small pores, cracks and other defects in organic coatings may cause ions, water, gases, and other corrosive species penetrate and distribute in the coatings, causing accumulation and swelling of coatings, so leading to the degradation of coatings. In addition, water affects the permeation of oxygen and other corrosive medium, consequently the presence of such substances at coating-metal interface promotes corrosion of metal substrate. So the absorbability of the coatings to water may be one of the most important factors in undercoating corrosion. In recent years, electrochemical impedance spectroscopy (EIS) has been established and frequently used as a non-destructive testing method for assessing the performance of organic coatings, especially for the determination of the water content in organic coatings, since the capacitance of the coatings is sensitive to the penetration of water. So from EIS it can extract a wealth of information on the electrochemical corrosion of coated steels, especially, it can be utilized to assess organic coatings used under particular surroundings. The principle, methods and application of EIS on evaluating life-span and analyzing failure mechanism of organic coatings are also introduced briefly. Combining other analysis techniques such as XRD, SEM and FTIR with electrochemical technique, it will blaze a way in studying degradation mechanism of organic coatings and estimating their lifetime.

Real-Time Prediction Algorithm for Intelligent Edge Networks with Federated Learning-Based Modeling

Intelligent healthcare networks represent a significant component in digital applications,where the requirements hold within quality-of-service(QoS)reliability and safeguarding privacy.This paper addresses these requirements through the integration of enabler paradigms,including federated learning(FL),cloud/edge computing,softwaredefined/virtualized networking infrastructure,and converged prediction algorithms.The study focuses on achieving reliability and efficiency in real-time prediction models,which depend on the interaction flows and network topology.In response to these challenges,we introduce a modified version of federated logistic regression(FLR)that takes into account convergence latencies and the accuracy of the final FL model within healthcare networks.To establish the FLR framework for mission-critical healthcare applications,we provide a comprehensive workflow in this paper,introducing framework setup,iterative round communications,and model evaluation/deployment.Our optimization process delves into the formulation of loss functions and gradients within the domain of federated optimization,which concludes with the generation of service experience batches for model deployment.To assess the practicality of our approach,we conducted experiments using a hypertension prediction model with data sourced from the 2019 annual dataset(Version 2.0.1)of the Korea Medical Panel Survey.Performance metrics,including end-to-end execution delays,model drop/delivery ratios,and final model accuracies,are captured and compared between the proposed FLR framework and other baseline schemes.Our study offers an FLR framework setup for the enhancement of real-time prediction modeling within intelligent healthcare networks,addressing the critical demands of QoS reliability and privacy preservation.

Efficient Harmonic Analysis Technique for Prediction of IGS Real-Time Satellite Clock Corrections

Real-time satellite orbit and clock corrections obtained from the broadcast ephemerides can be improved using IGS real-time service (RTS) products. Recent research showed that applying such corrections for broadcast ephemerides can significantly improve the RMS of the estimated coordinates. However, unintentional streaming interruption may happen for many reasons such as software or hardware failure. Streaming interruption, if happened, will cause sudden degradation of the obtained solution if only the broadcast ephemerides are used. A better solution can be obtained in real-time if the predicted part of the ultra-rapid products is used. In this paper, Harmonic analysis technique is used to predict the IGS RTS corrections using historical broadcasted data. It is shown that using the predicted clock corrections improves the RMS of the estimated coordinates by about 72%, 58%, and 72% in latitude, longitude, and height directions, respectively and reduces the 2D and 3D errors by about 80% compared with the predicted part of the IGS ultra-rapid clock corrections.

Real-time numerical shake prediction and updating for earthquake early warning

Ground motion prediction is important for earthquake early warning systems, because the region＇s peak ground motion indicates the potential disaster. In order to predict the peak ground motion quickly and pre- cisely with limited station wave records, we propose a real- time numerical shake prediction and updating method. Our method first predicts the ground motion based on the ground motion prediction equation after P waves detection of several stations, denoted as the initial prediction. In order to correct the prediction error of the initial prediction, an updating scheme based on real-time simulation of wave propagation is designed. Data assimilation technique is incorporated to predict the distribution of seismic wave energy precisely. Radiative transfer theory and Monte Carlo simulation are used for modeling wave propagation in 2-D space, and the peak ground motion is calculated as quickly as possible. Our method has potential to predict shakemap, making the potential disaster be predicted before the real disaster happens. 2008 Ms8.0 Wenchuan earthquake is studied as an example to show the validity of the proposed method.

Application of predictive control scheduling method to real-time periodic control tasks overrun

Based on the abort strategy of fixed periods, a novel predictive control scheduling methodology was proposed to efficiently solve overrun problems. By applying the latest control value in the prediction sequences to the control objective, the new strategy was expected to optimize the control system for better performance and yet guarantee the schedulability of all tasks under overrun. The schedulability of the real-time systems with p-period overruns was analyzed, and the corresponding stability criteria was given as well. The simulation results show that the new approach can improve the performance of control system compared to that of conventional abort strategy, it can reduce the overshoot and adjust time as well as ensure the schedulability and stability.

An analytical model for predicting battery lifetime

We used an analytical high-level battery model to estimate the battery lifetime for a given load.The experimental results show that this model to predict battery lifetime under variable loads is more appropriate than that under constant loads.

A Real-time Updated Model Predictive Control Strategy for Batch Processes Based on State Estimation

Nonlinear model predictive control(NMPC) is an appealing control technique for improving the performance of batch processes, but its implementation in industry is not always possible due to its heavy on-line computation. To facilitate the implementation of NMPC in batch processes, we propose a real-time updated model predictive control method based on state estimation. The method includes two strategies: a multiple model building strategy and a real-time model updated strategy. The multiple model building strategy is to produce a series of sim-plified models to reduce the on-line computational complexity of NMPC. The real-time model updated strategy is to update the simplified models to keep the accuracy of the models describing dynamic process behavior. The me-thod is validated with a typical batch reactor. Simulation studies show that the new method is efficient and robust with respect to model mismatch and changes in process parameters.