Long-term prediction on atmospheric corrosion data series of carbon steel in China based on NGBM(1,1) model and genetic algorithm

2019 ◽  
Vol 66 (4) ◽  
pp. 403-411 ◽  
Author(s):  
Yuanjie Zhi ◽  
Dongmei Fu ◽  
Tao Yang ◽  
Dawei Zhang ◽  
Xiaogang Li ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Carbon Steel ◽  
Atmospheric Corrosion ◽  
Data Series ◽  
Data Sets ◽  
Content Type ◽  
Term Prediction ◽  
Long Term Prediction ◽  
Corrosion Data

PurposeThis study aims to achieve long-term prediction on a specific monotonic data series of atmospheric corrosion rate vs time.Design/methodology/approachThis paper presents a new method, used to the collected corrosion data of carbon steel provided by the China Gateway to Corrosion and Protection, that combines non-linear gray Bernoulli model (NGBM(1,1) with genetic algorithm to attain the purpose of this study.FindingsResults of the experiments showed that the present study’s method is more accurate than other algorithms. In particular, the mean absolute percentage error (MAPE) and the root mean square error (RMSE) of the proposed method in data sets are 9.15 per cent and 1.23 µm/a, respectively. Furthermore, this study illustrates that model parameter can be used to evaluate the similarity of curve tendency between two carbon steel data sets.Originality/valueCorrosion data are part of a typical small-sample data set, and these also belong to a gray system because corrosion has a clear outcome and an uncertainly occurrence mechanism. In this work, a new gray forecast model was proposed to achieve the goal of long-term prediction of carbon steel in China.

Long-Term Prediction of Atmospheric Corrosion Loss in Various Field Environments

CORROSION ◽  
10.5006/2706 ◽  
2018 ◽  
Vol 74 (6) ◽  
pp. 669-682 ◽  
Author(s):  
Yi-kun Cai ◽  
Yu Zhao ◽  
Xiao-bing Ma ◽  
Kun Zhou ◽  
Hao Wang
Keyword(s):  
Neural Network ◽  
Linear Function ◽  
Environmental Variables ◽  
Atmospheric Corrosion ◽  
Accurate Estimation ◽  
Corrosion Loss ◽  
Surface Method ◽  
Long Term Prediction ◽  
Corrosion Data

This paper deals with the prediction of long-term atmospheric corrosion in different field environments using the power-linear function. A method for the calculation of exponent n and stationary corrosion rate α in the power-linear function is proposed based on the 1- and 8-y corrosion loss results (C1 and C8) of the ISO CORRAG program. The response surface method and the artificial neural network methodology are used to obtain the accurate estimation of C1 and C8 in different locations using environmental variables. Considering the uncertainty of the model and the experimental data, the confidence intervals of n and α are also calculated. It is shown that the long-term predictions obtained by the proposed method coincide with the actual corrosion loss within ±30% relative error. The estimations for the range of the long-term corrosion loss are also reliable. The proposed method is helpful in extrapolating the knowledge of corrosion management to different field environments where corrosion data are not available.

scholarly journals Multistep-Ahead Air Passengers Traffic Prediction with Hybrid ARIMA-SVMs Models

2014 ◽  
Vol 2014 ◽  
pp. 1-14 ◽  
Author(s):  
Wei Ming ◽  
Yukun Bao ◽  
Zhongyi Hu ◽  
Tao Xiong
Keyword(s):  
Prediction Models ◽  
Nonlinear Modeling ◽  
Real Data ◽  
Data Preprocessing ◽  
Air Transportation ◽  
Data Sets ◽  
Term Prediction ◽  
Short Term Prediction ◽  
Long Term Prediction

The hybrid ARIMA-SVMs prediction models have been established recently, which take advantage of the unique strength of ARIMA and SVMs models in linear and nonlinear modeling, respectively. Built upon this hybrid ARIMA-SVMs models alike, this study goes further to extend them into the case of multistep-ahead prediction for air passengers traffic with the two most commonly used multistep-ahead prediction strategies, that is, iterated strategy and direct strategy. Additionally, the effectiveness of data preprocessing approaches, such as deseasonalization and detrending, is investigated and proofed along with the two strategies. Real data sets including four selected airlines’ monthly series were collected to justify the effectiveness of the proposed approach. Empirical results demonstrate that the direct strategy performs better than iterative one in long term prediction case while iterative one performs better in the case of short term prediction. Furthermore, both deseasonalization and detrending can significantly improve the prediction accuracy for both strategies, indicating the necessity of data preprocessing. As such, this study contributes as a full reference to the planners from air transportation industries on how to tackle multistep-ahead prediction tasks in the implementation of either prediction strategy.

