Search scope:
排序: Display mode:
Quality-related locally weighted soft sensing for non-stationary processes by a supervised Bayesian network with latent variables Research Articles
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 9, Pages 1234-1246 doi: 10.1631/FITEE.2000426
It is necessary to construct an adaptive model to cope with process non-stationaries. In this study, a novel quality-related locally weighted soft sensing method is designed for non-stationary processes based on a Bayesian network with . Specifically, a is proposed where quality-oriented are extracted and further applied to a double-layer similarity measurement algorithm. The proposed soft sensing method tries to find a general approach for non-stationary processes via quality-related information where the concepts of local similarities and window confidence are explained in detail. The performance of the developed method is demonstrated by application to a numerical example and a debutanizer column. It is shown that the proposed method outperforms competitive methods in terms of the accuracy of predicting key quality variables.
Keywords: 软测量;有监督贝叶斯网络;隐变量;局部加权建模;质量预测
Short-term Load Forecasting Using Neural Network
Luo Mei
Strategic Study of CAE 2007, Volume 9, Issue 5, Pages 77-80
Based on the load data of meritorious power of some area power system, three BP ANN models, namely SDBP, LMBP and BRBP Model, are established to carry out the short-term load forecasting work, and the results are compared. Since the traditional BP algorithm has some unavoidable disadvantages, such as the low training speed and the possibility of being plunged into minimums local minimizing the optimized function, an optimized L-M algorithm, which can accelerate the training of neural network and improve the stability of the convergence, should be applied to forecast to reduce the mean relative error. Bayesian regularization can overcome the over fitting and improve the generalization of ANN.
Keywords: short-term load forecasting(STLF) ANN Levenberg-Marquardt Bayesian regularization optimized algorithms
Hybrid Bayesian Network Method for Predicting Intrusion
Wang Liangmin, Ma Jianfeng
Strategic Study of CAE 2008, Volume 10, Issue 8, Pages 87-96
To solve the open problem of predicting intrusion in Reactive Intrusion Tolerance System, a hybrid Bayesian network method is presented in this paper. Firstly, an intrusion model is presented, which pays its emphasis on the influence of the intrusion upon the system and describes the intrusion as the state transition process of the attackers' capability. The intrusion model is appropriate to trig the reactive intrusion tolerance system. We proposed the constructing algorithm and the proof of its feasibility. Secondly, a hybrid Bayesian network model based on this intrusion model is presented to show the casual relation of the attack behavior and secure state. The model is divided into two layers: attack behavior layer and secure state layer, in which the attack edges and state nodes of intrusion model are used as nodes in behavior layer and state layer respectively. In this hybrid Bayesian network model, the connections of the same layer are continuous, but that of the different layer are converge. The algorithm for computing the joint probability distribution of the hybrid Bayesian network is presented. In the end, the efficiency of the intrusion model and hybrid Bayesian network in predicting intrusion is shown by the experiment with our belief propagation algorithm, and the advantages of this predicting method over the related work are shown by analysis and comparisons.
Keywords: intrusion tolerance alert correlation intrusion model intrusion prediction
A Local Quadratic Embedding Learning Algorithm and Applications for Soft Sensing Article
Yaoyao Bao, Yuanming Zhu, Feng Qian
Engineering 2022, Volume 18, Issue 11, Pages 186-196 doi: 10.1016/j.eng.2022.04.025
Inspired by the tremendous achievements of meta-learning in various fields, this paper proposes the local quadratic embedding learning (LQEL) algorithm for regression problems based on metric learning and neural networks (NNs). First, Mahalanobis metric learning is improved by optimizing the global consistency of the metrics between instances in the input and output space. Then, we further prove that the improved metric learning problem is equivalent to a convex programming problem by relaxing the constraints. Based on the hypothesis of local quadratic interpolation, the algorithm introduces two lightweight NNs; one is used to learn the coefficient matrix in the local quadratic model, and the other is implemented for weight assignment for the prediction results obtained from different local neighbors. Finally, the two sub-models are embedded in a unified regression framework, and the parameters are learned by means of a stochastic gradient descent (SGD) algorithm. The proposed algorithm can make full use of the information implied in target labels to find more reliable reference instances. Moreover, it prevents the model degradation caused by sensor drift and unmeasurable variables by modeling variable differences with the LQEL algorithm. Simulation results on multiple benchmark datasets and two practical industrial applications show that the proposed method outperforms several popular regression methods.
