Study on Box-Jenkins Method of Prediction of Chloride Concentration of Marine Concrete Structures

2013 ◽  
Vol 351-352 ◽  
pp. 1629-1636
Author(s):  
Er Ju Li ◽  
Xin Gang Zhou
Keyword(s):  
Life Prediction ◽  
Prediction Models ◽  
Time Series Prediction ◽  
Concrete Structures ◽  
Model Identification ◽  
Chloride Concentration ◽  
Prediction Method ◽  
Parameter Estimate ◽  
Test Model ◽  
Marine Concrete

The paper introduces life prediction models and existing questions of marine concrete structures exposed to chloride environment; Theory of Box-Jenkins time series prediction method is put forward to analyze the change law of chloride concentration of reinforcemnet surface of marine concrete structures along with time; Stationary test, model identification and parameter estimate are introduced; Modeling process and best model identification are discussed by means of analyzing laws of chloride concentration changing with time, and predicts using the best model. Analysis results show that the prediction model built by Box-Jenkins method has simple form and high prediction accuracy. Whats more, future chloride concentration can be well predicted by history values without determining specific values of durability parameters.This is a new method of life prediction of marine concrete structures.

scholarly journals FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework

Water ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1031
Author(s):  
Jianlong Xu ◽  
Kun Wang ◽  
Che Lin ◽  
Lianghong Xiao ◽  
Xingshan Huang ◽  
...  
Keyword(s):  
Water Quality ◽  
Prediction Models ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Quality Data ◽  
Enterprise Management ◽  
Feature Interaction ◽  
Quality Prediction ◽  
Water Quality Data ◽  
Water Quality Prediction

Water quality prediction plays a crucial role in both enterprise management and government environmental management. However, due to the variety in water quality data, inconsistent frequency of data acquisition, inconsistency in data organization, and volatility and sparsity of data, predicting water quality accurately and efficiently has become a key problem. This paper presents a recurrent neural network water quality prediction method based on a sequence-to-sequence (seq2seq) framework. The gate recurrent unit (GRU) model is used as an encoder and decoder, and a factorization machine (FM) is integrated into the model to solve the problem of high sparsity and high dimensional feature interaction in the data, which was not addressed by the water quality prediction models in prior research. Moreover, due to the long period and timespan of water quality data, we add a dual attention mechanism to the seq2seq framework to address memory failures in deep learning. We conducted a series of experiments, and the results show that our proposed method is more accurate than several typical water quality prediction methods.

scholarly journals Research on low cycle fatigue life prediction considering average strain

2022 ◽  
Author(s):  
Yan Peng ◽  
Yang Liu ◽  
Haoran Li ◽  
Jiankang Xing
Keyword(s):  
Fatigue Life ◽  
Life Prediction ◽  
Damage Mechanics ◽  
Prediction Models ◽  
Low Cycle Fatigue ◽  
Prediction Method ◽  
Fatigue Life Prediction ◽  
Model Parameters ◽  
Cycle Fatigue ◽  
Average Strain

Abstract To address the difficult problems in the study of the effect of average strain on fatigue life under low-cycle fatigue loads, the effect of average strain on the low-cycle fatigue life of materials under different strain cycle ratios was discussed based on the framework of damage mechanics and its irreversible thermodynamics. By introducing the Ramberg-Osgood cyclic constitutive equation, a new low-cycle fatigue life prediction method based on the intrinsic damage dissipation theory considering average strain was proposed, which revealed the correlation between low-cycle fatigue strain life , material properties, and average strain. Through the analysis of the low-cycle fatigue test data of five different metal materials, the model parameters of the corresponding materials were obtained. The calculation results indicate that the proposed life prediction method is in good agreement with the test, and a reasonable characterization of the low-cycle fatigue life under the influence of average strain is realized. Comparing calculations with three typical low-cycle fatigue life prediction models, the new method is within two times the error band, and the prediction effect is significantly better than the existing models, which is more suitable for low-cycle fatigue life prediction. The low-cycle fatigue life prediction of different cyclic strain ratios based on the critical region intrinsic damage dissipation power method provides a new idea for the research of low-cycle fatigue life prediction of metallic materials.

scholarly journals A Network Traffic Prediction Model Based on Quantum-Behaved Particle Swarm Optimization Algorithm and Fuzzy Wavelet Neural Network

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Kun Zhang ◽  
Zhao Hu ◽  
Xiao-Ting Gan ◽  
Jian-Bo Fang
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Network Traffic ◽  
Prediction Models ◽  
Time Series Prediction ◽  
Particle Swarm ◽  
Prediction Method ◽  
Wavelet Neural Network ◽  
Swarm Optimization ◽  
Fuzzy Wavelet Neural Network