Development of Mathematical Models for Long-Term Prediction of Corrosion Behaviour of Carbon Steel Overpacks for Radioactive Waste Disposal

1996 ◽  
Vol 465 ◽  
Author(s):  
A. R. Hoch ◽  
A. Honda ◽  
F. M. Porter ◽  
S. M. Sharland ◽  
N. Taniguchi
Keyword(s):  
Carbon Steel ◽  
Radioactive Waste ◽  
Mathematical Models ◽  
Waste Disposal ◽  
Corrosion Behaviour ◽  
Radioactive Waste Disposal ◽  
Cathodic Reaction ◽  
Term Prediction ◽  
Long Term Prediction

ABSTRACTMathematical models to enable long-term prediction of the corrosion behaviour of carbon steel overpacks for radioactive waste have been developed. An existing model of the growth of pits, implemented in the CAMLE software, has been extended and used to investigate the sensitivity of the predictions to input parameters, including cathodic reaction kinetics and the relative position of the anode and cathode. Predictions have also been made of the aeration period of the repository, during which localised corrosion is possible.

Modeling research of initial atmospheric corrosion of Q235 carbon steel based on electrical resistance probe

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Zhuolin Li ◽  
Dongmei Fu ◽  
Zibo Pei
Keyword(s):  
Carbon Steel ◽  
Corrosion Rate ◽  
Real Time ◽  
Electrical Resistance ◽  
Atmospheric Corrosion ◽  
Steel Corrosion ◽  
Classification Model ◽  
Content Type ◽  
Q235 Carbon Steel ◽  
Corrosion Data

Purpose This paper aims to discover the mathematical model for Q235 carbon steel corrosion date acquired in the initial stage of atmospheric corrosion using electrical resistance probe. Design/methodology/approach In this paper, mathematical approaches are used to construct a classification model for atmospheric environmental elements and material corrosion rates. Findings Results of the experiment show that the corrosion data can be converted into corrosion depth for calculating corrosion rate to obtain corrosion kinetics model and conform corrosion acceleration phase. Combined with corresponding atmospheric environmental elements, a real time grade subdivision model for corrosion rate can be constructed. Originality/value These mathematical models constructed by real time corrosion data can be well used to research the characteristics about initial atmospheric corrosion of Q235 carbon steel.

scholarly journals Ship Model Identification with Genetic Algorithm Tuning

2021 ◽  
Vol 11 (12) ◽  
pp. 5504
Author(s):  
Anna Miller
Keyword(s):  
Genetic Algorithm ◽  
Standard Deviation ◽  
Short Term ◽  
Validation Data ◽  
Ship Model ◽  
Ship Dynamics ◽  
Term Prediction ◽  
Predictive Controller ◽  
Long Term Prediction

Modeling is the most important component in predictive controller design. It should predict outputs precisely and fast. Thus, it must be adequate for the ship dynamics while having as simple a structure as possible. In a good ship model the standard deviation of a particular coefficient should not exceed 10% of its value. Fitting the validation data to 80% for short-term prediction and 65% for long-term prediction is treated as a declared benchmark for model usage in ship course predictive controller. Regularization was proposed to ensure better state-space models to fit the real ship dynamics and more accurate standard deviation value control. Usage of the simulation results and real-time trials, as model estimation and validation data, respectively, during the identification procedure is proposed. In the first step a predictive linear model is identified conventionally, and then coefficients are regularized, based on the validation data, using a genetic algorithm. Particular linearized model coefficient standard deviations were decreased from more than 100% of their values to approximately 5% of them using genetic algorithm tuning. Moreover, the proposed method eliminated model output signal oscillations, which were observed during the validation process based on experimental data, gained during ship trials. Improved mapping of ship dynamics was achieved. Fit to validation data increased from 71% and 54% to 89% and 76%, respectively, for short-term and long-term prediction. The proposed method, which may be applied to real applications, is easily applicable and reliable. The tuned model is sufficiently suited to plant dynamics and may be used for future predictive control purposes.

scholarly journals Novel robust time series analysis for long-term and short-term prediction

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hiroshi Okamura ◽  
Yutaka Osada ◽  
Shota Nishijima ◽  
Shinto Eguchi
Keyword(s):  
Robust Regression ◽  
Simulated Data ◽  
New Method ◽  
Short Term ◽  
Least Absolute Deviations ◽  
Term Prediction ◽  
Regression Approach ◽  
Short Term Prediction ◽  
Long Term Prediction

AbstractNonlinear phenomena are universal in ecology. However, their inference and prediction are generally difficult because of autocorrelation and outliers. A traditional least squares method for parameter estimation is capable of improving short-term prediction by estimating autocorrelation, whereas it has weakness to outliers and consequently worse long-term prediction. In contrast, a traditional robust regression approach, such as the least absolute deviations method, alleviates the influence of outliers and has potentially better long-term prediction, whereas it makes accurately estimating autocorrelation difficult and possibly leads to worse short-term prediction. We propose a new robust regression approach that estimates autocorrelation accurately and reduces the influence of outliers. We then compare the new method with the conventional least squares and least absolute deviations methods by using simulated data and real ecological data. Simulations and analysis of real data demonstrate that the new method generally has better long-term and short-term prediction ability for nonlinear estimation problems using spawner–recruitment data. The new method provides nearly unbiased autocorrelation even for highly contaminated simulated data with extreme outliers, whereas other methods fail to estimate autocorrelation accurately.

Sign in / Sign up

Export Citation Format

Share Document