An integrated surrogate modeling method for fusing noisy and noise-free data

2021 ◽  
pp. 1-23
Author(s):  
Kunpeng Li ◽  
Shuo Wang ◽  
Yin Liu ◽  
Xueguan Song
Keyword(s):  
Data Fusion ◽  
Noisy Data ◽  
Proposed Model ◽  
Free Data ◽  
Multiple Surrogate Models ◽  
Engineering Problems ◽  
Practical Engineering ◽  
Key Issues ◽  
Type Data ◽  
Underlying Trend

Abstract Datasets in engineering applications often contain multiple types of data, i.e., noise-free data, noisy data with known noise variances, and noisy data with unknown noise variances. In this paper, a data fusion method, termed as multi-type data fusion (MTDF) model, is proposed to fully utilize the information provided by each of these types of data. The proposed model strives to capture the underlying trend implied in the multiple types of data better by approximately interpolating the noise-free data while regressing with the noisy data. To evaluate the prediction accuracy of the MTDF model, it is compared with multiple surrogate models including interpolation models, regression models, and multi-fidelity models on both numerical and practical engineering problems. The results show that the proposed MTDF model presents a more outstanding performance than the other benchmark models. The key issues, i.e., the effect of noise level, the effect of the sample size of noise-free data, and the robustness of the MTDF model are also investigated. The results illustrate that the MTDF model possesses satisfactory feasibility, practicality, and stability.

scholarly journals Prediction of Dead Oil Viscosity: Machine Learning vs. Classical Correlations

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 930
Author(s):  
Fahimeh Hadavimoghaddam ◽  
Mehdi Ostadhassan ◽  
Ehsan Heidaryan ◽  
Mohammad Ali Sadri ◽  
Inna Chapanova ◽  
...  
Keyword(s):  
Machine Learning ◽  
Viscosity Data ◽  
Oil Viscosity ◽  
Pvt Data ◽  
Proposed Model ◽  
Wide Range ◽  
Engineering Problems ◽  
Functional Forms ◽  
Insight Into

Dead oil viscosity is a critical parameter to solve numerous reservoir engineering problems and one of the most unreliable properties to predict with classical black oil correlations. Determination of dead oil viscosity by experiments is expensive and time-consuming, which means developing an accurate and quick prediction model is required. This paper implements six machine learning models: random forest (RF), lightgbm, XGBoost, multilayer perceptron (MLP) neural network, stochastic real-valued (SRV) and SuperLearner to predict dead oil viscosity. More than 2000 pressure–volume–temperature (PVT) data were used for developing and testing these models. A huge range of viscosity data were used, from light intermediate to heavy oil. In this study, we give insight into the performance of different functional forms that have been used in the literature to formulate dead oil viscosity. The results show that the functional form f(γAPI,T), has the best performance, and additional correlating parameters might be unnecessary. Furthermore, SuperLearner outperformed other machine learning (ML) algorithms as well as common correlations that are based on the metric analysis. The SuperLearner model can potentially replace the empirical models for viscosity predictions on a wide range of viscosities (any oil type). Ultimately, the proposed model is capable of simulating the true physical trend of the dead oil viscosity with variations of oil API gravity, temperature and shear rate.

Self-determined Occupational Performance Model for Children From Economically Disadvantaged Backgrounds

2021 ◽  
pp. 000841742110356
Author(s):  
Laura M.P. Bray ◽  
Gilson Capilouto
Keyword(s):  
Low Income ◽  
Economically Disadvantaged ◽  
Psychological Needs ◽  
Basic Psychological Needs ◽  
Performance Model ◽  
Social Deficits ◽  
Occupational Performance ◽  
Low Socioeconomic ◽  
Proposed Model ◽  
Key Issues

Background. Children from low-income backgrounds have a higher incidence of handwriting challenges due to the unique social and environmental stressors associated with poverty. Additionally, children from economically disadvantaged households are at risk for motor, cognitive, and social deficits, which further impact their handwriting performance. Purpose. The purpose of this paper is to propose a theoretical model that provides a holistic perspective for addressing the handwriting needs of children from low-socioeconomic backgrounds. Key Issues. The presented conceptual model is derived from the person–environment–occupation model for occupational performance and self-determination theory. These theories reciprocally complement and enhance each other, providing a foundation from which clinicians can guide evaluation and intervention. Implications. Through the use of the proposed model, evaluation and intervention focus on intrinsic motivation while considering the physical, social, and cultural impacts on a child's occupational performance. The provider connects with the child's basic psychological needs, thus improving handwriting outcomes and facilitating improved academic performance.

scholarly journals Considering the dynamic refueling behavior in locating electric vehicle charging stations

2014 ◽  
Vol II-2 ◽  
pp. 41-46 ◽  
Author(s):  
K. Liu ◽  
X.H. Sun
Keyword(s):  
Influence Factors ◽  
Spatial Location ◽  
Location Model ◽  
Electric Vehicle Charging ◽  
Charging Time ◽  
Proposed Model ◽  
Key Issues ◽  
Charging Stations ◽  
Dual Objectives ◽  
Ev Charging

