Showing papers by "Hong Wang published in 2020"

Robust Online Sequential RVFLNs for Data Modeling of Dynamic Time-Varying Systems With Application of an Ironmaking Blast Furnace

Abstract: By dealing with robust modeling and online learning together in a unified random vector functional-link networks (RVFLNs) framework, this paper presents a novel robust online sequential RVFLNs for data modeling of dynamic time-varying systems together with its application for a blast furnace (BF) ironmaking process. First, to overcome the difficulties caused by the nonlinear time-varying dynamics of process and to enable the RVFLNs to learn online and to avoid data saturation, an improved online sequential version of RVFLNs (OS-RVFLNs) is presented by sequential learning with forgetting factor. It has been shown that the improved OS-RVFLNs with forgetting factor is not only suitable for the large-scale and real-time data transfer situation but also can adjust the sensitivity of the algorithm to different samples. Second, in order to solve the issue of modeling robustness when the dataset is contaminated with various outliers, a Cauchy distribution function weighted M-estimator is introduced to strengthen the robustness of the improved OS-RVFLNs. The non-Gaussian Cauchy distribution function is used to estimate the weights of different data and thus the corresponding contribution on modeling can be properly distinguished. Experiments using actual industrial data of a large BF ironmaking process have demonstrated that the proposed algorithm produces a much stronger robustness and better estimation accuracy than other algorithms.

Characteristics of streamflow in the main stream of Changjiang River and the impact of the Three Gorges Dam

Abstract: The assumption that natural system changes in a constant range runs through the practice of water resources application. However, under the changing environment, whether hydrological characteristics have changed is a crucial and important foundation for flood control and drought resistance. Based on daily water level, discharge, and precipitation for the last 100 or 60 years, this study analyzed the hydrological characteristics and their changes as results of the operation of the Three Gorges Dam (TGD) in the Changjiang (Yangtze) River. Results showed that the monthly precipitation did not significantly change for the longer period and the annual precipitation remained stationary during 1959–2018. However, the water level and discharge significantly increased during most months from January to March and significantly decreased from August to November. Yichang station, the nearest station to the TGD, changed the most, which annual runoff and water level series (1959–2018) showed obvious non-stationarity behavior. The same results were showed in period 1890–2018, while the process remained stationary for the period 1890–1970. 50.15% of the discharge at Yichang station decrease from June to November was attributed to water storage of the TGD and 57.57% of its increase during other months was attributed to recharge of the TGD. The TGD had a greater impact on the discharge, while the water level was affected by both the TGD and Gezhouba Dam. The trends of the water level and discharge were in perfect synchronization prior to 1980, but went out of sync in terms of a different direction or rate after 1980 given the operation of Gezhouba Dam. The non-stationarity behavior of discharge and water level and the change of their laws make it difficult to directly apply the relationship among precipitation-discharge-water level in the past, which brings great challenges to the planning and management of water resources.

Nonlinear Multiobjective MPC-Based Optimal Operation of a High Consistency Refining System in Papermaking

Abstract: As one of the most important unit in the papermaking industry, the high consistency (HC) refining system is confronted with challenges such as improving pulp quality, energy saving, and emissions reduction in its operation processes. In this correspondence, an optimal operation of HC refining system is presented using nonlinear multiobjective model predictive control strategies that aim at set-point tracking objective of pulp quality, economic objective, and specific energy (SE) consumption objective, respectively. First, a set of input and output data at different times are employed to construct the subprocess model of the state process model for the HC refining system, and then the Wiener-type model can be obtained through combining the mechanism model of Canadian Standard Freeness and the state process model that determines their structures based on Akaike information criterion. Second, the multiobjective optimization strategy that optimizes both the set-point tracking objective of pulp quality and SE consumption is proposed simultaneously, which uses NSGA-II approach to obtain the Pareto optimal set. Furthermore, targeting at the set-point tracking objective of pulp quality, economic objective, and SE consumption objective, the sequential quadratic programming method is utilized to produce the optimal predictive controllers. Finally, the simulation results demonstrate that the proposed methods can make the HC refining system provide a better performance of set-point tracking of pulp quality when these predictive controllers are employed. In addition, while the optimal predictive controllers orienting with comprehensive economic objective and SE consumption objective, it has been shown that they have significantly reduced the energy consumption.

Detecting Unfavorable Driving States in Electroencephalography Based on a PCA Sample Entropy Feature and Multiple Classification Algorithms.

Abstract: Unfavorable driving states can cause a large number of vehicle crashes and are significant factors in leading to traffic accidents. Hence, the aim of this research is to design a robust system to detect unfavorable driving states based on sample entropy feature analysis and multiple classification algorithms. Multi-channel Electroencephalography (EEG) signals are recorded from 16 participants while performing two types of driving tasks. For the purpose of selecting optimal feature sets for classification, principal component analysis (PCA) is adopted for reducing dimensionality of feature sets. Multiple classification algorithms, namely, K nearest neighbor (KNN), decision tree (DT), support vector machine (SVM) and logistic regression (LR) are employed to improve the accuracy of unfavorable driving state detection. We use 10-fold cross-validation to assess the performance of the proposed systems. It is found that the proposed detection system, based on PCA features and the cubic SVM classification algorithm, shows robustness as it obtains the highest accuracy of 97.81%, sensitivity of 96.93%, specificity of 98.73% and precision of 98.75%. Experimental results show that the system we designed can effectively monitor unfavorable driving states.

A Concealed Information Test System Based on Functional Brain Connectivity and Signal Entropy of Audio–Visual ERP

Abstract: Deception is a human behavior and its cognitive process and mechanism involve complex neuronal activities of the brain. In this article, we develop a simple and feasible concealed information test (CIT) method which is based on the audio–visual event-related potentials (ERPs) and its spatial and temporal features. The main purpose of this article is to extend a pattern recognition method with functional network parameters and global feature entropy of the EEG signals from the whole brain. At the same time, a novel quantum neural network (QNN) classifier was developed to distinguish the guilty and innocent conditions. Functional connectivity can provide extra information of interdependence between different brain regions from the spatial dimension, and entropy can reflect the complexity of the whole brain from the temporal dimension. 20 subjects participated in the CIT experiment and 30 channel ERPs were recorded. A high accuracy of 87.67% was got in recognizing the concealed information, which was higher than 85.43% for basic features, demonstrated the effectiveness of this article. Future studies should further clarify the connectivity difference and further improve the accuracy of the QNN classifier for CIT.