Keywords: Local quadratic embedding Metric learning Regression machine Soft sensor
The application of advanced threshold denoising tothe MMW target radiation signal
Fan Qinghui,Li Xingguo
Strategic Study of CAE 2008, Volume 10, Issue 7, Pages 153-157
In this paper based on the characteristics of millimeter wave radiation signal for wavelet transform, non-negative wavelet coefficient is used as the wavelet coefficient of the signal. For a given threshold value, the wavelet coefficient which is smaller than the threshold is set zero and the wavelet coefficient which is larger than the threshold is set the difference between the coefficient and a constant a.The method for valuing a is inferred by the variance function of signal, and the experiments show that it has good ability of removing the noise in MMW target radiation signal.
Keywords: The application of advanced threshold denoising tothe MMW target radiation signal
A Probabilistic Architecture of Long-Term Vehicle Trajectory Prediction for Autonomous Driving Article
Jinxin Liu, Yugong Luo, Zhihua Zhong, Keqiang Li, Heye Huang, Hui Xiong
Engineering 2022, Volume 19, Issue 12, Pages 228-239 doi: 10.1016/j.eng.2021.12.020
In mixed and dynamic traffic environments, accurate long-term trajectory forecasting of surrounding vehicles is one of the indispensable preconditions for autonomous vehicles (AVs) to accomplish reasonable behavioral decisions and guarantee driving safety. In this paper, we propose an integrated probabilistic architecture for long-term vehicle trajectory prediction, which consists of a driving inference model (DIM) and a trajectory prediction model (TPM). The DIM is designed and employed to accurately infer the potential driving intention based on a dynamic Bayesian network. The proposed DIM incorporates the basic traffic rules and multivariate vehicle motion information. To further improve the prediction accuracy and realize uncertainty estimation, we develop a Gaussian process (GP)-based TPM, considering both the short-term prediction results of the vehicle model and the driving motion characteristics. Afterward, the effectiveness of our novel approach is demonstrated by conducting experiments on a public naturalistic driving dataset under lane-changing scenarios. The superior performance on the task of long-term trajectory prediction is presented and verified by comparing with other advanced methods.
Keywords: Autonomous driving Dynamic Bayesian network Driving intention recognition Gaussian process Vehicle trajectory prediction
Supervised topic models with weighted words: multi-label document classification None
Yue-peng ZOU, Ji-hong OUYANG, Xi-ming LI
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 4, Pages 513-523 doi: 10.1631/FITEE.1601668
Keywords: Supervised topic model Multi-label classification Class frequency Labeled latent Dirichlet allocation (L-LDA) Dependency-LDA
Data-Driven Model Falsification and Uncertainty Quantification for Fractured Reservoirs Article
Junling Fang, Bin Gong, Jef Caers
Engineering 2022, Volume 18, Issue 11, Pages 116-128 doi: 10.1016/j.eng.2022.04.015
Many properties of natural fractures are uncertain, such as their spatial distribution, petrophysical properties, and fluid flow performance. Bayesian theorem provides a framework to quantify the uncertainty in geological modeling and flow simulation, and hence to support reservoir performance predictions. The application of Bayesian methods to fractured reservoirs has mostly been limited to synthetic cases. In field applications, however, one of the main problems is that the Bayesian prior is falsified, because it fails to predict past reservoir production data. In this paper, we show how a global sensitivity analysis (GSA) can be used to identify why the prior is falsified. We then employ an approximate Bayesian computation (ABC) method combined with a tree-based surrogate model to match the production history. We apply these two approaches to a complex fractured oil and gas reservoir where all uncertainties are jointly considered, including the petrophysical properties, rock physics properties, fluid properties, discrete fracture parameters, and dynamics of pressure and transmissibility. We successfully identify several reasons for the falsification. The results show that the methods we propose are effective in quantifying uncertainty in the modeling and flow simulation of a fractured reservoir. The uncertainties of key parameters, such as fracture aperture and fault conductivity, are reduced.