Electric vehicles (EVs) will certainly play an important role in addressing the energy and environmental challenges at current situation. However, location problem of EV charging stations was realized as one of the key issues of EVs launching strategy. While for the case of locating EV charging stations, more influence factors and constraints need to be considered since the EVs have some special attributes. The minimum requested charging time for EVs is usually more than 30minutes, therefore the possible delay time due to waiting or looking for an available station is one of the most important influence factors. In addition, the intention to purchase and use of EVs that also affects the location of EV charging stations is distributed unevenly among regions and should be considered when modelling. Unfortunately, these kinds of time-spatial constraints were always ignored in previous models. Based on the related research of refuelling behaviours and refuelling demands, this paper developed a new concept with dual objectives of minimum waiting time and maximum service accessibility for locating EV charging stations，named as Time-Spatial Location Model (TSLM). The proposed model and the traditional flow-capturing location model are applied on an example network respectively and the results are compared. Results demonstrate that time constraint has great effects on the location of EV charging stations. The proposed model has some obvious advantages and will help energy providers to make a viable plan for the network of EV charging stations.

scholarly journals Reflections on the Hysteretic Damping Model

2009 ◽  
Vol 16 (5) ◽  
pp. 529-542 ◽  
Author(s):  
Nuno Maia
Keyword(s):  
Free Vibration ◽  
Point Of View ◽  
The Other ◽  
Hysteretic Damping ◽  
Engineering Problems ◽  
Practical Engineering ◽  
The Subject ◽  
The One ◽  
Damping Model ◽  
Free Vibration Response

This paper presents a reflection on a recently proposed solution to the problem of the free vibration response with the constant hysteretic damping model, that has been presented in some conferences in recent years, by the author himself and some of his colleagues. On the one hand, as expected, the subject has been received with natural criticism, mainly due to the well-known non-causal behaviour of the model in free vibration. On the other hand, it was not easy to understand what could be wrong in that proposal, as apparently everything was perfect from a mathematical point of view. The author decided that this subject deserved a more careful and detailed analysis and – in this kind of tutorial paper – the issue seems to have been clarified. It is concluded that the proposed solution involving the constant hysteretic damping corresponds in fact to an equivalent viscously damped model; it is therefore concluded that the application of the constant hysteretic damping to model the free vibration of practical engineering problems should be considered only in the perspective of an equivalent viscously damped model.

Automated monitoring and assessment of productivity in earthmoving projects

2018 ◽  
Vol 45 (11) ◽  
pp. 958-972 ◽  
Author(s):  
Ashraf Salem ◽  
Osama Moselhi
Keyword(s):  
Data Fusion ◽  
Continuous Monitoring ◽  
Research Work ◽  
Sensor Data ◽  
Fusion Algorithm ◽  
Cost Overruns ◽  
Knowledge Based ◽  
Monitoring Model ◽  
Multi Sensor Data Fusion ◽  
Proposed Model

Continuous monitoring of productivity and assessment of its variations are crucial processes that significantly contribute to success of earthmoving projects. Numerous factors may lead to productivity variations. However, these factors are subjectively identified using manual knowledge-based expert judgment. Such manual recognition process is not only subject to errors but also time-consuming. There is a lack of research work that focuses on near real-time assessment of productivity variation and its effect on cost, schedule and effective utilization of resources in earthmoving projects. This paper presents a customized multi-source automated data acquisition model that acquires data from a variety of wireless sensing technologies. The acquired multi-sensor data are transmitted to a central MySQL database. Then a newly developed data fusion algorithm is applied for truck state recognition, and hence the duration of each earthmoving state. Multi-sensor data fusion facilitates measurement of actual productivity, and consequently the assessment of productivity ratios that support continuous monitoring of productivity variation in earthmoving operations. The developed tracking and monitoring model generates an early warning that supports proactive decisions to avoid schedule delays, cost overruns, and inefficient depletion of resources. A case study is used to reveal the applicability of the proposed model in monitoring and assessing actual productivity and its deviations from planned productivity. Finally, results are discussed and conclusions are drawn highlighting the features of the proposed model.

Antecedents of Consumer Trust in B2C Electronic Commerce and Mobile Commerce

2011 ◽  
pp. 158-176
Author(s):  
Dan J. Kim
Keyword(s):  
Electronic Commerce ◽  
Large Scale ◽  
Reference Model ◽  
Mobile Commerce ◽  
Third Party ◽  
Consumer Trust ◽  
Consumer Electronic ◽  
Proposed Model ◽  
Key Issues ◽  
Business To Consumer

Despite the importance of trust in electronic commerce including mobile commerce, there is insufficient theory and model concerning the determinants of consumer trust in business-to-consumer electronic commerce. Thus, the purpose of this chapter is to: i) identify the major antecedents of a consumer’s trust in electronic commerce and mobile commerce contexts through a large-scale literature review, ii) develop an integrative trust antecedent reference model summarizing the antecedents of consumer trust, and iii) finally discuss six categories of mobile applications as future trends of technologies and key issues related to consumer trust area in electronic commerce. In addition, to provide the validity of the proposed reference model, this chapter also proposes a research model derived from the reference model and discusses the constructs of the proposed model in detail. The chapter concludes that building trust is not simply an issue related to consumer-technology-buyer, but it is a complex issue that involves the interactions of key elements (buyer, seller, third-party, technology, and market environment) at least.