Due to the fact that the fluctuation of network traffic is affected by various factors, accurate prediction of network traffic is regarded as a challenging task of the time series prediction process. For this purpose, a novel prediction method of network traffic based on QPSO algorithm and fuzzy wavelet neural network is proposed in this paper. Firstly, quantum-behaved particle swarm optimization (QPSO) was introduced. Then, the structure and operation algorithms of WFNN are presented. The parameters of fuzzy wavelet neural network were optimized by QPSO algorithm. Finally, the QPSO-FWNN could be used in prediction of network traffic simulation successfully and evaluate the performance of different prediction models such as BP neural network, RBF neural network, fuzzy neural network, and FWNN-GA neural network. Simulation results show that QPSO-FWNN has a better precision and stability in calculation. At the same time, the QPSO-FWNN also has better generalization ability, and it has a broad prospect on application.

scholarly journals Prakiraan Waktu Transit Pada Transportasi Intermoda Menggunakan Metode Prediction Time Series Dan Computer Vision

2019 ◽  
Vol 6 (2) ◽  
pp. 99-108
Author(s):  
Muhammad Amin Bakri ◽  
Syahri Ramadhan
Keyword(s):  
Computer Vision ◽  
Time Series ◽  
Real Time ◽  
Transit Time ◽  
Prediction Models ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Video Data ◽  
Traffic Prediction ◽  
Prediction Time

Meskipun model prediksi arus lalu lintas sudah banyak dikembangkan, hasilnya seringkali masih bersifat kurang memuaskan. Oleh karena itu, model prediksi lalu lintas dengan kebutuhan data yang bersifat real-time serta dalam jumlah besar, kompleks, dan dinamis, perlu dikaji ulang kembali untuk mendapatkan hasil yang optimal. Tulisan ini bertujuan untuk mengajukan sebuah prosedur peramalam transit time transportasi intermoda dengan memanfaatkan data video kendaraan yang diperoleh dengan menggunakan sensor kamerayang diterapkan pada transportasi bus Transjakarta dan commuter line di Jabodetabek. Sistem transit timejourney yang ditawarkan memiliki input sensor camera, kemudian outputnya dikonversi melalui computer vision, lalu diproses dengan menggunakan metode prediction time series setelah mendapatkan masukan informasi rute perjalanan. Luaran dari sistem ini meghasilkan transit timeuntuk rute yang diinginkan.   Although many traffic prediction models have been developed, the results are often still unsatisfactory. Therefore, traffic prediction models on real-time, large, complex, and dynamic data, needto be developed to obtain optimal results. This paper aims to propose a procedure for the transition of intermodal transportation time by utilizing vehicle video data obtained using camera sensors applied to Trans Jakarta bus transportation and commuter lines case in Jabodetabek. The transit time journey system offered has a camera sensor input, then the output is converted through computer vision, then processed using the time series prediction method after getting input of travel route information. The results of this system is the transit time for desired route.

Hybrid remaining useful life prediction method. A case study on railway D-cables

2021 ◽  
pp. 107746
Author(s):  
Yu Zang ◽  
Wei Shangguan ◽  
Baigen Cai ◽  
Huasheng Wang ◽  
Michael. G. Pecht
Keyword(s):  
Life Prediction ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Useful Life

Remaining useful life prediction method for machine tools based on meta-action theory

2021 ◽  
pp. 1748006X2110025
Author(s):  
Zongyi Mu ◽  
Yan Ran ◽  
Genbao Zhang ◽  
Hongwei Wang ◽  
Xin Yang
Keyword(s):  
Machine Tools ◽  
Life Prediction ◽  
Action Theory ◽  
Prediction Method ◽  
Operational Reliability ◽  
Remaining Useful Life ◽  
Practical Application ◽  
Dynamic Prediction ◽  
Degradation Model ◽  
Useful Life

Remaining useful life (RUL) is a crucial indictor to measure the performance degradation of machine tools. It directly affects the accuracy of maintenance decision-making, thus affecting operational reliability of machine tools. Currently, most RUL prediction methods are for the parts. However, due to the interaction among the parts, even RUL of all the parts cannot reflect the real RUL of the whole machine. Therefore, an RUL prediction method for the whole machine is needed. To predict RUL of the whole machine, this paper proposes an RUL prediction method with dynamic prediction objects based on meta-action theory. Firstly, machine tools are decomposed into the meta-action unit chains (MUCs) to obtain suitable prediction objects. Secondly, the machining precision unqualified rate (MPUR) control chart is used to conduct an out of control early warning for machine tools’ performance. At last, the Markov model is introduced to determine the prediction objects in next prediction and the Wiener degradation model is established to predict RUL of machine tools. According to the practical application, feasibility and effectiveness of the method is proved.

Sign in / Sign up

Export Citation Format

Share Document