Keywords: Bayesian evidential learning Falsification Fractured reservoir Random forest Approximate Bayesian computation
Data Centric Design: A New Approach to Design of Microstructural Material Systems Article
Wei Chen, Akshay Iyer, Ramin Bostanabad
Engineering 2022, Volume 10, Issue 3, Pages 89-98 doi: 10.1016/j.eng.2021.05.022
Building processing, structure, and property (PSP) relations for computational materials design is at the heart of the Materials Genome Initiative in the era of high-throughput computational materials science. Recent technological advancements in data acquisition and storage, microstructure characterization and reconstruction (MCR), machine learning (ML), materials modeling and simulation, data processing, manufacturing, and experimentation have significantly advanced researchers’ abilities in building PSP relations and inverse material design. In this article, we examine these advancements from the perspective of design research. In particular, we introduce a data-centric approach whose fundamental aspects fall into three categories: design representation, design evaluation, and design synthesis. Developments in each of these aspects are guided by and benefit from domain knowledge. Hence, for each aspect, we present a wide range of computational methods whose integration realizes data-centric materials discovery and design.
Keywords: Materials informatics Machine learning Microstructure Reconstruction Bayesian optimization Mixed-variable modeling Dimension reduction Materials design
Wang Huating,Feng Junweng,Gao Peng ,Wang Jian
Strategic Study of CAE 2007, Volume 9, Issue 12, Pages 4-9
How to use experience and test result to make the best choice is a decision problem for a electric power company when deciding to build a reactor, and valuation networks is a new method for representing and solving Bayesian decision problems. This article used Valuation Networks to analyze the reactor problem of a given company, which valuation network representing and solving process is demonstrated in detail.
Keywords: decision theory valuation networks influence diagrams Bayesian decision
Bayesian Optimization for Field-Scale Geological Carbon Storage
Xueying Lu, Kirk E. Jordan, Mary F. Wheeler, Edward O. Pyzer-Knapp, Matthew Benatan
Engineering 2022, Volume 18, Issue 11, Pages 96-104 doi: 10.1016/j.eng.2022.06.011
We present a framework that couples a high-fidelity compositional reservoir simulator with Bayesian optimization (BO) for injection well scheduling optimization in geological carbon sequestration. This work represents one of the first at tempts to apply BO and high-fidelity physics models to geological carbon storage. The implicit parallel accurate reservoir simulator (IPARS) is utilized to accurately capture the underlying physical processes during CO2 sequestration. IPARS provides a framework for several flow and mechanics models and thus supports both stand-alone and coupled simulations. In this work, we use the compositional flow module to simulate the geological carbon storage process. The compositional flow model, which includes a hysteretic three-phase relative permeability model, accounts for three major CO2 trapping mechanisms: structural trapping, residual gas trapping, and solubility trapping. Furthermore, IPARS is coupled to the International Business Machines (IBM) Corporation Bayesian Optimization Accelerator (BOA) for parallel optimizations of CO2 injection strategies during field-scale CO2 sequestration. BO builds a probabilistic surrogate for the objective function using a Bayesian machine learning algorithm—the Gaussian process regression, and then uses an acquisition function that leverages the uncertainty in the surrogate to decide where to sample. The IBM BOA addresses the three weaknesses of standard BO that limits its scalability in that IBM BOA supports parallel (batch) executions, scales better for high-dimensional problems, and is more robust to initializations. We demonstrate these merits by applying the algorithm in the optimization of the CO2 injection schedule in the Cranfield site in Mississippi, USA, using field data. The optimized injection schedule achieves 16% more gas storage volume and 56% less water/surfactant usage compared with the baseline. The performance of BO is compared with that of a genetic algorithm (GA) and a covariance matrix adaptation (CMA)-evolution strategy (ES). The results demonstrate the superior performance of BO, in that it achieves a competitive objective function value with over 60% fewer forward model evaluations.