Characterization of the Time-Dependent Rheological Behavior of Fluids for Electronics Packaging

2003 ◽  
Author(s):  
X. B. Chen ◽  
W. J. Zhang ◽  
G. Schoenau ◽  
B. W. Surgenor
Keyword(s):  
Rheological Behavior ◽  
Flow Behavior ◽  
Electronics Packaging ◽  
Structural Theory ◽  
Time Dependent ◽  
Fluid Behavior ◽  
Proposed Model ◽  
Key Issues

To effectively control the dispensing process by which fluids are delivered onto substrates in electronics packaging, one of the key issues is to understand and characterize the flow behavior of the fluids being dispensed. However, this task has proven to be a demanding one as the fluids used for electronics packaging usually exhibit the time-dependent rheological behavior, which has not been well documented in the literature. In this paper, the characterization of time-dependent rheological behavior of fluids is studied. In particular, a model using the structural theory is proposed and applied to the characterization of the decay and recovery of fluid behavior, which are typically encountered in a dispensing process. Experiments are conducted to validate the proposed model.

A Mesoscopic Damage Model for Predicting the Plastic-Creep Life of Welded Joints Subjected to Quasi-Static Loading

2010 ◽  
Author(s):  
Khosrow Zarrabi ◽  
Jad Jelwan ◽  
Tahir Mahmood
Keyword(s):  
Welded Joints ◽  
Welded Joint ◽  
Damage Model ◽  
Life Assessment ◽  
Research Activities ◽  
Proposed Model ◽  
Engineering Problems ◽  
Complex Engineering ◽  
The Subject ◽  
Plastic Creep

The integrity and life assessment of welded joints operating at high temperatures and subjected to non-linear damage mechanisms such as plasticity and creep are complex engineering problems and currently the subject of intensive research activities. This paper gauges the accuracy of a model that takes into account creep and plasticity deformation proposed by Zarrabi et al. to a butt welded thick tube. It is shown that the proposed model can predict the life of this welded joint with an error of 1%. Currently the model is being extended to include fatigue deformation.

scholarly journals Performance Evaluation of MDO Architectures within a Variable Complexity Problem

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Daiyu Zhang ◽  
Baowei Song ◽  
Peng Wang ◽  
Yanru He
Keyword(s):  
Performance Evaluation ◽  
Multidisciplinary Design Optimization ◽  
Large Scale ◽  
Multidisciplinary Design ◽  
Design Variables ◽  
Complexity Problem ◽  
Engineering Problems ◽  
Practical Engineering ◽  
Coupling Variables ◽  
Selection Of

Though quite a number of multidisciplinary design optimization (MDO) architectures have been proposed for the optimal design of large-scale multidisciplinary systems, how their performance changes with the complexity of MDO problem varied is not well studied. In order to solve this problem, this paper presents a variable complexity problem which allows people to obtain a MDO problem with arbitrary complexity by specifying its changeable parameters, such as the number of disciplines and the numbers of design variables. Then four investigations are performed to evaluate how the performance of different MDO architectures changes with the number of disciplines, global variables, local variables, and coupling variables varied, respectively. Finally, the results supply guidance for the selection of MDO architectures in solving practical engineering problems with different complexity.

A Possibility Estimation Model and its Application

2013 ◽  
Vol 475-476 ◽  
pp. 423-427
Author(s):  
Lin Na Ji ◽  
Feng Bao Yang ◽  
Xiao Xia Wang
Keyword(s):  
Measurement Data ◽  
Engineering Application ◽  
Transformation Method ◽  
Estimation Model ◽  
Property Estimation ◽  
New Methods ◽  
Proposed Model ◽  
Practical Engineering ◽  
New Ideas ◽  
Possibility Distributions

Aiming at some uncertainty problems such as quality inspection of adhesive structure and risk assessment in the practical engineering application, a possibility estimation model is established. Firstly, according to the fuzziness, randomness and uncertainty of the measurement data, a transformation method of possibility distribution with non-single peak values and nonlinearity is proposed from probability density function. Secondly, for possibility distributions of measurement data of each sensor, a kind of possibility fusion rules is put forward, then the fusion distribution is estimated by the possibility mean. Finally the model is applied to the mechanical property estimation of adhesive structure, and the result forecasts the quality. The proposed model with strong applicability, not only provides convenience for the operations among possibility distributions, but also offers new ideas and new methods to deal with uncertain problems.

Sign in / Sign up

Export Citation Format

Share Document