Keywords: Compositional flow Bayesian optimization Geological carbon storage CCUS Machine learning AI for science
Label fusion for segmentation via patch based on local weighted voting Article
Kai ZHU, Gang LIU, Long ZHAO, Wan ZHANG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 5, Pages 680-688 doi: 10.1631/FITEE.1500457
Keywords: Label fusion Local weighted voting Patch-based Background analysis
Data-driven soft sensors in blast furnace ironmaking: a survey Review Article
Yueyang LUO, Xinmin ZHANG, Manabu KANO, Long DENG, Chunjie YANG, Zhihuan SONG
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 3, Pages 327-354 doi: 10.1631/FITEE.2200366
Keywords: Soft sensors Data-driven modeling Machine learning Deep learning Blast furnace Ironmaking process
The Use of Data Mining Techniques in Rockburst Risk Assessment
Luis Ribeiro e Sousa, Tiago Miranda, Rita Leal e Sousa, Joaquim Tinoco
Engineering 2017, Volume 3, Issue 4, Pages 552-558 doi: 10.1016/J.ENG.2017.04.002
Rockburst is an important phenomenon that has affected many deep underground mines around the world. An understanding of this phenomenon is relevant to the management of such events, which can lead to saving both costs and lives. Laboratory experiments are one way to obtain a deeper and better understanding of the mechanisms of rockburst. In a previous study by these authors, a database of rockburst laboratory tests was created; in addition, with the use of data mining (DM) techniques, models to predict rockburst maximum stress and rockburst risk indexes were developed. In this paper, we focus on the analysis of a database of in situ cases of rockburst in order to build influence diagrams, list the factors that interact in the occurrence of rockburst, and understand the relationships between these factors. The in situ rockburst database was further analyzed using different DM techniques ranging from artificial neural networks (ANNs) to naive Bayesian classifiers. The aim was to predict the type of rockburst—that is, the rockburst level—based on geologic and construction characteristics of the mine or tunnel. Conclusions are drawn at the end of the paper.
Keywords: Rockburst Data mining Bayesian networks In situ database
Unsupervised feature selection via joint local learning and group sparse regression Regular Papers
Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 4, Pages 538-553 doi: 10.1631/FITEE.1700804
Feature selection has attracted a great deal of interest over the past decades. By selecting meaningful feature subsets, the performance of learning algorithms can be effectively improved. Because label information is expensive to obtain, unsupervised feature selection methods are more widely used than the supervised ones. The key to unsupervised feature selection is to find features that effectively reflect the underlying data distribution. However, due to the inevitable redundancies and noise in a dataset, the intrinsic data distribution is not best revealed when using all features. To address this issue, we propose a novel unsupervised feature selection algorithm via joint local learning and group sparse regression (JLLGSR). JLLGSR incorporates local learning based clustering with group sparsity regularized regression in a single formulation, and seeks features that respect both the manifold structure and group sparse structure in the data space. An iterative optimization method is developed in which the weights finally converge on the important features and the selected features are able to improve the clustering results. Experiments on multiple real-world datasets (images, voices, and web pages) demonstrate the effectiveness of JLLGSR.
Keywords: Unsupervised Local learning Group sparse regression Feature selection
Title Author Date Type Operation
Quality-related locally weighted soft sensing for non-stationary processes by a supervised Bayesian network with latent variables
Journal Article
A Local Quadratic Embedding Learning Algorithm and Applications for Soft Sensing
Yaoyao Bao, Yuanming Zhu, Feng Qian
Journal Article
The application of advanced threshold denoising tothe MMW target radiation signal
Fan Qinghui,Li Xingguo
Journal Article
A Probabilistic Architecture of Long-Term Vehicle Trajectory Prediction for Autonomous Driving
Jinxin Liu, Yugong Luo, Zhihua Zhong, Keqiang Li, Heye Huang, Hui Xiong
Journal Article
Supervised topic models with weighted words: multi-label document classification
Yue-peng ZOU, Ji-hong OUYANG, Xi-ming LI
Journal Article
Data-Driven Model Falsification and Uncertainty Quantification for Fractured Reservoirs
Junling Fang, Bin Gong, Jef Caers
Journal Article
Data Centric Design: A New Approach to Design of Microstructural Material Systems
Wei Chen, Akshay Iyer, Ramin Bostanabad
Journal Article
Application of Valuation Networks in Making the Decision to Build a Reactor for Electric Power Company
Wang Huating,Feng Junweng,Gao Peng ,Wang Jian
Journal Article
Bayesian Optimization for Field-Scale Geological Carbon Storage
Xueying Lu, Kirk E. Jordan, Mary F. Wheeler, Edward O. Pyzer-Knapp, Matthew Benatan
Journal Article
Label fusion for segmentation via patch based on local weighted voting
Kai ZHU, Gang LIU, Long ZHAO, Wan ZHANG
Journal Article
Data-driven soft sensors in blast furnace ironmaking: a survey
Yueyang LUO, Xinmin ZHANG, Manabu KANO, Long DENG, Chunjie YANG, Zhihuan SONG
Journal Article
The Use of Data Mining Techniques in Rockburst Risk Assessment
Luis Ribeiro e Sousa, Tiago Miranda, Rita Leal e Sousa, Joaquim Tinoco
Journal Article